An integrated framework for traffic control in ATM networks based on soft-computing techniques

In this paper we assess the application of artificial intelligence techniqu es to the complex problem of traffic control in Asynchronous Transfer Mode (ATM) networks. The paper deals with the close link between Call Admission Control (CAC) and Usage Parameter Control (UPC) and proposes a simulation-b ased analysis to demonstrate how inefficiency on the part of policing affec ts bandwidth allocation. To take this into account, the paper proposes a fr amework for traffic control in which the CAC and policing functions are bot h based on artificial intelligence techniques, i.e., neural networks and fu zzy logic. A measurement-based CAC mechanism is then proposed and implement ed by means of neural networks trained in such a way as to take into accoun t the real behaviour of the policer. As the results obtained show, this all ows us to implement traffic management strategies that can improve the expl oitation of network resources. (C) 2001 Elsevier Science Inc. All rights re served.