一种新的流媒体批处理补丁缓存算法

Novel batched patch caching algorithm for streaming media

在分布式流媒体分送系统中,一个关键的问题就是如何降低骨干网络带宽的消耗.通过在网络的边缘部署代理服务器,由代理负责响应本地客户的请求并转交从服务器来的媒体数据流.将服务器的批处理补丁调度技术与代理服务器分段缓存策略有效地结合起来,提出了批处理补丁预先缓存算法(BPP).根据当前客户请求到达的分布情况,代理服务器提前分配相应的缓存空间,对正在进行的组播多媒体数据流实行分段缓存,使后续到达的客户请求能够共享代理服务器中缓存的数据段.理论分析及实验结果表明了该算法能够明显降低骨干网络带宽的消耗,并对客户请求到达速率的变化具有很好的适应性.

In distributed streaming media delivery system, an important topic is how to reduce the consumption of backbone network bandwidth. By deploying the proxy at the edge of network, it made response to a group of local clients' request and forwarded the multimedia data streamed out of the server. An efficient algorithm called batched patch pre-caching (BPP) was proposed, which tightly combined the server scheduling with proxy caching strategies. In terms of the distribution of clients' request arrival at current time, the proxy allocated the corresponding buffer units in advance and cached data in segments from the ongoing multicast stream started at server. These cached data could be shared by subsequent requests till they were evicted from the proxy. The results of theoretical analysis and experimental simulation show that this algorithm can significantly reduce the bandwidth consumption on backbone link, and has very good adaptability for the variation of request arrival rate.