Research On Offloading Method Based On Mobile Edge Computing

The development and popularization of mobile Internet and wireless communication technology have given birth to a large number of computation-intensive and time-intensive applications.Mobile Devices(MDs)can't meet the performance requirements of new applications due to the limitations of their computing resources and battery capacity.However,the existing mobile cloud computing technology needs to transmit data to be stored and tasks to be calculated to the cloud over a long distance,which will cause high latency.Mobile Edge Computing(MEC)technology can use wireless communication technology to offload data to be stored and tasks to be calculated to nearby Helpers or edge servers with idle resources.In this way,it not only solves the problem of high latency caused by long-distance transmission of stored data and computing tasks to the cloud,but also makes up for the shortcomings of mobile devices in terms of computing resources and battery capacity.Based on the above analysis,the main work of this paper is as follows:(1)In data offloading based on mobile devices and Device-to-Device(D2D)communication,the average offloading cost of mobile devices and the average download delay of users are studied.Firstly,the parallel data offloading scenario with Helpers as the edge node is designed,and the D2D communication model,calculation model and hot data model are established.Then,the problem is modeled as the problem of minimizing the average offloading cost of mobile devices and the average download delay of users.According to the interests of the two matching parties,different utility functions are designed.The many-to-one matching offloading algorithm and many-to-many matching offloading algorithm are proposed respectively,and the stability and convergence of the algorithm are proved.Finally,the simulation results verify the performance of the proposed algorithm.The results show that the proposed algorithm can effectively reduce the average offloading cost of mobile devices and the average download delay of users,and is superior to other benchmark algorithms with faster convergence speed and lower computational complexity.(2)In the computing offloading based on multi-task and cellular communication,the task scheduling and resource allocation of multi-task offloading are studied.Firstly,a two-layer computing offloading scenario with a Base Station(BS)as the edge node is designed,and a multi-task model,a cellular communication model and a computing model are established.Then,the task slack time is introduced to improve the traditional priority-based preemptive task scheduling algorithm,and the preemptive task scheduling algorithm based on slackness is designed in the task control block,which reduces the energy consumption of the near network side.The problem is modeled as a non-convex problem with the system energy consumption minimized by considering both the near and far network sides.The separable Semi-Definite Programming(SDP)method and Quadratically Constrained Quadratic Programming(QCQP)method are used to transform non-convex problems into convex problems under the condition of considering task decision and resource allocation.And the convex optimization solver is used to solve the problem.Finally,the effectiveness of the proposed algorithm is verified by simulation experiments.The results show that the proposed algorithm can achieve convergence in a finite number of steps,and has better performance in reducing system energy consumption compared with other benchmark schemes.