A dynamic multi-objective evolutionary algorithm based on two-stage dimensionality reduction and a region Gauss adaptation prediction strategy

Dynamic multi-objective optimization evolutionary algorithms (DMOEAs) have attracted increasing attention due to their superior performance in real-world applications. It is challenging to rapidly track the changing Pareto set (PS) and Pareto front (PF) in DMOEAs. However, most existing studies only...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied soft computing Ročník 142; s. 110333
Hlavní autoři: Yang, Yue, Ma, Yongjie, Wang, Peidi, Xu, Yang, Wang, Minghao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.07.2023
Témata:
Dynamic multi-objective optimization
Evolutionary algorithm
Prediction
Region Gauss adaptation
Two-stage dimensionality reduction
Two-stage dimensionality reduction
Dynamic multi-objective optimization
Evolutionary algorithm
Prediction
Region Gauss adaptation
ISSN:1568-4946, 1872-9681
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Dynamic multi-objective optimization evolutionary algorithms (DMOEAs) have attracted increasing attention due to their superior performance in real-world applications. It is challenging to rapidly track the changing Pareto set (PS) and Pareto front (PF) in DMOEAs. However, most existing studies only focus on the position change in the PS. To address this problem, we define a series of new PS region changes. Based on these definitions, we propose a dynamic multi-objective evolutionary algorithm based on two-stage dimensionality reduction and a region Gauss adaptation prediction strategy (DRPS). Specifically, we estimate the possible type of PS changes at the next moment by processing historical information. Afterward, the basic scaling population PSB is generated by dimensionality reduction, while parameters including the scaling factor and density change rate are calculated. Combining these parameters with a Gaussian distribution, the algorithm adaptively adjusts the sampling probability of individuals in PSB, achieving prediction with different types of PS changes. We conducted extensive experiments and compared classical algorithms, the latest algorithms, and algorithms with the same type in 25 test functions. The results demonstrate that the proposed algorithm outperforms the compared algorithms in most cases, while implying that the newly defined PS region change is reasonable. •Two new dimensionality reduction strategies were devised.•New PS change types were defined.•A model that can predict multiple types of PS changes was proposed.
ISSN:1568-4946
1872-9681
DOI:10.1016/j.asoc.2023.110333