This paper addresses the use of fuzzy neural networks （FNN） for predicting the nonlinear network traffic. Through training the fuzzy neural networks with momentum back-propagation algorithm （MOBP） and choosing the appropriate activation function of output node, the traffic series can be well predicted by these structures. From the effective forecasting results obtained, it can be concluded that fuzzy neural networks can be well applicable for the traffic series prediction. In addition,the performance of the FNN was particularly discussed and analyzed in terms of prediction ability compared with solely neural networks. The effectiveness of the oroBosecl FNN is demonstrated through the simulation.
WANG Zhao-xiaSUN Yu-gengZHANG QiangQIN JuanSUN Xiao-weiSHEN Hua-yu
A supervised genetic algorithm (SGA) is proposed to solve the quality of service (QoS) routing problems in computer networks. The supervised rules of intelligent concept are introduced into genetic algorithms (GAs) to solve the constraint optimization problem. One of the main characteristics of SGA is its searching space can be limited in feasible regions rather than infeasible regions. The superiority of SGA to other GAs lies in that some supervised search rules in which the information comes from the problems are incorporated into SGA. The simulation results show that SGA improves the ability of searching an optimum solution and accelerates the convergent process up to 20 times.
