Application of neural network based fuzzy logic control in the network congestion control

A active queue management (AQM) scheme is presented to provide congestion control using the combination of neural network and fuzzy logic control approach. The proposed method allows neural network to achieve fuzzy logic reasoning, which can adjust the membership function parameters and weights adaptively, and optimize the fuzzy logic controller. Simulation results demonstrate that it can lead to the convergence of the queue length to the desired value quickly and maintain the small oscillation. So, the scheme has better performace and robustness than the traditional PD controllers.