ROUTING IN BROAD-BAND COMMUNICATION-NETWORKS USING NEURAL COMPUTATIONS

This paper will briefly review some of the published work on applying Artificial Neural Networks (ANN) to routing in Asynchronous Transfer M ode (ATM) networks and critically appraise some of the conclusions whi ch have been drawn from these studies. The paper will go on to explain the design and implementation of a simulation of a neural network arr ay superimposed on a simulated ATM network. The results of routing exp eriments, which were compared with decisions made using Shortest Path First (SPF) routing, will be discussed and the need for appropriate co mparison metrics explained. The paper will end with a review of what n eeds to be considered when the applicability of ANNs to ATM network co ntrol is being assessed and the required functionality of simulation t ools which allow these assessments to be made. (C) 1998 IMACS/Elsevier Science B.V.