Bandwidth allocation in ATM networks using genetic algorithms and neural networks

We propose a control scheme for the bandwidth allocation in ATM networks. The scheme is based on genetic algorithms and neural networks and thus is capable of selecting adaptively optimal step sizes of virtual paths. For the optimization problem is constrained, traditional genetic algorithms no longer are applicable. We, therefore, propose the masked genetic algorithms with seeds (MGAS) to solve the problem. To achieve better performance, the relationships among the QOS measures and the evaluation of seed scores are discussed.