Self-Adaptive PSO-GA Hybrid Model for Combinatorial Water Distribution Network Design

Abstract

In modern civilization, water distribution network has a substantial role in preserving the desired living standard. It has different components such as pipe, pump, and control valve to convey water from the supply source to the consumer withdrawal points. Among these elements, optimal sizing of pipes has great importance because more than 70% of the project cost is incurred on it. Unfortunately, optimal pipe sizing falls in the category of nonlinear polynomial time hard (NP-hard) problems. Hence, solid research activities march on because of two facts, namely, importance and complexity of the problem. The literature revealed that the stochastic optimization algorithms are successful in exploring the combination of least-cost pipe diameters from the commercially available discrete diameter set, but with the expense of significant computational effort. The hybrid model PSO-GA, presented in this paper aimed to effectively utilize local and global search capabilities of particle swarm optimization (PSO) and genetic algorithm (GA), respectively, to reduce the computational burden. The analyses on different water distribution networks uncover that the proposed hybrid model is capable of exploring the optimal combination of pipe diameters with minimal computational effort.