变长分组Banyan网中排队的神经网络调度  

Neural Network Based Scheduling for Banyan Network with Variable-Length Packets

作　　者：李生红[1] 薛质[1] 诸鸿文[1] 潘理[1] 

机构地区：[1]上海交通大学电子工程系,上海200030

出　　处：《上海交通大学学报》2001年第6期866-869,共4页Journal of Shanghai Jiaotong University

基　　金：上海邮电管理局 -上海交通大学联合信息通信技术实验室资助基金项目 !(1999-GR1-3)

摘　　要：提出了适用于变长分组情形下进行调度的系统结构 ;给出了分组调度的具体原则 ;基于所给出的调度原则 ,研究了利用 Hopfield神经网络实现优化调度的方法和在硬件电路上的可实现性 .The input-output-queuing scheduling problem in Banyan network with variable-length packets was studied, and a scheduling approach based on neural network was proposed. For the proposed approach, a scheduling system structure fit for the variable-length packet case is proposed at first. Then some rules for scheduling are given. At last, based on the rules, an optimal scheduling approach using Hopfield neural network is given. Furthermore, the paper indicated that the approach can be realized by hardware circuit. The simulation results show the effectiveness of the proposed approach.

关 键 词：BANYAN网 神经网络 排队 多级互联网络 分组调度 通信网 分组网 交换结构 

分 类 号：TN919.21[电子电信—通信与信息系统]