@ARTICLE{Jaya9109:Coding,
AUTHOR="Nuggehally S. Jayant and Victor B. Lawrence and Dimitrios P.
Prezas",
TITLE="Coding of Speech and Wideband Data",
JOURNAL=atttj,
VOLUME=69,
NUMBER=5,
PAGES="25-41",
MONTH="September/October",
YEAR=1991,
KEYWORDS="packet voice; speech coding",
ABSTRACT="Advances in coding algorithms and digital signal processing
have led to sophisticated technologies for speech communication for a
variety of applications, as well as to greater flexibilities in the
design of ISDN terminals for integrated communication of speech, images,
and data. For traditional telephony with a signal bandwidth of 3.2 kHz,
the transmission rate for network-quality speech is now down to 16 kb/s.
Robust communications-quality speech appropriate for cellular radio has
been realized at 8 kb/s. Research attention is shifting towards 4 kb/s,
focused on improved speaker identification and the naturalness of coded
speech. For wideband audio with a signal bandwith of 7 kHz, high-quality
coding is now possible at 32 kb/s, which implies stereo teleconferencing
or dual-language programming over a 64-kb/s channel. Transparent coding
of 20-kHz audio has been demonstrated at 128 kb/s, with near-transparent
performance at rates as low as 64 kb/s for some classes of signals.",
ANNOTE="Speech quality and delay considerations of waveform and
model-based speech coding algorithms from 2.4 kb/s (LPC) to 128 kb/s.",
}

@TECHREPORT{Ferr91:Buffer,
AUTHOR="D. Ferrari and Dinesh Verma",
TITLE="Buffer space allocation for real-time channels in a packet
switching network",
TYPE="Technical Report",
INSTITUTION="Computer Science Division, Department of Electrical
Engineering and Computer Sciences, University of California",
ADDRESS="Berkeley, California",
YEAR=1991,
KEYWORDS="real-time communications; Tenet; buffer allocation",
ABSTRACT="Broadband integrated networks will have to offer real-time
communication services; that is, they will have to transport information
with performance guarantees. A paper previously published by the authors
presented a scheme for establishing real-time channels in a pure
packet-switching network; that scheme did not include any method for
allocating buffer space in the network's nodes to the channels being
established. This paper completes the description and evaluation of that
scheme, since it presents one such method, and some of the results of
the extensive simulations performed to test it. The method is found to
be correct and to have a low overhead. While the utilization of the
buffer space allocated to the statistical channels is often quite low,
thereby indicating that our worst-case approach tends to overallocate
space to those channels, the space our method gives to deterministic
channels seems to be reasonably well utilized.",
}

@MISC{Moha91:Effect,
AUTHOR="B. P. Mohanty and Christos Cassandras",
TITLE="The Effect of Model Uncertainty on Optimal Routing",
YEAR=1991,
KEYWORDS="routing",
ANNOTE="optimal routing in a system of parallel queues with uncertain
system time distribution.",
}

@MISC{Ping91:Scheduling,
AUTHOR="Shridhar Pingali and James F. Kurose",
TITLE="On Scheduling Two Classes of Real Time Traffic with Identical
Deadlines",
YEAR=1991,
KEYWORDS="discrete time queue; packet video; minimum laxity",
ABSTRACT="The problem of scheduling two classes of real-time traffic
with correlated time constraints is considered. Three scheduling
disciplines are studied: a priority discipline which gives strict
priority to one class of traffic, a threshold-based scheme in which
priority is given to one class of traffic when the minimum laxity of its
queued packets falls below some threshold, and a ``balancing'' scheme
which assigns priority on the basis of the differences in minimum
laxities in the two classes of traffic. Analytic results are obtained by
using a discrete time model to obtain the state occupancy probabilities
for the system. Here, the state is defined using the laxities of the
queued real-time packets. Parameters are defined to study the tradeoff
in the performance of the two classes of traffic. Results are obtained
to demonstrate how the balancing scheme permits us to achieve
significant improvement in the performance of one class of traffic with
only minimal effect on the performance of the other class. A video
application is suggested for this work.",
URL="ftp://gaia.cs.umas.edu/pub/Ping91:Scheduling.ps.Z",
}

@UNPUBLISHED{Yee91:Convergence,
AUTHOR="James Yee and M. J. Lee",
TITLE="Convergence of an Iterative Method for {ATM} Networks",
NOTE="submitted to {\em IEEE Transactions on Information Theory}",
YEAR=1991,
ABSTRACT="In this paper, the authors present a flow model for evaluating
the performance of a network of ATM switches. The performance measures
used include the link and end-to-end cell loss probabilities as well as
the link (nodal) and end-to-end cell delays. In the model, the routing
assignments are assumed to be given. The assumed form of routing
assignments may be used to represent either virtual circuit or datagram
service. Due to the nonlinear relationship between cell losses and
offered flows, the flow model is a system of nonlinear equations. We
develop a sufficient condition for the existence of a unique solution to
the nonlinear system of equations. We present an iterative method and
prove that it converges to a unique fixed point provided the sufficient
condition is satisfied. The unique fixed point corresponds to the unique
solution of the flow model. We applied the iterative method to evaluate
the performance of a 61-node wide area ATM network. Four typical routing
strategies were compared with respect to the end-to-end delays and
throughputs. In this example, 99\% of the end-to-end delay was due to
the propagation delay.",
ANNOTE="Discrete-time queues.",
}

@ARTICLE{Kish9108:HDTV,
AUTHOR="R. Kishimoto and Ichiro Yamashita",
TITLE="{HDTV} communication Systems in Broadband Communication
Networks",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=8,
PAGES="28-35",
MONTH="Aug",
YEAR=1991,
KEYWORDS="HDTV communication systems; broadband communication networks;
packet video; subband coding; DPCM; DCT",
ABSTRACT="Society is rapidly moving into the information age. Demand is
growing for a high-quality telecommunication system that supports a wide
variety of services. High Definition Television (HDTV) is the coming
standard for the television of the future. HDTV will be one of the
market forces driving fiber optic cables into the home. Therefore, a
nationwide HDTV transmission and distribution network must be developed
in order to offer economical HDTV services to the customer.",
ANNOTE="120 Mb/s",
}

@ARTICLE{Nino9108:HDTV,
AUTHOR="Yuichi Ninomiya",
TITLE="{HDTV} Broadcasting Systems",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=8,
PAGES="15-22",
MONTH="Aug",
YEAR=1991,
KEYWORDS="HDTV broadcasting systems; high definition television; packet
video; MUSE; HD-MAC",
ABSTRACT="High definition television (HDTV) systems are now reaching the
stage of practical use. In Japan, daily HDTV broadcasting by the
Multiple Sub-Nyquist Sampling Encoding (MUSE) system has been going on
for more than two years on an experimental basis. This will be increased
to nearly full scale test broadcasting late this year, preceding the
start of a regular service. As regards software, many programs have
already been produced in the U.S., Europe, and Japan, a large number of
which have been presented at the Electronic Cinema Festival, which is
held almost every year and has a good reputation with audiences. Several
have been screened in theaters on a commercial basis.",
}

@MANUAL{Zilo91:Datacom,
AUTHOR="Zilog",
TITLE="Datacom {ICs}",
ORGANIZATION="Zilog",
ADDRESS="Campbell, California",
YEAR=1991,
}

@ARTICLE{Eckb9109:Controlling,
AUTHOR="A. E. Eckberg and B. T. Doshi and Richard Zoccolillo",
TITLE="Controlling Congestion in {B-ISDN/ATM:} Issues and Strategies",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=9,
PAGES="64-74",
MONTH="Sep",
YEAR=1991,
KEYWORDS="Congestion control; B-ISDN; ATM",
ABSTRACT="A layered and distributed congestion-control framework can
realize the high-level goals of simplicity, robustness, flexibility, and
controllability.",
}

@ARTICLE{Robe9109:Variable,
AUTHOR="J. W. Roberts",
TITLE="Variable-Bit-Rate Traffic Control in {B-ISDN}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=9,
PAGES="50-57",
MONTH="Sep",
YEAR=1991,
KEYWORDS="Variable-Bit-Rate Traffic Control; B-ISDN",
ABSTRACT="The three-way relationship between traffic descriptors,
admission control, and rate enforcement determine the kinds of traffic
control that can guarantee quality-of-service.",
ANNOTE="Traffic control. Distinguishes cell and burst component of
buffer saturation probability.",
}

@TECHREPORT{Cido91:Bandwidth,
AUTHOR="I. Cidon and I. Gopal and R. Guérin",
TITLE="Bandwidth management and congestion control in {plaNET}",
TYPE="Technical Report",
INSTITUTION="High Performance Computing and Communications Directorate,
IBM T. J. Watson Research Center",
ADDRESS="Yorktown Heights, New York",
YEAR=1991,
KEYWORDS="ATM; plaNET; leaky bucket; congestion control; admission
control",
ABSTRACT="In this paper we describe the algorithms, protocols and
concepts that make up the bandwidth management and congestion control in
the plaNET gigabit/second wide area network. Most of the concepts are
relatively general and can be applied to any high speed integrated
network, including ATM based systems. We will implement and
experimentally validate the ideas presented in this paper in several
test-beds and field trials planned over the course of the next year.",
}

@TECHREPORT{Ferr91:Guaranteeing,
AUTHOR="D. Ferrari and Dinesh Verma and Hui Zhang",
TITLE="Guaranteeing delay jitter bounds in packet-switching networks",
INSTITUTION="TENET Group, CS Division of the University of California
and the International Computer Sciences Institute",
ADDRESS="Berkeley, California",
PAGES="1-6",
YEAR=1991,
KEYWORDS="queueing theory; congestion control",
ANNOTE="Delay and jitter bounds for VCs by reconstructing input pattern
at each node. Contract specifies minimum and average spacing between
packets. Scheduler delays until delay bound at each node. Shows some
numerical results.",
}

@BOOK{Come91:Internetworking1,
AUTHOR="D. Comer and David L. Stevens",
TITLE="Internetworking with {TCP/IP}",
ISBN="0-13-468505-9",
PUBLISHER="Prentice Hall",
ADDRESS="Englewood Cliffs, New Jersey",
VOLUME=1,
YEAR=1991,
KEYWORDS="computer networks; TCP/IP; internet",
}

@BOOK{Wils91:Berkeley,
AUTHOR="James R. Wilson",
TITLE="Berkeley Unix -- A Simple and Comprehensive Guide",
ISBN="0-471-61582-X",
PUBLISHER="John Wiley and Sons",
ADDRESS="New York",
YEAR=1991,
KEYWORDS="Unix; operating systems",
}

@UNPUBLISHED{Gopa91:Transparency,
AUTHOR="I. Gopal and R. Guérin",
TITLE="Network transparency: the {plaNET} approach",
INSTITUTION="IBM T. J. Watson Research Center",
ADDRESS="Yorktown Heights, New York",
NOTE="unpublished memorandum",
YEAR=1991,
KEYWORDS="ATM; network architecture",
ABSTRACT="Asynchronous transfer mode (ATM) is being suggested as the
basis for future high speed, ``universal'' networks. Unfortunately, the
standardization process and the subsequent delay anticipated in
deployment make it likely that ATM will not be widely available till the
late 1990's. We argue in this paper that by this time a key requirement
for networks will be ``transparency,'' i.e., for the network to alter or
manipulate the user information as little as possible. A ``transparent''
tranport mechanism, plaNET, based on extensions of the current ATM
standard and IBM earlier PARIS technology, is proposed. It is shown that
plaNET can satisfy the ``universal'' transport requirement of ATM, while
avoiding some demonstrated deficiencies. In fact, it is claimed that
plaNET can be viewed as an enhanced version of ATM that may be more
suitable for the late 1990's than the current standard.",
ANNOTE="argues for use of variable-size packets; AURORA",
}

@INPROCEEDINGS{Wein91:Virtual,
AUTHOR="A. Weinrib and L. T. Wu",
TITLE="Virtual clocks and leaky buckets: flow control protocols for
high-speed networks",
BOOKTITLE="IFIP Working Group WG 6.1 and WG 6.4 Second International
Workshop on Protocols for High-Speed Networks",
EDITOR="Marjory Johnson",
ORGANIZATION="IFIP",
PAGES="3-15",
YEAR=1991,
KEYWORDS="flow control; leaky bucket; virtual clock; fairness",
ABSTRACT="We show that two protocols proposed for rate-based flow
control of broadband packet networks, the virtual clock and the leaky
bucket, are in a sense ``equivalent'' in that the equations that their
underlying state variables satisfy are closely related. The differences
between the two protocols arise from the use of the state information,
rather than from some fundamental difference in the state variables. We
then turn to a discussion of fairness in broadband networks, aruging
that both fairness in delay and packet dropping and fairness in
guaranteeing service are desirable. Neither of the two protocols fully
meets both requirements for fairness. Comparing the fairness-performance
of the two protocols, we suggest a modified protocol that appears to
better meet the fairness requirements.",
}

@BOOK{Holz91:Validation,
AUTHOR="Gerard J Holzmann",
TITLE="Design and Validation of Computer Protocols",
ISBN="0-13-539925-4",
PUBLISHER="Prentice Hall",
ADDRESS="Englewood Cliffs, New Jersey",
YEAR=1991,
KEYWORDS="protocol; protocol verification; checksum; survey; error
control; finite state machines; conformance testing; SPIN; PROMELA",
}

@BOOK{Stal91:Data,
AUTHOR="W. Stallings",
TITLE="Data and Computer Communications",
ISBN="0-02-415454-7",
PUBLISHER="Macmillan",
ADDRESS="New York, New York",
YEAR=1991,
ANNOTE="Computer networking --- tutorial.",
}

@ARTICLE{Sher9107:Les,
AUTHOR="M. H. Sherif and Marie-Pascale Bosse",
TITLE="Les paquets de bande élargie: une nouvelle technique de
transmission",
JOURNAL=atele,
VOLUME=46,
NUMBER="7--8",
PAGES="392-407",
MONTH="July--August",
YEAR=1991,
KEYWORDS="packet transmission; speech coding; differential PCM; ADPCM;
multimedia; packet voice",
ABSTRACT="The purpose of this article is to describe the principles and
applications of a new transmission technology for multimedia traffic
based on wideband packets. This integration allows more efficient
utilization of the network and reduces the operation and maintenance
costs. Next, we present AT\\&T's integrated access and crossconnect
system (IACS) as an example of an implementation of this technology.",
ANNOTE="Describes G.764 and G.727 in some detail.",
}

@ARTICLE{Camp9103:Federal,
AUTHOR="Andrew T Campbell and Thomas E. Tremain and Vanoy C. Welch",
TITLE="The Federal Standard 1016 4800 bps {CELP} Voice Coder",
JOURNAL="Digital Signal Processing",
VOLUME=1,
NUMBER=3,
PAGES="145-155",
YEAR=1991,
KEYWORDS="CELP; low-rate speech coding",
}

@INCOLLECTION{Camp91:DoD,
AUTHOR="Andrew T Campbell and Thomas E. Tremain and Vanoy C. Welch",
TITLE="The {DoD} 4.8 kbps Standard (Proposed Federal Standard 1016)",
BOOKTITLE="Advances in Speech Coding",
EDITOR="B. Atal and V. Cuperman and A. Gersho",
CHAPTER=12,
PUBLISHER="Kluwer Academic Publishers",
PAGES="121-133",
YEAR=1991,
KEYWORDS="CELP; low-rate speech coding",
}

@ARTICLE{Agne91:Global,
AUTHOR="Ralf Agne",
TITLE="Global Cyclic Scheduling: A Method to Guarantee the Timing
Behavior of Distributed Real-Time Systems",
JOURNAL="Journal of Real-Time Systems",
VOLUME=3,
PAGES="45-66",
YEAR=1991,
}

@INPROCEEDINGS{Agra91:Architectural,
AUTHOR="Gopal Agrawal and Baio Chen and W. Zhao and Sadegh Davari",
TITLE="Architectural Impact of {FDDI} Network on Scheduling Hard
Real-Time Traffic",
BOOKTITLE="Real-Time Systems Symposium",
ADDRESS="San Antonio, Texas",
PAGES="22-26",
YEAR=1991,
}

@INPROCEEDINGS{Aras91:Improving,
AUTHOR="Caglan M. Aras and Ren C. Luo and Douglas Reeves",
TITLE="Improving Hierarchical Architecture Performance with Dynamic
Segmentation",
BOOKTITLE="International Conference on Systems, Man and Cybernetics",
ADDRESS="Charlottesville, Virginia",
VOLUME=2,
PAGES="801-806",
YEAR=1991,
}

@ARTICLE{Arvi91:Local,
AUTHOR="K. Arvind and Krithivasan Ramamritham and John Stankovic",
TITLE="A Local Area Network Architecture for Communication in
Distributed Real-Time Systems",
JOURNAL="Journal of Real-Time Systems",
VOLUME=3,
PAGES="115-14",
YEAR=1991,
}

@TECHREPORT{Chen91:Multimedia,
AUTHOR="M.-S. Chen",
TITLE="A multimedia multiparty teleconference",
TYPE="Technical Note",
INSTITUTION="IBM T. J. Watson Research Center",
ADDRESS="Yorktown Heights, New York",
YEAR=1991,
KEYWORDS="multimedia; teleconferencing; shared whiteboard; multicast;
shared editor; CSCW",
ABSTRACT="MEET (multiple end-to-end teleconference) is envisioned as a
desktop hub-free (peer) personal teleconference system that allows
people to do ``face-to-face'' meetings without leaving their offices.
Using MEET, users see each other via real-time motion video, talk and
hear all the talks via real-time audio and present documents such as
foils via an on-line Electronic Blackboard (EB). MEET is currently being
designed and prototyped by the High Bandwidth Applications group at IBM
T. J. Watson Research Center, and will be installed in the PARIS fast
packet switched networks in the Aurora testbed. This article describes
the goals, specifications, and prototype of the project.",
ANNOTE="PS/2 Model 80; disable voices from particular sources; dynamic
connection-oriented multicast",
}

@BOOK{Dhas91:Broadband,
AUTHOR="C. R. Dhas and V. Konangi and M. Sreetharan",
TITLE="Broadband Switching: Architectures, Protocols, Design and
Analysis",
PUBLISHER="IEEE Computer Society Press",
ADDRESS="Los Alamitos, California",
YEAR=1991,
}

@INPROCEEDINGS{Du91:Mapping,
AUTHOR="D. Z. Du and Guy Vidal-Naquet",
TITLE="Mapping communicating task graphs onto reconfigurable
multiprocessor architectures",
BOOKTITLE="International Symposium on Computers and Information
Systems",
ADDRESS="Antalya, Turkey",
VOLUME=1,
YEAR=1991,
}

@INPROCEEDINGS{Kand91:Real,
AUTHOR="D. Kandlur and Kang G. Shin and D. Ferrari",
TITLE="Real-Time Communication in Multi-hop Networks",
BOOKTITLE="11th International Conference on Distributed Computing
Systems",
ADDRESS="Arlington, Texas",
PAGES="300-307",
YEAR=1991,
}

@INPROCEEDINGS{Kim91:Modeling,
AUTHOR="Jaehyung Kim and Ch. Das",
TITLE="Modeling Wormhole Routing in a Hypercube",
BOOKTITLE="1th Conference on Distributed Computing Systems",
ADDRESS="Arlington, Texas",
PAGES="386-393",
YEAR=1991,
}

@BOOK{Li91:Reconfigurable,
AUTHOR="Hungwen Li and Quentin F. Stout",
TITLE="Reconfigurable Massively Parallel Computers",
PUBLISHER="Prentice Hall",
ADDRESS="Englewood Cliffs, New Jersey",
YEAR=1991,
}

@INPROCEEDINGS{Lim91:Comparative,
AUTHOR="C. S. Lim and Li-jun Yao and W. Zhao",
TITLE="A Comparative Study of Three Token Ring Protocols for Real-Time
Communications",
BOOKTITLE="11th Conference on Distributed Computing Systems",
ADDRESS="Arlington, Texas",
PAGES="308-317",
YEAR=1991,
}

@INPROCEEDINGS{Luo91:MARGE,
AUTHOR="Ren C. Luo and Caglan M. Aras and Harsha Potlapalli and Min
Lin",
TITLE="{MARGE:} Mobile Autonomous Robot for Guidance Experiments",
BOOKTITLE="SME Conference on Manufacturing and Automation",
ADDRESS="Pittsburgh, Pennsylvania",
YEAR=1991,
}

@INPROCEEDINGS{Pamu91:Computational,
AUTHOR="Yahya Pamukcuoglu and Oguz Tosun",
TITLE="Computational Models for Task Response Time Optimization in
Real-Time Distributed Systems",
BOOKTITLE="International Symposium on Computers and Information
Systems",
ADDRESS="Antalya, Turkey",
YEAR=1991,
}

@INPROCEEDINGS{Reis91:Demo,
AUTHOR="B. D. Reister and John Jones and P. L. Butler and M. Beckerman
and F. J. Sweeney",
TITLE="Demo-89 The initial Experiment with the {Hermies-III} Robot",
BOOKTITLE="IEEE International Conference on Robotics and Automation",
ADDRESS="Sacremento, California",
VOLUME=3,
PAGES="2562-2567",
YEAR=1991,
}

@INPROCEEDINGS{Shuk91:Scheduling,
AUTHOR="Shridhar B. Shukla and D. P. Agrawal",
TITLE="Scheduling Pipelined Communication in Distributed Memory
Multiprocessors for Real-time Applications",
BOOKTITLE="18th International Symposium on Computer Architecture",
ADDRESS="Toronto, Canada",
PAGES="222-231",
YEAR=1991,
}

@INPROCEEDINGS{Sing91:Obstacle,
AUTHOR="S. Singh",
TITLE="Obstacle Detection for High Speed Autonomous Navigation",
BOOKTITLE="IEEE International Conference on Robotics and Automation",
ADDRESS="Sacramento, California",
VOLUME=3,
PAGES="2798-2805",
YEAR=1991,
}

@BOOK{Spra91:Telecommunications,
AUTHOR="J. D. Spragins and J. L. Hammond and Krzysztof Pawlikowski",
TITLE="Telecommunications: Protocols and Design",
PUBLISHER="Addison-Wesley",
ADDRESS="Reading, Massachusetts",
YEAR=1991,
}

@ARTICLE{Verh91:Static,
AUTHOR="J. P. C. Verhoosel and E. J. Luit and D. K. Hammer",
TITLE="A Static Scheduling Algorithm for Distributed Hard Real-Time
Systems",
JOURNAL="Journal of Real-Time Systems",
VOLUME=3,
PAGES="227-246",
YEAR=1991,
}

@BOOK{Tilb91:Foundations,
AUTHOR="Andre van Tilborg and Gary M. Koob",
TITLE="Foundations of Real-Time Computing: Scheduling and Resource
Management",
PUBLISHER="Kluwer Academic Publishers",
ADDRESS="Boston/Dordrecht/London",
YEAR=1991,
}

@ARTICLE{Youn91:Integrated,
AUTHOR="Young Sik Youn and Chong Kwan Un",
TITLE="Performance analysis of an integrated voice/data cut-through
switching network",
JOURNAL=cnis,
VOLUME=21,
PAGES="41-51",
YEAR=1991,
KEYWORDS="packet voice; cut-through switching; integrated services",
ABSTRACT="In this paper, the performance of an integrated voice/data
cut-through switching network is studied. We first derive cut-through
probabilities of voice and data packets at intermediate nodes. Then, the
Laplace transform for the network delay is obtained. According to our
numerical results, the cut-through switching method is superior in its
delay characteristics to the conventional packet switching for voice and
data in integrated voice/data networks.",
}

@ARTICLE{Ngoh91:Multicast,
AUTHOR="L. H. Ngoh",
TITLE="Multicast support for group communications",
JOURNAL=cnis,
VOLUME=22,
PAGES="165-178",
YEAR=1991,
KEYWORDS="multicast; group communications; multimedia",
ABSTRACT="This paper describes a multicast model which can be integrated
into existing unicast communication systems to provide better support
for group communications. Multicast services are becoming more
important, as more and more of today's network workstation environments
are used to provide group communication for the exchange of multimedia
information. These environments allow users to exchange information in
the form of 'documents' containing text, graphics and voice; some
systems support both store-and-forward (e.g., mail) and real-time (e.g.,
conferencing) material. In this paper, various multicast design issues
are addressed and solutions are proposed to provide an effective
multicast extension for a wide range of existing unicast protocols.",
}

@ARTICLE{Wils91:Computer,
AUTHOR="Paul Wilson",
TITLE="Computer supported cooperative work {(CSCW):} origins, concepts
and research initiatives",
JOURNAL=cnis,
VOLUME=23,
PAGES="91-95",
YEAR=1991,
KEYWORDS="computer supported cooperative work; CSCW; groupware;
multimedia; collaboratory; research networks; requirements",
ABSTRACT="Computer Supported Cooperative Work (CSCW) aims to improve the
effectiveness of teams of all sizes - from 2 people up to whole
organizations. CSCW has two main components: Underlying Technologies
(communication systems, shared work space facilities, shared information
facilities, and group activity support facilities); and Group Process
Issues (individual aspects, organizational aspects, group work design
aspects, group dynamics aspects). CSCW systems will require networks to
transport voice and video material, to provide services to enable groups
to establish themselves and conduct their work, and to do all this with
outstanding levels of usability. The concept of a Collaboratory - a
research centre without walls - is outlined and its applicability in
Europe is discussed.",
}

@BOOK{Unic91:Unicode,
AUTHOR="The Salutation Consortium",
TITLE="The Unicode Standard",
PUBLISHER="Addison-Wesley",
ADDRESS="New York, New York",
YEAR=1991,
KEYWORDS="unicode; character set",
}

@ARTICLE{Lahe9103:Fortran,
AUTHOR="Thomas M. Lahey",
TITLE="Fortran 90 is coming!",
JOURNAL="Programmer's Journal",
MONTH="March/April",
YEAR=1991,
KEYWORDS="Fortran; computer languages",
}

@BOOK{Inmo91:T9000,
AUTHOR="Inmos",
TITLE="The {T9000} transputer: products overview manual",
PUBLISHER="SGS-Thomson",
ADDRESS="Bristol, United Kingdom",
YEAR=1991,
KEYWORDS="transputer; computer architecture",
}

@INCOLLECTION{Cohe91:Multidimensional,
AUTHOR="Michael Cohen and L. F. Ludwig",
TITLE="Multidimensional audio window management",
BOOKTITLE="Computer-supported cooperative work and groupware",
EDITOR="Saul Greenberg",
CHAPTER=10,
SERIES="Computers and People Series",
PUBLISHER="Harcourt Bruce Jovanovich",
ADDRESS="London",
PAGES="193-210",
YEAR=1991,
KEYWORDS="audio; teleconferencing; user interface; sound localization",
ABSTRACT="This paper proposes an organization of presentation and
control that implements a flexible audio management system we call
``audio windows''. The result is a new user interface integrating an
enhanced spatial sound presentation system, an audio emphasis system,
and a gestural input recognition system. We have implemented these ideas
in a modest prototype, also described, designed as an audio server
appropriate for a teleconferencing system. Our system combines a
gestural front end (currently based on a DataGlove, but whose concepts
are appropriate for other devices as well) with an enhanced spatial
sound system, a digital signal processing separation of multiple sound
sources, augmented with ``filtears'', audio feedback cues that convey
added information without distraction or loss of intelligibility. Our
prototype employs a manual front end (requiring no keyboard or mouse)
driving an auditory back end (requiring no CRT or visual display).",
ANNOTE="teleconference applications: source separation, moving between
conversations, high-lighting of sources, muffling of selected sources",
}

@UNPUBLISHED{Klei91:Writing,
AUTHOR="S. Kleiman and Bart Smaalders and D. Stein and D. Shah",
TITLE="Writing multithreaded code in Solaris",
NOTE="Sun Microsystems",
YEAR=1991,
KEYWORDS="multithreading; threads; operating systems; RPC; Solaris;
SunOS",
ABSTRACT="SunOS 5.0 is the operating system component of Solaris 2.0.
SunOS 5.0 contains the kernel support for multiple threads of control in
a single process address space. This allows a single application to
efficiently overlap I/O operations and to take advantage of more than
one processor, if available. We describe some of the issues in using and
converting libraries to the multithreaded environment. In addition, we
give several examples of different uses of threads in user
applications.",
}

@INPROCEEDINGS{Powe91:SunOS,
AUTHOR="Mike L. Powell and S. Kleiman and S. Barton and D. Shah and D.
Stein and M. Weeks",
TITLE="{SunOS} 5.0 multithreaded architecture",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
YEAR=1991,
KEYWORDS="multithreading; operating systems; threads; SunOS; Solaris",
ABSTRACT="This paper describes a model for multiple threads of control
within a single process. The main goals are to provide extremely
lightweight threads and to rationalize and extend the UNIX application
programming interface for a multithreaded environment. The threads are
intended to be sufficiently lightweight so that there can be thousands
present and that synchronization and context switching can be
accomplished rapidly without entering the kernel. These goals are
achieved by providing lightweight user-level threads that are
multiplexed on top of kernel-supported threads of control. This
architecture allows the programmer to separate logical (program)
concurrency from the required real concurrency, which is relatively
costly, and to control both within a single programming model.",
}

@TECHREPORT{Cido91:Critique,
AUTHOR="I. Cidon and Jeffrey H. Derby and I. Gopal and Bharath K.
Kadaba",
TITLE="A critique of {ATM} from a data communications perspective",
INSTITUTION="IBM T. J. Watson Research Center",
ADDRESS="Yorktown Heights, New York",
YEAR=1991,
KEYWORDS="ATM; PTM; fast packet switching; gigabit networks; data",
ABSTRACT="Fast packet switching is emerging as the preferred technology
for future high speed, integrated networks. Asynchronous transfer mode
(ATM) is an approach to FPS that is in the process of standardization
and is the preferred approach of the carrier community. Concurrently,
alternative approaches to FPS based on variable sized packets have been
proposed by segments of the data communications industry. These
approaches include frame relay and an approach developed by IBM called
PARIS. The purpose of this paper is to examine the suitability of ATM
for data communications relative to some of these alternative
approaches. By using LAN traffic data, we show that the fixed length
packets in ATM can result in significantly worse transmission efficiency
over variable size in many real traffic scenarios. In addition, we
demonstrate that considerably more processing power is needed to handle
segmentation and reassembly for ATM and that statistical multiplexing
also present some unique problems. Also, we present some qualitative
arguments to show that the label swapping approach for routing in ATM is
more complex to implement, potentially slower in processing call setup
and less capable of supporting datagrams when compared to the source
routing technique.",
}

@BOOK{Rose91:Simple,
AUTHOR="Marshall T. Rose",
TITLE="The Simple Book",
ISBN="0-13-812611-9",
PUBLISHER="Prentice-Hall",
ADDRESS="Englewood Cliffs, New Jersey",
YEAR=1991,
KEYWORDS="SNMP; network management; TCP/IP",
}

@BOOK{Rose91:Little,
AUTHOR="Marshall T. Rose",
TITLE="The Little Black Book: Mail-Bonding with {OSI} Directory
Services",
PUBLISHER="Prentice-Hall",
ADDRESS="Englewood Cliffs, New Jersey",
YEAR=1991,
KEYWORDS="X.500; X.400; electronic mail; OSI",
}

@MASTERSTHESIS{Reid91:Electropolis,
AUTHOR="Elizabeth M. Reid",
TITLE="Electropolis: communication and community on internet relay
chat",
SCHOOL="University of Melbourne, Department of History",
ADDRESS="Melbourne, Australia",
NOTE="Honours Thesis",
YEAR=1991,
KEYWORDS="Internet; IRC; internet relay chat; social implications;
electronic communities; virtual reality; computer-mediated
communication",
URL="ftp://parcftp.xerox.com/pub/MOO/papers/electropolis.ps",
}

@ARTICLE{Rich91:Building,
AUTHOR="R. F. Richardson",
TITLE="Building and managing an integrated support environment",
JOURNAL="Hewlett-Packard Journal",
PUBLISHER="Hewlett-Packard Company",
ADDRESS="Palo Alto, California",
VOLUME=42,
NUMBER=2,
PAGES="90-96",
YEAR=1991,
}

@ARTICLE{Dudi91:Optimising,
AUTHOR="A. N. Dudin and V. I. Klimenok",
TITLE="Optimising the Dynamic Control of Traffic in a Node of a Computer
Network",
JOURNAL="Avtomatika I Vychislitelnaya Tekhnika (Automation and remote
control)",
PUBLISHER="Instrument Society of America",
VOLUME=2,
PAGES="25-31",
YEAR=1991,
}

@ARTICLE{Mukh91:Open,
AUTHOR="B. Mukherjee",
TITLE="The Open-Ring Active Bus Network Structure - Access Techniques
and their Heavy Traffic Performance",
JOURNAL=ieeecom,
PUBLISHER="IEEE",
VOLUME=39,
NUMBER=4,
PAGES="474-477",
YEAR=1991,
}

@ARTICLE{Chem91:Supporting,
AUTHOR="Prosper Chemouil and J. Filipiak",
TITLE="Supporting Network Management with Real-Time Traffic Models",
JOURNAL=ieeejsac,
PUBLISHER="IEEE",
VOLUME=9,
NUMBER=2,
PAGES="151-156",
YEAR=1991,
}

@ARTICLE{Cahn9107:Intrepid,
AUTHOR="Robert S. Cahn and P. Y. Chang and Parviz Kermani and A.
Kershenbaum",
TITLE="Intrepid: An Integrated Network Tool for Routing, Evaluation of
Performance, and Interactive Design",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=7,
PAGES="40-47",
MONTH="Jul",
YEAR=1991,
KEYWORDS="Intrepid; Integrated Network Tool",
ABSTRACT="The network design problem, and in particular the environment
in which network design is currently being done, is becoming more
complex. A number of promising approaches to solving parts of this
problem have been described in the literature. Networking products
continue to emerge as do new tariff offerings. The designer is thus
confronted by an often bewildering variety of design alternatives,
including radically different network architectures. In the case of some
of the recently announced new tariffs such as Software Defined Networks
(SDNs), these architectures may include measured services in addition to
leased facilities. Hybrid architectures, including multiple
vendors'-products and tariffed offerings, are also possible.",
}

@ARTICLE{Crin91:Implementation,
AUTHOR="J. K. Cringen and R. England and G. A. Manson P. Willett",
TITLE="Network Design for the implementation of text searching using a
multicomputer",
JOURNAL="Information Processing and Management",
PUBLISHER="Pergamon Press",
VOLUME=27,
NUMBER=4,
PAGES="265-283",
YEAR=1991,
}

@ARTICLE{Dand91:Hybercube,
AUTHOR="S. Dandamudi and D. L. Eager",
TITLE="On Hybercube based heirarchical interconnection network design",
JOURNAL=jpdc,
VOLUME=12,
NUMBER=3,
PAGES="283-289",
YEAR=1991,
}

@ARTICLE{Shar91:Application,
AUTHOR="U. Sharma and K. B. Misra and A. K. Bhattacharji",
TITLE="Application of an efficient search technique for optimal design
of a computer communcations network",
JOURNAL="Microelectronics and Reliability",
PUBLISHER="Pergamon Press",
ADDRESS="Oxford, UK",
VOLUME=31,
NUMBER="2-3",
PAGES="337-341",
YEAR=1991,
}

@ARTICLE{Seng91:Synthesis,
AUTHOR="A. Sengupta and P. D. Joshi and S. Bandyopadhyay",
TITLE="A synthesis approach to design optimally fault tolerant network",
JOURNAL=ieeetc,
PUBLISHER="IEEE",
VOLUME=40,
NUMBER=1,
PAGES="94-100",
YEAR=1991,
}

@ARTICLE{Jone91:Protocol,
AUTHOR="M. Jones and S. A. Sorenson and S. R. Wilbur",
TITLE="Protocol Design for Large Group Mulicasting - The Message
Distribution Protocol",
JOURNAL=comcom,
VOLUME=14,
NUMBER=5,
PAGES="287-297",
YEAR=1991,
}

@ARTICLE{Kaku91:Integrated,
AUTHOR="Y. Kakuda and H. Saito",
TITLE="An Integrated Approach To Design of Protocol Specifications Using
Protocol Validation and Synthesis",
JOURNAL=ieeetc,
PUBLISHER="IEEE",
VOLUME=40,
NUMBER=4,
PAGES="459-467",
YEAR=1991,
}

@ARTICLE{Huan91:Computer,
AUTHOR="Chia-chi Huang and Y.-C. Chang and Minkui Liu",
TITLE="A Computer-Aided Protocol Design by Production Systems Approach",
JOURNAL=ieeejsac,
PUBLISHER="IEEE",
VOLUME=8,
NUMBER=9,
PAGES="1748-1762",
YEAR=1991,
}

@ARTICLE{Thei91:Buffered,
AUTHOR="T. H. Theimer and Erwin P. Rathgeb and M. Huber",
TITLE="Performance Analysis of Buffered Banyan Networks",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=2,
PAGES="269-277",
YEAR=1991,
REFERENCES=23,
KEYWORDS="ATM; interconnection network; simulation; analysis; Banyan",
}

@ARTICLE{Sing91:Basic,
AUTHOR="M. Singhal",
TITLE="Performance analysis of the basic timestamp ordering algorithm
via Markov modelling",
JOURNAL=pe,
PUBLISHER="North Holland",
VOLUME=12,
NUMBER=1,
PAGES="17-41",
YEAR=1991,
REFERENCES=36,
KEYWORDS="Database; time stamp; queueing network; concurrency",
ANNOTE="We analyze a single transaction in isolation rather than
analyzing the whole system. We reflect the presence of other tr. by the
prob. that a conflicting access to the data object has been made.
Comparison with simulations.",
}

@ARTICLE{Stan91:Interdeparture,
AUTHOR="D. A. Stanford",
TITLE="Interdeparture-time distributions in the non-preemptive priority
sum Mi/Gi/1 queue",
JOURNAL=pe,
PUBLISHER="North Holland",
VOLUME=12,
NUMBER=1,
PAGES="43-60",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Queueing system; nonpreemptive priority; M/G/1; output",
ANNOTE="This paper provides exact results for the Laplace-Stieltjes
transform of the interdeparture time distribution for each class in the
non-preemptive priority M/G/1 queue where each priority class is allowed
to have its own generally distributed service time characteristics.
Exact formulas of the squared coefficient of variation of the
interdeparture time are also provided, and are illustrated through
several examples.",
}

@TECHREPORT{Neum91:Proxy,
AUTHOR="B. Clifford Neuman",
TITLE="Proxy-Based Authorization and Accounting for Distributed
Systems",
INSTITUTION="Dept. of Computer Science, University of Washington",
YEAR=1991,
}

@ARTICLE{Berg91:Simple,
AUTHOR="Ted Bergstrom and Jeffrey MacKie-Mason",
TITLE="Some Simple Analytics of Peak-Load Pricing",
JOURNAL="Rand Journal of Economics",
VOLUME=22,
MONTH="Summer",
YEAR=1991,
}

@BOOK{Pryc91:Asynchronous,
AUTHOR="M. de Prycker",
TITLE="Asynchronous Transfer Mode: Solution for {ISDN}",
ISBN="0-13-053513-3",
PUBLISHER="Ellis Horwood",
ADDRESS="New York",
YEAR=1991,
KEYWORDS="book; ATM; BISDN",
}

@PHDTHESIS{Labo91:Rearrangeability,
AUTHOR="Jean-Francois Labourdette",
TITLE="Rearrangeability Techniques for Multihop Lightwave Networks and
Applications to Distributed {ATM} Switching Systems",
SCHOOL="Columbia University, Center for Telecommunications Research",
ADDRESS="New York, New York",
YEAR=1991,
KEYWORDS="network; lightwave; ATM; switching; reconfiguration",
ABSTRACT="Its huge bandwidth potential has established single mode fiber
as the transmission medium of choice for distributed communication
systems. However, in order to exploit the optical bandwidth, network
architectures must be designed that overcome the electro-optic
bottleneck, i.e., the mismatch that results from the peak transmission
rate of electronics utilizing only a tiny fraction of the enormous
bandwidth available in the fiber. The multihop architecture uses {\it
wavelength division multiplexing} to provide concurrency in the network
and thus access a large portion of the optical bandwidth. With this
approach, some small number of transmitters and receivers are allocated
to each network station. By assigning transmit and receive wavelengths
to the stations, high-speed channels are created and multiplexed onto
the medium, thereby creating a {\it logical connection diagram} among
stations. Since every two stations will not be directly connected, some
of the traffic may have to hop through intermediate stations to reach
its destination. This thesis expands upon the multihop architecture and
considers the use of slowly tunable lasers and optical filters. Such
devices provide the capability to logically reconfigure the connection
diagram, independently of the fiber infrastructure, by retuning the
transmitters and receivers at each station. This offers the ability to
optimize the network with respect to changing nonuniform traffic
conditions, and to cope with failure/recovery/addition of network
stations. This work evaluates the traffic performance of distributed
lightwave networks based on the reconfigurable multihop architecture. A
heuristic algorithm is developed that seeks the logical connection
diagram and routing which maximize the network throughput under
nonuniform traffic conditions. An original application is proposed in
the form of a highly modular distributed ATM switching system, where the
connection diagram may change each time a newly offered call cannot be
accommodated on the current configuration. Results to be presented show
how rearrangeability techniques can exploit traffic nonuniformities so
that the distributed switch achieves maximum traffic-handling
performance. Finally, a minimally disruptive approach is analyzed that
takes a network from its current connection diagram to a target diagram
through a sequence of intermediate diagrams.",
}

@INCOLLECTION{Bonf91:Conference,
AUTHOR="A. Bonfiglio and G. Malatesta and Francesco Tisato",
TITLE="Conference Toolkit: a framework for real-time conferencing",
BOOKTITLE="Studies in computer supported cooperative work",
EDITOR="J. M. Bowers and Steve David Benford",
SERIES="Human Factors in Information Technology",
PUBLISHER="North-Holland",
ADDRESS="Amsterdam",
PAGES="63-77",
YEAR=1991,
REFERENCES=12,
KEYWORDS="CSCW; toolkit; computer supported cooperative work; X; shared
applications",
ABSTRACT="This paper introduces Conference Toolkit, a system layer
supporting multimedia, real-time cooperation among users via shared
applications. Conference Toolkit allows both to integrate standard
applications in a conference environment and to develop ``conference
aware'' applications. It is based on a concurrent object-oriented
scheme. Conference Desk, a prototype based on the Conference Toolkit
model, is described.",
}

@INCOLLECTION{Gale91:Adding,
AUTHOR="Stephen Gale",
TITLE="Adding audio and video to an office environment",
BOOKTITLE="Studies in computer supported cooperative work",
EDITOR="J. M. Bowers and Steve David Benford",
SERIES="Human Factors in Information Technology",
PUBLISHER="North-Holland",
ADDRESS="Amsterdam",
PAGES="49-62",
YEAR=1991,
REFERENCES=14,
KEYWORDS="CSCW; audio; video; office automation",
ABSTRACT="The aim of the VISION project was to determine the value added
to an office system by incorporating audio and video communication. The
performance, feelings, and perceptions of work groups were measured
while they carried out cooperative tasks in a controlled environment
using an experimental multimedia communication system. The results
showed no significant differences in the quality of the output, or the
time taken to complete the tasks, under three conditions: data sharing;
data sharing plus audio; data sharing plus audio and video. The results
suggest that high bandwidth communication is particularly effective for
social, informal, communication.",
}

@BOOK{Jain91:Art,
AUTHOR="Raj Jain",
TITLE="The art of computer systems performance analysis: techniques for
experimental design, measurement, simulation, and modeling",
ISBN="0-471-50336-3",
PUBLISHER="John Wiley",
ADDRESS="New York",
YEAR=1991,
KEYWORDS="simulation; performance evaluation; statistics",
}

@INCOLLECTION{Prin91:Relevance,
AUTHOR="Wolfgang Prinz and Paola Pennelli",
TITLE="Relevance of the {X.500} directory to {CSCW} applications",
BOOKTITLE="Studies in computer supported cooperative work",
EDITOR="J. M. Bowers and Steve David Benford",
SERIES="Human Factors in Information Technology",
PUBLISHER="North-Holland",
ADDRESS="Amsterdam",
PAGES="267-283",
YEAR=1991,
REFERENCES=19,
KEYWORDS="CSCW; X.500; directory service",
ABSTRACT="In 1988 the standardization bodies ISO and CCITT released the
first international standard of a distributed directory service. The
purpose of the directory as it is described by the standard is to supply
a global nameserver and an application independent management and
information service. But these applications are not exhausting the
possibilities of a directory usage. It is the intention of this paper to
present the possibilities and chances the directory offers to
applications in the CSCW area. Our investigation focuses on CSCW models
and applications that support and coordinate communications in groups.
First the paper identifies and analyzes components which most of these
applications have in common. For the analysis we introduce the
classification of activity oriented models and conversation oriented
models. Then, after a brief introduction into the X.500 directory
service, it is shown in which way the identified components can be
represented by the directory service. The paper concludes with a
discussion of desirable improvements on the directory service.",
}

@INCOLLECTION{Smit91:Preliminary,
AUTHOR="Randall B. Smith and Tim O'Shea and Tim O'Malley and Eileen
Scanlon and J. Taylor",
TITLE="Preliminary experiments with a distributed, multimedia, problem
solving environment",
BOOKTITLE="Studies in computer supported cooperative work",
EDITOR="J. M. Bowers and Steve David Benford",
SERIES="Human Factors in Information Technology",
PUBLISHER="North-Holland",
ADDRESS="Amsterdam",
PAGES="31-48",
YEAR=1991,
REFERENCES=20,
KEYWORDS="CSCW; computer-supported cooperative work; user behavior;
video",
ABSTRACT="We report on studies of pairs of subjects using a system
called SharedARK (for ``Shared Alternate Reality Kit''). In SharedARK,
users at separate workstations interact in real time with the same world
of simulated physical objects. In the experiments, two users are in
separate rooms with a workstation each, and communicate through a high
fidelity, hands-free audio and a camera-monitor device called a ``video
tunnel'' which enables eye contact. For comparison, we have removed the
video tunnel for some subjects, giving them only a workstation each.
Within SharedARK, subjects are given a ``microworld'' within which to
solve a problem in everyday physics. Subjects are videotaped, and
monitored from a remote room. The protocols have been submitted to a
preliminary analysis, in which we categorise activities as they relate
to use of the interface, task performance and social interaction. We
also catalogue eye glances and eye contact in terms of their relation to
these activities. Our primary purpose has been to assess the
learnability and usability of this technology, and to identify factors
that are important in facilitating collaborative problem solving by
directly comparing remote, electronically mediated communication with
physical co-presence. We find the system is easily learned and fairly
easily used. Subjects normally find the task engaging, and usually work
together through largely unarticulated task division to obtain at least
a partial understanding of the solution space. Our observations have led
us to to the hypothesis that this technology can bring subjects in some
ways closer together than if they were to engage in a similar task in
the real world. We present evidence suggesting that this artificially
enhanced proximity may play a positive role in supporting non-interface
specific discourse and task division negotiation.",
}

@ARTICLE{Anon91:Changes,
AUTHOR="A. C. M",
TITLE="Introduction and changes to the Computing Reviews {(CR)}
classification scheme",
JOURNAL=acmcr,
VOLUME=32,
NUMBER=1,
PAGES="7-50",
YEAR=1991,
KEYWORDS="Classification; bibliography",
ANNOTE="Update of the 1982 classification scheme.",
}

@ARTICLE{Bala91:Parallel,
AUTHOR="E. Balas and D. Miller and J. Pekny and P. Toth",
TITLE="A parallel shortest augmenting path algoritm for the assignment
problem",
JOURNAL=jacm,
VOLUME=38,
NUMBER=4,
PAGES="985-1004",
YEAR=1991,
REFERENCES=28,
KEYWORDS="Routing; shortest path; parallel computing; speedup",
ANNOTE="A parallel version of the shortest augmenting path algorithm for
the assignment problem is described.",
}

@TECHREPORT{Thom91:Parallel,
AUTHOR="Graham Thomas and J. L. Zahorjan",
TITLE="Parallel simulation of performance Petri nets: extending the
domain of parallel simulation",
INSTITUTION="University of Washington, Dept. of Computer Science and
Engineering Technology",
ADDRESS="Washington",
NUMBER="91-04-02",
PAGES=19,
YEAR=1991,
REFERENCES=23,
KEYWORDS="Distributed simulation; SPN; stochastic Petri net; speedup",
ABSTRACT="We present a parallel simulation protocol for performance
Petri nets \ldots",
}

@ARTICLE{Mayr91:Testing,
AUTHOR="A. von Mayrhauser",
TITLE="Testing and evolutionary development",
JOURNAL=sigsoft,
VOLUME=16,
NUMBER=4,
PAGES="31-36",
YEAR=1991,
REFERENCES=8,
KEYWORDS="Test; software; validation; regression analysis",
}

@TECHREPORT{Katz91:Modeling,
AUTHOR="I. Katz",
TITLE="Modeling and Simulation of Medium-Access-Protocols in Local Area
Networks",
INSTITUTION="Virginia Polytechnic Institute and State University",
PAGES="6-15",
YEAR=1991,
REFERENCES=5,
KEYWORDS="Modeling; simulation; access protocol; LAN; CSMA/CD",
ANNOTE="The paper focusses on two general classes of protocols: CSMA/CD
and CSMA/CA. Two variations of each class are examined, and comparisons
are made between the classes and the variants of each class.",
}

@ARTICLE{Evan91:Optimal,
AUTHOR="Steve Evans",
TITLE="Optimal bandwidth management and capacity provision in a
broadband network using virtual paths",
JOURNAL=pe,
VOLUME=13,
NUMBER=1,
PAGES="27-43",
YEAR=1991,
REFERENCES=12,
KEYWORDS="ATM; resource allocation",
ANNOTE="This article describes a mathematical model for a BISDN using
virtual paths. It looks at performance measures relating to revenue and
GOS, and gives simple asymptotic formulae for evaluating the performance
function\ldots",
}

@ARTICLE{Cunn91:Delay,
AUTHOR="G. Cunningham",
TITLE="Delay versus throughput comparisons for stabilizet slotted
{ALOHA}",
JOURNAL=ieeecom,
VOLUME=38,
NUMBER=11,
PAGES="1932-1934",
YEAR=1991,
KEYWORDS="ALOHA; performance evaluation; throughput analysis; delay
analysis",
ANNOTE="Methods to stabilize the slotted ALOHA channel are simulated to
compare delay versus throughput performance. It is shown that the best
performance is provided by methods that use deferred first transmission
and estimate the number of blocked terminals. Three such methods,
previously thought to be independent, are shown to be the same scheme
with different control parameters. It is shown that these three methods
do not differ in delay versus",
}

@ARTICLE{Bals91:Closed,
AUTHOR="Simonetta Balsamo and V. De Nitto-Persone",
TITLE="Closed queueing networks with finite capacities: blocking types,
product-form solution and performance indices",
JOURNAL=pe,
VOLUME=12,
NUMBER=2,
PAGES="85-102",
YEAR=1991,
REFERENCES=30,
KEYWORDS="Closed queueing network; blocking; finite buffer; product
form; performance evaluation",
}

@ARTICLE{Mukh91:Dual,
AUTHOR="B. Mukherjee",
TITLE="Performance of a dual-bus fiber optic network operating under a
probabilistic scheduling strategy",
JOURNAL=pe,
VOLUME=12,
NUMBER=2,
PAGES="127-139",
YEAR=1991,
REFERENCES=20,
KEYWORDS="LAN; WAN; DQDB; performance evaluation; fiber optics",
}

@ARTICLE{Glyn91:Parallel,
AUTHOR="P. W. Glynn and P. Heidelberger",
TITLE="Analysis of parallel replicated simulations under a completion
time constraint",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=1,
PAGES="3-23",
YEAR=1991,
REFERENCES=39,
KEYWORDS="Distributed simulation; output analysis",
}

@ARTICLE{Nico91:Bounds,
AUTHOR="D. M. Nicol",
TITLE="Performance bounds on parallel self-initiating discrete-event
simulations",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=1,
PAGES="24-50",
YEAR=1991,
REFERENCES=25,
KEYWORDS="Distributed simulation; speedup; upper bound",
}

@ARTICLE{Lin91:Study,
AUTHOR="Y. Lin and E. D. Lazowska",
TITLE="A study of time warp rollback mechanisms",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=1,
PAGES="51-72",
YEAR=1991,
REFERENCES=35,
KEYWORDS="Distributed simulation; time warp; rollback",
ANNOTE={The rollback mechanisms "aggressive cancellation" and "lazy
cancellation" are studied.},
}

@TECHREPORT{Anag91:Overview,
AUTHOR="Miltos Anagnostou and E. Protonotarios",
TITLE="An overview of congestion control architecures and mechanisms for
{ATM} networks",
INSTITUTION="National Tech. University of Athens",
ADDRESS="Athens",
PAGES=11,
YEAR=1991,
REFERENCES=25,
KEYWORDS="ATM; congestion control; connection admission control; flow
control; survey",
ANNOTE="Good overview, no derivations.",
}

@ARTICLE{Bamb91:Stability,
AUTHOR="N. Bambos and J. Walrand",
TITLE="On stability and performance of parallel processing systems",
JOURNAL=jacm,
VOLUME=38,
NUMBER=2,
PAGES="429-452",
YEAR=1991,
REFERENCES=12,
KEYWORDS="Parallel computing; performance evaluation; queueing network",
ANNOTE="Very general model assumptions, G/G/1 and G/G/oo being marginal
cases.",
}

@ARTICLE{Abey91:High,
AUTHOR="Bandula W. Abeysundara and A. E. Kamal",
TITLE="High-speed local area networks and their performance: a survey",
JOURNAL=acmcs,
VOLUME=23,
NUMBER=2,
PAGES="221-264",
YEAR=1991,
REFERENCES=122,
KEYWORDS="HSLAN; survey; performance evaluation",
ANNOTE="This paper introduces LANs and discusses the performance
degradation of LANs at high speeds. It surveys recently proposed LAN
schemes designed to operate at high data rates, including their
performances characteristics.",
}

@ARTICLE{Anag91:Quality,
AUTHOR="Miltos Anagnostou and M. E. Theologou and K. M. Vlakos and et
al",
TITLE="Quality of Service Requirements in {ATM-based} {BISDNs}",
JOURNAL=comcom,
VOLUME=14,
NUMBER=4,
PAGES="197-204",
YEAR=1991,
REFERENCES=22,
KEYWORDS="ATM; BISDN; QOS; multiplexing",
}

@ARTICLE{Barr91:Switching,
AUTHOR="Peter Barri and J. A. O. Goubert",
TITLE="Implementation of a 16 to 16 Switching Element for {ATM}
Exchanges",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=5,
PAGES="751-757",
YEAR=1991,
REFERENCES=11,
KEYWORDS="ATM; switching block; architecture; implementation; central
buffer",
}

@ARTICLE{Blon91:Finite,
AUTHOR="C. Blondia",
TITLE="Finite Capacity Vacation Models with Non-renewal Input",
JOURNAL=jap,
VOLUME=28,
NUMBER=1,
PAGES="174-197",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Vacation system; performance evaluation; analysis; Markov
chain; matrix geometric method",
}

@ARTICLE{Haye91:Multicast,
AUTHOR="J. F. Hayes and R. Breault and M. Mehmet-Ali",
TITLE="Performance Analysis of a Multicast Switch",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=4,
PAGES="581-587",
YEAR=1991,
REFERENCES=12,
KEYWORDS="ATM; switching system; performance evaluation; multicast;
input buffer",
}

@ARTICLE{Ghod91:Parallel,
AUTHOR="M. Ghodsi and K. Kant",
TITLE="Performance analysis of parallel search algorithms on
multiprocessor systems",
JOURNAL=pe,
VOLUME=13,
NUMBER=1,
PAGES="67-81",
YEAR=1991,
REFERENCES=6,
KEYWORDS="Parallel computing; Markov chain; performance evaluation;
routing",
ANNOTE="The performance of a parallel path searching algorithm is
studied.",
}

@ARTICLE{Lee91:Trade,
AUTHOR="M. J. Lee and Song Li",
TITLE="Performance Trade-Offs in Input/Output Buffer Design for a
Non-Blocking Space-Division Packet Switch",
JOURNAL="International Journal of Digital and Analog Communication
Systems",
VOLUME=4,
NUMBER=1,
PAGES="21-31",
YEAR=1991,
REFERENCES=12,
KEYWORDS="ATM; switching system; input buffer; output buffer;
performance evaluation; analysis; matrix geometric method; phase-type
model",
}

@ARTICLE{Luca91:New,
AUTHOR="David M. Lucantoni",
TITLE="New Results on the Single Server Queue with a Batch Markovian
Arrival Process",
JOURNAL=comstat,
VOLUME=7,
NUMBER=1,
PAGES="1-46",
YEAR=1991,
REFERENCES=47,
KEYWORDS="Matrix geometric method; N/G/1; analysis; batch arrival;
phase-type model; MMPP/G/1; MAP/G/1",
}

@ARTICLE{Patt91:Broadband,
AUTHOR="Achille Pattavina",
TITLE="Broadband Switching Systems: First Generation",
JOURNAL=ett,
VOLUME=2,
NUMBER=1,
PAGES="75-87",
YEAR=1991,
REFERENCES=23,
KEYWORDS="ATM; switching system; architecture; performance evaluation;
anyan network; buffered Banyan network; analysis; survey",
}

@ARTICLE{Patt91:Batcher,
AUTHOR="Achille Pattavina",
TITLE="Performance Evaluation of a Batcher-Banyan Interconnection
Network with Output Pooling",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=1,
PAGES="95-103",
YEAR=1991,
REFERENCES=15,
KEYWORDS="ATM; switching system; performance evaluation; simulation;
Batcher-Banyan; input buffer",
}

@ARTICLE{Take91:Switch,
AUTHOR="T. Takeuchi and H. Suzuki and T. Aramaki",
TITLE="Switch Architectures and Technologies for Asynchronous Transfer
Mode",
JOURNAL=ieice,
VOLUME="E74",
NUMBER=4,
PAGES="752-760",
YEAR=1991,
REFERENCES=26,
KEYWORDS="ATM; switching; architecture; survey; classification",
ANNOTE="This paper reviews various switch architectures for ATM, which
have been proposed and developed so far in Japan. The switch fabrics can
be classified, owing to the arrangement of switch matrices and buffer
memories, into four categories: input buffer, output buffer, shared
buffer and crosspoint buffer. Those switches have their own advantages
and disadvantages, which require additional to implement the switches
for the practical",
}

@ARTICLE{Lea91:Tradeoff,
AUTHOR="C. Lea and D.-J. Shyy",
TITLE="Tradeoff of horizontal decomposition versus vertical stacking in
rearrangeable nonblocking networks",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=6,
PAGES="899-904",
YEAR=1991,
REFERENCES=10,
KEYWORDS="Fault tolerance; switching network; self routing;
rearrangement; Banyan network; multistage interconnection network",
ABSTRACT="In this paper, a class of fault-tolerant switching networks is
proposed",
}

@ARTICLE{Endr91:NETMON,
AUTHOR="O. Endriss and M. Steinbrunn and M. Zitterbart",
TITLE="{NETMON-II:} a monitoring tool for distributed and multiprocessor
systems",
JOURNAL=pe,
VOLUME=12,
NUMBER=3,
PAGES="191-202",
YEAR=1991,
REFERENCES=20,
KEYWORDS="Distributed system; multiprocessor system; monitoring;
measurement; hybrid monitor",
ANNOTE="NETMON-II is a distributed monitoring system, with the special
goal of least interference with the monitored object.",
}

@ARTICLE{Heis91:Overload,
AUTHOR="H.-U. Heiss",
TITLE="Overload effects and their prevention",
JOURNAL=pe,
VOLUME=12,
NUMBER=4,
PAGES="219-235",
YEAR=1991,
REFERENCES=64,
KEYWORDS="Overload control; performance evaluation; optimization;
control theory",
ANNOTE={The so-called "thrashing effect" well known from virtual
storagehas become a common phenomenon of large systems with concurrent
processing. An control-theoretic approach is used.},
}

@ARTICLE{Levy91:Polling,
AUTHOR="H. M. Levy and L. Kleinrock",
TITLE="Polling systems with zero switch-over periods: a general method
for analyzing the expected delay",
JOURNAL=pe,
VOLUME=13,
NUMBER=2,
PAGES="97-107",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Polling; delay analysis",
ANNOTE="We propose a general approach for using the results for
non-zeroswitch-over polling systems and applying them to solve the
corresponding ZSOP systems.",
}

@ARTICLE{Mura91:Analytic,
AUTHOR="M. Murata and M. Miyahara",
TITLE="An analytic solution of the waiting time distribution for the
discrete-time {GI/G/1} queue",
JOURNAL=pe,
VOLUME=13,
NUMBER=2,
PAGES="87-95",
YEAR=1991,
REFERENCES=12,
KEYWORDS="Queueing system; GI/G/1; discrete time analysis; waiting time;
distribution function; server vacation; generating function",
ANNOTE="A GI/G/1 queue in a discrete-time domain is analyzed.",
}

@ARTICLE{Haze91:Evolution,
AUTHOR="R. Ed. Hazell",
TITLE="Evolution of Alcatel Exchanges",
JOURNAL=ec,
ADDRESS="Paris",
VOLUME=65,
NUMBER=1,
PAGES="19-21",
NOTE="Special Issue Telecom 91",
YEAR=1991,
KEYWORDS="BISDN; ATM; switching system; architecture",
}

@ARTICLE{Haze91:Broadband,
AUTHOR="R. Ed. Hazell",
TITLE="Broadband Technology",
JOURNAL=ec,
ADDRESS="Paris",
VOLUME=65,
NUMBER=1,
PAGES="12-18",
NOTE="Special Issue Telecom 91",
YEAR=1991,
KEYWORDS="BISDN; ATM; architecture; switching system; CPN; customer
premises network; MAN; SMDS",
}

@ARTICLE{Li91:Trunk,
AUTHOR="Song Li",
TITLE="Performance of Trunk Grouping in Packet Switch Design",
JOURNAL=pe,
VOLUME=12,
NUMBER=4,
PAGES="207-218",
YEAR=1991,
REFERENCES=13,
KEYWORDS="Switching; packet switching; fast packet switching; ATM;
performance evaluation; analysis; input buffer; output buffer;
asymmetric load",
ABSTRACT="This paper studies the performance of trunk grouping in packet
switch system design, with emphasis on the analysis of maximum
throughput, input queue delay and packet loss rate.  The trunk grouping
technique can be implemented on both side of the switch.  In principle,
the output trunk grouping relieves traffic output contentions, while the
input trunk grouping, proposed in this paper, prevents individual input
links from overloading.  The study shows a significant advantage of both
input and output trunk groupings in removing local congestions caused by
individual links, especially in a highly non-uniform traffic
environment.  To implement trunk grouping, we suggest not to designate
the connection of each virtual circuit to individual links in high speed
network protocol design.",
URL="http://www.ece.utexas.edu/~sanqi/papers.html",
}

@ARTICLE{Mour91:Comprehensive,
AUTHOR="A. Mourad and B. Oezden and M. Malek",
TITLE="Comprehensive Testing of Multistage Interconnection Networks",
JOURNAL=ieeetc,
VOLUME=40,
NUMBER=8,
PAGES="935-951",
YEAR=1991,
REFERENCES=21,
KEYWORDS="Multistage interconnection network; Banyan network; test;
testing; fault; packet switching",
ANNOTE="We present efficient methods for testing packet-switched
multi-stage interconnection networks.  In addition to testing the data
paths and routing capabilities, we provide tests for detecting faults in
the control circuitry including the conflict resolution capab. Using a
general model of the switch, we construct testing sequences for the
internal functions of the fxf switch requiring only $O(f^2 2^f)$ tests
in the case of round robin",
}

@ARTICLE{Yang91:Nonblocking,
AUTHOR="Yi Yang and G. M. Masson",
TITLE="Nonblocking Broadcast Switching Networks",
JOURNAL=ieeetc,
VOLUME=40,
NUMBER=9,
PAGES="1005-1015",
YEAR=1991,
REFERENCES=26,
KEYWORDS="Circuit switching; multicast; switching network; nonblocking;
multistage interconnection network; path control",
}

