Work

From penalty function to learning-driven: evolution and perspectives of constrained multi-objective evolutionary algorithm

Year: 2025

Type: article

Abstract: With the increasing prevalence of constrained multi-objective optimization problems (CMOPs) in complex systems, balancing constraints and multi-objective conflicts has become a key challenge in evolutionary algorithm research. This paper systematically reviews the development of constrained multi-objective evolutionary algorithms (CMOEAs), focusing on the evolution from traditional penalty-based methods to learning-driven approaches for handling complex CMOPs. It also explores how learning strategies, such as adaptive learning, deep learning, and knowledge transfer, efficiently handle constraints. Finally, the paper reviews various applications of CMOEAs in CMOPs and discusses the potential of next-generation intelligent, learning-driven CHTs in more complex scenarios.

Source: Swarm and Evolutionary Computation

DOI: 10.1016/j.swevo.2025.102006

Authors: Min Hu, Gang Huang, Xueying Yang, Jinwei Xiao, Xun Wang, Tiantian Zhang

Institution: Space Engineering University

Language: English

Topic: Advanced Multi-Objective Optimization Algorithms

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,690

Funder: National Natural Science Foundation of China