Classification-based multi-strategy prediction method for dynamic multi-objective optimization problems

doi:10.13195/j.kzyjc.2019.1320

	Classification-based multi-strategy prediction method for dynamic multi-objective optimization problems
	Li, Er-Chao; Zhou, Yang
刊名	Kongzhi yu Juece/Control and Decision
	2021-07-01
卷号	36 期号:7 页码:1569-1580
关键词	Evolutionary algorithms Forecasting Optimal systems Time series Approximate optimal solutions Dynamic multiobjective optimization Environment change Historical information Optimal solution sets Optimization problems Prediction methods Preservation strategies
ISSN号	10010920
DOI	10.13195/j.kzyjc.2019.1320
英文摘要	There are many dynamic multi-objective optimization problems in real life. Once the environment changes, evolutionary algorithms are required to quickly track the moving Pareto front or Pareto set of optimization problems over time. We propose a classification-based multi-strategy prediction method (CMSP). Firstly, the approximate optimal solution obtained by optimization is used to detect the type of the Pareto set (PS) change: invariance, translation and others. Then, different coping strategies are adopted for different types of change: If type is invariance, the elite individual is retained and diversity is ensured; If it is translation, a time series is established for the center point of the optimal solution set, and the population is updated using the predictive gradient strategy, the predicted individuals are compared with the individuals retained from the old population to ensure the accuracy of the prediction; If it belongs to other situation, several time series are established for multiple special points to predict the location of individuals in the new environment. Finally, a population preservation strategy and a memory retrieval strategy are introduced, which is beneficial to more fully utilizing historical information. The experimental results show that the CMSP can perform dynamic multi-objective optimization well. Copyright ©2021 Control and Decision.
语种	中文
出版者	Northeast University
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/150751]
专题	电气工程与信息工程学院
作者单位	College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou; 730050, China
推荐引用方式 GB/T 7714	Li, Er-Chao,Zhou, Yang. Classification-based multi-strategy prediction method for dynamic multi-objective optimization problems[J]. Kongzhi yu Juece/Control and Decision,2021,36(7):1569-1580.
APA	Li, Er-Chao,&Zhou, Yang.(2021).Classification-based multi-strategy prediction method for dynamic multi-objective optimization problems.Kongzhi yu Juece/Control and Decision,36(7),1569-1580.
MLA	Li, Er-Chao,et al."Classification-based multi-strategy prediction method for dynamic multi-objective optimization problems".Kongzhi yu Juece/Control and Decision 36.7(2021):1569-1580.