@PHDTHESIS{Schm91:Einsatzmoeglichkeiten,
AUTHOR="L. Schmickler",
TITLE="Einsatzmöglichkeiten der Optimalstrategie {SRPT} in Lokalen
Rechnernetzen",
PUBLISHER="Aachener Hochschulschriften, Verlag der
Augustinus-Buchhandlung",
SCHOOL="RWTH Aachen",
ADDRESS="Aachen",
PAGES=192,
YEAR=1991,
LANGUAGE="German",
REFERENCES=139,
KEYWORDS="Queueing discipline; LAN; CSMA/CD; token bus; token ring;
SRPT; shortest remaining processing time; FDDI",
}

@PHDTHESIS{Nieb91:Struktur,
AUTHOR="N. Niebert",
TITLE="Struktur und Algorithmen eines Formelauswertesystems für die
Datenverkehrstheorie",
PUBLISHER="Aachener Hochschulschriften, Verlag der
Augustinus-Buchhandlung",
SCHOOL="RWTH Aachen",
ADDRESS="Aachen",
PAGES=140,
YEAR=1991,
LANGUAGE="German",
REFERENCES=88,
KEYWORDS="Queueing theory; formula manipulation; language processor",
}

@PHDTHESIS{Ding91:Korrelierte,
AUTHOR="W. Ding",
TITLE="Korrelierte Zufallsprozesse in Wartesystemen von
Kommunikationsnetzen",
PUBLISHER="Aachener Hochschulschriften, Verlag der
Augustinus-buchhandlung",
SCHOOL="RWTH Aachen",
ADDRESS="Aachen",
PAGES=116,
YEAR=1991,
LANGUAGE="German",
REFERENCES=118,
KEYWORDS="MMPP; RVG; queueing system; parameter estimation",
}

@ARTICLE{Sezg91:Fast,
AUTHOR="F. Sezgin",
TITLE="On a fast and portable uniform quasi-random number generator",
JOURNAL=sigsim,
VOLUME=21,
NUMBER=2,
PAGES="30-36",
YEAR=1991,
REFERENCES=7,
KEYWORDS="RNG; linear congruential generator",
ANNOTE="a RNG with a very large period (> 10**592) is proposed.",
}

@ARTICLE{Bern91:Methodology,
AUTHOR="F. Bernabei and Roberto Ferretti and M. Listanti and Giuseppe
Zingrillo",
TITLE="A methodology for buffer design in {ATM} switches",
JOURNAL=ett,
ADDRESS="Milan",
VOLUME=2,
NUMBER=4,
PAGES="367-379",
YEAR=1991,
REFERENCES=15,
KEYWORDS="ATM; switching block; buffer dimensioning; simulation; extreme
value theorem",
ANNOTE="Using the generalized extreme value theory, very low cell loss
probabilities are estimated from simulation runs.",
}

@ARTICLE{Cont91:Comprehensive,
AUTHOR="M. Conti and Enrico Gregori and Luniano Lenzini",
TITLE="A comprehensive analysis of {DQDB}",
JOURNAL=ett,
ADDRESS="Milan",
VOLUME=2,
NUMBER=4,
PAGES="403-413",
YEAR=1991,
REFERENCES=20,
KEYWORDS="MAN; DQDB; performance evaluation; simulation; fairness",
ANNOTE="This paper reports on an extended simulation analysis of the
asynchronous part of the DQDB MAC protocol.",
}

@ARTICLE{Balb91:ATM,
AUTHOR="G. P. Balboni and W. Chiarottino and Carlo Demichelis and R.
Melen and  others",
TITLE="An {ATM} switching testbed",
JOURNAL=ett,
ADDRESS="Milan",
VOLUME=2,
NUMBER=4,
PAGES="391-401",
YEAR=1991,
REFERENCES=12,
KEYWORDS="ATM; switching network; buffered banyan network; multistage
interconnection network",
ANNOTE="An experimental ATM switching node being developed by CSELT is
described.",
}

@INPROCEEDINGS{Schm91:Statistik,
AUTHOR="N. Schmitz",
TITLE="Statistik-Fehler, Fallen, Schwindel",
BOOKTITLE={GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="1-14",
NOTE="Informatik Fachbericht",
YEAR=1991,
LANGUAGE="German",
REFERENCES=5,
KEYWORDS="Fundamentals in statistics; correlation; random number
testing; conditional probability",
ANNOTE="Anhand von (übersimplifizierten) Beispielen wird vor Fehlern/
Fehlinterpretationen gewarnt, die in der deskriptiven Statistik
(Darstellung und Aufbereitung von Meßdaten), der stochastischen
Modellierung (wahrscheinlichkeitstheoretische Beschreibung quantitativer
Experiment) und der statistischen Inferenz (Auswertung von Meßdaten,
Bewertung von Systemen) zu falschen Resultaten führen können.",
}

@INPROCEEDINGS{Hass91:Modellierung,
AUTHOR="G. Hasslinger and E. S. Rieger",
TITLE="Modellierung offener Warteschlangennetzwerke durch
Erneuerungsprozesse im diskreten Zeitbereich",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen"},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="15-29",
NOTE="Informatik Fachbericht",
YEAR=1991,
LANGUAGE="German",
REFERENCES=23,
KEYWORDS="Open queueing network; approximation; decomposition; renewal
approximation; discrete time analysis",
ABSTRACT="Es wird ein Ansatz zur Berechnung der Verteilungen der
Wartezeit und der Kundenanzahl an den Stationen eines offenen Netzes mit
beliebig gegebenen Verzweigungswahrscheinlichkeiten vorgestellt. Die
Analyse erfolgt durch ein Iterationsverfahren und geht von einer
Dekomposation des Netzwerks in einzelne Knoten aus, wobei insbesondere
Einbedienerstationen (GI/G/1-Systeme) betrachtet werden.",
}

@INPROCEEDINGS{Buch91:Numerical,
AUTHOR="P. Buchholz",
TITLE="The Numerical Analysis of Hierarchical Queueing Network Models",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen"},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="30-45",
NOTE="Informatik Fachberichte",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Hierarchical modeling; numerical method; steady state
analysis; queueing network",
ANNOTE="In this paper a class of hierarchically structured queueing
network models is considered and it is shown that the hierarchical model
structure is directly reflected in the state space and the generator
matrix of the underlying Markov process. Iterative solution techniques
can be modified to make use of the model structure, which allows the
efficient numerical analysis of large, up to now not solvable queueing
network models.",
}

@INPROCEEDINGS{Mahl91:Job,
AUTHOR="M. Mähler",
TITLE="Job Scheduling under Fairness Aspects",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modell. u. Bewert. v.
Rechensystemen},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="46-60",
NOTE="Informatik Fachberichte",
YEAR=1991,
REFERENCES=21,
KEYWORDS="Distributed computing system; performance parameter;
scheduling; load sharing; fairness",
ANNOTE="It is the goal of this paper to study how to make this second
decision (select the next job) in order to assign servers to clients in
a fair way. A general fairness criterion is introduced and applied to
different algorithms, which are tested analytically and by simulation.
Assignment by consumption dependent priorities gives the best results.",
}

@INPROCEEDINGS{Hofs91:Leistungsbewertung,
AUTHOR="H. Hofstetter",
TITLE="Leistungsbewertung von {ISDN-Vermittlungsknoten}",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modell. u. Bewert. v.
Rechensystemen},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="109-120",
NOTE="Informatik Fachberichte",
YEAR=1991,
LANGUAGE="German",
REFERENCES=9,
KEYWORDS="Performance evaluation; QOS; BISDN; ISDN; CCITT",
ANNOTE="Auch bezüglich der Leistungsbewertung des ISDN und seiner
Komponenten werden beim CCITT Konzepte und Empfehlungen erarbeitet. Der
vorliegende Beitrag gibt eine Einführung in diese Leistungskonzepte.",
}

@INPROCEEDINGS{Blon91:Cell,
AUTHOR="C. Blondia and O. Casals",
TITLE="Cell Loss Probabilities in a Statistical Multiplexer in an {ATM}
Network",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen"},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="121-136",
NOTE="Informatik Fachberichte",
YEAR=1991,
REFERENCES=14,
KEYWORDS="ATM; statistical multiplexing; loss probability; QOS",
ABSTRACT="In this paper we evaluate the loss probability of cells
generated by a burst/silence source which is mixed with a superposition
of $M$ independent identical burst/silence traffic streams in a
statistical multiplexer with a finite buffer capacity. The impact of the
buffer size of the multiplexer, the burst length of sources and the load
of the system on this conditional loss probability is studied.",
}

@INPROCEEDINGS{Nieb91:Strukturelemente,
AUTHOR="N. Niebert",
TITLE="Strukturelemente eines Systems zur Auswertung analytischer
Formeln in der Datenverkehrstheorie",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="137-151",
NOTE="Informatik Fachberichte",
YEAR=1991,
LANGUAGE="German",
REFERENCES=15,
KEYWORDS="Analytical model; performance evaluation; symbolic algebraic
computation; numerical evaluation; computer arithmetic; object-oriented
programming; distributed computing system",
ANNOTE="Analytische Modelle zur Berechnung von Leistungsgrößen in
Kommunikations- oder Rechnersystemen, die auf den mathematischen
Methoden der Datenverkehrstheorie basieren, stellen eine schnelle und
allgemeine Möglichkeit zur Auswertung dar. Um einen einfachen Einsatz
der oft komplexen Formeln zu ermöglichen, bedarf es eines Systems zur
Unterstützung der numerischen Formelauswertung, grafischen
Ergebnisdarstellung und Archivierung.",
}

@INPROCEEDINGS{Hoff91:Leistungsbewertung,
AUTHOR="S. Hoff and D. Hübner and F. Reichert and A. Scunio",
TITLE="Leistungsbewertung von Verfahren der Mobil-Kommunikation:
Dezentrale Paketsynchronisation und Kanalzugriff",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="152-166",
NOTE="Informatik Fachberichte",
YEAR=1991,
LANGUAGE="German",
REFERENCES=13,
KEYWORDS="Mobile radio; synchronization; decentralized control; channel
assignment; channel simulation",
ANNOTE="Neue Anwendungen im Bereich der mobilen Datenfunknetze mit
strengen Anforderungen z.B. an Echtzeitverhalten erfordern neuartige
Verfahren des Datenaustausches. Hierzu entwickelte Protokolle für solche
Anwendungsgebieete werden in Werkzeug zur Simulation dieser Verfahren
wird vorgestellt.",
}

@INPROCEEDINGS{Bras91:Quittierungsverfahren,
AUTHOR="V. Brass",
TITLE="Ein Quittierungsverfahren für Multi-Hop Paketfunknetze",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="167-181",
NOTE="Informatik Fachberichte",
YEAR=1991,
LANGUAGE="German",
REFERENCES=8,
KEYWORDS="Multihop; slotted ALOHA; multipoint; point-to-multipoint
communication; acknowledgement; performance evaluation; analysis;
simulation",
ANNOTE="In diesem Beitrag wird ein Mehrfach-Quittierungsverfahren
vorgestellt, daß sich für Punkt-zu-Punkt und Punkt-zu-Mehrpunkt
Kommunikation in Multi-hop Paketfunknetzen eignet. Das Verfahren wird in
guter Näherung analytisch bewertet, und die Ergebnisse simulative
validiert. Die hier vorliegenden Berechnungen gelten für das S-ALOHA
Protokoll.",
}

@INPROCEEDINGS{Gott91:Verteilung,
AUTHOR="K. Gotthardt",
TITLE="Verteilung der Anzahl Hops einer Quelle-Ziel-Übertragung im
Multihop-Paketfunknetz",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen"},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="182-195",
NOTE="Informatik Fachberichte",
YEAR=1991,
LANGUAGE="German",
REFERENCES=7,
KEYWORDS="Multihop; access protocol; modeling; performance evaluation",
ANNOTE="Die Verteilung der Zahl benötiger Hops für eine
Quelle-Ziel-Übertragung eines Paketes in einem Multihop-Funknets ist
unerläßlich um interessierende Leistungsgrößen wie Quelle-Ziel-Durchsatz
und Verzoegerung zu berechnen. In diesem Beitrag wird diese Verteilung
für ein Netz mit mobilen Stationen bestimmt, wobei angenommen wird, daß
die Zahl der Stationen in einem Flächenelement einer Poissonverteilung
genügt.",
}

@INPROCEEDINGS{Weic91:Benchmarking,
AUTHOR="Reinhold Weicker",
TITLE="Benchmarking: Status, Kritik und Aussichten",
BOOKTITLE="6. GI/ITG-Fachtagung ``Messung, Modellierung und Bewertung
von Rechensystemen''",
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="259-277",
NOTE="Informatik Fachberichte",
YEAR=1991,
LANGUAGE="German",
REFERENCES=20,
KEYWORDS="Benchmark; performance measurement; LINPACK",
ANNOTE="Zunächst werden heute uebliche Industrie-Standards im
Benchmarking kurz charakterisiert (MIPS, MFLOPS, Whetstone, Chrystone,
Linpack). Dann werden neue Initiativen von Herstellern oder Anwendern
besprochen, die sich um die Zusammenstellung von größeren,
repräsentativen Programmen als Benchmarks bemühen (SPEC, TPC, Perfect,
u.a.).",
}

@INPROCEEDINGS{Borc91:Datenkommunikations,
AUTHOR="M. Borchert and M. Angela Sasse",
TITLE="Datenkommunikations-Benchmark {LAMBDA}",
BOOKTITLE={6. GI/ITG-Fachtagung"Messung, Modellierung und Bewertung von
Rechensystemen"},
ISBN="3-540-54550-6",
ADDRESS="Neubiberg",
PAGES="278-291",
NOTE="Informatik Fachberichte",
YEAR=1991,
LANGUAGE="German",
REFERENCES=9,
KEYWORDS="Communication network; performance measurement; performance
measure; benchmark; traffic generator",
ANNOTE="DIN 66273; In diesem Beitrag wird ein neuartiger
Datenkommunikations-Benchmark vorgestellt (LAMBDA-Benchmark).",
}

@ARTICLE{Acam91:Metropolitan,
AUTHOR="A. S. Acampora and Tom Chu and C. Dragone and M. Gans",
TITLE="A Metropolitan Area Radio System Using Scanning Pencil Beams",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=1,
PAGES="141-151",
YEAR=1991,
KEYWORDS="Radio channel; TDMA; time division multiple access",
ANNOTE="A new metropolitan area radio system is proposed which provides
continuous 360\`e coverage over a large service region from a centrally
located base station. This new approach differs from others in that the
base station blankets the service region witha raster of very narrow
pencil beams which can be rapidly scanned to any position in synchronism
with the switching sequences of a Time-Division-Multiple-Access
assignment.",
}

@ARTICLE{Berg91:Comparison,
AUTHOR="Arthur W. Berger",
TITLE="Comparison of Call Gapping and Percent Blocking for Overload
control in Distributed Switching Systems and Telecommunications
networks",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=4,
PAGES="574-580",
YEAR=1991,
KEYWORDS="Communication system; distributed system; overload control;
robustness",
ANNOTE="Two overload control techniques are compared, prevent blocking
and call gapping, which have been used in distributed switching systems
and in telecommunications networks. The comparison is based on nine
criteria, seven of which concern robustness. The results are useful in
the design of practical, effective overload controls.",
}

@ARTICLE{Chla91:Wave,
AUTHOR="I. Chlamtac and O. Weinstein",
TITLE="The Wave Expansion Approach to Broadcasting in Multihop Radio
Networks",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=3,
PAGES="426-433",
YEAR=1991,
KEYWORDS="Packet radio; multihop; radio channel; broadcast",
ANNOTE="In this paper we propose an algorithm for efficient
communication between neighbours in multihop radio networks.
Thealgorithm guarantees a bound on the transmission efficiency in aradio
channel for arbitrary topology. The algorithm can be embedded in
protocols for solving basic network problems such asbroadcast,
multicast, leader election, or finding shortest paths",
}

@ARTICLE{Cho91:Window,
AUTHOR="Yong Soo Cho and Chong Kwan Un",
TITLE="Window Flow Control with Error-Checking Scheme in
Quasi-Cut-Through Switching Network with Noisy Channels",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=3,
PAGES="394-397",
YEAR=1991,
KEYWORDS="Flow control; acknowledgement; fast packet switching; window
mechanism; error handling",
ABSTRACT="We investigate two acknowledgement schemes for window flow
contrfull and partial ACK schemes, in conjunction with two
error-checking schemes at every node or at the store-and-forward
nodesonly in a quasi-cut-through switching network with noisy channelWe
study their various properties including throughput, delay, and the
combined delay-throughput performance, and show that theproposed ACK
schemes provide efficiently delay .",
}

@ARTICLE{Glis91:Carrier,
AUTHOR="S. G. Glisic",
TITLE="1-Persistent Carrier Sense Multiple Access in Radio Channels with
Imperfect Carrier Sensing",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=3,
PAGES="458-464",
YEAR=1991,
KEYWORDS="CSMA; carrier sense multiple access; radio channel;
performance evaluation",
ANNOTE="A comprehensive analysis of 1-persistent CSMA system using
radiochannel with imperfect carrier sensing is presented and
discussed.Two main results of the analysis are a) the optimum value of
the channel state detector is determined and b) it was shown how much
the system performance is degraded due to imperfect carrier sensing.
Simulation check points confirmed thetheoretical analysis.",
}

@ARTICLE{Kall91:Sequential,
AUTHOR="Samir Kallel and David Haccoun",
TITLE="Sequential Decoding with an Efficient Partial Retransmission
{ARQ} Strategy",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=2,
PAGES="208-213",
YEAR=1991,
KEYWORDS="ARQ; coding theory; throughput analysis",
ANNOTE="In this paper, we present and analyze an efficient partial
retransmission ARQ strategy using convolutional coding and sequential
decoding, in conjunction with code combining. In the proposed ARQ
scheme, whenever a packet of data needs to be retransmitted, that packet
is not repeated entirely as in the case of conventional full
retransmission ARQ strategies.",
}

@ARTICLE{Kers91:Mentor,
AUTHOR="A. Kershenbaum and Parviz Kermani and G. A. Grover",
TITLE="Mentor: An Algorithm for Mesh Network Topological Optimization
and Routing",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=4,
PAGES="503-513",
YEAR=1991,
KEYWORDS="Communication network; cost function; optimization; routing",
ANNOTE="We consider the problem of obtaining a minimum cost topology
fora mesh network given matrices specifying the cost of links between
all pairs of nodes and the internode requirements. We present a
heuristic algorithm which works in terms of general network design
principles and uses utilization as a figure of merit.",
}

@ARTICLE{Mitr91:Comparative,
AUTHOR="D. Mitra and J. B. Seery",
TITLE="Comparative Evaluations of Randomized and Dynamic Routing
Strategies for Circuit-Switched Networks",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=1,
PAGES="102-116",
YEAR=1991,
KEYWORDS="Alternate routing; dynamic routing; circuit switching;
simulation model",
ANNOTE="The theory and practice of circuit switching on networks has
recently been rapidly evolving. We investigate two fundamentallyseparate
classes of routing algorithms-randomized and deterministic. The main
randomized algorithm is Gibben's and Kelly's recently introduced Dynamic
Alternate Routing. In the contrasting deterministic algorithm, attempts
to carry a call are made in a specific precomputed order.",
}

@ARTICLE{Mitt91:Note,
AUTHOR="K. K. Mittal and A. N. Venetsanopoulos",
TITLE="A Note Optimal Input Control Policy for an {ALOHA} Access
Scheme",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=2,
PAGES="197-199",
YEAR=1991,
KEYWORDS="ALOHA; controlled access; multiple access; simulation",
ANNOTE="Input control policies had been proposed to improve the delay -
throughput performance of ALOHA access schemes. Through simulation
results, it was observed that the optimal control policies were in
general of control limit type. This paper discusses input control
policies for one such ALOHA access scheme and proves analytically that
the optimal policy is indeedof control limit type.",
}

@ARTICLE{Mizu91:Burst,
AUTHOR="T. Mizuike and Y. Ito and D. Kennedy and L. Nguyen",
TITLE="Burst Scheduling Algorithms for {SS/TDMA} Systems",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=4,
PAGES="533-539",
YEAR=1991,
KEYWORDS="Communication system; TDMA; time division multiple access",
ANNOTE="This paper proposes efficient algorithms to generate a detailed
operation plan for SS/TDMA systems. A burst time plan generationproblem
is first analyzed and two algorithms are presented for burst
scheduling.The first method is an algorithm based upon binpacking
problem. The other algorithm schedules new bursts while reassigning
already scheduled bursts by using single machine scheduling model.",
}

@ARTICLE{Wang91:Combined,
AUTHOR="Xin Wang and Jaidev Kaniyil and Y. Onozato and Jia Liu and 
others",
TITLE="Performance Analysis of a Combined Random-Reservation Access
Scheme",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=4,
PAGES="478-481",
YEAR=1991,
KEYWORDS="Access protocol; reservation system; stability; throughput
analysis",
ANNOTE="Stability and throughput are investigated for a combined
random-reservation access scheme employed in a satellite-based very
small aperture terminal packet communication network. The analysis is
based on the use of catastrophe theory by which the system behaviour is
characterized by the cusp catastrophe. A stable region is given in terms
of system.",
}

@ARTICLE{Yu91:Buffered,
AUTHOR="H. C. Yu and R. L. Hamilton",
TITLE="A Buffered Two-Node Packet Radio Network with Product Form
Solution",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=1,
PAGES="62-75",
YEAR=1991,
KEYWORDS="Packet radio; ALOHA; performance evaluation",
ANNOTE="We consider a packet radio network with two nodes; both nodes
access a single radio channel the slotted-ALOHA protocol. This model
results in a network of two interfering queues. Network ofinterfering
queues seldom have closed-form expressions for the equilibrium
probabilities. However, when certain constraints are placed on the
network parameters, the network will have a product form solution for
the equilibrium probabilities.",
}

@INPROCEEDINGS{Denz91:ATM,
AUTHOR="W. Denzel",
TITLE="{ATM} switching network architectures",
BOOKTITLE="ITG/GI Workshop Verbindungsnetzwerke für Parallelrechner und
Breitband-übermittlungssysteme",
ADDRESS="Stuttgart",
PAGES="9-16",
YEAR=1991,
REFERENCES=32,
KEYWORDS="ATM; switching network; buffer management; input buffer;
survey; output buffer",
ANNOTE="This paper gives an overview of advanced packet switch
architectures. Performance aspects are discussed.",
}

@INPROCEEDINGS{Lang91:Konzept,
AUTHOR="K.-D. Langer",
TITLE="Konzept eines Koppelelements für die hochratige
{ATM-Vermittlung}",
BOOKTITLE="ITG/GI Workshop Verbindungsnetzwerke für Parallelrechner und
Breitband-übermittlungssysteme",
ADDRESS="Stuttgart",
PAGES="42-47",
YEAR=1991,
LANGUAGE="German",
REFERENCES=14,
KEYWORDS="ATM; switching block; input buffer; performance evaluation",
ANNOTE="Eingangspufferung mit Pufferzugriffstiefe",
}

@INPROCEEDINGS{Thei91:Wegesuchstrategien,
AUTHOR="T. H. Theimer",
TITLE="Wegesuchstrategien für {ATM-Koppelnetze} und deren
Leistungsfähigkeit",
BOOKTITLE="ITG/GI Workshop Verbindungsnetzwerke für Parallelrechner und
Breitband-übermittlungssysteme",
ADDRESS="Stuttgart",
PAGES="82-88",
YEAR=1991,
LANGUAGE="German",
REFERENCES=16,
KEYWORDS="ATM; switching network; routing; performance evaluation",
ANNOTE="Leistungsvergleich verschiedener Wegesuchverfahren und
Koppelnetzstrukturen.",
}

@ARTICLE{Stas91:Computationally,
AUTHOR="G. I. Stassinopoulos and M. G. Kazantzakis",
TITLE="A computationally efficient iterative solution of the
multidestination optimal dynamic routing problem",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=9,
PAGES="1370-1378",
YEAR=1991,
REFERENCES=14,
KEYWORDS="Dynamic routing; efficient computer algorithm; iterative
method",
ANNOTE="The dynamic routing problem for multiple destination networks is
considered.",
}

@ARTICLE{Shyy91:Log2,
AUTHOR="D.-J. Shyy and C. Lea",
TITLE="Log2(N, m, p) strictly nonblocking networks",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=10,
PAGES="1502-1510",
YEAR=1991,
REFERENCES=10,
KEYWORDS="Switching network; nonblocking; self routing; fault
tolerance",
ANNOTE="A new class of self-routing strictly nonblocking switching
networks, called Log2(N, m, p) network is introduced.",
}

@ARTICLE{Ng91:Improving,
AUTHOR="S. Ng",
TITLE="Improving disk performance via latency reduction",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=1,
PAGES="22-30",
YEAR=1991,
REFERENCES=20,
KEYWORDS="Computer system; disk; performance evaluation",
ANNOTE="This paper demonstrates that a reduction in the rotational
latency and RPS miss delay (both of which are related to the rotation of
the disk drives) has the greatest impact in reducing the disk's basic
service time",
}

@INPROCEEDINGS{Boll91:Two,
AUTHOR="R. Bolla and F. Davoli",
TITLE="A two-layer optimization structure for access control and
bandwidth sharing in high-speed integrated networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="177-188",
YEAR=1991,
REFERENCES=7,
KEYWORDS="TDM; time division multiplex; broadband; traffic mix;
bandwidth allocation; packet switching; circuit switching",
ANNOTE="The access to a multiservice broad-band synchronous TDM network
is considered, where hybrid frames are used to carry two basic traffic
types (a circuit-switched isochronous and a packet-switched asynchronous
one), generated by several users. Each user is assigned a portion of the
total available bandwidth, in terms of slots/frame, which is dynamically
allocated between the two traffic types at the user premises",
}

@ARTICLE{Brun91:Exact,
AUTHOR="H. Bruneel",
TITLE="Exact Derivation of Transient Behaviour for Buffers with Random
output Interruptions",
JOURNAL=cnis,
VOLUME=22,
NUMBER=4,
PAGES="277-285",
YEAR=1991,
REFERENCES=21,
KEYWORDS="Queueing system; discrete time queue; transient analysis;
interrupted service; server vacation",
}

@INPROCEEDINGS{Burs91:Priority,
AUTHOR="D. Bursztynowski and W. Burakowski and W. Syski",
TITLE="On priority assignment problems in {SPC} systems",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="219-227",
YEAR=1991,
REFERENCES=14,
KEYWORDS="SPC; traffic model; M/G/1; priority; response time; Poisson
distribution; cost function; central server",
ANNOTE="The paper addresses some performance-oriented design problems in
a class of SPC systems with central control modeled by an M/G/1 system
with priorities and feedback, especially performance optimization by
task prioritizing. Two different types of objectives are identified:
capazity-oriented and average response time-oriented ones. Also, the
problem of dependence of the optimal character of the solutions on call
mix changes is discussed.",
}

@INPROCEEDINGS{Chle91:Off,
AUTHOR="E. Chlebus",
TITLE="Off-line verus on-line network management - Implementation and
performance study of circuit-switched traffic control methods",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=3,
PAGES="38-53",
YEAR=1991,
REFERENCES=25,
KEYWORDS="Routing; network management; dynamic routing; static routing;
random routing; control theory",
ANNOTE="The paper presents a comparative study of various traffic
routing strategies aiming at overall network blocking minimization.
Circuit-switched traffic is modelled by means of static and dynamic
flows as well as Markov decision processes. The corresponding
optimization problems are formulated and solved by methods of control
theory.",
}

@INPROCEEDINGS{Cott91:Adaptive,
AUTHOR="M. Cotton and L. G. Mason",
TITLE="Adaptive isarithmic flow control in fast packet switching
networks - Heavy traffic case",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="114-125",
YEAR=1991,
REFERENCES=15,
KEYWORDS="Flow control; fast packet switching; heavy traffic
approximation; propagation delay",
ANNOTE="The centralized adaptive isarithmic flow control scheme is
considered, proposed by Mason and Gu, in the context of fast packet
switching networks. The high transmission rates involved in such
networks make it necessary to specifically consider propagation
delays.",
}

@ARTICLE{Cour91:Minimization,
AUTHOR="P.-J. Courtois and G. Scheys",
TITLE="Minimization of the Total Loss Rate for Two Finite Queues in
series",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=11,
PAGES="1651-1661",
YEAR=1991,
REFERENCES=11,
KEYWORDS="M/Ek/1; delay loss model; tandem queue; loss probability;
optimization; performance evaluation; analysis",
}

@INPROCEEDINGS{Dutk91:Connection,
AUTHOR="E. Dutkiewicz and G. J. Anido",
TITLE="Connection admission control in {ATM} networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="166-176",
YEAR=1991,
REFERENCES=16,
KEYWORDS="ATM; network management; network control system; MMPP;
resource management; traffic control; virtual path; virtual network;
virtual channel",
ANNOTE="A three level management architecture forms a basis for managing
and controlling network resources in ATM networks. It utilises the
concepts of virtual channels, virtual paths, and virtual networks. Call
admission model using a 2-state Markov modulated Poisson process
approximation for traffic streams is studied in order to obtain simple
approximation algorithms.",
}

@INPROCEEDINGS{Dzio91:Buffer,
AUTHOR="Z. Dziong and K. Liao and L. G. Mason",
TITLE="Buffer dimensioning and effective bandwidth allocation in {ATM}
based networks with priorities",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="154-165",
YEAR=1991,
REFERENCES=11,
KEYWORDS="Buffer dimensioning; ATM; priority; bandwidth allocation;
FIFO; blocking; delay time; multiplexer; nonpreemptive priority; GOS",
ANNOTE="An ATM multiplexer with several FIFO buffers is considered
operating in non preemptive priority regime. It is assumed that each
connection or type of traffic is allocated to one priority characterized
by its grade of service constraints. A model for buffer dimensioning and
effective bandwidth allocation is derived. It consists of one
independent multiplexer for each priority.",
}

@INPROCEEDINGS{Econ91:Title,
AUTHOR="D. Economou and P. Taylor",
TITLE="Title unknown",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="220-231",
YEAR=1991,
REFERENCES=11,
KEYWORDS="Cyclic service; processor sharing; buffer; DQDB; packet
length",
ANNOTE="The problem of determining the distribution of segmentation and
reassembly buffer occupancy in a discrete time cyclic queue with
variable length packets. Exact expressions for these distributions are
obtained for a continous time, processor sharing approximation. The
predicted proportion of lost segments is compared with simulation
results.",
}

@INPROCEEDINGS{Ehri91:H2,
AUTHOR="I. Ehriel",
TITLE="Performance analysis of the {H2/G/1} system",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="238-244",
YEAR=1991,
REFERENCES=5,
KEYWORDS="Hyperexponential; waiting time; model; arrival process;
signalling; D-channel; signalling protocol; CSMA/CD; LAPD; X.25;
H2/G/1",
ANNOTE="New user-network interface which is recommended by CCITT has
definite peculiarity. The main attention should be turn upon model
selection for the signalling channel. The suggested model has a
hyperexponential distribution for the incoming demand flow and general
distribution for service time. By the analysing of this queueing system
an approach for the mean waiting time is offered.",
}

@INPROCEEDINGS{Fili91:Model,
AUTHOR="J. Filipiak",
TITLE="A model of a flexible User/Network Interface for {BISDN}",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="1-26",
YEAR=1991,
REFERENCES=5,
KEYWORDS="BISDN; UNI; user network interface; open network;
IN=intelligent network; communication network; OSI; signalling
protocol",
ANNOTE="A new model of the user-network interface in a broadband ISDN is
presented, called Flexible User Network Interface (F-UNI). It is
developed to encompass new features of ATM, ISDN, Open Network
Architecture, IN and Personal Communication Network. It is an
abstraction of existing interfaces.",
}

@INPROCEEDINGS{Ghas91:Study,
AUTHOR="M. Ghassemi and R. A. Skoog",
TITLE="Study of message delays in the presence of long messages and
correlated arrivals in Signalling System No. 7 networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=3,
PAGES="121-130",
YEAR=1991,
REFERENCES=2,
KEYWORDS="Signalling protocol; correlation; arrival process; message
traffic; delay time; traffic control; controlled load",
ANNOTE="Introduction of long MSU traffic, even in limited amounts,
deteriorates the network delay performance radically. Various options
have been examined for reducing the impact of carrying long MSUs on SS
No. 7 networks.",
}

@INPROCEEDINGS{Gira91:Routing,
AUTHOR="Andre Girard and B. Liau and N. Boumzebra",
TITLE="Routing Optimization and Dimensioning of Networks with Revenues:
Numerical Results",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="153-164",
YEAR=1991,
REFERENCES=11,
KEYWORDS="Routing algorithm; alternate routing; hierarchical network;
load sharing; adaptive routing",
ANNOTE="A numerical solution procedure is presented that is in many ways
similar to the classical ECCS dimensioning method commonly used for
hierarchical networks. First numerical results are shown.",
}

@INPROCEEDINGS{Hend91:New,
AUTHOR="W. Henderson",
TITLE="A Survey of, and Some New Results on, Stochastic Petri Nets",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="138-152",
YEAR=1991,
REFERENCES=55,
KEYWORDS="Petri net; SPN; stochastic Petri net; communication model;
communication protocol",
ANNOTE="This paper is an introduction to the modelling tool of Petri
nets (PNs) but concentrates mostly on its performance counterpart,
stochastic Petri nets (SPNs). It is a short and personal survey with the
majority of the paper dedicated to recent research from the Teletraffic
Research Centre of Adelaide University.",
}

@INPROCEEDINGS{Herb91:Buffer,
AUTHOR="G. Herbuterne and C. Rosenberg",
TITLE="Buffer sizing in Bulk Service Systems",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="232-237",
YEAR=1991,
REFERENCES=7,
KEYWORDS="Bulk service; hybrid; M/GI/1; M/G/1; cyclic service; ATM;
Markov chain",
ANNOTE="The paper addresses the problem of buffer sizing for queues with
bulk service. The model arises in the context of the study of a hybrid
frame where synchronous cells are first served and ATM cells are given
access to the remaining slots. Loss probabilities are derived by means
of simple conservation arguments from the state probabilities at
departure epochs obtained through classical Markov chain analysis.",
}

@INPROCEEDINGS{Kwia91:Multi,
AUTHOR="M. Kwiatkowski",
TITLE="Performance Analysis of multi-layer token ring local area
networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="126-137",
YEAR=1991,
REFERENCES=14,
KEYWORDS="Token ring; LAN; OSI; window mechanism; decomposition; media
access control; logical link control",
ANNOTE="A queueing network performance model is considered of a token
ring LAN in which multi-layer OSI architecture is used. Several
performance submodels are developed for each layer working in isolation.
Statistical independance and Poisson character of exogenous streams of
messages arriving in layer are usually assumed in these submodels.",
}

@INPROCEEDINGS{Lebo91:General,
AUTHOR="M. Lebourges",
TITLE="A general purpose model for circuit-switched networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=3,
PAGES="95-106",
YEAR=1991,
REFERENCES=9,
KEYWORDS="Model; blocking; stream traffic; overflow; peakedness;
adaptive routing",
ANNOTE="The general purpose circuit-switched networks model integrates
known models for particular systems or phenomena, e.g. multi-services
traffics, repeated attempts, exchange blockings, adaptive routing, in a
single network model. The aim is not to have a precise modelling of each
system, but to get correct qualitative behaviour and quantitative
averages at the network level.",
}

@INPROCEEDINGS{Mari91:Hybrid,
AUTHOR="M. I. Marie and M. S. Moustafa",
TITLE="Performance of hybrid switching networks with priority: Fixed
boundary case",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="256-264",
YEAR=1991,
REFERENCES=5,
KEYWORDS="Hybrid switching; switching network; circuit switching;
voice/data integration; packet switching; waiting time",
ANNOTE="This paper deals with the performance of hybrid switching
networks. The frame length is divided into two fixed portions one for
the voice traffic (circuit switched) and the other for data traffic
(packet switched); i.e., fixed boundary. Voice traffic is treated as a
loss system. Exact analytical expressions for the expected waiting time
for data packets of multiple classes of different priorities are
given.",
}

@INPROCEEDINGS{Mart91:Packet,
AUTHOR="F. E. Martin and E. Granel",
TITLE="Packet network structures based on multilink interfaces",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="91-102",
YEAR=1991,
REFERENCES=8,
KEYWORDS="Interface; arrival process; data network; packet switching;
hyperexponential; H2/M/N",
ANNOTE="The paper presents a qualitative performance analysis of
multilink interfaces in data packet networks by comparing with other
systems based on several single links. Both alternatives are useful for
increasing throughput capacity without changing the bitrate.",
}

@INPROCEEDINGS{Mizu91:Experiences,
AUTHOR="J. Mizusawa and M. Akiyama",
TITLE="Experiences and Expectations of Introducing {PSTN} New Services
in {JAPAN}",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=3,
PAGES="13-24",
YEAR=1991,
REFERENCES=3,
KEYWORDS="Public network; network planning; X.25; X.21; X.28; X.29;
ISDN; traffic analysis; network design",
ANNOTE="New network design is classified into three categories, New
public network construction, Access network construction and Adding new
service function. The examples are DDX packet network, DDX Telephone to
Packet access service and Freedial service. ISDN network design concepts
are explained, together with the present traffic characteristics. The
direction of PSTN design concept is indicated in terms of VIPA
(virtually integrated public access).",
}

@INPROCEEDINGS{Mous91:Hybrid,
AUTHOR="M. S. Moustafa and M. I. Marie",
TITLE="Performance of hybrid switching networks with priority: Movable
boundary case",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="194-206",
YEAR=1991,
REFERENCES=5,
KEYWORDS="Hybrid switching; voice/data integration; nonpreemptive
priority; priority",
ANNOTE="This paper deals with performance of hybrid switching networks.
To achieve a better transmission utilization than the fixed boundary
case, data are allowed to use any residual voice capacity available;
i.e., movable boundary case. The voice traffic is treated as a loss
system, while data traffic is considered as multiple classes of
different priorities. Comparison with nonpriority case and fixed
boundary with nonpreemptive priority case is givn",
}

@INPROCEEDINGS{Onoz91:Behaviour,
AUTHOR="Y. Onozato and Jaidev Kaniyil and S. Noguchi",
TITLE="Behaviour characterization of alternate routing in a
non-hierarchical homogeneous network",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=3,
PAGES="141-153",
YEAR=1991,
REFERENCES=13,
KEYWORDS="Alternate routing; homogeneous network; stability;
nonhierarchical network; congestion; blocking",
ANNOTE="A model of non-hierarchical alternate routing scheme in a
homogeneous fully connected network is formulated. The state variable of
the system is considered to be the blocking prob. From the dynamic flow
consideration principles, a Liapunov function which dictates the
dynamics of a perturbed system is found out. The results of catastrophe
theory can be applied on the model to estimate the value of control
parameter exceeding which congestion spr",
}

@INPROCEEDINGS{Pior91:Telecom,
AUTHOR="M. Pioro and M. de Miguel and I. Pita",
TITLE="Telecom networks evolution towards secure dynamic structures
Routing Aspects of the Network Digitization",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=3,
PAGES="1-12",
YEAR=1991,
REFERENCES=12,
KEYWORDS="Dynamic routing; alternate routing; network management;
digital network; random routing",
ANNOTE="A natural scenario for the digitization of PSTN leads to a
two-level network structure. The digital upper transit level will
provide an excellent environment for some kind of dynamic routing. In
the paper a way of introducing dynamic routing to such transit networks
is discussed in order to achieve efficiency in traffic routing at
minimum cost.",
}

@INPROCEEDINGS{Pope91:Alternative,
AUTHOR="A. Popescu and R. Singh",
TITLE="An Alternative Solution to the Electro-Optic and Service
Bottleneck Problems in Multi Gbit/s {LANs:} the {SUPERLAN}
Architecture",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="27-37",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Bottleneck; WDM; wavelength division multiplex; access
control; access protocol",
ANNOTE="The two main bottleneck problems in the design of integrated
multi Gbit/s LANs are examined; the electro-optic and the service
bottleneck problem. A novel archtitectural solution is proposed that
makes use of the WDM-principle. It is based on a multiclass network
model in which the total traffic on the fiber is separated into two
classes - isochronous and nonisochronous - each carried on a separate
wavelength at multi Gbit/s rates.",
}

@INPROCEEDINGS{Rich91:Rapid,
AUTHOR="Philip Richards",
TITLE="Rapid Service Delivery and Customization in a Developing Network
Infrastructure",
BOOKTITLE="ITC Specialists Seminar, Telecommunication services for
developing economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="12-23",
YEAR=1991,
REFERENCES=6,
KEYWORDS="IN; intelligent network; CCITT; standardization",
ANNOTE="This paper examines the role of the IN in the modernization of a
developing network infrastructure to provide advanced services. An
overview of the IN capability Set 1 is given as currently being defined
in SG XI of CCITT.",
}

@INPROCEEDINGS{Roos91:Optimization,
AUTHOR="A. H. Roosma",
TITLE="Optimization of {ATM} multi-service-networks - some early
investigations",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="118-129",
YEAR=1991,
REFERENCES=29,
KEYWORDS="ATM; network planning; network design; model; optimization",
ANNOTE="The paper explores the optimal dimensioning of future ATM
multiservice networks. It investigates the important characteristics of
these networks, as far as they are already standardized. Existing models
for optimization of circuit-switched networks are analysed. Some
indications are given to adapt such models to deal with the specific
characteristics of ATM networks.",
}

@INPROCEEDINGS{Rose91:Models,
AUTHOR="C. Rosenberg and A. Le Bon",
TITLE="Performance Models for Hybrid Broadband Networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="208-219",
YEAR=1991,
REFERENCES=8,
KEYWORDS="Broadband; network; hybrid switching; BISDN; ATM;
decomposition; voice/data integration",
ANNOTE="A model is presented for the performance analysis of hybrid
broadband networks in which multi-rate circuit switched traffic as well
as fast packet switched data traffic compete for the use of $N$ slots or
channels. The novelty is that the authors allow for several classes of
circuit switched traffic based on the number of channels required as
well as obtain approximations based on temporal decompositions due to
the different time scales present.",
}

@INPROCEEDINGS{Ryde91:Overload,
AUTHOR="T. Ryden and G. Lindgren",
TITLE="Overload control of {SPC} switches using optimal alarming",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="231-239",
YEAR=1991,
REFERENCES=5,
KEYWORDS="Overload control; SPC; central server; FIFO; queueing network;
arrival process; Markov chain; optimal control",
ANNOTE="In 1980 a theory was developed how to construct optimal alarms
for unwanted events in stochastic processes. This paper describes how
this theory can be used to derive load regulators for SPC-switches. The
new regulators are calculated to optimize the sationary performance of
the switch, but transient properties are also studied.",
}

@INPROCEEDINGS{Saks91:Traffic,
AUTHOR="V. R. Saksena and T. J. Schonfeld",
TITLE="Traffic management of corporate utility networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="47-57",
YEAR=1991,
REFERENCES=7,
KEYWORDS="Traffic engineering; network management; backbone network",
ANNOTE="The paper describes the traffic management function for
corporate utility networks. As users move towards consolidating multiple
applications and protocols on a common backbone network, the task of
network management and control becomes quite complex. An overall
framework for traffic management is proposed and key issues central to
an effective functional architecture are emphasized.",
}

@INPROCEEDINGS{Salz91:Communication,
AUTHOR="F. J. M. Salzborn",
TITLE="The Communication spanning tree problem: an heuristic algorithm",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="70-79",
YEAR=1991,
REFERENCES=6,
KEYWORDS="Tree network; algorithm; topological design; star network;
network planning; traffic matrix",
ANNOTE="The problem considered here is that of finding minimum cost
communication spanning trees, assuming that the cost of the tree is
equal to the sum of the cost of its links and that the cost of each link
is proportional to the traffic carried on that link. The cost of a link
is actually taken to be the length of the link mulitplied by the traffic
carried. An heuristic algorithm is discussed that appears to give good
results.",
}

@INPROCEEDINGS{Schm91:Traffic,
AUTHOR="J. A. Schmitt",
TITLE="Traffic modeling in networks with incomplete data",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="165-176",
YEAR=1991,
REFERENCES=5,
KEYWORDS="Traffic model; alternate routing; adaptive routing;
hierarchical network",
ANNOTE="The paper describes an algorithm that infers a set of direct
traffic demands between switches that can be routed an a given alternate
routing network with specified trank group sizes. The theoretical basis
of the algorithm and the bounds on the nonunique solutions (traffic
demands) are developed.",
}

@TECHREPORT{Tubt91:Method,
AUTHOR="A. Tubtiang and H. I. Kwon and",
TITLE="A Method for Classification of {ATM} Switches",
TYPE="Research Report",
INSTITUTION="Institut Blaise Pascal, Universite Paris VI",
ADDRESS="Paris",
NUMBER="MASI 91.63",
PAGES=13,
YEAR=1991,
REFERENCES=17,
KEYWORDS="ATM; switching system; architecture; classification; Banyan
network; DQDB",
}

@INPROCEEDINGS{Veir91:Generalised,
AUTHOR="Bio Veiro",
TITLE="Generalised Karlsson measurement for {ATM} networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="201-207",
YEAR=1991,
REFERENCES=19,
KEYWORDS="Measurement; ATM; traffic source model",
ANNOTE="A brief review of the procedure of generalized Karlsson
measurement is given. Some source models for real coded video data are
given, but it turns out, that only simulation will be accurate enough to
assess the generalized Karlsson measurements and a simulation study the
shows, that the procedure works well.",
}

@INPROCEEDINGS{Vese91:Comparison,
AUTHOR="G. G. Veselovsky and M. V. Kupryanova",
TITLE="Comparison of some combinatorial properties of direct and
indirect binary $n$-cube interconnection networks",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="79-90",
YEAR=1991,
REFERENCES=5,
KEYWORDS="Interconnection network; hypercube; shuffle exchange",
ANNOTE="The combinatorial features of the two main types of $n$-cube
networks are compared. Investigations are carried out for perfect
shuffle, cyclic shift with amplitude a, bit reversal and flip
permutation. Analysis is done with number theory methods. The conditions
under which conflicts in the networks occur are formulated.",
}

@INPROCEEDINGS{Vill91:Accelerated,
AUTHOR="M. Villen-Altamirano and J. Villen-Altamirano",
TITLE="Accelerated simulation of rare events using {RESTART} method with
hysteresis.",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="240-251",
YEAR=1991,
REFERENCES=4,
KEYWORDS="Simulation; simulation model; ATM; output analysis",
ANNOTE="RESTART (REpetitive Simulations Trials After Reaching
Threshold)is a method for accelerating simulations to estimate the
probability of rare events. It allows dramatic reduction of simulation
time for an equal confidence of results.",
}

@INPROCEEDINGS{Wern91:Architecture,
AUTHOR="Marek R. Wernik and R. Kositpaiboon and P. Carbone",
TITLE="Architecture and Control Aspects of Data Service Evolution to
Broadband",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="36-46",
YEAR=1991,
REFERENCES=14,
KEYWORDS="Architecture; ATM; broadband; frame relay; BISDN",
ANNOTE="This paper addresses Virtual Data Network (VDN) service and
technology evolution to broadband. The BISDN protocol enabling Frame
Relay service evolution to broadband VDN is then proposed with emphasis
on the use of the ATM network for Frame Relay trunking and on
interworking aspects. The traffic management and control requirements
enabling evolution from Frame Relay service to broadband VDN are further
discussed.",
}

@INPROCEEDINGS{Wozn91:Study,
AUTHOR="J. Wozniak",
TITLE="Study of {S-ALOHA} packet radio networks with a split-channel
cinfiguration",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="103-113",
YEAR=1991,
REFERENCES=9,
KEYWORDS="ALOHA; slotted ALOHA; MAN; WAN; Petri net; Markov chain;
throughput analysis; buffer",
ANNOTE="The study of an S-ALOHA packet radio network is presented that
employs a split-channel configuration. In particular two station
operational schemes are investigated with almost instantaneous
acknowledgements. The stations be equipped with buffers assigned to
local and transit packets and their copies. Applying an approximate
Markov chain approach the behaviour of station buffers and the station
throughput - delay performances are analysed.",
}

@INPROCEEDINGS{Yoko91:Study,
AUTHOR="Tetsuya Yokotani and H. Sato and S. Nakatsuka",
TITLE="A Study on Performance Improvement Algorithm in {DQDB} {MAN}",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=2,
PAGES="38-49",
YEAR=1991,
REFERENCES=6,
KEYWORDS="DQDB; MAN; access protocol; M/G/1; waiting time; transmission
delay",
ANNOTE="Performance improvement algorithm in DQDB MAN is proposed. At
first, a special node called erasure node is introduced in DQDB network
for slot reultilization in downstream side and the operation of erasure
node is described. In the latter half the performance of this algorithm
is estimated using a queueing model, where M/G/1 is applied to the
network model. Average and variance of queueing and transmission delay
are calculated by this meth",
}

@INPROCEEDINGS{Yosh91:End,
AUTHOR="H. Yoshino and Y. Hoshiai",
TITLE="End-to-End Blocking in an Integrated Services Network with Link
Capacity Allocation Control",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=3,
PAGES="131-140",
YEAR=1991,
REFERENCES=6,
KEYWORDS="Alternate routing; blocking; BISDN; controlled access; model;
overflow traffic; traffic mix; arrival process; Poisson process;
stability",
ANNOTE="At first the imbalance and bistable behaviour of individual
end-to-end blocking probabilities without control for a multi-class
network model are shown. To prevent these effects link capacity
allocation control is introduced. The effects of this control on a
nonhierarchical alternate routing network are clarified by approximate
analysis for various traffic mixes and allocation control parameters.",
}

@INPROCEEDINGS{Zhan91:New,
AUTHOR="Z. Zhang",
TITLE="New Technique for Queueing Analysis with Markovian Arrivals and
Services in {BISDNs}",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow",
VOLUME=1,
PAGES="104-117",
YEAR=1991,
REFERENCES=15,
KEYWORDS="BISDN; Markov chain; queue length; arrival process; finite
buffer",
ANNOTE="A new, efficient computational procedure to calculate the queue
size of distribution in a queueing system with a number of independent
sources is presented. Each source is characterized by a finite state
discret-time Maikov chain. The service process can be Markovian as well.
Explicit expression for the queue size distribution is obtained
directly. The method is based on computing the spectral expansion of the
state distribution of the system.",
}

@ARTICLE{Akyi91:Moment,
AUTHOR="Ian Akyildiz and J. C. Strelen",
TITLE="Moment Analysis for Load-Dependent Mixed Product Form Queueing
Networks",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=6,
PAGES="828-832",
YEAR=1991,
KEYWORDS="Queueing theory; product form; moment approximation",
ANNOTE="A solution algorithm is developed for higher moments of the
number of jobs at the stations in load-dependent mixed product form
queueing networks. A relationship is proved and applied between the
derivatives of these moments and higher moments. Thederivative measures
are calculated using a mean value analysis type algorithm called. Moment
analysis enables the computation of second moments, variances and
covariances.",
}

@ARTICLE{Ganz91:Satellite,
AUTHOR="A. Ganz and G. Karmi",
TITLE="Satellite Clusters: A Performance Study",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=5,
PAGES="747-757",
YEAR=1991,
KEYWORDS="Satellite radio; ALOHA; performance evaluation; TDMA; time
division multiple access",
ANNOTE="In this paper, we present a performance study of two on-board
stored, baseband switched, TDMA satelites interconnected
throughintersatellite links. The uplinks are operated under the
slottedALOHA policy, while the downlinks and intersatellite links are
operated employing TDM policy. Each satellite has a finite buffer
capacity for successful packets arriving on the uplinks and on the
intersatellite links.",
}

@ARTICLE{Humb91:Another,
AUTHOR="Pierre A. Humblet",
TITLE="Another Adaptive Distributed Shortest Path Algorithm",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=6,
PAGES="995-1003",
YEAR=1991,
KEYWORDS="Routing; shortest path; algorithm",
ANNOTE="We give a distributed algorithm to compute shortest paths in a
network with changing topology. It does not suffer from the routing
table looping behavior associated with the Ford-Bellman distributed
shortest path algorithm although it uses truly distributed processing.
Its time and message complexities are evaluated.",
}

@ARTICLE{Onun91:CSMA,
AUTHOR="J. O. Onunga and R. W. Donaldson",
TITLE="Performance Analysis of {CSMA} with Priority Acknowledgements
{(CSMA/PA)} on Noisy Data Networks with Finite User Population",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=7,
PAGES="1088-1096",
YEAR=1991,
KEYWORDS="Multiple access; CSMA/PA; acknowledgement; priority;
performance evaluation",
ANNOTE="Carrier sense multiple access with priority acknowledgments
enables information and acknowledgement packets to efficiently share a
common channel. We develop an analytical procedure to calculate delay
and throughput performance of CSMA/PA. Time-axis slotting and Markov
chain analysis are used to determine the channel backlog per cycle. A
cycle includes INFO packet access and transmission time followed by ACK
transmission",
}

@ARTICLE{Rama91:Delay,
AUTHOR="G. Ramamurthy and B. Sengupta",
TITLE="Delay Analysis of a Packet Voice Multiplexer by the Su Di/D/1
queue",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=7,
PAGES="1107-114",
YEAR=1991,
KEYWORDS="Communication network; waiting time; packet voice;
multiplexer; DI/D/1",
ANNOTE="We study the performance of a statistical multiplexer whose
inputs consist of a superposition of voice packets from trunks. Voice
calls are established according to a Poisson process and call holding
times have a general distribution. Each voice call, while in progress,
generates packets at a fixed intervals of deltha.",
}

@ARTICLE{Rubi91:Message,
AUTHOR="I. Rubin and Z. Zhang",
TITLE="Message Delay and Queue-Size Analysis for Circuit-Switched {TDMA}
Systems",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=6,
PAGES="905-914",
YEAR=1991,
KEYWORDS="Multiple access channel; TDMA; time division multiple access",
ANNOTE="We consider a multiple-access communications channel which is
shared among network stations using a circuitswitched TDMA scheme. Each
station is allocated a fixed number of slots duringeach frame. A station
provides access to the channel for its sessions, by assigning to a ready
session one of its dedicated circuits, for the total duration of the
session.",
}

@ARTICLE{Wong91:Controlled,
AUTHOR="Eugene Wong and T. S. Yum",
TITLE="A Controlled Multiaaccess Protocol for Packet Satellite
Communication",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=7,
PAGES="1133-1140",
YEAR=1991,
KEYWORDS="Satellite radio; packet switching; ALOHA; multiple access",
ANNOTE="A controlled multiaccess protocol for packet satellite
communication is introduced and analyzed in this paper. This protocol is
fully distributed and no on-board processing is required for the
satellite. A control parameter is used to adaptively control the packet
transmission rate such that maximum system capacity can be attained and
the average delay isalways minimized for a given throughput.",
}

@ARTICLE{Yue91:Effect,
AUTHOR="W. Yue",
TITLE="The Effect of Capture on Performance of Multichannel Slotted
{ALOHA} Systems",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=6,
PAGES="818-822",
YEAR=1991,
KEYWORDS="Satellite radio; ALOHA; performance evaluation; multiple
access",
ANNOTE="In this paper, we present an exact analysis to evaluate the
effect of capture on multichannel slotted ALOHA protocol. We derive the
probabilities of the successful transmission, then by using these
probabilities, we calculate the throughputs, average packet delays for
both IFT and DFT protocols and numerically compare the performances of
the systems to and without capture.",
}

@INPROCEEDINGS{Bodn91:Synthetic,
AUTHOR="R. R. Bodnarchuk and R. B. Bunt",
TITLE="A Synthetic Workload Model for a Distributed System File Server",
BOOKTITLE=sigmetrics,
ADDRESS="San Diego, California",
PAGES="50-59",
YEAR=1991,
REFERENCES=12,
KEYWORDS="LAN; traffic measurement; traffic model; file server",
ANNOTE="The goal of the paper is to model the workload of a distributed
system file server in a UNIX/NFS environment.",
}

@INPROCEEDINGS{Gerl91:Interconnecting,
AUTHOR="M. Gerla and T.-Y. Tai and José Augusto Suruagy Monteiro and
Giorgio Gallassi",
TITLE="Interconnecting {LANs} and {MANs} to {ATM}",
BOOKTITLE=lcn,
ADDRESS="Minneapolis, Minnesota",
PAGES="259-270",
YEAR=1991,
REFERENCES=15,
KEYWORDS="ATM; connectionless service; LAN; MAN; interconnection;
bandwidth allocation",
ANNOTE="The authors focus on the problem of bandwidth management for the
VPs within the ATM network connecting the gateways to each other.",
}

@INPROCEEDINGS{Mong91:Proposal,
AUTHOR="L. Mongiovi and M. Farrell and V. Trecordi",
TITLE="A Proposal for Interconnecting {FDDI} Networks Through {BISDN}",
BOOKTITLE=infocom,
ADDRESS="Bal Harbour, Florida",
PAGES="10B.4",
YEAR=1991,
REFERENCES=17,
KEYWORDS="ATM; FDDI; interconnection; gateway; bandwidth allocation;
virtual channel",
ANNOTE="This paper investigates the problem of a transparent
interconnection of remote FDDI networks through BISDN. They propose a
hybrid interworking method that keeps connectionless transfer mode on
FDDI and a connection oriented mode on BISDN. The major focus is on a
bandwidth allocation algorithm that allows the remote gateways to size
the transmission bandwidth on the BISDN virtual connections according to
the traffic needs.",
}

@TECHREPORT{Paxs91:Measurements,
AUTHOR="V. Paxson",
TITLE="Measurements and Models of Wide Area {TCP} Conversations",
INSTITUTION="Department of Computer Systems Engineering, University of
California",
ADDRESS="Berkeley, California",
PAGES=43,
YEAR=1991,
REFERENCES=16,
KEYWORDS="LAN; traffic measurement; traffic model",
ANNOTE="This paper describes measurements of all of the wide area
network TCP conversations between the Lawrence Berkeley Lab. (LBL) and
the rest of the world for the months of Nov., 1990, and March, 1991.",
}

@INPROCEEDINGS{Dirk91:Development,
AUTHOR="P. Dirke and P. Lindberg",
TITLE="Development and application of the analytical method for planning
dependability (reliability)",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="273-278",
YEAR=1991,
REFERENCES=4,
KEYWORDS="Network planning; circuit switching; forecasting; economic
evaluation; reliability",
ANNOTE="The analytical method for planning dependability (reliability,
maintainability and maintanance support) is shown. The level of
dependability is dimensioned according to cost-benefit analysis. A
simple method for predicting the impact on revenue is derived, taking
the market situation and different principles for setting rates and
charges into account.",
}

@INPROCEEDINGS{Gopa91:Algorithms,
AUTHOR="G. Gopal and C. Kim and A. Weinrib",
TITLE="Algorithms for reconfigurable networks",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="341-347",
YEAR=1991,
REFERENCES=15,
KEYWORDS="Network design; logical network structure; cross connect;
network topology; network optimization",
ANNOTE="A reconfigurable network, one which can change logical networks
dynamically, has been emerging as a promising design for network
resiliency under traffic changes and physical facility failures. We
investigate configuration management and optimal logical network design
for reconfigurable networks. We define the underlying constraint
optimization problem and develop a heuristic solution technique.",
}

@INPROCEEDINGS{Harr91:Mathematical,
AUTHOR="R. J. Harris",
TITLE="A mathematical programming model for service protection in a
telecommunications network",
BOOKTITLE=itc13,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="225-229",
YEAR=1991,
REFERENCES=1,
KEYWORDS="Network planning; circuit switching; channel assignment;
protection",
ANNOTE="The paper describes a mathematical model for assigning channels
in the event of node or link failures. This is done by throughput
optimization resulting in a linear programming problem.",
}

@INPROCEEDINGS{Kami91:Capacity,
AUTHOR="K. Kamimura and H. Nishino",
TITLE="Capacity and flow assignment of packet-switched networks with a
concave line cost function",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="285-290",
YEAR=1991,
REFERENCES=14,
KEYWORDS="Network planning; packet switching; flow optimization; network
design",
ANNOTE="The packet-switched network design is formulated as a capacity
and flow assignment problem with concave line-cost strukture. Efficient
methods for obtaining the global optimum or a good local minimum are
introduced by confining attention to a class of hierarchical networks
which consists of elementary networks. A basic iterative procedure
obtains the global optimum of the elementary networks within finite
iterations.",
}

@INPROCEEDINGS{Kani91:Unified,
AUTHOR="Jaidev Kaniyil and Y. Onozato and S. Noguchi",
TITLE="A unified approach towards characterization of structural
stabilities in telecommunication networks",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="253-256",
YEAR=1991,
REFERENCES=17,
KEYWORDS="Network stability; alternate routing; random multiple access",
ANNOTE="A rewiew of some recent results on studies on the properties of
stability associated with the dynamic flows in different network schemes
such as input buffer limiting, nonhierarchical alternate routing and
combined random-reservation multiple access schemes.",
}

@INPROCEEDINGS{Key91:Highly,
AUTHOR="P. B. Key and A. Elvidge",
TITLE="Design and analysis of a highly reliable transmission network",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="323-328",
YEAR=1991,
REFERENCES=15,
KEYWORDS="Network design; network planning; availability; reliability",
ABSTRACT="In this paper we comment on existing methods of calculating
network availibility measures, and present a new analytic technique
which ca model rerouting strategies, as well as the present link-based
protection techniques.",
}

@INPROCEEDINGS{Kono91:Throughput,
AUTHOR="J. Konorski",
TITLE="Throughput of a packet-switching network under a class of
store-and-foreward deadlock prevention mechanisms",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="297-302",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Packet switching; deadlock prevention; analysis",
ANNOTE="In the paper an approximate stochastic analysis of store-and
forward deadlocks in packet switched networks is carried out. Structered
buffer pools, circulating token and erasable packet controllers are
analysed to demonstrate the need of combining the controller with a
proerly designed congestion control mechanismen.",
}

@INPROCEEDINGS{Kouv91:Queueing,
AUTHOR="D. D. Kouvatsos and P. H. Georgatsos",
TITLE="Queueing models of packet-switched networks with locally adaptive
routing",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="303-308",
YEAR=1991,
REFERENCES=9,
KEYWORDS="Packet switching; closed queueing network; open queueing
network; adaptive routing; product form",
ANNOTE="A universal framework is presented for the approximate analysis
of general queueing networks models of packet-switched networks. The
network is modeled as a collection of nodel queueing systems each of
which consists of a set of outgoing channel queues and a node
dispatching the incomming traffic to these queues according to a local
adaptive routing policy. Product-form approximations for the queue
length of open and closed networks are given.",
}

@INPROCEEDINGS{Liu91:ISDN,
AUTHOR="Feng Liu and D. Seagraves",
TITLE="An {ISDN} application-simulation modeling of {NACD}",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="279-284",
YEAR=1991,
REFERENCES=2,
KEYWORDS="ISDN; simulation; ACD; automatic call distribution",
ANNOTE="Network automatic call distribution utilizes the ISDN standard
as a vehicle to effectively distribute calls betwen ACD sites. The
performance of a network with NACD application is simulated, taking into
account an alternative routing scheme and a flow control mechanismen.",
}

@INPROCEEDINGS{Luba91:Effectiveness,
AUTHOR="J. Lubacz and A. Tomaszewski",
TITLE="Effectiveness vs. controllability in traffic engineering",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="267-272",
YEAR=1991,
KEYWORDS="Traffic control; blocking; circuit switching; discrete time
analysis; loss probability",
ANNOTE="The paper concerns modelling the performance of teletraffic
systems in fixed-length sequences (windows) of consequtive service
demands acceptance/rejection decisions. The presented results are
focused on evaluating and controlling the distribution of losses in a
window. The proposed methodology employes a combination of discrete-time
Markov propcesses of order K>0 and simulation.",
}

@INPROCEEDINGS{Mili91:Dynamic,
AUTHOR="Rodolfo Milito and Y. Levy and Y. Arian",
TITLE="Dynamic algorithms for distributed queues with abandonments",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="329-324",
YEAR=1991,
REFERENCES=12,
KEYWORDS="Dynamic routing; distributed system",
ANNOTE="The paper considers the problem of distributing traffic to mult
iple parallel queues based on inclomplete and possible inaccuratstate
information. This problem arises in the context of intelligent networks
where large customers rely on the network for traffic distribution to
multiple locations. The problem is solved through a revenue-driven
Markovian decision model.",
}

@INPROCEEDINGS{Morr91:Prospects,
AUTHOR="R. M. Morris",
TITLE="Prospects for neural networks in broadband resource management",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="335-338",
YEAR=1991,
REFERENCES=46,
KEYWORDS="Congestion control; neural network; dynamic resource
allocation; connection admission control",
ANNOTE="The prospects for application of emerging neural network
technology to the problems of broadband network resource management are
explored. We identify two particulary appropriate attributes of neural
networks, namely adaptivity and high speed. We describe a new method of
admission control using a neural network controller.",
}

