Research On Resource Scheduling Problem In Cloud Manufacturing Environment

Manufacturing is the mainstay of the real economy.Promoting the high-quality development of manufacturing has become one of the important directions of China's economic development.The traditional manufacturing model has been difficult to comply with the requirements of current economic development.This requires us to accelerate the change of traditional manufacturing models.The digitalization,networking and intelligence of the manufacturing industry have become the main development direction.Cloud manufacturing is a new model of intelligent manufacturing.Cloud manufacturing is based on the web.The main job of cloud manufacturing is to provide services.Resource scheduling is one of the core issues of cloud manufacturing.The quality of resource scheduling directly affects the quality of cloud manufacturing platform operations.This paper focuses on the issue of resource scheduling in a cloud manufacturing environment.The main purpose of this paper is to provide a high-quality resource scheduling solution for users in the cloud manufacturing environment.This paper first analyzes the manufacturing process in a cloud manufacturing environment.Research on the operation mechanism of resource scheduling.Decompose complex and large manufacturing projects in cloud manufacturing platforms.In this paper,the project is decomposed into multiple tasks with constraints,and each task is decomposed into several relatively independent subtasks to prepare for resource scheduling.Based on the diversity of users of cloud manufacturing platform,a multi-objective static resource scheduling model is established considering multiple objectives such as time,cost,user satisfaction and service quality.Based on the significant dynamics and widely generated interference in the cloud manufacturing environment,a dynamic scheduling strategy based on periodic and event dual drivers is added to the static model.This paper designs a hybrid scheduling model in a cloud manufacturing environment.In order to improve the efficiency of resource scheduling,the stability of scheduling is also guaranteed.The particle swarm optimization algorithm is easy to implement and has good convergence speed performance when searching.However,it is easy to fall into local optimum in the process of finding the optimal solution.In this paper,the immune algorithm is introduced into it,and the affinity-based mutation strategy is used to prevent falling into local optimum while avoiding population degradation.Improve the population update strategy.The antibodies are divided by antibody balancing selection mechanisms that are controlled by individual concentrations and affinities and evolved in different ways.This strategy increases the scope of optimization and speeds up convergence.The high-quality antibodies obtained in each iteration are selected by the elite and then deposited into the memory unit to immunoselect the individuals who are updated in the population.This method speeds up the convergence of the population.The simulation results prove the validity and stability of the model in this paper.The convergence speed and solution accuracy of the algorithm are verified.Finally,an example is used to verify that the proposed scheduling scheme can efficiently complete the task of resource scheduling in cloud manufacturing environment.The effectiveness of the scheduling scheme in actual production is proved.