文献类型：期刊文献

英文题名：Neural Network Training Using PSO Algorithm in ATM Traffic Control

作者：Jing, Yuan-wei[1] Ren, Tao[1] Zhou, Yu-cheng[2]

第一作者：Jing, Yuan-wei

机构：[1] Northeastern University, Liaoning, Shenyang, 110004, China; [2] Research Institute of Wood Industry, Chinese Academy of Forestry, Beijing, 100091, China

年份：2006

卷号：344

起止页码：341-350

外文期刊名：Lecture Notes in Control and Information Sciences

收录：EI(收录号：20232514280784)

语种：英文

外文关键词：Adaptive control systems - Advanced traffic management systems - Air traffic control - Delay control systems - Global optimization - Neural networks - Particle swarm optimization (PSO) - Quality control - Quality of service - Traffic congestion

摘要：In this paper, we address an end-to-end congestion control algorithm for available bit-rate traffic in high speed asynchronous transfer mode network. A neural network controller is proposed, because the precise characteristics of the switching system architecture are not known and some conditions such as time delay and network load change over time. The particle swarm optimization algorithm, which characterizes fast convergence and global minimum is introduced in neural network weights training. Simulation results show that the control system is adaptive, robust and effective, the quality of service is guaranteed. ? 2006, Springer-Verlag Berlin Heidelberg.