Cloud Resources Allocation Strategy Based On Fuzzy Clustering And Strict Matching

Cloud computing is one of the core technologies in the mobile Internet era with the explosion of big data.Resource scheduling management strategy,as the kernel of cloud computing,has become a research hotspot in the industry.However,existing strategies are failed to balance the preference of both parties due to the pursuit of personalized service by cloud users and the pursuit of revenue by service providers,which resulting in a low efficiency of resource scheduling and overall satisfaction.Therefore,it is an effective approach to improve resource allocation efficiency and service satisfaction by taking the user demand preference and resource execution preference into account.By studying the existing resource matching strategy,the research results obtained in this thesis mainly include:1.For the low efficiency of resource allocation,a bilateral clustering model of user tasks and cloud resources based on the principle that a certain type of resources is suitable for processing the similar type of tasks is proposed in this thesis.For narrowing the scope of resource retrieval to a set of the same type,this model clusters the task demands and the resource attributes aiming at improving the accuracy and efficiency of resource matching.The validity and effectiveness of the model are verified by a large number of numerical examples.2.Aiming at the low overall satisfaction of both parties in resource matching,preference ordering is carried out for the objects to be matched in the set of the same type according to the preferences of both parties in this thesis.Then the satisfaction function and the number of reference matching objects to obtain the minimum satisfaction standard of both parties are established.By fusing and optimizing the satisfaction objective function of both parties,task and resource strict matching strategy is proposed.This strategy ensures high overall satisfaction of both parties in resource matching under the minimum satisfaction standard by extracting task demand preference and resource execution preference.Finally,this thesis adopts the Spring MVC framework to design and implement the resource matching system,and explicitly verifies the two models proposed in this thesis,and proposes a new solution for the resource scheduling strategy of the cloud service system.