@INPROCEEDINGS{Pach91:Technique,
AUTHOR="A. R. Pach",
TITLE="A technique for calculation of the optimal timeout for the class
4 transport protocol in a packet switched network",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="291-296",
YEAR=1991,
REFERENCES=9,
KEYWORDS="Packet switching; transport layer; delay time; delay
analysis",
ANNOTE="A simple method of calculation of the optmal timeout for the
class 4 transport protocol in a packet switched network is presented.
The optimal timeout minimizes a number of performancemeasures such as
average TSDU and DT TPDU transit delay, TSDU reassembly time or their
variances. The analysis has been carried out under the assumption that
the network service is of a virtual-circuit type.",
}

@INPROCEEDINGS{Pham91:Control,
AUTHOR="X. H. Pham",
TITLE="Control loop for traffic management of network under focussed
overload",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="315-322",
YEAR=1991,
REFERENCES=11,
KEYWORDS="Circuit switching; overload control; leaky bucket; network
management",
ANNOTE="This paper describes an effective dynamic control loop to ensure
a stable and good GOS under focussed overload. Qualitative and
quantitative influences on the declination of network goodness will be
studied. Network performance deterioration is classified into distinct
congestion types. Control through Call Gapping and Leaky Bucket
principles will be analaysed and compared. Simulation results are
presented.",
}

@INPROCEEDINGS{Ueda91:Demand,
AUTHOR="T. Ueda",
TITLE="Demand forecasting models for markets with competition",
BOOKTITLE=itc13,
ISBN=0444888664,
ADDRESS="Copenhagen",
VOLUME=14,
PAGES="261-265",
YEAR=1991,
REFERENCES=16,
KEYWORDS="Network planning; forecasting",
ANNOTE="This paper introduces a competitive Bass model efficient for
competitive markets. The model takes into account inoovative and
competitive affects. The estimation procedures for regression
coelficients are shown. Three models are compared, one of them takes
into account the increase of potential adopters.",
}

@ARTICLE{Kivi91:Simulation,
AUTHOR="P. J. Kiviat",
TITLE="Simulation, technology, and the decision process",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=2,
PAGES="89-98",
YEAR=1991,
KEYWORDS="Simulation; survey",
ANNOTE="Keynote address at 1990 WSC",
}

@ARTICLE{Tezu91:Efficient,
AUTHOR="S. Tezuka and P. L'Ecuyer",
TITLE="Efficient and portable combined Tausworthe random number
generator",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=2,
PAGES="99-112",
YEAR=1991,
REFERENCES=26,
KEYWORDS="RNG; Tausworthe generator; survey; SR",
ANNOTE="We propose three combined Tausworthe RNGs with period length
about $10^18$, whose $k$-distribution properties are good and which can
be implemented in a portable way.",
}

@ARTICLE{Luba91:Rollback,
AUTHOR="B. D. Lubachevsky and A. Weiss and A. Shwartz",
TITLE="An analysis of rollback-based simulation",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=2,
PAGES="154-193",
YEAR=1991,
REFERENCES=30,
KEYWORDS="Distributed simulation; rollback; parallel computing",
ANNOTE="We present and analyze a general model of rollback in parallel
processing. We identify the parameters that determine a stability or
efficiency region for the simulation.",
}

@ARTICLE{Bach91:Architektur,
AUTHOR="W. Bachhuber and W. Fürst and R. Knorr and T. Wild",
TITLE="Architektur, Technologie und Realisierung eines
{ATM-Koppelnetzes}",
JOURNAL="ITG/GI Workshop Verbindungsnetzwerke für Parallelrechner und
Breitband-übermittlungssysteme",
ADDRESS="Stuttgart",
PAGES="48-52",
YEAR=1991,
LANGUAGE="German",
REFERENCES=5,
KEYWORDS="ATM; switching network; buffer management; output buffer;
central buffer; architecture; implementation; VLSI; priority",
ANNOTE="Nachfolgend werden zwei Prinzipien für ATM-Koppelvielfache -
ausgangsgepufferte Matrix und Zentralspeicher - vorgestellt und
hinsichtlich der Implementierung miteinander verglichen.",
}

@ARTICLE{Bern91:Effiziente,
AUTHOR="E. Bernath and T. Schwederski and M. Siegel and J. Wenzel",
TITLE="Effiziente {VLSI-Strukturen} für mehrstufige
Verbindungsnetzwerke",
JOURNAL="ITG/GI Workshop Verbindungsnetzwerke für Parallelrechner und
Breitband-übermittlungssysteme",
ADDRESS="Stuttgart",
PAGES="53-58",
YEAR=1991,
LANGUAGE="German",
REFERENCES=10,
KEYWORDS="ATM; switching network; buffer management; central buffer;
architecture; implementation; VLSI; simulation; performance evaluation",
ANNOTE="Anhand von Simulationen wurden optimale Parameter für ein 4x4
Koppelelement mit Zentralspeicher ermittelt. Ein Prototyp des
Koppelelementes kann 8-Byte Pakete mit 25Mhz Byte-Taktrate vermitteln,
und erlaubt eine maximale Last von 70\% bei gleichverteiltem Verkehr.
Die Paketpufferspeicher werden mittels dynamischer Schieberegister
implementiert, und die hohen Anforderungenan die Speicherbandbreite
werden durch verteilte Eingangs- und",
}

@ARTICLE{Chao91:Architecture,
AUTHOR="Hung-Po Chao and S. C. Liew",
TITLE="Architecture Design for {ATM} Statistical Multiplexers",
JOURNAL="International Journal of Digital and Analog Communication
Systems",
VOLUME=4,
NUMBER=4,
PAGES="237-248",
YEAR=1991,
REFERENCES=23,
KEYWORDS="ATM; BISDN; statistical multiplexer; architecture; design;
buffer management; input buffer; output buffer; central buffer; buffer
dimensioning; simulation; bursty traffic",
ANNOTE="The main function of a statistical multiplexer is to
concentratetraffic from a number of input ports to a smaller number of
out-put ports; switching in the sense that a cell must be delivered to a
specific output port is often not required. This implies that the
channel grouping design principle, in which more than one path is
available for each virtual circuit connection, can be applied in the
multiplexer. This technique reduces the",
}

@INPROCEEDINGS{Chen91:Shared,
AUTHOR="Xiaopeng Chen and J. F. Hayes",
TITLE="A Shared Buffer Memory Switch with Maximum Queue and Minimum
allocation",
BOOKTITLE="Canadian Conference on Electrical and Computer Engineering",
ADDRESS="Quebec",
PAGES="7.1.1-7.1.4",
YEAR=1991,
REFERENCES=8,
KEYWORDS="ATM; switching; architecture; central buffer; analysis;
performance evaluation; approximation; loss probability; unbalanced
traffic",
ANNOTE="A shared buffer memory switch architecture is proposed. In this
switch, a shared buffer pool and a dedicated buffer pool are properly
handled for switching and buffering the packets. Being able to prevent
monopolizing the use of the shared buffers and to secure a full
utilization of all the $N$ output channels, the sharing policy with
maximum queue and minimum allocation provides good traffic
characteristics, esp. under bursty traffic.",
}

@INPROCEEDINGS{Chen91:One,
AUTHOR="Xiaopeng Chen and J. F. Hayes and M. K. Mehmothersi",
TITLE="A One-Shot Access Scheme for a Multicast Switch",
BOOKTITLE="Canadian Conference on Electrical and Computer Engineering",
ADDRESS="Quebec",
PAGES="7.2.1-7.2.4",
YEAR=1991,
REFERENCES=7,
KEYWORDS="ATM; packet switching; multicast; switching; input buffer;
performance evaluation; analysis",
ANNOTE="The analysis is based on the assumption of random traffic,
modeled by a Bernoulli process of packet arrival and a Bernoullitrials
of copy distribution pattern. Input port queueing along with random
selection policy is used to resolve the output request conflict. The
primary performance measurement is the packet delay. A key assumption is
that all copies of the same packet must be switched in the same slot.",
}

@ARTICLE{DAmb91:ATM,
AUTHOR="M. D'Ambrosio and R. Melen",
TITLE="Performance Analysis of {ATM} Switching Architectures: A Review",
JOURNAL="Performance Evaluation and Design of Multiservice Networks,
COST 224 Seminar",
ADDRESS="Paris",
YEAR=1991,
REFERENCES=74,
KEYWORDS="ATM; switching; architecture; performance evaluation; survey;
input buffer; output buffer; central buffer; bursty traffic; multistage
interconnection network",
ANNOTE="The objective of this paper is to give a brief outline of the
state of the art in the field of the performance evaluation of ATM
switching architectures.",
}

@ARTICLE{Heek91:Statistical,
AUTHOR="H. Heeke",
TITLE="Statistical Multiplexing Gain for Variable Bit Rate Video Codecs
in {ATM} Networks",
JOURNAL="International Journal of Digital and Analog Communication
Systems",
VOLUME=4,
NUMBER=4,
PAGES="261-268",
YEAR=1991,
REFERENCES=11,
KEYWORDS="ATM; packet video; video coding; statistical multiplexing;
congestion control; measurement; loss probability",
ANNOTE="A gain in transmission efficiency is expected when several
videosources share a common ATM channel ('statistical
multiplexing').This paper reports on a series of measurements that have
been performed using a large variety of video sources to determine the
possible gain in transmission efficiency. For realistic video phone
scenes, up to three times the number of signals can be transmitted
compared to CBR transmission at the same quality",
}

@INPROCEEDINGS{Henr91:ALCATEL,
AUTHOR="M. A. Henrion",
TITLE="{ALCATEL} {ATM} Switch Fabric and its Network Applications",
BOOKTITLE="6th World Telecommunication Forum",
ADDRESS="Geneva",
PAGES="259-263",
YEAR=1991,
REFERENCES=6,
KEYWORDS="ATM; switching network; architecture; self routing; multistage
interconnection network; central buffer",
}

@TECHREPORT{Holt91:Leaky,
AUTHOR="D. S. Holtsinger and Harry Perros",
TITLE="Performance Analysis of Leaky Bucket Policing Mechanisms",
INSTITUTION="Department of Computer Science, North Carolina State
University",
ADDRESS="Raleigh",
NUMBER="TR-91-28",
PAGES=35,
YEAR=1991,
REFERENCES=18,
KEYWORDS="ATM; policing function; leaky bucket; output process; bursty
traffic; MMBP; analysis",
ANNOTE="In this paper, we examine the efficacy of the Leaky Bucket
policing mechanism through the analysis of the mean and squared
coefficient of variation of the interdeparture time of cells from the
Leaky Bucket, assuming that the arrival process is a two-state MMBP. We
show that the Leaky Bucket can either be configured to restrict the mean
rate or the burstiness of theexcess traffic, but not both
simultaneously.",
}

@ARTICLE{Lin91:Priority,
AUTHOR="A. Y. Lin and J. A. Silvester",
TITLE="Priority Queueing Strategies and Buffer Allocation Protocols for
traffic Control at an {ATM} Integrated Broadband Switching System",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=9,
PAGES="1524-1536",
YEAR=1991,
REFERENCES=30,
KEYWORDS="ATM; BISDN; traffic control; priority; loss probability;
survey; performance evaluation; analysis; batch arrival; Markov chain;
multiserver",
ANNOTE="We consider several different loss priority queueing strategies,
differing in the degree of resource sharing, namely complete sharing
with pushout and head-of-the-line, partial buffer sharing, complete
buffer partitioning but complete bandwidth sharing, and complete
partitioning. A rather general multichannel system model taking the
correlation between the two traffic classes into account, is developed
for performance evaluation.",
}

@TECHREPORT{Morr91:Multi,
AUTHOR="T. D. Morris and Harry Perros",
TITLE="Performance Analysis of a Multi-Buffered Banyan {ATM} Switch
Under bursty Traffic",
INSTITUTION="Department of Computer Science, North Carolina State
University",
ADDRESS="Raleigh",
PAGES=30,
YEAR=1991,
REFERENCES=16,
KEYWORDS="ATM; switching network; multistage interconnection network;
Banyan network; buffered Banyan network; output buffer; performance
evaluation; analysis; approximation; bursty traffic; MMBP; unbalanced
traffic",
ANNOTE="We present an analytical model of a buffered Banyan ATM switch
which allows complex switching elements, bursty traffic, non-uniform
destination distributions and permits the analysis of large scale
switches. The results obtained are approximate and validation tests have
shown that they have good accuracy. Using this model, the cell loss,
throughput, and the mean time to traverse the switch were obtained for
different traffic paramete",
}

@ARTICLE{Niu91:Statistical,
AUTHOR="Z. Niu and H. Akimaru",
TITLE="Analysis of Statistical Multiplexer with Selective Cell
Discarding Control in {ATM} Systems",
JOURNAL=ieice_communications,
VOLUME=74,
NUMBER=12,
PAGES="4069-4079",
YEAR=1991,
REFERENCES=41,
KEYWORDS="ATM; statistical multiplexer; priority; bursty traffic; MMPP;
batch arrival; performance evaluation; analysis; matrix analytic
method",
ABSTRACT="The multiplexer integrates delay-sensitive traffic such as
voiceor video and loss-sensitive traffic such as data, for which
cellarrival processes are of bursty nature.  The selective cell
discarding scheme is based on the embedded ADPCM coding technology to
packetize the delay-sensitive information into two kinds of cells: more
significant part (MSP) cells and less significant part (LSP) cells. 
When system congestion occurs, the LSP cells",
}

@ARTICLE{Patt91:ATM,
AUTHOR="Achille Pattavina",
TITLE="An {ATM} Switch Architecture for Provision of Integrated
Broadband services",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=9,
PAGES="1537-1548",
YEAR=1991,
REFERENCES=31,
KEYWORDS="ATM; switching network; architecture; Batcher-Banyan; self
routing; nonblocking; input buffer; output buffer; performance
evaluation; analysis",
ANNOTE="The proposed architecture adopts mixed input-output queueing.
Input queueing is particularly suited to the definition of internal
frame structures, that allows us to guarantee for specific services
absence of cell loss due to congestion. Output queueing makes it
possible to implement in hardware a switching speedup that practically
removes the performance degradation dueto the well-known
head-of-the-line blocking phenomenon typical",
}

@TECHREPORT{Rath91:Policing,
AUTHOR="Erwin P. Rathgeb",
TITLE="Policing of Realistic {VBR} Video Traffic in an {ATM} Network",
TYPE="Technical Memorandum",
INSTITUTION="Bellcore",
NUMBER="TM-ARH-019745",
PAGES=25,
YEAR=1991,
REFERENCES=32,
KEYWORDS="ATM; video service; policing function; leaky bucket; moving
window; jumping window; performance evaluation; simulation; loss
probability",
}

@INPROCEEDINGS{Sato91:Experimental,
AUTHOR="Y. Sato and Naoaki Yamanaka and K. Sato and Nobuyuki. Tokura",
TITLE="Experimental {ATM} Transport System and Virtual Path Management
techniques",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
VOLUME=3,
PAGES="2110-2116",
YEAR=1991,
REFERENCES=25,
KEYWORDS="ATM; virtual path; cross connect; architecture; resource
management; policing function; statistical multiplexing",
}

@ARTICLE{Schw91:Simulative,
AUTHOR="A. Schwarz and T. H. Theimer",
TITLE="Simulative Untersuchungen an einem {ATM-Koppelelement} mit
Zentralspeicher",
JOURNAL="ITG/GI Workshop Verbindungsnetzwerke für Parallelrechner und
Breitband-übermittlungssysteme",
ADDRESS="Stuttgart",
PAGES="95-100",
YEAR=1991,
LANGUAGE="German",
REFERENCES=11,
KEYWORDS="ATM; switching network; buffer management; central buffer;
performance evaluation; simulation; priority; bursty traffic",
ABSTRACT="In diesem Beitrag wird ein 4x4 Koppelelement simulativ
untersucht, das für ATM-Vermittlungen eingesetzt werden soll. Dabeiwurde
die Puffergröße dimensioniert und die Pufferanordnung miteinem
Koppelelement mit Ausgangspuffern verglichen.  Außerdem wurde das
Zentralspeicherverhalten bezüglich inhomogenem Verkehrsowie die
Prioritätsbehandlung verschiedener Verkehrsklassen untersucht.",
}

@ARTICLE{Shio91:Virtual,
AUTHOR="Shigeo Shioda and H. Uose",
TITLE="Virtual Path Bandwidth Control Method for {ATM} Networks:
Successive Modification Method",
JOURNAL=ieice,
VOLUME=74,
NUMBER=12,
PAGES="4061-4068",
YEAR=1991,
REFERENCES=13,
KEYWORDS="ATM; virtual path; bandwidth allocation; control; performance
evaluation; analysis",
ANNOTE="This paper proposes two new VP bandwidth control algorithms
suitable for distributed implementation. Decentralized controllers are
located at network nodes including ATM switch or cross-connect
functions, and each controller observes the quality of the VP relevant
to it. The bandwidth is modified successively asthese distributed
controllers communicate with each other. Numerical evaluation shows the
effectiveness of these algorithms",
}

@INPROCEEDINGS{Stey91:Effective,
AUTHOR="B. Steyaert and H. Bruneel",
TITLE="An Effective Algorithm to Calculate the Distribution of the
buffer Contents and the Packet Delay in a Multiplexer with Bursty
sources",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
VOLUME=1,
PAGES="471-475",
YEAR=1991,
REFERENCES=9,
KEYWORDS="ATM; statistical multiplexer; finite buffer; bursty traffic;
erformance evaluation; analysis; queue length; delay",
}

@ARTICLE{Toma91:Multiprozessor,
AUTHOR="S. Tomann and R. Holzner",
TITLE="Ein Multiprozessor-Verbindungsnetzwerk mit 8x8
Crossbar-Schaltern",
JOURNAL="ITG/GI Workshop Verbindungsnetzwerke für Parallelrechner und
Breitband-übermittlungssysteme",
ADDRESS="Stuttgart",
PAGES="23-28",
YEAR=1991,
LANGUAGE="German",
REFERENCES=5,
KEYWORDS="ATM; switching network; buffer management; input buffer;
architecture; implementation; VLSI; multistage interconnection network;
multiprocessor system",
ABSTRACT="Der folgende Artikel beschreibt das paketvermittelnde,
mehrstufige Verbindungsnetzwerk eines Parallelrechners, der für
leistungsfähige Datenbankanwendungen entwickelt wurde. Kernstückdes
Netzwerks bildet ein Schaltelement mit der Funktion eines 8x8 Crossbars,
der zusätzlich 32 Zwischenspeicher für Datenpakete anbietet.  Es kann
bis zu 8 Datenpfade gleichzeitig schalten, und findet in einem einzigen
VLSI-Baustein Platz.",
}

@INPROCEEDINGS{Tsuk91:Ultrafast,
AUTHOR="M. Tsukada and Y. Shimazu",
TITLE="Ultrafast Photonic {ATM} Switch Based on Time-Division
broadcast-and-Select Network",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
VOLUME=1,
PAGES="1230-1234",
YEAR=1991,
REFERENCES=10,
KEYWORDS="ATM; fast packet switching; switching network; architecture;
ptical switching; self routing; implementation",
}

@ARTICLE{Dijk91:Truncation,
AUTHOR="N. van Dijk",
TITLE="Truncation of Markov chains with applications to queueing",
JOURNAL=or,
VOLUME=39,
NUMBER=6,
PAGES="1018-1026",
YEAR=1991,
REFERENCES=24,
KEYWORDS="Markovian queueing system; Markov chain; reduction of rank;
overflow; tandem queue; approximation",
ANNOTE="State space truncation is frequently demanded for computation
oflarge or infinite Markov Chains. Conditions are given that guarantee
an error bound or rate of convergence. Roughly, these conditions apply
either when probabilities of large states are sufficiently small, or
when transition probabilities (rates) forstate increases become small in
sufficiently large states. The conditions and their verification are
illustrated by two",
}

@INPROCEEDINGS{Wang91:New,
AUTHOR="Q. R. Wang and Victor S. Frost",
TITLE="A New Solution Technique for Discrete Queueing Analysis of {ATM}
systems",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
VOLUME=1,
PAGES="358-364",
YEAR=1991,
REFERENCES=17,
KEYWORDS="Queueing system; discrete time; multiserver; finite queue;
G/D/1/S; analysis; bursty traffic; correlation; ATM; Markov chain",
ANNOTE="This paper presents a general solution technique for the
discre-te-time queueing analysis of ATM systems. The traffic is
charac-terized as a $r$-dependent Markov modulated phase-type process,
and the queue is assumed to have finite capacity and multiple servers
with fixed service time. The queue is functionally modelled as a
nonlinear feedback loop and a procedure is developed to construct the
stationary equations to determine the",
}

@ARTICLE{Yama91:Control,
AUTHOR="Makoto Yamamoto and H. Tode and H. Okada and Y. Tezuka",
TITLE="A Control-Ahead {ATM} Switch Architecture and its Performance",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=9,
PAGES="1549-1559",
YEAR=1991,
REFERENCES=13,
KEYWORDS="ATM; BISDN; switching block; ring; speedup; output buffer;
architecture; performance evaluation; analysis; simulation; bursty
traffic",
ANNOTE="In this paper, we propose a new ATM switch architecture which
uses the broadcasting transmission medium for transmission of cells from
input to output ports. Cell transmission and its control are separated
completely and cell transmission control, i.e. header operation, is
executed before cell transmission (control ahead). By this operation,
cell transmission and its control can be executed in pipeline style.
This enables",
}

@INPROCEEDINGS{Yin91:Leaky,
AUTHOR="Nanying Yin and M. G. Hluchyj",
TITLE="Analysis of the Leaky Bucket algorithm for On-Off Data Sources",
BOOKTITLE=globecom,
ADDRESS="Phoenix",
VOLUME=1,
PAGES="254-260",
YEAR=1991,
REFERENCES=16,
KEYWORDS="ATM; policing function; leaky bucket; analysis; performance
evaluation; bursty traffic; fluid flow model",
}

@ARTICLE{Lin91:Optimal,
AUTHOR="Y. Lin and B. R. Preiss",
TITLE="Optimal memory management for time warp parallel simulation",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=4,
PAGES="283-307",
YEAR=1991,
REFERENCES=29,
KEYWORDS="Distributed simulation; time warp; rollback; memory
management",
ANNOTE="Memory management strategies for Time Warp and the Chandy-Misra
algorithm are studied. Proposals such as 'cancelback' and 'artificial
rollback' are made.",
}

@ARTICLE{Bagr91:Unifying,
AUTHOR="R. L. Bagrodia and K. M. Chandy and W. T. Liao",
TITLE="A unifying framework for distributed simulation",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=4,
PAGES="348-385",
YEAR=1991,
REFERENCES=21,
KEYWORDS="Distributed simulation; survey; algorithm; virtual time;
discrete event simulation; continuous simulation",
ANNOTE="A theory of distributed simulation applicable to both
discrete-event and continuous simulation is presented. A high-level
discrete-event simulation language has been implemented, using the new
algorithm, on parallel computers; performance results of the
implementation are also presented.",
}

@ARTICLE{Feld91:Bounds,
AUTHOR="Robert E. Felderman and L. Kleinrock",
TITLE="Bounds and approximations for self-initiating distributed
simulation without lookahead",
JOURNAL=tomacs,
VOLUME=1,
NUMBER=4,
PAGES="386-406",
YEAR=1991,
KEYWORDS="Distributed simulation; virtual time; speedup; time warp;
approximation",
ANNOTE="We provide upper and lower bounds and an approximation for
speedup of an optimistic self-initiated distributed simulation using a
very simple model. We assume an arbitrary no. of processors and a
uniform connection topology. By showing that the lower bound increases
essentially linearly with $P$, the number of processors, we find that
the optimistic approach scales well as $P$ increases. The model tracks
the progress of Global Virtual Time",
}

@ARTICLE{Ayan91:Parallel,
AUTHOR="R. Ayani",
TITLE="Parallel discrete-event simulation on shared memory
multiprocessors",
JOURNAL="International journal on computer simulation (IEEE)",
VOLUME=1,
NUMBER=1,
PAGES="81-97",
YEAR=1991,
REFERENCES=15,
KEYWORDS="Discrete event simulation; parallel algorithm; simulation;
distributed simulation; performance measurement; algorithm",
ANNOTE="In this paper, a new parallel simulation algorithm is presented.
The algorithm, which is based on distances between objects, is a
conservative approach to parallel discrete-event simulation. However, in
contrast to the Chandy-Misra paradigm, it is deadlock-free and does not
lead to any memory overflow. An implementation of the algorithm on a
shared memory multiprocessor shows almost a linear speedup for certain
classes of problems.",
}

@ARTICLE{Covi91:Efficient,
AUTHOR="R. G. Covington and  others",
TITLE="Efficient simulation of parallel computer systems",
JOURNAL="International journal in computer simulation",
VOLUME=1,
NUMBER=1,
PAGES="31-58",
YEAR=1991,
REFERENCES=26,
KEYWORDS="Simulation; parallel computing; computer system; performance
evaluation; validation",
ANNOTE="An ongoing research project involves the design and evaluation
of a software system for simulating parallel computers. A major goal in
the development of this system was to avoid the high overhead associated
with the conventional instruction-level simulation of sequential
computers, but to retain the accuracy of that technique derived from its
use of the execution of real programs. The resulting system is
program-driven.",
}

@ARTICLE{Desa91:Event,
AUTHOR="H. H. Desai",
TITLE="An event scheduling technique for digital logic simulation",
JOURNAL="International journal in computer simulation",
VOLUME=1,
NUMBER=1,
PAGES="99-109",
YEAR=1991,
REFERENCES=14,
KEYWORDS="Simulation; scheduling; VLSI; system design; digital",
ANNOTE="The major objective of this paper is to introduce the
modification of event wheel technique, which has evolved over many years
of modeling of systems in computers and telecommunications, for digital
logic simulation and to describe the basic event-driven simulation
concept. The event manipulation technique described here permits
reasonably fast logic simulation of digital circuits.",
}

@INPROCEEDINGS{Eade91:Modelling,
AUTHOR="J. P. Eade and C. J. Hughes and J. Xiong",
TITLE="Modelling multiplexed video {VBR} networks",
BOOKTITLE="Packet Video",
ADDRESS="Kyoto",
PAGES="E2",
YEAR=1991,
REFERENCES=5,
KEYWORDS="ATM; modeling; multiplexing; network; video service; circuit
switching; switching network; VBR; variable bitrate coding",
ANNOTE="Since the VBR video and speech services and the ATM network may
be under the control of different administrations, it is very important
to define the interactions between them. For economic reasons, the
network should be loaded to as high a capacity as possible but, if the
users are to be offered a service that is good as that provided by a
circuit switched network, any impairments in the VBR services should be
barely perceptible.",
}

@ARTICLE{Hann91:Prototyping,
AUTHOR="W. Hanna and G. Shao",
TITLE="Prototyping in the design of military electronics",
JOURNAL="International journal in computer simulation",
VOLUME=1,
NUMBER=1,
PAGES="111-123",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Design; analysis; simulation",
ANNOTE="This paper presents reasons for including soft prototyping into
the design of new military electronic products. Examples of how soft
prototyping has benefited the process of electronic circuit design in
one large aerospace corporation are presented. The future of soft
prototyping activities related to military product development is
discussed.",
}

@INPROCEEDINGS{Kim91:Statistical,
AUTHOR="C. Kim and Shiang-feng Lee",
TITLE="Statistical analysis of a hybrid {DPCM/DCT} algorithm with
periodic replenishment",
BOOKTITLE="Packet Video",
ADDRESS="Kyoto",
PAGES="D3",
YEAR=1991,
REFERENCES=6,
KEYWORDS="Packet video; statistics; hybrid; algorithm",
ANNOTE="In this work, we analyze the compressed bitstream
characteristics of hybrid DPCM/DCT coding with periodic intraframe
replenishment. We use the statistical estimation for the analysis
because each individual bitstream is highly cyclo-stationary and the
effect of small network queues is negligible. The results suggest that
close to average bit rate allocation per video channel is possible for
video trunking of more than 20 channels.",
}

@ARTICLE{Kwok91:Simulating,
AUTHOR="B. T. K. Kwok and B. R. Preiss",
TITLE="Simulating continuous systems with piecewise-linear signals using
time warp",
JOURNAL="International journal in computer simulation",
VOLUME=1,
NUMBER=1,
PAGES="59-79",
YEAR=1991,
REFERENCES=25,
KEYWORDS="Simulation; synchronization; continuous simulation; time warp;
benchmark; algorithm",
ANNOTE="We have implemented a prototype simulator and measured its
performance on a multiprocessor using several benchmarks. On the basis
of these benchmarks, we show that the best performance is achieved when
using a scheduling algorithm that gives priority to messages with lower
time stamps and when the lazy-cancellation variant of time warp is
used.",
}

@INPROCEEDINGS{Ledu91:General,
AUTHOR="J.-P. Leduc and L. Vandendorpe",
TITLE="General model of {TV} codecs with related {ATM} network
performances",
BOOKTITLE="Packet Video",
ADDRESS="Kyoto",
PAGES="E3",
YEAR=1991,
REFERENCES=9,
KEYWORDS="Packet video; ATM; network; performance parameter; statistics;
simulation; algorithm",
ANNOTE="This paper aims to present a general model of output bit rates
on a sub-frame basis for TV and HDTV codecs.",
}

@INPROCEEDINGS{Louv91:Versus,
AUTHOR="Jean Raymond Louvion",
TITLE="2-layer versus 1-layer {VBR} codecs: a network performance
approach",
BOOKTITLE="Packet Video",
ADDRESS="Kyoto",
PAGES="E1",
YEAR=1991,
REFERENCES=13,
KEYWORDS="ATM; VBR; variable bitrate coding; network; performance
evaluation",
ANNOTE="2-layer video codecs have been developped to benefit from the
flexibility of ATM networks. Thanks to an original calculation method
based on a fluid flow model, network performances of these codecs are
compared to classical 1-layer VBR codecs. The results obtained do not
allow to conclude strongly in favor of 2-layer codes.",
}

@ARTICLE{Mill91:Query,
AUTHOR="John M. Miller and K. J. Kochut and W. D. Potter and E. Ucar and
A. A. Keskin",
TITLE="Query-driven simulation using active {KDL:} A functional
object-oriented database system",
JOURNAL="International journal in computer simulation",
VOLUME=1,
NUMBER=1,
PAGES="1-30",
YEAR=1991,
REFERENCES=70,
KEYWORDS="Object-oriented programming; database; simulation",
ANNOTE="Contents: 1. Introduction; 2. Language design goals and
motivation 3. Active KDL-type system; 4. Active KDL as a data modeling
language: simulation model construction; 5. Active KDL as a query
language: query-driven simulation 6. Summary and future work",
}

@INPROCEEDINGS{Pear91:Motion,
AUTHOR="Don Pearson and V. Seferidis and J. Xiong",
TITLE="A motion related bit-rate model for packet video",
BOOKTITLE="Packet Video",
ADDRESS="Kyoto",
PAGES="D1",
YEAR=1991,
REFERENCES=2,
KEYWORDS="Packet video; simulation",
ANNOTE="In this paper we report on a new line of approach to modelling
which seeks to characterize the motion itself by a stochastic process.
We will show that, having done that, the bit rate variations can then be
derived in a straightforward way, giving a more general model.",
}

@INPROCEEDINGS{Reib91:Combined,
AUTHOR="Andrew Reibman and Praveen Goli and V. Kumar",
TITLE="Combined performance study of a video compression system and an
{ATM} switch",
BOOKTITLE="Packet Video",
ADDRESS="Kyoto",
PAGES="E4",
YEAR=1991,
REFERENCES=9,
KEYWORDS="Performance evaluation; video service; algorithm; ATM",
ANNOTE="We present a study of the combined performance of a video
compression algorithm and an ATM switch carrying the video traffic
generated by this algorithm. The video compression algorithm separates
the image sequence into high priority and low priority packets. We study
the effect of packet loss on image quality when low priority packets are
lost and when both low and high priority packets are lost.",
}

@INPROCEEDINGS{Zuke91:Traffic,
AUTHOR="Moshe Zukerman and M. Leditschke and M. J. Biggar",
TITLE="Traffic studies of variable bit rate conferencing video",
BOOKTITLE="Packet Video",
ADDRESS="Kyoto",
PAGES="D2",
YEAR=1991,
REFERENCES=3,
KEYWORDS="Traffic analysis; VBR; variable bitrate coding; video
conference; network design",
ANNOTE="This paper begins by describing a method for producing
sequential data representing the number of bits über macroblock
generated by a coded video-conference source. Then, the statistical
characteristics of this sequence are described. The paper discusses the
issue of whether or not, for the purpose of network design and
dimensioning, it is important to consider traffic fluctuation within a
video frame.",
}

@ARTICLE{Kuba91:Alternatives,
AUTHOR="P. Kubat",
TITLE="Alternatives for reliable and quality telecommunication network
design",
JOURNAL="Annals of Operations Research",
PUBLISHER="J.C. Baltzer AG",
ADDRESS="Basel",
VOLUME=33,
PAGES="95-105",
YEAR=1991,
REFERENCES=14,
KEYWORDS="Reliability; system design",
ANNOTE="This paper discusses alternative approaches to the system design
from the view point of future costs. We will illustrate that the system
can be improved not only by increasing reliability of subsystems, but
also by effectively utilizing systems operations support. Network
support is defined, and customers' expectations are discussed.",
}

@PHDTHESIS{Dewe91:ATM,
AUTHOR="H. Dewes",
TITLE="{ATM-Netze} auf Basis von {PRELUDE-} und {STARLITE-Strukturen}",
SCHOOL="Lehrstuhl für Nachrichten- und Vermittlungstechnik, Universität
des Saarlandes",
ADDRESS="Saarbrücken, Germany",
PAGES=213,
YEAR=1991,
LANGUAGE="German",
REFERENCES=71,
KEYWORDS="ATM; BISDN; switching network; switching methodology; network
characteristics; simulation method; MMPP",
}

@PHDTHESIS{Gill91:Statistische,
AUTHOR="T. Gillen",
TITLE="Statistische Multiplexer bei Stromverkehr",
SCHOOL="Lehrstuhl für Nachrichten- und Vermittlungstechnik, Universität
des Saarlandes",
ADDRESS="Saarbrücken",
PAGES=139,
YEAR=1991,
LANGUAGE="German",
REFERENCES=39,
KEYWORDS="Statistical multiplexer; stream traffic; ATM; service
discipline; FIFO; cyclic service; simulation",
}

@PHDTHESIS{Klei91:Eigenschaften,
AUTHOR="T. Klein",
TITLE="Eigenschaften von Zellströmen und statistischen Multiplexern im
{BISDN} mit Asynchronem Transfer-Modus",
SCHOOL="Lehrstuhl für Nachrichten- und Vermittlungstechnik, Universität
des Saarlandes",
ADDRESS="Saarbrücken",
PAGES=257,
YEAR=1991,
LANGUAGE="German",
REFERENCES=93,
KEYWORDS="ATM; BISDN; traffic pattern; statistical multiplexing;
performance evaluation; traffic source model; superposition; delay
throughput characteristics; delay analysis; simulation",
}

@ARTICLE{Blan91:Power,
AUTHOR="J. P. Blanc",
TITLE="The power-series algorithm applied to cyclic polling systems",
JOURNAL=comstat,
VOLUME=7,
NUMBER=4,
PAGES="527-545",
YEAR=1991,
KEYWORDS="Queueing system; cyclic service; analysis",
}

@ARTICLE{Bosc91:Generic,
AUTHOR="M. Bosch and G. Schmid",
TITLE="Generic Petri net models of protocol mechanisms in communication
systems",
JOURNAL=comcom,
VOLUME=14,
NUMBER=3,
PAGES="143-156",
YEAR=1991,
}

@ARTICLE{Boxm91:Queue,
AUTHOR="O. J. Boxma and J. W. Cohen",
TITLE="The {M/G/1} queue with permanent customers",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=2,
PAGES="179-184",
YEAR=1991,
KEYWORDS="Queueing system; vacation system; analysis",
}

@ARTICLE{Conw91:Perspective,
AUTHOR="A. E. Conway",
TITLE="A perspective on the analytical performance evaluation of
multilayered communication protocol architectures",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=1,
PAGES="4-14",
YEAR=1991,
}

@ARTICLE{Coop91:Convergence,
AUTHOR="R. B. Cooper and D. Gross",
TITLE="On the convergence of Jacobi and Gauss-Seidel iteration for
steady-state probabilities of finite-state continuous-time Markov
chains",
JOURNAL=comstat,
VOLUME=7,
NUMBER=1,
PAGES="185-189",
YEAR=1991,
KEYWORDS="Eigenvalue; linear equation",
}

@ARTICLE{Mora91:Mean,
AUTHOR="L. de Moraes and S. W. Fuhrmann",
TITLE="Mean delay approximations for polling systems with batch Poisson
input",
JOURNAL=pe,
VOLUME=12,
NUMBER=3,
PAGES="147-156",
YEAR=1991,
KEYWORDS="Queueing system; cyclic service; analysis",
}

@ARTICLE{Gele91:Product,
AUTHOR="E. Gelenbe",
TITLE="Product-form queueing networks with negative and positive
customers",
JOURNAL=jap,
VOLUME=28,
NUMBER=3,
PAGES="656-663",
YEAR=1991,
KEYWORDS="Queueing network; product form",
}

@ARTICLE{Gele91:Queues,
AUTHOR="E. Gelenbe and K. Sigman and P. W. Glynn",
TITLE="Queues with negative arrivals",
JOURNAL=jap,
VOLUME=28,
NUMBER=1,
PAGES="245-250",
YEAR=1991,
}

@ARTICLE{Gosz91:CCITT,
AUTHOR="G. Gosztony",
TITLE="{CCITT} work in teletraffic engineering",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=2,
PAGES="131-134",
YEAR=1991,
KEYWORDS="Traffic engineering; standardization",
}

@INPROCEEDINGS{Gryg91:EVALNET,
AUTHOR="K. Grygiel and T. Gruzlewski and Z. Weiss",
TITLE="{EVALNET} -- a software package for computer systems performance
evaluation",
BOOKTITLE={Tagungsband"Kurzvorträge und Werkzeugausstellung"der 6.
GI/ITG-Fachtagung über Messung, Modellierung, Bewertung von
Rechnersystemen},
ADDRESS="Neubiberg",
YEAR=1991,
KEYWORDS="Computer tool; performance evaluation",
}

@INPROCEEDINGS{Have91:DyQNtool,
AUTHOR="Boudewijn R. Haverkort and I. G. Niemegeers and P. van Zanten",
TITLE="DyQNtool -- a performability modelling tool based on the dynamic
queueing network concept",
BOOKTITLE="5th International Conference on Modelling Techniques and
Tools for Computer Performance Evaluation",
ADDRESS="Torino",
PAGES="174-188",
YEAR=1991,
KEYWORDS="Computer tool; performability",
}

@INPROCEEDINGS{Kata91:Priority,
AUTHOR="T. Katayama and Yutaka Takahashi",
TITLE="Analysis of a priority queue with Bernoulli schedules",
BOOKTITLE="International Conference on the Performance of Distributed
Systems and International Communication Networks",
EDITOR="T. Hasegawa and Christopher Carothers",
PAGES="87-105",
YEAR=1991,
KEYWORDS="Queueing system; vacation system; analysis",
}

@INPROCEEDINGS{Klei91:Large,
AUTHOR="W. Klein and R. Kleinewillinghöfer-Kopp",
TITLE="Performance analysis of a large-scale common channel signalling
network",
BOOKTITLE=itc13,
ADDRESS="Copenhagen",
PAGES="73-78",
YEAR=1991,
KEYWORDS="Signalling; common channel; CCS",
}

@BOOK{Kopk91:LaTeX,
AUTHOR="H. Kopka",
TITLE="LaTeX-Erweiterungsmöglichkeiten.",
PUBLISHER="Addison-Wesley Publishing Company, Bonn",
YEAR=1991,
LANGUAGE="German",
}

@ARTICLE{Lee91:Characteristics,
AUTHOR="Hwang-Soo Lee and M. M. Srinivasan and C. A. Yano",
TITLE="Characteristics of optimal workload allocation for closed
queueing networks",
JOURNAL=pe,
VOLUME=12,
NUMBER=4,
PAGES="255-268",
YEAR=1991,
KEYWORDS="Queueing network; product form",
}

@ARTICLE{Liu91:Sensitivity,
AUTHOR="Z. Liu and P. Nain",
TITLE="Sensitivity results in open, closed and mixed product form
queueing networks",
JOURNAL=pe,
VOLUME=13,
NUMBER=4,
PAGES="237-251",
YEAR=1991,
KEYWORDS="Queueing network; product form; analysis",
}

@INPROCEEDINGS{MacD91:Risk,
AUTHOR="D. MacDonald and F. Kaudel",
TITLE="Risk analysis for improving {CCS\#7} survivability",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Az",
PAGES="1-5 (paper 6)",
YEAR=1991,
KEYWORDS="Signalling; common channel; CCS",
}

@ARTICLE{Mann91:GSM,
AUTHOR="A. Mann",
TITLE="Der {GSM-Standard} -- Grundlage für digitale europäische
Mobilfunknetze",
JOURNAL=infspec,
VOLUME=14,
NUMBER=3,
PAGES="137-152",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Mobile radio; standardization",
}

@BOOK{Mant91:Common,
AUTHOR="R. J. Manterfield",
TITLE="Common-Channel Signalling",
PUBLISHER="Peter Peregrinus Ltd.",
ADDRESS="London",
YEAR=1991,
KEYWORDS="Signalling; common channel; CCS",
}

@ARTICLE{Matu91:Hierarchical,
AUTHOR="R. Matuschka",
TITLE="Hierarchical evaluation of generalized stochastic Petri nets
based on subnetwork time distribution",
JOURNAL={In "Informatik-Fachberichte Messung, Modellierung und Bewertung
von Rechensystemen" (Hrsg. A. Lehmann)},
ADDRESS="Neubiberg",
VOLUME=286,
PAGES="292-305",
YEAR=1991,
}

@ARTICLE{McKe91:Calculating,
AUTHOR="J. McKenna",
TITLE="Calculating joint queue length moments with {RECAL.}",
JOURNAL=comstat,
VOLUME=7,
NUMBER=1,
PAGES="47-66",
YEAR=1991,
KEYWORDS="Queueing network; product form; analysis",
}

@ARTICLE{Anon91:Qualit,
AUTHOR="Anonymous",
TITLE="Qualitätsmerkmale im {ISDN}",
JOURNAL=ntz,
VOLUME=44,
NUMBER=11,
PAGES="841-851",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="ISDN",
}

@TECHREPORT{Rath91:Verkehrsflüsse,
AUTHOR="Erwin P. Rathgeb",
TITLE="Verkehrsflüsse in {ATM-Netzen} -- Modellierung und Analyse von
Verkehrsquellen und Quellflußkontrollverfahren",
TYPE="Bericht über verkehrstheoretische Arbeiten",
INSTITUTION="Institut für Nachrichtenvermittlung und Datenverarbeitung,
Universität Stuttgart",
ADDRESS="Stuttgart",
NUMBER=51,
YEAR=1991,
LANGUAGE="German",
}

@ARTICLE{Reis91:Quarter,
AUTHOR="M. Reiser",
TITLE="A quarter century of performance evaluation -- where do we
stand?",
JOURNAL=pe,
VOLUME=12,
NUMBER=1,
PAGES="1-4",
YEAR=1991,
KEYWORDS="Performance evaluation; survey",
}

@INCOLLECTION{Skoo91:Study,
AUTHOR="R. A. Skoog",
TITLE="Study of clustered arrival processes and signaling link delays",
BOOKTITLE="North-Holland Studies in Telecommunication",
EDITOR="A.Jensen and Christopher Carothers",
PUBLISHER="North-Holland, Amsterdam",
VOLUME=14,
PAGES="61-66",
YEAR=1991,
KEYWORDS="Signalling; common channel; CCS; performance evaluation",
}

@BOOK{Taka91:Queueing,
AUTHOR="H. Takagi",
TITLE="Queueing Analysis: A Foundation of Performance Evaluation --
Vacation and Priority Systems, Part 1",
PUBLISHER="Elsevier Science Publishers B.V. (North-Holland)",
ADDRESS="Amsterdam",
VOLUME=1,
YEAR=1991,
KEYWORDS="Queueing system; vacation system; priority; analysis",
}

@INPROCEEDINGS{Tang91:MeanProtocol,
AUTHOR="M. Tangemann",
TITLE="A mean value analysis for throughputs and waiting times of the
{FDDI} timed token protocol",
BOOKTITLE="North Holland Studies in Telecomm",
EDITOR="A. Jensen and Christopher Carothers",
PUBLISHER="North-Holland, Amsterdam",
VOLUME=14,
PAGES="173-179",
YEAR=1991,
KEYWORDS="Queueing system; cyclic service; analysis",
}

@INPROCEEDINGS{Wang91:Traffic,
AUTHOR="Jin-Tuu Wang",
TITLE="Traffic routing and performance analysis of the common channel
signaling system 7 network",
BOOKTITLE=globecom,
PAGES="10.3 (1-5)",
YEAR=1991,
KEYWORDS="Signalling; common channel; CCS; performance evaluation",
}

@INPROCEEDINGS{Will91:Modellierung,
AUTHOR="G. Willmann",
TITLE="Modellierung und Leistungsbewertung des
{CCITT-Signalisiersystems} Nr. 7",
BOOKTITLE="Kurzfassungen der Beiträge",
EDITOR="P. J. Kühn",
ADDRESS="Stuttgart, Germany",
PAGES="51-52",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Signalling; common channel; CCS; performance model",
}

@ARTICLE{Wolf9109:Finite,
AUTHOR="R. W. Wolff",
TITLE="On finite delay-moment conditions in queues",
JOURNAL=or,
VOLUME=39,
NUMBER=5,
PAGES="771-775",
MONTH="September/October",
YEAR=1991,
}

@INCOLLECTION{Yech91:Optimal,
AUTHOR="U. Yechiali",
TITLE="Optimal dynamic control of polling systems",
BOOKTITLE="North-Holland Studies in Telecommunication",
EDITOR="J. W. Cohen and Christopher Carothers",
PUBLISHER="North-Holland, Amsterdam",
PAGES="205-217",
YEAR=1991,
KEYWORDS="Queueing system; cyclic service; analysis",
}

@INCOLLECTION{Zepf91:Transient,
AUTHOR="J. Zepf and G. Willmann and G. Rufa",
TITLE="Transient analysis of congestion and flow control mechanisms in
common channel signalling networks",
BOOKTITLE="North-Holland Studies in Telecommunication",
EDITOR="A. Jensen and Christopher Carothers",
PUBLISHER="North-Holland, Amsterdam",
PAGES="413-419",
YEAR=1991,
KEYWORDS="Signalling; common channel; CCS; performance evaluation",
}

@INPROCEEDINGS{Brau91:OSI,
AUTHOR="T. Braun and B. Stiller and M. Zitterbart",
TITLE="{OSI} or Special Protocols for High Speed Networks?",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="41-43",
YEAR=1991,
REFERENCES=7,
KEYWORDS="OSI; VMTP; versatile message transaction protocol; transport
protocol",
ANNOTE="OSI, XTP and VMTP are compared.",
}

@INPROCEEDINGS{Brie91:Discrete,
AUTHOR="U. Briem and T. H. Theimer and Hans Kröner",
TITLE="A Discrete-Time Queueing Model for {ATM}",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="61-63",
YEAR=1991,
REFERENCES=14,
KEYWORDS="ATM; modeling; discrete time analysis",
}

@ARTICLE{Broo91:Deadlock,
AUTHOR="S. D. Brookes and A. W. Roscoe",
TITLE="Deadlock analysis in networks of communicating processes",
JOURNAL=distcomp,
VOLUME=4,
NUMBER=4,
PAGES="209-230",
YEAR=1991,
REFERENCES=26,
KEYWORDS="Distributed simulation; deadlock",
ANNOTE="We introduce a number of simple conditions on networks which aid
deadlock analysis either by localizing the analysis required for a proof
of deadlock-freedom or by restricting the circumstances in which
deadlock could occur. We introduce a methodology for proving
deadlock-freedom in a large network by decomposing it into subnetworks
which can be analysed separately. A variety of examples is given.",
}

@INPROCEEDINGS{Chen91:Conflict,
AUTHOR="M.-S. Chen and T. S. Yum",
TITLE="A Conflict-Free Protocol for Optical {WDMA} Networks",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="1276-1281",
YEAR=1991,
REFERENCES=11,
KEYWORDS="WDM; wavelength division multiplex; optical LAN; star; LAN;
man",
ANNOTE="A conflict-free protocol for packet-switched wavelenght division
multiaccess networks is proposed. With the use of a control channel,
each station in the network can obtain packet backlog information of all
other stations, and so packet transmission can be scheduled to avoid
destination conflicts",
}

@INPROCEEDINGS{Chou91:Markov,
AUTHOR="Z. Choueiri and M. Becker and A. Beylot",
TITLE="A Markov Model of Sources for {ATM} Traffic: Superposition of
On-Off Voice, Data and Video Sources",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="105-118",
YEAR=1991,
REFERENCES=26,
KEYWORDS="Markovian model of system behaviour; ATM; source model;
superposition",
ANNOTE="A quantized-state continuous-time Markov model for independent
ATM sources, voice, data and video is presented in this paper. The
model's parameters are fitted with experimental data. Video sources are
limited to Video telephone conversations. The input rate into a
statistical multiplexer is modelled and a flow-equivalent approximate
queueing analysis is used to obtain the common buffer length
distribution and the loss probability.",
}

@INPROCEEDINGS{Decr91:Analytical,
AUTHOR="L. Decreusefond and D. Kofman",
TITLE="An Analytical Model for {FDDI} with Synchronous and Asynchronous
Traffics",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="79-81",
YEAR=1991,
REFERENCES=1,
KEYWORDS="FDDI; analytical model",
ABSTRACT="In the special case of a FDDI ring, we study the behaviour and
the mutual influence of synchronous and asynchronous traffics,
respectively. That is to say, we deal with a FDDI ring in which each
station generates both types of traffic. The synchronous traffic, which
is served first, is not submitted to any time constraint in the sense
that at leas a fixed part is sure to be served in each cycle.",
}

@INPROCEEDINGS{Desm91:Assessment,
AUTHOR="E. M. Desmet",
TITLE="Performance Assessment of an {ATM} Self-Routing Switching Network
using Parallel Programming Techniques and a Network of Transputers",
BOOKTITLE="International Computer and Communication Conference",
ADDRESS="Beijing",
YEAR=1991,
REFERENCES=9,
KEYWORDS="ATM; switching; performance evaluation; simulation;
multiprocessor system; transputer; distributed simulation",
}

@ARTICLE{Drip91:Architektur,
AUTHOR="A. Dripke",
TITLE="Architektur von Multiuser-Systemen",
JOURNAL="Elektronik",
VOLUME=26,
PAGES="80-83",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Bus; processor",
ANNOTE="Personal Computer unter SCO Unix werden als Mehrplatzsysteme
eingesetzt, die herkömmlichen Minicomputern Konkurrenz machen. ARC
-Workstations (Advanced RISC Computing) sollen im Rahmen der Initiative
Advanced Computing Environment (ACE) in Wettbewerb zu Mainframes treten.
Erste Stimmen sprechen bereits von Risc-Grossrechenzentren. Was häufig
übersehen wird: Die Hardware-Archit ektur von PCs ist primär für
Einplatzbetrieb ausgelegt.",
}

@INPROCEEDINGS{Foll91:Interworking,
AUTHOR="D. Follett and E. Dutkiewicz and G. J. Anido",
TITLE="Interworking {FASTPAC} and Frame Relay: Evolution to {BISDN}",
BOOKTITLE="Australian Broadband Switching and Services Symposium",
ADDRESS="Sydney",
VOLUME=1,
PAGES="234-241",
YEAR=1991,
REFERENCES=16,
KEYWORDS="MAN; DQDB; BISDN; Frame Relay; architecture",
ANNOTE="Frame relay bearer service can be used to provide
interconnection between local and metropolitan area networks to form
international high speed data networks. An architecture foran
interworking unit capable of interconnecting IEEE 802.6 MANs to form an
extended FASTPAC service is proposed.",
}

@INPROCEEDINGS{Gagn91:Comparison,
AUTHOR="M. Gagnaire and",
TITLE="Comparison of Different Voice-Data Integration Schemes on the
{DQDB} {MAN}",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="89-91",
YEAR=1991,
KEYWORDS="Dqdb; man",
ANNOTE="In this paper, we propose to integrate a data traffic and a
packetized voice traffic on the DQDB network via a Queued-Arbitrated
access scheme.",
}

@INPROCEEDINGS{Ganz91:WDM,
AUTHOR="A. Ganz and Z. Koren",
TITLE="{WDM} Passive Star - Protocols And Performance Analysis",
BOOKTITLE=infocom,
PAGES="991-1000",
YEAR=1991,
REFERENCES=9,
KEYWORDS="WDM; wavelength division multiplex; optical LAN; star; aloha;
andom",
ANNOTE="Two synchronous channel access protocols requiring no
pertransmission penalty are considered: random access and fixed
transmission scheduling. In this paper we present an efficient
approximate analysis with drastically reduced computational complexity,
incorporating all of the above system characteristics.",
}

@ARTICLE{Gerl91:Evolution,
AUTHOR="M. Gerla and L. Fratta and J. Bannister",
TITLE="Evolution of {LANs} and {MANs} Towards High Speeds: Gigabits per
second and Beyond",
JOURNAL=ett,
VOLUME=2,
NUMBER=1,
PAGES="89-104",
YEAR=1991,
REFERENCES=57,
KEYWORDS="LAN; MAN; ring; bus; FDDI; DQDB; protocol; HSLAN; CRMA; cyclic
reservation multiple access",
ANNOTE="This paper traces the evolution of LANs and MANs from the early
Ethernet days to recent Gigabit per second prototypes. In the second
part, two representative examples of third generation networks, namely,
TreeNet and WON, are presented.",
}

@INPROCEEDINGS{Gold91:High,
AUTHOR="E. H. Göldner",
TITLE="High Speed Data Services in {BISDN}",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="31-36",
YEAR=1991,
REFERENCES=9,
KEYWORDS="BISDN; man",
}

@ARTICLE{Gree91:Future,
AUTHOR="P. E. Green",
TITLE="The Future Of Fiber-Optic Computer Networks",
JOURNAL=ieeecomp,
PAGES="78-87",
YEAR=1991,
KEYWORDS="LAN; fiber optics; star; bus; tree network; WDM; wavelength
division multiplex; TDMA; time division multiple access; CDMA; code
division multiple access; protocol",
}

@ARTICLE{Gros91:Distributed,
AUTHOR="B. Groselj and C. Tropper",
TITLE="The distributed simulation of clustered processes",
JOURNAL=distcomp,
VOLUME=4,
NUMBER=4,
PAGES="111-121",
YEAR=1991,
REFERENCES=21,
KEYWORDS="Distributed simulation; deadlock",
ANNOTE="An efficient method for use in the discrete-event distributed
simulation of large systems is presented. A conservative distributed
simulation as well as the mapping of several simulated processes onto
the same processor is assumed. The method consists of two algorithms: an
algorithm for computing the lower bounds on times of future events, and
a distributed algorithm that resolves deadlocks.",
}

@INPROCEEDINGS{Jabb91:Call,
AUTHOR="B. Jabbari and F. Yegenoglu and G. Mason",
TITLE="Call Admittance Policy based on the Cell Loss Upper Bound for
Bursty and Variable Bit Rate Video Sources in Broadband Packet
Networks",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="93-95",
YEAR=1991,
KEYWORDS="ATM; loss probability",
ANNOTE="In this presentation, we focus on an upper bound for the
probability of cell loss of bursty and VBR video sources in ATM. The
bursty sources considered here alternate between active and silent
states.",
}

@ARTICLE{Klei91:Synchrone,
AUTHOR="M. Klein",
TITLE="Synchrone Digitale Hierarchie - Prinzipien und Anwendungen",
JOURNAL="Philips Innovation Technische Mitteilungen Telekommunikation",
ADDRESS="Nürnberg",
VOLUME=2,
PAGES="4-10",
YEAR=1991,
LANGUAGE="German",
REFERENCES=4,
KEYWORDS="SDH; synchronous digital hierarchy; overview; application",
ANNOTE="Die Einführung der Synchronen Digitalen Hierarchie (SDH)
eröffnet die Möglichkeit eines weltweit homogenen übertragungsnetzes.
Der Beitrag beschreibt die grundsätzliche Funktionsweise SDH, den Stand
der internationalen Standardisierung sowie noch zu lösende Probleme.
Anhand von Beispielen wird die Flexibilität von Geräten und Netzen auf
der Basis des SDH-Standards unter Einbeziehung gegenwärtiger
Anforderungen aufgezeigt.",
}

@INPROCEEDINGS{Kofm91:Modelling,
AUTHOR="D. Kofman",
TITLE="Modelling and Analysis of Finite Capacity Polling Systems",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="69-71",
YEAR=1991,
REFERENCES=2,
KEYWORDS="Polling system; modeling; analysis",
ANNOTE="In this paper we analyze the same polling system as analyzed by
Takagi (6/91) without the independence hypothesis, by computing the
conditional probability of the vacation time given the number of packets
served between the end of the preceding vacation and the beginning of
the present vacation.",
}

@INPROCEEDINGS{Kofm91:Superposition,
AUTHOR="D. Kofman and H. Korezlioglu",
TITLE="Superposition of Processes After Leaky Bucket Control",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="101-103",
YEAR=1991,
REFERENCES=1,
KEYWORDS="Leaky bucket; ATM",
ANNOTE="The model, described in this paper, allows us to fit our problem
to Neuts and Pearce's superposition model, from which we deduce for
particular numerical cases meaningful results concerning the number of
cells appearing in an interval of n+1 slots length after superposition
procedure: its mean value, its variance and its probability of being
greater than a given threshold value.",
}

@ARTICLE{Krei91:Zweiter,
AUTHOR="J. Kreidl and A. Krepil",
TITLE="Zweiter Frühling für den {VMEbus}",
JOURNAL="Elektronik",
VOLUME=26,
PAGES="30-35",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Vme-bus; throughput",
ANNOTE="Zehn Jahre nach seiner Entstehung steht der VMEbus vor seinem
zweiten Frühling. Im Verbund mit dem seriellen Hochgeschwindigkeitsbus
``Autobahn'' erreicht der VMEbus Datendurchsatzraten bis zu 560 MByte/s.
``Autobahn'' nutzt dabei zwei serielle Leitungen am Stecker P1 des
VMEbus, die bisher nicht benutzt waren.",
}

@INPROCEEDINGS{Kron91:Statistical,
AUTHOR="Hans Kröner",
TITLE="Statistical Multiplexing of Sporadic Sources",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="65-67",
YEAR=1991,
REFERENCES=9,
KEYWORDS="Multiplexing; source model",
}

@INPROCEEDINGS{Lela91:High,
AUTHOR="Will Leland and Daniel H. Wilson",
TITLE="High Time-Resolution Measurement and Analysis of {LAN} Traffic:
Implications for {LAN} Interconnection",
BOOKTITLE=infocom,
ADDRESS="Bal Harbour",
VOLUME=3,
PAGES="1360-1366",
YEAR=1991,
REFERENCES=16,
KEYWORDS="LAN; Ethernet; Traffic Measurement",
ANNOTE="We present a high time-resolution hardware monitor for Ethernet
LANs that avoids the shortcomings of previous monitoring tools, such as
traffic burst clipping and timestamp jitter. Using data recorded by our
monitor for several hundred million Ethernet packets, we present an
overview of the short-range time correlations in external LAN traffic.
Our analysis shows that LAN traffic is extremely bursty across time
domains spanning 6",
}

@TECHREPORT{Ofek91:Principles,
AUTHOR="Y. Ofek and M. Yung",
TITLE="Principles for High Speed Network Control: Lossless-ness and
Deadlock-freeness, Selfrouting and a Single Buffer per Link",
INSTITUTION="IBM Research Division, T. J. Watson Research Center",
ADDRESS="Yorktown Heights, New York",
PAGES=26,
YEAR=1991,
REFERENCES=24,
KEYWORDS="Ring network; hsLAN; LAN; man",
ANNOTE="In this paper we present principles of operation for the basic
control functions of a high-speed network with an arbitrary topology, we
then suggest a design of such a network. In the architecture we design,
on one hand a node can try to transmit asynchronously, without
reservation, as much as it can, and on the other hand the network access
and flow control will ensure no loss, fair access to the network, no
deadlocks and self-routing.",
}

@TECHREPORT{Ofek91:Lossless,
AUTHOR="Y. Ofek and M. Yung",
TITLE="Lossless Asynchronous Broadcast-with-Feedback on the MetaNet
Architecture",
INSTITUTION="IBM Research Division, T. J. Watson Research Center",
ADDRESS="Yorktown Heights, New York",
PAGES=26,
YEAR=1991,
REFERENCES=16,
KEYWORDS="Ring network; hsLAN; LAN; MAN; broadcast",
ANNOTE="In this work we present broadcast and broadcast-with-feedback on
the recently suggested MetaNet. The MetaNet is a novel network
architecture wich can be viewed as local area network with an arbitrary
topology. Broadcast and broadcast-with-feedback algorithms which are
presented in this work are functionally equivalent to the broadcast on
today's LANs. The broadcast algorithms are completely loss free under
asynchronous access method.",
}

@TECHREPORT{Ofek91:Efficient,
AUTHOR="Y. Ofek and M. Yung",
TITLE="Efficient Mechanism for Fairness and Flowcontrol for the MetaNet
Architecture",
INSTITUTION="IBM Research Division, T. J. Watson Research Center",
ADDRESS="Yorktown Heights, New York",
PAGES=26,
YEAR=1991,
REFERENCES=23,
KEYWORDS="HsLAN; LAN; MAN; flow control; fairness",
ANNOTE="In this work we present a general control mechanism for fair
access to communication links of a network with an arbitrary topology.
The proposed control mechanism operates over a spanning tree that was
constructed for this purpose in the network. The fairness mechanism
implies deadlock-freeness. The mechanism regulates the network access
and can work much faster than previous ones.",
}

@ARTICLE{Phil91:Concurrent,
AUTHOR="Chris Phillips and L. G. Cuthbert",
TITLE="Concurrent Discrete Event-Driven Simulation Tools",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=3,
PAGES="477-485",
YEAR=1991,
REFERENCES=32,
KEYWORDS="Discrete event simulation; multiprocessor system; simulation
method; transputer; occam; distributed simulation",
}

@ARTICLE{Roth91:Leistungssportler,
AUTHOR="R. Roth and J. Hüggenberg",
TITLE="Leistungssportler: Performance en masse mit {RISC-Chips} und
Signalprozessoren",
JOURNAL="Elektronik",
VOLUME=26,
PAGES="84-89",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Risc; processor",
ANNOTE="Hohe Prozessorleistung bedeutet nicht nur, die
Taktgeschwindigkeit dieser Chips in schwindelnde Höhen zu treiben.
Ausschlaggebend für die Leistung eines Prozessors ist genauso die in
Hardware eingebrannte Verarbeitungslogik. Nur wenn sich auf dieser Ebene
die Befehle nicht gegenseitig im Weg stehen, lässt sich die Taktfrequenz
in echte Systemleistung umsetzen.",
}

@ARTICLE{Ruko91:Hierarchical,
AUTHOR="M. Rukoz",
TITLE="Hierarchical deadlock detection for nested transactions",
JOURNAL=distcomp,
VOLUME=4,
NUMBER=3,
PAGES="123-129",
YEAR=1991,
REFERENCES=8,
KEYWORDS="Distributed simulation; deadlock",
ANNOTE="In this paper, we propose an algorithm for detecting deadlocks
in a distributed Nested Transaction. This algorithm does not require
that the global wait-for graph be built and maintained nor that the
edges of a global wait-for graph be followed in order for deadlocks to
be detected. Our algorithm uses the fact that transactions are organized
in a tree structure. Each transaction maintains a representative
wait-for graph.",
}

@INPROCEEDINGS{Scho91:MANs,
AUTHOR="W. Schödl and M. Tangemann",
TITLE="Performance of {MANs} for Correlated and Uncorrelated Source
Traffic",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="73-77",
YEAR=1991,
REFERENCES=6,
KEYWORDS="Dqdb; fddi-ii; MAN; source model; mmpp",
ANNOTE="Recently, many source models have been developed to emulate more
or less precisely all kinds of traffic sources. In this paper, we employ
various source models to investigate their influence on the performance
of High Speed Local Area Networks (HSLANs). Our investigations are
carried out for two well-known HSLANs, namely FDDI-II and DQDB.",
}

