Research On Task Resource Allocation And Scheduling Optimization Method In Cloud Manufacturing Environment

The "Made in China 2025" plan was proposed,which made advanced manufacturing technology more valued by academia and industry.The "Made in China 2025" plan aims to adopt "innovation and green" as the guiding principle,combined with new technology,new ideas to improve China's manufacturing industry.With the integration of “ Internet + ” and manufacturing,cloud manufacturing is also more attention.Cloud manufacturing upgrades the traditional manufacturing model by integrating information technologies such as Internet of Things and big data.The cloud manufacturing platform will face massive data access and management,as well as high concurrent manufacturing resource service requests and new scheduling problems in the new model.This thesis is supported by the National Natural Science Foundation.Cloud manufacturing is studied as the following aspects in the thesis :Firstly,the current problems faced by China's manufacturing industry are analyzed and the background of cloud manufacturing is elaborated in this thesis.The current research status of cloud manufacturing at home and abroad is summarized in the thesis.Through the theory is analyzed in the field of cloud manufacturing,the problems to be studied in this thesis are put forward.Secondly,the virtualization of manufacturing resources in the cloud manufacturing platform is studied.The basic characteristics of cloud manufacturing resources are summarized,and manufacturing resources are divided into two categories: physical resources and soft resources.Based on these,a cloud virtualization framework for manufacturing resources is proposed.Based on the framework,a service resource model for manufacturing resources and a service request model for cloud manufacturing are constructed.Thirdly,aiming at solving the problem of processing efficiently large-scale concurrent sequential service requests in the cloud manufacturing service platform,a service request segmenting algorithm considering service responsetime and a manufacturing service resource allocation algorithm based on associated regions are proposed to improve the efficiency of global optimal allocation of manufacturing service resources under the condition of limited resources.Finally,aiming at manufacturing resource scheduling problem in cloud manufacturing environment,a multi-objective scheduling problem model considering service completion time,service cost,service quality and service satisfaction is established.A non-dominated sorting PSO is proposed to solve the scheduling problem.In the end of this chapter,the actual production data through experiments to prove the feasibility of the model and the effectiveness of the algorithm.The models and algorithms proposed in the thesis are applied to the cloud manufacturing scheduling experiment system,and the rationality of the models and the efficiency of the algorithms are verified.