模糊自适应算法在网络主动队列管理中的研究

为了改善由于RED算法控制的主动队列管理策略(AQM)系统引起网络响应时间过长,许多文献提出了基于P/PI控制器的AQM策略。但是,由于网络具有非线性特点,论文设计了一种模糊自适应PID控制器的主动队列管理系统,根据队列长度和队列长度变化通过模糊控制规则在线调整PID控制器参数,并用Matlab进行了仿真,验证了当网络出现突发分组时,该算法能够较快的使分组稳定在队列阀值附近,同时不产生队列震荡。

Research of Active Queue Management in Network Based on Self-adjusting Controller Algorithm of Fuzzy

In order to improve time response of network too lengthy based on RED(Random Early Detection) in AQM (Active Queue Management),a lot of literature put forward P/PI controller in AQM.Because network has nonlinear response characteristic,this paper designs a self-adjusting PID controller of fuzzy in AQM.Using this control method,the three parameters of PID controller can be adjusted adaptively on line according to queue length and variety of queue length,meanwhile this method is validated in Matlab.The simulation results show that packets stabilize near the limit range of queue quickly and don't produce vibration when the packets emerge in the network.