A Coevolutionary Algorithm Based on Dominance and Decomposition for Constrained Multiobjective Optimization

Solving constrained multiobjective optimization problems (CMOPs) by constrained multiobjective evolutionary algorithms (CMOEAs) has been a timely research topic in recent years. While various improvement strategies have been proposed in existing studies, the dominance-based and decomposition-based frameworks are usually used independently, despite their complementary characteristics on different problem types-dominance excels in feasibility handling while decomposition offers directional guidance-which could jointly enhance search performance when properly integrated. With this in mind, this article proposes a coevolutionary algorithm using both dominance-based and decomposition-based frameworks to coevolve two populations, thereby leveraging their respective advantages. Specifically, the dominance-based population optimizes a dynamic problem derived from the original problem and achieves diversity preservation through a tolerance-based selection strategy, while the decomposition-based population focuses on the unconstrained Pareto front in the early stage and the constrained Pareto front in the later stage through stage identification, objective switching, and relevance-based selection strategy, thereby directly addressing the limitation of isolated framework usage. In addition, populations with different frameworks are capable of sharing information between parents and offspring during offspring generation and environmental selection, respectively, enabling mutual reinforcement that existing single-framework or loosely coupled approaches lack. Experimental results with 11 state-of-the-art CMOEAs on four benchmark suites and five real-world CMOPs demonstrate the performance advantages of the proposed algorithm.