自适应PI主动队列管理算法

An Adaptive PI Active Queue Management Algorithm

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(proportional 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 seriescompensation and position feedback compensation),API具有更快的收敛速度和更小的队列抖动.

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.