基于贡献度的自适应P2P流媒体数据调度算法

CONTRIBUTION-BASED ADAPTIVE DATA SCHEDULING ALGORITHM FOR P2P STREAMING MEDIA

在P2P流媒体系统中,数据调度算法是决定视频播放质量和系统性能的核心部分。针对当前P2P流媒体数据调度算法未能考虑节点带宽和服务能力的差异,从而造成对系统资源利用不充分的问题,提出一种基于贡献度的自适应(CBA)流媒体数据调度算法。算法定义节点贡献度来衡量节点的数据上传和可用带宽情况,预先向部分节点传输准备数据。并根据数据块优先级、带宽估计情况和节点贡献度等信息进行自适应调整,确定数据块请求的提供方和次序。仿真实验表明,CBA算法能充分地利用节点可用带宽,降低流媒体的启动延迟和服务器负载,改善系统的整体性能。

In peer-to-peer streaming media system, data scheduling algorithm is the key to determine the playback quality and system performance. Existing P2P streaming media scheduling algorithms make insufficient consideration on differences between the node bandwidth and the service capacities, thereby cause the inadequate use of system resources. In light of these problems, we propose in this paper a contribution-based adaptive （CBA） data scheduling algorithm for streaming media. In the algorithm, the contribution is defined to measure the capacity of node in data uploading and the available bandwidth, the preparation data is transmitted to some of pecm in advance, and is adaptively adjusted according to the information of priority of data blocks, bandwidth estimation and node contributions to decide the suppliers of data block requests and the scheduling orders. Simulation experiments show that the CBA algorithm can take full advantage of the available bandwidth of node, reduce start-up delay of streaming media and the load of server, and improve the overall performance of the system as well.