基于QoS的制造云服务组合优选问题研究  

Study on Optimization of Manufacturing Cloud Services Composition Based on QoS

作　　者：唐雨[1] 汪永超[1] 王宇[1] 

机构地区：[1]四川大学制造科学与工程学院,成都610065

出　　处：《组合机床与自动化加工技术》2016年第1期154-156,共3页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家"十一五"科技支撑计划项目(2006BAC02A02)

摘　　要：基于云制造的QoS(Quality of Service)属性分析了制造云服务的组合优选问题,建立了该问题的以时间、费用、信誉和可靠性为目标的云服务组合数学模型。提出了结合层次分析法和改进的粒子群算法对该模型进行求解的优化方法。为了分析用户需求,细化了每个QoS属性,形成了云服务属性层次,采用层次分析法确定各属性的权重。改进的粒子群算法则可以快速有效地收敛到最优解。这种优化方法既弥补了以往单一优化方法的不足,同时又能深入分析用户对云服务的需求,找到满足用户需求动态变化的云服务组合方案。The optimization problem of manufacturing cloud services composition was analysed based on QoS of cloud manufacturing. A mathematical model with time, cost, reputation and reliability goals of this problem was set up. To solve the mathematical model, an optimization method which combined the Analytic Hierarchy Process （AHP） with the improved particle swarm algorithm was proposed. In order to analyze us- er＇ s needs, each QoS attributes were refined to form a cloud service attribute level, and AHP was used to determine the weight of each attribute. The improved particle swarm algorithm can converge to the optimal solution quickly and efficiently. This optimization method is able to make up for the shortages of the previous method and also find cloud services composition solution meeting user＇ s dynamic demands.

关 键 词：云制造 云服务组合 粒子群算法 层次分析法 

分 类 号：TH166[机械工程—机械制造及自动化] TG506[金属学及工艺—金属切削加工及机床]