@INPROCEEDINGS{Schr91:Architectural,
AUTHOR="K. J. Schrodi",
TITLE="Architectural Aspects of {BISDN}",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="27-29",
YEAR=1991,
REFERENCES=1,
KEYWORDS="BISDN; architecture",
ANNOTE="This paper discusdses a number of architectural options, which
can be envisaged to support the introduction of BISDN.",
}

@INPROCEEDINGS{Seni91:Efficient,
AUTHOR="J. M. Senior and J. M. Mc Veigh and S. D. Cusworth",
TITLE="Efficient Access Protocols for Wavelength Division Multiple
Access on Optical Fibre {LANs}",
BOOKTITLE=efoc,
PAGES="114-117",
YEAR=1991,
KEYWORDS="LAN; WDM; wavelength division multiplex; protocol;
reservation",
}

@ARTICLE{Shan91:Modular,
AUTHOR="A. U. Shankar",
TITLE="Modular Design Principles for Protocols with an Application to
the Transport Layer",
JOURNAL=ieeeproc,
ADDRESS="New York",
VOLUME=79,
NUMBER=12,
PAGES="1687-1707",
YEAR=1991,
REFERENCES=57,
KEYWORDS="Osi; iso; protocol specification; transport layer; transport
protocol",
ANNOTE="This paper presents a method for specifying services, specifying
protocols, and constructing protocol specifications. The method is based
on assertional reasoning and a refinement relation between state
transition systems. The method is demonstrated on the transport layer.",
}

@INPROCEEDINGS{Sieg91:High,
AUTHOR="M. Siegel",
TITLE="Design and Implementation of a High-Speed {ISO} {TP4} Transport
System",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="45-49",
YEAR=1991,
REFERENCES=16,
KEYWORDS="transport layer; transport protocol; HSLAN; MAN; ISO reference
model",
ANNOTE="An architecture is presented for HSLAN/MAN controllers. This
front-end processor system (FEP) is designed for operation in a CLNS/LLC
1 environment and implements the ISO OSI TP4 transport protocol. The FEP
uses one or more commercial microprocessors with layers 2b-4 implemented
in firmware. The protocol processors are supported by custom VLSI
hardware such as a checksummer, DMA units, and process coupling devices
as required.",
}

@INPROCEEDINGS{Sieg91:Overcoming,
AUTHOR="M. Siegel and G. Rößler and M. B. Williams",
TITLE="Overcoming Bottlenecks in High-Speed Transport Systems",
BOOKTITLE=lcn,
ADDRESS="Minneapolis",
PAGES="399-407",
YEAR=1991,
REFERENCES=15,
KEYWORDS="Transport protocol; osi; protocol implementation",
ANNOTE="An architecture is presented for the interface adapter between
the host and a high-speed LAN or MAN. The adaptor, known as a front-end
processor system, (FEP) is designed for operation in a CLNS/LLC 1
environment, and implements the ISO OSI TP4 transport protocol. Rather
than implement the protocols purely in hardware, it was decided to
implement layers 2b to 4 in firmware on a multiprocessor architecture
supported by special-purpose hardw.",
}

@ARTICLE{Simh9102:Starvation,
AUTHOR="R. Simha and Y. Ofek",
TITLE="A starvation-free access protocol for a full-duplex buffer
insertion ring local area network",
JOURNAL=cnis,
VOLUME=21,
NUMBER=2,
PAGES="109-120",
YEAR=1991,
REFERENCES=22,
KEYWORDS="LAN; MAN; hsLAN; ring network; protocol",
ABSTRACT="Of several existing designs for local area networks, the
buffer insertion ring has been shown to provide higher throughputs,
lower mean delays, and greater spatial reuse than competing designs such
as the token ring and slotted ring networks. However, one disadvantage
is that the normally unregulated access scheme of the Insertion Ring
allows for the phenomenon of starvation, when a network node has to wait
too long before it can access the ring. In our work we demonstrate that
starvation is a serious problem and we present a protocol to prevent it.
It is shown that the new protocol is correct, stable, and does not
substantially degrade the otherwise efficient operation of the ring.",
ANNOTE="In buffer insertion ring networks one disatvantage is that the
normally unregulated access scheme of the insertion ring allows for the
phenomenon of ``starvation'' - when a network node has to wait too long
befor it can access the ring. In our work, we demonstrate that
starvation is a serious problem and present a protocol to prevent it. It
is shown that the new protocol is correct, stable.",
}

@INPROCEEDINGS{Simo91:Interconnection,
AUTHOR="N. Simoni and S. Znaty and A. Savoye and M. Michelin",
TITLE="Interconnection of high speed data networks: Quality of service
and dynamic control",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="51-56",
YEAR=1991,
KEYWORDS="Control; service level; hsLAN; MAN; interconnection",
ANNOTE="Our paper intends to present the adopted process and the means
used to dynamically manage the internetworking devices and the transfer
data protocols.",
}

@INPROCEEDINGS{Simo91:Fluid,
AUTHOR="A. Simonian",
TITLE="Fluid Queueing Models for an {ATM} Multiplexer",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="57-59",
YEAR=1991,
REFERENCES=10,
KEYWORDS="ATM; multiplexer; fluid flow model",
ANNOTE="In the paper, we are concernded with modelling queues in the
burst scale.",
}

@INPROCEEDINGS{Tang91:Mean,
AUTHOR="M. Tangemann",
TITLE="Mean Value Analysis of {FDDI}",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="83-87",
YEAR=1991,
REFERENCES=8,
KEYWORDS="FDDI; analysis; MAN; HSLAN",
ABSTRACT="This paper deals with a mean value analysis of an FDDI system
with synchronous and asynchronous traffic over the whole load range.
Although the analysis derived here is simple, it considers the main
effects that determine the performance of the MAC protocol, which is
derived in terms of throughputs of asynchronous as well as synchronous
packets. Some examples are discussed, and the results are validated by
detailed simulation.",
}

@INPROCEEDINGS{Tonk91:Future,
AUTHOR="B. A. Tonkin and F. Symons",
TITLE="Future Applications for {MANs}",
BOOKTITLE="Australian Broadband Switching and Services Symposium",
ADDRESS="Sydney",
VOLUME=1,
PAGES="130-137",
YEAR=1991,
REFERENCES=13,
KEYWORDS="MAN; DQDB; Application; Multimedia",
ANNOTE="This paper describes future applications for MANs that make use
of workstations and personal computers already connected to local area
networks. It suggests areas that require further research, which may
provide ideas for postgraduate and collaborative research projects.",
}

@INPROCEEDINGS{Tran91:CRMA,
AUTHOR="P. Tran-Gia and R. Dittmann",
TITLE="Performance Analysis of the {CRMA-Protocol} in High-Speed
Networks",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="5-24",
YEAR=1991,
REFERENCES=11,
KEYWORDS="CRMA; cyclic reservation multiple access; MAN; HSLAN;
performance analysis",
ANNOTE="In this paper a performance analysis of the CRMA medium access
protocol is presented. An approximate computational method is derived to
obtain the distribution functions of performance measures of interest
like the medium access delay and the packet transfer time. The
reservation-cancelation backpressure mechanism is also taken into
account in the model. Fairness, jitter of maximum access delay and
several overload conditions are discussed.",
}

@INPROCEEDINGS{Wats91:Gbit,
AUTHOR="G. N. Watson and S. Ooi",
TITLE="What should a Gbit/s network interface look like?",
BOOKTITLE="IFIP",
PAGES="237-250",
YEAR=1991,
REFERENCES=15,
KEYWORDS="Interface; hardware; media access control; lan",
ANNOTE="In this paper we focus on the architecture of a network
interface unit for a Gbit/s network and describe how our architecture
provides the variety of services that might be needed. We comment on
some architectural decisions in the light of experience gained from
constructing a prototype network, and we relate our work to that of
others in the field.",
}

@INPROCEEDINGS{Zein91:Satellite,
AUTHOR="T. Zein and G. Maral and D. Seret and M. Tondriaux",
TITLE="Satellite access to the Broadband {ISDN:} a {DAMA} approach",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart",
PAGES="37-40",
YEAR=1991,
REFERENCES=5,
KEYWORDS="Satellite radio; BISDN; ATM",
ANNOTE="We propose a new demand assignment multiple access (DAMA) with
two types of services: delay sensitive and delay insensitive. The
capacity of the satellite link is dynamically shared between both
services at the call set-up level. At the transfer level. stream type
connections are handled by fixed allocation, while capacity assignment
to bursty connections is done in a reservation-allocation manner
according to a new mechanism.",
}

@TECHREPORT{Bane91:Real,
AUTHOR="A. Banerjea and Bruce A. Mah",
TITLE="The Real-Time Channel Administration Protocol.",
TYPE="Technical Report",
INSTITUTION="UC Berkeley",
PAGES="1-11",
YEAR=1991,
KEYWORDS="realtime; delay variance (jitter); bandwidth allocation;
bandwidth management; traffic management; Real-Time Internet Protocol
(RTIP); RMTP (Real-Time Message Transport Protocol); CMTP (Continuous
Media Transport Protocol); XUNET II; ATM; FDDI",
ABSTRACT="The Real-time Channel Administration Protocol (RCAP) provides
control and administration services for the Tenet real-time protocol
suite, a connection-oriented suite of network and transport layer
protocols for real-time communication. RCAP performs per-channel
reservation of network resources based on worst-case analysis to provide
hard guarantees on delay, jitter, and packet loss bounds. It uses a
hierarchical approach to provide these guarantees across a heterogeneous
internetwork environment. In this paper, we outline our assumptions and
approaches to real-time communication. We then describe the service
provided by RCAP, the protocol itself, our plans for implementation, and
current status of our research.",
URL="ftp://tenet.berkeley.edu/pub/tenet/Papers/BanMah91.ps",
}

@TECHREPORT{Cace91:Separating,
AUTHOR="R. Caceres",
TITLE="Separating Abstraction from Implementation in Communication
Network Design",
TYPE="Technical Report",
INSTITUTION="UC Berkeley",
PAGES="1-12",
YEAR=1991,
KEYWORDS="VC (virtual channel) datagram flow control congestion control
network; stateless network; stateful connection establishment/teardown
routing buffer allocation",
ABSTRACT="Datagrams and virtual circuits are not disjoint conceptual
models for data communication, but rather inhabitants of a wide design
space containing many other viable networking solutions. Many design
choices often closely associated with these two communication styles can
be decoupled from the datagram and virtual circuit abstractions, and
combined to form new and effective network implementations. This paper
examines several key elements of network architecture. For each element,
it shows how certain characteristics often thought to differentiate
datagrams and virtual circuits are independent of these two concepts and
form a multi-valued spectrum of design choices. This discussion is
motivated by the current drive to design a new generation of high-speed
wide-area networks, and the observation that this effort would benefit
from a more systematic evaluation of existing and future network design
alternatives.",
URL="ftp://tenet.berkeley.edu/pub/tenet/Papers/Caceres89a.ps",
}

@TECHREPORT{Ramo91:Efficiency,
AUTHOR="R. Caceres",
TITLE="Efficiency of Asynchronous Transfer Mode Networks in Transporting
Wide-Area Data Traffic",
TYPE="Technical Report",
INSTITUTION="UC Berkeley",
PAGES="1-14",
YEAR=1991,
KEYWORDS="ATM traffic analysis traffic measurement TCP/IP UDP TCP/IP
header compression ATM transmission overhead (header; trailer;
alignment; padding) Message Stream Protocol (MSP) Frame Relay SMDS XUNET
2 SAR (segmentation and reassembly sublayer) NNStat WAN",
ABSTRACT="For performance and economic reasons, ATM networks must
efficiently support the Internet family of protocols. We calculate the
transmission efficiency achieved by a range of ATM-related protocols
when transporting TCP and UDP wide-area traffic. We also compare the
efficiency effects of several non-standard compression techniques. To
assure an accurate workload characterization, we drive these
calculations with millions of wide-area packet lengths measured on the
current Internet. We find that networks using standard ATM procedures
are dismally inefficient in carrying traditional data traffic -
depending on the protocols used, efficiency as seen by an application
program ranges between 40 and 53\%. Moreover, due to interaction between
TCP-IP datagram lengths and ATM cell padding, efficiency responds
abruptly to changes in certain protocol parameters - for example, a
4-byte increase in ATM cell payload size can yield a 10\% increase in
efficiency. Using one compression technique in isolation can improve
efficiency by 12\%, and simultaneously using three techniques can
improve it by 34\%. These issues should be considered when designing
future ATM networks.",
URL="ftp://tenet.berkeley.edu/pub/tenet/Papers/Caceres91b.ps",
}

@TECHREPORT{Uz91:Multiresolution,
AUTHOR="Kamil M. Uz and K. Ramchandran and M. Vetterli",
TITLE="Multiresolution Source and Channel Coding for Digital Broadcast
of {HDTV}",
TYPE="Technical Report",
INSTITUTION="Columbia University",
PAGES="1-10",
NOTE="presented in part at the 4th International Workshop on HDTV,
Torino, Italy, September 1991",
YEAR=1991,
ABSTRACT="HDTV; end-to-end all-digital multiresolution system; joint
source-channel coding and modulation to achieve efficient broadcast of
digital HDTV; threshold effect; multiresolution source coding;
multiresolution transmission; 64-QAM; comparison of multiresolution,
single resolution, and independent constellations; simulation of an
Additive White Gaussian Noise (AWGN) for MR, SR and independent
constallations; video",
URL="ftp://ftp.ctr.columbia.edu/pub/papers/image/92/ram92b.ps",
}

@BOOK{Watk91:ART,
AUTHOR="John Watkinson",
TITLE="The art of digital video",
ISBN="0-240-51287-1",
PUBLISHER="Focal Press",
PAGES="580 pages",
YEAR=1991,
KEYWORDS="book video; digital DAC DSP (digital signal processing) DVTR
audio; digital",
ABSTRACT="Chapter 1 Why Digital? Chapter 2 Conversion Chapter 3 Digital
video coding and processing Chapter 4 The C-format timebase corrector
Chapter 5 Advanced digital processing Chapter 6 Digital magnetic and
optical recording Chapter 7 Error correction Chapter 8 Digital video
interconnects Chapter 9 Rotary-head tape transports Chapter 10 The D-1
Colour difference DVTR format Chapter 11 The D-2 composite digital
format Chapter 12 Disk drives in digital video Chapter 13 Digital audio
with video",
}

@MISC{Smou91:PACKET,
AUTHOR="M. Smouts",
TITLE="{PACKET} {SWITCHING} {EVOLUTION} {FROM} {N-ISDN} {TO} {B-ISDN}",
ISBN="0-89006-542-X",
NOTE="CIP (Dec. 91) TK5105.S59 1991",
YEAR=1991,
KEYWORDS="book; BISDN; NISDN; ISDN; packet switching",
}

@MISC{Hand91:Integrated,
AUTHOR="Rainer Handel and M. Huber",
TITLE="Integrated Broadband Networks: An introduction to {ATM-based}
networks",
ISBN="0-201-54444-X",
YEAR=1991,
KEYWORDS="book; BISDN; ATM",
ABSTRACT="1 Introduction 1.1 The Current Situation 1.2 The Idea of the
Integrated Services Digital Network 1.3 BISDN 1.3.1 What is BISDN? 2
BISDN Service Requirements 3 Principles and Building Blocks of BISDN 3.1
BISDN Principles 3.2 Asynchronous Transfer Mode 3.3 Optical Transmission
4 BISDN Network Concept 4.1 General Architecture of the BISDN 4.2
Networking Techniques 4.2.1 Network Layering 4.2.2 Switching of Virtual
Channels and Virtual Paths 4.2.3 Applications of Virtual Channel/Path
Connections 4.3 Signalling Principles 4.3.1 General Aspects 4.3.2
Capabilities Required for BISDN Signalling 4.3.3 Signalling Virtual
Channels 4.4 Broadband Network Performance 4.5 Traffic Control and
Resource Management 4.5.1 Overview of Traffic Control Functions 4.5.1.1
Connection Admission Control 4.5.1.2 Usage Parameter Control 4.5.1.3
Priority Control 4.5.1.4 Congestion Control 4.5.2 Traffic Control
Procedures and Their Impact on Resource Management 4.6 Operation and
Maintenance Aspects 4.6.1 General Principles 4.6.2 OAM Levels in BISDN
4.7 Customer Network Aspects 4.7.1 Reference Configuration of the BISDN
UNI 4.7.2 Customer Categories 4.7.3 General Requirements 4.7.4
Topologies 4.7.5 Interworking with Existing Networks 5 BISDN
User-Network Interfaces and Protocols 5.1 BISDN Protocol Reference Model
5.1.1 General Aspects 5.1.2 Layered Architecture 5.1.3 Relationship
Between the BISDN PRM and the OSI Reference Model 5.1.4 BISDN PRM
Description 5.1.5 Layer Functions 5.1.5.1 Cell Terminology 5.1.5.2
Physical Layer Functions 5.1.5.3 ATM Layer Functions 5.1.5.4 ATM
Adaptation Layer Functions 5.1.6 Primitives and Information Flows
5.1.6.1 Physical Layer and ATM Layer Primitives 5.1.6.2 Information
Flows of the Physical Layer 5.1.7 Relationship of OAM Functions with the
BISDN PRM 5.2 General Aspects of the User-Network Interface 5.2.1
Transfer Mode 5.2.2 Bit Rates 5.2.3 Interface Structure 5.2.4 BISDN UNI
Reference Configuration and Physical Realizations 5.2.5 Special Issues
5.3 Physical Layer of the user-Network Interface 5.3.1 Functions of the
Transmission Convergence Sublayer 5.3.1.1 SDH-Based Interface at 155.520
Mbit/s 5.3.1.2 SDH-Based Interface at 622.080 Mbit/s 5.3.1.3 Cell-Based
Interface 5.3.1.4 Cell Rate Decoupling 5.3.1.5 Header Error Control
5.3.1.6 Cell Delineation 5.3.2 Physical Medium Characteristics 5.3.2.1
Physical Medium 5.3.2.2 Bit Timing and Interface Code 5.3.2.3 Power
Feeding 5.3.2.4 Modes of Operation 5.4 ATM Layer 5.4.1 Cell Structure
5.4.2 Cell Header 5.4.2.1 Pre-Assigned Cell Header Values 5.4.2.2
Generic Flow Control 5.4.2.3 Virtual Path Identifier 5.4.2.4 Virtual
Channel Identifier 5.4.2.5 Payload Type 5.4.2.6 Reserved Field 5.4.2.7
Cell Loss Priority 5.4.2.8 Header Error Control 5.4.3 ATM Layer
Connections 5.4.3.1 Active Connections at the BISDN UNI 5.4.3.2 Virtual
Channel Connections 5.4.3.3 Virtual path Connections 5.5 ATM Adaptation
Layer [NOTE: I'm leaving out detail in the remainder of this table of
contents until I get some time to finish it. -allen] 5.6 Higher Layers
5.7 Operation and Maintenance of the BISDN UNI 6 ATM Switching 7 ATM
Transmission Network 8 Evolution Scenarios for BISDN 9 Miscellaneous 10
Outlook Appendix A BISDN Standardization Appendix B BISDN and DQDB
Protocols",
ANNOTE="maximum one-way voice delay is 400 ms [p. 175]. As a rule of
thumb, echo cancellation should be employed whenever a one-way delay of
about 25 ms is exceeded. [hgs]",
}

@ARTICLE{Wong91:Distributed,
AUTHOR="Jing-Win Wong and Anand K. Varadachari",
TITLE="Performance Analysis of the Distributed Queuing Protocol used in
{QPSX}",
JOURNAL="Journal of Data and Computer Communications",
PAGES="54-62",
MONTH="Summer",
YEAR=1991,
ABSTRACT="QPSX; MAN; IEEE 802.6; simulation; performance",
}

@INPROCEEDINGS{Fuji91:Multimedia,
AUTHOR="Kenji Fujikawa",
TITLE="Multimedia presentation System with Temporal and Active Media",
BOOKTITLE=usenixs,
ADDRESS="Nashville",
PAGES="75-93",
MONTH="Summer",
YEAR=1991,
ABSTRACT="multimedia",
}

@INPROCEEDINGS{Weis9106:Advanced,
AUTHOR="Christoph Weiss and Fridtjof. Berlin and Dieter. Geller",
TITLE="Advanced Voice Communication with Acoustic Echocancelling and
Enhanced Sound Quality",
BOOKTITLE=icc,
ISBN="0-7803-0006-8",
VOLUME=1,
PAGES="478-483 (17.1)",
YEAR=1991,
KEYWORDS="echo cancellation; coding; coder; DSP (digital signal
processing); codec; ADPCM (adaptive pulse code modulation); adaptive
digital FIR filter/ G.722; AT\\&T DSP16; digital signal processor;
DSP56200; TLC32044",
ABSTRACT="This paper initially considers speech coding according to
CCITT-Rec. G.722, which allows an increased audio bandwidth of 7 kHz at
a data rate of 64 kbit/s in the ISDN. The problem of handsfree telephony
will then be afforded special attention and a solution will be proposed
utilizing an acoustic echocanceller. The objective was to develop a
compact implementation of both algorithms, using digital signal
processors, which also provides for optimal determination and control of
system parameters. The results will be discussed and applications for
future services will be presented.",
}

@BOOK{Effe91:Kommunikation,
TITLE="Kommunikation in Verteilten Systemen -- Grundlagen, Anwendungen,
Betrieb",
EDITOR="Wolfgang Effelsberg and Hans W. Meuer and Günter Müller",
ISBN="0-387-53721-X",
PUBLISHER="Springer-Verlag, Berlin Heidelberg",
NOTE="GI/ITG-Fachtagung, Mannheim",
YEAR=1991,
}

@INPROCEEDINGS{Hofm91:Analyse,
AUTHOR="Bernd Hofmann",
TITLE="Analyse und Optimierung von Protokollspezifikationen",
BOOKTITLE="Kommunikation in Verteilten Systemen, {\rm GI/ITG-Fachtagung,
Mannheim}",
EDITOR="W. Effelsberg and Hans W. Meuer and G. Müller",
SERIES="Informatik-Fachberichte 267",
ISBN="0-387-53721-X",
PUBLISHER="Springer-Verlag, Berlin Heidelberg",
PAGES="568-584",
YEAR=1991,
}

@INPROCEEDINGS{Lamp91:X,
AUTHOR="B. Lamparter and W. Effelsberg",
TITLE="{X-MOVIE:} Digitale Filmübertragung und Darstellung im
X-Window-System",
BOOKTITLE="Telekommunikation und multimediale Anwendungen der
Informatik, Tagungsband GI-21. Jahrestagung",
SERIES="Informatik-Fachberichte 293",
PUBLISHER="Springer-Verlag, Berlin Heidelberg",
ADDRESS="Darmstadt",
PAGES="343-352",
YEAR=1991,
}

@BOOK{Andr91:Concurrent,
AUTHOR="G. R. Andrews",
TITLE="Concurrent Programming. Principles and Practice",
ISBN="0-8053-0086-4",
PUBLISHER="Benjamin Cummings",
YEAR=1991,
}

@INPROCEEDINGS{Vale91:Derivation,
AUTHOR="A. Valenzano and C. Sisto",
TITLE="Derivation of Executable Code from Formal Protocol Specifications
Written in {LOTOS}",
BOOKTITLE="of TriComm",
ADDRESS="Chapel Hill",
YEAR=1991,
}

@TECHREPORT{Crow91:Multimedia,
AUTHOR="Jon Crowcroft and Ian Wakeman",
TITLE="Multimedia Packet Teleconferencing Systems and Workstations",
TYPE="RN/91/46",
INSTITUTION="EurOpen Forum for Open Systems",
VOLUME=11,
NUMBER=3,
PAGES="2-6",
MONTH="Autumn",
YEAR=1991,
}

@INPROCEEDINGS{Sore91:CLOWN,
AUTHOR="S.-A. Sorensen and M. Jones",
TITLE="The {CLOWN} Network Simulator",
BOOKTITLE="Seventh UK Performance Engineering Workshop",
PUBLISHER="Springer Verlag",
VOLUME=1,
YEAR=1991,
KEYWORDS="simulators; tools",
}

@BOOK{Pear91:Image,
AUTHOR="Don Pearson",
TITLE="Image Processing",
PUBLISHER="McGraw-Hill",
YEAR=1991,
ABSTRACT="A book covering most of the British work in Image processing
and compression",
}

@INPROCEEDINGS{Fitz91:Evaluating,
AUTHOR="R. Fitzgerald and P. Rosson and L. Uljon",
TITLE="Evaluating Alternative Display Sharing System Architectures",
BOOKTITLE="of TriComm",
ADDRESS="Chapel Hill",
YEAR=1991,
}

@INPROCEEDINGS{Kats91:Synchronisation,
AUTHOR="H. P. Katseff and R. D. Gaglianello",
TITLE="On the Synchronisation of Multiple Full Motion Video Streams",
BOOKTITLE="of TriComm",
ADDRESS="Chapel Hill",
YEAR=1991,
}

@ARTICLE{Blai91:Incorporating,
AUTHOR="Paul Blair and Geoff Coulson and W. S. Davies",
TITLE="Incorporating Multimedia in Distributed Open Systems",
JOURNAL="UK USENIX",
YEAR=1991,
}

@INPROCEEDINGS{Pei91:VLSI,
AUTHOR="Tong-Bi Pei and Charles. Zukowski",
TITLE="{VLSI} Implementations of Routing Tables: {TRIES} and {CAMS}",
BOOKTITLE=infocom,
YEAR=1991,
}

@INPROCEEDINGS{Powe91:Sun,
AUTHOR="Mike L. Powell and S. R. Kleinman and S. Barton and D. Shah and
D. Stein and M. Weeks",
TITLE="{SunOS} Multi-thread Architecture",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH="Winter",
YEAR=1991,
KEYWORDS="distributed systems",
}

@TECHREPORT{Danz91:Tcplib,
AUTHOR="Peter Danzig and S. Jamin",
TITLE="tcplib: A Library of {TCP} Internetwork Traffic characteristics",
INSTITUTION="Computer Science Department, University of Southern
California",
ADDRESS="Los Angeles, California",
NUMBER="USC-CS-91-495",
YEAR=1991,
REFERENCES=15,
KEYWORDS="Traffic characteristic; tcplib; network simulation",
ABSTRACT="This paper describes tcplib, a workload or source library for
network simulation.  This paper motivates the need for tools like tcplib
and discusses how to incorporate it into a network simulatior. Tcplib is
available by anonymous ftp.",
URL="ftp://jerico.usc.edu/pub/jamin/tcplib/tcplibtr.ps.Z",
}

@ARTICLE{Sait91:Optimal,
AUTHOR="H. Saito",
TITLE="Optimal control of variable rate coding with incomplete
observation in integrated voice/data packet networks",
JOURNAL=ejor,
PAGES="0047-0064",
YEAR=1991,
KEYWORDS="Traffic control; ATM; BISDN; queueing theory; coding rate
control",
}

@BOOK{Wall9101:Programming,
AUTHOR="Larry Wall and Randal L. Schwartz",
TITLE="Programming perl",
ISBN="0-937175-64-1",
PUBLISHER="O'Reilly",
ADDRESS="Sebastopol, California",
PAGES=482,
YEAR=1991,
KEYWORDS="Perl; computer languages; programming; script language",
ABSTRACT="An authoritative guide to the hottest new UNIX utility in
years, co-authored by its creator, Larry Wall.  Perl is a language for
easily manipulating text, files, and processes.  Programming perl Covers
Perl syntax, functions, debugging, efficiency, the Perl library, and
more.",
}

@TECHREPORT{Danz91:Fingerns,
AUTHOR="Peter Danzig and Mark Diamond",
TITLE="Fingerns",
INSTITUTION="USC",
YEAR=1991,
URL="ftp://catarina.usc.edu/pub/fingerns/",
}

@TECHREPORT{JTCS91:Intermediate,
AUTHOR="ISO/IEC/ JTC1/SC6",
TITLE="Intermediate System to Intermediate System Inter-domain Routeing
Exchange Protocol",
INSTITUTION="International Standards Organization",
NUMBER="CDXXXX",
YEAR=1991,
}

@TECHREPORT{Skel91:Histogram,
AUTHOR="Paul. Skelly and M. Schwartz",
TITLE="A Histogram Based Model for Video Traffic Behavior in an {ATM}
Network Node with an Application to Congestion Control",
INSTITUTION="Columbia University",
NUMBER="CU/CTR/TR 228-91-09",
YEAR=1991,
}

@TECHREPORT{Katz91:Study,
AUTHOR="A. R. Katz and Stephen Casner",
TITLE="Study of {FAX} Compression Algorithms",
INSTITUTION="ISI, University of Southern California",
YEAR=1991,
}

@TECHREPORT{Floy91:Connections,
AUTHOR="S. Floyd",
TITLE="Connections with Multiple Congested Gateways in Packet-Switched
Networks Part1: One-way Traffic",
INSTITUTION="Lawrence Berkeley Labs",
YEAR=1991,
}

@TECHREPORT{Stal91:GNU,
AUTHOR="Stallman",
TITLE="{GNU} C User and Porting Guide",
INSTITUTION="MIT",
YEAR=1991,
}

@BOOK{Gosc91:Distributed,
AUTHOR="Andrzej Goscinski",
TITLE="Distributed Operating Systems The Logical Design",
PUBLISHER="Addison-Wesley",
YEAR=1991,
}

@ARTICLE{Wagn9101:Algorithmic,
AUTHOR="D. B. Wagner",
TITLE="Algorithmic Optimizations of Conservative Parallel Simulations",
JOURNAL="SCS Multiconference: Advances in Parallel and Distributed
Simulation",
VOLUME=23,
NUMBER=1,
PAGES="25-32",
YEAR=1991,
}

@TECHREPORT{Stas91:Animating,
AUTHOR="J. T. Stasko",
TITLE="Animating Parallel Programs",
INSTITUTION="Georgia Tech",
NUMBER="Draft",
YEAR=1991,
}

@TECHREPORT{Ordi91:Active,
AUTHOR="Joann Ordille and Barton P. Miller",
TITLE="Active Cataloguing and Caching in a Descriptive Name Service",
INSTITUTION="Computer Science Department, University of
Wisconsin-Madison, Madison, Wisconsin",
YEAR=1991,
}

@ARTICLE{Smet91:Distributed,
AUTHOR="B. Smetaniuk",
TITLE="Distributed Operation of the {X.500} Directory",
JOURNAL=cnis,
PAGES="17-40",
YEAR=1991,
}

@ARTICLE{Ural9104:Test,
AUTHOR="H. Ural and B. Yang",
TITLE="A test sequence selection method for protocol testing",
JOURNAL=ieeecom,
VOLUME=39,
NUMBER=4,
PAGES="514-523",
YEAR=1991,
}

@PROCEEDINGS{Kroo91:4th,
TITLE="4th {IFIP} {WG6.1} Intern. Workshop on Protocol Test Systems,
Leidschendamm, The Netherlands",
BOOKTITLE="4th IFIP WG6.1 International Workshop on Protocol Test
Systems, Leidschendamm, The Netherlands",
EDITOR="J. Kroon and E. Brinksma",
SERIES="IFIP Transactions",
PUBLISHER="North-Holland",
YEAR=1991,
}

@MANUAL{ISO91:9646.1,
AUTHOR="I. S. O",
TITLE="{IS} 9646 Part 1: General Concepts",
YEAR=1991,
}

@MANUAL{ISO91:9646.2,
AUTHOR="I. S. O",
TITLE="{IS} 9646 Part2: Abstract Test Suite Specification",
YEAR=1991,
}

@MANUAL{ISO91:9646.4,
AUTHOR="I. S. O",
TITLE="{IS} 9646 Part4: Test Realization",
YEAR=1991,
}

@MANUAL{ISO91:9646.5,
AUTHOR="I. S. O",
TITLE="{IS} 9646 Part5: Requirements on Test Labs and Clients for the
Conformance Assessment Process",
YEAR=1991,
}

@PROCEEDINGS{Jons91:11th,
TITLE="11th Intern. Symposium on Protocol Specification, Testing and
Verification, Stockholm, Sweden",
BOOKTITLE="11th International Symposium on Protocol Specification,
Testing and Verification, Stockholm, Sweden",
EDITOR="B. Jonsson and J. Parrow and B. Pehrson",
SERIES="IFIP Transactions",
PUBLISHER="North-Holland",
YEAR=1991,
}

@INPROCEEDINGS{Velt91:Relating,
AUTHOR="R. J. Velthyus and G. Zörntlein",
TITLE="Relating events for conformance testing --- a pragmatic
approach",
BOOKTITLE="4th IFIP WG6.1 International Workshop on Protocol Test
Systems, Leidschendamm, The Netherlands",
EDITOR="J. Kroon and E. Brinksma",
SERIES="IFIP Transactions",
PUBLISHER="North-Holland",
PAGES="267-282",
YEAR=1991,
}

@INPROCEEDINGS{Brin91:Framework,
AUTHOR="Ed Brinksma and J. Tretmans and L. Verhaard",
TITLE="A Framework for Test Selection",
BOOKTITLE="11th International Symposium on Protocol Specification,
Testing and Verification, Stockholm, Sweden",
EDITOR="B. Jonsson and J. Parrow and B. Pehrson",
SERIES="IFIP Transactions",
PUBLISHER="North-Holland",
PAGES="216-231",
YEAR=1991,
}

@INPROCEEDINGS{Wvon91:LAPB,
AUTHOR="R. Wvong",
TITLE="{LAPB} Conformance Testing Using Trace Analysis",
BOOKTITLE="11th International Symposium on Protocol Specification,
Testing and Verification, Stockholm, Sweden",
EDITOR="B. Jonsson and J. Parrow and B. Pehrson",
SERIES="IFIP Transactions",
PUBLISHER="North-Holland",
PAGES="248-261",
YEAR=1991,
}

@INPROCEEDINGS{Br91:Presentation,
AUTHOR="U. Bär and M. Strecker and W. Stoll and W. Effelsberg",
TITLE="Presentation Layer Conformance Testing with {TTCN}",
BOOKTITLE="11th International Symposium on Protocol Specification,
Testing and Verification, Stockholm, Sweden",
EDITOR="B. Jonsson and J. Parrow and B. Pehrson",
SERIES="IFIP Transactions",
PUBLISHER="North-Holland",
PAGES="262-277",
YEAR=1991,
}

@INPROCEEDINGS{v.Bo91:Fault,
AUTHOR="G. v.Bochmann and A. Das and R. Dssouli and M. Dubuc and A.
Ghedamski and G. Luo",
TITLE="Fault models in testing",
BOOKTITLE="11th International Symposium on Protocol Specification,
Testing and Verification, Stockholm, Sweden",
EDITOR="B. Jonsson and J. Parrow and B. Pehrson",
SERIES="IFIP Transactions",
PUBLISHER="North-Holland",
PAGES="17-30",
YEAR=1991,
}

@INPROCEEDINGS{v.d.91:Real,
AUTHOR="M. E. v.d.Haven and Maarten Kockelmans and E. J. Slotboom",
TITLE="Real effects testing of {OSI} applications",
BOOKTITLE="11th International Symposium on Protocol Specification,
Testing and Verification, Stockholm, Sweden",
EDITOR="B. Jonsson and J. Parrow and B. Pehrson",
SERIES="IFIP Transactions",
PUBLISHER="North-Holland",
PAGES="107-119",
YEAR=1991,
}

@TECHREPORT{Grea91:Preliminary,
AUTHOR="David Greaves and K. Zielinski",
TITLE="Preliminary Performance Results for {CBN} Half-Duplex {VME}
Stations {(V1S)}",
TYPE="Technical Report",
INSTITUTION="Olivetti Research Laboratory (ORL)",
ADDRESS="Cambridge, England",
NUMBER="TR 91-5",
NOTE="Document identification OSI95/Deliverable ORL-1 annex/V1",
YEAR=1991,
ABSTRACT="The CBN (Cambridge Backbone Network) offers an ATM LAN/MAN
architecture based around a source release slotted ring. The current
implementation operates at 512 MHz, interconnecting five sites at
Olivetti Research Limited and the University of Cambridge Computer
Laboratory. This paper reports performance measurements of this first
implementation in terms of throughput and response time, when using the
V1S CBN station interface, Motorola MVME 147 68030 CPU cards (20MHz),
the MSNA (multi-service network architecture) fragmentation protocol and
the Wanda micro-kernel. The purpose of this work was to identify
throughput limitation in the current station interface and protocol
stack, in order to guide future development.",
URL="ftp://ftp.cam-orl.co.uk/pub/docs/ORL/tr.91.5.ps.Z",
}

@TECHREPORT{Grea91:ATM,
AUTHOR="David Greaves and D. Milway and David Garnett and Andrew
Hopper",
TITLE="Design and Implementation of an {ATM} Backbone Ring",
TYPE="Technical Report",
INSTITUTION="Olivetti Research Laboratory (ORL)",
ADDRESS="Cambridge, England",
NUMBER="TR 91-4",
YEAR=1991,
ABSTRACT="The Cambridge Backbone Ring (CBR) is a collaborative project
between Olivetti Research Limited and the University of Cambridge
Computer Laboratory. The project has designed and built and experimental
ring communication network for computer data, and real-time
applications. The network forms a backbone facility for interconnecting
groups of CFR (Cambridge Fast Ring) networks and Pandora multi-media
workstations in the Cambridge area. Access control uses the empty slot
protocol, using short, fixed-length cells which contain 32 bytes of
payload and a 4 byte header containing the virtual circuit identifier.
Although the architecture was designed for line rates of 1Gbit/second
and higher, the current implementation operates at 512 MHz. Twenty-five
stations have been constructed, to date. A revision incorporating the
now-standard, 48 byte cells, and operating at a higher line-rate, is
planned.",
URL="ftp://ftp.cam-orl.co.uk/pub/docs/ORL/tr.91.4.ps.Z",
}

@TECHREPORT{Wilk91:Computing,
AUTHOR="M. V. Wilkes",
TITLE="Computing Perspectives",
TYPE="Technical Report",
INSTITUTION="Olivetti Research Laboratory (ORL)",
ADDRESS="Cambridge, England",
NUMBER="TR 91-3",
NOTE="Columns reprinted from the Communications of the ACM. April 1990
-- August 1991",
YEAR=1991,
ABSTRACT="Columns with the following titles: Computer Security in the
Business World -- Networks, Email, and Fax -- The Bandwidth Famine --
It's All Software Now -- The Rise of the VLSI Processor -- Software and
the Programmer -- Revisiting Computer Security in the Business World",
}

@TECHREPORT{Wilk91:Progress,
AUTHOR="M. V. Wilkes",
TITLE="Progress and Research in the Computer Industry",
TYPE="Technical Report",
INSTITUTION="Olivetti Research Laboratory (ORL)",
ADDRESS="Cambridge, England",
NUMBER="TR 91-1",
NOTE="<Royal Society Clifford Patterson Lecture, 15 November 1990. Phil.
Trans R. Soc. Lond. A(1991)334, 173-184",
YEAR=1991,
ABSTRACT="The paper surveys the technical progress which has occurred in
the computer industry in the recent past and the way in which the
relationship between that industry and the semi-conductor industry has
developed. Research in the computer industry is now dominated by
software, a subject which has an intellectual basis rather than a basis
in the experimental sciences. For this reason, the management of
research in the computer industry presents problems of its own.",
}

@BOOK{Bell91:Digital,
AUTHOR="John Bellamy",
TITLE="Digital Telephony",
ISBN="0-471-62056-4",
PUBLISHER="John Wiley \\& Sons",
ADDRESS="New York",
YEAR=1991,
KEYWORDS="telephony; voice digitization; digital transmission and
multiplexing; digital switching; digital modulation and radio systems;
network synchronization; network control; network management; fiber
optic transmission systems; data and integrated services digital
networks; traffic analysis",
}

@TECHREPORT{Parr91:Modal,
AUTHOR="Joachim Parrow and David Walker",
TITLE="Modal Logics for Mobile Processes",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-03",
YEAR=1991,
ABSTRACT="In process algebras, bisimulation equivalence is typically
defined directly in terms of the operational rules of action; it also
has an alternative characterisation in terms of a simple modal logic
(sometimes called Hennessy-Milner logic . This paper first defines two
forms of bisimulation equivalence for the 031-calculus , a process
algebra which allows dynamic reconfiguration among processes; it then
explores a family of possible logics, with different modal operators. It
is proven that two of these logics characterise the two bisimulation
equivalences. Also, the relative expressive power of all the logics is
exhibited as a lattice.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-03--SE.ps.Z",
}

@TECHREPORT{Sahl91:Variable,
AUTHOR="Da Sahlin and Mats Carlsson",
TITLE="Variable Shunting for the {WAM}",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-07",
YEAR=1991,
ABSTRACT="This paper describes how to extend the garbage collection for
WAM so that it will shunt chains of bound variables if possible. Doing
so has two advantages: 1. Space is saved by making it possible to
deallocate the intermediate cells. This is particularly useful when
those cells are associated with frozen goals. 2. Later dereferencing is
speeded up by not having to follow long variable chains. The main
complication of this optimization is the treatment of the trailed
variables. We claim that all possible chains of variables are shunted by
this algorithm. The algorithm has been implemented in {SICStus} Prolog,
and benchmark results are presented in this paper. The full source code
for the shunting algorithm is given in this paper.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-07--SE.ps.Z",
}

@TECHREPORT{Jans91:Programming,
AUTHOR="and S. Haridi",
TITLE="Programming paradigms of the Andorra Kernel Language
Programming",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-08",
YEAR=1991,
ABSTRACT="The Andorra Kernel Language (AKL) is introduced. It is shown
how AKL provides the programming paradigms of both Prolog and GHC. This
is the original goal of the design. However, it has also been possible
to provide capabilities beyond that of Prolog and GHC. There are means
to structure search, more powerful thanplain backtracking. It is
possible to encapsulate search in concurrent reactiveprocesses. It is
also possible to write a multi-way merger with constant delay.In these
respects AKL is quite original. Although AKL is an instance of our
previously introduced Kernel Andorra Prolog framework, this exposition
contains important extensions, and a considerable amount of unnecessary
formal overhead has been stripped away.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-08--SE.ps.Z",
}

@TECHREPORT{Sjod91:Strong,
AUTHOR="Gunnar Sjödin and Clas Löfwall",
TITLE="Strong normalizability in Martin-Löf's Type Theory",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-09",
YEAR=1991,
ABSTRACT="In this paper we prove that any subexpression of a correct
judgement in Martin-Löf's Type Theory is strongly normalizable. We use
the well-established technique with a ``computability predicate''. The
logic used in the proof is classical set theory.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-09--SE.ps.Z",
}

@TECHREPORT{Aron91:Definitional,
AUTHOR="Martin Aronson",
TITLE="A Definitional Approach to the Combination of Functional and
Relational Programming",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-10",
YEAR=1991,
ABSTRACT="We show how the programming language GCLA can be used to
naturally express both relational and functional programs in an
integrated framework. We give a short introduction to GCLA, and to the
theory of partial inductive definitions on which GCLA is based. GCLA is
best regarded as a logic programming language, but instead of saying
that the query follows from the program in some a priori given logic, we
say that the program defines the logic in which the query is proved. We
then demonstrate how to implement both relational and functional
programs as well as a combination of them in GCLA.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-10--SE.ps.Z",
}

@TECHREPORT{Nils91:External,
AUTHOR="Hans Nilsson",
TITLE="The External Storage Facility in {SICStus} Prolog",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-13",
YEAR=1991,
ABSTRACT="The {SICStus} Prolog External Database implements an efficient
way of storing possibly non-ground Prolog terms on disk with indexing on
user specified parts of the terms. The model and the implementation are
described and some performance data are given.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-13--SE.ps.Z",
}

@TECHREPORT{Lisp91:Formal,
AUTHOR="Björn Lisper",
TITLE="Formal derivation of concurrent assignements from scheduled
single",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-15",
YEAR=1991,
ABSTRACT="Concurrent assignments are commonly used to describe
synchronous parallel computations. We show how a sequence of concurrent
assignments can be formally derived from the schedule of an acyclic
single assignment task graph and a memory allocation. In order to do
this we develop a formal model of memory allocation in synchronous
systems. We use weakest precondition semantics to show that the sequence
of concurrent assignments computes the same values as the scheduled
single assignments. We give a lower bound on the memory requirements of
memory allocations for a given schedule. This bound is tight: we define
a class of memory allocations whose memory requirements always meets the
bound. This class corresponds to conventional register allocation for
DAGs and is suitable when memory access times are uniform. We
furthermore define a class of simple ``shift register'' memory
allocation. These allocations have the advantage of a minimum of
explicit storage control and they yield local or nearest-neighbour
accesses in distributed systems whenever the schedule allows this. Thus,
this class of allocations is suitable when designing parallel
special-purpose hardware, like systolic arrays.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-15--SE.ps.Z",
}

@TECHREPORT{Land91:Study,
AUTHOR="Anders Landin and S. Haridi",
TITLE="A performance study of the {DDM} - a cache-only memory
architecture",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-17",
YEAR=1991,
ABSTRACT="Large-scale multiprocessors suffer from long latencies for
remote accesses. Caching is by far the most popular technique for hiding
such delays. Caching not only hides the delay, but also decreases the
network load. Cache-Only Memory Architectures (COMA), have no physically
shared memory. Instead, all the memory resources are invested in caches,
resulting in caches of the largest possible size. A datum has no home,
and is moved by a protocol between the caches, according to its usage.
It might exist in multiple caches. Even though no shared memory exists,
the architecture still provides the shared memory view to a programmer.
Simulation results from large programs running on 64 processors indicate
that the COMA adapts well to existing programs for shared memory. They
also show that an application with a poor locality can benefit by
adopting to the COMA principle of no home for data, resulting in a
reduced execution time of a factor three. In a COMA, a large majority of
the misses are invalidation misses, or share misses caused by
write-once/read-many behavior, or a producer-consumer relation, i.e.
would ben- efit from write broadcast. A new protocol is proposed that
behaves like a write-invalidate protocol by default for all data. A
reader can detect its need for a write-broadcast behavior for a datum,
which it enables by sending a subscribe request for the datum to the
writer.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-17--SE.ps.Z",
}

@TECHREPORT{Land91:DDM,
AUTHOR="Anders Landin and S. Haridi",
TITLE="{DDM} - a cache-only memory architecture",
TYPE="Technical Report",
INSTITUTION="Swedish Institute of Computer Science (SICS)",
ADDRESS="Kista, Sweden",
NUMBER="R91-19",
YEAR=1991,
ABSTRACT="The long latencies introduced by remote accesses in a large
multiprocessor can be hidden by caching. Caching also decreases the
network load. We introduce a new class of architectures called Cache
Only Memory Architectures (COMA). These architectures provide the
programming paradigm of the shared-memory architectures, but have no
physically shared memory; instead, the caches attached to the processors
containallthe memory in the system, and their size is therefore large. A
datum is allowed to be in any or many of the caches, and will
automatically be moved to where it is needed by a cache-coherence
protocol,which also ensures that the last copy of a datum is never lost.
The location of a datum in the machine is completely decoupled from its
address. We also introduce one example of COMA: the Data Diffusion
Machine (DDM), and its simulated performance for large applications. The
DDM is based on a hierarchical network structure, with processor/memory
pairs at its tips. Remote accesses generally cause only a limited amount
of traffic over a limited part of the machine.",
URL="ftp://ftp.sics.se/pub/SICS-reports/Reports/SICS-R--91-19--SE.ps.Z",
}

@BOOK{Lidi91:Perspectives,
AUTHOR="W. P. Lidinsky and David Vlack",
TITLE="Perspectives on Packetized Voice and Data Communications",
ISBN="0-87942-233-5",
PUBLISHER="IEEE Press",
YEAR=1991,
KEYWORDS="packet voice; MAN; SuperMAN",
}

@BOOK{Perr91:VHDL,
AUTHOR="D. E. Perry",
TITLE="{VHDL}",
PUBLISHER="McGraw-Hill",
YEAR=1991,
KEYWORDS="Vhdl",
}

@INPROCEEDINGS{Cont91:IAPA,
AUTHOR="G. Conti",
TITLE="{IAPA} A New Protocol Architecture Based on Interacting
Activities",
BOOKTITLE="16th Conference On Local Computer Networks",
PUBLISHER="{IEEE} Computer Society Press",
YEAR=1991,
}

@ARTICLE{Peng9103:Data,
AUTHOR="W. Peng and S. Puroshothaman",
TITLE="Data Flow Analysis of {COmmunicating} Finite State machines",
JOURNAL=toplas,
VOLUME=13,
NUMBER=3,
PAGES="399-442",
YEAR=1991,
KEYWORDS="data flow analysis; data flow; compile; compiler;
optimization",
}

@INPROCEEDINGS{OMal91:Highly,
AUTHOR="Sean O'Malley and L. L. Peterson",
TITLE="A Highly Layered Architecture for High-Speed Networks",
BOOKTITLE="Protocols for High Speed Networks II",
EDITOR="M. E. Johnson",
PUBLISHER="Elsevier Science Publishers (North-Holland)",
PAGES="141-156",
YEAR=1991,
KEYWORDS="lazy; messages; optimization; microprotocol; architecture;
layer",
}

@ARTICLE{Sing9103:Relative,
AUTHOR="G. Singh and Arthur J. Bernstein",
TITLE="On the Relative Execution Times of Distributed Protocols",
JOURNAL="Internation Journal of Parallel Programming",
VOLUME=20,
NUMBER=3,
PAGES="203-235",
YEAR=1991,
KEYWORDS="resequencing; optimization; formal description; partial order;
knowledge logic",
}

@INPROCEEDINGS{Hwan91:Scheduling,
AUTHOR="CH Hwang and Yu Hsu and Y. Lin",
TITLE="Scheduling for {FUnctional} Pipelinging and Loop Winding",
BOOKTITLE="28th ACM/IEEE Design Automation Conference",
ORGANIZATION="ACM/IEEE",
PAGES="764-769",
YEAR=1991,
KEYWORDS="scheduling; pipeline",
}

@ARTICLE{Chen9101:Optimal,
AUTHOR="W.-Y. Cheng and R. R. Muntz",
TITLE="Optimal routing for closed queueing networks",
JOURNAL=pe,
ADDRESS="Netherlands",
VOLUME=13,
NUMBER=1,
PAGES="3-16",
YEAR=1991,
REFERENCES=26,
KEYWORDS="Routing; optimization; closed queueing network",
ABSTRACT="...a generalization of the vertex allocation scheme of
Tripathi and Woodside is presented.",
}

@ARTICLE{Leun9102:Single,
AUTHOR="K. K. Leung and M. Eisenberg",
TITLE="A single-server queue with vacations and non-gated time-limited
service",
JOURNAL=pe,
VOLUME=12,
NUMBER=2,
PAGES="115-125",
NOTE="also IEEE Infocom 1990, San Francisco, pp. 277-283",
YEAR=1991,
REFERENCES=12,
KEYWORDS="Queueing system; M/G/1; server vacation; waiting time",
ABSTRACT="The model is applicable to analyzing the (T1,T2)-priority
scheme used in the wideband packet network, token-passing networks, and
other systems where timers are used to allocate service (e.g. cyclic
service queues with time-limited service).",
}

@ARTICLE{Epem9101:Mean,
AUTHOR="D. H. J. Epema",
TITLE="Mean waiting times in a general feedback queue with priorities",
JOURNAL=pe,
ADDRESS="Netherlands",
VOLUME=13,
NUMBER=1,
PAGES="45-58",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Queueing system; M/G/1; preemptive priority; waiting time",
ABSTRACT="A general single server time-sharing model with multiple
queues and job classes, priorities and feedback is considered which
includes HOL, preemptive, and round robin scheduling.",
}

@ARTICLE{Mont9103:Statistical,
AUTHOR="José Augusto Suruagy Monteiro and M. Gerla and L. Fratta",
TITLE="Statistical multiplexing in {ATM} networks",
JOURNAL=pe,
ADDRESS="Netherlands",
VOLUME=12,
NUMBER=3,
PAGES="157-167",
YEAR=1991,
REFERENCES=18,
KEYWORDS="ATM; statistical multiplexing; traffic source model; fluid
flow model; bursty traffic; performance evaluation; connection admission
control",
ABSTRACT="In this paper we evaluate the statistical multiplexing gain
for bursty as well as VBR traffic using a fluid flow approximate model.
also:  4th international conference on data communications networks and
their performance.  June 20-22, 1990, Barcelona, Spain, 148-162",
}

@ARTICLE{Reim9101:Allocation,
AUTHOR="M. I. Reiman",
TITLE="Some allocation problems for critically loaded loss systems with
independent links",
JOURNAL=pe,
ADDRESS="Netherlands",
VOLUME=13,
NUMBER=1,
PAGES="219-235",
YEAR=1991,
REFERENCES=3,
KEYWORDS="Loss system; Erlang B formula; resource allocation",
ABSTRACT="..we consider the allocation of traffic and/or servers to
independent links, where each link is an Erlang loss system.",
}

@ARTICLE{Mahl91:Job,
AUTHOR="M. Mähler",
TITLE="Job Scheduling under Fairness Aspects",
JOURNAL="6. GI/ITG-Fachtagung Messung, Modellierung und Bewertung von
Rechensystemen",
ISBN="3-540-54550-6",
ADDRESS="Neubiberg, Germany",
PAGES="46-60",
YEAR=1991,
REFERENCES=21,
KEYWORDS="Distributed computing system; performance parameter;
scheduling; load sharing; fairness",
ABSTRACT="It is the goal of this paper to study how to make this second
decision (select the next job) in order to assign servers to clients in
a fair way. A general fairness criterion is introduced and applied to
different algorithms, which are tested analytically and by simulation.
assignment by consumption dependent priorities gives the best results.",
}

@ARTICLE{Brow9104:Block,
AUTHOR="Geoffrey Brown and M. G. Gouda and R. G. Miller",
TITLE="Block Acknowledgement: Redesigning the Window Protocol",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=4,
PAGES="524-532",
YEAR=1991,
KEYWORDS="Flow control; acknowledgement; window mechanism; protocol
performance",
ABSTRACT="We describe a new version of the window protocol where message
sequence numbers are taken from a finite domain and where both message
disorder and loss can be tolerated. Most existing windowprotocols
achieve only one of these two goals. Our protocol is based on a new
method of acknowledgement, called where each acknowledgement message has
two numbers m and n to acknowledge the reception of all data messages
with sequence numbers ranging",
}

@ARTICLE{Guri9107:Equivalent,
AUTHOR="R. Guérin and Hazim Ahmadi and M. Nagshineh",
TITLE="Equivalent capacity and its application to bandwidthallocation in
high-speed networks",
JOURNAL=ieeejsac,
VOLUME="SAC-9",
NUMBER=7,
PAGES="968-981",
YEAR=1991,
REFERENCES=26,
KEYWORDS="ATM; traffic control; approximation; fluid flow model",
ABSTRACT={.. we propose a computationally simple approximate expression
for the "equivalent capacity" or bandwidth requirement of both
individual and multiplexed connections, based on their statistical
characteristics and the desired GOS.},
}

@INPROCEEDINGS{Uhl91:Resource,
AUTHOR="T. Uhl and J. Ulmer",
TITLE="Performance analysis of resource allocation and routing
techniques in {B-ISDN}",
BOOKTITLE="ITC Specialists' Seminar Telecommunication Services for
Developing Economies",
ADDRESS="Cracow, Poland",
VOLUME=1,
PAGES="189-200",
YEAR=1991,
REFERENCES=17,
KEYWORDS="Resource allocation; routing; B-ISDN; ATM; bursty traffic;
routing table; network topology; allocation; DATEX-P; alternate
routing",
ABSTRACT="The paper provides a simulative analysis of resource
allocation and routing in the B-ISDN. The main performance values, i.e.
average establishment time and blocking probability are presented as
functions of the offered traffic and different services. The
investigations also can be applied as a basis for the design of routing
protocol in B-ISDN",
}

@BOOK{Hnde91:Integrated,
AUTHOR="Rainer Händel and M. Huber",
TITLE="Integrated Broadband Networks: An Introduction to {ATM-Based}
Networks",
ISBN="0-201-54444-X",
PUBLISHER="Addison-Wesley",
ADDRESS="Wokingham, Great Britain",
YEAR=1991,
KEYWORDS="Communication network; ATM; protocol; broadband",
ABSTRACT="1. Introduction 2. B-ISDN Service Requirements 3. Principles
and Building Blocks of B-ISDN 4. B-ISDN Network Concept 5. B-ISDN
User-Network Interfaces and Protocols 6. ATM Switching 7. ATM
Transmission Network",
}

@INPROCEEDINGS{Lin91:Finite,
AUTHOR="T.-P. Lin and L. Kleinrock",
TITLE="Performance Analysis of Finite-Buffered Multistage
Interconnection Networks with a General Traffic Pattern",
BOOKTITLE=sigmetrics,
ADDRESS="San Diego",
PAGES="68-78",
YEAR=1991,
REFERENCES=23,
KEYWORDS="Multistage interconnection network; Banyan network;
performance evaluation; analysis; output buffer; unbalanced traffic;
Markov chain; finite queue",
ANNOTE="We present an analytical model for evaluating the performance
offinite-buffered packet switching multistage interconnection networks
using blocking switches under any general traffic pattern. An
approximation method is also proposed to refine the analytical model to
account for the memory characteristic of a blocking switch which causes
persistent blocking of packets contending for the same output ports.",
}

@ARTICLE{Sato9101:Virtual,
AUTHOR="Y. Sato",
TITLE="Virtual Path and Link Capacity Design for {ATM} Networks",
JOURNAL=ieeejsac,
ISBN="0733-8716",
VOLUME="SAC-9",
NUMBER=1,
PAGES="104-111",
YEAR=1991,
REFERENCES=32,
KEYWORDS="ATM; statistical multiplexing; virtual path; delay; capacity
assignment; policing function; analysis; simulation",
}

@MANUAL{Bela91:MODSIM,
AUTHOR="R. Belanger and A. Mullarney",
TITLE="{MODSIM} {II} Tutorial (rev. 8)",
PUBLISHER="CACI Products Company 3344 North Torrey Pines Court La Jolla,
California 92037",
ADDRESS="La Jolla, Ca., USA",
PAGES="1-80",
YEAR=1991,
KEYWORDS="Simulation language; object-oriented programming; tutorial;
time warp; MODULA-2",
ABSTRACT="This tutorial gives a survey of the object-oriented simulation
language MODSIM, which is based on MODULA-2.",
}

@ARTICLE{McKe9101:Calculating,
AUTHOR="J. McKenna",
TITLE="Calculating joint queue length moments with {RECAL}",
JOURNAL="Communications in Statistics -- Stochastic Models",
VOLUME=7,
NUMBER=1,
PAGES="47-66",
YEAR=1991,
KEYWORDS="Queueing network; product form; analysis",
}

@ARTICLE{Ferr9101:Real,
AUTHOR="D. Ferrari",
TITLE="Real-Time communication in an Internetwork",
JOURNAL=jhsn,
ADDRESS="Netherlands",
VOLUME=1,
NUMBER=1,
PAGES="79-103",
YEAR=1991,
REFERENCES=19,
KEYWORDS="Real time; internetwork; communication",
ABSTRACT="Can end-to-end communication performance be guaranteed by a
packet-switching internetwork? This paper addresses the question by
examining the feasibility of extending to an internetwork the Tenet
approach to real-time communication service design. The conditions to be
satisfied by an internetwork so that the approach can be extended to it
are investigated. These include conditions for the scheduling discipline
to be used in the nodes.",
}

@INPROCEEDINGS{Gldn91:High,
AUTHOR="E. H. Göldner",
TITLE="High Speed Data Services in {B-ISDN}",
BOOKTITLE="2nd Joint Workshop on High Speed Networks",
ADDRESS="Stuttgart, Germany",
PAGES="31-36",
YEAR=1991,
REFERENCES=9,
KEYWORDS="B-isdn; man",
}

@ARTICLE{Abra9101:Constructing,
AUTHOR="D. Abramson",
TITLE="Constructing School Timetables Using Simulated Annealing:
Sequential and Parallel Algorithms",
JOURNAL=ms,
VOLUME=37,
NUMBER=1,
PAGES="98-113",
YEAR=1991,
KEYWORDS="scheduling",
ABSTRACT="Skoleskema",
}

@ARTICLE{Agni9102:Complementarity,
AUTHOR="S. R. Agnihothri",
TITLE="Complementarity Between the Finite Capacity and Finite Source
Queueing Systems",
JOURNAL="Computers \& Operations Research",
VOLUME=18,
NUMBER=2,
PAGES="183-188",
YEAR=1991,
KEYWORDS="machine-repair-man model; loss system",
ABSTRACT="Palm's machine problem",
}

@ARTICLE{Anan91:Mean,
AUTHOR="V. Ananthraram",
TITLE="A Mean Field Limit for a Lattice Caricature of Dynamic Routing in
Circuit Switched Networks",
JOURNAL="The Annals of Applied Probability",
VOLUME=1,
NUMBER=4,
PAGES="481-503",
YEAR=1991,
KEYWORDS="circuit switching; communication network; dynamic routing;
reservation",
ABSTRACT="Interacting particle systems; mean field limit; Trunk
reservation",
}

@ARTICLE{Ariz91:Queueing,
AUTHOR="I. Arizono and Y. Cui and Hiroshi Ohta",
TITLE="An Analysis of M/M/s Queueing Systems Based on the Maximum
Entropy Principle",
JOURNAL=jors,
VOLUME=41,
NUMBER=12,
PAGES="69-73",
YEAR=1991,
KEYWORDS="entropy; Markov process; queueing theory",
ABSTRACT="Lagrange's method",
}

@ARTICLE{Bitr91:Approximations,
AUTHOR="G. R. Bitran and D. Tirupati",
TITLE="Approximations for Networks of Queues with Overtime",
JOURNAL=ms,
VOLUME=37,
NUMBER=3,
PAGES="282-300",
YEAR=1991,
KEYWORDS="queueing network; approximation; interdeparture time",
}

@ARTICLE{Bouc91:Product,
AUTHOR="R. J. Boucherie and N. Van Dijk",
TITLE="Product Forms for Queueing Networks with State-Dependent Multiple
Job Transitions",
JOURNAL=aap,
VOLUME=23,
PAGES="152-187",
YEAR=1991,
KEYWORDS="Product form; queueing network; state dependent service;
multiple job processing",
}

@ARTICLE{Boxm91:Queueing,
AUTHOR="O. J. Boxma and G. A. P. Kindervater",
TITLE="A Queueing Network Model for Analyzing a Class of
Branch-and-Bound Algorithms on a Master-Slave Architecture",
JOURNAL=or,
VOLUME=39,
NUMBER=6,
PAGES="1005-1017",
YEAR=1991,
KEYWORDS="Master-slave architecture; analysis of parallel
branch-and-bound algorithms; fluid flow approximations; analysis;
parallel algorithm; approximation; fluid flow model",
}

@ARTICLE{Boye91:Traffic,
AUTHOR="P. Boyer and J. W. Roberts",
TITLE="Traffic Control for Stepwise {VBR} Connections in an {ATM}
Network",
EDITOR="M. Bonatti and F. Casali and G. Popple",
JOURNAL="Integrated Broadband Communication Views from RACE",
PUBLISHER="North-Holland",
PAGES="391-398",
YEAR=1991,
KEYWORDS="fast reservation protocol; space controller",
ABSTRACT="We consider the critical problems of traffic control and
resource management for stepwise variable bit rate sources in an ATM
network.  Statistical multiplexing can provide considerable gains over
peak rate allocation if the peak rate is restricted to a small fraction
of the multiplex bandwidth.  However, it is not feasible to enforce a
statistical parameter",
}

@ARTICLE{Burk91:Artificial,
AUTHOR="L. I. Burke",
TITLE="Introduction to Artificial Neural Systems for Pattern
Recognition",
JOURNAL="Computers Operations Research",
VOLUME=18,
NUMBER=2,
PAGES="211-220",
YEAR=1991,
KEYWORDS="neural network",
ABSTRACT="Pattern recognition",
}

