A new multi-objective evolutionary algorithm for the optimization of water distribution networks

Abstract This work introduces a new bi-objective optimization model for the design of water distribution network (WDN). Reliability and cost are two contradicting objectives that optimized. The evolutionary technique multi-objective (MO) Jaya, hereafter referred as MO-JAYANET, is developed optimal WDN. EPANET used hydraulic solver in this study. concept constraint violation, dominance, non-dominance crowding distance to develop MO-JAYANET. As Jaya algorithm parameter-less technique, with dominance involved MO model, penalty parameter required penalize non-feasible solution also dropped. makes MO-JAYANET completely requiring no tuning at all. applied on benchmark networks from literature using three different reliability indices Resilience Index, Network Modified Index. found be very easy efficient WDN optimization. present obtains smooth Pareto Front (PF) overlaps best-known PF. maximum diameters obtained by simulated both mechanical failures under scenarios identify better-performing index.