A two‐stage many‐objective evolutionary algorithm with dynamic generalized Pareto dominance

Abstract

Many-objective evolutionary algorithms (MaOEAs) are widely used to solve many-objective optimization problems. As the number of objectives increases, it is difficult to achieve a balance between the population diversity and the convergence. Additionally, the selection pressure decreases rapidly. To tackle these issues, this paper proposes a two-stage manyobjective evolutionary algorithm with dynamic generalized Pareto dominance (called TS-DGPD). First, a two-stage method is utilized for environmental selection. The first stage employs the cosine distance to accelerate the convergence. The second stage uses L p -norm maintain the population diversity.Moreover, a dynamic generalized Pareto dominance (DGPD) is used to increase the selection pressure of the population. To evaluate the performance of TS-DGPD, we compare it with several other MaOEAs on two benchmark sets with 3, 5, 8, 10, 15, and 20 objectives. Experimental results show that TS-DGPO performs satisfactorily on convergence and diversity.