Prof Don Towsley (University of Massachusetts Amherst, USA) - iCore & CommNet2 Workshop Speaker
Don Towsley holds a B.A. in Physics (1971) and a Ph.D. in Computer Science (1975) from University of Texas. He is
currently a Distinguished Professor at the University of Massachusetts in the Department of Computer Science. He has held visiting
positions at numerous universities and research labs. His research interests include networks and performance evaluation.
He was a founding Co-Editor-in-Chief of the new ACM Transactions on Modeling and Performance Evaluation of Computing Systems (ToMPECS)
and has served as Editor-in-Chief of the IEEE/ACM Transactions on Networking and on numerous editorial boards. He has served as
Program Co-chair of several conferences including INFOCOM 2009. He is a member of ACM and IEEE.
He has received numerous IEEE and ACM awards including the 2007 IEEE Koji Kobayashi Award, and the ACM SIGCOMM and ACM SIGMETRICS
Achievement Awards. Last, he has been elected Fellow of both the ACM and IEEE and is a corresponding member of the Brazilian
Academy of Sciences.
Talk Title: "The TTL Cache: A Versatile Tool for Analysis, Optimization, and Control "
Abstract: In this talk we report on two recent developments regarding the time-to-live (TTL) cache as a tool for understanding and designing new cache management policies. The first development regards the use of a TTL cache to analyze cache management policies such as least recently used (LRU). It has recently been shown that the behavior of an LRU cache as cache size increases approaches that of a TTL cache under very general workloads. This leads to very accurate and easily computable estimates of hit and miss rates for LRU caches, even when cache sizes are small. The second development concerns the use of the TTL cache for optimizing performance objectives, such as weighted content hit rates through the choice of individual content timer values. This can be done either in an off line manner or through on-line control. Last, we combine the two developments to develop control algorithms for sharing LRU caches among different providers.