@ARTICLE{Carr91:Extensions,
AUTHOR="M. J. Carrillo",
TITLE="Extensions of Palm's Theorem: A Review",
JOURNAL=ms,
VOLUME=37,
NUMBER=6,
PAGES="739-744",
YEAR=1991,
KEYWORDS="M/G/OO; transient behaviour; poisson distribution; batch
arrival; batch processing; nonhomogeneous Poisson Process; multi-echelon
repair system",
ABSTRACT="This note reviews the transient behavior the M/G/oo queue with
nonhomogeneous Poisson or compound Poisson input and nonstationary
service distribution.  In the case of nonhomogeneous Poisson input, the
number of customers in the queueing system over time turns out to have a
Poisson distribution.  The generality of the
nonhomogeneity/nonstationary assumptions and",
}

@ARTICLE{Chan91:Analytic,
AUTHOR="J. Chandramohan",
TITLE="An Analytic Multiservice Performance Model for a Digital Link
with a Wide class of Bandwidth Reservation Strategies",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=2,
PAGES="220-225",
YEAR=1991,
KEYWORDS="multiserver",
ABSTRACT="Today's telecommunications networks are in a state of
transition.  These networks will soon be all digital, with new features
that will permit them to carry traffic of different bandwidths on common
facilities.  Market considerations may require the network provider to
provide controls that give preferential treatment to some services at
the expense of others.  To plan such networks, there is a need for a
general framework",
}

@ARTICLE{Chan91:Stochastic,
AUTHOR="C. J. Chang and XiuLi Chao and M. Pinedo and J. G. Shantikumar",
TITLE="Stochastic Convexity for Multidimensional Processes and Its
Applications",
JOURNAL=ieeeac,
VOLUME="AC-36",
NUMBER=12,
PAGES="1347-1355",
YEAR=1991,
KEYWORDS="Stochastic Theory",
ABSTRACT="Consider a multidimensional stochastic process, which is a
function of a parametric process. The parametric process may be
multidimensional as well. In this paper, we compare two such processes
that differ only in their parametric processes. We extend known
stochastic convexity results for one-dimensional stochastic processes,
which are recently obtained by Shaked and Shantikumar, to
multidimensional processes. These resu",
}

@ARTICLE{Chle91:Validation,
AUTHOR="E. Chlebus",
TITLE="Validation of models for a telephone network employing routing
over transit paths",
JOURNAL="Applied Math. Modelling",
VOLUME=15,
PAGES="440-443",
YEAR=1991,
KEYWORDS="telephony; routing; traffic model; mathematical model;
convolution algorithm; multiserver; transit path",
ABSTRACT="The analysis of links in series aiming at modelling transit
paths in telephone networks is presented.  Two models based on intuition
and systematic considerations are discussed.  Their validity is examined
by means of simulations for a mesh-structure network operated under
various load conditions.",
}

@ARTICLE{Chow91:Virtual,
AUTHOR="Shyamal Chowdhury",
TITLE="An Analysis of Virtual Circuits with Parallel Links",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=8,
PAGES="1184-1188",
YEAR=1991,
REFERENCES=12,
KEYWORDS="Virtual Channel; Multichannel",
ABSTRACT="Computer networks supporting virtual circuits deliver packets
at the destination in the same sequence as they are received at the
source. But packets may arrive at the destination out of sequence if the
source is connected to the destination by multiple links. Hence, the
packets must be resequenced at the destination. Consequently, in
addition to the queueing delay and service time (transmission delay) the
packets suffer",
}

@ARTICLE{Coff91:Controlled,
AUTHOR="E. G. Coffman and B. M. Igelnik and Y. Kogan",
TITLE="Controlled Stochastic Model of a Communication System with
Multiple Sources",
JOURNAL=ieeeit,
VOLUME=37,
NUMBER=5,
PAGES="1379-1386",
YEAR=1991,
KEYWORDS="buffer; model; data communication; asymptotic analysis;
interpolating schemes",
ABSTRACT="A stochastic model of buffering in a data communication system
is considered, with source and sink transmission parameters depending on
the number of active sources.  For models in this control setting, we
analyze an effective numerical method for evaluating the equilibrium
distribution of buffer content.  The theoretical basis of the method is
established first.  Then, it is shown that the method has",
}

@ARTICLE{Cram91:Limit,
AUTHOR="J. P. Crametz and P. J. Hunt",
TITLE="A Limit Result Respecting Graph Structure for a Fully Connected
Loss Network with Alternative Routing",
JOURNAL="The Annals of Applied Probability",
VOLUME=1,
NUMBER=3,
PAGES="436-444",
YEAR=1991,
KEYWORDS="loss system; random graphs; functional law of large numbers",
ABSTRACT="Recently there has been a considerable amount of work on the
transient behaviour of loss networks in two different limiting regimes.
The first of these, which we do not consider here, is when link
capacities and offered traffics become large but the number of links
remain finite.  The second is the diverse routing limit when the number
of links increases with the offered load",
}

@ARTICLE{Dall91:Optimal,
AUTHOR="Y. Dallery and K. E. Stecke",
TITLE="On the Optimal allocation of Servers and Workloads in Closed
Queueing Networks",
JOURNAL=or,
VOLUME=38,
NUMBER=4,
PAGES="694-703",
YEAR=1991,
KEYWORDS="queueing system; closed queueing network; production system;
flexible manufacturing system; inventory; FMS",
ABSTRACT="In this paper, properties are derived that are useful for
characterizing optimal allocations of servers and workloads in
single-class, multiserver closed queueing networks (CQNs).  The problem
is as follows:  Suppose a particular workload is allocated to a set of
servers within a subnetwork of a CQN.  This set of servers is to be
partitioned into several multiserver stations.  The number of stations,
the number",
}

@ARTICLE{Dall91:Symmetry,
AUTHOR="Y. Dallery and Donald F. Towsley",
TITLE="Symmetry Property of the Throughput in Closed Tandem Queueing
Networks with Finite Buffers",
JOURNAL=orl,
VOLUME=10,
PAGES="541-547",
YEAR=1991,
KEYWORDS="tandem queue; blocking; symmetry reversibility",
ABSTRACT="In this paper we consider closed tandem queueing networks with
finite buffers and blocking before service.  With this type of blocking,
a server is allowed to start processing a job only if there is an empty
space in the next buffer.  It was recently conjectured that the
throughput of such networks is symmetrical with respect to the
population of the network.  that is, the throughput of the network
with",
}

@ARTICLE{Dove91:Algorithms,
AUTHOR="R. D. Doverspike",
TITLE="Algorithms for Multiplex Bundling in a Telecommunications
Network",
JOURNAL=or,
VOLUME=39,
NUMBER=6,
PAGES="925-944",
YEAR=1991,
KEYWORDS="Multiplexer; telecommunications transmission networks;
capacity expansion of telecommunications equipment; network design
optimization",
}

@ARTICLE{Glyn91:Departures,
AUTHOR="P. W. Glynn and W. Whitt",
TITLE="Departures from Many Queues in Series",
JOURNAL="The Annals of Applied Probability",
YEAR=1991,
KEYWORDS="tandem queue; queueing network; interdeparture time; transient
behaviour; limit theorem; approximation; ergodicity; standard
deviation",
ABSTRACT="Queues in series; Reflected Brownian motion; Invariance
principle; Strong approximation; Subadditive ergodictheorem; Large
deviations",
}

@ARTICLE{Gree91:Pointwise,
AUTHOR="L. Green and P. Kolesar",
TITLE="The Pointwise Stationary Approximation for Queues with Stationary
Arrivals",
JOURNAL=ms,
VOLUME=37,
NUMBER=1,
PAGES="84-97",
YEAR=1991,
KEYWORDS="queueing system; instationary process; approximation",
ABSTRACT="Nonstationary",
}

@ARTICLE{Gree91:Enhancing,
AUTHOR="A. J. Greenwood",
TITLE="Enhancing the Coverage of Simulation in the Introductory {MS/OR}
course: Needs, Problems, and Solutions",
JOURNAL="International Journal of Engineering Education",
VOLUME=7,
NUMBER=1,
PAGES="20-30",
YEAR=1991,
KEYWORDS="simulation",
ABSTRACT="The topic of simulation should be an important part of any
business or engineering school's curriculum; but, several pedagogical
problems currently limit the significant coverage of simulation in an
introductory MS/OR (management science/operations research) course - an
overview course where a variety of quantitative methods are introduced.
In response to these needs and problems, this paper reports an
innovative",
}

@ARTICLE{Havi91:Two,
AUTHOR="M. Haviv",
TITLE="Two Sufficient Properties for the Insensitivity of a Class of
Queueing Models",
JOURNAL=jap,
NUMBER=28,
PAGES="664-672",
YEAR=1991,
KEYWORDS="work conservation; workload; Poisson process; Poisson
arrivals; indivisibility",
ABSTRACT="For indivisible strong work-conserving queueing models with a
Poisson arrival process, each of the following two properties is a
sufficient condition for insensitivity.  (1) The completed workload of a
job receiving service is independent of the number of jobs in the
system.  (2) Independently of the completed workloads of the jobs in the
system, they all are equally likely to be in service",
}

@ARTICLE{Heid91:Queue,
AUTHOR="D. Heidemann",
TITLE="Queue Length and Waiting-time Distributions at Priority
Intersections",
JOURNAL="Transportations Research B",
VOLUME="25B",
NUMBER=4,
PAGES="163-174",
YEAR=1991,
KEYWORDS="Queueing System; Delay Model; Priority; Queue Length; Waiting
Time; Delay Distribution",
ABSTRACT="Specialist literature on priority intersections provides
formulas for calculating mean waiting times and mean queue lengths for
the traffic flow which has to give way (minor road). In the present
paper, these results on mean values are extended to yield formulas for
the corresponding distributions. This is achieved by developing a
queueing-theory approach which is applied to a formula due to Tanner.
The results are subjec",
}

@ARTICLE{Jin9106:Aggregate,
AUTHOR="Q. Jin and Y. Sugasawa and K. Seya",
TITLE="Aggregate Approach of Markov Renewal Process and Extended
Stochastic Petri Net Model and Its Applications",
JOURNAL=ieice,
ADDRESS="Japan",
VOLUME="E74",
NUMBER=6,
PAGES="1479-1485",
YEAR=1991,
KEYWORDS="Markov process; SPN",
ABSTRACT="Markov Renewal Proces (MRP) is an extremely powerful analyzing
tool for concurrent systems. But it is often difficult to determine the
correct Markov model for even moderately complex systems. Petri net is
very descriptive and flexible in modeling various kinds of systems of
concurrency and asynchronization. This paper presents an aggregate
approach of Markov Renewal Process and Extended Stochastic Petri Net
(ESPN) model",
}

@ARTICLE{Jord9108:Throughput,
AUTHOR="S. Jordan and P. Varaiya",
TITLE="Throughput in Multiple Service, Multiple Resource Communication
Networks",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=8,
PAGES="1216-1222",
YEAR=1991,
KEYWORDS="multiserver; product form; convexity",
ABSTRACT="The merging of telephone and computer networks is introducing
multiple resources into networks, and information is becoming
increasingly distributed across the network.  Related services are being
integrated onto a single network rather than being offered on separate
uncoordinated networks.  In this paper, we focus upon communication
networks that integrate multiple services using multiple resources.",
}

@ARTICLE{Kell91:Effective,
AUTHOR="F. P. Kelly",
TITLE="Effective Bandwidths at Multi-Class Queues",
JOURNAL=qs,
VOLUME=9,
PAGES="5-16",
YEAR=1991,
KEYWORDS="standard deviation; M/G/1; circuit switching; connection
admission control; large deviations",
ABSTRACT="Consider a queue which serves traffic from a number of
distinct sources and which is required to deliver a performance
guarantee, expressed in terms of the mean delay or the probability the
delay exceeds a threshold. For various simple models we show that an
effective bandwidth can be associated with each source, and that the
queue can deliver its performance guarantee by limiting the sources
served so t",
}

@ARTICLE{Kim91:Bandwidth,
AUTHOR="Dong Kim and Chong Kwan Un",
TITLE="Bandwidth Allocation Strategy with State-Dependent Bernoulli
Access and Pre-emptive Priority",
JOURNAL=elet,
VOLUME=27,
NUMBER=24,
PAGES="2202-2204",
YEAR=1991,
KEYWORDS="ISDN; communication network; digital communication;
multiserver",
ABSTRACT="A study is presented of a bandwidth allocation strategy with
state-dependent Bernoulli access and pre-emptive priority to serve
wideband and narrowband traffic in an integrated services digital
network. By varying the Bernoulli access probability, this proposed
allocation strategy shows better performance than other strategies.",
}

@ARTICLE{Kimu91:Approximating,
AUTHOR="Takumi Kimura",
TITLE="Approximating the Mean Waiting Time in the {GI/G/s} Queue",
JOURNAL=jors,
VOLUME=42,
NUMBER=11,
PAGES="959-970",
YEAR=1991,
KEYWORDS="approximation; queueing theory",
ABSTRACT="We provide two distribution-dependent approximations for the
mean waiting time in a GI/G/s queue. Both approximations are weighted
combinations of the exact mean waiting times for the GI/M/s and M/D/s
queues each of which has the same mean service time and traffic
intensity as in the approximating GI/G/s queue. The weights in the
approximations are expressed by the service-time c.d.f. and the first
two moments of interarr",
}

@ARTICLE{Kimu91:Refining,
AUTHOR="Takumi Kimura",
TITLE="Refining Cosmetatos' Approximation for the Mean Waiting Time in
the M/D/s Queue",
JOURNAL=jors,
VOLUME=42,
NUMBER=7,
PAGES="595-603",
YEAR=1991,
KEYWORDS="M/D/N; approximation",
ABSTRACT="This paper deals with refining Cosmetatos' approximation for
the mean waiting time in an M/D/s queue.  Although his approximation
performas quite well in heavy traffic, it overestimates the true value
when the number of servers is large or the traffic is light.  We first
focus on a normalized quantity that is the ratio of the mean waiting
times for the M/D/s and M/M/s queues.  Using some asymptotic properties
of the quantity",
}

@ARTICLE{Kimu9102:Approximations,
AUTHOR="Takumi Kimura",
TITLE="Approximations for the Waiting Time in the {GI/G/s} Queue",
JOURNAL=jorsj,
ADDRESS="Japan",
VOLUME=34,
NUMBER=2,
PAGES="173-186",
YEAR=1991,
KEYWORDS="GI/G/N; waiting time; approximation",
ABSTRACT="We provide some two-moment approximation formulas for the mean
waiting time and the delay probability in a GI/G/s queue. These formulas
are certain combinations of the exact mean waiting times for the M/M/s,
M/D/s and D/M/s queues and the first two moments of the interarrival
times and service times. To see the quality of the approximations, they
are numerically compared with exact solutions and other approximations
for s",
}

@ARTICLE{Klad9104:SORSA,
AUTHOR="K. Kladakis and N. M. Staerfeldt and S. Vedsegaard",
TITLE="{SORSA} - et Kanalallokeringssystem",
JOURNAL="Teleteknik",
ADDRESS="Sweden",
NUMBER=4,
PAGES="203-210",
YEAR=1991,
LANGUAGE="Swedish",
KEYWORDS="cellular system; channel; frequency distribution; allocation",
ABSTRACT="Channel or Frequency allocation",
}

@ARTICLE{Knes91:Transient,
AUTHOR="Ch. Knessl",
TITLE="On the Transient Behaviour of the Repairman Problem",
JOURNAL=aap,
VOLUME=23,
PAGES="327-354",
YEAR=1991,
KEYWORDS="machine-repair-man model; transient condition; probability;
Palm machine interference; singular perturbations; Ray method",
ABSTRACT="We consider the repairman problem which corresponds to the
finite population M/M/1 quque.  Asymptotic approximations for the
transient probability distribution of the number of broken machines
constructed when the number M of machines is large and the service
(repair) rate is also large, specifically, O(M).  The approximations are
constructed by using singular",
}

@ARTICLE{Koen9102:Queueing,
AUTHOR="E. Koenigsberg",
TITLE="Is Queueing Theory Dead?",
JOURNAL=omega,
VOLUME=19,
NUMBER="2/3",
PAGES="69-78",
YEAR=1991,
KEYWORDS="Queueing theory; survey",
ABSTRACT="Review",
}

@ARTICLE{Lee9101:Channel,
AUTHOR="John Lee and Chong Kwan Un",
TITLE="A Channel Access Strategy with a Both-Way Overflow Mechanism in
Integrated Services Networks",
JOURNAL=ieice,
ADDRESS="Japan",
VOLUME="E74",
NUMBER=1,
PAGES="101-104",
YEAR=1991,
KEYWORDS="Packet switching; overflow traffic",
ABSTRACT="In this letter we present a channel access strategy with both
downward and upward (thus called both-way) overflow mechanisms, which
allocates channel bandwidth dynamically to multiple heterogeneous
traffic with differing intensities, bit rates, and holding times. Each
input traffic has its own service channel and finite waiting room and
can overflow to any other channels. The threshold parameter which limits
overflow is a",
}

@ARTICLE{Liu91:Counter,
AUTHOR="D. Liu and M. F. Neuts",
TITLE="Counter-Examples Involving Markovian Arrival Processes",
JOURNAL="Communications in Statistics -- Stochastic Models",
VOLUME=7,
NUMBER=3,
PAGES="499-509",
YEAR=1991,
KEYWORDS="Markov process; event counting",
ABSTRACT="By considering simple two-state Markovian arrival processes, a
number of examples are given, which show the limitations of the
information conveyed by the distributions of the counting random
variables.  Some of these are intended to lay some conjectures on point
processes to rest, while others have primarily didactic value.  We also
prove the (unanticipated) equivalence of the point processes generated
by the two",
}

@ARTICLE{Liu91:Approximate,
AUTHOR="Y. Liu and Harry Perros",
TITLE="Approximate Analysis of A Closed Fork/Join Model",
JOURNAL=ejor,
VOLUME=53,
PAGES="382-392",
YEAR=1991,
KEYWORDS="fork-join queue; closed queueing network; exponential
distribution; service time; approximation",
ABSTRACT="An approximate algorithm for analyzing a closed queueing
systems with a K-sibling fork/join queue is presented.  The procedure is
based on decomposition and aggregation.  The approximation procedure
gives good results for the mean response time and the system throughput.
However, it gives results which are an upper bound of the mean response
time of the fork/join operation and a lower bound of the",
}

@ARTICLE{Mars91:New,
AUTHOR="G. Marsaglia and A. Zaman",
TITLE="A New Class of Random Number Generators",
JOURNAL="The Annals of Applied Probability",
VOLUME=1,
NUMBER=3,
PAGES="462-480",
YEAR=1991,
KEYWORDS="random number; Monte Carlo simulation; lagged-Fibonacci;
Add-with-carry; Subtract-with-borrow",
ABSTRACT="We introduce a new class of generators of two types:
add-with-carry and subtract-with-borrow. Related to lagged-Fibonacci
generators, the new class has interesting underlying theory,
astonishingly long periods and provable uniformity for full sequences.
Among several that we mention, we recommend particularly promising ones
that will generate a sequence of 2E1751 bit",
}

@ARTICLE{Masu91:Approximations,
AUTHOR="K. Masuda",
TITLE="Approximations of State Transition Probabilities in Finite
Birth-Death Processes",
JOURNAL=ieice,
VOLUME="E74",
NUMBER=4,
PAGES="715-721",
YEAR=1991,
KEYWORDS="Time dependent queueing system; M/M/N",
ABSTRACT="Time-dependent traffic theory; Gnedenko's approximation",
}

@ARTICLE{Mert9102:Routing,
AUTHOR="M. K. Mertsch and T. Uhl",
TITLE="Evaluation of Routing Tables Updating Period in Computer
Communication Networks",
JOURNAL=aeu,
ADDRESS="Germany",
VOLUME=45,
NUMBER=2,
PAGES="84-89",
YEAR=1991,
KEYWORDS="Computer network; routing",
ABSTRACT="This study provides an investigation about special problems of
distributed and adaptive routing rules.  In general a distributed
adaptive routing scheme include several separate processes:  1) a
measurement process for the determination of pertinent network
characteristics, 2) a protocol for disseminating information concerning
these characteristics, and 3) a calculation to determine how traffic
should be",
}

@ARTICLE{Miya9104:ATM,
AUTHOR="H. Miyahara",
TITLE="{ATM:} A Most Promising Switching Technique",
JOURNAL=ieice,
ADDRESS="Japan",
VOLUME="E74",
NUMBER=4,
PAGES="747-751",
YEAR=1991,
KEYWORDS="ATM; survey",
ABSTRACT="Broadband Integrated Service Digital Network (B-ISDN) is
expected to support diverse applications ranging from low bit rate
communications between terminals and host computers, to the broadcasting
high resolution TV Signals. One of the most promising approaches for the
B-ISDN is the Asynchronous Transfer Mode (ATM) where all information
(such as voice, data, image and video) is divided into fixed length data
format, calle",
}

@ARTICLE{Mura91:Commmunication,
AUTHOR="Kurenai Murakami and Kazuo Hajikano and S. Abe and Y. Kato",
TITLE="Commmunication Service and Media Control Using {ATM}",
JOURNAL=ieice,
VOLUME="E74",
NUMBER=4,
PAGES="772-779",
YEAR=1991,
KEYWORDS="connectionless service",
ABSTRACT="ATM's bandwidth flexibility and high switching speed
advantages have made it the predominant solution to the B-ISDN. However,
networks based on ATM suffer from phenoma not encountered in the STM
network, i.e.  cell loss and cell jitter.  For ATM to support varied
media, problems arising from these phenomena must be resolved. This
paper discusses techniques which enable ATM to support CBR, VBR voice,
VBR video, and connectionless",
}

@ARTICLE{Nied91:Recent,
AUTHOR="H. Niederreiter",
TITLE="Recent Trends in Random Number and Random Vector Generation",
JOURNAL="Annals of Operations Research",
VOLUME=31,
PAGES="323-346",
YEAR=1991,
KEYWORDS="pseudo-random generator; random number testing; lattice test;
linear congruential generator; matrix; uniformity test; serial test;
nonlinear congruential method; GFST method; uniform pseudorandom
vectors; matrix generator; digital multistep method",
ABSTRACT="A survey of recent work in the areas of uniform pseudorandom
number and uniform pseudorandom vector generation is presented.  The
emphasis is on methods for which a detailed theory is available.  A
progress report",
}

@INPROCEEDINGS{Nils91:Provisioning,
AUTHOR="A. Nilsson and M. Perry",
TITLE="Provisioning Models for Digital Loop Carriers",
BOOKTITLE=itc13,
ADDRESS="Copenhagen, Denmark",
PAGES="271-276",
YEAR=1991,
KEYWORDS="multiserver",
}

@ARTICLE{Ocin91:PhaseMajorization,
AUTHOR="C. A. O'Cinneide",
TITLE="Phase-Type Distributions and Majorization",
JOURNAL="The Annals of Applied Probability",
YEAR=1991,
KEYWORDS="hit ratio; Markov chain; martingale; phase-type model;
majorization",
ABSTRACT="Aldous and Shepp recently proved that the Erlang distribution
of a given order is the least variable phase-type distribution of that
order, in the sense of minimizing the coefficient of variation.  Here we
prove that it is also the least variable in the sense of majorization.
We give an example showing thet the result does not extend in the
obvious way to general distributions with rational transforms and",
}

@ARTICLE{OCin91:Phase,
AUTHOR="C. A. O'Cinneide",
TITLE="Phase-Type Distributions and Invariant Polytopes",
JOURNAL=aap,
VOLUME=23,
PAGES="515-535",
YEAR=1991,
KEYWORDS="phase-type model; Markov chain; laplace transform; generating
function; upper bound; lower bound; triangular representations;
generators",
}

@ARTICLE{Paul91:Recent,
AUTHOR="R. J. Paul",
TITLE="Recent Developments in simulation Modelling",
JOURNAL=jors,
VOLUME=42,
NUMBER=3,
PAGES="217-226",
YEAR=1991,
KEYWORDS="computer; modeling; simulation",
ABSTRACT="Current trends in simulation software development are towards
the automation of the modelling process. Some systems provide a method
of specifying the problem so that the computer program can be
automatically generated. Other systems provide a generic framework for a
particular class of modelling problem that can be input as data to the
system. Examples of the latter are flexible manufacturing systems
simulations. Most cu",
}

@ARTICLE{Poor91:Maximum,
AUTHOR="H. V. Poor",
TITLE="The Maximum Difference Between the Binomial and Poisson
Distributions",
JOURNAL=spl,
VOLUME=11,
PAGES="103-106",
YEAR=1991,
KEYWORDS="Poisson distribution; approximation; binomial distribution",
ABSTRACT="Poisson approximation",
URL="http://www.math.wm.edu/~leemis/1996amerstat.ps",
}

@ARTICLE{Quin9101:Allocating,
AUTHOR="P. Quinn and B. Andrews and H. Parsons",
TITLE="Allocating Telecommunications Resources at {L.L.} Bean, Inc",
JOURNAL="Interfaces",
VOLUME=21,
NUMBER=1,
PAGES="75-91",
YEAR=1991,
KEYWORDS="Communication network",
}

@ARTICLE{Reim91:Critically,
AUTHOR="M. I. Reiman",
TITLE="A Critically Loaded Multiclass {Erlang} Loss system",
JOURNAL=qs,
VOLUME=9,
PAGES="65-82",
YEAR=1991,
KEYWORDS="Circuit switching; multiserver; multiservice integrated
network; ISDN; asymptotic analysis; Erlang B formula",
ABSTRACT="We consider a generalization of the classical Erlang loss
model to multiple classes of customers.  Each of the J customer classes
has an associated Poisson arrival process and an arbitrary holding itme
distribution.  Class j customers require Mj servers simultaneously.  We
determine the asymptotic form of the blocking probabilities for all
customer classes in the regime known as critical load",
}

@ARTICLE{Ross91:Optimal,
AUTHOR="Keith W. Ross and D. D. Yao",
TITLE="Optimal Load Balancing and Scheduling in a Distributed Computer
System",
JOURNAL=jacm,
VOLUME=38,
NUMBER=3,
PAGES="676-690",
YEAR=1991,
KEYWORDS="load balancing; scheduling; queueing theory",
}

@INPROCEEDINGS{Rubi9104:Queueing,
AUTHOR="I. Rubin and Kuang-Shin Lin",
TITLE="Queueing Behaviour under Flow Control at the
Subscriber-to-Network Interface for High Speed Metropolitan Networks",
BOOKTITLE=infocom,
ADDRESS="Bal Harbour, Florida",
PAGES="382-390 (paper 4C.2)",
YEAR=1991,
KEYWORDS="MAN; flow control",
ABSTRACT="A Credit Manager Algorithm (CMA) is used to control the flow
of packets between a subscriber station (or a local area network) and
the access to a high-speed metropolitan area network.  The parameters of
the algorithm are used to regulate the mean throughput and the level of
burstiness at the Subscriber-to-Network Interface (SNI).  Such a flow
control procedure has been recently considered by the Bellcore's
Switched Multimedia",
}

@ARTICLE{Sait91:Transient,
AUTHOR="H. Saito and F. Machihara",
TITLE="Transient Analysis of a Markovian Loss System with Heterogeneous
Inputs for Time Congestion Measurements",
JOURNAL=qs,
VOLUME=8,
PAGES="81-96",
YEAR=1991,
KEYWORDS="Markov process; loss system; transient analysis; traffic
measurement",
ABSTRACT="This paper presents transient analyses for a markovian loss
system with heterogeneous inputs. Results are applied to the analysis of
the measured time congestion of this system. Transient analyses show the
properties of system recovery and covariance functions. The measured
time congestion is analyzed and approximations are proposed using these
properties. These results are significant for management and control in
the In",
}

@ARTICLE{Sche9106:Delay,
AUTHOR="R. Schehrer",
TITLE="On a Delay-Loss System with Hysteresis and Unlimited Waiting Room
for Overload Protection in {ISDN-Systems}",
JOURNAL=aeu,
ADDRESS="Stuttgart, Germany",
VOLUME=45,
NUMBER=6,
PAGES="365-374",
YEAR=1991,
KEYWORDS="Queueing system; cut-off priority",
ABSTRACT="This paper deals with cut-off priority queueing systems with
hysteresis and unlimited waiting room which have shown to be suitable
for overload protection.  A recursive method as well as an explicit
solution is presented for exact calculation of such systems.  Results
are shown with the aid of examples.",
}

@ARTICLE{Sche9105:Cyclic,
AUTHOR="R. Schehrer",
TITLE="On Cyclic Processes",
JOURNAL=aeu,
ADDRESS="Stuttgart, Germany",
VOLUME=45,
NUMBER=5,
PAGES="298-",
YEAR=1991,
KEYWORDS="Queueing theory",
ABSTRACT="This paper deals with a class of Markovian processes with the
property that their state diagram forms a closed loop.  for such
processes, which are denoted as cyclic processes, a recursive method as
well as an explicit formula is presented for the exact calculation of
the state probabilities.  Furthermore, these calculation methods are
extended to a generalized type of cyclic processes, the state diagrams",
}

@ARTICLE{Shan91:Starshapeness,
AUTHOR="J. G. Shanthikumar and Chengke Wu",
TITLE="On the Starshapeness of G/G/c Queueing Systems",
JOURNAL=aap,
VOLUME=23,
PAGES="431-435",
YEAR=1991,
KEYWORDS="queueing system; design; second-order properties; single-stage
queueing systems; stochastic starshapeness; stochastic convexity",
ABSTRACT="In this paper we show that the waiting and the sojourn times
of a customer in a single-stage, multiple-server, G/G/c queueing system
are increasing and starshaped with respect to the mean service time.
Usefulness of this result in the design of the optimal service speed in
the G/G/c queueing system is also demonstrated.",
}

@ARTICLE{Song9103:Aggregate,
AUTHOR="Y. H. Song and Yutaka Takahashi",
TITLE="Aggregate Approximation for Tandem Queueing Systems with
Production Blocking",
JOURNAL=jorsj,
ADDRESS="Japan",
VOLUME=34,
NUMBER=3,
PAGES="329-353",
YEAR=1991,
KEYWORDS="Tandem queue",
ABSTRACT="In this paper, we study problems arising in applications of
the cross aggregation method to tandem queueing systems with production
blocking, and propose two types of applications with different state
descriptions. The cross aggregation method provides a nested family of
approximations of stationary state probabilities of the model by
imposing several different levels of assumptions on independence among
nodes. Namely, in",
}

@TECHREPORT{Span91:ODP,
AUTHOR="O. Spaniol",
TITLE="{ODP} (Open Distributed Processing): Yet another Viewpoint
(Revised edition)",
TYPE="Aachener Informatik-Berichte",
INSTITUTION="RWTH Aachen",
ADDRESS="Aachen, Germany",
NUMBER="91-21",
PAGES="13 (paper 14)",
YEAR=1991,
KEYWORDS="Parallel computing",
}

@ARTICLE{Stal9102:Practical,
AUTHOR="W. Stallings",
TITLE="A Practical Guide to Queueing Analysis",
JOURNAL=byte,
VOLUME=16,
NUMBER=2,
PAGES="309-316",
YEAR=1991,
KEYWORDS="Queueing system; performance evaluation",
}

@ARTICLE{Taka91:Supplementary,
AUTHOR="H. Takagi and L. B. Boguslavsky",
TITLE="A Supplementary Bibliography of Books on Queueing Analysis and
Performance Evaluation",
JOURNAL=qs,
VOLUME=8,
PAGES="313-322",
YEAR=1991,
KEYWORDS="Queueing system; bibliography",
}

@ARTICLE{Tsio9104:Blocking,
AUTHOR="George D. Tsiotras and Hussein Badr and E. Beltrami",
TITLE="Blocking Probabilities for a Class of Two-Station Tandem Queueing
Models",
JOURNAL="IIE Transactions",
VOLUME=23,
NUMBER=4,
PAGES="331-345",
YEAR=1991,
KEYWORDS="Tandem queue",
ABSTRACT="We study a two-station tandem queueing system with a finite
buffer of maximum size M (M>=0) between the stations.  The first service
station has L>=1 (homogeneous) parallel servers with a nunlimited
waiting space, while at the second there are N>=1 (homogeneous) parallel
servers.  Assuming Poisson arrivals and exponential service times, we
derive exact results for the blocking probabilities for some special
cases",
}

@ARTICLE{Dijk91:Stop,
AUTHOR="N. van Dijk",
TITLE="'Stop - Recirculate' for Exponential Product form Queueing
Networks with Departure Blocking",
JOURNAL=orl,
VOLUME=10,
PAGES="343-351",
YEAR=1991,
KEYWORDS="queueing network; product form; protocol; multiserver; stop
protocol; recirculate protocol; partial balance",
ABSTRACT="The steady-state queue-size distribution of Jacksonian
queueing networks with departure blocking is shown to have exactly the
same product form under both a 'stop' and a 'recirculate' protocol.
Under the stop protocol services are interrupted while under the
circulate protocol jobs leaving the network are recycled into the
network, when blocking occurs.  Extensions to",
}

@ARTICLE{Dijk91:Note,
AUTHOR="N. van Dijk",
TITLE="A Note on Extended Uniformization for Non-Exponential Stochastic
Networks",
JOURNAL=jap,
VOLUME=28,
PAGES="955-961",
YEAR=1991,
KEYWORDS="Stochastic network; uniformization; global balance equations",
ABSTRACT="The standard uniformization technique for continuous-time
Markov chains is generalized to non-exponential stochastic networks.",
}

@ARTICLE{Vint9103:Networks,
AUTHOR="G. C. Vinton",
TITLE="networks",
JOURNAL="Scientific American",
VOLUME=265,
NUMBER=3,
PAGES="42-51",
YEAR=1991,
KEYWORDS="Communication network",
ABSTRACT="As the diversity of computer applications increases the
burgeoning flow of megabit traffic between machines will be accomodated
by wider and smoother highways.",
}

@ARTICLE{Virt91:Stochastic,
AUTHOR="J. T. Virtamo and S. Aalto",
TITLE="Stochastic Optimization of Reservation Systems",
JOURNAL=ejor,
VOLUME=51,
PAGES="327-337",
YEAR=1991,
KEYWORDS="stochastic process; Markov process; decision theory;
communication; control; process",
ABSTRACT="Dynamic programming",
}

@ARTICLE{Walk91:CCS7,
AUTHOR="M. J. Walker",
TITLE="{CCS7} Offers New Paths to Revenue Generating Services",
JOURNAL="AT\&T Technology",
VOLUME=6,
NUMBER=2,
PAGES="8-15",
YEAR=1991,
KEYWORDS="Ccs",
}

@ARTICLE{Whit91:Review,
AUTHOR="W. Whitt",
TITLE="A Review of L = lambda W and Extensions",
JOURNAL=qs,
VOLUME=9,
PAGES="235-268",
YEAR=1991,
KEYWORDS="little's formula; mean waiting time; conservation law; limit
theorem; stationary process; inversion; Time averages and customer
averages; sample-path methods; Stationary marked point process; rate
conservation law; level crossings; inversion formula; Campbell's
formula; central limit theorem",
ABSTRACT="A fundamental principle of queueing theory is L = lambda W
(Little's law), which states that the time-average or expected
time-stationary number of customers in a system is equal to the product
of the arrrival rate a",
}

@ARTICLE{Will91:Steady,
AUTHOR="H. Willie",
TITLE="Steady State of Loss Systems with a Superposition of Inputs",
JOURNAL=qs,
VOLUME=9,
PAGES="441-460",
YEAR=1991,
KEYWORDS="loss system; steady state; point process; superposition;
blocking; random marked point process; individual call blocking; empty
point",
ABSTRACT="The total input of a loss system consisting of a finite number
of fully available, identical servers is assumed to be a superposition
of a finite number of partial traffic streams, which need not be
independent and which are represented by a random marked point process.
This paper derives the existence, uniqueness and ergodic statements for
the steady state",
}

@ARTICLE{Zach91:Blocking,
AUTHOR="S. Zachary",
TITLE="On Blocking in Loss Networks",
JOURNAL=aap,
VOLUME=23,
PAGES="355-372",
YEAR=1991,
KEYWORDS="Circuit switching; Erlang B formula",
ABSTRACT="We consider a reduced state space approach to the analysis of
blocking in stochastic loss networks.  We show how this approach
provides insight into the approximations currently used in large
networks and enables improved approximations to be deduced.  We further
give some heavy traffic asymptotic results for the limiting scheme of
Kelly (1986).",
}

@ARTICLE{Zahe91:Neural,
AUTHOR="F. Zahedi",
TITLE="An Introduction to Neural Networks and a Comparison with
Artificial Intelligence and Expert Systems",
JOURNAL="Interfaces",
VOLUME=21,
NUMBER=2,
PAGES="25-38",
YEAR=1991,
KEYWORDS="artificial intelligence; neural network; expert system",
}

@ARTICLE{Inou9104:Transport,
AUTHOR="Y. Inoue and Ikuo Tokizawa",
TITLE="Transport Network Evolution Toward {ATMized} {B-ISDN}",
JOURNAL=ieice,
VOLUME="E74",
NUMBER=4,
PAGES="780-786",
YEAR=1991,
KEYWORDS="B-ISDN; ATM; survey",
ABSTRACT="Enhancing the ISDN (Integrated Services Digital Network)
capability to cover broadband capacity will change the telecommunication
world greatly. This paper discusses the way where telecommunication
networks should be evolved, the main features of the ATM (Asynchronous
Transfer Mode) based B-ISDN, and its basic structure principles with the
close relationship to customers demands. ATM will play a key role in
technology tow",
}

@PHDTHESIS{Grün91:Stochastic,
AUTHOR="Reto Grünenfelder",
TITLE="Stochastic modelling of the traffic and its properties in an
{ATM} network",
SCHOOL="Ecole Polytechnique Federale de Lausanne, Departement
d'Electricite",
ADDRESS="Lausanne, Switzerland",
NUMBER=912,
PAGES=147,
YEAR=1991,
REFERENCES=47,
KEYWORDS="ATM; traffic source model; performance evaluation; switching
network; G/G/1; routing; perturbation analysis; simulation method; delay
analysis",
ABSTRACT="Inroduction to broadband networks; Traffic in an ATM network;
Source models; Characterisation of an ATM switching element; End-to-end
cell queueing delay; Routing in an ATM network; Software for
Simulations; Appendices; Conclusions",
}

@INPROCEEDINGS{Lind91:Combining,
AUTHOR="Ch. Lindemann and G. Hommel",
TITLE="Combining Deterministic and Stochastic Petri Net and Product-Form
Queueing Network Models for Evaluation Gracefully Degradable Systeable
Systems",
BOOKTITLE="5th Annual European Computer Conference: Advanced Computer
Technology, Reliable Systems and Applied",
ADDRESS="Bologna, Italy",
PAGES="880-884",
YEAR=1991,
REFERENCES=11,
KEYWORDS="Petri net; queueing network; product form; evaluation",
ABSTRACT="The paper introduces an approach for determining the
performability of repairable degradable systems based upon combining
Deterministic and Stochastic Petri Nets and product-form queueing
network models. The novel feature of the proposed modeling techniquelies
in its detailed representation of the transient behaviour during a
reconfiguration process. To illustrate the modeling technique a
loosely-coupled multi-computer system consisting of two",
}

@MASTERSTHESIS{Rebm91:Verbindungsannahmealgorithmen,
AUTHOR="H. Rebmann",
TITLE="Verbindungsannahmealgorithmen für {ATM-Netze} - Untersuchung von
Zell- und Rufverslusten",
SCHOOL="Universität Stuttgart, Institut für Nachrichtenvermittlung und
Datenverarbeitung",
ADDRESS="Stuttgart, Germany",
PAGES=70,
YEAR=1991,
LANGUAGE="German",
KEYWORDS="ATM; connection admission control; loss system",
}

@ARTICLE{Ster91:Separable,
AUTHOR="T. E. Stern and A. I. Elwalid",
TITLE="Analysis of Separable Markov-Modulated Rate Models for
Information-Handling Systems",
JOURNAL=aap,
VOLUME=23,
PAGES="105-139",
YEAR=1991,
REFERENCES=24,
KEYWORDS="Fluid flow model; decomposition; eigenvalue; ATM;
multiplexer",
ABSTRACT="In this paper, arrival and service rates are modelled as
superpositions of a number of independent finite state reversible Markov
processes. We call such models separable Markov-modulated rateprocesses
(MMRP). In this work a general mathematical model for separable MMRPs is
presented, focusing on Markov-modulated cont inuous flow models. An
efficient procedure for analysing their performance is derived. It is
shown that the 'state explosion' pr",
}

@BOOK{Gerk91:Digitale,
AUTHOR="P. Gerke",
TITLE="Digitale Kommunikationsnetze",
ISBN="3-540-52330-8",
PUBLISHER="Springer-Verlag",
ADDRESS="Berlin, Germany",
VOLUME="1. Aufl.",
PAGES=386,
YEAR=1991,
LANGUAGE="German",
REFERENCES=247,
KEYWORDS="Network; survey; digital network; switching network; isdn;
B-ISDN; switching system; switching methodology; data communication;
signalling; service characterization; EWSD; ATM; dqdb; DATEX-L;
DATEX-P",
ABSTRACT="Grundlagen von Kommunikationsnetzen, Prinzipien digitaler
Koppelnetze, Vermittlungssysteme, Datenkommunikation und Signalisierung,
digitale Netze, Dienste (O: IfN-BM: 95.8 58089 001)",
}

@INPROCEEDINGS{Ali91:Neural,
AUTHOR="K. K. M. Ali and F. Kamoun",
TITLE="A Neural Network Approach to the Maximum Flow Problem",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="130-134",
YEAR=1991,
KEYWORDS="Flow control; neural network",
}

@INPROCEEDINGS{Aly91:Photonic,
AUTHOR="K. A. Aly and P. W. Dowd",
TITLE="A Photonic Fast Packet Switch for High-Speed Intra-node Routing:
Architecture and Delay Analysis",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="35.5",
YEAR=1991,
KEYWORDS="Architecture; delay analysis; optical switching; routing;
TDM",
}

@INPROCEEDINGS{Ansa91:New,
AUTHOR="N. Ansari and D. Liu",
TITLE="The Performance Evaluation of a New Neural Network Based Traffic
Management Scheme for a Satellite Communication Network",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="110-114",
YEAR=1991,
KEYWORDS="Neural network; traffic control",
}

@INPROCEEDINGS{Bala91:Minimum,
AUTHOR="Krishna Bala and T. E. Stern",
TITLE="A Minimum Interference Routing Algorithm for a Linear Lightwave
Network",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="1264-1269",
YEAR=1991,
REFERENCES=8,
KEYWORDS="Linear network; routing algorithm; wdm",
ABSTRACT="A routing algorithm for setting up point to point connections
is proposed for a Linear Lightwave Network. The overall problem of
routing is decomposed into the subproblems of physical path allocation,
checking for violations of some of the special constraints of the LLN on
the allocated physical path and the allocation of an appropriate
channel. It is shown that the problem of physical path allocation is
NP-complete, several algorithms are pres",
}

@ARTICLE{Bart91:FDDI,
AUTHOR="A. J. Barth",
TITLE="{FDDI} wird erwachsen",
JOURNAL="Elektronik",
ADDRESS="Germany",
VOLUME=21,
PAGES="60-64",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Fddi",
}

@INPROCEEDINGS{Cole91:Neural,
AUTHOR="K. G. Coleman",
TITLE="Neural Networks - A High Impact Technology with Applications in
Telecommunications",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="1038-1042",
YEAR=1991,
KEYWORDS="Communication; neural network",
}

@BOOK{Come91:Internetworking,
AUTHOR="D. Comer",
TITLE="Internetworking with {TCP/IP} - Volume {I;} Principles, Protocols
andArchitecture",
PUBLISHER="Prentice Hall",
YEAR=1991,
KEYWORDS="Arpanet; internetwork; internetwork protocol; internetworking;
network management; protocol; tcp/ip",
}

@TECHREPORT{Daup91:Method,
AUTHOR="P. Dauphin and M. Paterok and U. Herzog",
TITLE="The Method of Moments for Higher Moments - Problems, Solutions,
and Tools",
INSTITUTION="IMMD VII, FAU Erlangen-Nürnberg",
ADDRESS="Erlangen, Germany",
PAGES=20,
YEAR=1991,
REFERENCES=15,
KEYWORDS="Analysis; little's formula; m/g/1; moment",
ABSTRACT="... This paper investigates the suitability of the method of
moments to derive higher moments. Sums of random variables, Little's law
for higher moments, and conditional remaining service times play an
important role. Starting from general considerations,the problems in
dealing with higher moments are insulated, and some solutions are
presented. The results give a deep insight into the nature of the method
of moments. ...",
}

@ARTICLE{Flem91:Interpolation,
AUTHOR="P. Fleming and B. Simon",
TITLE="Interpolation approximations of sojourn time distributions",
JOURNAL=or,
VOLUME=39,
NUMBER=2,
PAGES="251-260",
YEAR=1991,
REFERENCES=18,
KEYWORDS="Approximation; feedback; interpolation; limit theorem;
priority; queueing system",
ABSTRACT="We present a method for approximating sojourn time
distributions in open queuing systems based on light and heavy traffic
limits. The method is consistent with and generalizes the interpolation
approximations for moments previously presented by M.I. Reiman and B.
Simon. The method is applicable to a class of systems ... networks of
priority queues with unique bottleneck node ... M/M/1 with Bernoulli
feedback ... priority queue with feedback ...",
}

@ARTICLE{Good9106:Trends,
AUTHOR="David J. Goodman",
TITLE="Trends in Cellular and Cordless Communications",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=6,
PAGES="31-41",
MONTH="Jun",
YEAR=1991,
KEYWORDS="Cellular; Cordless Communications; mobile radio; packet
radio",
ABSTRACT="As Products that allow people to use the worldwide public
telecommunications network in a natural, convenient manner, cellular
telephones and residential cordless telephones enjoy widespread public
approval. Both are relatively new, introduced in the 1980s in most
places, and the demand for both is increasing rapidly. To meet this
demand, increase quality, and enlarge the range of applications, new
second generation systems are emerging. The second generation will be
characterized by digital speech transmission and enhanced capabilities
of wireless terminals to exchange signaling and control information with
the remainder of the network. Meanwhile, researchers and planners are
devoting increasing attention to third generation technologies to meet
the needs of the next century.",
}

@INPROCEEDINGS{Gril91:Future,
AUTHOR="D. Grillo and F. U. Bordoni",
TITLE="Future Public Land Mobile Telecommunication Systems {(FPLMTS)} -
Teletraffic and Performance Issues",
BOOKTITLE=itc13,
ADDRESS="Torino, Italy",
PAGES="271-276",
YEAR=1991,
REFERENCES=17,
KEYWORDS="In; intelligent network; mobile radio; survey; traffic
engineering",
ABSTRACT="To cope with the prospected high demand for mobile services
and personal communication, future mobile radio systems are considered
worldwide. Teletraffic issues for future mobile systems are receiving
increasing attention. The impact should be measured, forecast and
appropriately handled, to ensure that it doesnot create service
impairment. In the following a few teletraffic problems arising with
FPLMTS are briefly addressed.",
}

@ARTICLE{Huth91:RISC,
AUTHOR="N. Huth",
TITLE="{RISC} und {CISC:} Die Grenzen verschwinden",
JOURNAL=design_elekt,
ADDRESS="München, Germany",
PAGES="72-75",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Processor; risc",
ABSTRACT="Wie kann die betagte 80x86-Familie gegenueber modernen
RISC-Architekturen bestehen?",
}

@ARTICLE{Hutt91:88k,
AUTHOR="R. Huttenloher",
TITLE="88k - die zweite",
JOURNAL=design_elekt,
ADDRESS="München, Germany",
PAGES="64-68",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Processor; risc",
ABSTRACT="Die zweite Generation der Prozessorfamilie M88000 steht mit
demBaustein MC88110 bereit. Seine symmetrische
Superscalar-Mikroarchitektur ist ausgelegt, um zwei Instruktionen pro
Takt abzuarbeiten, somit wird eine Rate von weit mehr als einem Befehl
pro Taktzyklus ermoeglicht. Bei einer Ausfuehrungstaktrate von 50 MHz
erreicht der Prozessor ein Performance-Potential von 100 MIPS.",
}

@INCOLLECTION{Ichi91:FDDI,
AUTHOR="T. Ichihashi and Y. Yokoyama and K. Hiramatsu and K. Kashima and
Y. Koi",
TITLE="{EVALUATION} {OF} {FDDI-II} {CYCLE} {SYNCHRONIZATION}
{MECHANISMS}",
BOOKTITLE="High Speed Networking III",
PUBLISHER="Elsevier (North-Holland)",
PAGES="91-108",
YEAR=1991,
REFERENCES=8,
KEYWORDS="Fddi-ii; hslan; synchronization",
ABSTRACT="In this paper, we explore a number of possible implementation
methods for 8 kHz synchronization technique and discuss the relationship
between the FDDI-II smoother mechanisms and jitter on cycles by computer
simulation to verify smoother's effectiveness.",
}

@INPROCEEDINGS{Kamo91:Neural,
AUTHOR="F. Kamoun and M. S. Ali",
TITLE="A Neural Network Shortest Path Algorithm for Optimum Routing in
Packet-Switched Communication Networks",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="120-124",
YEAR=1991,
KEYWORDS="Neural network; routing; shortest path",
}

@INPROCEEDINGS{Karo91:PAC,
AUTHOR="Mark Karol and B. S. Glance",
TITLE="Performance of the {PAC} Optical Packet Network",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="1258-1263",
YEAR=1991,
REFERENCES=11,
KEYWORDS="FDMA; optical LAN; WDM",
ABSTRACT="This paper discusses performance aspects of the PAC
(Protection Against Collision) Optical Packet Network. The
delay-throughput performance is analyzed.",
}

@ARTICLE{Kuca9111:Mobile,
AUTHOR="A. D. Kucar",
TITLE="Mobile Radio: An Overview",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="72-85",
MONTH="Nov",
YEAR=1991,
KEYWORDS="Mobile radio; packet radio",
ABSTRACT="Technology is giving us impressive communications,
information, and navigation systems. The social and economic impact will
be substantial.",
}

@INPROCEEDINGS{Lanc91:Experiments,
AUTHOR="R. Lancini and F. Perego and S. Tubaro",
TITLE="Some Experiments on Vector Quantization Using Neural Nets",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="135-139",
YEAR=1991,
KEYWORDS="Neural network",
}

@BOOK{Law91:Simulation,
AUTHOR="A. M. Law and W. David Kelton",
TITLE="Simulation modelling and analysis",
PUBLISHER="McGraw Hill",
YEAR=1991,
KEYWORDS="Analysis; modeling; simulation; simulation model",
}

@BOOK{Lipp91:C,
AUTHOR="S. B. Lippman",
TITLE="{C++} Primer",
PUBLISHER="Addison Wesley",
YEAR=1991,
KEYWORDS="C++; object-oriented programming; programming language",
}

@INCOLLECTION{Lund91:Improving,
AUTHOR="G. Lundy",
TITLE="Improving Throughput in the {FDDI} Token Ring Network",
BOOKTITLE="phsn",
PUBLISHER="Elsevier (North-Holland)",
PAGES="369-382",
YEAR=1991,
REFERENCES=12,
KEYWORDS="Fddi; hslan",
ABSTRACT="In this paper an alternative protocol is suggested, which
attempts to take full advantage of the double ring topology. It does so
by increasing efficiency and parallelism. The token passing part of the
protocol is the same as with FDDI; the change is in the method of
transmitting frames. The maximum throughput is approximately three times
that of the current FDDI, for the suggested procedure.",
}

@INPROCEEDINGS{Naka91:Photonic,
AUTHOR="T. Nakashima and Y. Hamazumi and Nobuyuki. Tokura and Katsuaki.
Kikuchi",
TITLE="Photonic Access Network Architecture",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES="602-606",
YEAR=1991,
REFERENCES=7,
KEYWORDS="Network architecture; wdm; access network",
ABSTRACT="A photonic access network architecture is proposed that can
create the large capacity and extremely flexible netwokr needed to offer
B-ISDN services economically. The networks are characterized by
increased managent flexibility and line capacity. Line capacity of over
100 Gb/s is possible with a single mode fiber. This architecture uses
WDM, FDM and optical switching techniques to keep pace with service and
demand growing. A wavelength division",
}

@BOOK{Anon91:Kriterien,
AUTHOR="Anonymous",
TITLE="Kriterien für die Bewertung der Sicherheit von Systemen der
Informationstechnik {(ITSEC)}",
PUBLISHER="Bundesamt für Sicherheit in der InformationstechnikBSI,
Bundesanzeiger",
ADDRESS="Germany",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Information system; security; system evaluation; technology",
}

@INPROCEEDINGS{Pand91:Universal,
AUTHOR="R. N. Pandya",
TITLE="Universal Personal Telecommunictaion {(UPT)} Services and Related
Traffic Engineering Challenges",
BOOKTITLE=itc13,
PAGES="307-314",
YEAR=1991,
KEYWORDS="Communication; in; intelligent network; survey; traffic
engineering",
ABSTRACT="Universal Personal Telecommunication (UPT) is a rapidly
emerging service concept being developed by the CCITT which will allowa
user to communicate with whomever, whenever and whereever on a global
scale. ...",
}

@INCOLLECTION{Pope91:SUPERLAN,
AUTHOR="A. Popescu and R. Singh",
TITLE="{SUPERLAN:} A Model for Very High Speed Local Area Networks",
BOOKTITLE="Protocols for High-Speed Networks",
PUBLISHER="Elsevier (North-Holland)",
PAGES="383-406",
YEAR=1991,
REFERENCES=21,
KEYWORDS="Hslan; ring network",
ABSTRACT="In this paper we report the results of our study in the design
of a very high speed optical fiber based local area network (LAN),
called SUPERLAN. We discuss the critical issues in designing a multi
Gbit/s network, motivate our concepts, and present the basic solutions
chosen for the media access control (MAC) layer and the physical layer
(PHY).",
}

@ARTICLE{Robr91:Intelligent,
AUTHOR="R. Stubbs I. I.",
TITLE="The Intelligent Network - Changing the Face of
Telecommunications",
JOURNAL=ieeeproc,
VOLUME=79,
NUMBER=1,
PAGES="7-20",
YEAR=1991,
REFERENCES=99,
KEYWORDS="In; intelligent network",
ABSTRACT={With the 1984 divestiture of the Bell Operating Companies from
AT\&T, the newly formed Regional Operating Companies embarked upon a
program to deploy an infrastructure for new service offerings - an
infrastructure called the "Intelligent Network." This network is
changing the face of telecommunications by allowing new services to be
deployed quickly and with ubiquity and service uniformity. The first
services on these new regional Intelligent Ne},
}

@ARTICLE{Schi9111:Broadband,
AUTHOR="Donald L. Schilling and L. B. Milstein and R. L. Pickholtz and
Fred Bruno and E. G. Kanterakis and Marvin Kullback and Vinko Erceg and
William Biederman",
TITLE="Broadband {CDMA} for Personal Communications Systems",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="86-93",
MONTH="Nov",
YEAR=1991,
KEYWORDS="Broadband CDMA; personal communications systems; multipath",
ABSTRACT="Field tests indicate that PCN systems can provide high-quality
communications when sharing the spectrum with fixed-service microwave
systems in suburban and urban areas -- even Manhattan.",
}

@INPROCEEDINGS{Sen91:Comparative,
AUTHOR="A. Sen and P. Maitra",
TITLE="A Comparative Study of Shuffle-Exchange, Manhattan Street and
Supercube Network for Lightwave Applications",
BOOKTITLE=globecom,
ADDRESS="Phoenix, Arizona",
PAGES=21,
YEAR=1991,
REFERENCES=10,
KEYWORDS="Comparison; hslan; man; shufflenet",
ABSTRACT={In this paper we present a new network topology called
"Supercube" and study its performance with respect to the Shuffle
Exchange network and the Manhattan Street network. The static
characteristics of the networks have been studied through their graph
theoretic properties. The dynamic characteristics of the network have
been studied through simulation.},
}

@INCOLLECTION{Serp91:High,
AUTHOR="Dimitrios Serpanos and Richard Lipton",
TITLE="The Design of a High-Speed Network",
BOOKTITLE="High Speed Networking III",
PUBLISHER="Elsevier (North-Holland)",
PAGES="167-176",
YEAR=1991,
REFERENCES=8,
KEYWORDS="Design; hslan; network",
ABSTRACT="The purpose of this paper is to describe how all the important
issues for high-speed networks are addressed in a memory level network
developed at Princeton University. The architecture presented is based
on the inconsistent shared memory model called PRAM, developed at
Princeton University. A prototype built implements most of the
architecture and demonstrates high throughput andlow latencies for many
applications.",
}

@INCOLLECTION{Spie91:Timed,
AUTHOR="E. M. Spiegel",
TITLE="Performance Analysis of the Timed-Token Protocol: A Vacation
Model",
BOOKTITLE="High Speed Networking III",
PUBLISHER="Elsevier (North-Holland)",
PAGES="109-124",
YEAR=1991,
REFERENCES=17,
KEYWORDS="Fddi; fddi-ii; performance evaluation; token bus",
ABSTRACT="We investigate the delay performance af a network using the
Timed-Token Protocol through the use of a vacation model. The
Timed-Token Protocol is a recent extension of previous token-passing
protocols. It has been implemented in the Fiber Distributed
DataInterface (FDDI) and the IEEE 802.4 Token Bus to control
mediumaccess for asynchronous traffic. In our vacation model, attention
is focused on the operation of the protocol at a single statio",
}

@BOOK{Stro91:C,
AUTHOR="B. Stroustrup",
TITLE="The c++ Programming Language: 2nd edition",
ISBN="0-201-53992-6",
PUBLISHER="Addison-Wesley",
ADDRESS="Reading, Massachusetts",
YEAR=1991,
KEYWORDS="C++; object-oriented programming; programming language",
}

@ARTICLE{Teki9111:Handover,
AUTHOR="S. Tekinay and B. Jabbari",
TITLE="Handover and Channel Assignment in Mobile Cellular Networks",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="42-47",
MONTH="Nov",
YEAR=1991,
KEYWORDS="Handover; channel assignment; mobile cellular networks",
ABSTRACT="Quick and timely handover has a crucial effect on how users
perceive quality of service, however, handover strategies should not be
too complicated.",
}

@BOOK{Zeid91:Lexikon,
AUTHOR="G. Zeidler and  others",
TITLE="Lexikon der Nachrichtentechnik - Ingenieurwissen für die Praxis",
PUBLISHER="Schiele and Schön",
ADDRESS="Germany",
YEAR=1991,
LANGUAGE="German",
KEYWORDS="Communication; dictionary; reference",
}

@ARTICLE{Hawl9103:Historical,
AUTHOR="George T. Hawley",
TITLE="Historical Perspectives on the {U.S.} Telephone Loop",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="24-30",
MONTH="Mar",
YEAR=1991,
KEYWORDS="U.S.; telephone loop",
ABSTRACT="The word loop implies a circle or ring. In the traditional
telephone business the loop is a pair of wires, usually copper, powered
by direct current between the telephone company's central office and a
person's home or office. The term loop probably comes from the notion of
electrons from a central battery traveling to the telephone over one
wire and returning (looping back) over the other wire. A great many
technological changes have occurred over the past 115 years that have
affected the nature and design of the telephone loop. So the telephone
loop, a simple concept, has proved to be a worldwide $100+ billion
investment by governments and major business enterprises with many
associated management and technological challenges. The end of these
challenges is not yet in sight.",
}

@ARTICLE{Andr9103:Evolution,
AUTHOR="Frederick T. Andrews",
TITLE="The Evolution of Digital Loop Carrier",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="31-35",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Digital Loop Carrier; DLC",
ABSTRACT="digital loop carrier systems are now firmly established as the
most cost effective means of providing up to \50\% of new subscriber
loop plant. This position has been achieved by the hard work of many
engineers and their organizations over a period of several decades. The
evolution to the present status of Digital Loop Carrier systems (DLCs)
has required major shifts from established methods for building loop
plant. Today, these shifts are popularly called ``paradigm shifts'' and
are recognized as being particularly difficult for those closest to
existing practices to accept.",
}

@ARTICLE{Tenz9103:Optical,
AUTHOR="Gerd Tenzer",
TITLE="The Introduction of Optical Fiber in the Subscriber Loop in the
Telecommunication Networks of {DBP} {TELEKOM}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="36-49",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Optical fiber; subscriber loop; telecommunication networks;
DBP TELEKOM",
ABSTRACT="Since the late 1970s, it has been more and more recognized in
the industrialized countries that the existing terrestrial
telecommunication networks can almost completely be replaced in their
essential components, i.e., the physical cable systems, the transmission
equipment, and the exchanges, if fundamentally new technologies are
introduced in the next few decades, and that the expected increases can
be built up directly in new technologies. These new technologies may be
described in three key concepts: The breathtaking and unbroken progress
achieved in semi-conductor technology (cheap chips); The development and
use of digital switching and Pulse-Code Modulation (PCM); The
development of optical communications over optical fiber cables, a new
transmission medium with bandwidth and other characteristics far
superior to those of copper",
}

@ARTICLE{Rowb9103:Local,
AUTHOR="Thomas R. Rowbotham",
TITLE="Local Loop Developments in the {U.K.}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="50-59",
MONTH="Mar",
YEAR=1991,
KEYWORDS="local loop; U.K",
ABSTRACT="The local loop is the most cost-sensitive area of any
telecommunications network. It is the all important interface to the
customer and, as such, plays a leading role in the revenue-earning
capacity of the telecommunications operator. Since the local loop is
both hardware- and manpower-intensive, even the smallest changes must be
based upon a coherent strategy. This strategy must reflect the changing
nature and demands of the customer. While it has to be based upon the
economic delivery of existing services, it must also demonstrate an
evolutionary path to future services. However, the nature and time
scales of future services are unclear. The growth of new services is
determined by many factors, which are often beyond the control of the
telecommunications operator. In the case of British Telecom (BT), the
provision of new services in the U.K. is distorted by a changing
regulatory and competitive operating environment. In addition, the U.K.
can no longer be considered in isolation from the worldwide
telecommunications market, in which the rest of Europe is particularly
significant.",
}

@ARTICLE{Miki9103:Japanese,
AUTHOR="T. Miki and R. Komiya",
TITLE="Japanese subscriber Loop Network and Fiber Optic Loop
Development",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="60-67",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Japanese subscriber loop network; fiber optic loop",
ABSTRACT="Telecommunication local network are rapidly evolving with the
introduction of local digital switching systems, high-speed digital
subscriber lines, optical fiber techniques, and the development of new
local network schemes. Roughly half the local switching systems have
been converted from analog to digital, and almost all local switching
systems will be completely digital by 1998 [1]. Optical fiber local-loop
cable installation has been rapidly advancing since 1984, mainly in
urban areas.",
}

@ARTICLE{Shum9103:Evolution,
AUTHOR="Paul W. Shumate and Richard K. Snelling",
TITLE="Evolution of Fiber in the Residential Loop Plant",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="68-75",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Fiber optic; residential loop plant",
ABSTRACT="Less than ten years ago, optical fiber was introduced into the
loop network as feeder for Digital Loop Carrier (DLC) systems. DLC
reduces costs by permitting dedicated facilities to be replaced with
lower-cost shared facilities. In addition, remote multiplexers located
near subscribers offer flexibility for dealing with growth. The success
of fiber fed DLC is reflected in the fact that several million
residential lines are derived in this way, and the application is
growing at about 35\% per year.",
}

@ARTICLE{Tayl9103:Power,
AUTHOR="Tracy M. Taylor",
TITLE="Power and Energy in the Local Loop",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="76-83",
MONTH="Mar",
YEAR=1991,
KEYWORDS="local loop; power supply",
ABSTRACT="The History of Powering Telecommunications in the local loop
is one that appears to be coming full circle in terms of the source of
power. From the time of Alexander Graham Bell's invention of the
telephone in 1875 through the first two decades of deployment, power was
provided at the customer end of the loop. We refer to this as ''local
powering.'' In 1894, deployment of common batteries in Central Offices
(COs) eliminated the need for a local source. With very few exceptions,
power for the local loop has been provided from the network-end ever
since. However, as new technologies such as Integrated Services Digital
Network (ISDN) and Fiber In The Loop (FITL) make their way into the
loop, local powering may again be preferred. The possibility of
returning to local powering invokes great concern from local exchange
carrier executives, for it moves this vital function out of the
controlled environment of the CO into a less controlled or even
uncontrolled outside plant. A preeminent concern for uninterruptable
service, however, is expected to cause this transition to be smooth.",
}

