期刊
IEEE ACCESS
卷 11, 期 -, 页码 53760-53771出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2023.3278594
关键词
Manufacturing; Optimization; Cloud computing; Decision making; Costs; Multi-agent systems; Heuristic algorithms; Cloud manufacturing; service composition optimization; multi-agent; grey target decision-making; NSGA-II
This paper addresses issues such as dynamic changes in historical attribute service evaluation indicators, lack of comprehensive consideration of the interest needs of all cloud manufacturing participants, and strong subjectivity in the composition optimization results in the process of cloud manufacturing service composition. A multi-objective optimization model is constructed, considering the demands of service demanders, platform operators, and service providers as constraints. The NSGA-II algorithm and grey target decision-making method are used to solve the optimization model, and case analysis demonstrates the feasibility and effectiveness of the proposed approach.
In order to solve the problems such as the dynamic change of historical attribute service evaluation indicators, the lack of comprehensive consideration of the interest needs of all cloud manufacturing participants, and the strong subjectivity of the composition optimization results in the process of cloud manufacturing service composition. Taking the demands of service demanders, platform operators and service providers as constraints, this paper constructs a multi-objective optimization model of cloud manufacturing service composition that comprehensively considers multi-agent interests, and introduces the time decay function to deal with the service evaluation indicators with historical attributes, which reduces the impact of the dynamic changes of service evaluation indicators. Secondly, this paper adopts the NSGA-II with the elite selection strategy to solve the cloud manufacturing service composition optimization (SCO) model, and uses the grey target decision-making method to select the optimal solution from the Pareto solutions obtained by the NSGA-II, which avoids the problem of strong subjectivity in service composition decision-making. Finally, through case analysis, it was found that the bull's-eye distance of the optimal solution obtained by the NSGA-II was reduced by at least 34.95% compared to the genetic algorithm, verifying the feasibility of the optimization model and the effectiveness of the algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据