基于忍耐度的流媒体批调度算法

A Batching Algorithm for Streaming Media Based on Degree of Tolerance

批处理是一种简单有效的流媒体调度机制。对于同一网络延迟,有些用户可以接受,有些用户则无法接受,调度时应区别对待。本文提出了一种基于忍耐度的批调度算法,考虑用户忍耐度不同,合理延迟用户请求,等待更多的用户请求到达,以便在下一次批处理时启动一个组播流来服务更多的用户,但不至于延迟过度,发生用户食言,从而提高资源有效利用率。仿真结果表明该算法能有效降低用户食言率。

Batching is a simple but efficient scheduling mechanism for streaming media. For the same network latency, some user can accept, but the other can＇ t accept, so that the scheduling algorithm should treat them differently. In this paper, a batching algorithm based on degree of tolerance are proposed, in which, requests are deferred for a specific period of time, the length of which depends on the tolerance of user and is limited to avoid significant latency, so that more requests could be served by a new muhicast stream started in next batch processing, resulting in effective resource utilization. The experimental results show that the algorithm can reduce user defection rate effectively.