Gene Expression Programming Algorithms for Optimization of Water Distribution Networks

Abstract

Water distribution system (WDS), as the important and expensive infrastructure, plays a crucial role in supplying water for the citizens living in the urban areas. The huge cost of the system drives researchers to seek the optimal cost design. During the last several decades, evolutionary methods such as genetic algorithms (GA), ant colony optimization algorithms (ACO) and simulated annealing (SA) have been found to explore the optimal combination of pipe diameters for design of WDS. However, in the case of complex distribution network, those methods suffer with low computational efficiency. In this paper, the gene expression programming (GEP) algorithms, a method based on the genetic algorithms, is adopted to solve the optimal design of WDS. This method is applied to the Hanoi benchmark network, the result of 6.081 million costs and 15,000 evaluations is combined with that obtained with GA and SA. From the results, it is observed that the proposed algorithm is an advanced alternative for the design of WDS, taking the computational efficiency and the ability of finding global or near-global optimal solutions into consideration.