一种新的主动队列管理自适应PI算法  

New Adaptive PI Algorithm for Active Queue Management

作　　者：王明文[1] 朱清新[1] 卿利[1] 

机构地区：[1]电子科技大学计算机科学与工程学院

出　　处：《电子测量与仪器学报》2007年第6期14-18,35,共6页Journal of Electronic Measurement and Instrumentation

基　　金：国家"863"高技术研究发展计划资助项目(编号:2005AA114030)

摘　　要：为克服PI算法所存在的响应速度慢,对网络参数变化敏感的缺点,将神经网络理论引入主动队列管理的研究中,提出一种基于单神经元的主动队列管理算法NPI(Neuron based PI)。NPI算法将PI控制器看成是二输入的ADALINE神经元,控制器的比例系数和积分系数按照LMS算法进行在线调整,对网络状态的变化有自学习能力,使队列长度能够快速收敛到目标值,并增强了队列的稳定性。仿真试验结果表明NPI算法比PI有更好的性能。PI is a famous active queue management algorithm, but its response is sluggish under heavy congestion, and static parameter setting causes PI sensitive to the network status. To overcome the shortcoming of PI algo-rithm, a new AQM scheme, Neuron based PI, is described in this paper. NPI looks PI controller as an ADALINE with two inputs, and the proportional factor and integral factor of the controller are adjusted online using LMS algo- rithm. NPI can lead to the convergence of the queue length to the desired value quickly and maintain the oscillation small. The simulation results show that NPI has better performance than PI.

关 键 词：拥塞控制 主动队列管理 PI算法 神经元 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]