Dynamically Expanding Choice-Table Approach to Genetic Algorithm Optimization of Water Distribution Systems

This paper proposes a modified genetic algorithm (GA) for optimization of water distribution systems. A method of dynamically expanding the pipe-choice-table selections and reducing the number of decision variables is introduced, which occurs during a GA run. On the basis of the progressive selection, an initially reduced choice table for each decision variable is allowed to dynamically expand, and then the number of decision variables is gradually reduced. This process enables the GA search to concentrate on promising regions of the search space. The dynamically expanding choice-table genetic algorithm (GADECT) has been applied to a benchmark case study, the New York Tunnels Problem. The results obtained show that the GADECT yields a superior performance in terms of solution quality and computational efficiency.