基于多种资源测量的流媒体实时接纳控制研究

为了根据计算、存储资源和网络带宽的占用情况进行更加精确的接纳控制决策,设计了受限的可变时间窗口测量法,提出了基于多种资源占用情况的测量和算法(MBMS)。在获取多种资源负载情况的基础上实现了流媒体服务的实时接纳控制方法。实验结果表明,该方法能够在高负载的情况下确保较高的服务接纳率,同时在低负载情况下提高了资源利用率。

Research on multi-resource-measurement-based admission control for real-time streaming media services

To make highly accurate decisions for the admission control based on the consumption of computing, storage re-sources and network bandwidth, this paper proposed the dynamic measurement using constrained time window, and presentedthe multi-resource-based measured sum algorithm(MBMS). It implemented the admission control for real-time streaming mediaservices depending on the obtainment of the system load. Experimental results show that this method ensures a high acceptancerate of the service in the high-load conditions, while improves resource utilization in the low-load case.