Task Offloading Strategy And Optimization In Cloud-assisted Mobile Edge Computing Network

With the rapid development of smart mobile devices and the Internet of Things(Io T),new applications such as artificial intelligence(AI),augmented reality(AR),and virtual reality(VR)continue to emerge,however,most mobile devices usually have limited computing power,Communication resources,storage size and power,this is a huge challenge to complete such computing-intensive and delay-sensitive applications.Mobile edge computing(MEC)provides computing services for mobile devices by deploying servers with computing and storage capabilities at the edge of the network,which can meet users' needs for computing-intensive and delay-sensitive tasks and widespread concern in industry.This article focuses on the most critical offloading problem in MEC.It mainly studies the task offloading strategy and optimization under cloud-assisted mobile edge computing.The main contents and innovations can be summarized as the following two aspects:1.The task offloading strategy in the cloud-assisted MEC system with the binary task offloading model is studied.In view of the limited computing resources of the MEC server and the interference between devices during task unloading,a potential game offloading algorithm(PGO)is proposed.First,a cloud-MEC-equipment three-tier system model is established,and two models of local computing and offload computing are listed.With the goal of minimizing the total system consumption as a research goal,the problem is modeled as a resource-constrained offload decision problem.Then,by analyzing the original problem is transformed into a potential game unloading problem,the problem is solved by constructing a potential game function,and the PGO algorithm is proposed.Finally,simulation experiments prove that the proposed PGO algorithm can achieve Nash equilibrium within a limited number of iterations,and compare with the two benchmark schemes,proving the effectiveness of the proposed algorithm in reducing the total system consumption.2.The optimization problem of task offloading in the cache-enabled cloud-assisted MEC system with the partial task offloading model is studied.In response to the problem of offloading tasks,the introduction of caching in the proposed network system proposed an effective cache cloud joint computing optimization algorithm,cloud,and joint computing,OCCJ).First,a cloud-MEC-device three-tier system model is established,a cache model based on popularity is proposed,and three task execution modes are listed.Then we modeled the problem as an optimization problem that minimized equipment energy consumption,and jointly optimized the execution mode selection,offload rate,transmit power,and calculation frequency,while ensuring multiple system constraints.This problem is a mixed integer nonlinear programming problem.We designed the OCCJ algorithm to decompose the problem into three sub-problems and solve it.Finally,the simulation experiment analyzes the change of task offload rate under various variables,and the experimental results show that our proposed scheme is superior to the other three benchmark comparison schemes in reducing equipment energy consumption.