Optimizing ATM network throughput based on virtual path concept by using genetic algorithm

The article proposes the application of genetic algorithms (GA) for optimizing an asynchronous transfer mode (ATM) network throughput based on the virtual path concept. The M/M/1/K queueing model is used to formulate the throughput of ATM networks which we want to optimize. We show the simple coding method in which each chromosome in the genetic model is represented as the part of each ATM* node pair. Also, the concept of past solution is used for periodical changes of traffic, in order to reduce calculation time. The numerical results show that, by our proposed method, we can obtain the optimum configuration of the ATM network which maximizes the network throughput.