Dept. of Computer Science, California Institute of Technology
Mar. 29, 11:00AM Interschool Lab, 750 CEPSR
Abstract: Cloud computing has emerged as a crucial platform for business and personal applications. However, the management of the infrastructure behind the cloud (i.e. data centers) is far from mature and there are many algorithmic challenges that remain, such as data management, capacity management and energy management. In this talk I focus on our recent work on two such challenges: dynamic provisioning and geographical load balancing. In both contexts I will present our new algorithms, which provide significantly improved performance guarantees when compared with the "standard" approaches using Receding Horizon Control. Additionally, I will present a case study of our algorithms for cost-effective geographical load balancing.
Speaker Biography: Minghong Lin is currently a Ph.D. student in Computer Science at California Institute of Technology. He received the B.S. degree in Computer Science from University of Science and Technology of China in 2006 and the M.Phil. degree in Computer Science from the Chinese University of Hong Kong in 2008. His research interests include energy efficient computing, online algorithms and nonlinear optimization. He has received best paper award at IEEE INFOCOM 2011, IEEE Green Computing conference 2012, and best student paper award at ACM GREENMETRICS 2011. He has also been awarded the highly competitive IBM Ph.D. Fellowship and named finalist in Facebook Fellowship.