Genetic algorithms in bus network optimization

This paper focuses on a new method to compute fitness function (ff) values in genetic algorithms for bus network optimization. In the proposed methodo logy, a genetic algorithm is used to generate iteratively new populations ( sets of bus networks). Each member of the population is evaluated by comput ing a number of performance indicators obtained by the analysis of the assi gnment of the O/D demand associated to the considered networks. Thus, ff va lues are computed by means of a multicriteria analysis executed on the perf ormance indicators so found. The goal is to design a heuristic that allows to achieve the best bus network satisfying both the demand and the offer of transport. (C) 2001 Elsevier Science Ltd. All rights reserved.