A Dynamic Penalty Function for Constrained Optimization

Abstract

Translate Article

Penalty function methods have been widely used for handling constraints, but it’s still a challenge about how to set the penalty parameter effectively though many related methods have been proposed. In this paper, the penalty parameter is firstly analyzed systematically by introducing four rules. Based on this analysis, a new Dynamic Penalty Function (DyPF) is proposed by adjusting penalty parameter in three different situations during the evolution (i.e., the infeasible situation, the semi-feasible situation, and the feasible situation). The experiments are designed to verify the effectiveness of our newly proposed DyPF. The results show that DyPF presents a better overall performance than other five dynamic or adaptive state-of-the-art methods in the community of constrained evolutionary optimization.