Optimizing ATM network configuration based on virtual path concept using genetic algorithm

This article proposes the application of a genetic algorithm (GA) for optimizing the asynchronous transfer mode (ATM) network configuration based on the virtual path (VP) concept. The multi-objective function which comprises of the average blocking rate (ABR) and the average packet delay (APD) is used as the network constraint which we want to minimize in our optimization method. We show the simple coding technique in which each chromosome is represented as the configuration of the ATM network. Also the concept of the past solution is used in order to reduce the calculation time for adaptive configuration control. The numerical results show that by our proposed method, the optimum configuration of the ATM network based on the VP concept also maximizes the ATM network throughput.