Decomposition based Multi Objective Evolutionary Algorithms for Design of Large-Scale Water Distribution Networks

• Published in: Water resources management Vol. 30; no. 8; pp. 2749 - 2766
• Main Author: Yazdi, J
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01-06-2016; Springer Nature B.V
• Subjects: Algorithms; Atmospheric Sciences; Case studies; Civil Engineering; Decomposition; Design; Design engineering; Dominance; Earth and Environmental Science; Earth Sciences; Engineering; Environment; Environmental engineering; Evolutionary algorithms; Genetic algorithms; Geotechnical Engineering & Applied Earth Sciences; Hydrogeology; Hydrology/Water Resources; Networks; Optimization; Pareto optimality; Studies; Water distribution; Water pipes; Water resources; Water resources management; Water supply engineering; NSGA2; MOEA; MOEA/D; Optimization; Water distribution network
• ISSN: 0920-4741; 1573-1650
• DOI: 10.1007/s11269-016-1320-z

In last two decades, multiobjective evolutionary algorithms (MOEAs) have shown their merit for solving different optimization problems within the context of water resources and environmental engineering. MOEAs mainly use the concept of Pareto dominance for obtaining the trade-off solutions considering different criteria. A new alternative method for solving multiobjective problems is multiobjective evolutionary algorithm based on decomposition (MOEA/D) which uses scalarizing the objective functions. In this paper, decomposition strategies are developed for the large-scale water distribution network (WDN) design problems by integrating the concepts of harmony search (HS) and genetic algorithm (GA) within the MOEA/D framework. The proposed algorithms are then compared with two well-known non-dominance based MOEAs: NSGA2 and SPEA2 across four different WDN design problems. Experimental results show that MOEA/D outperform the Pareto dominance methods in terms of both non-domination and diversity criteria. MOEA/D-HS in particular could provide very high quality solutions with a uniform distribution along the Pareto front preserving the diversity and dominating the solutions of the other algorithms. It suggests that decomposition based multiobjective evolutionary algorithms are very promising in dealing with complicated large-scale WDN design problems.