BANDWIDTH ALLOCATION OF VIRTUAL PATHS USING NEURAL NETWORKS AND MASKED GENETIC ALGORITHS

The concept of virtual paths has become the key technology in the band networks. In this paper, a control scheme using neural networks（NN） and masked genetic algorithms（MGA） is proposed and applied to the virtual paths in the band networks. The proposed scheme is capable of estimating utilization of the virtual path’s network and selecting adaptively optimal bandwidths of the virtual paths using masked genetic algorithms according to the multirate’s traffic characteristics and network environment. As the optimization problem is constrained, traditional genetic algorithms are no longer applicable to this problem. The authors propose the masked genetic algorithms to solve the optimization problem. Simulation results demonstrate the superiority of this kind of dynamic allocation.