摘要：Multimodal multiobjective optimization problem (MMOP) is a special kind of multiobjective optimization problem (MOP) with multimodal characteristics, where multiple different Pareto optimal sets (PSs) map to the same Pareto optimal front (PF). To handle MMOPs, a decomposition-based harmony search algorithm (called MOEA/D-HSA) is devised. In MOEA/D-HSA, multiple individuals who are assigned to the same weight vector form a subpopulation for finding multiple different PSs. Then, an environmental selection method based on greedy selection is designed to dynamically adjust the subpopulation scale for keeping the population diversity. Finally, the modified harmony search algorithm and elite learning strategy are utilized to balance the diversity and convergence of the population. Experimental results on the CEC 2019 test suite reveal that MOEA/D-HSA has superior performance than a few state-of-the-art algorithms.
