基于历史优势信息的学习评估和绘图指导的多目标进化算法

IF 5.4 3区 材料科学 Q2 CHEMISTRY, PHYSICAL
Jinlian Xiong, Gang Liu, Zhigang Gao, Chong Zhou, Peng Hu, Qian Bao
{"title":"基于历史优势信息的学习评估和绘图指导的多目标进化算法","authors":"Jinlian Xiong, Gang Liu, Zhigang Gao, Chong Zhou, Peng Hu, Qian Bao","doi":"10.1093/jcde/qwae022","DOIUrl":null,"url":null,"abstract":"\n Multi-objective optimization algorithms have shown effectiveness on problems with two or three objectives. As the number of objectives increases, the proportion of non-dominated solutions increases rapidly, resulting in insufficient selection pressure. Nevertheless, insufficient selection pressure usually leads to the loss of convergence, too intense selection pressure often results in a lack of diversity. Hence, balancing the convergence and diversity remains a challenging problem in many-objective optimization problems. To remedy this issue, a many-objective evolutionary algorithm based on learning assessment and mapping guidance of historical superior information, referred to here as MaOEA-LAMG, is presented. In the proposed algorithm, an effective learning assessment strategy according to historical superior information based on an elite archive updated by indicator ${I}_{\\varepsilon + }$ is proposed, which can estimate the shape of the Pareto front and lay the foundation for subsequent fitness and acute angle-based similarity calculations. From this foundation, to balance the convergence and diversity dynamically, a mapping guidance strategy based on the historical superior information is designed, which contains clustering, associating, and proportional selection. The performance of the proposed algorithm is validated and compared with ten state-of-the-art algorithms on 24 test instances with various Pareto fronts and real-world water resource planning problem. The empirical studies substantiate the efficacy of the results with competitive performance.","PeriodicalId":4,"journal":{"name":"ACS Applied Energy Materials","volume":"59 7","pages":""},"PeriodicalIF":5.4000,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A many-objective evolutionary algorithm based on learning assessment and mapping guidance of historical superior information\",\"authors\":\"Jinlian Xiong, Gang Liu, Zhigang Gao, Chong Zhou, Peng Hu, Qian Bao\",\"doi\":\"10.1093/jcde/qwae022\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n Multi-objective optimization algorithms have shown effectiveness on problems with two or three objectives. As the number of objectives increases, the proportion of non-dominated solutions increases rapidly, resulting in insufficient selection pressure. Nevertheless, insufficient selection pressure usually leads to the loss of convergence, too intense selection pressure often results in a lack of diversity. Hence, balancing the convergence and diversity remains a challenging problem in many-objective optimization problems. To remedy this issue, a many-objective evolutionary algorithm based on learning assessment and mapping guidance of historical superior information, referred to here as MaOEA-LAMG, is presented. In the proposed algorithm, an effective learning assessment strategy according to historical superior information based on an elite archive updated by indicator ${I}_{\\\\varepsilon + }$ is proposed, which can estimate the shape of the Pareto front and lay the foundation for subsequent fitness and acute angle-based similarity calculations. From this foundation, to balance the convergence and diversity dynamically, a mapping guidance strategy based on the historical superior information is designed, which contains clustering, associating, and proportional selection. The performance of the proposed algorithm is validated and compared with ten state-of-the-art algorithms on 24 test instances with various Pareto fronts and real-world water resource planning problem. The empirical studies substantiate the efficacy of the results with competitive performance.\",\"PeriodicalId\":4,\"journal\":{\"name\":\"ACS Applied Energy Materials\",\"volume\":\"59 7\",\"pages\":\"\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2024-03-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Applied Energy Materials\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1093/jcde/qwae022\",\"RegionNum\":3,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Energy Materials","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1093/jcde/qwae022","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

摘要

多目标优化算法在处理具有两个或三个目标的问题时非常有效。随着目标数量的增加,非主导解的比例也会迅速增加,从而导致选择压力不足。然而,选择压力不足通常会导致收敛性下降,而选择压力过大往往会导致缺乏多样性。因此,在多目标优化问题中,平衡收敛性和多样性仍然是一个具有挑战性的问题。为了解决这个问题,本文提出了一种基于学习评估和历史优势信息映射引导的多目标进化算法,简称为 MaOEA-LAMG。在所提出的算法中,基于由指标${I}_{\varepsilon + }$更新的精英档案,根据历史优势信息提出了有效的学习评估策略,该策略可以估计帕累托前沿的形状,并为后续的适应度和基于锐角的相似度计算奠定基础。在此基础上,为了动态地平衡收敛性和多样性,设计了一种基于历史优势信息的映射指导策略,其中包含聚类、关联和比例选择。在 24 个具有不同帕累托前沿的测试实例和现实世界的水资源规划问题上,对所提出算法的性能进行了验证,并与 10 种最先进的算法进行了比较。实证研究证实了这些结果的有效性和具有竞争力的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A many-objective evolutionary algorithm based on learning assessment and mapping guidance of historical superior information
Multi-objective optimization algorithms have shown effectiveness on problems with two or three objectives. As the number of objectives increases, the proportion of non-dominated solutions increases rapidly, resulting in insufficient selection pressure. Nevertheless, insufficient selection pressure usually leads to the loss of convergence, too intense selection pressure often results in a lack of diversity. Hence, balancing the convergence and diversity remains a challenging problem in many-objective optimization problems. To remedy this issue, a many-objective evolutionary algorithm based on learning assessment and mapping guidance of historical superior information, referred to here as MaOEA-LAMG, is presented. In the proposed algorithm, an effective learning assessment strategy according to historical superior information based on an elite archive updated by indicator ${I}_{\varepsilon + }$ is proposed, which can estimate the shape of the Pareto front and lay the foundation for subsequent fitness and acute angle-based similarity calculations. From this foundation, to balance the convergence and diversity dynamically, a mapping guidance strategy based on the historical superior information is designed, which contains clustering, associating, and proportional selection. The performance of the proposed algorithm is validated and compared with ten state-of-the-art algorithms on 24 test instances with various Pareto fronts and real-world water resource planning problem. The empirical studies substantiate the efficacy of the results with competitive performance.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
ACS Applied Energy Materials
ACS Applied Energy Materials Materials Science-Materials Chemistry
CiteScore
10.30
自引率
6.20%
发文量
1368
期刊介绍: ACS Applied Energy Materials is an interdisciplinary journal publishing original research covering all aspects of materials, engineering, chemistry, physics and biology relevant to energy conversion and storage. The journal is devoted to reports of new and original experimental and theoretical research of an applied nature that integrate knowledge in the areas of materials, engineering, physics, bioscience, and chemistry into important energy applications.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信