DMEA-II: the direction-based multi-objective evolutionary algorithm-II

作     者：Long Nguyen Bui, Lam T. Abbass, Hussein A. 

作者机构：Le Quy Don Tech Univ Fac Informat Technol Hanoi Vietnam Univ New S Wales Australian Def Force Acad Canberra ACT Australia 

出 版 物：《SOFT COMPUTING》 (Soft Comput.)

年 卷 期：2014年第18卷第11期

页      面：2119-2134页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Vietnam's National Foundation for Science and Technology (NAFOSTED) [102.01-2010.12] 

主　　题：Multi-objective evolutionary algorithms Direction-based MOEAs Performance measurement DMEA 

摘      要：This paper discusses the use of direction of improvement in guiding multi-objective evolutionary algorithms (MOEAs) during the search process towards the area of Pareto optimal set. We particularly propose a new version of the Direction based Multi-objective Evolutionary Algorithm (DMEA) and name it as DMEA-II. The new features of DMEA-II includes (1) an adaptation of the balance between convergence and spreading by using an adaptive ratio between the convergence and spreading directions being selected over time;(2) a new concept of ray-based density for niching;and (3) a new selection scheme based on the ray-based density for selecting solutions for the next generation. To validate the performance of DMEA-II, we carried out a case study on a wide range of test problems and comparison with other MOEAs. It obtained quite good results on primary performance metrics, namely the generation distance, inverse generation distance, hypervolume and the coverage set. Our analysis on the results indicates the better performance of DMEA-II in comparison with the most popular MOEAs.