Abstract: P2P stream media takes plenty of bandwidth resources. This paper presents a strategy for data schedule from the perspective of detecting the unnecessary data downloads promptly. It can help node avoid unnecessary data downloads and reduce download cost of the system. A data download mathematical model is introduced, which converts the problem of improving the playing continuity of stream media to the problem of finding the optimal solution for job schedule with deadline. Experimental results show that the strategy can reduce download cost effectively and obtain perfect playing continuity.

Key words: real-time stream media, P2P network, job schedule with deadline

摘要： 针对P2P流媒体占用大量带宽资源的问题，提出一种数据调度策略，在基于Gossip协议的数据可用信息交互过程中添加少量本地信息，以帮助下载者避免不必要的数据下载，降低系统下载开销。给出数据下载过程的数学模型，将提高流媒体播放连续度问题转变为求带限期作业调度问题的最优解。实验结果表明该策略能有效节省带宽资源，获得较高的播放连续度。

关键词: 实时流媒体, P2P网络, 带限期作业调度

CLC Number: 

• TP393