Multiobjective Differential Evolution for Higher-Dimensional Multimodal Multiobjective Optimization  

作　　者：Jing Liang Hongyu Lin Caitong Yue Ponnuthurai Nagaratnam Suganthan Yaonan Wang 

机构地区：[1]School of Electrical and Information Engineering,Zhengzhou University,Zhengzhou 450001 [2]School of Electrical Engineering and Automation,Henan Institute of Technology,Xinxiang 453003,China [3]School of Electrical and Information Engineering,Zhengzhou University,Zhengzhou 450001,China [4]KINDI Center for Computing Research,Qatar University,Doha,Qatar,and also with the Nanyang Technology University,Singapore [5]College of Electrical and Information Engineering,and also with the National Engineering Research Center for Robot Visual Perception and Control Technology,Hunan University,Changsha 410082,China [6]IEEE

出　　处：《IEEE/CAA Journal of Automatica Sinica》2024年第6期1458-1475,共18页自动化学报（英文版）

基　　金：supported in part by National Natural Science Foundation of China(62106230,U23A20340,62376253,62176238);China Postdoctoral Science Foundation(2023M743185);Key Laboratory of Big Data Intelligent Computing,Chongqing University of Posts and Telecommunications Open Fundation(BDIC-2023-A-007)。

摘　　要：In multimodal multiobjective optimization problems(MMOPs),there are several Pareto optimal solutions corre-sponding to the identical objective vector.This paper proposes a new differential evolution algorithm to solve MMOPs with higher-dimensional decision variables.Due to the increase in the dimensions of decision variables in real-world MMOPs,it is diffi-cult for current multimodal multiobjective optimization evolu-tionary algorithms(MMOEAs)to find multiple Pareto optimal solutions.The proposed algorithm adopts a dual-population framework and an improved environmental selection method.It utilizes a convergence archive to help the first population improve the quality of solutions.The improved environmental selection method enables the other population to search the remaining decision space and reserve more Pareto optimal solutions through the information of the first population.The combination of these two strategies helps to effectively balance and enhance conver-gence and diversity performance.In addition,to study the per-formance of the proposed algorithm,a novel set of multimodal multiobjective optimization test functions with extensible decision variables is designed.The proposed MMOEA is certified to be effective through comparison with six state-of-the-art MMOEAs on the test functions.

关 键 词：Benchmark functions diversity measure evolution-ary algorithms multimodal multiobjective optimization. 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]