Lead


Lay summary
Peer-to-peer (P2P) systems, in which peer computers form a cooperativenetwork and share their resources (storage, CPU, bandwidth), haveattracted a lot of interest lately. After the apparition of the firsttruly successful P2P systems, and the significant amount of researchconducted in Academia and in the Industry, most researchers now agree thatP2P systems are more than just a fashion phenomenon. They offer greatpotential for building cooperative networks that are self-organizing,efficient, scalable, and reliable.Research in P2P networks has so far mainly focused on content storage andlookup, but little work has been done about its actual distribution. Bycapitalizing the bandwidth of peer nodes, P2P architectures offer greatpotential for addressing some of the most challenging issue of today'sInternet: the cost-effective distribution of bandwidth-intensive contentto thousands of simultaneous users and the resilience to "flash crowds" (ahuge and sudden surge of request traffic that usually leads to thecollapse of the affected server).In this project, we propose to address the problem of cooperativedistribution of streaming media and large content from a networkingperspective. We plan to specifically focus on three complementary researchdirections: first, the design of topology-aware P2P substrates specializedfor efficient content distribution; second, the push-based distribution ofstreaming content with timing constraints, such as streaming media (TV,radio); third, the pull-based distribution of large, but time-insensitivestored content. Each of these research topics will be supported upstreamby extensive analysis and modeling, and downstream by prototypeimplementations and experimental validation.This project is expected to yield not only novel research contributions,but also practical techniques for cooperative content distributionapplicable both Internet-wide and in large private networks. Thesetechniques can be of great interest to media and infrastructure providers,as well as to medium and large companies that wish to avoid the cost ofdedicated Content Delivery Networks (CDNs) for reliable contentdistribution.