Water Distribution System Design Using Multi-Objective Genetic Algorithm with External Archive and Local Search

TL;DR

This paper introduces a hybrid multi-objective genetic algorithm with external archive and local search to improve water distribution system design, demonstrating enhanced solution quality and new solutions for medium-sized networks.

Contribution

The paper presents a novel hybrid algorithm combining NSGA-II, external archive, and local search for better water network design solutions.

Findings

Local search found new solutions for one network.

External archive improved the non-dominated set.

Hybrid approach outperformed standard methods.

Abstract

Hybridisation of the multi-objective optimisation algorithm NSGA-II and local search is proposed for water distribution system design. Results obtained with the proposed algorithm are presented for four medium-size water networks taken from the literature. Local search is found to be beneficial for one of the networks in terms of finding new solutions not reported earlier. It is also shown that simply using an external archive to save all non-dominated solutions visited by the population, even without local search, leads to substantial improvement in the non-dominated set produced by the algorithm.