Collaborative Caching in P2P Streaming Networks

Abstract

With the development of the Internet, the Internet applications represented by Peer-to-Peer (P2P) streaming systems bring more and more communication overhead. In order to alleviate communication pressure of the Internet, and improve the user’s access experience, we aim at taking full advantage of peer upload bandwidth contributions with a cache on each peer. While, the size of such a cache on each peer is limited, it is necessary to design the cache replacement strategy in such P2P Systems. In this paper, we implemented a collaborative caching mechanism for P2P streaming networks. Firstly, we designed some measurement experiments for the existing large-scale P2P streaming systems to find some features and problems. Then, we proposed the collaborative caching strategy based on the chunk value and requesting distribution factor to address the existing problems. Our goal is to keep those chunks with high requesting frequency and farther away from the current peer in order to achieve higher cache hit rate and load balancing. Compare to the measured P2P streaming systems, the simulation results show that the proposed method has better performance on multiple metrics such as cache hits, system load and peer collaboration.