A Framework for Comparing Multi-Objective Optimization Approaches for a Stormwater Drainage Pumping System to Reduce Energy Consumption and Maintenance Costs

Reducing energy consumption and maintenance costs of a pumping system is seen as an important but difficult multi-objective optimization problem. Many evolutionary algorithms, such particle swarm (PSO), (MOPSO), non-dominated sorting genetic algorithm II (NSGA-II) have been used. However, lack comparison between these approaches poses challenge to the selection approach for stormwater drainage stations. In this paper, new framework comparing proposed. Two kinds approaches, single-objective optimization, are considered. Three representing two types selected comparison, including PSO with linear weighted sum method (PSO-LWSM), MOPSO technique order preference by similarity ideal solution (MOPSO-TOPSIS), NSGA-II TOPSIS (NSGA-II-TOPSIS). Four objectives based on number pump startups/shutoffs, working hours, consumption, capacity considered, which first ones quantified in terms operational economy paper. methods—TOPSIS (E&C)—are The demonstrated tested case China. average values comprehensive evaluation index three 0.021, 0.154, 0.375, respectively, E&C 0.785, 0.813, 0.839, respectively. results show that PSO-LWSM has better results. validate efficiency framework. proposed will help find systems reduce costs.