@ARTICLE{Spen9103:Establishing,
AUTHOR="J. Spencer and Duane S. Kobayashi",
TITLE="Establishing Reliability and Availability Criteria for
Fiber-in-the-Loop Systems",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="84-91",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Fiber-in-the-loop systems",
ABSTRACT="With mass deployment of fiber in the LOOP (FITL) ready to
begin (and all the inherent technology issues associated with this), it
is essential to understand some of the factors that have shaped the
development of reliability criteria and availability objectives. This
article deals exclusively with these topics, focusing on Plain Old
Telephone Service (POTS). More generally, though, the issues addressed
here apply to any existing narrowband service provided via 64 kb/s
telephone lines.",
}

@ARTICLE{Cox9103:Low,
AUTHOR="Donald Cox and Wesley M. Gifford and Howard Sherry",
TITLE="Low-Power Digital Radio as a Ubiquitous Subscriber Loop",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="92-95",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Digital radio; subscriber loop",
ABSTRACT="Digital radio has become an economical technology for
implementing subscriber loops in low-density rural areas. The use of
digital radio technology for this rural loop application was facilitated
by the 1988 Federal Communications Commission (FCC) allocation of radio
spectrum at 150 MHz, 450 MHz, and 900 MHz in its Basic Exchange
Telecommunications Radio Service (BETRS) proceedings. Relatively
high-power (greater than 1 W) radio links are used in BETRS to provide
subscriber loops of up to 10 miles or so to widely scattered
subscribers.",
}

@ARTICLE{Wari9103:Digital,
AUTHOR="David L. Waring and Joseph Lechleider and To R. Hsing",
TITLE="Digital Subscriber Line Technology Facilitates a Graceful
Transition from Copper to Fiber",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="96-108",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Digital subscriber line; DSL; copper; fiber",
ABSTRACT="High-performance transmission over subscriber loops has
historically required considerable engineering in order to accommodate
the wide range of loop makeups encountered in the distribution plant.
Recently, self- adaptive filtering techniques have been applied to
transmission over subscriber loops. This technology, which had
previously been too complex and expensive for widespread use, can now be
integrated into single Very Large-Scale Integration (VLSI) devices that
make transmission over the loop plant much more robust and cost
effective. Continuing advances will enable higher bit rates to be
achieved. In this article, we review the loop environment and the
techniques that historically have been used for providing transmission
treatment. Then we introduce the Digital Subscriber Line (DSL), which
applies adaptive filtering to yield significant performance and
administrative advantages. Finally, we discuss how this technology will
evolve to complement the emerging fiber-based network, providing timely,
ubiquitous wire pair transmission capabilities at Basic Rate, Primary
Rate, and above.",
}

@ARTICLE{Latt9103:Business,
AUTHOR="P. Douglas Lattner and Robert L. Fike and Gary A. Nelson",
TITLE="Business and Residential Services for the Evolving Subscriber
Loop",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="109-115",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Residential services; subscriber loop",
ABSTRACT="It Is the unanimous position of the Regional Bell Operating
Companies (RBOCs) and Bell Communications Research (Bellcore) that Fiber
In The Loop (FITL) will only be deployed when the technology is at, or
below, cost parity with today's copper systems for the delivery of Plain
Old Telephone Service (POTS). Thus, the services deliverable on FITL are
not specifically aimed at providing new revenue sources during early
deployment of the new technology. The principal reason for this is the
fact that even the most optimistic rollout scenario does not predict
ubiquitous fiber access before the year 2010. If this is the case, then
economic justification of any new services that rely entirely upon FITL
will be very difficult.",
}

@ARTICLE{Whit9103:Role,
AUTHOR="Patrick E. White",
TITLE="The Role of the Broadband Integrated Services Digital Network",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=3,
PAGES="116-119",
MONTH="Mar",
YEAR=1991,
KEYWORDS="Broadband Integrated Services Digital Network; BISDN",
ABSTRACT="The broadband integrated services Digital Network (BISDN) is
commonly viewed as the next major step in the evolution of the switched
telephone network. It is based on an infrastructure consisting of
optical fiber transmission and high-speed electronic switching systems,
at least in the early stages. The BISDN is designed to handle a wide
variety of services ranging from voice to data and, ultimately, the
distribution of high-quality entertainment video signals. BISDN is also
expected to support multimedia services such as conferencing, which have
subelements consisting of voice, data, and video.",
}

@ARTICLE{Andr9101:Switching,
AUTHOR="Frederick T. Andrews",
TITLE="Switching in a Competitive Market",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="18-24",
MONTH="Jan",
YEAR=1991,
KEYWORDS="communications networks",
ABSTRACT="The last decade has seen an accelerating trend towards more
open and competitive telecommunications networks on a worldwide basis.
Nowhere has that change been more significant than in the U.S. As a
result of both technological advances and a series of judicial and
regulatory actions, users now have a choice of communications products
and services undreamed of in the past. Large users, in particular, have
taken advantage of this flexibility to configure communications networks
that make the best use of public and private resources to meet their
needs. They are driven by their more sophisticated requirements for
information networking and a desire to have control over a resource so
important to their ability to compete. There is developing competition
for mass markets as well.",
}

@ARTICLE{Murp9101:Automation,
AUTHOR="Michael A. Murphy and Gregory Bielby and Bruce Roe and Ken Read
and Al O'Gorman and Matthew Lennig",
TITLE="Automation of Alternate Billed Calls Using Speech Recognition",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="25-29",
MONTH="Jan",
YEAR=1991,
KEYWORDS="Automation; Alternate Billed Calls; Speech Recognition",
ABSTRACT="Alternate billed calls (collect, calling-Card,
bill-to-third-party) represent close to 50\% of the toll and assist
traffic in North America, requiring substantial operator workforce
expenditures for telephone companies. This article describes the
Automated Alternate Billing Service (AABS) developed by Bell-Northern
Research (BNR) and being deployed throughout North America by Northern
Telecom, which automates a large component of this traffic. Emphasized
are the usage of recent advances in voice recognition technology and an
innovative call script tool designed to simplify realization of the AABS
application.",
}

@ARTICLE{Guen9101:ISDN,
AUTHOR="Jean-Pierre Guenin and Therese Morin and Pierre Deffin and
Francois Leclerc and Roger Trubert",
TITLE="{ISDN} in France - 1987 to 1990: From the First Commercial
Offering to National Coverage of {NUMERIS}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="30-35",
MONTH="Jan",
YEAR=1991,
KEYWORDS="ISDN; France; NUMERIS",
ABSTRACT="Numeris, The commercial name of the integrated Services
Digital Network (ISDN) in France, is now completing its phase of
nationwide coverage. By the end of 1990, any subscriber request for
access to NUMERIS from anywhere in the country will be satisfied (see
Figure 1). This achievement has been made possible by the development of
equipment at the subscriber access and transmission line levels, and new
software releases for in-service digital exchanges. This development,
having already been the object of an upgrading phase for enhanced
service quality and reduced costs, was undertaken while international
standards were still being discussed. In order to fully comply with the
resulting standards, further adaptations have been required.",
}

@ARTICLE{John9101:5ESS,
AUTHOR="Jerald L. Johnson and Richard P. Cetti and Michael H. Cooper and
R. J. Wilson and Robin J. Thompson",
TITLE="{AT\&T's} {5ESS} Switch: Early Experiences and Details on
Planning and Implementing a Large-Scale {ISDN} Corporate {R\&D}
Network",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="36-43",
MONTH="Jan",
YEAR=1991,
KEYWORDS="AT\&T; 5ESS Switch; ISDN; Corporate R\&D Network",
ABSTRACT="Integrated services digital network (ISDN) is a reality in the
United States. Corporations, both large and small, have found the
enhanced services provided by ISDN to be productive and beneficial. The
AT\&T Bell Laboratories Indian Hill campus is a corporate campus
Research and Development (R\&D) environment located in Naperville,
Illinois with approximately 8,000 employees spread across several
buildings. In mid-1987, Bell Lab- oratories, together with Illinois Bell
Telephone (IBT), began planning the replacement and upgrade of existing
voice and data telecommunications equipment.",
}

@ARTICLE{Fuji9101:Universal,
AUTHOR="M. Fujioka and Hikaru Yagi and Y. Ikeda",
TITLE="Universal Service Creation and Provision Environment for
Intellligent Network",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="44-51",
MONTH="Jan",
YEAR=1991,
KEYWORDS="Universal Service Creation; Provision Environment; Intelligent
Network",
ABSTRACT="With the progress of the information-oriented society, the
role Of telecommunications is becoming more and more important. Not only
has the amount of telecommunications traffic been increasing, but also
the demand for variation in service capability. The so-called
Intelligent Network (IN) functions have been realized to provide a
number of services to respond to this demand. On the other hand, with
the recent deployment of Integrated Services Digital Network (ISDN) in
various countries, powerful networking functions and signaling
capabilities have been provided at the user-network interface as well as
inside the network. Accordingly, underlying arrangements for the
provision of a greater variety of services are being completed. It is
now necessary to establish a widely applicable mechanism to realize
various services. which individual customers are demanding by making
full use of these advanced network capabilities.",
}

@ARTICLE{Bowe9101:Scale,
AUTHOR="T. F. Bowen and G. Gopal and G. Herman and William Jr.
Mansfield",
TITLE="A Scale Database Architecture for Network Services",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="52-59",
MONTH="Jan",
YEAR=1991,
KEYWORDS="Database Architecture; Network Services",
ABSTRACT="In the united states telecommunication network, network
databases are increasingly involved in call processing for the
realization of new network services. A major motivation for this
architectural trend has been the desire to permit more rapid creation
and deployment of new network services. Deploying service-specific data
in central databases allows the data required to process certain call
attempts to be accessed as necessary by any switching node in the
network over a common channel signaling network. This approach permits
ubiquitous availability of a service with only minimal changes to local
switches, and allows many aspects of the service to be defined and
modified based on the contents of the central databases. The initial
deployment of such an architecture began in the 1970s to provide 800
service and credit card verification.",
}

@ARTICLE{Maru9101:Concurrent,
AUTHOR="K. Maruyama and Nayoa Watanabe and Keiich Koyanagi and Toshihiro
Kai and Shinji Tomita",
TITLE="A Concurrent Object-Oriented Switching Program in Chill",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="60-68",
MONTH="Jan",
YEAR=1991,
KEYWORDS="Switching services; Concurrent Object-Oriented Switching
Program; Chill",
ABSTRACT="Switching services and features are becoming more and more
complex, and they are being added more frequently.",
}

@ARTICLE{Byrn9101:Evolution,
AUTHOR="William R. Byrne and George Clapp and H. J. Kafka and Gottfried
Luderer and Bruce Nelson",
TITLE="Evolution of Metropolitan Area Networks to Broadband {ISDN}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="69-82",
MONTH="Jan",
YEAR=1991,
KEYWORDS="Metropolitan Area Networks; Broadband ISDN",
ABSTRACT="The rapid growth of personal computers (PCs) and workstations
in the business market has in turn spawned a 30 to 35\% annual growth
rate in sales of Local Area Networks (LANs). Today's LANs are on the
edge of broadband speeds(e.g., 10 Mb/s Ethernets and 4 Mb/s token
rings), and new LAN proposals call for higher speeds(l6 Mb/s token rings
and 100 Mb/s Fiber Distributed Data Interface--FDDI). Higher speeds are
needed to match the increasing speed of the PCs and to support diskless
workstations and Computer-Aided Design/Manufacture (CAD/CAM) terminals
that rely on LANs for interconnection to file servers.",
}

@ARTICLE{Wern9101:Broadband,
AUTHOR="Marek R. Wernik and E. A. Munter",
TITLE="Broadband Public Network and Switch Architecture",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="83-89",
MONTH="Jan",
YEAR=1991,
KEYWORDS="Broadband Public Network; Switch Architecture",
ABSTRACT="In order to satisfy future services requirements,
telecommunication networks are undergoing significant functional changes
enabled by transmission, switching, and signaling technology advances.
Today's public switched networks are increasingly penetrated by digital
technology. This has provided a base network capability suitable for a
range of services beyond the traditional voice service. Further
enhancements are required to support the increased volume of existing
applications and provide the flexibility and performance required for
future multimedia broadband applications. Fiber transmission standards
such as Synchronous Optical Network (SONET) provide the capability to
build reliable and survivable transmission structures, and will also
allow for the design of high-performance fiber access systems, therefore
enabling physical integration of existing and future services.",
}

@ARTICLE{Saku9101:Large,
AUTHOR="Y. Sakurai and N. Ido and S. Gohara and Noboru Endo",
TITLE="Large-Scale {ATM} Multistage Switching Network with Shared Buffer
Memory Switches",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="90-96",
MONTH="Jan",
YEAR=1991,
KEYWORDS="ATM Multistage Switching Network; Shared Buffer Memory
Switches",
ABSTRACT="Progress toward the Standardization OF Broadband Integrated
Services Digital Network (BISDN) by the International Consultative
Committee for Telephone and Telegraph (\%CITT) is being accelerated.
Asynchronous Transfer Mode LATM) is considered a promising technique to
implement BISDN, because ii is able to deal efficiently with various
kinds of media such as telephone speech, digital data, motion video, and
multimedia. The efficiency of ATM is based on the statistical
multiplexing of fixed-length packets, which are called ``cells.'' One of
the main concerns of researchers in this field so far is constructing
technologies for the ATM cell switching network. A high-speed hardware
switch is required for ATM switching because the transfer rate of BISDN
is 150 Mb/s or more, and cell buffers are required because of the
statistical multiplexing. The arrangement of the buffers and switches is
an important technological point for realizing the ATM switching
network.",
}

@ARTICLE{Doma9101:Two,
AUTHOR="Gunter Domann",
TITLE="Two Years of Experience with Broadband {ISDN} Field Trial",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="97-104",
MONTH="Jan",
YEAR=1991,
KEYWORDS="Broadband ISDN",
ABSTRACT="Due to immense progress in technology during the past few
decades, the basic conditions for the development of broadband
communication systems are available. To demonstrate the technical and
economic feasibility of such systems, a comprehensive research program
was started in 1985 at the SEL Research Center, with the target to
provide the necessary components for Integrated Services Digital Network
(ISDN)-based broadband systems and to demonstrate their application in a
prototype system. This system was designed to be expandable for up to
10,000 subscribers. Due to this activity, SEL was able to provide the
first digital broadband network (See Figure 1) for the BERKOM project,
which represents the largest Broadband ISDN (BISDN) field trial in the
world. The modularity of SEL concept allows the extension of an existing
ISDN switch (System 12) to a broadband exchange. The exchange and
equipment for the first subscribers were installed in the beginning of
1988, starting system operation in March 1988. This article first
outlines the targets of the BERKOM field trial and then reports on three
topics of the test network: sys- tem concept, system extension, and
system experience.",
}

@ARTICLE{Buck9101:Business,
AUTHOR="Colin Buckingham and Ge Klein Wolterink and Dag Akerberg",
TITLE="A Business Cordless {PABX} Telephone System on 800 {MHz} Based on
the {DECT} Technology",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=1,
PAGES="105-110",
MONTH="Jan",
YEAR=1991,
KEYWORDS="Business Cordless PABX Telephone System; 800 MHz Based; DECT
Technology",
ABSTRACT="In January 1988, the European conference of Postal and
Telecommunications administrations (CEPT), the standardization body for
the European Postal, Telephone, and Telegraphs (PTTs), decided to base
the standard for medium- and long-term applications of advanced Digital
European Cordless Telecommunications (DECT) on Multicarrier/Time
Division Multiple Access/Time Division Duplex (MC/TDMA/TDD). The
applications, including voice and data, range from simple residential
cordless telephones to Private Automatic Branch Exchanges (PABXs) with
wireless extensions and wireless PABXs to Pan European telepoints with
both ingoing and outgoing calls and other evolutionary systems.",
}

@ARTICLE{Obuc9102:Wireless,
AUTHOR="Janice Obuchowski",
TITLE="Wireless Communications and Spectrum Conservation: Sending a
Signal to Conserve",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="26-29",
MONTH="Feb",
YEAR=1991,
KEYWORDS="Wireless Communications; Spectrum Conservation",
ABSTRACT="When saddam hussein threatened to take the world's oil supply
hostage, President Bush sent in the 82nd Airborne Division. When we
start to run low on radio spectrum, calling in the cavalry will not
help. Our only rescue will come from spectrum engineers. But our call
for help must come in time. Every reader of this magazine probably knows
a dozen ways to improve spectrum efficiency to facilitate new personal
communications and other wireless applications, but other engineers in
the late LS)60s knew how to improve gas mileage in automobiles and did
little about it. When customers do not know or care about coming
shortages, neither do the executives who set engineering priorities.
What was true of the impending energy crisis in the late '60s is even
more true of the impending spectrum shortage of the '90s: All of the
expertise of spectrum engineers, all of their science, and all of their
capacity for hard work will be irrelevant to spectrum efficiency unless
we can somehow build incentives to make their customers and clients care
about it.",
}

@ARTICLE{Ginn9102:Personal,
AUTHOR="Sam Ginn",
TITLE="Personal Communication Services: Expanding the Freedom to
Communicate",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="30-39",
MONTH="Feb",
YEAR=1991,
KEYWORDS="Personal Communication Services; Freedom to Communicate",
ABSTRACT="As the tumultuous events in eastern Europe continue to unfold,
it is ironic to recall that television was born in 1946, just as World
War II ended. As television grew up, so did the Iron Curtain. But in the
end, the power of the airways proved stronger. The day after the Berlin
Wall fell, West Germany's Minister of Posts and Telecommunications,
Christian Schwarz-Schilling, spoke to an audience in Boston. ``The Iron
Curtain that was to hermetically seal off Eastern Europe from Western
Europe,'' he said, ``could not prevent radio waves from reaching the
East and carrying information on the success of the Western democratic
societies.'' Freedom of communication took a different route in China,
where the airwaves were decidedly not free. During the weeks following
the Tiananmen Square massacre in June 1989, the Chinese government used
state-run TV and radio to broadcast its own version of events. But
Chinese students turned to another communications medium--a network of
telephone lines and fax machines--to bypass formal authority and tell
the world a different story. Afterward, in the weeks following the
government crackdown, China's only source of uncensored news about
Tiananmen--and the world's outraged reaction-- was a flood of fares from
Hong Kong, Europe, and the U.S.",
}

@ARTICLE{Ross9102:Wireless,
AUTHOR="Ian M. Ross",
TITLE="Wireless Network Directions",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="40-43",
MONTH="Feb",
YEAR=1991,
KEYWORDS="Wireless Network",
ABSTRACT="Alexander Graham Bell'S Invention OF the telephone over one
hundred years ago launched a revolution in communications that enabled
people to communicate efficiently over distance. Today, a new revolution
is taking shape--a wireless communications revolution--that will at long
last free customers from the tether of the phone cord. Wireless
techniques have long been used by communications carriers and the very
largest of businesses. Radio technology has been used for point-to-point
carrier and private micro- wave transmission systems as alternatives to
copper wire and coaxial cable. Even today, digital radio instead of
fiber is widely used for some network links. Wireless loop systems are
used in rural areas for cost and terrain reasons. And satellite
communication is well established for broadcast services, data networks,
and voice services.",
}

@ARTICLE{Smit9102:Spread,
AUTHOR="D. G. Smith",
TITLE="Spread Spectrum for Wireless Phone Systems: The Subtle Interplay
between Technology and Regulation",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="44-47",
MONTH="Feb",
YEAR=1991,
KEYWORDS="Spread Spectrum; Wireless Phone Systems",
ABSTRACT="Since the First federal communication Commission (FCC)
hearings on new wireless telephone services, held on July 1 i, 1989,
there has been an explosion of interest in spread spectrum technology
for use in telephone products. The reason is simple: There are no
unallocated frequencies in the United States that are practical for use
in portable Radio Frequency (RF) devices, and spread spectrum techniques
offer the potential for sharing the radio spectrum However, the
similarity between different spread spectrum proposals ends with this
common goal. The specific reasons, techniques, and claims vary
considerably from proposal to proposal. Moreover, the results of several
technical experiments will set the framework for the regulatory options.
This article will attempt to categorize some of the spread spectrum
proposals and outline why one must differentiate between the issues
raised by the proposed wireless services versus those raised by the
proposed wireless equipment. In particular, it will focus on some of the
requirements for introducing wireless telephones into office systems
such as Private Branch Exchanges (PBXs) and key systems. Thus far, the
needs of the office market seem to have been overshadowed by discussion
and debates on spectrum allocation for new telephone services.",
}

@ARTICLE{Tayl9102:Spread,
AUTHOR="J. Taylor and J. K. Omura",
TITLE="Spread Spectrum Technology: A Solution to the Personal
Communications Services Frequency Allocation Dilemma",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="48-51",
MONTH="Feb",
YEAR=1991,
KEYWORDS="Spread Spectrum Technology; Personal Communications Services
;Frequency Allocation",
ABSTRACT="On October 1, 1990, a virtual tidal wave of paper hit the
Federal Communications Commission (FCC). That was the due data for
comments in the FCC's Notice of Inquiry (NOI) into the establishment of
new Personal Communications Services (PCS) (Gen. Docket No. 90-314).
Over 100 companies filed comments. In the NOI, the Commission identified
PCS in the broadest of terms to encompass wireless communications
services",
}

@ARTICLE{Agne9102:Efficient,
AUTHOR="C. E. Agnew",
TITLE="Efficient Spectrum Allocation for Personal Communications
Services",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="52-55",
MONTH="Feb",
YEAR=1991,
ABSTRACT="Personal communications service (PCS) is A general term used
to describe a variety of mobile radio services that reuse the spectrum
among a number of cells. PCS is intended to provide everyone with the
ability to communicate wherever they are--",
}

@ARTICLE{Lync9102:PCN,
AUTHOR="Richard J. Lynch",
TITLE="{PCN:} Son of Cellular? The Challenges of Providing {PCN}
Service",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="56-57",
MONTH="Feb",
YEAR=1991,
KEYWORDS="PCN; Cellular; PCN Service",
ABSTRACT="Just over a century ago, there was a public demonstration of
what would be a major step forward in the field of communications at the
1876 Centennial Exposition in Philadelphia. It was, of course, Mr.
Bell's telephone set, and initially it met with skepticism that few
people would be interested in such a device when there was such ready
access to delivery boys and the telegraph. In London it was called a
``scientific toy,'' of no lasting import. Yet by early 1881 , the first
American Bell Telephone Company annual report noted that only nine
cities with populations greater than 10,000 lacked a telephone exchange,
and that there were already 132,692 telephones in use.",
}

@ARTICLE{Nore9102:Regulatory,
AUTHOR="Gary K. Noreen",
TITLE="Regulatory Flexibility in Commercial Satellite Communications",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="58-61",
MONTH="Feb",
YEAR=1991,
KEYWORDS="MSAT; Commercial Satellite Communications; Mobile Satellite
Service",
ABSTRACT="The launch of the first MSAT spacecraft in 1994 will herald a
revolution in mobile communications. It will also mark the completion of
a twelve-year regulatory and institutional formation process that has
created a highly flexible regulatory structure and a strong
institutional base for the introduction of innovative mobile services
provided through satellites. MSAT is a domestic Mobile Satellite Service
(MSS) system under development in the United States by the American
Mobile Satellite Corporation (AMSC) and in Canada by Telesat Mobile,
Inc.. Communications between fixed ground stations and mobiles
throughout North America will be relayed through MSAT satellites in
geostationary orbits at far greater power than previously available. A
system under development by Radio Satellite Corporation (RSC) will use
MSAT to pro- vide a wide range of integrated services to consumers
through low-cost radios, including paging, two-way voice and data
communications, data and audio broadcasts, and precision navigation.",
}

@ARTICLE{Sing9102:Personal,
AUTHOR="Richard M. Singer and D. Irwin",
TITLE="Personal Communications Services: The next technological
Revolution",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="62-67",
MONTH="Feb",
YEAR=1991,
KEYWORDS="Personal Communications Services; PCS",
ABSTRACT="The telecommunications industry IS witnessing the beginning of
a technological revolution that may transform its role in society.
Personal Communications Services (PCS) have the prospect of providing
more convenient, ubiquitous, and versatile services than the public has
ever received. PCS could enhance the importance of telecommunications in
daily life, improve business productivity, and spawn the entry of new
providers of communications services. PCS may appear in many forms,
including portable coin Cordless Telephone second generation (CT-2)
offerings, wireless Private Branch Exchanges (PBXs), wireless local area
distribution links, and two-way portable Personal Communications
Networks (PCNs), which are self-contained and interconnected with the
public switched telephone network. PCS, effectively, would afford dial
tone to the world.",
}

@ARTICLE{Hoff9102:Imminent,
AUTHOR="and Paul C. Clark",
TITLE="Imminent Policy Considerations in the Design and Management of
National and International Computer Networks",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=2,
PAGES="68-74",
MONTH="Feb",
YEAR=1991,
KEYWORDS="Policy; Management; National; International Computer
Networks",
ABSTRACT="The computer networking community stands at the threshold of a
new era in communications, linking persons around the world. There is a
window of time available now in which to act to rapidly develop policy
standards that are consistent among the various national and
international networks. This article discusses policy questions in
network operation that must be addressed, including privacy, export
policy, and access policy. Concerns about the adequacy of the existing
policy-setting mechanisms are also discussed. In addition, a number of
legal issues are cropping up as networks expand. These are also
considered, and then a brief look at existing systems, such as the
telephone system, the highway network, and the Internet computer
network, is taken to assess how these systems handle policy issues, in
the hope that these solutions may provide insight into resolving policy
questions related to future networks.",
}

@ARTICLE{Finl9104:Intelligent,
AUTHOR="M. R. Finley and Ancilla Karakura and Raphael Nbogni",
TITLE="Survey of Intelligent Building Concepts",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=4,
PAGES="18-23",
MONTH="Apr",
YEAR=1991,
KEYWORDS="Intelligent Building Concepts",
ABSTRACT="Intelligent or smart buildings represent an activity that is
the result of the fusion of several fields involved in building design
and construction, some of which have been in the past regarded as
essentially distinct and non-overlapping, namely, interior and exterior
architecture, the computer and telecommunications technologies,
ergonomics, human factors, building construction technologies in
general, the building Heating, Ventilating and Air-Conditioning (HVAC)
technologies, building security, and all the pertinent mechanical and
electrical technologies. In addition, in order to market the buildings
resulting from this fusion, there is the whole question of educating and
convincing potential clients of the value of choosing an intelligent
building as opposed to a mom traditionally designed one. In this
connection, one frequently hears such terms as ``increased employee
productivity,'' ``savings on computer and telecommunications costs,''
``safer working environment,'' ``greater connectivity,'' ``ergonomic
gains,'' and so forth.",
}

@ARTICLE{Flax9104:Intelligent,
AUTHOR="Barry M. Flax",
TITLE="Intelligent Buildings",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=4,
PAGES="24-27",
MONTH="Apr",
YEAR=1991,
KEYWORDS="Intelligent Buildings",
ABSTRACT="An intelligent building is one that Creates an environment
that maximizes the efficiency of the occupants of the building while at
the same time allowing effective management of resources with minimum
life-time costs. Intelligent buildings make good business sense. As the
Information Age takes us to new heights, the Intelligent Building System
(IBS) has the flexibility, and modularity to accommodate every change.
An intelligent premise distribution system will allow the owner,
administrators, and occupants to take advantage of new technology as it
becomes available, at a minimum cost and without a major disruption of
the productivity of the office work space. Today's competitive society
demands efficiency. In a typical building the power supplies, air
conditioning systems (Heating, Ventilation and Air Conditioning-- HVAC),
lighting, external fabric, security systems, and computers all operate
independently; consequently, building management struggles to satisfy
conflicting demands. But if one adds a comprehensive and integrated IBS
and interrelates the various subsystems through a single control
framework, then the building, factory, hotel, or other type structure
can respond to its environment in a timely and cost-effective manner.",
}

@ARTICLE{Kash9104:Telecommunications,
AUTHOR="Takao Kashiwamura and Hisao Koga and Yasuji Murakami",
TITLE="Telecommunications Aspects of Intelligent Buildings",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=4,
PAGES="28-41",
MONTH="Apr",
YEAR=1991,
KEYWORDS="Telecommunications; Intelligent Buildings",
ABSTRACT="Intelligent buildings offer comfortable office and apartment
environments by interconnecting telecommunications, building automation,
office automation, and facility management systems. In recent years
there have been advances in telecommunications and new information
processing systems involving Private Branch Exchanges (PBXs) and
computers for office automation.",
}

@ARTICLE{Krea9104:Intelligent,
AUTHOR="Paul S. Kreager",
TITLE="The Intelligent Building Telecommunications Infrastructure",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=4,
PAGES="42-49",
MONTH="Apr",
YEAR=1991,
KEYWORDS="Intelligent Building; Telecommunications Infrastructure",
ABSTRACT="There are many aspects to what constitutes an intelligent
building, as witnessed by the variety of areas covered in this special
issue. This article focuses on the telecommunications infrastructure
required for an intelligent building to support the overall
telecommunications utility. Although the infrastructure is perhaps one
of the least exciting topics in the intelligent building arena, this
article will attempt to convey that it is one of the more important. The
infrastructure for telecommunications is the foundation upon which the
success or failure of the building telecommunications utility rests.",
}

@ARTICLE{Fuji9104:Construction,
AUTHOR="Sumio Fujie and Yuji Mikami",
TITLE="Construction Aspects of Intelligent Buildings",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=4,
PAGES="50-57",
MONTH="Apr",
YEAR=1991,
KEYWORDS="Intelligent Buildings",
ABSTRACT="Conventional buildings can no longer meet user' needs in
diverse and internationalized industries for systematic information
services provided through advanced computer technology. In answer to
this, intelligent buildings now contribute to office productivity, which
has grown immensely since the introduction of office automation
techniques.",
}

@ARTICLE{Free9104:Enabling,
AUTHOR="Thomas A. Freeburg",
TITLE="Enabling Technologies for Wireless In-Building Network
communications -Four Technical Challenges, Four Solutions",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=4,
PAGES="58-65",
MONTH="Apr",
YEAR=1991,
KEYWORDS="Wireless; In-Building Network communications",
ABSTRACT="The advances in power and performance we now enjoy thanks to
modern solid-state electronics, we are still shackled with the
problems--physical, logistical, and financial--of wire- and cable-based
communications within buildings. Anyone familiar with installing,
maintaining, and changing building cabling has no need to be convinced
that it is a nightmare crying for a viable wireless alternative. What is
needed is a high-performance, easy-to-deploy, user-transparent,
reliable, wireless in-building communications network technology. Such a
system would also have to be compatible with present and future
cable-based voice/data communications performance, standards, and
protocols.",
}

@ARTICLE{Schi9104:Spread,
AUTHOR="Donald L. Schilling and L. B. Milstein and R. L. Pickholtz and
Marvin Kullback and Frank Miller",
TITLE="Spread Spectrum for Commercial Communications",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=4,
PAGES="66-79",
MONTH="Apr",
YEAR=1991,
KEYWORDS="Spread Spectrum; Commercial Communications",
ABSTRACT="Spectrum has a long and interesting history. It has been, and
still is, used extensively in military communications systems, both to
permit communications which are not detectable by enemy jamming systems
(this property of spread spectrum is called Low Probability of
Interception (LPI), and resist jamming by an enemy desiring to disrupt
communications.",
}

@ARTICLE{Cope9105:VLSI,
AUTHOR="Miles A. Copeland",
TITLE="{VLSI} for Analog/Digital Communications",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=5,
PAGES="25-31",
MONTH="May",
YEAR=1991,
KEYWORDS="VLSI; Analog; Digital Communications",
ABSTRACT="The purpose of this article is to review the state of the art
of Very Large-Scale Integration (VLSI) as applied to communications. We
will discuss the main trends of the present and some extrapolations for
the future. A particular emphasis will be on the prospects for fuller
VLSI integration of low-power digital radio, for applications such as in
building wireless radio receivers. Although some reference will be made
to purely digital/Digital Signal Processing (DSP) contexts, the main
emphasis will be on the front end of the receiver, including
continuous-time analog and sampled analog VLSI filtering, and
technologies that can mix analog and digital on the same chip. We will
be particularly interested in the prospects for the use of Bipolar
Complementary Metal Oxide Semiconductor (BiCMOS) technology in
communications. This new VLSI fabrication process [i] can combine
bipolar and CMOS circuits on the same chip, allowing the use of bipolar
transistors where required for high-analog bandwidth, low noise, and
good current drive, and the use of CMOS circuits where required for high
density and low power. Such a combination makes it possible to
contemplate a one-chip digital radio receiver, and perhaps a
transmitter, that is capable of low-power operation at frequent Although
it is not yet evident that complete success is possible, even partial
success could have a major economic impact.",
}

@ARTICLE{Ahme9105:Recent,
AUTHOR="Hassan M. Ahmed and Richard Kline",
TITLE="Recent Advances in {DSP} Systems",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=5,
PAGES="32-45",
MONTH="May",
YEAR=1991,
KEYWORDS="DSP Systems; Digital SIGNAL PROCESSING; VLSI",
ABSTRACT="Digital Signal processing (DSP) systems have progressed
remarkably in the past decade, especially within the last few years.
Advances in circuit technology, architecture and algorithms have
contributed to the multitude of novel applications of DSP chips. We will
describe some of the advances that have contributed particularly to
communications systems realized with programmable DSP processors. The
commercial Very Large-Scale Integration (VLSI) DSP market is barely a
decade old but the advances have been so rapid that our attention will
largely be focussed on developments within the last few years.",
}

@ARTICLE{Fett9105:High,
AUTHOR="G. Fettweis and Heinrich Meyr",
TITLE="High-Speed Parallel Viterbi Decoding: Algorithm and
{VLSI-Architecture}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=5,
PAGES="46-55",
MONTH="May",
YEAR=1991,
KEYWORDS="Parallel Viterbi Decoding; VLSI; Digital SIGNAL PROCESSING;
DSP",
ABSTRACT="Digital signal processing (DSP) Applications often require
computing speeds that cannot be achieved by standard signal processor
implementations. In this case the use of customized data flow processors
is necessary to meet the given requirements. This requires a careful
examination of algorithms in order to find an architecture appropriate
for Very Large-Scale Integration (VLSI) implementation. The vast
increase in gate density and the ability to build increasingly larger
chips not only enables the integration of whole systems on one
Application Specific Integrated Circuit (ASIC) but also allows the
implementation of massive parallel processors to achieve a speedup by
orders of magnitude for high data rate applications.",
}

@ARTICLE{Rubi9105:General,
AUTHOR="Steven M. Rubin",
TITLE="A General-Purpose Framework for {CAD} Algorithms",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=5,
PAGES="56-62",
MONTH="May",
YEAR=1991,
KEYWORDS="CAD Algorithms",
ABSTRACT="As circuits become larger, the demands on Computer Aided
Design (CAD) systems increase greatly. Not only is there a need for
increasingly larger design capacity, but systems must grow to
accommodate many new synthesis and analysis tools. These tools
proliferate because of new analysis techniques and more effective
generation methods. The need to cut fabrication costs and quickly
produce working parts demands new tools that can eliminate multiple
design iterations. Also, the density and speed of modern Integrated
circuits (ICs) is so sensitive to layout features that effective tools
must make use of both geometry and connectivity. Thus, many traditional
tools are inadequate and must be rewritten.",
}

@ARTICLE{Koni9106:Cryptographic,
AUTHOR="Hans-Peter Konigs",
TITLE="Cryptographic Identification Methods for Smart Cards in the
Process of Standardization",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=6,
PAGES="42-50",
MONTH="Jun",
YEAR=1991,
KEYWORDS="Cryptographic Identification Methods; Smart Cards;
Standardization",
ABSTRACT="In the course of the discussion, it will become apparent that
a smart card (integrated circuit card) in credit card format with a
built-in microcontroller is superior to a magnetic strip card. One
reason is that extremely long cryptographic keys can be stored in secret
zones of the smart car Another reason is that complicated computation
procedures-that are highly essential in cryptography-can be carried out
right in the card.",
}

@ARTICLE{Sosn9106:SONET,
AUTHOR="J. Sosnosky and T.-H. Wu",
TITLE="{SONET} Ring Applications for Survivable Fiber Loop Networks",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=6,
PAGES="51-58",
MONTH="Jun",
YEAR=1991,
KEYWORDS="SONET Ring; Fiber Loop Networks",
ABSTRACT="Fiber in the local loop has progressed from the exploratory
and trial stage to the planning and development of implementation
strategies. Fiber loop diversity has become increasingly important for
network service survivability since today's single fiber system may
carry several gigabits of data per second.",
}

@ARTICLE{Star9106:OAM,
AUTHOR="T. Starr",
TITLE="{OAM\&P} for {ISDN} Basic Access {DSL} Based on {ANSI} Physical
Layer Standards",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=6,
PAGES="59-63",
MONTH="Jun",
YEAR=1991,
KEYWORDS="OAM\&P; ISDN Basic Access; DSL Based; ANSI Physical Layer
Standards",
ABSTRACT="The specification of a digital subscriber Line (DSL) for
Integrated Services Digital Network (ISDN) basic access is more than an
exercise in digital transmission design. Operations Administration
Maintenance and Provisioning (OAM\&P) characteristics must also be
considered so that the digital transmission system may be easily
installed, used, and repaired.",
}

@ARTICLE{Fan9107:Development,
AUTHOR="Changxin Fan",
TITLE="Development of Telecommunications Undertakings in China",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=7,
PAGES="16-17",
MONTH="Jul",
YEAR=1991,
KEYWORDS="Telecommunications; China",
ABSTRACT="Telecommunications Plays a very important role in today's
information society. It is closely linked to the economic development
and social progress of a country. In China, there has been a growing
demand for information exchange in all aspects of life, especially in
major and coastal cities, and special economics zones. The Chinese
government pays attention to telecommunications as a strategic policy.
It is one of the top priority sectors, equal to energy and
transportation. In this article, the history, current status, and future
plans of telecommunications undertakings in China are presented.",
}

@ARTICLE{Pach9107:Latin,
AUTHOR="Mario Pachajoa-Burbano",
TITLE="Latin American Telecommunications Networks",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=7,
PAGES="18-22",
MONTH="Jul",
YEAR=1991,
KEYWORDS="Latin American; Telecommunications Networks",
ABSTRACT="This article describes Telecommunications systems in Latin
America with specific details of networks in Colombia, Uruguay, and
Costa Rica. The points of view and comments in this article are the sole
responsibility of the author and not necessarily the views of the
Organization of American States (OAS), the Inter-American
Telecommunications Conference (CITEL), Administrations, or their
representatives.",
}

@ARTICLE{Vara9107:Prospects,
AUTHOR="L. E. Varakin and A. S. Adjemov and L. I. Golyayeva and A. F.
Petrov and V. M. Tjomkin",
TITLE="Analysis of Prospects of Fiber Optic Long-Distance Telephone
Network Architecture",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=7,
PAGES="23-25",
MONTH="Jul",
YEAR=1991,
KEYWORDS="Fiber Optic; Long-Distance Telephone Network Architecture",
ABSTRACT="Throughout the last decade, world practice was characterized
by the wide scale introduction of optical transmission facilities,
remarkable for its technical and economic performance. However, the
efficiency of optical applications, to a great extent, is defined by the
volume of information exchange. The first area of mass application of
optical transmission systems, of course, was broadband high-speed
services and international telephone communication networks
characterized by a high concentration of telephone traffic. The latter
field of optics application is the most vital for the U.S.S.R., since a
drastic increase in long-distance traffic is anticipated, driven by the
significant growth of telephone density in the country.",
}

@ARTICLE{Adje9107:Architecture,
AUTHOR="A. S. Adjemov and E. A. Zarkevitch and V. I. Smirnov",
TITLE="Architecture and Development of Telecommunications Networks",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=7,
PAGES="26-28",
MONTH="Jul",
YEAR=1991,
KEYWORDS="Telecommunications Networks",
ABSTRACT="Today, fiber optic facilities are broadly used for
communications network development. When talking about the use of fiber
optic facilities, one should mention some key points.",
}

@ARTICLE{Modi9107:Common,
AUTHOR="Nasser Modiri",
TITLE="An Implementation of the Common Network Management Information
Service Element Interfaces",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=7,
PAGES="29-39",
MONTH="Jul",
YEAR=1991,
KEYWORDS="Common Network Management; Information Service; Element
Interfaces",
ABSTRACT="As networks expand in size, it becomes increasingly difficult
for a network manager to determine the status of the various nodes
attached to the network. When a fault develops in the communications
subsystem of a node it is necessary, first, to be able to identify the
system in error and, second, determine the fault within its
communications subsystem.",
}

@ARTICLE{Habe9108:HDTV,
AUTHOR="Werner Habermann",
TITLE="{HDTV} Standards",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=8,
PAGES="10-14",
MONTH="Aug",
YEAR=1991,
KEYWORDS="HDTV Standards; CCIR",
ABSTRACT="Speaking of high definition television (HDTV) standardization
means consideration of relevant International Radio Consultative
Committee (CCIR) activities. All efforts taken hitherto in establishing
a package of parameters configuring what will finally be called an HDTV
standard were channeled towards CCIR Study Groups.",
}

@ARTICLE{Hass9108:FCC,
AUTHOR="William H. Hassinger",
TITLE="{FCC} policy on {HDTV}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=8,
PAGES="23-24",
MONTH="Aug",
YEAR=1991,
KEYWORDS="FCC policy; HDTV",
ABSTRACT="In 1941, THE Federal Communications Commission (FCC) made the
first spectrum allocation and adopted the first technical standard for
the transmission of black and white television in the U.S. Forty-six
years later, in response to a joint petition filed by the Association of
Maximum Service Telecasters, Inc. and 57 other broadcast organizations
and companies, the Commission began a formal proceeding to replace that
standard. On July 16, 1987, the Commission adopted a Notice of Inquiry
in the matter of Advanced Television (ATV) Systems and their impact on
the existing television broadcast service.",
}

@ARTICLE{Bedf9108:Industrial,
AUTHOR="Ronald A. Bedford",
TITLE="Industrial Application of {HDTV}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=8,
PAGES="25-27",
MONTH="Aug",
YEAR=1991,
KEYWORDS="Hdtv",
ABSTRACT="The development of high definition Television (HDTV) for
broadcasting purposes has, to some extent, overshadowed the applications
of the technology for other purposes in commerce and industry. It is in
fact in the nonbroadcasting application area that the most use has been
made of HDTV to date. The High Resolution Imagery (HRI) possible using
HDTV technology opens the door to users ranging from education to
industry. Table I illustrates some of the applications that are in use
today or being developed for use in the near future.",
}

@ARTICLE{Conn9108:High,
AUTHOR="William Connolly",
TITLE="High Definition Television Studio Equipment",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=8,
PAGES="42-45",
MONTH="Aug",
YEAR=1991,
KEYWORDS="High Definition Television; Studio Equipment",
ABSTRACT="High definition television (HDTV) emerged from the desire for
an electronic imaging system that could deliver a more exciting viewing
experience than current TV technology offers. In time, this desire
evolved into a real goal for the Research and Development (R\&D) arms of
the international television production community. Their quest: to
create a completely new television standard for studio origination and
international program exchange that could compare to the quality and
viewing experience of projected 35 mm film.",
}

@ARTICLE{Walt9109:New,
AUTHOR="S. M. Walters",
TITLE="A New Direction for Broadband {ISDN}",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=9,
PAGES="39-43",
MONTH="Sep",
YEAR=1991,
KEYWORDS="Broadband ISDN",
ABSTRACT="Current vision of a multifeatured network rolling out in 1994
may be overly ambitious and still not meet end-user needs.",
}

@ARTICLE{Burg9109:Resource,
AUTHOR="J. L. Burgin and D. M. Dorman",
TITLE="{B-ISDN} Resource Management: The Role of Virtual Paths",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=9,
PAGES="44-49",
MONTH="Sep",
YEAR=1991,
KEYWORDS="B-ISDN; Resource Management; Virtual Paths",
ABSTRACT="Controlling access to network resources is the key to
achieving the desired grade and quality of services. Virtual paths will
be key in the cost effective management of these resources.",
}

@ARTICLE{Breu9109:ATM,
AUTHOR="Han-Jurgen Breuer",
TITLE="{ATM-Layer} {OAM:} Principles and Open Issues",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=9,
PAGES="75-78",
MONTH="Sep",
YEAR=1991,
KEYWORDS="ATM-Layer; OAM; operation and maintenance",
ABSTRACT="Developers of operation and maintenance (OAM) principles for
Broadband ISDN can draw some inspiration from Basic and Primary Rate
ISDN, but B-ISDN is dramatically different from its narrow-band cousins
and requires many entirely new solutions.",
}

@ARTICLE{Ande9109:ATM,
AUTHOR="J. P. Anderson and Matt D. Nguyen",
TITLE="{ATM-Layer} {OAM} Implementation Issues",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=9,
PAGES="79-81",
MONTH="Sep",
YEAR=1991,
KEYWORDS="ATM-Layer; OAM; operations and maintenance",
ABSTRACT="As work on the architectural aspects of operations and
maintenance (OAM) has matured, the CCITT is turning its attention to OAM
functionality in B-ISDN's ATM layer.",
}

@ARTICLE{Wolf9110:How,
AUTHOR="Stephen. Wolf and C. A. Dvorak and R. F. Kubichek and C. R.
South and Richard. Schaphorst and Stephen Voran",
TITLE="How Will We Rate Telecommunications System Pencormance?",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=10,
PAGES="23-30",
MONTH="Oct",
YEAR=1991,
KEYWORDS="Telecommunications System",
ABSTRACT="In Standards Topics the authors present their collective
vision of future work in relating objective and subjective
telecommunications system performance measures.",
}

@ARTICLE{Lee9111:Smaller,
AUTHOR="Duan-Shin. Lee",
TITLE="Smaller Cells for Greater Performance",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="19-23",
MONTH="Nov",
YEAR=1991,
KEYWORDS="Cells; PCS systems; microcell architecture",
ABSTRACT="A new microcell architecture that reduces inter- ference,
increases system capacity, improves voice quality, and demands fewer
handoffs is ideally suited for PCS systems",
}

@ARTICLE{Lodg9111:Mobile,
AUTHOR="John Lodge",
TITLE="Mobile Satellite Communications Systems: Toward Global Personal
Communications",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="24-31",
MONTH="Nov",
YEAR=1991,
KEYWORDS="Mobile Satellite Communications; Global Personal
Communications",
ABSTRACT="A rich assortment of systems and services will soon be placed
before us, but the evolution of a truly integrated approach will take
decades",
}

@ARTICLE{Wood9111:Mobile,
AUTHOR="Peter Wood",
TITLE="Mobile Satellite Services for Travelers",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="32-35",
MONTH="Nov",
YEAR=1991,
KEYWORDS="Mobile Satellite Services; Travelers",
ABSTRACT="By the end of the century, Inmarsat will offer services
ranging from worldwide pocket telephone to very-low-cost data
communications.",
}

@ARTICLE{Hart9111:Mobile,
AUTHOR="Nick Hart and Paul Robertson and Paul Bartels",
TITLE="Mobile Services in Australia",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="36-41",
MONTH="Nov",
YEAR=1991,
KEYWORDS="Mobile Services; Australia",
ABSTRACT="AUSSAT's mobilesat will use ISDN-like features to bring
advanced mobile voice and data services to travelers in Australia's
Outback",
}

@ARTICLE{Grub9111:Traveler,
AUTHOR="Jerry L. Grubb",
TITLE="The Traveler's Dream Come True",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="48-51",
MONTH="Nov",
YEAR=1991,
KEYWORDS="personal communications system; satellite",
ABSTRACT="The Iridium sm satellite-based personal communications system
will bring cellular telephone service to virtually every point on the
globe.",
}

@ARTICLE{Rapp9111:Wireless,
AUTHOR="Theodore Rappaport",
TITLE="The Wireless Revolution",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="52-71",
MONTH="Nov",
YEAR=1991,
KEYWORDS="global wireless communication",
ABSTRACT="Rapid multinational progress will soon make global wireless
communication a ubiquitous reality.",
}

@ARTICLE{Fili9111:Telecommunications,
AUTHOR="J. Filipiak and Krzysztof Wajda",
TITLE="Telecommunications in Poland",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=11,
PAGES="94-99",
MONTH="Nov",
YEAR=1991,
KEYWORDS="Telecommunications; Poland",
ABSTRACT="Making telecommunications efficient is a requirement for the
country's economic development and a hallmark of its progress.",
}

@ARTICLE{Forn9112:Combined,
AUTHOR="G. D. Forney",
TITLE="Combined Equalization and Coding Using Preceding",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=12,
PAGES="25-35",
MONTH="Dec",
YEAR=1991,
KEYWORDS="Combined Equalization; Precoding",
ABSTRACT="Techniques for approaching the capacity of high-SNR
bandlimited channels have been developed only in the past decade.
Precoding is an effective equalization method for such channels, and is
now in use in telephone-line modems.",
}

@ARTICLE{Ande9112:Modulation,
AUTHOR="John Anderson and C.-E. W. Sundberg",
TITLE="Modulation",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=12,
PAGES="36-45",
MONTH="Dec",
YEAR=1991,
KEYWORDS="Modulation; Bandwidth-efficient coding",
ABSTRACT="Communications traffic continually rises, but the width of the
electromagnetic spectrum is fixed. Bandwidth-efficient coding with a
constant radio-frequency envelope helps.",
}

@ARTICLE{Sasa9112:Multi,
AUTHOR="I. Sasase and S. Mori",
TITLE="Multi-h Phase-Coded Modulation",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=12,
PAGES="46-57",
MONTH="Dec",
YEAR=1991,
KEYWORDS="Multi-h Phase-Coded Modulation",
ABSTRACT="A special class of continuous phase modulation offers power
and bandwidth efficiency where time-varying modulation indices are
used.",
}

@ARTICLE{Cald9112:Spectral,
AUTHOR="A. R. Calderbank and J. E. Mazo",
TITLE="Spectral Nulls and Coding with Large Alphabets",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=12,
PAGES="58-67",
MONTH="Dec",
YEAR=1991,
KEYWORDS="Spectral Nulls; Coding",
ABSTRACT="Generalizing the simple alternate-mark-inversion line code
provides enhanced immunity to additive noise, as well as spectral
shaping.",
}

@ARTICLE{Sieg9112:Modulation,
AUTHOR="Paul H. Siegel and J. Wolf",
TITLE="Modulation and Coding for Information Storage",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=12,
PAGES="68-87",
MONTH="Dec",
YEAR=1991,
KEYWORDS="Modulation; coding; information storage",
ABSTRACT="The success of certain modulation and coding techniques in
data communications have inspired promising new applications in digital
data storage.",
}

@ARTICLE{Kato9112:Coded,
AUTHOR="S. Kato and M. Morikura and Shuji Kubota",
TITLE="Implementation of Coded Modems",
JOURNAL=ieeecm,
VOLUME=29,
NUMBER=12,
PAGES="88-97",
MONTH="Dec",
YEAR=1991,
KEYWORDS="Coded Modems; DSP; LSIC; Trellis-coded",
ABSTRACT="Trellis-coded modems use DSP and LSIC technologies to deliver
robust operation and high reliability from miniature hardware.",
}

@INPROCEEDINGS{Chen91:Mirrored,
AUTHOR="S. Chen and Donald F. Towsley",
TITLE="Performance of a Mirrored Disk in a Real-Time Transaction
System",
BOOKTITLE=sigmetrics,
PAGES="198-207",
YEAR=1991,
}

@ARTICLE{Li91:General,
AUTHOR="Song Li",
TITLE="A General Solution Technique for Discrete Queueing Analysis of
Multi-Media Traffic on {ATM}",
JOURNAL=ieeecom,
VOLUME=4,
YEAR=1991,
ABSTRACT="This paper presents a general solution technique for discrete
queueing analysis of multi-media traffic on ATM in multiple dimensions,
using generating function approach.  The queue has multiple
deterministic servers with infinite buffer size.  Each server represents
a time slot on an ATM link for the transmission of one cell.  The
arrival process is modeled by a number of independent Markov chains and
each characterizes the stochastic properties of different traffic type.
By decomposing the generating function of the queue we separate the
evaluation of the characteristic roots.  Further, to characterize the
great diversity of time scales of variation in multi-media traffic, we
decompose the overall traffic arrivals into multiple independent types.
Each type is constructed by a number of $i.i.d.$ two-state Markov chains
and represents a different time scale of variation.  Simple Kronecker
product properties are then used to separate the evaluation of each
individual root, so that the complexity involved to solve such a root is
basically independent of the system size.  As the system size becomes
large, the main computational limit in this method is the memory size
required to solve linear equations for the boundary terms.  Complete
solutions for the first two moments of the queue are therefore
constructed.  In numerical examples, we calculate the mean and the
variance of the queue for a four-dimensional Markov queueing process.  A
new concept of time scale decomposition is also introduced to simplify
the numerical analysis of large systems.  The new insight relation
between the generating function approach and the queueing analysis of
multi-media traffic, exposed by this paper, is a fruitful starting point
for further research.",
URL="http://www.ece.utexas.edu/~sanqi/papers.html",
}

@INCOLLECTION{LaMa91:Computation,
AUTHOR="and A. M. Odlyzko",
TITLE="Computation of Discrete Logarithms in Prime Fields",
BOOKTITLE="Lecture Notes in Computer Science",
PUBLISHER="Springer Verlag",
VOLUME=537,
PAGES="616-618",
YEAR=1991,
REFERENCES=40,
ABSTRACT="The presumed difficulty of computing discrete logarithms in
finite fields is the basis of several popular public key cryptosystems.
The secure identification option of the Sun Network File System, for
example, uses discrete logarithms in a field GF (p) with p a prime of
192 bits.  This paper describes an implementation of a discrete
logarithm algorithm which shows that primes of under 200 bits, such as
that in the Sun system, are very insecure.  Some enhancements to this
system are suggested.",
URL="http://citeseer.nj.nec.com/lamacchia91computation.html",
}

@ARTICLE{Nish91:WD,
AUTHOR="Makoto Nishio and Shuji Suzuki",
TITLE="{WD\&MMT} Switching Networks in Combination with Photonic and
Electronic Switching Technique",
JOURNAL=icc,
PAGES="590-596",
YEAR=1991,
REFERENCES=9,
KEYWORDS="Hybrid switching; optical switching; switching; wdm",
ABSTRACT="New photonic and electronic hybrid switching networks, WD\&MMT
switching networks, which are constructed in combination with photonic
wavelength-division switching and electronic memory matrix time
switching technique, are proposed. The WD\&MMT switching networks can be
used to construct large line-capacity switching networks with a small
amount of the hardware, because of their very large total multiplexity
given by the product of wavelength-div",
}

@BOOK{Mann91:Temporal,
AUTHOR="Zohar Manna and Amir Pnueli",
TITLE="The Temporal Logic of Reactive and Concurrent Systems:
Specification",
PUBLISHER="Springer-Verlag",
ADDRESS="New York",
YEAR=1991,
LANGUAGE="English",
}

@MISC{Sjo:thes,
AUTHOR={P.Sj{\"o}di},
TITLE="From {LOTOS} Specifications to Distributed Implementations",
HOWPUBLISHED="PhD thesis",
ADDRESS="Department of Computer Systems, Uppsala University, Uppsala,
Sweden",
YEAR=1991,
}

@INPROCEEDINGS{Hager:multicon,
AUTHOR="Erik Hagersten and Anders Landin and Seif Haridi",
TITLE="Multiprocessor Consistency and Synchronization thru Transient
Cache States",
BOOKTITLE="Workshop on Scalable Shared-Memory Architectures",
YEAR=1991,
}

@INPROCEEDINGS{Land:race,
AUTHOR="Anders Landin and Erik Hagersten and Seif Haridi",
TITLE="Race-Free Interconnection Networks and Multiprocessor
Consistency",
YEAR=1991,
ABSTRACT="Modern shared-memory multiprocessors require complex
interconnection networks to provide sufficient communication bandwidth
between processors. They also rely on advanced memory systems that allow
multiple memory operations to be made in parallel. It is expensive to
maintain a high consistency level in a machine based on a general
network, but for special interconnection topologies, some of these costs
can be reduced. We define and study one class of interconnection
networks, {\it race-free networks}. New conditions for sequential
consistency are presented which show that sequential consistency can be
maintained if all accesses in a multiprocessor can be ordered in an
acyclic graph. We show that this can be done in race-free networks
without the need for a transaction to be globally performed before the
next transaction can be issued. We also investigate what is required to
maintain processor consistency in race-free networks. In a race-free
network which maintains processor consistency, writes may be pipelined,
and reads may bypass writes. The proposed methods reduce the latencies
associated with processor write-misses to shared data",
URL="http://www.sics.se/~landin/RFN.ps.Z",
}

@INPROCEEDINGS{Awer91:Concurrent,
AUTHOR="Baruch Awerbuch and David Peleg",
TITLE="Concurrent Online Tracking of Mobile Users",
BOOKTITLE="Conference on Communications Architecture and Protocols",
ADDRESS="Zürich, Switzerland",
PAGES="221-233",
YEAR=1991,
}

@MISC{Prot9101:XTP,
AUTHOR="Protocol Engines Incorporated",
TITLE="{XTP} Protocol Definition Revision 3.5 (Addendum 1a)",
NUMBER="PEI 91-2",
MONTH=jan,
YEAR=1991,
KEYWORDS="transport protocol; XTP",
}

@ARTICLE{Cruz9101:Calculus1,
AUTHOR="Rene L. Cruz",
TITLE="A Calculus for Network Delay, Part {I:} Network Elements in
Isolation",
JOURNAL=ieeeit,
VOLUME=37,
NUMBER=1,
PAGES="114-131",
MONTH=jan,
YEAR=1991,
KEYWORDS="queueing theory; queueing networks; flow control; high speed
networks; packet switching",
ABSTRACT="A calculus is derived in this paper (Part I) and the sequel
(Part II) for obtaining bounds on delay and buffering requirements in a
communication network operating in a packet switched mode under a fixed
routing strategy. The theory we develop is different from traditional
approaches to analyzing delay because the model the paper uses to
describe the entry of data into the network is nonprobabilistic: The
paper supposes that the data stream entered into the network by any
given user satisfies ``burstiness constraints.'' A data stream is said
to satisfy a burstiness constraint if the quantity of data from the
stream contained in any interval of time is less than a value that
depends on the length of interval. Several network elements are defined
that can be used as building blocks to model a wide variety of
communication networks. Each type of network element is analyzed by
assuming that the traffic entering it satisfies burstiness constraints.
Under this assumption bounds are obtained on delay and buffering
requirements for the network element, burstiness constraints satisfied
by the traffic that exits the element are derived.",
}

@ARTICLE{Cruz9101:Calculus2,
AUTHOR="Rene L. Cruz",
TITLE="A Calculus for Network Delay, Part {II:} Network Analysis",
JOURNAL=ieeeit,
VOLUME=37,
NUMBER=1,
PAGES="132-141",
MONTH=jan,
YEAR=1991,
KEYWORDS="queueing theory; queueing networks; flow control; high speed
networks; packet switching",
ABSTRACT="In part I of this paper, several network elements were defined
that can be used to model a wide variety of communication networks. A
method to analyze the flow of data in a network consisting of the
interconnection of these network elements is now presented. Assuming
that the data that enters the network satisfies burstiness constraints,
burstiness constraints are derived for traffic flowing between network
elements. These derived constraints imply bounds on network delay and
buffering requirements. By example, it is shown that the use of
regulator elements (defined in Part I) within the network can reduce
maximum network delay. It is also found that such a use of regulator
elements can enlarge the throughput region where finite bounds for delay
are found. Finally, it is shown how regulator elements connected in
series can be used to enforce general burstiness constraints.",
}

@ARTICLE{DeSi9101:Generating,
AUTHOR="A. DeSimone",
TITLE="Generating Burstiness in Networks: A Simulation Study of
Correlation Effects in Networks of Queues",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="24-31",
MONTH=jan,
YEAR=1991,
REFERENCES=13,
KEYWORDS="queueing theory",
ANNOTE="compares coefficient of variation ($c$) of interdeparture
process to that of arrival process for single stream traversing access,
backbone and egress link. The stream of interest contributes one tenth
of the backbone utilization. Round-robin service among connections
limits burstiness. ``At moderate and higher utilizations, the
variability in packet interarrival times on egress from a network
attains a value determined by the network configuration and packet size
distribution rather than by the packet interarrival times on access.
Traffic smoothing at the network edge can have only a limited role in
protecting the network from congestion.''",
URL="ftp://gatekeeper.dec.com/.b/doc/sigcomm/ccr/archive/1991/jan91/desimone.ps.Z",
}

@ARTICLE{Wang9101:New,
AUTHOR="Zhen Wang and Jon Crowcroft",
TITLE="A New Congestion Control Scheme: Slow Start and Search (Tri-S)",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="32-43",
MONTH=jan,
YEAR=1991,
REFERENCES=9,
ABSTRACT="Recently, there have been many measures proposed to tackle the
problem of congestion in computer networks. In this paper, the authors
first analyze some of the measures and then present a new scheme in
which the optimal operating point is obtained by evaluation of
throughput gradient and resource sharing is adjusted only at the
beginning and end of a connection. Simulation results show that the
scheme converges to an optimal operating point quickly and fairly.",
ANNOTE="Congestion control.",
}

@INPROCEEDINGS{Scho9101:Multimedia,
AUTHOR="Eve Schooler and Stephen Casner and J. B. Postel",
TITLE="Multimedia Conferencing: Has it come of age?",
BOOKTITLE="24th Hawaii International Conference on System Science",
ORGANIZATION="IEEE",
ADDRESS="Hawaii",
VOLUME=3,
PAGES="707-716",
MONTH=jan,
YEAR=1991,
KEYWORDS="multimedia; cooperative work",
ABSTRACT="Summarizes notable cooperative work and multimedia
conferencing systems as well as the common issues they address.
Differentiates synchronous vs. asynchronous (mail), local (face-to-face)
vs. remote, inter-office vs. meeting room, centralized vs. replicated,
simultaneous vs. one-person-at-a-time access, explicit vs. implicit
floor change, LAN vs. WAN, digital vs. analog media.",
ANNOTE="Also: ISI/RS-91-286. ``Delay is generally undetectable when
under 20 ms, can cause trouble when significant echo is present if
between 40--80 ms, and begins to effect normal conversation when greater
than the hundred millisecond range.''",
URL="ftp://ftp.isi.edu/pub/hpcc-papers/mmc/hicss.ps",
}

@ARTICLE{Hutc9101:X,
AUTHOR="N. Hutchinson and L. L. Peterson",
TITLE="The x-Kernel: An Architecture for Implementing Network
Protocols",
JOURNAL=ieeese,
VOLUME=17,
NUMBER=1,
PAGES="64-76",
MONTH=jan,
YEAR=1991,
KEYWORDS="protocol; operating system; protocol implementation",
ABSTRACT="This paper describes a new operating system kernel, called the
x-kernel, that provides explicit architecture for constructing and
composing network protocols. Our experience implementing and evaluating
several protocols in the x-kernel shows that this architecture is both
general enough to accommodate a wide range of protocols, yet efficient
enough to perform competitively with less structured operating
systems.",
URL="ftp://cs.arizona.edu/architecture.ps",
}

@INPROCEEDINGS{Leon9101:UNIX,
AUTHOR="Philip Leong and Chen Khong Tham",
TITLE="{UNIX} password encryption considered insecure",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH=jan,
YEAR=1991,
LANGUAGE="English",
KEYWORDS="encryption; password; DES; Unix",
ABSTRACT="Recently there has been a revival of interest in the security
of the password encryption scheme employed in the Unix operating system
and its derivatives. This resurgence was due mainly to the success of an
attack on the Internet by a virus program in November 1988. The current
encryption scheme used is a variant of the NBS Data Encryption Standard
(DES) modified in such a way that existing DES hardware implementations
cannot be used. There is currently no reported way of reversing the
password encryption, i.e., to obtain a password from its encrypted
string. In this paper, we show that the current encryption scheme can no
longer be considered secure as most UNIX passwords can be decrypted
using a brute force search within a reasonable amount of time. As an
example, all passwords containing only lower-case alphabetic characters
can be decrypted in less than 15 days. In order to perform a brute force
search, we need the ability to encrypt a Unix password in the shortest
time possible. Accordingly, we present a hardware design of a password
encryption device that can encrypt a Unix password in 6 $\\mu$s. This
device consists of approximately 100 emitter coupled logic (ECL) chips
and can be built by any electronic hobbyist for less than \\$2000. The
board can also be used to encrypt DES at 266 Mbps, more than ten times
faster than a recent CMOS VLSI design. We also present a software only
implementation of the encryption algorithm recoded for maximum speed.
This implementation can encrypt a Unix password in 1.2 ms on an IBM
RS/6000 Model 530 machine.",
}

