Research On The Cloud Manufacturing Service Aggregation Optimization Method Based On Correlation Model

As a new service-oriented network manufacturing model based on knowledge, Cloud Manufacturing(CMfg) can provide the cloud users distributed in different places with on-demand, safe and reliable services supported for the whole life cycle of manufacturing process through the virtualization of manufacturing resources and manufacturing capabilities based on the development of cloud computing, the Internet of Things, virtualization, servitization, high performance computing, etc. As an effective way to realize of value-added and efficiency-added of cloud manufacturing service, and manufacturing resource sharing and on-demand using, research on service aggregation plays a great role in the achievement of concept of CMfg.Although some research result has been achieved by previous researches on service aggregation, but exiting works on service aggregation method cannot be simply applied to CMfg model, in order to achieve service aggregation in CMfg model, some key problems must to be solved. In view of the existing problems, the paper establishes a service aggregation framework supporting full life-cycle, and researches on the involving theories and key technologies, which provides technical supporting for the implementation of CMfg. The main works is as follow.(1)In view of the life-cycle of service aggregation, the paper analyses and descripts service aggregation, proposes a service aggregation framework supporting full life-cycle and discuss the involving key technologies to realize service aggregation in CMfg.(2)In view of the existing problems of research on service aggregation model and the correlation between services affect service aggregation process, the correlation between series is researched, and the correlation formal description model of correlation is presented. Based on correlation degree of service, QoS evaluation model and aggregation service QoS computation correlation model are established to support correlation. Finally, relevant experiments have been carried out to verify the effectiveness of the proposed model.(3)To provide user high-quality service, the problem of service aggregation is transformed into a multi-objective global optimal problem with multi-constraints. Solution of service aggregation is researched and an improved discrete bees algorithm based on Pareto(IDBA-Pareto) is designed based on the concept of Pareto. In order to improve the optimization performance of the proposed algorithm, the strategy of keeping population diversity and accepting solutions is introduced. A case study based on the real manufacturing application scenario is established for simulation test including efficient and comparative experiment.The experiment results about QoS value of aggregation service influenced by the existence of the correlation between services indicate that the study of the correlation can improve the accuracy of QoS value of aggregation service. The simulation results of IDBA-Pareto algorithm prove the effectiveness, high-efficiency and superiority of the proposed algorithm in the paper, and IDBA-Pareto algorithm has better population diversity and convergence speed.