基于多种资源测量的流媒体实时接纳控制研究  

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

作　　者：杨帆[1] 张冬松[1] 金士尧[1] 卢为[1] 

机构地区：[1]国防科学技术大学计算机学院并行与分布处理国防科技重点实验室,长沙410073

出　　处：《计算机应用研究》2012年第3期1044-1047,共4页Application Research of Computers

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

关 键 词：多种资源 动态测量 流媒体服务 接纳控制 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]