Research On Offloading Strategy Of Joint Resource Allocation In Mobile Edge Computing

With the development of mobile communication technology and the explosive growth of the number of mobile terminals,various new applications such as webcasting,virtual reality,and augmented reality are constantly emerging.However,due to the limitations of some objective factors,such as mobile device's volume and battery,the mobile device's own resources are insufficient to meet the user's needs for these services.The emergence of Mobile Edge Computing(MEC)technology provides an effective way to solve this problem.This technology allows mobile devices to offload computation intensive applications to MEC servers with strong computing power for execution,thereby effectively reducing computing task delay and energy consumption and improving user service quality.In a MEC system,it is particularly important to design efficient task offloading and resource allocation strategies.This thesis studies the joint task offloading and resource allocation in the MEC system,and the main works are as follows:For the mobile edge computing system in a heterogeneous network scenario with a single MEC server and multiple small cells,the joint optimization of user computing tasks offloading and resource allocation are analyzed.Considering the impact of radio and computing resources on task offload performance,with the goal of minimizing user delay and energy consumption overhead,an optimized solution for joint offloading decision,sub-channel allocation and computing resource allocation is formulated.In this scheme,the original optimization problem is decomposed into two tasks: task offloading and resource allocation.For the task offloading sub-problem,the user's offloading decision is optimized by the coordinate descent method.For the resource allocation sub-problem,design a matching algorithm to allocate sub-channels to users and use the convex optimization method to obtain the allocation of computing resources,and then the optimal offloading decision and resource allocation results are obtained by iteration.Simulation results show that the proposed scheme can effectively reduce the user's overhead.For the mobile edge computing system in the scenario of multiple MEC servers and multiple small cells,a multi-round combination auction algorithm is designed.The algorithm models the allocation of radio and computing resources as an auction process.Its purpose is to maximize the benefits of the service node with the resource constraints of the service node.The auction process is mainly divided into two stages: task bidding and winner determining.In the task bidding stage,the priority of the service node is determined by considering the resource capacity of the service node and the distance between the user and the service node.In the winner determining stage,a dynamic programming algorithm is used to determine the winning user.Simulation results show that the proposed algorithm can effectively increase the number of winning users and the benefits of service nodes compared with existing algorithms.