Constrained Multi-Modal Multi-Objective Evolutionary Algorithm with Problem Transformation into Two-Objective Subproblems

Real-world optimization problems often have multi-ple conflicting objective functions to be optimized simultaneously. In some of them, there are different Pareto optimal solutions with the same objective function values. Those problems are called multi-modal multi-objective optimization problems (MM...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems (SCIS&ISIS) S. 1 - 6
Hauptverfasser: Tokusaka, Teruhiko, Masuyama, Naoki, Nojima, Yusuke
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 09.11.2024
Schlagworte:
Constrained dominance principle
Constrained multi-modal multi-objective optimization problems
Constraint handling
Evolutionary computation
Linear programming
Multi-objective evolutionary algorithms
Optimization
Pareto optimization
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Real-world optimization problems often have multi-ple conflicting objective functions to be optimized simultaneously. In some of them, there are different Pareto optimal solutions with the same objective function values. Those problems are called multi-modal multi-objective optimization problems (MMOPs). For MMOPs, we proposed a decomposition-based multi-modal multi-objective evolutionary algorithm called MM2T in our previous study. However, MM2T does not consider constraints and thus cannot solve constrained MMOPs (CMMOPs). To apply MM2T to CMMOPs, we introduce the constrained dominance principle (CDP) into MM2T. We examine the search performance of MM2T with CDP through computational experiments.
DOI:10.1109/SCISISIS61014.2024.10760179