基于Additive2multipl icative 模糊神经网的ATM 网络拥塞控制

考虑了模糊神经网络的学习功能，提出利用Additive-multiplicative模糊神经网络(AMFNN)对ATM网络进行拥塞控制的方案．在拥塞控制过程中，利用AMFNN模糊神经网络预测下一个将要到达流的特征，结合当前缓冲区的队列信息预测网络是否发生拥塞．一旦预测出将有拥塞发生，控制器则向源端反馈拥塞控制信息，信源根据拥塞信息适当降低传输速率，从而避免了拥塞的发生．仿真结果表明，该方法可改善网络对拥塞的实时处理能力，提高网络资源的利用率．

Congestion control in ATM networks based on additive-multiplicative fuzzy neural network

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. 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.