Zhanglu Hou, Juan Zou, Gan Ruan, Yuan Liu, Yizhang Xia
{"title":"Combining kernelised autoencoding and centroid prediction for dynamic multi‐objective optimisation","authors":"Zhanglu Hou, Juan Zou, Gan Ruan, Yuan Liu, Yizhang Xia","doi":"10.1049/cit2.12335","DOIUrl":null,"url":null,"abstract":"Evolutionary algorithms face significant challenges when dealing with dynamic multi‐objective optimisation because Pareto optimal solutions and/or Pareto optimal fronts change. The authors propose a unified paradigm, which combines the kernelised autoncoding evolutionary search and the centroid‐based prediction (denoted by KAEP), for solving dynamic multi‐objective optimisation problems (DMOPs). Specifically, whenever a change is detected, KAEP reacts effectively to it by generating two subpopulations. The first subpopulation is generated by a simple centroid‐based prediction strategy. For the second initial subpopulation, the kernel autoencoder is derived to predict the moving of the Pareto‐optimal solutions based on the historical elite solutions. In this way, an initial population is predicted by the proposed combination strategies with good convergence and diversity, which can be effective for solving DMOPs. The performance of the proposed method is compared with five state‐of‐the‐art algorithms on a number of complex benchmark problems. Empirical results fully demonstrate the superiority of the proposed method on most test instances.","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":null,"pages":null},"PeriodicalIF":8.4000,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CAAI Transactions on Intelligence Technology","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1049/cit2.12335","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Evolutionary algorithms face significant challenges when dealing with dynamic multi‐objective optimisation because Pareto optimal solutions and/or Pareto optimal fronts change. The authors propose a unified paradigm, which combines the kernelised autoncoding evolutionary search and the centroid‐based prediction (denoted by KAEP), for solving dynamic multi‐objective optimisation problems (DMOPs). Specifically, whenever a change is detected, KAEP reacts effectively to it by generating two subpopulations. The first subpopulation is generated by a simple centroid‐based prediction strategy. For the second initial subpopulation, the kernel autoencoder is derived to predict the moving of the Pareto‐optimal solutions based on the historical elite solutions. In this way, an initial population is predicted by the proposed combination strategies with good convergence and diversity, which can be effective for solving DMOPs. The performance of the proposed method is compared with five state‐of‐the‐art algorithms on a number of complex benchmark problems. Empirical results fully demonstrate the superiority of the proposed method on most test instances.
期刊介绍:
CAAI Transactions on Intelligence Technology is a leading venue for original research on the theoretical and experimental aspects of artificial intelligence technology. We are a fully open access journal co-published by the Institution of Engineering and Technology (IET) and the Chinese Association for Artificial Intelligence (CAAI) providing research which is openly accessible to read and share worldwide.