Research On Offloading Technology Of Mobile Edge Computing For Broadband Wireless Network

As the volume of data in the communications network increases,Greater demands are placed on the capacity,speed,delay and other aspects.5G standard promotion organization(such as 5GPPP,3GPP,etc.)proposed a series of performance indicators for the new generation 5G mobile communication system,requiring 5G communication system capacity to be 1000 times of the current LTE network,while ensuring higher Reliability and lower latency of data transmission.So academia and industry have proposed large-scale MIMO,ultra-dense network,residential virtualization,Mobile-Edge Computing and other key technologies,MEC technology is the future 5G One of the key technologies in mobile communication networks,defined as deployment of MEC cloud servers on the edge of the mobile network,which is on the RAN side,providing IT services and cloud computing capabilities for the wireless access network,ensuring efficient network operations and reducing services Delivery delay,enhance the user experience.Based on the study of the basic principles,network architecture and the related application scenarios of MEC,this paper makes an in-depth study on the existing algorithm of computation offloading decision.Due to the limited resources of the MEC server and system performance optimization,the user's computing tasks are selected to execute computation offloading.This paper discusses how to perform subcarrier allocation on the basis of the first come first service scheduling method of the MEC server's.Introduces related mathematical expression and modeling.The quantum behavior particle swarm optimization algorithm is introduced into it,and the corresponding feasible solution form and fitness function are designed.By allocating Sub-carrier to effectively reduce the completion time of user computing tasks to achieve the goal of system performance optimization.In order to reduce the complexity of the solution,the water injection algorithm is integrated into it,then a computation offloading decision algorithm based on the hybrid quantum behavior particle swarm optimization is proposed.The simulation results show that the proposed algorithm can effectively reduce the completion time of computation task,with fast solving speed and good solving accuracy.Secondly,this paper also studies the MEC computation offloading decision algorithm in the network.In the view of description of the vehicle network based on the MEC cloud,the computation offloading process is classified according to the location,speed and task information of the vehicle users,and the corresponding mathematical expressions of the completion time are given.After that,the computation offloading decision problem is described as a model of the two-dimensional 0/1 knapsack problem.Finally,we propose a solving method based on utility function and dynamic programming,and gives a specific algorithm flow.The simulation results show that the proposed algorithm can significantly reduce the computation completion time of vehicle users.Further research work may take into account the interplay of multiple MEC clouds.At the same time,considering compromising time and energy consumption of MEC computation offloading to obtain a more suitable dynamic decision algorithm.In order to solve the MEC computation offloading technology in the vehicular network,considering to apply prediction methods to study the handover of the vehicle users in depth.