基于二次型优化的神经元PID无线拥塞算法研究  

PID congestion control based on neural network in Ad Hoc Network

作　　者：胡为民[1] 陈亮[1,2] 

机构地区：[1]南通纺织职业技术学院信息系,江苏南通226007 [2]南京理工大学计算机科学与技术学院,江苏南京210094

出　　处：《苏州大学学报（自然科学版）》2009年第3期42-46,共5页Journal of Soochow University(Natural Science Edition)

摘　　要：神经元PID算法能较好地控制瓶颈节点的队列长度,但当网络环境发生较大变化时,其控制效果往往难以保证.根据Ad Hoc网络环境参量时变的特点,推导了无线TCP/AQM离散模型,在神经元算法的加权系数中引入二次型性能指标,设计了一种基于二次型性能指标的神经元PID的AQM.仿真结果表明:在动态拓扑、突发流及链路容量变化的Ad Hoc网络中,该改进算法优于PI算法.Neuron PID can regulate the queue size of a bottleneck node successfully, but its control often is worse when the network state changes. For Ad Hoc network＇s time-varying, it deduced discrete math model of TCP/AQM control object in wireless network. It introduced Quadratic Performance Index to weighting coefficient modification for neuron PID controller. Finally, a neuron Proportional-Intions demonstrate that new algorithm performance is better than PI under different link capacity, dy-amical topology and sudden flow condition.

关 键 词：无线自组网 拥塞控制 二次型性能指标 神经元PID 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]