考虑能耗与用户效用的制造云服务调度优化  

Cloud Manufacturing Service Scheduling Optimization Considering Energy Consumption and User Utility

作　　者：王天日[1,2] 张敏敏 张鹏志 栗继祖 WANG Tian-ri;ZHANG Min-min;ZHANG Peng-zhi;LI Ji-zu(School of Economics and Management,Taiyuan University of Technology,Taiyuan 030024,China;Postgraduate Education Innovation Center of Big Data Management and Application of Shanxi Province,Taiyuan 030024,China)

机构地区：[1]太原理工大学经济管理学院,山西太原030024 [2]山西省大数据管理与应用研究生教育创新中心,山西太原030024

出　　处：《系统科学学报》2024年第4期118-125,共8页Chinese Journal of Systems Science

基　　金：国家自然科学基金(71701141);教育部人文社会科学研究项目(21YJC630135);山西省应用基础研究项目(201801D221227)。

摘　　要：针对云制造环境下多用户制造任务调度问题中忽视能耗对云制造系统的影响,综合考虑云服务需求方和云服务供应方的利益,以最小化服务供应商能耗和最大化用户平均效用为目标,建立了多目标多用户任务调度模型。然后,将模拟退火算法融入带精英策略的非支配排序遗传算法(NSGA-Ⅱ),设计了一种混合多目标算法HNSGA-Ⅱ。通过算例分析验证了模型的适用性,并说明所提模型能够为云制造平台中具有不同需求的用户生成不同的调度方案。最后,利用不同规模的模拟试验,将所提算法与NSGA-Ⅱ、SPEA2算法进行比较,仿真结果说明该算法能够获得高质量的解。For multi-user manufacturing task scheduling problem,most research ignores the effect of energy consumption on cloud manufacturing system.Considering the interests of cloud service demanders and cloud service providers,a multi-objective multi-user task scheduling model is established to minimize energy consumption of service providers and maximize user utility.Then,a hybrid multi-objective algorithm HNSGAII is designed by combining simulated annealing algorithm(SA)with non-dominated sorting genetic algorithm(NSGA-Ⅱ)to solve the model.By numerical example analysis,the feasibility of proposed model is validated,and this model can generate different scheduling schemes for users with different requirements in cloud manufacturing(CMfg)platform.Finally,compared with NSGA-Ⅱand SPEA2 on different scale experiments,simulation results show that the proposed approach can obtain high quality solution.

关 键 词：云制造 多用户任务 能耗 非支配排序遗传算法 模拟退火 

分 类 号：N949[自然科学总论—系统科学] C934[经济管理—管理学]