Many-Objective Evolutionary Optimization Algorithm based on the Conflict Measurement Grouping Strategy

In order to address the convergence issues faced by traditional multi-objective optimization algorithms as the number of objectives increases, this paper proposes a new optimization algorithm, MaOEA-SPC, based on the conflict measurement grouping strategy. First, due to the inherent correlation between subproblems and many-objective optimization problems, we propose a conflict measurement grouping strategy to facilitate knowledge transfer. Next, we extract the distribution characteristics of Pareto solutions during the evolution process of subproblems to establish a Gaussian distribution model that serves as knowledge information. Subsequently, the new individuals generated by the distribution model are added to the population of MaOPs. Finally, the simulation results indicate that the MaOEA-SPC algorithm effectively enhances the convergence speed of MaOPs without lowering the quality of the solution.