STUDY OF SENSITIVITY OF THE PARAMETERS OF A GENETIC ALGORITHM FOR DESIGN OF WATER DISTRIBUTION NETWORKS

Journal Of Urban And Environmental Engineering

Endereço:
UFPB/CT
João Pessoa / PB
Site: http://www.journal-uee.org
Telefone: (83)3216-7684
ISSN: 1982-3932
Editor Chefe: Celso Augusto Guimarães Santos
Início Publicação: 31/12/2006
Periodicidade: Semestral
Área de Estudo: Engenharia civil

STUDY OF SENSITIVITY OF THE PARAMETERS OF A GENETIC ALGORITHM FOR DESIGN OF WATER DISTRIBUTION NETWORKS

Ano: 2007 | Volume: 1 | Número: 2
Autores: Pedro L. Iglesias, Daniel Mora, F. Javier Martinez, Vicente S. Fuertes
Autor Correspondente: Pedro L. Iglesias | [email protected]

Palavras-chave: algorithms, design, water networks, reliability

Resumos Cadastrados

Resumo Inglês:

The Genetic Algorithms (GAs) are a technique of optimization used for water distribution networks design. This work has been made with a modified pseudo genetic algorithm (PGA), whose main variation with a classical GA is a change in the codification of the chromosomes, which is made of numerical form instead of the binary codification. This variation entails a series of special characteristics in the codification and in the definition of the operations of mutation and crossover. Initially, the work displays the results of the PGA on a water network studied in the literature. The results show the kindness of the method. Also is made a statistical analysis of the obtained solutions. This analysis allows verifying the values of mutation and crossing probability more suitable for the proposed method. Finally, in the study of the analyzed water supply networks the concept of reliability in introduced. This concept is essential to understand the validity of the obtained results. The second part, starting with values optimized for the probability of crossing and mutation, the influence of the population size is analyzed in the final solutions on the network of Hanoi, widely studied in the bibliography. The aim is to find the most suitable configuration of the problem, so that good solutions are obtained in the less time.