Application of several meta-heuristic techniques to the optimization of real looped water distribution networks

The optimization of looped water distribution systems is a complex problem as the pipe flows are unknown variables. Although many researchers have reported algorithms for minimizing the network cost applying a large variety of techniques, such as linear programming, non-linear programming, global optimization methods and meta-heuristic approaches, a totally satisfactory and efficient method is not available as yet. Many works have assessed the performance of these techniques using small or medium-sized benchmark networks proposed in the literature, but few of them have tested these methods with large-scale real networks, The aim of this paper is to evaluate the performance of several meta-heuristic techniques: genetic algorithms, simulated annealing, tabu search, and iterated local search. These techniques were first validated and compared by applying them to a medium-sized benchmark network previously reported in the literature. They were then applied to a large irrigation water distribution network that has been proposed in a previous work to assess their performance in a practical application. All the methods tested performed adequately well, compared with the results found in previous works. Genetic algorithm was more efficient when dealing with a medium-sized network, but other methods outperformed it when dealing with a real complex one.