Banyan网输入输出排队的神经网络调度及其实现  

Neural Network－Controlled Banyan Network with Input－Output－Queueing and Its Implementation

作　　者：南华[1] 刘泽民[1] 

机构地区：[1]北京邮电大学

出　　处：《电子学报》1997年第7期120-123,共4页Acta Electronica Sinica

摘　　要：Ｂａｎｙａｎ网是一种多级互联网络，它广泛地应用在ＡＴＭ交换结构中．Ｂａｎｙａｎ网输入排队的神经网络调度方法已有文章提出，但其硬件实现比较复杂．本文提出了一种Ｂａｎｙａｎ网输入输出排队的神经网络调度方法，它的硬件实现容易．计算机模拟结果表明，该调度方法是非常有效的．在此，还给出了该系统的硬件实现方法．The Banyan network is a kind of multistage interconnection networks (MINs) and is widly used as a building block in ATM switch fabric designs. The neural network controlled Banyan networks have been proposed in some papers but its hardward implementation is complicated. In this paper we propose a new neural network controlled Banyan network with input-output-queueing. Its neural network controller is easy to implement. Our simulation results show that this mathod is very efficient. Here,we give its hardware implementation.

关 键 词：ATM 神经网络 信元调度 BANYAN网 B-ISDN 

分 类 号：TN913.24[电子电信—通信与信息系统]