首页 | 本学科首页   官方微博 | 高级检索  
     

自适应PI主动队列管理算法
引用本文:卢锡城,张明杰,朱培栋.自适应PI主动队列管理算法[J].软件学报,2005,16(5):903-910.
作者姓名:卢锡城  张明杰  朱培栋
作者单位:国防科学技术大学,计算机学院,湖南,长沙,410073
基金项目:Supported by the National Natural Science Foundation of China under Grant Nos.90104001,90204005(国家自然科学基金)
摘    要:主动队列管理是一个非常活跃的研究领域,相对于丢尾算法,AQM(active queue management)能够提供更短的平均队列延迟和更高的带宽利用率.虽然PI(proporrional integral)主动队列管理算法的性能优于RED(random early detection)算法,但是PI算法的收敛速度比较慢.以PI算法为基础提出了一种自适应PI算法API(adaptive proportional integral).API通过实时测量链路的报文丢失率,获得当前的负载信息,然后动态设置PI算法中的有关参数.通过ns-2模拟表明,相对于PI及其改进算法PIP(proportional integral based series compensation and position feedback compensation),API具有更快的收敛速度和更小的队列抖动.

关 键 词:主动队列管理  成比例积分  自适应  收敛速度  队列抖动
文章编号:1000-9825/2005/16(05)0903
收稿时间:2003/11/17 0:00:00
修稿时间:2003年11月17

An Adaptive PI Active Queue Management Algorithm
LU Xi-Cheng,ZHANG Ming-Jie and ZHU Pei-Dong.An Adaptive PI Active Queue Management Algorithm[J].Journal of Software,2005,16(5):903-910.
Authors:LU Xi-Cheng  ZHANG Ming-Jie and ZHU Pei-Dong
Abstract:Active queue management (AQM) is a very active research area in networking. Compared with drop-tail, AQM can provide smaller average queue delay and higher bandwidth utilization. Although the performance of proportional integral (PI) controller is superior to that of random early detection (RED), its convergence speed is slow. This paper proposes an adaptive proportional integral (API) algorithm based on the original PI. API obtains load information by measuring the current packet-dropping rate, then sets PI parameters accordingly. Verified by using NS-2 simulations, API can achieve faster convergence speed and smaller queue oscillation than PI and PIP (proportional integral based series compensation and position feedback compensation) which is an improved algorithm of PI.
Keywords:active queue management  proportional integral  adaptive  convergence speed  queue oscillation
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《软件学报》浏览原始摘要信息
点击此处可从《软件学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号