【摘要】 针对TCP网络的拥塞控制问题,考虑了TCP负载和往返时延具有较大的突发性和时变性的情况,结合滑模控制与RBF神经网络提出了一种主动队列管理算法。考虑到网络系统参数是未知时变的,采用RBF神经网络逼近网络系统参数,从而使得主动队列管理算法易于实现。依据李雅普诺夫稳定性理论设计了RBF神经网络权值的自适应律,使得网络系统参数得到了较好的估计。采用RBF神经网络的输出作为滑模控制器的参数设计了一种主动队列管理算法,使得网络系统是渐近稳定的。仿真结果表明所提出的算法与比例积分控制器和传统的滑模控制器相比具有较快的响应和稳定的队列长度,在网络参数变化时仍能获得较好的鲁棒性。更多还原

【Abstract】 To save the problem of congestion control in transmission control protocol(TCP) networks,by incorporating sliding mode control with radial basis function(RBF) neural networks,an active queue management algorithm is presented in presence of TCP load and round trip time which are more abrupt and time-varying.Since network system parameters are unknown and time-varying,the RBF neural networks were used to approximate the network system parameters so that the active queue management algorithm was easily implemented.The network system parameters are well estimated by updating the RBF neural network weights according to Lyapunov theory.By using the output of the RBF neural network as the sliding mode controller parameters,an active queue management algorithm was designed to guarantee the network system was asymptotically stable.Compared with proportional-integral controller and conventional sliding mode controller,simulation results show that the proposed algorithm has fast system response and steady queue length as well as better robustness under various network conditions.更多还原