节点文献
基于模型算法控制的主动队列管理算法
Active queue management algorithm based on model algorithmic control
【摘要】 通过深入分析TCP/AQM系统的动态特性,提出一个新的预测模型.基于该模型,结合模型算法控制(MAC)提出一种新的主动队列管理算法(MACAQM),并给出了MACAQM的详细设计过程和参数选取的原则.大量不同网络环境的仿真实验表明了MACAQM算法的有效性.与PI,RaQ和REM等算法相比较,MACAQM具有收敛速度快、队列抖动小的优点.同时,MACAQM的采样间隔相对较大,算法实现简单,所以计算量较小,占用的路由器资源也较少.
【Abstract】 Through the analysis of the TCP/AQM system dynamics,a new predictive model is proposed.New active queue management(AQM) algorithm based on model algorithmic control(MACAQM) is proposed.The design details and the principles of choosing parameters are also presented.The results of simulations under different network environments show that MACAQM is effective in controlling the queue length to the desired value.In comparison to other AQM algorithms,such like PI,RaQ and REM,MACAQM has faster response and lower queue fluctuations.In the same time,MACAQM has larger interval with simple implementation,so it uses less resource on the routers.
【Key words】 network congestion; active queue management; predictive model; model algorithmic control;
- 【文献出处】 控制与决策 ,Control and Decision , 编辑部邮箱 ,2013年10期
- 【分类号】TP393.07
- 【被引频次】3
- 【下载频次】129