Design of a Robust Active Queue Management Altorithm Based on Adaptive Neuron Pid

The paper designs a new AQM algorithm called ANPID, which applies the theory of adaptive linear neuron to AQM controller in congestion control. ANPID can adjust the queue length to the desired value, revise its weights online by LMS learning rule, and tune the coefficients of PID controller. The weighted factors are regulated continuously according to the system errors, as well as eliminate the sensitivity to the parameter. The result of simulation shows that the presented ANPID controller can effectively avoid network congestion, stabilize queue length to the desire value quickly, and have good performances in respect to robustness to variation of system parameters