Research On Task Offloading Strategy Based On Mobile Edge Computing

With the rapid development of artificial intelligence and Internet of things mobile applications,face recognition,augmented reality and other new applications are widely used in a variety of mobile devices.However,mobile devices are limited by the size,battery capacity and other factors,so it is difficult to meet the demand of new applications for time delay and energy consumption.Mobile-edge computing(MEC)as a new paradigm to solve this problem.By offloading computation-intensive applications to edge servers with rich computing resources,MEC can effectively reduce the time delay and energy consumption required to process computing tasks,and improve the service quality of operators.However,while MEC brings many advantages,it also has the problem of how to make a reasonable computing task offloading strategy according to the limited computing and communication resources.Therefore,this paper focuses on the joint optimization of computing task offloading strategy and resource allocation in multi-user scenarios the details are as follows:Assuming that the computing resources of the edge server are not limited,the optimization problem of resource allocation and offloading strategy is decomposed into channel allocation and transmission power adjustment problems.According to the effective offloading theory,the channel allocation results can be obtained and the offloading strategy is formulated.Then,the optimal solution of transmission power is obtained by using the quasi-convex optimization theory.Simulation results show that the proposed scheme can effectively reduce the time delay and energy consumption when performing the computation task,even with a large number of users,this scheme can still maintain good system performance and formulate reasonable offloading strategy.When the computing resources of edge server are limited,in order to improve the battery life of users' mobile devices and the service quality of MEC system,a time-delay and energy-consumption adaptive weighting scheme based on the mobile device power residual rate was introduced to construct the utility function of the system,so as to solve the joint optimization problem of offloading strategy and resources.Firstly,the method uses the coordinate rising method to update the offloading strategy of computing tasks.Then,on the basis of the specific offload strategy,the channel matching algorithm based on user offload priority is used to allocate the channel.On this basis,on the grounds of the convex optimization and Hessian Matrix theory,we use one-dimensional search method to adjust the transmission power of mobile devices,and use Lagrange multiplier method and KKT condition to allocate the computing resources of edge server.The simulation results show that the scheme not only improves the endurance of low-power users,but also improves the overall service quality of MEC system by reducing the competition between high-power users and low-power users to unload resources.