A Hybrid Evolutionary Algorithm Based on Clustering Good-Point Set Crossover for Constrained Optimization

A hybrid evolutionary algorithm based on multi-parent crossover of clustering good-point set and adaptive constraint-handling technique is proposed in this paper for solving constrained optimization problems. As for search mechanism, it utilizes good-point set to construct the initialization population that is scattered uniformly over the entire search space in order to maintain the diversity. The individuals of population are divided into several sub-populations according to the similarity of the two parents. The parents are selected randomly from the several sub-populations to arrange the crossover operation. The crossover operator can effectively make use of the information carried by the parents and generate representation offspring in order to maintain and increase the diversity of population. In addition, a local search scheme is introduced to enhance the local search ability and speed up the convergence of the proposed algorithm. As for constraint-handling technique, a new individual comparison criterion is proposed, which can adaptively select different individual comparison criterion according to the proportion of feasible solution in current population. The proposed algorithm is tested on 15 well-known benchmark functions, and the empirical evidence shows its effectivity.