Congestion control in ATM networks using additive-multiplicative fuzzy neural network
Zhai Dong-Hai, Li Li, Jin Fan · 2004
Based on additive-multiplicative fuzzy neural network (AMFNN), a novel congestion control scheme for ATM network is presented. This scheme uses AMFNN to accurately predict the traffic arrival patterns. The predicted traffic with the current queue information of the buffer can be used as a measure of congestion. When the congestion level is reached, a control signal is generated to throttle the input arrival rate. Here, the AMFNN model and its learning algorithm are discussed. The simulation results show that this method can improve the congestion processing capability in real time, and raise the utilization of the network resource at the same time.