Genetic algorithm and neural network approaches to local access network design

Abstract

This paper examines the utility of genetic algorithms and neural nets for optimization problems occurring in local access network design. It contrasts an existing Hopfield net approach to concentrator assignment with a genetic algorithm approach and finds that the genetic algorithm performs better, while offering greater generality. It describes how genetic algorithms may also be used to solve terminal layout problems, and introduces a representation and special-purpose operators for the solution of concentrator layout problems.<>