Connection Admission Control in ATM Networks Using Neural Networks

Paul Cullen and Brian Carse, University of the West of England

A number of attempts have been made recently (roughly since 1990) to implement connection admission control (CAC) in ATM networks by means of neural networks. These attempts use various methods and have met with varying levels of success. They all try to solve some very serious networking problems related to the inadequacies of conventional algorithmic computing. Given that there has been little or no adoption of neural network solutions for CAC within the commercial world to date, there are serious questions as to whether or not research scientists are solving the problems which commercial R&D are experiencing. This paper discusses these issues and their relevance to current commercial development.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.