Neural network-based real-time dynamic nonhierarchical network routing for B-ISDN

We propose a neural network method for B-ISDN real-time dynamic nonhierarchical network routing in this paper. This method can optimize routing according to VCC request and resource of network, balance average call blocking rate and average routing distance of a global network, and reduce average call setup time. We give the routing algorithm and energy function of the Hopfield neural network. Finally, our simulation results show that the proposed neural network method is very effective