PVPS:P2P点播中的分布式搜索算法

PVPS:DISTRIBUTED SEARCHING ALGORITHM IN P2P VOD

PVPS系统针对P2P点播服务实现中的源节点搜索问题给出了一种实用高效的解决策略。PVPS在节点结构组织上采用了基于节目内容分簇的网状结构,每个分簇中由代理节点进行管理。在簇间搜索过程中,PVPS采用改进的启发式MPR算法、基于邻居优先级的自裁减策略和基于消息冗余度的剪枝策略对非结构化搜索进行多次优化,提高了搜索的效率。理论分析和实验结果表明,PVPS服务体系采用的搜索策略在性能上优于现有策略,在大型网络中具有良好的稳定性和扩展性。

This paper presents a novel service system PVPS,which encompasses a practical and effective solution to P2P （peer-to-peer） VoD （Video on demand） resource nodes searching problem in its service realization. PVPS employs a content-based clustering mesh structure in organizing nodes, and in each cluster there are several broker nodes managing the others. In the searching process between clusters, PVPS uses altered heuristics MPR algorithm, self-pruning policy based on neighbour priority and pruning policy based on message redundancy to optimize the unstructured P2P searching few times, and this increases the searching efficient. Both theoretical analysis and experiment results show that the searching strategies in PVPS outperform the existing strategies in terms of performance,and can maintain a fine state and scalability in large-scale networking.