Research On Cloud Manufacturing Services Optimal-Selection Based On Time Series

With the coming of "Industrial 4.0",the information technology and industrial manufacturing technology a high degree of integration,the depth of intertwined a new manufacturing model-cloud manufacturing.This model utilizes cloud manufacturing service platform to organize the manufacturing resources in the platform according to the actual needs of the users and provide various manufacturing services to the users.It provides the solution to the problem of resource waste caused by irrational use of manufacturing resources in China's manufacturing field.Therefore,how to select the appropriate manufacturing services from a large number of shared manufacturing resources in the cloud manufacturing platform has become a research hotspot.In this paper,the auto parts manufacturing,for example,to study the corresponding manufacturer selection issues,through the manufacture of cloud service selection method for the automobile factory to choose the most suitable parts manufacturing cloud service providers,making the maximum satisfaction of automobile manufacturers Their own manufacturing needs.The research of this paper can also provide reference for other manufacturing enterprises to make cloud services selection.Firstly,this paper constructs a set of QoS evaluation index system with the characteristics of manufacturing cloud service by consulting a large amount of relevant documents and combining manufacturing resources and network performance.Then,according to the characteristics of manufacturing cloud service,we introduce the concept of "time series" to express the dynamic change of manufacturing QoS in time series.Taking into account the actual application due to equipment failure and other reasons,there will be QoS observation data in some time sequence node is missing.This paper solves this problem by using the missing value estimation method based on cloud service QoS sequence feature to predict and fill the corresponding missing value.Secondly,this paper presents a cloud service time series selection method based on subjective and objective weight.This paper considers the subjective weight based on the user QoS preference level and the objective weight based on the correlation of the QoS indicators,and provides the help for the manufacturing enterprise by combining the time series QoS model for cloud service selection.Finally,the simulation results show that this method can effectively solve the user QoS preferences while fully considering the data distribution characteristics of the QoS indicators of the cloud service set,and the result of selection has high accuracy and scientificity.