关键词: 对等网络, 流媒体, 数据调度, 启动延迟, 服务器负载

Abstract: The data scheduling algorithm in data-driven overlay network is identified as one of the most influential factors affecting system performance of P2P streaming media. Considering the fact that the current algorithm fails to make use of the data blocks and nodes efficiently, which leads to low-quality streaming media services, a new method for data scheduling algorithm was proposed in this study based on both priority of data blocks and capacity of nodes. This algorithm could get priority value according to the scarcity and urgency of blocks. It also could get the capacity of the nodes according to uplink-bandwidths, time-online and relative distance of the nodes. With the utilization of this algorithm, higher priority blocks and higher capacity nodes were requested, and the waiting time to play was decreased. The simulations in the OPNET network indicate that the algorithm can efficiently reduce start-up delay of streaming media playing system and the server load.

Key words: Peer-to-Peer (P2P), streaming media, data scheduling, start-up delay, server load