Research On Offloading Strategy Of Mobile Edge Computing Based On Collaborative Technology

With the rapid development of technology,mobile smart devices and many new applications(such as face recognition,augmented reality,etc.)are rapidly popularizing.Although mobile smart devices have made great progress,their computing power and battery capacity are still very limited,so that they cannot provide users with satisfactory service quality.Mobile Edge Computing(MEC)effectively compensates for the above shortcomings because the MEC server provides cloud computing capabilities in edge networks close to user terminals.The current research on task offloading of mobile edge computing mainly considers how to achieve the goals of reducing user delay and energy consumption.However,the resources of the MEC server are limited.Few studies have considered the use of idle mobile devices with computing capabilities in the edge network and assumed these mobile devices as virtual MEC servers to relieve the computational pressure of real MEC servers.Secondly,in a distributed decision-making scenario,channel interference will occur among multiple users,and the offloading decisions among users influence each other.In the existing literature,the construction of such models is ideal.Most of them ignore the influence between users.Based on the above shortcomings,this article mainly does the following three aspects:(1)This paper proposes and constructs a single MEC server multi-user collaborative computing system model.It is proposed to combine collaborative computing technology with mobile edge computing offloading technology,and use idle computing-capable devices in the edge network to assist the MEC server in task calculations,taking into account multi-user channel interference factors.And for the first time,an indicator is proposed—coordination cost.The requesting party should give the cost of coordination to encourage users to actively carry out resource sharing.Then an adaptive hybrid algorithm(AHA)is proposed,in which a solution generation strategy of task priority mechanism is added to solve the optimization problem.Finally,the results of the simulation experiment not only show that the algorithm can completely execute all tasks under different tasks,and effectively reduce the energy consumption of the entire system.And it also proves the validity of the method(2)This paper proposes and constructs a multi-MEC server multi-user collaborative computing system model.It is further expanded on the single MEC server multi-user collaborative computing system model,in which each mobile device can assist the MEC server in task offloading calculations as much as possible when its own resources are sufficient.On this basis,a two-tier optimization method is adopted to reduce the difficulty of joint optimization of offloading decision-making and computing resources.Finally,the simulation experiment results show the superiority of the model,and the relationship between the number of servers and the total energy consumption of the system is explored.(3)This paper builds a mobile edge computing offloading system based on collaborative technology.On the basis of the above work,the Gentelella front-end framework,My SQL database,MATLAB and other technologies are used to realize mobile edge collaborative computing and automatic offloading in different scenarios.