文献类型：会议论文

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, Shenyang, Liaoning 110004, China; [2] Research Institute of Wood Industry, Chinese Academy of Forestry, Beijing 100091, China

会议论文集：Intelligent Control and Automation: International Conference on Intelligent Computing, ICIC 2006

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 - Traffic congestion

年份：2006

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. ? Springer-Verlag Berlin/Heidelberg 2006.