Abstract: The traditional Gossip protocol selects the neighbor nodes randomly. It does not consider the factors such as node storage, which affects the network performance. It causes the drawback of successful search ratio relatively lower, and network transmission payloads have the characteristics of randomness. By studying the Gossip protocol in P2P networks, a new neighbor node selection strategy is proposed, which is the Most Reliable Gossip(MR-Gossip) message transmission protocol based on fuzzy theory. Simulation experiments with various data analysis demonstrate the improvement of efficiency of the proposed strategy on node selection and correctness of the proposed algorithm in P2P networks.

Key words: P2P streaming media, node selection, Gossip protocol

摘要： 传统Gossip协议对节点的选择存在盲目性，没有考虑节点的存储能力等影响因素，致使节点选择时网络搜索成功率较低，网络传输负载呈现出随机性。通过对非结构化P2P网络中广泛应用的Gossip协议进行探索和研究，运用模糊理论提出基于可靠性的节点选择策略。通过模拟实验对相关数据进行分析，结果表明该策略能有效提高P2P网络中节点的选择效率。

关键词: P2P流媒体, 节点选择, Gossip协议

CLC Number: 

• TP393