A multi-population evolutionary algorithm based on knowledge transfer for constrained many-objective optimization

Constrained Many-objective Optimization Problems (CMaOPs) are challenging in handling objectives and constraints simultaneously. Here, a novel Constrained Many-objective Optimization Evolutionary Algorithm (CMaOEA) based on Multi-population, Knowledge transfer and Improved environmental selection ca...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Engineering optimization Jg. 57; H. 3; S. 813 - 843
Hauptverfasser: Ge, Wenlong, Zhang, Shanxin, Song, Weida, Wang, Wei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Abingdon Taylor & Francis 04.03.2025
Taylor & Francis Ltd
Schlagworte:
Algorithms
Constrained many-objective optimization
Constraints
environmental selection
evolutionary algorithm
Evolutionary algorithms
knowledge transfer
multi-population
Multiple objective analysis
Optimization
ISSN:0305-215X, 1029-0273
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Constrained Many-objective Optimization Problems (CMaOPs) are challenging in handling objectives and constraints simultaneously. Here, a novel Constrained Many-objective Optimization Evolutionary Algorithm (CMaOEA) based on Multi-population, Knowledge transfer and Improved environmental selection called CMaMKI is proposed to handle CMaOPs. The proposed framework evolves a task population to solve the original CMaOP and evolves another population to solve a helper problem derived from the original one. To assist solving the original CMaOP, a knowledge expression and transfer strategy is designed to share useful information in the helper population with the task population. Meanwhile, to balance population convergence, diversity and feasibility, an enhanced environmental selection strategy is devised by combining the ε-constrained technique, θ-dominance and subregional density evaluation. The proposed algorithm is evaluated and contrasted with six state-of-the-art algorithms on a set of benchmark CMaOPs. The experimental results demonstrate the superiority and competitiveness of the proposed method.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0305-215X
1029-0273
DOI:10.1080/0305215X.2024.2335552