论文部分内容阅读
针对传输控制协议(Transmission Control Protocol,TCP)网络存在网络参数不确定和UDP流干扰的拥塞问题,提出了一种基于终端滑模控制的自适应有限时主动队列管理算法。为了避免事先获得TCP网络参数的不确定和UDP流干扰的界,使用RBF神经网络估计了参数的不确定和干扰。为了使瞬时队列长度能在有限时间内收敛到目标队列长度,基于终端滑模控制方法设计了一种自适应有限时控制器。应用网络模拟器NS2验证了所提出的算法在不同情况下的优越性。
In order to solve the problem of network parameter uncertainty and UDP flow jamming in Transmission Control Protocol (TCP) network, an adaptive finite-time active queue management algorithm based on terminal sliding mode control is proposed. In order to avoid the prejudice of TCP network parameter uncertainty and UDP flow interference in advance, the RBF neural network is used to estimate the parameter uncertainty and interference. In order to make the instantaneous queue length converge to the target queue length in a finite time, an adaptive finite-time controller is designed based on terminal sliding mode control. The application of network simulator NS2 verifies the superiority of the proposed algorithm in different situations.