A dual opposition learning-based multi-objective Aquila Optimizer for trading-off time-cost-quality-CO2 emissions of generalized construction projects

IF 1.5 4区 工程技术 Q3 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Mohammad Azim Eirgash, Vedat Toğan
{"title":"A dual opposition learning-based multi-objective Aquila Optimizer for trading-off time-cost-quality-CO2 emissions of generalized construction projects","authors":"Mohammad Azim Eirgash, Vedat Toğan","doi":"10.1108/ec-01-2024-0043","DOIUrl":null,"url":null,"abstract":"<h3>Purpose</h3>\n<p>Most of the existing time-cost-quality-environmental impact trade-off (TCQET) analysis models have focused on solving a simple project representation without taking typical activity and project characteristics into account. This study aims to present a novel approach called the “hybrid opposition learning-based Aquila Optimizer” (HOLAO) for optimizing TCQET decisions in generalized construction projects.</p><!--/ Abstract__block -->\n<h3>Design/methodology/approach</h3>\n<p>In this paper, a HOLAO algorithm is designed, incorporating the quasi-opposition-based learning (QOBL) and quasi-reflection-based learning (QRBL) strategies in the initial population and generation jumping phases, respectively. The crowded distance rank (CDR) mechanism is utilized to rank the optimal Pareto-front solutions to assist decision-makers (DMs) in achieving a single compromise solution.</p><!--/ Abstract__block -->\n<h3>Findings</h3>\n<p>The efficacy of the proposed methodology is evaluated by examining TCQET problems, involving 69 and 290 activities, respectively. Results indicate that the HOLAO provides competitive solutions for TCQET problems in construction projects. It is observed that the algorithm surpasses multiple objective social group optimization (MOSGO), plain Aquila Optimization (AO), QRBL and QOBL algorithms in terms of both number of function evaluations (NFE) and hypervolume (HV) indicator.</p><!--/ Abstract__block -->\n<h3>Originality/value</h3>\n<p>This paper introduces a novel concept called hybrid opposition-based learning (HOL), which incorporates two opposition strategies: QOBL as an explorative opposition and QRBL as an exploitative opposition. Achieving an effective balance between exploration and exploitation is crucial for the success of any algorithm. To this end, QOBL and QRBL are developed to ensure a proper equilibrium between the exploration and exploitation phases of the basic AO algorithm. The third contribution is to provide TCQET resource utilizations (construction plans) to evaluate the impact of these resources on the construction project performance.</p><!--/ Abstract__block -->","PeriodicalId":50522,"journal":{"name":"Engineering Computations","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Computations","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1108/ec-01-2024-0043","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose

Most of the existing time-cost-quality-environmental impact trade-off (TCQET) analysis models have focused on solving a simple project representation without taking typical activity and project characteristics into account. This study aims to present a novel approach called the “hybrid opposition learning-based Aquila Optimizer” (HOLAO) for optimizing TCQET decisions in generalized construction projects.

Design/methodology/approach

In this paper, a HOLAO algorithm is designed, incorporating the quasi-opposition-based learning (QOBL) and quasi-reflection-based learning (QRBL) strategies in the initial population and generation jumping phases, respectively. The crowded distance rank (CDR) mechanism is utilized to rank the optimal Pareto-front solutions to assist decision-makers (DMs) in achieving a single compromise solution.

Findings

The efficacy of the proposed methodology is evaluated by examining TCQET problems, involving 69 and 290 activities, respectively. Results indicate that the HOLAO provides competitive solutions for TCQET problems in construction projects. It is observed that the algorithm surpasses multiple objective social group optimization (MOSGO), plain Aquila Optimization (AO), QRBL and QOBL algorithms in terms of both number of function evaluations (NFE) and hypervolume (HV) indicator.

Originality/value

This paper introduces a novel concept called hybrid opposition-based learning (HOL), which incorporates two opposition strategies: QOBL as an explorative opposition and QRBL as an exploitative opposition. Achieving an effective balance between exploration and exploitation is crucial for the success of any algorithm. To this end, QOBL and QRBL are developed to ensure a proper equilibrium between the exploration and exploitation phases of the basic AO algorithm. The third contribution is to provide TCQET resource utilizations (construction plans) to evaluate the impact of these resources on the construction project performance.

基于双反对学习的 Aquila 多目标优化器,用于权衡一般建筑项目的时间-成本-质量-二氧化碳排放量
目的现有的时间-成本-质量-环境影响权衡(TCQET)分析模型大多侧重于解决简单的项目表征,而没有考虑典型的活动和项目特征。本文设计了一种 HOLAO 算法,在初始种群和跳跃生成阶段分别采用了基于准位置学习(QOBL)和基于准反思学习(QRBL)的策略。利用拥挤距离排序(CDR)机制对最优帕累托前沿解决方案进行排序,以帮助决策者(DMs)实现单一折中解决方案。研究结果通过研究分别涉及 69 个和 290 个活动的 TCQET 问题,对所提方法的有效性进行了评估。结果表明,HOLAO 为建筑项目中的 TCQET 问题提供了有竞争力的解决方案。据观察,该算法在函数求值次数(NFE)和超体积(HV)指标方面都超过了多目标社会群体优化算法(MOSGO)、普通阿奎拉优化算法(AO)、QRBL 算法和 QOBL 算法:作为探索性对立的 QOBL 和作为探索性对立的 QRBL。在探索和利用之间实现有效平衡对任何算法的成功都至关重要。为此,我们开发了 QOBL 和 QRBL,以确保基本 AO 算法的探索和利用阶段之间的适当平衡。第三个贡献是提供 TCQET 资源利用率(施工计划),以评估这些资源对施工项目绩效的影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Engineering Computations
Engineering Computations 工程技术-工程:综合
CiteScore
3.40
自引率
6.20%
发文量
61
审稿时长
5 months
期刊介绍: The journal presents its readers with broad coverage across all branches of engineering and science of the latest development and application of new solution algorithms, innovative numerical methods and/or solution techniques directed at the utilization of computational methods in engineering analysis, engineering design and practice. For more information visit: http://www.emeraldgrouppublishing.com/ec.htm
×
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