A neural network approach for routing in computer networks

This paper presents a new approach based on artificial neural networks to solve the routing problem in a context of computer network design. This approach is based on a network representation enabling one to match each network configuration with a Hopfield (1984) neural network in order to find the best path between any node pair by minimizing an energy function. It is suitable to be integrated into an overall topological design process of moderate-speed and high-speed networks subject to quality of service constraints as well as to changes in configuration and link costs.