Network coding as an efficient scheduling algorithm for large scale systems
|Author:||Christos Gkantsidis Microsoft|
|Date:||May 18, 2007|
Designing large scale content distribution systems, such as peer-to-peer networks, is a very challenging task. One fundamental problem is to schedule optimally (e.g. as to minimize the time to distribute the content to all users) using local information only. Using ideas borrowed from network coding theory, in particular by treating data as algebraic entities that can be transformed, we have designed systems that effectively use the resources of the network and, yet, do not use global information. Our systems target two particular applications of great current interest, namely file swarming using p2p and video-on-demand distribution using again p2p. Using the same ideas, we are currently in the process of designing a multipath routing scheme for wireless mesh networks. In this talk, I will describe our experiences designing and using those systems, and demonstrate that network coding is a communication paradigm with great potential for large scale communication systems.
Christos is a researcher in the Systems and Networking Research Group at Microsoft Research in Cambridge, UK. Christos has a Ph.D. in CS from the Georgia Institute of Technology, GA, USA and a bachelors in CS from the University of Patras, Greece. His current research interests include the areas of content distribution networks, peer-to-peer technologies, analysis, and modeling of complex communication networks. Christos is a member of the IEEE and the ACM.