Abstract: Data delivery can be easily interrupted by departure of end hosts in P2P live streaming network, which may lead to degradation of QoS in time-sensitive applications. This paper proposes a new layered and clustering protocol. Based on user behavior analysis in live streaming, it can keep a level of efficiency while reduce the interruption times of Application Layer Multicast(ALM) tree. Simulation results show that the protocol can effectively boost up the robustness, reduce the average ALM latency, and satisfy the scalability.

Key words: P2P, Application Layer Multicast(ALM), user behavior analysis, live streaming

摘要： 在P2P视频直播网络中，用户频繁地加入或离开组播组会造成数据传输中断。该文提出一种新的基于分层分簇思想的应用层组播协议，基于视频直播中的用户行为分析，通过分层获得一个有效层来减少组播树中的节点失效次数。仿真实验表明，该协议能够有效提高稳定性，减少平均组播时延并具有可扩展性。

关键词: 点对点, 应用层组播, 用户行为分析, 视频直播

CLC Number: 

• TP393