Design optimization of water distribution networks through a novel differential evolution

Abstract

Optimization algorithms have proven to be a useful tool in different areas of water resource management including water distribution network (WDN), which may be modelled as a large scale, combinatorial problem subject to constraints with the typical objective of minimizing the cost. In this study, a fuzzy C-means adaptive differential evolution (FCADE) is proposed to solve three well-known WDN problems: the two-loop distribution network problem, the Hanoi distribution network problem, and New York tunnel distribution network problem. FCADE is integrated with a well-known simulation software EPANET to manage the pressure constraints requirement. A comparative analysis of results through various performance metrics indicate the competence of FCADE for solving complex WDN problems.