@MISC{Camp9101:CELP,
AUTHOR="Andrew T Campbell and Thomas E. Tremain and Vanoy C. Welch",
TITLE="{CELP} documentation version 3.2",
MONTH=jan,
YEAR=1991,
KEYWORDS="voice coding; CELP",
}

@ARTICLE{Abra9101:Multicomputer,
AUTHOR="Santosh Abraham",
TITLE="Performance of Multicomputer Networks under Pin-out Constraints",
JOURNAL=jpdc,
VOLUME=12,
PAGES="237-248",
MONTH=jan,
YEAR=1991,
}

@TECHREPORT{Lowe9101:Protocols,
AUTHOR="Carlyn M. Lowery",
TITLE="Protocols for Providing Performance Guarantees in a
Packet-Switching {Internet}",
TYPE="Technical Report",
INSTITUTION="Computer Science Division, University of California",
ADDRESS="Berkeley, California",
NUMBER="TR-91-002",
MONTH=jan,
YEAR=1991,
KEYWORDS="real-time services; XUNET; RCAP; RTIP; real-time protocols;
connection establishment; ST-II",
ABSTRACT="As advances in technology enable us to implement very high
speed computer networks, we expect to use our networks for more diverse
applications. While the Internet was designed with textual data
processing in mind, future networks will carry information such as
voice, music, images, and video, along with textual data. Many new
applications will have real-time performance requirements, where the
timing of data arrival is crucial to its usefulness. This paper
describes a methodology developed at the University of California at
Berkeley to support such applications, reviews related research work,
and proposes a real-time delivery system, composed of a new protocol for
administration of real-time connections, combined with modifications to
the Internet Protocol (IP) to support such connections. Transport
protocol requirements are also discussed. This work is intended to
facilitate experiments with real-time communication over the
Experimental University Network (XUNET).",
ANNOTE="RTIP packets are nearly identical to standard IP packets, with
the addition of jitter control factor and local channel id options.
Critique of ST-II.",
}

@ARTICLE{Zitt9101:High,
AUTHOR="M. Zitterbart",
TITLE="High-speed transport components",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=1,
PAGES="54-63",
MONTH=jan,
YEAR=1991,
REFERENCES=29,
KEYWORDS="transport protocols; high-speed networks; XTP; VMTP; NETBLT;
transputer; protocol implementations",
ANNOTE="Describes transputer-based implementation of CLNP on an
eight-node system, observing a speed-up of four. With eight T414
transputers, about 2000 packets per second could be processed.",
}

@ARTICLE{Haas9101:Protocol,
AUTHOR="Z. Haas",
TITLE="A protocol structure for high-speed communication over broadband
{ISDN}",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=1,
PAGES="64-70",
MONTH=jan,
YEAR=1991,
REFERENCES=12,
KEYWORDS="high-speed protocols; layering; protocol implementation",
ANNOTE="Layering as an implementation tool reduces performance by
duplicating functions, performing unnecessary functions, overhead of
control messages and inability to parallelize protocol processing. The
author proposes a horizontally oriented protocol structure (HOPS) that
divides a protocol into functions instead of layers.",
}

@INPROCEEDINGS{Mack9101:Lessons,
AUTHOR="Rick Macklem",
TITLE="Lessons Learned Tuning the {4.3BSD} Reno Implementation of the
{NFS} Protocol",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH=jan,
YEAR=1991,
KEYWORDS="Distributed File Systems",
}

@INPROCEEDINGS{Sklo9101:Tree,
AUTHOR="Keith Sklower",
TITLE="A Tree-Based Packet Routing Table for Berkeley {UNIX}",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH=jan,
YEAR=1991,
KEYWORDS="Operating Systems",
}

@INPROCEEDINGS{Fost9101:Evolutionary,
AUTHOR="Antony W. Foster and Robert K. Israel and A. Taylor and Tracy M.
Taylor and Neil Webber",
TITLE="Evolutionary Path to Network Storage Management",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH=jan,
YEAR=1991,
KEYWORDS="Distributed File Systems",
}

@INPROCEEDINGS{Bhid9101:Highly,
AUTHOR="Anupan Bhide and Samuel P. Morgan",
TITLE="A Highly Available Network File Server",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH=jan,
YEAR=1991,
KEYWORDS="Distributed File Systems",
}

@INPROCEEDINGS{Bish9101:Authentication,
AUTHOR="M. Bishop",
TITLE="An Authentication Mechanism for {USENET}",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH=jan,
YEAR=1991,
KEYWORDS="Security",
}

@INPROCEEDINGS{Free9101:Experience,
AUTHOR="Dan Freedman",
TITLE="Experience Building a Process Migration Subsystem for {UNIX}",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH=jan,
YEAR=1991,
KEYWORDS="Distributed Systems",
}

@INPROCEEDINGS{Youn9101:Modular,
AUTHOR="M. Young and D. H. Thompson and Elliot Jaffe",
TITLE="A Modular Architecture for Distributed Transaction Processing",
BOOKTITLE=usenixw,
ADDRESS="Dallas, Texas",
MONTH=jan,
YEAR=1991,
KEYWORDS="Distributed Systems",
}

@ARTICLE{Chen9101:Multistage,
AUTHOR="Xiaopeng Chen",
TITLE="A Survey of Multistage Interconnection Networks in Fast Packet
Switching",
JOURNAL="International Journal of Digital and Analog Communication
Systems",
VOLUME=4,
NUMBER=1,
PAGES="33-59",
MONTH=jan,
YEAR=1991,
REFERENCES=61,
KEYWORDS="ATM; switching system; multistage interconnection network;
Banyan network; blocking; nonblocking; Batcher-Banyan; self routing;
CLOS",
}

@ARTICLE{ONei9101:Method,
AUTHOR="C. O'Neill",
TITLE="A Method for Congestion Control in {ATM} Networks using Peak Rate
Throttling",
JOURNAL="International Journal of Digital and Analog Communication
Systems",
VOLUME=4,
NUMBER=1,
PAGES="1-10",
MONTH=jan,
YEAR=1991,
REFERENCES=16,
KEYWORDS="ATM; congestion control",
}

@ARTICLE{Heid9101:Traffic,
AUTHOR="P. Heidelberger and P. A. Franaszek",
TITLE="Traffic Studies of Unbuffered Delta Networks",
JOURNAL=ibmjrd,
VOLUME=35,
NUMBER=1,
PAGES="288-299",
MONTH=jan,
YEAR=1991,
REFERENCES=37,
KEYWORDS="Delta network; Banyan network; performance evaluation;
analysis; asymmetric load; unbalanced traffic; multistage
interconnection network; packet switching; circuit switching",
}

@ARTICLE{Chen9101:Study,
AUTHOR="Jinghu Chen and R. Guérin",
TITLE="Performance Study of an Input Queueing Packet Switch with Two
Priority Classes",
JOURNAL=ieeecom,
VOLUME="COM-39",
NUMBER=1,
PAGES="117-126",
MONTH=jan,
YEAR=1991,
KEYWORDS="Multiclass queue; priority; approximation; distribution
function",
ANNOTE="This paper studies an NxN nonblocking packet switch with input
queues and two priority classes which can be used to support traffic
with different requirements. The switch operation is slotted and, at
each time slot, fixed size packets arrive at theinputs with distinct
Bernoulli distributions for both the high and low priority classes. Two
policies are studied. In the firstpolicy, packets of both priority
classes are queued when waiting",
}

@ARTICLE{Iori9101:Integrating,
AUTHOR="Nicola Di Iorio",
TITLE="Integrating {ISDN} and {OSI:} An example",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=1,
PAGES="10-24",
MONTH=jan,
YEAR=1991,
REFERENCES=22,
KEYWORDS="ISDN; OSI",
}

@ARTICLE{Mitr9101:Relationship,
AUTHOR="N. Mitra and S. D. Usiskin",
TITLE="Relationship of the signaling system No. 7 protocol architecture
to the {OSI} reference model",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=1,
PAGES="26-37",
MONTH=jan,
YEAR=1991,
REFERENCES=18,
KEYWORDS="Signalling; common channel; CCS; OSI",
}

@ARTICLE{Anon9101:Future,
AUTHOR="Anonymous",
TITLE="The Future of {OSI} and {ISDN}",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=1,
MONTH=jan,
YEAR=1991,
KEYWORDS="ISDN; OSI",
}

@ARTICLE{Dert9101:Building,
AUTHOR="M. L. Dertouzos",
TITLE="Building the Information Marketplace",
JOURNAL="Technology Review",
PAGES="29-40",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Estr9101:Inter,
AUTHOR="D. Estrin and M. Steenstrup",
TITLE="Inter Domain Policy Routing: Overview of Architecture and
Protocols",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="71-78",
MONTH=jan,
YEAR=1991,
REFERENCES=18,
}

@ARTICLE{Lync9101:Z39,
AUTHOR="C. A. Lynch",
TITLE="The {Z39.50} Information Retrieval Protocol: An Overview and
Status Report",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="58-70",
MONTH=jan,
YEAR=1991,
REFERENCES=16,
}

@ARTICLE{McCr9101:Strategy,
AUTHOR="J. M. McCaig",
TITLE="A Strategy for Synchronising Simplex Message Streams",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="79-98",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Bovo9101:Optimal,
AUTHOR="Andreas Bovopoulos and Aurel A. Lazar",
TITLE="Optimal Resource Allocation for Markovian Queueing Networks: The
Complete Observation Case",
JOURNAL="Stochastic Models",
VOLUME=7,
NUMBER=1,
PAGES="161-184",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Laza9101:Markovian,
AUTHOR="Aurel A. Lazar and T. G. Robertazzi",
TITLE="Markovian Petri Net Protocols with Product Form Solution",
JOURNAL=pe,
VOLUME=12,
NUMBER=1,
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Wake9101:Layering,
AUTHOR="Ian Wakeman and Jon Crowcroft and Zhen Wang and D. Sirovica",
TITLE="Layering considered harmful",
JOURNAL=ieeenet,
MONTH=jan,
YEAR=1991,
ABSTRACT="During an investigation into the performance of Remote
Procedure Call mechanisms over TCP, anomalous behaviour was observed for
certain sizes of the parameters being passed. Investigation of this
phenomenon revealed the problem to be rooted in a mismatched interface
between the socket and the TCP modules, where behaviour analagous to the
Silly Window Syndrome was seen. From this we draw lessons to be used in
designing and building communications software, based on Integrated
Layer Processing.",
URL="/cs/research/darpa/ron/iwakeman/docs/DARPA/rpcperf/rpcperf.ps",
}

@TECHREPORT{Mill9101:Input,
AUTHOR="Ethan L. Miller",
TITLE="Input/Output Behavior of Supercomputing Applications",
INSTITUTION="University of California, Berkeley",
NUMBER="UCB/CSD 91/616",
NOTE="Appeared in Supercomputing",
MONTH=jan,
YEAR=1991,
URL="ftp://ftp.cs.berkeley.edu/ucb/raid/papers/tech91\_616.ps.Z",
}

@ARTICLE{Marz9101:Making,
AUTHOR="K. Marzullo and Mark D. Wood",
TITLE="Making real-time reactive systems reliable",
JOURNAL=acmosrev,
VOLUME=25,
NUMBER=1,
PAGES="45-48",
NOTE="4th ACM SIGOPS European Workshop",
MONTH=jan,
YEAR=1991,
REFERENCES=8,
KEYWORDS="reliability; fault-tolerance; reactive systems",
}

@ARTICLE{Hald9101:Fairness,
AUTHOR="S. Haldar and D. K. Subramanian",
TITLE="Fairness in processor scheduling in time sharing systems",
JOURNAL=acmosrev,
VOLUME=25,
NUMBER=1,
PAGES="4-18",
MONTH=jan,
YEAR=1991,
REFERENCES=19,
KEYWORDS="operating systems; scheduling; fairness; round robin",
ABSTRACT="Loosely, fairness is the assurance of granting each request,
from a set of requests, within a predetermined bounded time even though
the request scheduling primitives are unfair or random. The fairness
property has been studied, in solutions to the mutual exclusion problem,
from a theoretical point of view. Many fair solutions to the mutual
exclusion problem have been proposed in recent years. This paper
presents one illustration to show how the concepts of fairness could in
incorporated in processor scheduling in time sharing systems. First, it
looks at some shortcomings associated with the round robin scheduler
used in the time sharing systems, and then presents a fair version of
the round robin scheduler.",
ANNOTE="Tries to favor I/O bound processes by maintaining an auxiliary
queue for jobs returning from I/O.",
}

@ARTICLE{Sala9101:Correction,
AUTHOR="Claudio Salati",
TITLE={Correction to "An Improved Persistent {CSMA} Algorithm Without
Collision Detection"},
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="11-11",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Norm9101:Review,
AUTHOR="Victor T. Norman",
TITLE="A Review of Telecommunications: Protocols and Design by John {D.}
Spragins, et al.",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="12-12",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Part9101:Review,
AUTHOR="C. Partridge",
TITLE="A Review of The Art of Computer System Performance Analysis by
Raj Jain",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="13-13",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Mean9101:Report,
AUTHOR="B. Meandzija",
TITLE="Report from {IFIP} 6.6 International Workshop on Distributed
Systems: Operations and Management",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="14-23",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Rekh9101:Constructing,
AUTHOR="Y. Rekhter",
TITLE="Constructing {Intra-AS} Path Segments for an {Inter-AS} Path",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="44-57",
MONTH=jan,
YEAR=1991,
REFERENCES=8,
}

@ARTICLE{Nich9101:High,
AUTHOR="A. Nicholson and J. Golio and David A. Borman and J. Young and
Wayne Roiger",
TITLE="High Speed Networking at Cray Research",
JOURNAL=ccr,
VOLUME=21,
NUMBER=1,
PAGES="99-110",
MONTH=jan,
YEAR=1991,
REFERENCES=5,
ABSTRACT="For many years, ethernet has been the mainstay for TCP/IP and
local area networking, and issues specific to wide area and long haul
networks have not been adequately addressed. The advent of FDDI and
HIPPI standards, which are, respectively, one and two orders of
magnitude faster then Ethernet, and high speed cross country links, are
causing what used to be experimental issues to become everyday problems.
This paper will cover some of these issues, as they relate to the TCP/IP
protocols, and the work that has happened at Cray Research in the
development of the UNICOS operating system to address these issues.",
}

@TECHREPORT{Chan9101:Bounds,
AUTHOR="Chi-ching Chang and R. T. Nelson",
TITLE="Bounds on the Speedup and Efficiency of Partial Synchronization
in Parallel Processing Systems",
INSTITUTION="IBM",
ADDRESS="T.J. Watson Research Center, Yorktown Heights, NY 10598",
NUMBER="RC 16474",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Nico9101:Parallel,
AUTHOR="D. M. Nicol",
TITLE="Parallel Self-initiating Discrete-Event Simulations",
JOURNAL="Transactions on Modelling and Computer Simulation",
PUBLISHER="Association for Computing Machinery",
VOLUME=1,
NUMBER=1,
PAGES="24-50",
MONTH=jan,
YEAR=1991,
}

@INPROCEEDINGS{Feld9101:Two,
AUTHOR="Robert E. Felderman and L. Kleinrock",
TITLE="Two Processor Time Warp Analysis: Some Results on a Unifying
Approach",
BOOKTITLE="SCS Multiconference on Advances in Parallel and Distributed
Simulation",
ORGANIZATION="Society for Computer Simulation",
VOLUME=23,
PAGES="3-10",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Mudg9101:Microsupercomputer,
AUTHOR="T. Mudge and  others",
TITLE="The Design of a Microsupercomputer",
JOURNAL=ieeecomp,
PAGES="57-64",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Sche9101:Lockup,
AUTHOR="C. Scheurich and M. Dubois",
TITLE="Lockup-free Caches in High-Performance Multiprocessors",
JOURNAL=jpdc,
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Mitr9101:Comparative,
AUTHOR="D. Mitra and J. B. Seery",
TITLE="Comparative Evaluations of Randomized and Dynamic Routing
Strrategies for Circuit-Switched Networks",
JOURNAL=ieeecom,
VOLUME=39,
NUMBER=1,
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Kim9101:Distributed,
AUTHOR="W. Kim and Nat Ballour and J. Garza and D. Woelk",
TITLE="A Distributed Object-Oriented Database System Supporting Shared
and Private Databases",
JOURNAL=tois,
VOLUME=9,
NUMBER=1,
PAGES="31-51",
MONTH=jan,
YEAR=1991,
}

@TECHREPORT{Schw9101:Resource,
AUTHOR="M. Schwartz",
TITLE="Resource Discovery and Related Research at the University of
Colorado",
INSTITUTION="Department of Computer Science, University of Colorado,
Boulder, Colorado",
NUMBER="CU-CS-508-91",
MONTH=jan,
YEAR=1991,
}

@TECHREPORT{Neum9101:Prospero,
AUTHOR="B. Clifford Neuman",
TITLE="The Prospero File System User's Manual",
INSTITUTION="Department of Computer Science and Enngineering, University
of Washington, Seattle, Washington",
MONTH=jan,
YEAR=1991,
}

@MISC{Curr9101:NFSwatch,
AUTHOR="David Curry and J. C. Mogul",
TITLE="{NFSwatch} 3.1 Software",
MONTH=jan,
YEAR=1991,
URL="ftp://gatekeeper.dec.com/pub/net/ip/nfs/nfswatch3.1.tar.Z",
}

@TECHREPORT{Daup9101:ZM4,
AUTHOR="P. Dauphin and R. Hofmann and R. Klar and B. Mohr and A. Quick
and M. Siegle and F. Söz",
TITLE="{ZM4/SIMPLE:} a general Approach to Performance Measurement and
Evaluation of distributed Systems",
INSTITUTION="University of Erlangen",
ADDRESS="Germany",
NUMBER="1/91",
MONTH=jan,
YEAR=1991,
}

@TECHREPORT{Yao9101:Simulated,
AUTHOR="Xin Yao",
TITLE="Simulated Annealing with Extended Neighbourhood",
INSTITUTION="Dept. of Computer Science, Australian National University",
ADDRESS="Canberra 0200 ACT, Australia",
NUMBER="TR-CS-91-02",
MONTH=jan,
YEAR=1991,
}

@TECHREPORT{Yao9101:Finding,
AUTHOR="Xin Yao",
TITLE="On Finding Approximate Solutions for Hard Problems by Neural
Networks",
INSTITUTION="Dept. of Computer Science, Australian National University",
ADDRESS="Canberra 0200 ACT, Australia",
NUMBER="TR-CS-91-01",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Cvij9101:ISDN,
AUTHOR="Z. Cvijan and A. E. Brock and F. P. Corr and J. D. Grieg and J.
E. Kuras and T. Schick",
TITLE="{ISDN} Computer-Aided Telephony",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=1,
PAGES="46-53",
MONTH=jan,
YEAR=1991,
REFERENCES=21,
}

@ARTICLE{Aike9101:Achieving,
AUTHOR="J. A. Aiken and S. R. Parker and D. R. Woodwell",
TITLE="Achieving Interoperability with Distributed Relational
Databases",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=1,
PAGES="38-45",
MONTH=jan,
YEAR=1991,
}

@ARTICLE{Bae9102:Traffic,
AUTHOR="J. Bae and T. Suda",
TITLE="Survey of Traffic Control Schemes and Protocols in {ATM}
Networks",
JOURNAL=ieeeproc,
VOLUME=79,
NUMBER=2,
PAGES="170-189",
MONTH=feb,
YEAR=1991,
KEYWORDS="Congestion control",
ABSTRACT="In the past few years, broadband ISDN (BISDN) has received
increasing attention as a communication architecture capable of
supporting multimedia applications. Among the techniques proposed to
implement BISDN, asynchronous transfer mode (ATM) is considered to be
the most promising transfer technique because of its efficiency and
flexibility. \par In ATM networks, the performance bottleneck of the
network, which was once the channel transmission speed, is shifted to
the processing speed at the network switching nodes and the propagation
delay of the channel. This shift is because the high-speed channel
increases the ratio of propagation delay to cell transmission time and
the ratio of processing time to cell transmission time. Due to the
increased ratio of propagation delay to cell transmission time, a large
number of cells can be in transit between two ATM switching nodes. In
addition, the increased ratio of processing time to cell transmission
time makes it difficult to implement hop-by-hop control schemes.
Therefore, traffic control in ATM is a challenge, and new network
architectures (flow control schemes, error control schemes, etc.) are
required in ATM networks. \par This paper surveys a number of important
research topics in ATM networks. The topics covered include mathematical
modeling of various types of traffic sources, congestion control and
error control schemes for ATM networks, and priority schemes to support
multiple classes of traffic. Standards activity for ATM networks and
future research problems in ATM are also presented.",
}

@ARTICLE{Berg9102:Overload,
AUTHOR="Arthur W. Berger",
TITLE="Overload Control Using Rate Control Throttle: Selecting Token
Bank Capacity for Robustness to Arrival Rates",
JOURNAL=ieeeac,
VOLUME=36,
NUMBER=2,
PAGES="216-219",
MONTH=feb,
YEAR=1991,
KEYWORDS="congestion control; leaky bucket",
ABSTRACT="This note provides new insights that ease the design of rate
control throttles, which are used for overload control of computer and
communication networks. A key result is that if the token bank capacity
is 10 or more and if jobs arrive as a Poisson process, then for many
practical applications in digital switching systems and
telecommunication networks, the control settings can be independent of
the arrival rate and need only be adjusted for changes in the desired
departure rate.",
}

@ARTICLE{Berg9102:Rate,
AUTHOR="Arthur W. Berger",
TITLE="Performance Analysis of a Rate-Control Throttle where Tokens and
Jobs Queue",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=2,
PAGES="165-170",
MONTH=feb,
YEAR=1991,
KEYWORDS="congestion control; leaky bucket",
ABSTRACT="A rate-control throttle is used for overload control in
distributed switching systems and computer and communication networks.
Typical implementations of the throttle have a token bank where an
arriving job is blocked and rejected if the bank is empty of tokens.
This paper examines an expanded implementation where an arriving job
queues in a finite buffer when the token bank is empty. We show that the
steady-state throughput and blocking of jobs depend on the capacity of
the job buffer and the capacity of the token bank only via the sum of
the two capacities, and not on their individual values. Thus, the job
buffer per se is not needed to enhance the robustness of the throughput
of the throttle to unknown exogeneous job arrival rates. However, a job
buffer, along with a token bank, with adjustable bufer capacities does
have the potential to shape the departure process and to adapt between a
delay control and a work-rejection control.",
}

@ARTICLE{Guse9102:Characterizing,
AUTHOR="Riccardo Gusella",
TITLE="Characterizing the Variability of Arrival Processes with Indexes
of Dispersion",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=2,
PAGES="203-211",
MONTH=feb,
YEAR=1991,
KEYWORDS="queueing theory; index of dispersion; variability; source
models",
ABSTRACT="The paper proposes to characterize the burstiness of packet
arrival processes with indexes of dispersion for intervals and counts.
These indexes, which are functions of the variance of intervals and
counts, are relatively straightforward to estimate and convey much more
information than simpler indexes such as the coefficient of variation,
that are often used to describe burstiness qualitatively. The paper
defines and evaluates the indexes of dispersion for some of the simple
analytical models that are frequently used to represent highly variable
processes. The author then estimates the indexes for a number of
measured point processes that were generated by workstations
communicating to file servers over a local-area network. The author
shows that nonstationary components in the measured packet arrival data
distort the shape of the indexes and proposes ways to handle
nonstationary data. Finally, to show how to incorporate measures of
variability into analytical models and to offer an example of how to
model the measured packet arrival processes, the author describes a
fitting procedure based on the index of dispersion for counts for the
Markov-modulated Poisson process.",
ANNOTE="Index of dispersion of counts (IDC) and intervals (IDI).",
}

@ARTICLE{Kano9102:ISDN,
AUTHOR="S. Kano and K. Kitami and M. Kawarasaki",
TITLE="{ISDN} Standardization",
JOURNAL=ieeeproc,
VOLUME=79,
NUMBER=2,
PAGES="118-124",
MONTH=feb,
YEAR=1991,
KEYWORDS="ISDN",
ABSTRACT="Thanks to the standards, ISDN's and their services all over
the world can be interworked and any ISDN terminal can be interconnected
with each other. This paper overviews the history and achievements of
ISDN standardization in the CCITT. Two of the most important
developments, namely ISDN basic and supplementary services and
broad-band ISDN, are focused upon. The background or underlying concepts
in the discussions of ISDN standardization are briefly explained.",
}

@ARTICLE{Klei9102:ISDN,
AUTHOR="L. Kleinrock",
TITLE="{ISDN} - The Path to Broadband Networks",
JOURNAL=ieeeproc,
VOLUME=79,
NUMBER=2,
PAGES="112-117",
MONTH=feb,
YEAR=1991,
KEYWORDS="BISDN; ATM; ISDN",
}

@ARTICLE{Liou9102:Model,
AUTHOR="Der-Ming Liou and An-Chi Lu",
TITLE="A Model for Dynamic Channel Allocation in an {ISDN}",
JOURNAL=ieeeproc,
VOLUME=79,
NUMBER=2,
PAGES="205-213",
MONTH=feb,
YEAR=1991,
KEYWORDS="ISDN; channel allocation",
ABSTRACT="Integrated services digital network (ISDN) is an attempt to
integrate different types of communication networks (e.g., packet
switching, circuit switching) to provide services (e.g., voice, video,
and data) on a demand basis. Traffic requirements from heterogeneous
users in ISDN vary in their data rate, arrival rate, and service time
distribution. To provide efficient service, we propose a dynamic channel
allocation strategy based on traffic characteristics and channel
utilization. Conventional channel allocation schemes such as complete
channel allocation, complete partition channel allocation, complete
competition channel allocation, and moving boundary channel allocation
are examined and compared with the proposed dynamic channel allocation
scheme. An analytic model is developed and a solution based on the
moment-generating function technique is given. Numerical examples are
also presented. The result shows that the scheme improves the system
performance.",
ANNOTE="Markov model.",
}

@ARTICLE{Meie9102:Packet,
AUTHOR="K. S. Meier-Hellstern and P. E. Wirth",
TITLE="Packet Switch Engineering Procedures when Customer
Characteristics are Uncertain",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=2,
PAGES="142-150",
MONTH=feb,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="Frequently, emerging switch services are not sufficiently well
understood to be accurately provisioned. Since there is a great deal of
uncertainty in the traffic estimates, accurate engineering of the switch
is extremely difficult. Distributed networks of packet switches are
particularly affected by these uncertainties, because the resources
available to individual users are shared and limited. In this paper, a
method for packet switch provisioning is demonstrated which accounts for
the effects of uncertainty in estimating customer characteristics. The
method models the traffic parameters of the customers as random
variables. It is used to calculate the maximum number of customers that
can be accomodated while controlling the probability that their total
traffic is beyond the nominal capacity of the system. We show that,
depending on the degree of uncertainty in estimating parameters for the
arrival process, the application of the method can have a substantial
impact on the provisioning of the switch.",
ANNOTE="moment-matching technique; queueing network analyzer.",
}

@ARTICLE{Wein9102:Limited,
AUTHOR="A. Weinrib and G. Gopal",
TITLE="Limited Waiting: An Adaptive Overload-Control Strategy for
Circuit Switched Networks",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=2,
PAGES="157-164",
MONTH=feb,
YEAR=1991,
ABSTRACT="The paper presents an adaptive control strategy for circuit
switched networks in which calls are permitted to wait for a limited
time to be carried on a low-cost preferred route. The strategy uses
network resources more efficiently than other conventional approaches,
exhibiting lower blocking of calls under overload conditions. The
strategy is also adaptive in that when there is little network
congestion, there is no penalty for the policy, in contrast to other
schemes in which improved performance under overload is achieved at the
cost of degraded performance at lower loads. The authors analyze an
exactly solvable model, and then present simulation results for a more
general network.",
ANNOTE="Congestion control.",
}

@ARTICLE{Zhan9102:Variable,
AUTHOR="Y.-Q. Zhang and Wei Wu and Kyu-han Kim and R. L. Pickholtz and
Jay Ramasastry",
TITLE="Variable Bit-Rate Video Transmission in the Broadband {ISDN}
Environment",
JOURNAL=ieeeproc,
VOLUME=79,
NUMBER=2,
PAGES="214-222",
MONTH=feb,
YEAR=1991,
KEYWORDS="packet video; ATM; BISDN; video transport",
ABSTRACT="While the ATM-based broadband ISDN network gives the
possibility to support source coding at the variable bit rate (VBR), it
also benefits from the VBR coding. The advantages of VBR coding include
consistent picture quality, bandwidth savings, and delay reduction.
However, one of the major drawbacks of ATM networks is the cell loss and
consequent aggravated picture degradation in case of VBR coding. Many
compensative measures have been proposed recently to make the cell loss
subjectively imperceptible. These schemes include simple ARQ schemes,
error concealment by command refreshment, appropriate queueing
discipline and priority switching design, layered source coding schemes,
and other signal processing techniques. This paper intends to summarize
these efforts and, in particular, elaborate on different layered source
coding schemes. Four types of signal priority classification schemes are
identified: bit-plane separation (BPS), frequency-domain separation
(FDS), combined bit-plane-frequency separation (CBFS), and feature plane
separation (FPS). Different layered coding techniques are discussed and
compared. Some open questions and recommendations are also given for
further research and study.",
}

@ARTICLE{Robe9102:Superposition,
AUTHOR="J. W. Roberts and J. T. Virtamo",
TITLE="The superposition of periodic cell arrival streams in an {ATM}
multiplexer",
JOURNAL=ieeecom,
VOLUME=39,
NUMBER=2,
PAGES="298-303",
MONTH=feb,
YEAR=1991,
KEYWORDS="queueing theory; multiplexer; CBR; performance evaluation;
periodic sources",
ABSTRACT="We consider the queue arising in a multiservice network using
ATM when a superposition of periodic streams of constant length cells is
multiplexed on a high speed link. An exact closed formula is derived for
the queue length distribution in the case where all streams have the
same period and we obtain tight upper and lower bounds on this
distribution when the periods are different. These results are deduced
from a novel characterization of the single server constant service time
queue which should be useful in other applications.",
}

@TECHREPORT{Gril9102:UMTS,
AUTHOR="D. Grillo and L. Pace and G. Subiaco",
TITLE="{UMTS} air-interface traffic performance modelling",
INSTITUTION="RACE",
ADDRESS="Rome, Italy",
NUMBER="Race 1043 rmtp/mss/k",
PAGES=15,
MONTH=feb,
YEAR=1991,
REFERENCES=27,
KEYWORDS="MAT; protocol simulation; RESQ; research queueing package",
ANNOTE="The model's objective is to estimate the combined effect of
alternative implementations of key design issues in the air-interface,
like multiple access schemes, error detection/recovery algorithms, and
handover versus call setup request handling.",
}

@INPROCEEDINGS{Chio9102:GreatSPN,
AUTHOR="Giovanni Chiola",
TITLE="{GreatSPN} 1.5 software architecture",
BOOKTITLE="5th International Conference on Modelling Techniques and
Tools for Computer Performance Evaluation",
ADDRESS="Torino",
PAGES="117-132",
MONTH=feb,
YEAR=1991,
KEYWORDS="Computer tool; performance evaluation",
}

@INPROCEEDINGS{Cros9102:MSCCC,
AUTHOR="S. Crosby and A. Krzesinski and Jean-Yves Le Boudec",
TITLE="A {MSCCC} model of multilayer window flow control",
BOOKTITLE="5th International Conference on Modelling Techniques and
Tools for Computer Performance Evaluation",
ADDRESS="Torino",
PAGES="71-85",
MONTH=feb,
YEAR=1991,
KEYWORDS="Communication network; window mechanism; flow control",
}

@ARTICLE{Gril9102:CCITT,
AUTHOR="D. Grillo and A. W. Lewis and R. N. Pandya and M.
Villen-Altamirano",
TITLE="{CCITT} {E.700} recommendation series -- a framework for traffic
engineering of {ISDN}",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=2,
PAGES="135-141",
MONTH=feb,
YEAR=1991,
KEYWORDS="Traffic engineering; standardization",
}

@ARTICLE{Jabb9102:Common,
AUTHOR="B. Jabbari",
TITLE="Common channel signalling system number 7 for {ISDN} and
intelligent networks",
JOURNAL=ieeeproc,
VOLUME=79,
NUMBER=2,
PAGES="155-169",
MONTH=feb,
YEAR=1991,
KEYWORDS="Signalling; common channel; CCS",
}

@INPROCEEDINGS{Kero9102:Qsolver,
AUTHOR="T. Kerola",
TITLE="Qsolver -- a modular environment for solving queueing network
models",
BOOKTITLE="5th International Conference on Modelling Techniques and
Tools for Computer Performance Eval",
ADDRESS="Torino",
PAGES="409-420",
MONTH=feb,
YEAR=1991,
KEYWORDS="Computer tool; performance evaluation",
}

@ARTICLE{Leun9102:Cyclic,
AUTHOR="K. K. Leung",
TITLE="Cyclic-service systems with probabilistically-limited service",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=2,
PAGES="185-193",
MONTH=feb,
YEAR=1991,
KEYWORDS="Queueing system; cyclic service; analysis",
}

@INPROCEEDINGS{Pate9102:SDL,
AUTHOR="M. Paterok and R. Heller and H. de Meer",
TITLE="Performance evaluation of an {SDL} run time system -- a case
study.",
BOOKTITLE="5th International Conference on Modelling Techniques and
Tools for Computer Performation Evaluation",
ADDRESS="Torino",
PAGES="86-101",
MONTH=feb,
YEAR=1991,
KEYWORDS="Queueing system; priority; analysis",
}

@INPROCEEDINGS{Pool9102:Integrated,
AUTHOR="R. J. Pooley",
TITLE="The integrated modelling support environment -- a new generation
of performance modelling tools",
BOOKTITLE="5th International Conference on Modelling Techniques and
Tools for Computer Performance Evaluation",
ADDRESS="Torino",
PAGES="1-15",
MONTH=feb,
YEAR=1991,
KEYWORDS="Computer tool; performance evaluation",
}

@INPROCEEDINGS{Schw9102:Approximate,
AUTHOR="P. Schweitzer and Ian Akyildiz",
TITLE="Approximate mean value analysis for non-product form networks of
queues with job class changes",
BOOKTITLE="5th International Conference on Modelling Techniques and
Tools for Computer Performance Evaluation",
ADDRESS="Torino",
PAGES="59-70",
MONTH=feb,
YEAR=1991,
KEYWORDS="Queueing network; analysis",
}

@INPROCEEDINGS{Smit9102:Integrating,
AUTHOR="C. U. Smith",
TITLE={Integrating new and "used" modeling tools for performance
engineering},
BOOKTITLE="5th International Conference on Modelling Techniques and
Tools for Computer Performance Evaluation",
ADDRESS="Torino",
PAGES="148-158",
MONTH=feb,
YEAR=1991,
KEYWORDS="Computer tool; performance evaluation",
}

@ARTICLE{Wu9102:ISDN,
AUTHOR="Wei Wu and A. Livne",
TITLE="{ISDN:} A snapshot",
JOURNAL=ieeeproc,
VOLUME=79,
NUMBER=2,
PAGES="103-111",
MONTH=feb,
YEAR=1991,
KEYWORDS="ISDN",
}

@INPROCEEDINGS{Wulz9102:Grammar,
AUTHOR="W. Dulz and S. Hofmann",
TITLE="Grammar-Based Workload Modeling of Communication Systems",
BOOKTITLE="5th International Conference on Modeling Techniques and Tools
for Computer Performance Evaluation",
ADDRESS="Torino, Italy",
PAGES="16-30",
MONTH=feb,
YEAR=1991,
KEYWORDS="workload modeling; communication systems; attributed grammars;
syntax-driven workload generator",
ABSTRACT="In this paper we present a new approach to describe workload
models by means of attributed grammars: productions specify the syntax
of protocol data units whereas attribute functions, as part of semantic
rules, formalize the influence of characteristic workload parameters,
such as packet length, interarrival times or timeouts. Proceeding from
this basic model we built a grammatical inference system for automated
construction of proper attributed grammars and a syntax-driven workload
generator which can easily be adjusted to any performance modeling
environment running under the UNIX operating system.  We also show how
attributed grammers can be used to emulate other workload characterizing
techniques, i.e.  compound poisson arrivals and train models.",
URL="ftp://ftp.uni-erlangen.de/pub/papers/immd7/vs/sfbb3/Grammar-based-Workload-Modeling-of-Communication-Systems.ps.Z",
}

@INPROCEEDINGS{Kirs9102:International,
AUTHOR="P. T. Kirstein and Jon Crowcroft",
TITLE="International Research Network Links",
BOOKTITLE="RARE High Speed Networks Conference",
ADDRESS="Brussels",
MONTH=feb,
YEAR=1991,
}

@TECHREPORT{Goto9102:Performance1,
AUTHOR="K. Goto and T. Suda",
TITLE="Performance Analysis of a Broadcast Star Local Area Network with
Collision Avoidance: Part 1, Infinite Station Population Model",
TYPE="Technical Report",
INSTITUTION="University of California, Irvine, Department of Information
and Computer Science",
NUMBER="ICS-TR-91-10",
PAGES=20,
MONTH=feb,
YEAR=1991,
ABSTRACT="Packet collisions and their resolution create a performance
bottleneck in random access LANs. As a solution to this problem, a
broadcast star network with collision avoidance has been proposed and
studied in other references. In a broadcast star network, collisions of
simultaneously transmitted packets are avoided by means of hardware
called a collision avoidance switch. While the channel is being used by
one station, the collision avoidance switch blocks other stations from
using it. This network implements random access protocols without the
penalty of collisions among packets and combines the benefits of random
access (low delay when traffic is light; simple, distributed, and
therefore robust protocols) with excellent network utilization. In this
paper, we analyze the performance of a broadcast star network, assuming
synchronous operation of a network. In synchronous operation, the
channel time is slotted, and stations transmit only at the beginning of
a slot. The number of stations on a network is assumed to be infinite,
and packets arrive at stations according to a Poisson process. An exact
analysis is developed, and the distribution for the transmission delays
is obtained. It is also shown through simulations that a broadcast star
operating under synchronous mode yields better performance than that
operating under asynchronous mode, where transmissions of packets are
not confined to the beginning of slots, and stations start transmission
any time.",
}

@TECHREPORT{Goto9102:Performance2,
AUTHOR="K. Goto and T. Suda",
TITLE="Performance Analysis of a Broadcast Star Local Area Network With
Collision Avoidance: Part 2, Finite Station Population Model",
TYPE="Technical Report",
INSTITUTION="University of California, Irvine, Department of Information
and Computer Science",
NUMBER="ICS-TR-91-11",
PAGES=35,
MONTH=feb,
YEAR=1991,
ABSTRACT="In order to overcome the performance bottleneck due to
collisions and their resolution in random access LANs, a new network
architecture called a broadcast star network with collision avoidance
has been proposed and studied by many researchers. The performance of a
broadcast star network is also studied in a companion paper [11],
assuming an infinite station population and synchronous operation of the
network. In this paper, we analyze the performance of a broadcast star
network assuming a finite number of stations, and we obtain the
throughput and the distribution of transmission delays. An exact
analysis is presented first. However, this analysis is computationally
practical for networks with a small number of stations only. Therefore,
an approximate analysis is also presented for a network having a large
number of stations. The accuracy of our approximation is examined
through simulations.",
}

@TECHREPORT{Huan9102:LAN,
AUTHOR="H. Huang and T. Suda and Yasuhiro Noguchi",
TITLE="{LAN} with Collision Avoidance: Switch Implementation and
Simulation Study",
TYPE="Technical Report",
INSTITUTION="University of California, Irvine, Department of Information
and Computer Science",
NUMBER="ICS-TR-91-13",
PAGES=33,
MONTH=feb,
YEAR=1991,
ABSTRACT="Packet collisions and their resolution create a performance
bottleneck in random access LANs. A hardware solution to this problem is
to use collision avoidance switches. These switches allow the
implementation of random access protocols without the penalty of
collisions among packets. The simplest network based on collision
avoidance is the Broadcast Star network, where all the stations are
connected to a central switch. A more sophisticated architecture based
on collision avoidance is the CAMB (Collision Avoidance Multiple
Broadcast) Tree network, where concurrent broadcast is possible. This
paper presents a design of a collision avoidance switch for the CAMB
Tree using TTL devices. Simulation study exploring the performance of
the Broadcast Star network in both synchronous and asynchronous
operations is also presented in this paper.",
}

@TECHREPORT{Marz9102:Tools,
AUTHOR="K. Marzullo and Mark D. Wood",
TITLE="Tools for Constructing Distributed Reactive Systems",
INSTITUTION="Cornell University, Computer Science Department",
NUMBER="TR90-1160",
PAGES=30,
MONTH=feb,
YEAR=1991,
ABSTRACT="Many distributed applications can be cast as reactive systems,
where a reactive system consists of an instrumented program that is
monitored and controlled by an input-driven control program. Examples of
non-real-time reactive systems include monitoring and debugging systems,
tool integration services, and network and distributed application
managers. There is currently little support for building reactive
systems. This paper describes the Meta toolkit that provides such
support. Using Meta, a distributed system can be instrumented with a
sensor and actuator abstraction that exposes the state of the system for
purposes of control. Then, a control program can be written that
interacts with the instrumented system using guarded commands. Of
particular concern is the efficiency of control, so Meta allows the
control program to be distributed in order to take advantage of locality
as much as possible.",
}

@TECHREPORT{Shep9102:TCP,
AUTHOR="Timothy Shepard",
TITLE="{TCP} Packet Trace Analysis",
TYPE="Technical Report",
INSTITUTION="MIT Laboratory for Computer Science",
ADDRESS="Cambridge, Massachusetts",
NUMBER="TR 494",
MONTH=feb,
YEAR=1991,
KEYWORDS="TCP; congestion control",
ABSTRACT="Examination of a trace of packets collected from the network
is often the only method available for diagnosing protocol performance
problems in computer networks.  This thesis explores the use of packet
traces to diagnose performance problems of the transport protocol TCP.
Unfortunately, manual examination of these traces can be so tedious that
effective analysis is not possible.  The primary contribution of this
thesis is a graphical method for displaying the packet trace which
greatly reduces the tediousness of examining a packet trace. The
graphical method is demonstrated by the examination of some packet
traces of typical TCP connections.  The performance of two different
implementations of TCP sending data across a particular network path is
compared.  Traces many thousands of packets long are used to demonstrate
how effectively the graphical method simplifies examination of long
complicated traces.  In the comparison of the two TCP implementations,
the burstiness of the TCP transmitter appeared to be related to the
achieved throughput.  A method of quantifying this burstiness is
presented and its possible relevance to understanding the performance of
TCP is discussed.",
URL="http://ana-www.lcs.mit.edu/anaweb/pdf-papers/\_TR\_494.pdf",
}

@ARTICLE{Knes9102:Diffusion,
AUTHOR="Ch. Knessl",
TITLE="On the diffusion approximation to a fork and join queueing
model",
JOURNAL=siapp,
VOLUME=51,
PAGES="160-171",
MONTH=feb,
YEAR=1991,
}

@INPROCEEDINGS{Golu9102:Modeling,
AUTHOR="L. Golubchik and G. D. Rozenblat and W.-Y. Cheng and R. R.
Muntz",
TITLE="The Tangram Modeling Environment",
BOOKTITLE="5th International Conference on Modeling Techniques and Tools
for Computer Performance Evaluation",
ADDRESS="Turin, Italy",
PAGES="421-435",
MONTH=feb,
YEAR=1991,
}

@INPROCEEDINGS{Fang9102:Approach,
AUTHOR="D. Fang and Q. Li and Dennis McLeod",
TITLE="An Approach to Partial Integration for Distributed, Autonomous,
Object Databases",
BOOKTITLE="Australian Database - Information Systems Conference",
ORGANIZATION="Kensington, Australia",
MONTH=feb,
YEAR=1991,
}

@INPROCEEDINGS{Fang9102:Remote,
AUTHOR="D. Fang and J. Hammer and Dennis McLeod and A. Si",
TITLE="Remote-Exchange: An Approach to Controlled Sharing among
Autonomous, Heterogeneous Database Systems",
BOOKTITLE="IEEE Spring Compcon",
ORGANIZATION="IEEE",
ADDRESS="San Francisco",
MONTH=feb,
YEAR=1991,
}

@MANUAL{Swed9102:SICS,
AUTHOR="Swedish Institute of Computer Science",
TITLE="{SICS} Protocol Implementation Measurement System {(SPIMS),} User
Manual",
NOTE="Version 3.0",
MONTH=feb,
YEAR=1991,
}

@TECHREPORT{Bole9102:Error,
AUTHOR="Daniel L. Boley and R. P. Brent and G. H. Golub and F. T. Luk",
TITLE="Error Correction via the Lanczos Process",
INSTITUTION="Dept. of Computer Science, Australian National University",
ADDRESS="Canberra 0200 ACT, Australia",
NUMBER="TR-CS-91-03",
NOTE="Revision in SIAM J. Matrix Analysis and Applications 13(1992),
312-332. (rpb124)",
MONTH=feb,
YEAR=1991,
}

@ARTICLE{Garr9102:Study,
AUTHOR="Mark Garrett and Song Li",
TITLE="A Study of Slot Reuse in Dual Bus Multiple Access Networks",
JOURNAL=ieeejsac,
MONTH=feb,
YEAR=1991,
ABSTRACT="In dual unidirectional bus networks, packets usually occupy
fixed-length slots from the sending station to the end of the network.
An erasure node is a specialized station which recognizes packets which
have passed their destination stations, and releases the slots for
subsequent use. This paper derives the optimal locations for erasure
nodes and shows analytically, for uniform traffic, that only serveral
erasure nodes are needed to achieve throughput close to twice the
nominal network bandwidth. The results are tested by simulation of the
DQDB protocol, which demonstrates a realistic improvement of 40\% with
only three erasure nodes. Fair access among the stations is improved as
well. We generalize the analytic results by providing an algorithm for
determining the optimal erasure node locations and the throughput
improvement, given any arbitrary traffic pattern. The application of
this methodology to the related problem of bridged subnetworks is
briefly discussed.",
URL="http://www.ece.utexas.edu/~sanqi/papers.html",
}

@TECHREPORT{Schi9102:Adaptive,
AUTHOR="Bill Schilit and Dan Duchamp",
TITLE="Adaptive Remote Paging for Mobile Computers",
INSTITUTION="Columbia University",
NUMBER="CUCS-004-91",
MONTH=feb,
YEAR=1991,
}

@INPROCEEDINGS{ElZa9103:Packet,
AUTHOR="Magda El Zarki and Ness Shroff",
TITLE="Performance Analysis of Packet Loss Recovery Schemes in
Interconnected {LAN-WAN-LAN} Networks",
BOOKTITLE="3rd IFIP WG 6.4 Conference on High Speed Networking",
ADDRESS="Berlin, Germany",
PAGES="337-351",
MONTH=mar,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="In this paper, we provide an approximate analysis for
determining the mean end-to-end delay for different packet loss recovery
schemes over heterogeneous interconnected LAN-WAN-LAN type networks. The
purpose is to demonstrate the tradeoffs between the different recovery
schemes as a function of WAN link capacities and nodal buffer sizes for
different throughput values. The analysis is based on a hybrid modeling
technique introduced by the authors in an earlier work on the
performance of tandem queues with bursty traffic streams.",
}

@ARTICLE{Ferr9103:Rate,
AUTHOR="Josep M. Ferrandiz and Aurel A. Lazar",
TITLE="Rate Conservation for Stationary Processes",
JOURNAL=jap,
VOLUME=28,
NUMBER=1,
PAGES="146-158",
MONTH=mar,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="We derive a rate conservation law for distribution densities
which extends a result of Brill and Posner. Based on this conservation
law, we obtain a generalized Takacs equation for the G/G/m/B queueing
system that only requires the existence of a stochastic intensity for
the arrival process and the residual service time distribution density
for the G/GI/1/B queue. Finally, we solve Takacs' equation for the
N/GI/1/infinity queueing system.",
}

@INPROCEEDINGS{Gidr9103:TeraNet,
AUTHOR="R. Gidron",
TITLE="TeraNet: A Multihop Multichannel {ATM} Lightwave Network",
BOOKTITLE="3rd IFIP WG 6.4 Conference on High Speed Networking",
ADDRESS="Berlin, Germany",
PAGES="61-76",
MONTH=mar,
YEAR=1991,
KEYWORDS="fast packet switching",
ABSTRACT="TeraNet is an experimental network that is being built at the
Center for Telecommunications Research, Columbia University. The network
is part of the ACORN (advanced communications organization for research
network) project. The purpose of ACORN is to investigate innovative
optical architectures which offer user access at data rates as high as
one gigabit per second (Gbps). The design principles of TeraNet
incorporate three main concepts: a transmission medium that contains
multiple channels, a system architecture that employs a multihop
approach to routing packets, and a traffic control architecture that
supports multiple traffic classes. The network contains a set of network
interface units (NIU) that are interconnected with passive optics. Each
NIU is a two by two switch with an additional user access port. Each of
the six NIU ports (three input and three output) can handle data rates
up to one Gbps. The NIU buffers and the bandwidth of the output links
are shared by four traffic classes according to the ATS concept of
resource allocation. The packet format and routing procedure are
compatible with the emerging ATM standard.",
}

@INPROCEEDINGS{Habi9103:Congestion,
AUTHOR="Ibrahim Habib and T. N. Saadawi",
TITLE="Congestion Control in Video Multiplexers in Broadband Networks",
BOOKTITLE="3rd IFIP WG 6.4 Conference on High Speed Networking",
ADDRESS="Berlin, Germany",
PAGES="241-260",
MONTH=mar,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="In this paper, we present a framework for the solution of the
problem of congestion control in broadband networks. We present and
analyze a flow control algorithm which is applied in packet video
multiplexers. The algorithm is based on the principle of applying
feedback control signal to the input arrival process, throttling the
peak bit rate to a level such that the burstiness of the aggregate
arrival process is decreased and hence we make an efficient use of the
allocated bandwidth and prevent congestion. The analysis is based upon a
two dimensional continuous-time Markov chain representation of the
multiplexer buffer queueing process.",
}

@INPROCEEDINGS{DePr9103:OSI,
AUTHOR="M. de Prycker and R. Peschl and T. Van Landegem",
TITLE="{BISDN} and the {OSI} Reference Model",
BOOKTITLE="3rd IFIP WG 6.4 Conference on High Speed Networking",
ADDRESS="Berlin, Germany",
PAGES="39-57",
MONTH=mar,
YEAR=1991,
REFERENCES=12,
KEYWORDS="ATM; B-ISDN; architecture; OSI; protocol",
ABSTRACT="This paper starts by presenting the rationale behind the
evolution of telecommunication networks towards ISDN and more
specifically towards BISDN. It then presents the salient features of the
asynchronous transfer mode (ATM), selected by CCITT as the transfer mode
for BISDN. Considering more specifically the support of connectionless
data services in BISDN, the paper relates the BISDN protocol reference
model to the OSI one. We will demonstrate that the service offered by
the ATM layer in the BISDN protocol reference model is equivalent to the
service offered by the OSI physical layer. Furthermore, we will show
that the service offered by the ATM adaptation layer for connectionless
data is equivalent to an OSI data link layer.",
}

@TECHREPORT{Schu9103:Congestion,
AUTHOR="Henning Schulzrinne and James F. Kurose and Donald F. Towsley",
TITLE="Congestion Control for Real-Time Traffic in High-Speed Networks",
TYPE="Technical Report",
INSTITUTION="Department of Computer and Information Science, University
of Massachusetts",
ADDRESS="Amherst, Massachusetts",
NUMBER="TR 89-92",
MONTH=mar,
YEAR=1991,
KEYWORDS="congestion control; real-time traffic; packet loss",
ABSTRACT="Traditional feedback congestion control is not suitable for
high-speed networks due to their high bandwidth-to-delay ratio. In this
paper, we investigate the possibility of locally controlling short-term
congestion for loss-tolerant, but delay-sensitive traffic such as packet
voice through selective discarding of packets based on the virtual work
found by a packet on arrival to a queue (local deadline). Five models,
$M/D/1/K$, $M/M/1/K$, bounded system time, bounded waiting time and a
discrete-time finite-buffer bulk-arrival system, are considered. For the
last three, it is shown by analysis and simulation of a multi-stage
virtual circuit that this approach can cut voice-tolerable loss rates in
half for high loads. Further, we show that the simple case of using the
same local deadline throughout the network performs nearly as well as
taking reduced interior traffic into consideration and optimizing loss
performance over a set of heterogeneous control parameters. By example,
the issue of establishing control parameters at call setup time is also
considered. Simulation results suggests that queue scheduling based on
time remaining to deadline can reduce losses by up to two orders of
magnitude.",
URL="http://www.cs.columbia.edu/~hgs/papers/Schu9103\_Congestion.ps.Z",
}

@TECHREPORT{Pasq9103:Operating,
AUTHOR="J. Pasquale and George C. Polyzos and Eric J. Anderson and Kevin
Fall and Jonathan S. Kay and Vachaspathi Kompella and Scott R. McMullan
and Dipti Ranganathan",
TITLE="Network and operating system support for multimedia
applications",
INSTITUTION="University of California, San Diego",
NUMBER="CS91-186",
PAGES=14,
MONTH=mar,
YEAR=1991,
KEYWORDS="OS support; multimedia",
ABSTRACT="This paper describes the general problems in providing system
software support for multimedia applications. We specifically focus on
applications which have digital continuous media (DCM) I/O components,
and the type of support that must be provided by the network software
and operating system. DCM applications have large bandwidth and low
delay requirements. We discuss network software support to meet these
requirements, such as resource reservation schemes based on
parameterized requests for some level of quality of service. Most
likely, DCM communications will be long-lived, which suggests that
connections are the appropriate network construct for such
communications. Regarding the operating system, we describe issues of
real-time resource scheduling, synchronization of processes and
temporally related DCM flows, shared memory, and the need for a modular,
uniform I/O abstraction. Finally, we present design principles based on
the concepts of moving processes to data and separating design from
implementation as important considerations for system software design.",
}

@INPROCEEDINGS{Ches9103:Evolution,
AUTHOR="G. L. Chesson",
TITLE="The Evolution of {XTP}",
BOOKTITLE="3rd IFIP WG 6.4 Conference on High Speed Networking,
Participants Edition",
EDITOR="André Danthine and Otto Spaniol",
ADDRESS="Berlin, Germany",
PAGES="15-24",
MONTH=mar,
YEAR=1991,
KEYWORDS="transport protocol; protocol implementation; XTP",
}

@ARTICLE{Mele9103:Distributed,
AUTHOR="R. Melen",
TITLE="Distributed protocols for access arbitration in tree-structured
communication channels",
JOURNAL=ieeecom,
VOLUME=39,
NUMBER=3,
PAGES="416-425",
MONTH=mar,
YEAR=1991,
KEYWORDS="multiple access; burst switching",
ABSTRACT="We consider the problem of arbitrating access to a tree
structured communication channel with large geographic extent, providing
multipoint communication among a set of terminals. In our model,
terminals transmit information in bursts consisting of many packets and
compete for the right to transmit bursts. In the simplest case, the
channel allows only one terminal to transmit at a time; this can be
extended to $k$ concurrent transmitters. The problem resembles
contention resolution in local area networks. It is distinguished by the
topology of the channel, the magnitude of the delays involved and the
potential for multiple transmitters. In this paper, we identify two
general approaches and several specific assess arbitration algorithms
and make a preliminary assessment of their promise.",
}

@TECHREPORT{Hopp9103:Use,
AUTHOR="Andrew Hopper",
TITLE="Design and use of multimedia high-speed networks in multimedia
applications",
TYPE="Technical Report",
INSTITUTION="Olivetti Research Limited",
ADDRESS="Cambridge, England",
NUMBER="ORL-91-2",
NOTE="also in {\em 3rd IFIP Conference on High Speed Networking},
Berlin, March 1991, pp. 25--28",
MONTH=mar,
YEAR=1991,
REFERENCES=11,
KEYWORDS="multimedia; packet voice; packet video; local area networks;
workstation architecture; real-time services; integrated services;
Cambridge Fast Ring",
ABSTRACT="This paper deals with architectures for networked multimedia
systems. Such architectures are made up of both network components and
multimedia device components. The networks include high speed switches
and backbones for real-time stream applications as well as systems with
lower capacity which provide additional facilities for different kinds
of multimedia devices. The devices range from lightweight portable
personal units to complex workstations. A report is given of experience
from a multimedia experimental system called Pandora which places a
camera on the desktop and allows many applications to be tried. An
estimate of the bandwidth requirements for future systems is made
drawing on experience from the popular applications in Pandora and in
the expectation of the much higher quality required by new multimedia
applications.",
ANNOTE="''Low cost high capacity switches are being developed which will
have throughput performances upto 10Gbps and higher''. LAN/MAN
technology of between 10Mbps and 2Gbps can carry both conventional data
traffic and real time audio and video streams. Video walls will require
huge bandwidths to be useful. ''only with the highest network bandwidth
can multiple and ubiquitous video applications be envisaged''.",
}

@INPROCEEDINGS{Gree9103:Exploiting,
AUTHOR="P. E. Green",
TITLE="Exploiting photonic Technology for Gigabit Computer Networks",
BOOKTITLE="3rd IFIP Conference on High Speed Networking",
ADDRESS="Berlin",
PAGES="3-14",
MONTH=mar,
YEAR=1991,
ANNOTE="The bandwidth of fibre optics is ten orders of magnitude greater
than that of standard telephone lines (30,000Ghz vs. 3Khz) To fully
utilise fibre in the next (third) generation optical communication
systems we must ask how we can make use of it's non-classical
properities to aid data communications. The use of Wavelength Division
Multiplexing Access (WDMA) is more attractive than Time Division
Multiple Access (TDMA) and Code Division Multiple Access (CDMA - aka
spread spectrum) as nothing in the network has to run faster than the
per-node bit rate (in the other two, you suffer from a 40-fold bandwidth
expansion factor or processing gain) ``[...] there is no reason to doubt
that 1000-node MANs (50 km diameter) at 1 sustained gigabit per second
per node can be built within three to five years'' The use of optical
fibre networks may require a rethink of the protocol stacks; espcially
as some view the link layer to be unnecessary due to the improved BER.",
}

@ARTICLE{Joli9103:Porting,
AUTHOR="William Jolitz and Lynne G Jolitz",
TITLE="Porting {UNIX} to the 386: the standalone system",
JOURNAL=drdobbs,
VOLUME=16,
NUMBER=3,
PAGES="38-88",
MONTH=mar,
YEAR=1991,
KEYWORDS="Unix; operating systems; 386BSD; Intel; PC; Berkeley Unix",
}

@ARTICLE{Neut9103:Superposition,
AUTHOR="M. F. Neuts and C. Pearce",
TITLE="The Superposition of Independent Discrete Markovian Packet
Streams",
JOURNAL=jap,
VOLUME=28,
NUMBER=1,
PAGES="84-95",
MONTH=mar,
YEAR=1991,
REFERENCES=10,
KEYWORDS="Markov process; point process; superposition",
}

@ARTICLE{Cont9103:Interconnection,
AUTHOR="M. Conti and Enrico Gregori and Luniano Lenzini and F. Grandoni
and L. Strigini",
TITLE="Interconnection of Dual Bus {MANs;} Architecture and Algorithms
for Bandwidth Allocation",
JOURNAL=internet,
VOLUME=2,
NUMBER=1,
PAGES="133-156",
MONTH=mar,
YEAR=1991,
KEYWORDS="MAC FASNET DQDB integrated services MAN XMAN bandwidth
reservation bandwidth allocation delay variance (jitter) network
performance evaluation simulation",
ABSTRACT="Metropolitan area networks (MANs) have the potential to be
interconnected in such a way that the resulting wider, composite
network--subsequently referred to as the extended MAN (XMAN) or simply
the network--still preserves the characteristics of the underlying
encompassed MANs. This means that, if the individual MANs are capable of
managing integrated services such as video, voice and data, the XMAN
will also have this potential. Techniques borrowed from conventional
packet switching technology (ISO 8648, for instance) requiring the use
of a common internetwork protocol and time-consuming error recovery and
flow control mechanisms, cannot be used to realize this capability. To
overcome this problem a bandwidth management algorithm has been devised.
The technical feasibility of the overall interconnection architecture is
explored, and performance figures are obtained.",
}

@INPROCEEDINGS{Shep9103:Application,
AUTHOR="D. Shepherd",
TITLE="An Application Platform for Distributed Multimedia Conferencing",
BOOKTITLE="TINA Worshop",
ADDRESS="Chantilly, France",
MONTH=mar,
YEAR=1991,
}

@TECHREPORT{Bier9103:Overview,
AUTHOR="Biersak and I. W. Cotton and David C. Feldmeier and Anthony
McAuley",
TITLE="An Overview of the {TP++} Transport Protocol Project",
INSTITUTION="Bellcore",
MONTH=mar,
YEAR=1991,
KEYWORDS="Transport Protocol; TP++",
ABSTRACT="Explains some of the rationale for the design of a multimedia
transport protocol that is to run over ATM.",
}

@TECHREPORT{Wild9103:Dynamics,
AUTHOR="R. P. Wilder and  Ramakrishan and Allison Mankin",
TITLE="Dynamics of Congestion Control and Avoidance of Two-Way Traffic
in an {OSI} Testbed",
INSTITUTION="MITRE",
MONTH=mar,
YEAR=1991,
KEYWORDS="Congestion Control; Dynamics",
ABSTRACT="Experiments on two way dynamics of TP4 with Cute in the
gateways on a real testbed.",
}

@INPROCEEDINGS{Wake9103:Emerging,
AUTHOR="Ian Wakeman",
TITLE="Emerging High Speed Transfer Protocols",
BOOKTITLE="3rd IEE Conference on Telecommunications",
PUBLISHER="IEE",
ADDRESS="Edinburgh",
MONTH=mar,
YEAR=1991,
KEYWORDS="XTP TCP Transport",
}

@TECHREPORT{Esco9103:Multi,
AUTHOR="J. Escobar and D. P. Deutsch and C. Partridge",
TITLE="A Multi-Service Flow Synchronisation Protocol",
TYPE="BBN STC Tech Report",
INSTITUTION="BBN",
ADDRESS="Cambridge, Mass",
MONTH=mar,
YEAR=1991,
KEYWORDS="multi media synch flow protocol",
}

@TECHREPORT{Govi9103:Scheduling,
AUTHOR="Ramesh. Govindan and D. P. Anderson",
TITLE="Scheduling and {IPC} Mechanisms for Continuous Media",
TYPE="Technical Report",
INSTITUTION="University of California at Berkeley",
ADDRESS="Berkeley, California",
NUMBER="CSD-91-622",
PAGES=26,
MONTH=mar,
YEAR=1991,
KEYWORDS="continuous media; multimedia; operating systems",
ABSTRACT="Next-generation workstations will have hardware support for
digital ``contiuous media'' (CM) such as audio and video. CM
applications handle data at high rates, with strict timing requirements,
and often in small ``chunks''.  If such applications are to run
efficiently and predictably as user-level programs, an operating system
must provide scheduling and IPC mechanisms that reflect those needs.  We
propose two such mechanisms: split-level CPU scheduling of lightweight
processes in multiple address spaces, and memory-mapped streams for data
movement between address spaces.  These techniques reduce the number of
user/kernel interactions (system calls, signals, and preemptions). 
Compared with existing mechanisms, they can reduce scheduling and I/O
overhead by a factor of 4 to 6.",
URL="ftp://tr-ftp.cs.berkeley.edu/pub/tech-reports/csd/csd-91-622",
}

@TECHREPORT{Gree9103:Behavior,
AUTHOR="Reuven Greenberg",
TITLE="Behavior Description and Safety in Real Time Models",
TYPE="Technical Report",
INSTITUTION="University of California, Irvine, Department of Information
and Computer Science",
NUMBER="ICS-TR-91-21",
PAGES=71,
MONTH=mar,
YEAR=1991,
ABSTRACT="This paper includes a survey on some modern methods that are
used for describing and analyzing behavior of complex systems. It is
believed that most safety problems arise in the interface between the
controlling parts and other controlled subsystems. Therefore, a
prerequisite for a good interface is an accurate definition of the
system. Two objectives are evaluated: the description power and the
analysis power for safety and timing properties. This is done by
describing and analyzing a simple system that is composed of two doors,
which are restricted by time and ``safety'' requirements. It is found
that although good description methods do exist, their usefulness for
analyzing safety timed properties is very limited.",
}

