Active Queue Management Algorithm Based on Neuron Dynamical Compensation PID Control

An active queue management (AQM) scheme based on neuron dynamical compensation PID control is proposed, it combines the advantages of neural network and traditional PID control. Through the way of learning and controlling on line to solve the insufficiency of traditional PID, and the controlled parameters can be adjusted online to ensure the stability of the network system around the desired operating point. Using the Jury stability standard gives the conditions to ensure the controlled system stability around its desired operating point. Simulation results demonstrate that this control scheme can lead to the convergence of the queue length to the desired value quickly and maintain the oscillation small. The results also show that this scheme is very robust to disturbance and outperforms the traditional PID controller significantly.