A special point-based transfer component analysis for dynamic multi-objective optimization
Abstract To solve dynamic multi-objective optimization problems better, the key is to adapt quickly to environmental changes and track the possible changing optimal solutions in time. In this paper, we propose a special point-based transfer component analysis for dynamic multi-objective optimization...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2022-02-01
|
Series: | Complex & Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1007/s40747-021-00631-3 |
_version_ | 1797840735840501760 |
---|---|
author | Ruochen Liu Nanxi Li Luyao Peng Kai Wu |
author_facet | Ruochen Liu Nanxi Li Luyao Peng Kai Wu |
author_sort | Ruochen Liu |
collection | DOAJ |
description | Abstract To solve dynamic multi-objective optimization problems better, the key is to adapt quickly to environmental changes and track the possible changing optimal solutions in time. In this paper, we propose a special point-based transfer component analysis for dynamic multi-objective optimization algorithm (SPTr-RM-MEDA). To be specific, when a change occurs, the neighbors of some special points are selected from the optimal set at previous time, and the transfer component analysis makes the use of minimizing the distance between the mapped previous optima and the mapped current optima. Accordingly, the purpose is to predict a part of next initial population from the neighborhoods of special points by transfer component analysis. To adapt to the change well, SPTr-RM-MEDA also reevaluates the previous optimal set. In addition, an adaptive diversity introduction strategy is adopted to maintain the population size. SPTr-RM-MEDA is performed on 12 test problems under 8 kinds of environmental changes, and experimental results show that it is superior to other five state-of-the-art algorithms on most of test problems. |
first_indexed | 2024-04-09T16:19:32Z |
format | Article |
id | doaj.art-9e4a1e015b3d4e35b13b5b4895720587 |
institution | Directory Open Access Journal |
issn | 2199-4536 2198-6053 |
language | English |
last_indexed | 2024-04-09T16:19:32Z |
publishDate | 2022-02-01 |
publisher | Springer |
record_format | Article |
series | Complex & Intelligent Systems |
spelling | doaj.art-9e4a1e015b3d4e35b13b5b48957205872023-04-23T11:32:22ZengSpringerComplex & Intelligent Systems2199-45362198-60532022-02-01921229124510.1007/s40747-021-00631-3A special point-based transfer component analysis for dynamic multi-objective optimizationRuochen Liu0Nanxi Li1Luyao Peng2Kai Wu3Key Lab of Intelligent Perception and Image Understanding of Ministry of Education, International Center of Intelligent Perception and Computation, Xidian UniversityKey Lab of Intelligent Perception and Image Understanding of Ministry of Education, International Center of Intelligent Perception and Computation, Xidian UniversityKey Lab of Intelligent Perception and Image Understanding of Ministry of Education, International Center of Intelligent Perception and Computation, Xidian UniversityKey Lab of Intelligent Perception and Image Understanding of Ministry of Education, International Center of Intelligent Perception and Computation, Xidian UniversityAbstract To solve dynamic multi-objective optimization problems better, the key is to adapt quickly to environmental changes and track the possible changing optimal solutions in time. In this paper, we propose a special point-based transfer component analysis for dynamic multi-objective optimization algorithm (SPTr-RM-MEDA). To be specific, when a change occurs, the neighbors of some special points are selected from the optimal set at previous time, and the transfer component analysis makes the use of minimizing the distance between the mapped previous optima and the mapped current optima. Accordingly, the purpose is to predict a part of next initial population from the neighborhoods of special points by transfer component analysis. To adapt to the change well, SPTr-RM-MEDA also reevaluates the previous optimal set. In addition, an adaptive diversity introduction strategy is adopted to maintain the population size. SPTr-RM-MEDA is performed on 12 test problems under 8 kinds of environmental changes, and experimental results show that it is superior to other five state-of-the-art algorithms on most of test problems.https://doi.org/10.1007/s40747-021-00631-3Special pointTransfer component analysisDynamic multi-objective optimization |
spellingShingle | Ruochen Liu Nanxi Li Luyao Peng Kai Wu A special point-based transfer component analysis for dynamic multi-objective optimization Complex & Intelligent Systems Special point Transfer component analysis Dynamic multi-objective optimization |
title | A special point-based transfer component analysis for dynamic multi-objective optimization |
title_full | A special point-based transfer component analysis for dynamic multi-objective optimization |
title_fullStr | A special point-based transfer component analysis for dynamic multi-objective optimization |
title_full_unstemmed | A special point-based transfer component analysis for dynamic multi-objective optimization |
title_short | A special point-based transfer component analysis for dynamic multi-objective optimization |
title_sort | special point based transfer component analysis for dynamic multi objective optimization |
topic | Special point Transfer component analysis Dynamic multi-objective optimization |
url | https://doi.org/10.1007/s40747-021-00631-3 |
work_keys_str_mv | AT ruochenliu aspecialpointbasedtransfercomponentanalysisfordynamicmultiobjectiveoptimization AT nanxili aspecialpointbasedtransfercomponentanalysisfordynamicmultiobjectiveoptimization AT luyaopeng aspecialpointbasedtransfercomponentanalysisfordynamicmultiobjectiveoptimization AT kaiwu aspecialpointbasedtransfercomponentanalysisfordynamicmultiobjectiveoptimization AT ruochenliu specialpointbasedtransfercomponentanalysisfordynamicmultiobjectiveoptimization AT nanxili specialpointbasedtransfercomponentanalysisfordynamicmultiobjectiveoptimization AT luyaopeng specialpointbasedtransfercomponentanalysisfordynamicmultiobjectiveoptimization AT kaiwu specialpointbasedtransfercomponentanalysisfordynamicmultiobjectiveoptimization |