Self-adaptive multi-objective evolutionary algorithm based on decomposition for large-scale problems: A case study on reservoir flood control operation

Abstract

Large-scale multi-objective optimization problems (LS-MOP) are complex problems with a large number of decision variables. Due to its high-dimensional decision space, LS-MOP poses a significant challenge to multi-objective optimization methods including multi-objective evolutionary algorithms (MOEAs). Following the algorithmic framework of multi-objective evolutionary algorithm based on decomposition (MOEA/D), an enhanced algorithm with adaptive neighborhood size and genetic operator selection, named self-adaptive MOEA/D (SaMOEA/D), is developed for solving LS-MOP in this work. Learning from the search history, each scalar optimization subproblem in SaMOEA/D varies its neighborhood size and selects a genetic operator adaptively. The former determines the size of the search scope, while the latter determines the search behavior and as a result the newly generated solution. Experimental results on 20 LS-MOP benchmarks have demonstrated that SaMOEA/D outperforms or performs similarly to the other four state-of-the-art MOEAs. The effectiveness of the self-adaptive strategies has also been experimentally verified. Furthermore, SaMOEA/D and the comparing algorithms are then applied to solve a challenging real-world problem, the multi-objective reservoir flood control operation problem. Optimization results illustrate the superiority of SaMOEA/D.