ANFIS Based AQM Controller for Congestion Control

Congestion Control is concerned with allocating the network resources such that the network can operate at an optimum performance level when the demand exceeds or it is near the capacity of the network resources. This paper presents a novel scheme of adaptive Neuro-Fuzzy Inference Controller (ANFIS). The advantages of both Fuzzy Logic and Neural Networks are combined together to design the ANFIS. A detailed comparison with the previous developed AQM controller Random Early Detection (RED) has been proposed. Finally, a simulation platform is developed, tested and validated to demonstrate the merits and capabilities of the proposed controller through a set of experiments and scenarios.