Multiobjective design of water distribution networks using modified NSGA-II algorithm

• Published in: Water science & technology. Water supply 2023-03, Vol.23 (3), p.1220-1233
• Main Authors: Naidu, M. Naveen, Vasan, A., Varma, Murari R. R., Patil, Mahesh B.
• Format: Article
• Language: English
• Subjects: balerma network; hanoi network; new york network; nsga-ii; water distribution network
• ISSN: 1606-9749; 1607-0798
• DOI: 10.2166/ws.2023.035

Optimally designed water distribution networks (WDNs) make engineers’ tasks difficult due to various challenges like non-linearity between head-loss and flow, commercially available distinct diameters, combinatorial, nondeterministic polynomial-time hard problems and a large number of decision variables. This paper develops a new hybrid NSGA-II algorithm augmented with a random multi-point crossover operator and a local search denoted by RLNSGA-II to design the multiobjective WDN. The efficiency of the proposed algorithm (RLNSGA-II) is tested on three benchmark problems, namely New York, Hanoi and Balerma networks. The results obtained are compared with the best-known algorithms available in the literature. The results have shown that the proposed algorithm RLNSGA-II has found better converged and distributed solutions for all three representative benchmark problems considered in the literature consistently and evidently when compared with the best-known approximation of solutions published. Furthermore, as the complexity of the WDN increases, its advantages over other algorithms become more significant.