The bandwidth allocation of ATM through genetic algorithm

The authors develop an optimization algorithm based on the genetic algorithm to achieve the bandwidth allocation of the ATM (asynchronous transfer mode) network. Using the ATM technique, one can flexibly reconfigure the network and reassign the bandwidth to meet the requirements of all types of services. By dynamically routing the traffic and adjusting the bandwidth assignment, the average packet delay of the whole network can be reduced to a minimum. The M/M/1 queueing model can be used to analyze the performance. The genetic algorithm is applied to the bandwidth allocation problem of ATM to find the minimum average packet delay of the network. Simulation results show that a delay improvement (41.8%) can be achieved within 30 iterations