Multiobjective optimization of the operation of water distribution systems with variable speed pumps

Faced with the urban population growth and the importance of water as a limited natural resource, there is a need to implement techniques to reduce the operational costs of water distribution systems and ensure adequate supply. The optimization of pump operation can be used to meet the demands of consumption with a lower energy cost, in addition to maximizing hydraulic reliability. In this work, a hybrid optimization/simulation model was developed based on the multiobjective genetic algorithms and the EPANET hydraulic simulator. The NSGA II (Non-dominated Sorting Genetic Algorithm II) method was used to optimize the operation of variable rotation pumps, that is, the decision variables of the problem were the rotation of the pumps for each hour throughout the day. A modification of the original EPANET hydraulic simulator, which does not correctly compute the efficiency of variable-speed pumps, was employed so that the power of each pump, and consequently the cost of electric power, was calculated correctly. Non-dominated solution sets (Pareto Front) were obtained considering first the negative pressure penalty at the nodes and, subsequently, the negative pressure penalties at the nodes and the closure/shutdown of tubes and/or pumps. The method has been applied in the hypothetical network called ANYTOWN and lower energy costs were obtained considering Brazilian energy tariffs.