Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (35): 123-125.DOI: 10.3778/j.issn.1002-8331.2010.35.035

• 网络、通信、安全 • Previous Articles     Next Articles

Research on improved neural network PID congestion control in ad hoc network

HU Wei-min   

  1. Department of Information,Nantong Textile Vocational Technology College,Nantong,Jiangsu 226007,China
  • Received:2009-04-15 Revised:2009-07-24 Online:2010-12-11 Published:2010-12-11
  • Contact: HU Wei-min

改进神经元PID无线拥塞研究

胡为民   

  1. 南通纺织职业技术学院 信息系,江苏 南通 226007
  • 通讯作者: 胡为民

Abstract: Neuron PID can regulate the queue size of a bottleneck node successfully,but its control effect is worse when the network state changes.For ad hoc network’s time-varying,it deduces discrete math model of TCP/AQM control object in wireless network.It introduces quadratic performance index to weighting coefficient modification for neuron PID controller.Furthermore neuron gain K is system sensitive coefficient.So constant K can’t be fit for time-varying ad hoc network.Finally,a new improved quadratic performance index neuron PID AQM is proposed.Matlab and NS-2 simulations demonstrate that the performance of new algorithm is better than PI under different link capacity,dynamical topology and sudden flow condition.

Key words: ad hoc network, congestion control, quadratic performance index, improved neuron PID

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。另外神经元增益K是系统敏感参数,而恒定的K值不易适应时变的无线自组织网络,据此设计了一种改进二次型性能指标神经元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。

关键词: 无线自组网, 拥塞控制, 二次型性能指标, 改进神经元PID

CLC Number: