Offloading Strategy Of Computing Requests In Mobile Fog Computing With Network Slicingy

With the advent of the era of big data,various emerging services have emerged,and the traditional single network communication technology has been unable to meet the diverse needs of users.In order to meet the differentiated service requirements,network slicing technology is proposed for network communication.Generally speaking,network slicing technology divides the physical network into multiple virtual networks to make services more flexible and diverse,and can provide different services according to the different needs of users.In order to ensure the normal operation of each network slice,the rational allocation of resources is a key issue that needs to be solved.This paper studies the offloading strategy of computing requests in the mobile fog computing system based on network slicing.First of all,in order to better solve the burden on MFC due to different business requirements,this paper proposes a resource scheduling architecture based on network slicing,which can effectively alleviate the processing pressure caused by the diversity of computing requests,while satisfying the differentiated requirements of computing requests and the flexibility of resource allocation are enhanced,thereby improving the resource management efficiency of the entire system.Secondly,this paper uses virtualization technology to virtualize the computing resources of one or more physical machines into a virtual machine(Virtual Machines,VMs)to form the computing resource pool of the MFC system,and then according to the number of available virtual machines in the system,reasonable Allocate resources to offload computing requests.In this paper,users' business requirements in MFC are divided into two categories,and an optimal scheme of resource allocation in MFC system is proposed to maximize the long-term expected reward of the system.Then,the optimization problem is formulated as a Semi-Markov Decision Process(SMDP).We solve the SMDP problem through an iterative algorithm and obtain the corresponding optimal solution.The proposed scheme can provide guidelines for fog computing,helping to decide how much resources should be allocated for mobile user requests.Numerical results show that this scheme outperforms other resource allocation schemes,improving system rewards and the experience gained by mobile users.Finally,we discussed that the MFC system will get a larger penalty because the computing request of the user is rejected due to insufficient computing resources due to resource occupancy.In order to avoid this situation,we consider multiple MFC systems.When the computing resources of the system are insufficient,the computing request can be migrated to the neighboring MFC system for offloading.To this end,we study the optimal offloading of computational requests and build a cost-optimized model.The effectiveness of the scheme is verified by numerical simulation experiments.This paper studies the resource allocation strategy of MFC system based on network slicing and the offloading strategy of computing requests,which lays a foundation for the research on the diversity of computing requests and satisfying the differentiated needs of users,and also for network slicing technology to adapt to different services.Types and different needs,supporting vertical industries provide direction.