@TECHREPORT{Godb9103:Station,
AUTHOR="Kenneth A. Godbille and H. Huang and T. Suda",
TITLE="Implementation of a Station/Network Interface for a {CAMB} Tree
Network",
TYPE="Technical Report",
INSTITUTION="University of California, Irvine, Department of Information
and Computer Science",
NUMBER="ICS-TR-91-26",
PAGES=26,
MONTH=mar,
YEAR=1991,
ABSTRACT="Packet collisions and their resolution create a performance
bottleneck in random-access LANs. A hardware solution to this problem is
to use collision avoidance switches. These switches allow the
implementation of random access protocols without the penalty of
collisions among packets. An architecture based on collision avoidance
is the CAMB (Collision Avoidance Multiple Broadcast) tree network, where
concurrent broadcasts are possible. This paper is a companion to an
earlier report. ``TTL Implementations of a CAMB Tree Switch.'' where a
tree network architecture was described for two different
implementations of a CAMB tree switch. In the pages that follow, a
hardware implementation of the interface between the network stations
and the packet switches is proposed. This implementation is based on the
first switch design in the companion paper.",
}

@TECHREPORT{Huan9103:TTL,
AUTHOR="H. Huang and Kenneth A. Godbille and T. Suda",
TITLE="{TTL} Implementation of a {CAMB} Tree Network Switch",
TYPE="Technical Report",
INSTITUTION="University of California, Irvine, Department of Information
and Computer Science",
NUMBER="ICS-TR-91-25",
PAGES=27,
MONTH=mar,
YEAR=1991,
ABSTRACT="Packet collisions and their resolution create a performance
bottleneck in random-access LANs. A hardware solution to this problem is
to use a collision avoidance switch. These switches allow the
implementation of random access protocols without the penalty of
collisions among packets. An architecture based on collision avoidance
is the CAMB (Collision Avoidance Multiple Broadcast) Tree network, where
concurrent broadcasts are possible. The purpose of this paper is to
present two implementations for a CAMB Tree switch. First a general
outline of the CAMB switch is provided. Then, a description of the two
implementations is given.",
}

@TECHREPORT{Horn9103:Objektbasierte,
AUTHOR="Uwe Horn",
TITLE="Objektbasierte Repräsentation der Dialogschicht von
Mensch-Computer-Schnittstellen als Grundlage adaptiver
Systemleistungen",
TYPE="Arbeitspapiere der GMD",
INSTITUTION="GMD Forschungszentrum Informationstechnik",
ADDRESS="Birlinghoven, Germany",
NUMBER=519,
NOTE="Diplomarbeit",
MONTH=mar,
YEAR=1991,
KEYWORDS="man-machine interface; HCI",
}

@ARTICLE{Milo9103:Multicast,
AUTHOR="Amir Milo and Ouri Wolfson",
TITLE="The multicast policy and its relationship to replicated data
placement",
JOURNAL=tods,
VOLUME=15,
NUMBER=1,
PAGES="181-206",
MONTH=mar,
YEAR=1991,
}

@INPROCEEDINGS{Danz9103:Distributed,
AUTHOR="Peter Danzig and Jong Suk Ahn and J. Noll and K. Obraczka",
TITLE="Distributed Indexing: A technique for scalable, distributed
information retrieval systems",
BOOKTITLE="ACM SIGIR",
PAGES="220-229",
MONTH=mar,
YEAR=1991,
}

@ARTICLE{Poo9103:OS,
AUTHOR="G. S. Poo and Boon-Ping Chai",
TITLE="{OS/2} driver software design for an Ethernet adapter",
JOURNAL=comcom,
VOLUME=14,
NUMBER=2,
PAGES="80-93",
MONTH=mar,
YEAR=1991,
KEYWORDS="OS/2; ethernet; driver; performance",
}

@ARTICLE{Tjad9103:Integrated,
AUTHOR="G Tjaden and M. Wall and J. Goldman and C. N. Jeromnimon",
TITLE="Integrated Network Management for Real-Time Operations",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=2,
PAGES="10-15",
MONTH=mar,
YEAR=1991,
REFERENCES=2,
ABSTRACT="Management of the real-time operation of large hybrid networks
is extremely difficult. Network managers badly need the capability to
seamlessly view and control their entire network. Today's tools provide
management capability only for individual subnetworks. The most
prominent approaches to providing an integrated network management
capability depend on network element suppliers conforming to particular
network management interface protocol-- Common Management Information
Protocol (CMIP), Simple Network Management Protocol (SNMP), Netview PC,
and UNMA/Network Management Protocol (NMP). This article describes an
approach to integrated network management that eliminates the need for
interface protocol conformance and provides applications taht seamlessly
isolate and resolve faults in the entire network. The approach uses
off-the-shelf artificial intelligence tools and open-architecture
client/server workstation technology.",
}

@ARTICLE{Klei9103:Operations,
AUTHOR="W. Klein",
TITLE="Operations and Management of a Campus Packet Network",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=2,
PAGES="16-22",
MONTH=mar,
YEAR=1991,
}

@ARTICLE{Jida9103:Traffic,
AUTHOR="S. Jidarian and D. M. Shapiro",
TITLE="Traffic Administration and Engineering of a Corporate Wide Area
Network",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=2,
PAGES="24-29",
MONTH=mar,
YEAR=1991,
REFERENCES=6,
ABSTRACT="In this article, we describe the development of a traffic
engineering and administration software system planned for use in
administering a private AT\&T Corporate Wide Area Network (CWAN). The
traffic administration system discussed here is intended to aid network
administrators in periodically, e. g., weekly, engineering the CWAN. The
objective of this ongoing engineering process is to minimize network
facilities and equipment expenditures while providing acceptable
performance levels to network end users proactively. In the first half
of this article, we describe the CWAN network and review the CWAN
network management and traffic administration approach used during the
network deployment and in the mature network. In the second half, we
describe the CWAN Traffic Administration System (CTAS), an automated
system that implements this CWAN traffic engineering and administation
approach.",
}

@ARTICLE{Simo9103:Peer,
AUTHOR="S. Simon",
TITLE="Peer-to-Peer Network Management in an {IBM} {SNA} network",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=2,
PAGES="30-34",
MONTH=mar,
YEAR=1991,
ABSTRACT="IBM's Systems Network Architecture (SNA) peer-to-peer
communication, called Low Entry Networking (LEN), will introduce many
benefits along with a number of challenges in managing an SNA network.
Prior to LEN, all host communication were hierarchical. LEN allows nodes
like Personal Computers (PCs), AS400, and host applications to
communicate wtih each other through the subarea network as peers. LEN
nodes can enable cooperative processing, initiate parallel and multiple
session simultaneously, require less prodefinition, and use a common LU
6.2 interface. LEN management will need to deal with the challenges of
decentralized processing, changes to management definitions, and dynamic
session initiation. This article will cover these challenges as they
impact network management in an IBM subarea network. Research was
conducted in the The Traveler's Network to determine impacts in the
areas of installation, session management, problem determination,
accouting, and performance.",
}

@ARTICLE{Dupu9103:NETMATE,
AUTHOR="A. Dupuy and S. Sengupta and Ouri Wolfson and Y. Yemini",
TITLE="{NETMATE:} A Network Management Environment",
JOURNAL=ieeenet,
VOLUME=5,
NUMBER=2,
PAGES="35-43",
MONTH=mar,
YEAR=1991,
REFERENCES=6,
ABSTRACT="As computer networks become larger (often involving thousands
of elements), more heterogeneous (supporting a variety of devices and
protocols), and more complex (involving subtle interactions and
relationships among components), the importance of network management
for large-scale systems increases. For the network to be the information
highway for an enterprise, there must exist effective management tools
to ensure smooth and efficient operation. A typical enterprise-wide
network is managed today by a set of nonintegrated tools, each of which
has a partial and incomplete view of the network and its management
needs. This leads to significant difficulties in accomplishing effective
management (see [1] for sample problems). The prime goal of the Network
Management, Analysis , and Testing Environment (NETMATE) project is to
develop a unified and comprehensive software environment for network
management to oversee and orchestrate the operations of diverse devices
and protocols.",
}

@INPROCEEDINGS{Acam9104:Multihop,
AUTHOR="A. S. Acampora and S. H. Shah",
TITLE="Multihop lightwave networks: a comparison of store-and-forward
and hot-potato routing",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="10-19 (2A.2)",
MONTH=apr,
YEAR=1991,
KEYWORDS="Routing",
ABSTRACT="Multihop networks with store-and-forward nodes were recently
proposed and studied as possible architectures for realizing the vast
capacity potential of multi-user lightwave networks subject to
electro-optic speed constraints imposed at each access node. In this
paper, we analytically determine the achievable aggregate capacity for a
variant of the basic multihop approach in which minimum distance
store-and-forward routing is replaced by a ``hot-potato'' routing
algorithm. With hot-potato routing, all packets simultaneously arriving
at a given node and not intended for reception at that node are
immediately placed onto the outbound links leaving that node; if two or
more packets contend for the same outgoing link to achieve minimum
distance routing, then all but one will be misrouted to links which
produce longer paths to the eventual destination. Our interest is in
studying such a scheme arises from the potential of optical pulse
generation techniques to permit the formation of optical packets at data
rates too high to permit electro-optic conversion, electronic packet
routing, and store-and-forward buffering at each node. While not
avoiding the electro-optic bottleneck for network access, each optical
link would operate at super-electronic data rate and contain time
multiplexed packets from a multitude of sources. --- We confine our
attention to the development of an analytical methodology for finding
the probability distribution of the number of hops with hot potato
routing for symmetric networks under uniform traffic load. From this,
the expected number of hops and the aggregate network capacity can be
found. Results show that the maximum throughput achievable can be as low
as 25\% of that for store-and-forward routing, and that the relative
degradation increases as the number of nodes grows larger. This implies
that the link speed-up needed to produce a significant overall capacity
advantage with hot potato should be at least a factor of 10. The
analytical methodology and results are quite general and applicability
is not limited to lightwave networks.",
}

@ARTICLE{Ahre9104:Design,
AUTHOR="K. Ahrens and J. Fischer and E. Holz and I. Schieferdecker",
TITLE="Design and Analysis of Formal Specifications with the
{SDL-Machine}",
JOURNAL="Systems Analysis, Modelling and Simulation",
VOLUME=8,
NUMBER="4/5",
PAGES="327-342",
MONTH=apr,
YEAR=1991,
ABSTRACT="The program system SDL-machine outlined in this paper aims at
supporting the correct design of complex and complicated distributed
software as in the telecommunication domain. SDL-machine primarily
supports the design-accompanied analysis of systems specified in the
standardized formal specification language SDL.  This is achieved by
deriving a prototype implementation from a given specification which is
applicable to simulative test.  The SDL-machine consists in its core of
a graphical editor (supporting various design levels), a compiler
(generating optionally C-code for simulation, petri net analysis and
virtual target execution), a run time system for simulative execution of
SDL-specifications, and a database interface supporting experiment
observation and evaluation). SDL-machine is available for MS-DOS and
UNIX.",
}

@INPROCEEDINGS{Akyi9104:General,
AUTHOR="Ian Akyildiz and Wen-Zu Liu",
TITLE="A General Analysis Technique for {ARQ} Protocol Performance in
High Speed Networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="498-507 (5C.4)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory; error control; ARQ protocol; high speed
networks; queueing networks; extended finite state machine model;
performance measures",
ABSTRACT="The general behavior of the ARQ protocols is modeled by a
queueing network with priorities representing the erroneous and recovery
processes. A mean value analysis algorithm is developed for the
performance analysis of the model. The input parameters, the erroneous
period and the recovery duration, for the model are gained from the
extended finite state machine model description of the protocols. By
giving several examples, the authors have demonstrated the general
applicability of the new approach.",
}

@ARTICLE{Atwa9104:Optimal,
AUTHOR="Geert A. Atwater and Frederik Carel Schoute",
TITLE="Optimal queueing policies for fast packet switching of mixed
traffic",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="458-467",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="The power of ATM (asynchronous transfer mode) is its ability
to provide bandwidth on demand: different sources can have different
bandwidth requirements. Sources also differ in performance requirements:
some ask for minimal delay variations whereas others must have extremely
low cell loss probabilities. This paper shows how these complementary
performance requirements can be exploited with an LDOLL (low delay or
low loss) queue, where sources get either service priority or storage
priority. The space of possible LDOLL queueing policies is very large:
even after a justified reduction, the size is still of order
{$O(2^{Q^2})$}, $Q$ being the maximum number of ATM cells in the LDOLL
queue. Using Markov decision theory and concepts of linear programming,
we arrive at only $Q$ so-called efficient solutions. These are the LDOLL
threshold policies, which are conceptually appealing, robust in
performance, and practical from the implementation standpoint.",
}

@ARTICLE{Baio9104:Loss,
AUTHOR="A. Baiocchi and Nicola Blefari Melazzi and M. Listanti and A.
Roveri and R. Winkler",
TITLE="Loss performance analysis of an {ATM} multiplexer loaded with
high-speed on-off sources",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="388-393",
MONTH=apr,
YEAR=1991,
KEYWORDS="Queueing theory",
ABSTRACT="In this paper, we study the performance of an ATM multiplexer,
whose input consists of the superposition of a multiplicity of
homogeneous on-off sources modeled by a two-state Markovian process. Our
approach is based on the approximation of the actual input process by
means of a suitably chosen two-state Markov modulated Poisson process
(MMPP), as a simple and effective choice for the representation of
superposition arrival streams. To evaluate the cell loss performance, we
have developed a new matching procedure, which leads to accurate results
as compared to simulation. The application limits of the proposed method
are also discussed. Moreover, the outstanding physical meaning of our
procedure lets us gain deep insight into the multiplexer performance
behavior as the source parameters and the multiplexer buffer size are
varied.",
}

@INPROCEEDINGS{Baio9104:Modeling,
AUTHOR="A. Baiocchi and Nicola Blefari Melazzi and M. Listanti and A.
Roveri and R. Winkler",
TITLE="Modeling issues on an {ATM} multiplexer within a bursty traffic
environment",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="83-91 (2C.2)",
MONTH=apr,
YEAR=1991,
KEYWORDS="Queueing theory",
ABSTRACT="In this paper we study the loss performance of an ATM
multiplexer, whose input consists of the superposition of a multiplicity
of homogeneous on-off sources. Our approach is based on the
approximation of the actual input process by means of a suitably chosen
two-state Markov modulated Poisson process (MMPP), as a simple and
effective choice for the representation of superposition arrival
streams. To accurately evaluate the cell loss performance, we have
developed a new matching procedure, which allows the derivation of a
tight upper bound of the cell loss probability and the characterization
of its asymptotic behavior as the buffer size increases. Moreover, the
outstanding physical meaning of our procedure let us gain deep insight
into the multiplexer performance behavior, as the buffer size and the
source parameters are varied and clarifies the modeling limits implied
by the choice of an approximating MMPP with only two states.",
}

@INPROCEEDINGS{Bern9104:ATM,
AUTHOR="F. Bernabei and Roberto Ferretti and M. Listanti and Giuseppe
Zingrillo",
TITLE="{ATM} system buffer design under very low cell loss probability
constraints",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="929-938 (8C.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="This paper deals with a general method for buffer design in an
ATM system in which the target loss probability should be very low
(e.g., less than $10^{-9}$). This method is based on the application of
the Generalized Extreme Value Theory (GEVT) on results arising from
simulation runs. This theory allows the estimation of very small
probabilities which would not be evaluable with traditional Montecarlo
approaches. An advantage of 4 to 5 decades with respect to Montecarlo
limits can be obtained utilizing the same sample set. The extension of
the theory to the case of distribution functions of discrete random
variables is here discussed. The applicability of the method is here
demonstrated with reference to known probability distributions
(exponential, normal, Weibull, hyperexponential, geometric, Bernoulli
and Poisson). Moreover, the GEVT is applied to the cases of classical
queueing systems, i.e., M/D/1, Geo/D/1 and MMPP/D/1. Finally, the
general criteria for the evaluation of the basic GEVT parameters are
discussed.",
}

@ARTICLE{LeBo9104:Efficient,
AUTHOR="Jean-Yves Le Boudec",
TITLE="An efficient solution method for Markov models of {ATM} links
with loss priorities",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="408-417",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory; ATM; priority; CLP (cell loss priority);
buffer modeling; Markov-modulated; cell level model for superposed
sources; Markov chain with block-Hessenberg transition matrix; layered
coding for video",
ABSTRACT="We consider a broadband network using the asynchronous
transfer mode (ATM), where loss priorities are used. With the loss
priority scheme, cells of low-priority classes are accepted only if the
instantaneous buffer queue length at the cell arrival epoch is below a
given threshold. We propose algorithms to solve for the cell loss rates,
and model the input by Markov-modulated Bernoulli processes. Finally, we
investigate the effect of the loss priority scheme on data, voice, and
video traffic.",
}

@ARTICLE{Butt9104:Effectiveness,
AUTHOR="M. Butto and E. Cavallero and A. Tonietti",
TITLE="Effectiveness of the ``leaky bucket'' policing mechanism in {ATM}
networks",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="335-342",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control; leaky bucket",
ABSTRACT="This paper presents an analysis of the performance of the
``leaky bucket,'' a device proposed for controlling the source traffic
parameters of an ATM network (policing function). The most critical
situation, i.e., an on/off bursty sources, is assumed. Moreover, the
delay jitter introduced by a possible multiplexing of sources inside the
customer premises is not considered. The leaky bucket can be analyzed as
a G/D/1/N queue with finite waiting room $N$ and a suitable arrival
process. But the complexity of the arrival pattern brings only to
numberical solutions for the system performance. An alternative approach
is presented in the paper: the ``fluid flow'' approximation, by which
the bit flow is considered as a continuous variable. By comparison with
the exact model, it is shown that the accuracy of the fluid flow
approach can be considered sufficient for practical purposes. Following
the fluid flow approximation, an explicit formula for the cell loss
probability, in case of exponential distributions for both the burst
duration and the inactivity period of the source, is derived. On the
basis of that formula, some numerical evaluations with the aim of
assessing the effectiveness of the leaky bucket mechanism are presented.
Two approaches are investigated. The first approach considers the
selectivity characteristics of the leaky bucket, i.e., the efficacy of
the device in detecting a critical source behavior. According to the
second approach, the leaky bucket is regarded as a device filtering the
traffic offered by the source and allowing to load the network with a
controlled flow. The conclusions are that, while the leaky bucket can
easily control the peak rate, difficulties arise in controlling the mean
rate (because of the long time required) and the burst duration (because
of the poor selectivity).",
}

@INPROCEEDINGS{Chan9104:Integrated,
AUTHOR="C. J. Chang and Stephen Wang",
TITLE="Performance analysis of integrated multiplexer in the customer
premise node of broadband integrated services network",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="76-82 (2C.1)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="An integrated multiplexer in the customer premise node of
broadband integrated services network is analyzed. This multiplexer is
assumed to have wideband (WB) and narrowband (NB) customers, where the
arrival process for the former is modeled as a single birth-death
Markovian chain and that of the latter is modeled as an independent
Poisson. Each NB customer needs a single server for service while each
WB customer needs more than one servers; both of their service times are
the same and constant. Higher access priority is given to WB customers.
To protect the NB service quality, a cutoff parameter $r\_1$, which
denotes the maximum number of WB customers simultaneously served in one
slot, is provided. Performance measures including queue length
distribution, blocking probability, and mean waiting time are
obtained.",
}

@ARTICLE{Chen9104:Throughput,
AUTHOR="Jinghu Chen and T. E. Stern",
TITLE="Throughput analysis, optimal buffer allocation, and traffic
imbalance study of a generic nonblocking packet switch",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="439-449",
MONTH=apr,
YEAR=1991,
KEYWORDS="fast packet switches",
ABSTRACT="This paper provides a general model to study the performance
of a family of space-domain packet switches, implementing both input and
output queueing and varying degrees of speedup. Based on this model, the
impact of the speedup factor on the switch performance is analyzed. In
particular, the maximum switch throughput and the average system delay
for any given degree of speedup are obtained. The results demonstrate
that the switch can achieve 99\% throughput with a modest speedup factor
of 4. Packet blocking probability for systems with finite buffers can
also be derived from this model and the impact of buffer allocation on
blocking probability is investigated. Given a fixed buffer budget, this
analysis obtains an optimal placement of buffers among input and output
ports to minimize the blocking probability. The model is also extended
to cover a nonhomogeneous system where traffic intensity at each input
varies and destination distribution is not uniform. Using this model,
the impact of traffic imbalance on the maximum switch throughput is
studied. It is seen that input imbalance has a more adverse effect on
throughput than output imbalance. It is also observed that, under the
same input imbalance conditions, the throughput reduction is more
significant for switches with higher speedup, while, under the same
output imbalance conditions, this trend is reversed.",
}

@INPROCEEDINGS{Choi9104:Overall,
AUTHOR="J.-K. Choi and M. H. Choi and T. S. Chung and Y. S. Shin and
Kyu-han Kim",
TITLE="Overall design requirements of broadband {ATM} networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="352-357 (4B.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="BISDN",
ABSTRACT="We investigate the overall design issues for broadband ATM
networks. Three kinds of network design requirements are considered:
user grade-of-service (GOS) requirements, network manager requirements,
and system designer requirements. In this work, we are focusing on the
balancing problems among performance measures. We suggest that the
design parameters for broadband ATM exchange would be tuned within the
acceptable sets by the layering concept on performance objectives.",
}

@INPROCEEDINGS{Chow9104:Distribution,
AUTHOR="Shyamal Chowdhury",
TITLE="Distribution of the total delay of packets in virtual circuits",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="911-918 (8C.1)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="In some computer network architectures a process communicates
with another process across the network by establishing a virtual
circuit. Consider a virtual circuit from node $S$ to node $D$ connected
by multiple links. The delay suffered by the packets of the virtual
circuit has three components: waiting time or queueing delay, service
time or transmission delay, and resequencing delay. The sum of these is
called the total delay. This paper presents the distribution of the
total delay for three different queueing models of node S: $G/M/m$
model, $G/M/\infty$ model and $M/H\_k/\infty$ model.",
}

@INPROCEEDINGS{Deci9104:Bandwidth,
AUTHOR="Maurizio D`ecina and L. Faglia and T. Toniatti",
TITLE="Bandwidth allocation and selective discarding for variable bit
rate video and bursty data calls in {ATM} networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="1386-1393 (12A.2)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="Congestion control mechanisms are required in ATM networks to
fairly and efficiently allocate network resources to the various service
types. Bandwidth assignment is a preventive control mechanism. On the
basis of the traffic description given by the source, of the traffic
load along the connection route and of the cell performance
requirements, this mechanism gives a criterion to accept or reject a
virtual connection request. A bandwidth called 'equivalent bandwidth' is
allocated in order to ensure the cell transport objectives. This paper
proposes a definition of equivalent bandwidth for stream, bursty data
and variable bit rate video sources (VBRV). The equivalent bandwidth
values are evaluated by simulation considering both homogeneous and
heterogeneous sources. In the heterogeneous mixes with different cell
loss probability requirements the selective discarding mechanism permits
a more efficient utilization of the network resources.",
}

@INPROCEEDINGS{Deci9104:Shuffle,
AUTHOR="Maurizio D`ecina and P. Giacomazzi and Achille Pattavina",
TITLE="Shuffle Interconnection Networks with Deflection Routing for
{ATM} Switching: the closed-loop shuffleout",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="1254-1263 (11A.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="fast packet switching",
ABSTRACT="A new class of switching architectures for broadband packet
networks, called shuffleout, is introduced in this paper. Its
interconnection network is a multistage structure built out of
unbuffered 2 $\times$ 4 switching elements. Shuffleout is basically an
output-queued architecture in which the number of cells that can be
concurrently switched from the inlets to each output queue equals the
number of stages in the interconnection network. The switching element
operates the cell self-routing adopting a shortest-path algorithm which,
in case of conflict for interstage links, is coupled with deflection
routing. The architecture presented here is called closed-loop
shuffleout, since the cells that cross the whole interconnection network
without entering the addressed output queues are lost. A different
version of this architecture, called open-loop shuffleout is described
in a companion paper. The key target of the proposed architecture is
coupling the implementation feasibility of a self-routing switch with
the desirable traffic performance typical of output queueing.",
ANNOTE="see \cite{Toba9104:Tandem}",
}

@ARTICLE{Desc9104:Stochastic,
AUTHOR="A. Descloux",
TITLE="Stochastic models for {ATM} switching networks",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="450-457",
MONTH=apr,
YEAR=1991,
KEYWORDS="fast packet switches",
ABSTRACT="It is widely recognized that the input streams to cell
switching networks cannot, in general, be adequately modeled as Poisson
point processes. The fact that the traffic passing through such systems
often displays marked burstiness must be taken into account, and many
contributions are concerned with the practical and analytical
consequences of the resulting dependencies between the cell interarrival
times. The models considered in this paper include yet another feature
that is usually ignored, namely that the switching speed may be
appreciably greater than the speed at which some sources generate their
respective cells. It is therefore important, as we do here, to
investigate the situation where the cells making up individual bursts
are spaced according to some prescribed probability distribution. The
purpose of this paper is to show that the switch performance is strongly
dependent on the input parameters and, at the same time, to demonstrate
that analytical approaches provide useful alternatives to the lengthy
simulation runs needed to evaluate probabilities of rare events such as
cell losses.",
}

@INPROCEEDINGS{Digh9104:Congestion,
AUTHOR="R. S. Dighe and C. J. May and G. Ramamurthy",
TITLE="Congestion avoidance strategies in broadband packet networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="295-303 (4A.1)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="The information network of the future presents a set of
interesting technical challenges. In this paper, we examine the
networking environment of the future, pose the technical questions that
need to be addressed to provide service assurance, and propose a set of
strategies for congestion avoidance. Congestion avoidance is recommended
instead of congestion control (which has very limited value in a
high-speed network, where the latency in detecting congestion and
reacting to it may make the control ineffective). The congestion
avoidance strategies proposed here obey the following ground rules: 1)
They are myopic in the sense that local problems are tackled locally. 2)
They are conservative in the sense that they are aimed at bounding tail
probabilities of delay distributions and minimizing packet losses due to
buffer overflows. The proposed solution consists of enforcing
rate-control at the network edges, bandwidth reservation for continuous
bit oriented (CBO) traffic using a unique 2-queue strategy, and a
scheduler-based packet cross connect system. Simulation results of a Q+
model of an access node are presented that quantify the performance of
this solution and compare it to existing control mechanisms. The results
effectively demonstrate that it is possible to meet the differing needs
of traffic types needing datagram service and those needing
virtual-circuit transport by using an intelligent scheduling strategy
and a meaningful packet transport protocol.",
}

@ARTICLE{Ditt9104:Flow,
AUTHOR="Lars Dittmann and S. B. Jacobsen and K. Moth",
TITLE="Flow enforcement algorithms for {ATM} networks",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="343-350",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control; leaky bucket; sliding window",
ABSTRACT="This paper characterizes four measurement algorithms for flow
enforcement in ATM networks. The algorithms are the leaky bucket, the
rectangular sliding window, the triangular sliding window and the
exponentially weighted moving average. A comparison, based partly on
teletraffic theory and partly on signal processing theory, is carried
out. It is suggested to use the RMS measurement bandwidth to dimension
linear algorithms for equal flow enforcement characteristics.
Implementations are proposed on the block diagram level, and
dimensioning examples are carried out when flow enforcing a renewal-type
connection using the four algorithms. The corresponding hardware demands
are estimated and compared.",
}

@ARTICLE{Dron9104:Delay,
AUTHOR="Lisa G. Dron and G. Ramamurthy and B. Sengupta",
TITLE="Delay analysis of continuous bit rate traffic over an {ATM}
network",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="402-407",
MONTH=apr,
YEAR=1991,
KEYWORDS="discrete time queue",
ABSTRACT="In this paper, we model a packet multiplexer for continuous
bit rate (CBR) traffic in an ATM network as an $nD/D/1$ queue. We
compare the efficiency of various algorithms for finding the delay
distribution. In particular, we propose a new algorithm whose time
complexity is $O(n^2)$ where $n$ is the number of voice sources being
multiplexed. Further, the use of the central limit theorem can reduce
the time complexity to $O(n)$ for large $n$. We find an asymptotic
formula whose time complexity is independent of $n$ and it works well
(for practical purposes) over a wide range of parameter values. We
examine and comment on the use of the $M/D/1$ results as an
approximation. In addition to comparing the performance of these
algorithms, we show that the buffer requirements for such a queue are
significantly less than the theoretical maximum (even when the
requirement on the call disruption probability is very low). This result
has important implications in the design of buffer size. Further, the
buffer requirement is relatively insensitive to the design criterion
(call disruption probability) so that inaccuracies in measurements
and/or traffic forecasts will not lead to erroneous design.",
}

@INPROCEEDINGS{Ferr9104:Admission,
AUTHOR="Josep M. Ferrandiz and Aurel A. Lazar",
TITLE="Admission Control for Real-Time Packet Sessions",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="553-559 (6A.2)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="In a real-time session packets are lost by buffer overflow or
because their delay deadline is not met. When a packet delay deadline is
not met we say that it is clipped. The quality of a real-time session is
measured by the individual packet loss and by the average packet gap. We
model the aggregated packet arrival process of a real-time session to
the access node by a Markov modulated point processes. A new session
will be accepted at a network access point if the quality of all
sessions already in progress can be guaranteed as negotiated at call set
up time and if the node can provide an adequate service to the new user.
We show that there exists a switching surface for the optimum admission
policy and that the admission decision can be based on the session
arrival rates if two conjectures on the stochastic ordering properties
of Markov modulated processes hold. The conjectures are satisfied for
Poisson processes.",
}

@INPROCEEDINGS{Ferr9104:Rate,
AUTHOR="Josep M. Ferrandiz and Aurel A. Lazar",
TITLE="Rate conservation analysis of the multiclass {$M/G/1/B$} queue",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="1475-1480 (12C.4)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="The authors study packet blocking in the multiclass $M/GI/1/B$
queueing system by rate conservation methods. It is assumed that two
classes of traffic are accessing the queue. Recursive formulas for the
packet loss probability and conditional probability of consecutive
blocking for class one traffic are obtained, with the other class
modeling the background traffic. The latter characterizes the
distribution of the number of consecutively class one packets blocked.
The authors show that these quantities depend essentially on the joint
distribution of the queue length and the residual service time. This
joint distribution is recursively computed by analyzing, through rate
conservation principles, the embedded queue at arrival times.",
}

@INPROCEEDINGS{Gihr9104:Layered,
AUTHOR="O. Gihr and P. Tran-Gia",
TITLE="A layered description of {ATM} cell traffic streams and
correlation analysis",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="137-144 (2D.4)",
MONTH=apr,
YEAR=1991,
KEYWORDS="discrete time queue",
ABSTRACT="This paper presents an approach to describe traffic processes
in ATM environments. Using a discrete-time Markov chain to describe the
cell process dynamics, we derive an algorithm to calculate the
correlation function of the traffic process. As an example the
correlation properties of the well-known two-state process are
investigated. We use a hierarchical characterization of discrete-time
traffic processes to capture the short-term and the long-term
dependencies of process segments as well as different time scales
according to cell, burst, dialog and call layers of traffic streams in
ATM systems. It is shown by comparison of the process description
techniques using the index of dispersion of count (IDC) and using the
correlation function (CF), that the CF gives significant additional
insight to understand the short- and long-term dependencies of traffic
processes in ATM environments.",
}

@INPROCEEDINGS{Gole9104:Duration,
AUTHOR="S. Jamaloddin Golestani",
TITLE="Duration-Limited Statistical Multiplexing of Delay Sensitive
Traffic in Packet Networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="323-332 (4A.4)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="A new strategy for the transmission and multiplexing of
delay-sensitive traffic, e.g., voice and video, in packet networks is
described. The strategy provides bounded end-to-end delay to all
delay-sensitive traffic and guarantees loss-free transmission to any
traffic with such a requirement. To achieve statistical multiplexing
gain, loss performance is provided to the rest of delay-sensitive
traffic on an as-needed basis, with possible distinction among different
classes. Bounded end-to-end delay is obtained by performing statistical
multiplexing at the switching nodes on a duration-limited basis.
Loss-free transmission is achieved by means of an underlying service
discipline called stop-and-go queueing. The performance of the strategy
for some special cases is analyzed and analytical expressions for the
loss probability are derived.",
ANNOTE="DLSM. Continuation of \cite{Gole9104:Duration}. All classes
delay-bounded; highest-priority has reserved bandwidth, with no loss.
All other priority classes may experience loss at intermediate nodes if
outgoing frame does not have enough capacity. Analysis for two
priorities and no priority; Gaussian assumption on traffic.",
}

@ARTICLE{Grun9104:Characterization,
AUTHOR="Reto Grünenfelder and J. P. Cosmas and Sam Manthorpe and A. C.
Odinma-Okafor",
TITLE="Characterization of video codecs as autoregressive moving average
processes and related queueing system performance",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="284-293",
MONTH=apr,
YEAR=1991,
KEYWORDS="packet video",
ABSTRACT="This paper describes a method of characterizing video codec
sources in ATM networks as an autoregressive moving average process
(ARMA). Measurements of the long-term mean and the autocorrelation
function of cell interarrival times allow the parameter estimation of
the ARMA model. The video source is then described by an ARMA model.
Furthermore, it is shown that the multiplexed stream of video cells is
an ARMA process, too. Such a cell stream is then applied to a model of a
queueing system to obtain performance measures of the system.
Perturbation analysis is then performed on the functional behavior of
the queueing system by appropriate perturbation of the model parameters
to determine cell waiting time sensitivity due to slight variations of
the input process.",
}

@INPROCEEDINGS{Gupt9104:Packet,
AUTHOR="A. Gupta and Nicolaos D. Georganas",
TITLE="Analysis of a Packet Switch with Input and Output Buffers and
Speed Constraints",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="694-700 (7A.2)",
MONTH=apr,
YEAR=1991,
KEYWORDS="fast packet switches",
ABSTRACT="A non-blocking $N \times N$ switch for high speed packet
switching networks is considered. In practice such a switch may operate
$L$ times faster than the input/output trunk. When $1<L<N$, the switch
would require buffers at input as well as output trunks to keep the
packet loss probability and delay within some desirable limits. This
paper analyzes the performance of such a switch for an arbitrary amount
of buffers per output port and speedup factor ($L$). The results show
that for sizable amount of output buffers, the switch with $L=3$ would
perform almost as well as the switch with $L=N$. For moderate loads, the
switch with $L=2$ can also be implemented. The input buffers are sized
according to stringent requirements of packet loss rate.",
}

@INPROCEEDINGS{Haas9104:Congestion,
AUTHOR="Z. Haas and Jack H. Winters",
TITLE="Congestion Control by Adaptive Admission",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="560-569 (6A.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="The authors discuss some issues in congestion control and
describe a novel congestion control scheme for high-speed networks. The
scheme is based on periodic transmission of sample time-stamped packets
through the network. Upon reception, the packet delays are calculated,
averaged, and used to determine the state of the network. The
information on the state of the network is then used to drive the
network admission control. The major advantage of the proposed scheme
over conventional congestion control techniques is that it copes with
traffic surges that are shorter than the network round-trip delay. This
is achieved by controlling traffic admission with continuous estimates
of the network state. The scheme is targeted towards networks that carry
aggregated traffic, and can be applied to ATM-based networks.",
}

@INPROCEEDINGS{Haas9104:Packet,
AUTHOR="Z. Haas and R. D. Gitlin",
TITLE="On the packet size in integrated networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="732-740 (7B.2)",
MONTH=apr,
YEAR=1991,
KEYWORDS="BISDN",
ABSTRACT="This paper addresses the selection of a single packet size for
broadband, integrated packet networks (e.g., BISDN) that carry many
traffic types, each with different performance requirements. To meet the
requirements of different types of traffic in an integrated network (for
example, synchronous stream traffic and delay sensitive bursty traffic,
or two different types of synchronous traffic), the probability
distribution of the end-to-end network delay must be determined. We
provide new insights and procedures for estimating such statistics for
store-and-forward, integrated packet networks that have a single packet
size. In particular, we address two problems: determining the required
build-out delay to achieve a given packet loss probability for real-time
stream traffic (e.g., voice), and determining a packet size that results
in the required delay characteristics for delay sensitive traffic (e.g.,
data for parallel processing applications). The central limit theorem is
used to approximate the probability distribution function for the
end-to-end packet delay in a network of M/D/1 nodes.",
}

@INPROCEEDINGS{Hac9104:Congestion,
AUTHOR="Anna Haç",
TITLE="Congestion control and switch buffer allocation in high-speed
networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="314-322 (4A.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="This paper proposes congestion control and switch buffer
allocation techniques that allow for packet admission and transfer based
on the switch and network occupancy. The packets are transferred if the
required bandwidth is smaller than the bandwidth currently available.
Otherwise, the packets are stored in the buffer. If the buffer is full,
the incoming packets are dropped and the transmission is delayed either
at the sender or at the nearest node. It is proven analytically that the
packets will not be dropped if the buffer size is greater than or equal
to twice the size of queue length and the traffic will not increase
during propagation delay of shut off signal between the switch and
either the source or the nearest node, depending on where the
transmission is delayed. Performance of different networks is evaluated
to show the applications of the proposed techniques.",
}

@ARTICLE{Hash9104:Switched,
AUTHOR="O. Hashida and Yutaka Takahashi and Shinsuke Shimogawa",
TITLE="Switched batch Bernoulli process {(SBBP)} and the discrete-time
{SBBP/G/1} queue with application to statistical multiplexer
performance",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="394-401",
MONTH=apr,
YEAR=1991,
KEYWORDS="discrete time queue",
ABSTRACT="This paper proposes and analyzes a doubly stochastic point
process, a switched batch Bernoulli process (SBBP) as a modeling tool
for bursty and correlated input processes to discrete-time queues
appearing in a recently developed telecommunication network. Through the
investigation of the counting process, statistical characterization
measures of the SBBP are explicitly obtained. A discrete-time
single-server queue with SBBP input and general service time (SBBP/G/1)
is then considered. The SBBP/G/1 queue has potential applicability to a
statistical multiplexer in the network. By using the supplementary
variable technique, the probability generating functions of performance
measures in the SBBP/G/1 queue are obtained. It is shown how the SBBP is
suitable for analyzing a discrete-time queue with bursty and correlated
input.",
}

@INPROCEEDINGS{Holt9104:SONET,
AUTHOR="Rony Holter",
TITLE="{SONET} --- a network management viewpoint",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="130-136 (2D.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="SONET",
ABSTRACT="SONET, synchronous optical networks -- ANSI T1 optical
interface rates and formats specifications, defines feature sets and
functionality for the next generation lightwave transmission systems to
be used in the public telephone networks. This new technology will
provide three major benefits to the network for future applications;
i.e., optical midspan meet, flexible bandwidth for future services, and
extensive network management features. The importance and priority of
each of the three major benefits has changed with the evolution of the
SONET specification and the understanding of the standard itself. The
midspan meet benefit allows consistent multivendor product evaluations
while flexible bandwidth features can be demonstrated by applying format
and mapping options to new service offerings. Unlike the two other
benefits, the extensive network management features reside in the SONET
architecture and must be understood as applied to the existing
transmission network and its operations support systems.",
}

@INPROCEEDINGS{Kani9104:Stability,
AUTHOR="Jaidev Kaniyil and Y. Onozato and Ken Katayama and S. Noguchi",
TITLE="Performance and stability aspects of congestion control by input
buffer limiting in store and forward networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="92-100 (2C.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="This paper presents the performance estimation and the
stability aspects of input buffer limiting (IBL) scheme. The model is
formulated with respect to the state dependent effective input rate and
effective service rate. The computation of the performance parameters
with respect to the effective service rate yields satisfactory results
when blocking probabilities are not restricted to very low values ($\ll
1$). The stability aspects are assessed with the results from
catastrophe theory: the stability is characterized as fold catastrophe.
It is seen that, at higher rates of input, this maximum value of IBL
ratio approaches the capacity law limit proposed by Lam and Reiser.
Further, this method also approximately indicates the no-congestion
region.",
}

@INPROCEEDINGS{Kham9104:Discrete,
AUTHOR="Asad Khamisy and Sidi Moshe",
TITLE="Discrete-time priority queueing system with two-state Markov
modulated arrival processes",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="1456-1463 (12C.2)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="A class of discrete-time priority queueing systems with Markov
modulated arrivals is considered. In these systems, $N$ queues are
served by a single server according to priorities that are preassigned
to the queues. Packet arrivals are modeled as discrete-time batch
processes with a distribution that depends on the state of an
independent common two-state Markov chain. This allows to cover a wide
range of applications in computer and communications systems when the
parameters of the arrival processes are not fixed in time, but vary
according to the state of the underlying Markov chain. The authors
derive the steady-state joint generating functions of the queue length
distributions of this class of systems. From the latter, moments of the
queue lengths as well as average time delays can be obtained. A
numerical example provides some insight into the behavior of such
systems. Also, the effect of the transition rate between the states of
the modulating Markov chain on the average time delays in the system is
investigated for different patterns of loads on the queues of the
system.",
}

@ARTICLE{Kron9104:Priority,
AUTHOR="Hans Kröner and Gérard Hebuterne and P. Boyer and A. Gravey",
TITLE="Priority management in {ATM} switching nodes",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="418-427",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control; space priority",
ABSTRACT="The future broadband ISDN needs a high degree of flexibility
in order to cope with a great variety of services with widely differing
bandwidth and quality of service requirements. The asynchronous transfer
mode, which is now widely accepted as the basis for this network, offers
very flexible information transfer with respect to bandwidth
requirements. The introduction of a special class of priorities, called
space priorities, adds a quality of service flexibility to the ATM
bearer service. This paper describes various space priority mechanisms
and their detailed performance evaluation. Furthermore, a comparative
performance study is given, indicating the excellent performance
characteristics of a simple buffer management scheme called partial
buffer sharing.",
}

@INPROCEEDINGS{Lee9104:Transient,
AUTHOR="D. Lee and Song Li",
TITLE="Transient analysis of multi-server queues with Markov-modulated
Poisson arrivals and overload control",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="1196-1205 (10C.4)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="This paper studies the transient behavior of a
Markov-modulated Poisson arrival queue under overload control. The queue
has finite or infinite buffer capacity with multiple exponential
servers. A Markov-modulated Poisson process is used to represent an
aggregated voice or video packet arrival process in integrated service
networks. By overload control, the authors mean to properly adapt the
arrival process once the buffer contents exceed a designated level. The
probability distribution of queue length as a function of time is
obtained. The temporal effect of the overload control is measured in two
forms. While in overload, the amount of time for the queue to fall into
underload is measured. While in underload, the amount of time for the
queue to rise to overload is measured. A proper design of the control
will not only reduce the fall time but also increase the rise time. We
also explore the transient queueing behavior as affected by time
stochastic properties of the underlying Markov chain for the arrival
process.",
}

@INPROCEEDINGS{Lela9104:High,
AUTHOR="Will Leland and Daniel H. Wilson",
TITLE="High time-resolution measurement and analysis of {LAN} traffic:
implications for {LAN} interconnections",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="1360-1366 (11D.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="LAN; traffic measurements; traffic characteristics; LAN
interconnection; time correlation; traffic correlation; SMDS; traffic
modeling",
ABSTRACT="The interconnection of local area networks is increasingly
important, but little data are available on the characteristics of the
aggregate traffic that LANs will be submitting to the interconnection
media. In order to understand the interactions between LANs and the
proposed interconnection networks (MANs, WANs, and BISDN networks), it
is necessary to study the behavior of this external LAN traffic over
many time scales --- from milliseconds to hundreds of seconds. The
authors present a high time-resolution hardware monitor for Ethernet
LANs that avoids the shortcomings of previous monitoring tools, such as
traffic burst clipping and timestamp jitter. Using data recorded by our
monitor for several hundred million Ethernet packets, the paper presents
an overview of the short-range time correlations in external LAN
traffic. The analysis shows that LAN traffic is extremely bursty across
time domains spanning six orders of magnitude. This behavior is compared
with simple traffic models and the data is employed in a trace-driven
simulation of the LAN-BISDN interface proposed for the SMDS service. The
results suggest that the pronounced short-term traffic correlations,
together with the extensive time regime of traffic burstiness, strongly
influence the patterns of loss and delay induced by LAN
interconnection.",
URL="ftp://thumper.bellcore.com/pub/wel/Leland+Wilson\_INFOCOM\_91.ps.Z",
}

@INPROCEEDINGS{Li9104:Discrete,
AUTHOR="Song Li and Hong-Dah Sheng",
TITLE="Discrete queueing analysis of multi-media traffic with diversity
of correlation and burstiness properties",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="368-381 (4C.1)",
MONTH=apr,
YEAR=1991,
KEYWORDS="discrete time queue",
ABSTRACT="This paper presents a solution for multi-media traffic
queueing analysis. The key properties of multi-media traffic are
characterized by the great diversity of correlation and burstiness. As
in previous work, we construct the multi-media traffic based on various
two-state Markov chains. Moreover, we here allow each two-state Markov
chain to be defined on different transition intervals, representing the
diversity of peak access rates from individual sources. Upon a time
index normalization, the queue is modeled by a multi-dimensional
discrete Markov process. Extending the technique developed earlier, the
entire solution of queue length distributions is constructed. It uses a
generating function approach. By matrix spectral decomposition and
diagonalization, one can decompose the evaluation of each individual
vanishing/non-vanishing root. Each vanishing root is used to obtain the
queue boundary values; each non-vanishing root constructs a geometric
term in the expression of the queue length distribution. It is found
that all the vanishing roots must be real and all the complex
non-vanishing roots can be ignored. In numerical studies, we first
verify the time index normalization in source modeling, and then examine
the effect of multi-media traffic properties on ATM queues.",
}

@ARTICLE{Liou9104:Overview,
AUTHOR="Ming L. Liou",
TITLE="Overview of the $p\times64$ kbit/s video coding standard",
JOURNAL=cacm,
VOLUME=34,
NUMBER=4,
PAGES="59-63",
MONTH=apr,
YEAR=1991,
KEYWORDS="packet video; H.261; video coding",
}

@INPROCEEDINGS{Mitr9104:Dynamic,
AUTHOR="D. Mitra and J. B. Seery",
TITLE="Dynamic adaptive windows for high speed data networks with
multiple paths and propagation delays",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="39-48 (2B.1)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="The optimal design of windows for virtual circuits has been
studied for high speed, wide area networks in an asymptotic framework in
which the delay-bandwidth product is the large parameter. The authors
have previously proposed and evaluated a new class of algorithms for
dynamically adapting windows in single path, multi-hop networks. Here,
the authors develop algorithms for networks having multiple paths with
different propagation delays. The source of each virtual circuit (VC)
measures the round trip response time of its packets and uses these
measurements to adjust its window with the goal of satisfying certain
asymptotic identities that have been proven to hold in stationary
asymptotically optimal designs. The authors also evaluate the
performance of the new adaptive algorithms in realistic, non-stationary
conditions by simulations of networks with data rates of 45 Mbps and
propagation delays of up to 47 msec. One of the two networks studied has
3 nodes, 2 paths and up to 16 VCs on each path. The simulation results
generally confirm that the realizations of the adaptive algorithms give
stable, efficient performance and are close to theoretical
expectations.",
}

@ARTICLE{Naga9104:Approximation,
AUTHOR="R. Nagarajan and James F. Kurose and Donald F. Towsley",
TITLE="Approximation Techniques for Computing Packet Loss in
Finite-Buffered Voice Multiplexers",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="368-377",
MONTH=apr,
YEAR=1991,
KEYWORDS="traffic modeling; packet voice; realtime traffic fluid flow
approximation; Markov modulated Poisson process (MMPP)",
ABSTRACT="In this paper, we examine three different approximation
techniques for modeling packet loss in finite-buffer voice multiplexers.
The performance models studied differ primarily in the manner in which
the superposition of the voice sources (i.e., the arrival process) is
modeled. The first approach models the superimposed voice sources as a
renewal process, and performance calculations are based only on the
first two moments of the renewal process. The second approach is based
on modeling the superimposed voice sources as a Markov modulated Poisson
process (MMPP). Our choice of parameters for the MMPP attempts to
capture aspects of the arrival process in an alternate, more intuitive,
manner than previously proposed approaches for determining the MMPP
parameters and is shown to compute loss more accurately. Finally, we
also evaluate a fluid flow approximation for computing packet loss. For
all three approaches, we consider, as a unifying example, the case of
multiplexing voice sources over a T1-rate link. The main conclusion of
this paper is that both the new MMPP model examined here and the fluid
flow approximation can provide accurate loss predictions for parameter
ranges of practical interest. These predictions are also shown to be
many orders of magnitude better than modeling the superimposed voice
sources simply as a Poisson process. We also discuss the problem of
modeling buffer overflow for general arrival processes and also briefly
outline modeling approaches for analyzing finite-buffer multiplexers
with general arrival and service processes in a network environment.",
}

@ARTICLE{Norr9104:Superposition,
AUTHOR="I. Norros and J. W. Roberts and A. Simonian and J. T. Virtamo",
TITLE="The superposition of variable bit rate sources in an {ATM}
multiplexer",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="378-387",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory",
ABSTRACT="When variable bit rate sources are multiplexed in an ATM
network, there arise queues with a particular form of correlated arrival
process. We analyze such queues by exploiting a result expressing the
distribution of work in system of the $G/G/1$ queue originally derived
by Bene\v{s}. We provide a simple alternative demonstration of this
result and extend it to the case of fluid input systems. The result is
applied first to a queue where the arrival process is a superposition of
periodic sources (the $\sum D\_i/D/1$ queue), and then to a variable
input rate constant output rate fluid system. The latter is shown to
model the so-called burst component of the considered superposition
queueing process. The difference between this and the real queue, the
cell component, can be evaluated by means of the results obtained for
the $\sum D\_i/D/1$ queue. The relative importance of these two
components is explored with reference to the particular case of a
superposition of on/off sources.",
}

@ARTICLE{Ohba9104:Interdeparture,
AUTHOR="Y. Ohba and M. Murata and H. Miyahara",
TITLE="Analysis of interdeparture processes for bursty traffic in {ATM}
networks",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="468-476",
MONTH=apr,
YEAR=1991,
KEYWORDS="discrete time queue; IPP; interrupted Poisson process;
multiplexer",
ABSTRACT="An ATM network is expected to support a large number of bursty
traffic sources and, therefore, it becomes critical to control network
traffic in order to provide a desirable level of performance. One
important realization for that purpose is admission control, which
decides to accept a new call or not dependent on current resource usage
so that the network does not fall into congestion. In this paper, we
model an ATM switch as a discrete-time single-server queue, at which the
following three kinds of arrival processes are allowed to join together:
i) arrivals of cells with general interarrival distribution, ii)
Bernoulli arrivals of cells in batches, and iii) interrupted Poisson
processes. We offer an exact analysis to derive the waiting-time
distributions and interdeparture-time distributions for arriving cells
subject to admission control in ATM networks. Next, we extend the model
to approximately obtain the end-to-end delay distributions for the
designated traffic stream. Such an analysis is important for voice or
coded video because they require a playout mechanism at the destination.
Since the analysis is approximate, we also provide the simulation
results to assess its accuracy. Numerical examples are also shown to
investigate how the traffic characteristics of the designated traffic
stream are affected by the total traffic load at the switching node, the
number of other bursty traffic sources, and the degree of burstiness of
the traffic source itself.",
ANNOTE="GI-stream (for example, IPP), B-stream ($N$ IPP), M stream
(Bernoulli process with batch arrivals); infinite queue.",
}

@INPROCEEDINGS{Ohta9104:Technique,
AUTHOR="Hiroshi Ohta and T. Kitami",
TITLE="A technique to detect and compensate consecutive cell loss in
{ATM} networks",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="781-790 (7C.3)",
MONTH=apr,
YEAR=1991,
KEYWORDS="error control",
ABSTRACT="This paper proposes a new cell loss recovery method applied to
virtual paths (VPs) of ATM networks. Its advantages over conventional
methods on virtual circuits (VCs) include reduced coding/decoding delays
and facility sharing. In addition to consecutive cell loss compensation
ability, another feature of this method is that cell loss compensation
facilities are only required at VP terminating nodes. Performance
estimations show an outstanding reduction in cell loss rate.",
}

@INPROCEEDINGS{Petr9104:Nested,
AUTHOR="David Petr and Victor S. Frost",
TITLE="Nested threshold cell discarding for {ATM} overload control:
optimization under cell loss constraints",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="1403-1412 (12A.4)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="This paper deals with overload control in asynchronous
transfer mode (ATM) networks via priority cell discarding mechanisms
governed by a set of nested queue fill thresholds. Specifically, we
develop an efficient search technique, applicable to any number of
discarding priorities, for determining the set of thresholds that
optimize the offered load when constraints on cell loss (discarding)
probabilities are specified. Results are presented as a function of
queue capacity for given traffic distribution and arrival statistics.
The results indicate that nested threshold discarding systems can
support significantly higher traffic loads than systems without
priorities. The sensitivity of the performance advantage to traffic mix
and cell loss constraints is also illustrated. The efficient search
procedure is shown to provide substantial computational gain compared to
exhaustive search when there are more than two discarding priorities.",
}

@INPROCEEDINGS{Pier9104:Simple,
AUTHOR="Gerard Pieris and Galen Sasaki",
TITLE="The performance of simple error control protocols under
correlated packet losses",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="764-772 (7C.1)",
MONTH=apr,
YEAR=1991,
KEYWORDS="error control; loss correlation",
ABSTRACT="The effect of correlated packet losses is studied for some
simple ARQ protocols: go-back-$\infty$ and blast. The packet losses are
modeled by a two-state Markov chain and it is assumed that the round
trip delay is random. The authors derive expressions for the
$z$-transform and the first and second moments of the time ($\tau$)
taken to successfully transmit $N$ packets for go-back-$\infty$ and
variations of the blast protocol. For go-back-$\infty$, bounds are
derived for $E[\tau]$ and it is shown that for a fixed mean round trip
delay, $E[\tau]$ is minimized when the distribution of the round trip
delay is such that its variance is minimized. Some of the protocols
investigated show a significant improvement when packet losses occur in
bursts. The authors propose and analyze a variation of the blast
protocol which seems particularly suited to bursty packet loss
situations.",
}

@INPROCEEDINGS{Poo9104:Modularity,
AUTHOR="G. S. Poo and Boon-Ping Chai",
TITLE="Modularity versus efficiency in {OSI} system implementation",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="950-959 (8D.2)",
MONTH=apr,
YEAR=1991,
KEYWORDS="transport protocol",
ABSTRACT="Modularity and efficiency in protocol implementations do not
go hand in hand. A tradeoff is inevitable between good structure and
good performance. Although a layered architecture has been proposed for
open communications, it is generally unknown as how the layer entities
ought to be structured and what are appropriate strategies that could be
adopted in implementations. This paper examines a number of possible
implementations strategies using the various prevailing facilities:
processes, threads, kernel and front-end processors. The pros and cons
of the strategies are analyzed showing their relative merits in
implementations. The analysis leads to the recommendation of an enhanced
subsystem architecture that holds the best compromise of the conflicting
requirements of modularity and efficiency.",
ANNOTE="Describes the modularity vs. efficiency tradeoff in the
implementation of a protocol stack. Discusses mapping of seven layers
onto hardware and software (drivers, processes, threads, etc.).
[Yates]",
}

@ARTICLE{Rasm9104:Source,
AUTHOR="C. Rasmussen and Jens H. Sørensen and Kenn S. Kvols and S. B.
Jacobsen",
TITLE="Source-independent call acceptance procedures in {ATM} networks",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="351-358",
MONTH=apr,
YEAR=1991,
KEYWORDS="admission control; congestion control; bounds",
ABSTRACT="This paper considers strategies for connection admission
control in ATM networks. Without any Poisson or renewal assumptions, two
easy computable upper bounds on the time congestion in a finite buffer
are derived. The first upper bound is valid for arbitrary peak and mean
rate policed sources while the second, and in principle, tighter bound
is valid for sources of the on/off type. The tightness of the bounds are
evaluated by a new periodic queueing model taking into account the
maximum allowed burst duration. It is concluded that the bounds form a
basis for a realization of a simple admission control algorithm.
Furthermore, it is pointed out that the derivation of the on/off bound
induces a decomposition of the queueing process into a cell scale
contribution and a burst scale contribution, a decomposition which is
superior to traditional Markov modulated approaches both in accuracy and
in offering insight into the queueing proces.",
}

@ARTICLE{Rath9104:Modeling,
AUTHOR="Erwin P. Rathgeb",
TITLE="Modeling and performance comparison of policing mechanisms for
{ATM} networks",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="325-334",
MONTH=apr,
YEAR=1991,
ABSTRACT="ATM networks, as proposed by CCITT as the solution for the
future BISDN, will provide high flexibility with respect to the varying
bandwidth requirements of the different services. They will also support
variable bit rates within a connection. The packetized information
transfer, without flow control between the user and the network in
combination with the asynchronous multiplexing principle, results in a
need to control the individual cell streams during the entire duration
of the calls to ensure an acceptable quality of service for all
coexisting calls sharing the same resources. This kind of control will
be provided for by introducing a ``policing'' or ``usage parameter
control'' function. First, this paper will describe basic design
objectives and requirements for such a function. These requirements will
serve as a basis for the comparison of some of the mechanisms proposed
so far, namely the ``leaky bucket'', the ``jumping window'', the
``triggered jumping window'', the ``moving window'', and the
``exponentially weighted moving average'' mechanisms.",
ANNOTE="congestion control; leaky bucket; policing; flow control; rate
control",
}

@UNPUBLISHED{Rayc9104:Packet,
AUTHOR="D. Raychaudhuri",
TITLE="Packet Video and Multimedia Communications",
NOTE="Slides from a presentation at the David Sarnoff Research Center",
MONTH=apr,
YEAR=1991,
KEYWORDS="packet video",
ANNOTE="outlines research issues",
}

@ARTICLE{Rodr9104:Prediction,
AUTHOR="Ramon M. Rodriguez-Dagnino and Masoud Khansari and A.
Leon-Garcia",
TITLE="Prediction of bit-rate sequences of encoded video signals",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=4,
PAGES="305-314",
MONTH=apr,
YEAR=1991,
KEYWORDS="packet video; source model",
ABSTRACT="Video traffic characterization (VTC) arises as an important
issue in the design of the BISDN. Up to now, researchers have focused on
characterizing the bit rate processes generated by video coders by
working directly with the encoded sequence. A separate modeling must
then be performed on the bit rate sequences generated by each variable
bit rate coding algorithm. In this paper, we propose a new approach for
VTC. It posits that every video sequence is characterized by a set of
fundamental indexes or parameters, and that the bit rate process can be
generated by a parametric model of the corresponding indexes. Among the
implications of this approach are: the encoding process is no longer
necessary to simulate the bit rate process for a particular video
sequence; a video sequence needs to be processed only once to obtain its
fundamental parameters; and, in general, the computation of the index
processes require much less processing than the actual encoding.
Finally, if parametric models are identified for all encoding algorithms
of interest, then the problem of developing models for various
combinations of encoders and classes of video sequences reduces to the
problem of developing a single model for the index processes of various
classes of video sequences.",
}

@INPROCEEDINGS{Rubi9104:Admission,
AUTHOR="I. Rubin and T. Cheng",
TITLE="Admission Control for Multi-Layer Management of High-Speed
Packet-Switched Networks under Observation Noise",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="570-578 (6A.4)",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control",
ABSTRACT="The authors study admission control as a congestion avoidance
mechanism in the management of high-speed packet-switched networks under
imperfect information. A multi-layer model which can be used for the
analysis of ISDN and BISDN-type networks is presented. In this model,
traffic requirements at the lower layers result in constraints on the
admission policies at the call layer. Using such a model, the authors
examine the effects of noisy estimates (due to uncertainties in measured
state information, or due to the use of realistic limited state
distribution mechanisms) on the performance of networks managed via
fixed threshold call admission policies. The standard deviation of the
collected information concerning the network status serves as a key
parameter in representing the complexity, coverage, extensiveness, and
cost of the implemented network management and information collecting
procedure. For a single-domain network, the effects of Gaussian noise on
call blocking, call throughput, packet throughput, and the probability
of excess calls are examined in detail. The throughput capacity
trajectory is described for fixed packet blocking, packet delay, and
probability of excess call constraints. Similar analysis can be carried
out for multi-domain networks in which uncertainty is introduced through
the management domain structure.",
}

@ARTICLE{Sait9104:Statistical,
AUTHOR="H. Saito and M. Kawarasaki and Hiroshi Yamada",
TITLE="An analysis of statistical multiplexing in an {ATM} transport
network",
JOURNAL=ieeejsac,
VOLUME=9,
NUMBER=3,
PAGES="359-367",
MONTH=apr,
YEAR=1991,
KEYWORDS="congestion control; multiplexer; ATM",
ABSTRACT="The traffic characteristics of an ATM network are analyzed by
theoretical methods. A new method is proposed to express the burstiness
of the cell arrival process. Both statistical multiplexing and
statistical bandwidth allocation are quantitatively evaluated. When
packetized video and voice traffic are multiplexed, the number of
multiplexable sources strongly depends on the peak rate of the
multiplexed video sources, and statistical bandwidth allocation is
ineffective without control. On the other hand, lowering the peak rate
of video traffic effectively improves bandwidth utilization.",
}

@ARTICLE{Sait9104:Traffic,
AUTHOR="H. Saito and K. Kawashima and K. Sato",
TITLE="Traffic Control Technologies in {ATM} Networks",
JOURNAL=ieice,
VOLUME="E74",
NUMBER=4,
PAGES="761-771",
MONTH=apr,
YEAR=1991,
ABSTRACT="This paper surveys and discusses traffic control in ATM
networks. Traffic control can be classified into path level control and
cell level control. The effectiveness and the remaining problems are
clarified for each level of control. The emphasis is on research
activities in this field in Japan.",
ANNOTE="Congestion control. Models cell stream as burst/silence
period.",
}

@INPROCEEDINGS{Schu9104:Distribution,
AUTHOR="Henning Schulzrinne and James F. Kurose",
TITLE="Distribution of the Loss Period for Some Queues in Continuous and
Discrete Time",
BOOKTITLE=infocom,
ADDRESS="Bal Harbour, Florida",
PAGES="1446-1455 (12C.1)",
MONTH=apr,
YEAR=1991,
KEYWORDS="queueing theory; loss period; loss correlation",
ABSTRACT="For soft real-time communication systems, packet loss due to
excessive delay rather than average delay becomes the critical
performance issue. While most previous studies of real-time systems
measure loss as a time-average fraction of excessively delayed packets,
this paper characterizes the stochastic properties of time-out loss
periods for infinite queues, that is, uninterrupted intervals during
which the virtual wait is at or above some fixed threshold. We present
analytic expressions and numerical techniques for computing both
``time-based'' measures such as the distribution of periods during which
all arriving packets are lost due to excessive delay as well as
``packet-based'' measures such as the distribution of the number of
consecutively lost packets and the number of successful packets between
such periods of loss. Both continuous and discrete-time systems are
examined. It is shown that the assumption of random packet loss severely
underestimates the number of consecutively lost packets. Also, the loss
period is found to be independent of the waiting time threshold for the
G/M/1 queue and $D^{\rm [Geo]/D/1}$ queue, with very little influence
for other queueing models.",
ANNOTE="distribution of loss period and composite loss period for
$G/M/1$ and $D^{\rm [Geo]}/D/1$ queue.",
URL="http://www.cs.columbia.edu/~hgs/papers/Schu9104\_Distribution.ps.Z",
}

@INPROCEEDINGS{Simh9104:Minimization,
AUTHOR="R. Simha and James F. Kurose",
TITLE="On-line minimization of call setup time via load balancing: a
stochastic approximation approach",
BOOKTITLE=infocom,
ORGANIZATION="IEEE",
ADDRESS="Bal Harbour, Florida",
PAGES="597-607 (6B.3)",
MONTH=apr,
YEAR=1991,
ABSTRACT="With the addition of new network services, it is anticipated
that the processing involved in setting up a call in a circuit-switched
network or a session in a packet switched network will vary greatly for
different classes of calls or sessions. In this paper, the authors
address the problem of reducing the call setup time in a
circuit-switched network, or equivalently the session setup time in a
packet-switched network, through the balancing of load across call
processors. The authors formulate a stochastic optimization problem and
study the use of stochastic approximation techniques. Given the
distributed nature of the problem, we extend previous results obtained
for a single node to the case where several nodes operate simultaneously
and in an asynchronous manner. Our results include a theoretical study
of convergence as well as several simulation results that compare two
stochastic approximation techniques.",
ANNOTE="Stoc