P2P流媒体数据调度研究综述

Data scheduling research overview in P2P media streaming

P2P流媒体通过利用网络上普通主机节点的资源来提供流媒体数据服务,是一种扩展性好、性价比高的流媒体服务体系。数据调度是P2P流媒体研究中的核心问题,流媒体中严格的服务质量要求、Peer节点状态的不稳定性以及其带宽资源的有限性是其面临的主要挑战。介绍了近几年来该领域基于单播树、多组播树和随机拓扑三类典型的数据调度策略的原理特点和Peer节点搜索定位技术的研究进展,指出了未来的几种研究方向。

Peer-to-peer streaming is cost-effective and scalable because it can capitalize the resources of peer nodes to provide service to other receivers, Data scheduling is the key problem in P2P media streaming, as there exist some challenges such as strict QoS requirements of P2P media streaming, instable states and limited resources of peer nodes and so on. The principles and characteristics of three representative data scheduling polices based on single cast tree, muhicast tree and random topology were mainly described. The research progress of identifying and searching techniques of peer nodes were also introduced. Finally the directions of research in this area were outlined.