一种基于主动代理的增强型分层多播算法——AELM  

Enhanced layered video multicast algorithm based on active agent——AELM

作　　者：赵昭灵[1] 邬江兴[1] 李明铎[1] 郭玉华[1] 

机构地区：[1]解放军信息工程大学,河南郑州450002

出　　处：《通信学报》2005年第3期106-110,共5页Journal on Communications

基　　金：国家"863"信息技术领域重大项目基金资助(2003AA103510)

摘　　要：为一种典型的多速率视频多播算法,RLM 通过动态地加入和退出一定的多播组来实现对网络的拥塞控制。然而,RLM 算法存在要求用户协同工作、反应时间长以及对路由表项容量要求高的问题。本文通过引入主动代理反馈机制以及历史相关决策因子对其进行了改进,提出了一种基于主动代理的增强型分层多播算法——AELM。试验表明本文的算法能够解决 RLM 算法存在的问题。As a promising multi-rate video broadcasting algorithm to heterogeneous receivers, RLM uses periodically conducting a combination of “join-experiments” and “branch pruning” events to manage network congestion. However, there are some problem in RLM, such as requirements of the users to cooperate with each other, slow reactions, and much more usage of routing entries. Based on the mechanism of RLM, this paper improved it through introducing into active agent and correlatively dropping with priority method and developed an enhanced layered video multicast algorithm based on active agent-AELM. Simulations show that the new algorithm proposed in this paper has solved the problems existed in the RLM algorithm.

关 键 词：多速率视频多播 分层编码 拥塞控制:主动代理:历史相关决策因子 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]