Up until recently, content distribution solutions consisted on placing dedicated equipment at certain places inside or at the edge of the Internet. However, in recent years, a new paradigm for Content Distribution has emerged based on a fully distributed architecture where commodity PCs are used to form a cooperative network and share their resources (storage, CPU, bandwidth). In this talk, we will study a P2P system for content distribution of large files that is based on network coding. With network coding, each node of the distribution network is able to generate and transmit informative blocks of information. This is particularly important in large unstructured overlay networks, where the nodes need to make decisions based on local information only. We will demonstrate the benefits of network coding under different realistic settings, present the results of several live trials, and discuss the implementation overheads and security related problems that need to be overcome to make such solution work.
Pablo Rodriguez is a researcher at Microsoft Research, Cambridge. Prior to Microsoft he was a Technical Staff Member at Bell-Labs and also worked for a couple of startups in California (Inktomi, Tahoe Networks). His research interests are in the areas of P2P (Avalanche), Content Distribution, Information Theory and Wireless networks. He holds a Ph.D. from the Swiss Federal Institute of Technology (EPFL).
As a result of his work Pablo Rodriguez received several awards including the "Prix de la Recherche" in France, and the "Extraordinary Category Classification in Science" from the USA government.
http://www.research.microsoft.com/~pablo
