Performance Analysis Of Mobile Edge Computing Network Based On D2D Communication

In recent years,with the rapid development of the Internet of Things,the number of Internet of Things devices has been growing exponentially.In the face of hundreds of billions of accesses,traditional cloud computing cellular wireless networks are difficult to meet future network requirements,and due to the limited computing,storage,and transmission capabilities of mobile devices,the realization of low latency requirements for wireless networks is facing a huge challenge.At the same time,the power consumption of mobile devices,which is limited by current battery technology,has also hindered the development of the Internet of Things.This thesis uses Device-to-Device(D2D)communication to assist mobile edge computing,makes full use of the resources of idle mobile devices in the wireless network,and studies the latency and energy consumption issues in edge computing networks.The main work of the research is summarized as follows:First of all,for the problem of delay problem of the edge computing network,a parallel offloading strategy of cellular link transmission and edge cloud computing is proposed,and the delays of three methods of complete offloading,partial offloading and D2 D enabled partial offloading are analyzed.In the full offloading method,the offloading sequence of mobile users is adjusted to minimize the total delay of the system based on the principle of the minimum waiting time of the edge cloud server.In the partial offloading method,based on the full offloading method,the task segmentation ratio of mobile users is optimized to minimize the system delay.In D2 D enabled partial offloading method,the original problem is divided into two sub-problems,and the calculation methods of the above two methods are used to obtain the minimum value of the system delay.The simulation results verify the correctness of the theoretical derivation,and show that the proposed parallel edge offloading strategy and the introduction of D2 D communication into mobile edge computing offloading can effectively reduce the system delay.Secondly,for the problem of energy consumption of the edge computing network,the strategy of introducing the cache queue into the D2 D communication-assisted mobile edge computing system is proposed,and the impact of adding the cache in the offloading on the system energy consumption is analyzed.The system processing task time is divided into multiple time slots.The computing tasks generated in each time slot first enter the mobile user's cache queue.The system will coordinate the allocation of tasks and perform calculations through local,edge cloud and D2 D devices.On this basis,the energy consumption expressions of local computing,edge offloading and D2 D offloading are deduced,respectively,and then the task amount of each time slot system calculation is optimized to obtain the minimum energy consumption of the system.The simulation results verify the correctness of the theoretical derivation and show that adding a cache queue to the mobile edge computing system can effectively reduce system energy consumption.