HIPPO: An Adaptive, Scalable, Hierarchical P2PLive Streaming System

Abstract

P2P live streaming is a hot research topic of Internet, but for the defective of system architecture and scheduling policy, P2P streaming applications have poor user experience, such as long start-delay, long play-delay, and low play-continuity and so on. Firstly, based on the analysis of the advantages and disadvantages of previous works, this paper designed and implemented a hierarchical P2P streaming system. The system is composed by three layers: source management servers, region management servers, and peers. The underlying P2P overlay network is organized through Mesh-pull mechanism. We propose a new scheduling strategy to utilize the capacity of the peer. The new adaptive scheduling strategy considers the urgency and scarcity of the data blocks, and selects the appropriate neighbor nodes by monitoring neighbor nodes’ the maximum load. The study of a real-life system provides valuable insights for the future development of P2P live streaming systems.