An Efficient Method for Maintaining Diversity in Evolutionary Multi-objective Optimization

摘要

Diversity maintenance of solutions is a crucial part in multi-objective optimization. In this paper, a maintenance method which is based on minimum spanning tree is proposed. The proposed method defines a density estimation metric – Minimum Spanning Tree Crowding Distance (MSTCD). Moreover, information of degree of solution combined with MSTCD is employed to truncate population. From an extensive comparative study with three other methods on a number of two and three objective test problems, it is observed that the proposed algorithm has good performance in distribution.