A new PID controller for AQM based on neural network

Active queue management (AQM) plays a significant role in network congestion. A new adaptive PID controller for AQM is presented to overcome the shortcomings of PID AQM such as parameters cannot be adjusted with time, cannot be adapted to the dynamic and nonlinear network. The new algorithm integrates PID control law and neural network, which not only has the merits of both but also overcomes the shortcomings of the general neural network. The results of simulation show that the new AQM algorithm is superior to a typical PID controller on the time delay, throughput and queue stability.