Routing in broadband communication networks using neural computations

Abstract

This paper will briefly review some of the published work on applying Artificial Neural Networks (ANN) to routing in Asynchronous Transfer Mode (ATM) networks and critically appraise some of the conclusions which have been drawn from these studies. The paper will go on to explain the design and implementation of a simulation of a neural network array superimposed on a simulated ATM network. The results of routing experiments, which were compared with decisions made using Shortest Path First (SPF) routing, will be discussed and the need for appropriate comparison metrics explained. The paper will end with a review of what needs to be considered when the applicability of ANNs to ATM network control is being assessed and the required functionality of simulation tools which allow these assessments to be made.