An improved Multi-objective Grey Wolf Optimization Algorithm Based on Multiple Strategies

According to the disadvantages of the grey wolf algorithm (GWO) in solving multi-objective optimization problems, such as slow convergence, easy to fall into local optimum and poor diversity of solution sets, an improved grey wolf algorithm based on multiple strategies (I-MOGWO) is proposed to solve...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2022 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI) S. 74 - 78
Hauptverfasser: Tian, Xiaohuan, Hu, Qiqi, Liu, Chun-An
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.07.2022
Schlagworte:
Approximation algorithms
Artificial intelligence
clustering
Clustering algorithms
Convergence
crowding distance
multi-objective grey wolf optimization algorithm
Optimization
Pareto optimization
perturbation operator
strategy
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:According to the disadvantages of the grey wolf algorithm (GWO) in solving multi-objective optimization problems, such as slow convergence, easy to fall into local optimum and poor diversity of solution sets, an improved grey wolf algorithm based on multiple strategies (I-MOGWO) is proposed to solve multi-objective optimization problems. It mainly includes: clustering the non-dominated individuals in the external archive set based on reference points, selecting the head wolves that guide the search according to the size of the density value of the clusters to improve the convergence speed, and using the mutation operator to perturb the position of the search agent so that it can jump out of the local optimum and improve the global exploration ability of the algorithm. The mechanism of crowding distance mechanism is applied to maintain the external archive size and keep the solution set diversity. Experimental results show that the proposed algorithm can not only effectively approximate the real Pareto front of the problem, but also the obtained Pareto optimal solutions have better distribution and diversity.
DOI:10.1109/ICCEAI55464.2022.00024