Research of AQM Strategy Based on Improved Neuron Adaptive PID

In this paper, we use a previously developed nonlinear dynamic model of TCP to design active queue management (AQM) controllers based on improved neuron adaptive PID for network congestion control. We introduce new type of neural networks controller based on PSD (proportion, sum and differential) to improve the lack of fixed gain in single neuron adaptive PID. We give and compare the performances of single neuron adaptive and PSD based on NS-2 simulation platform to support our design. In the end, we prefer to use the BP arithmetic to adjust the coefficients of the PID controller as its better performance at dynamic network load.