Research And Simulation Of Edge Computing Migration Strategy For 5G Network

With the growth of IoT terminals and intelligent terminals,the way to offload tasks to the cloud in existing networks not only increases the network load,but also introduces a large amount of data transmission delay.This is not only unfavorable to the rapid development of high band-width applications such as ultra-clear video and Virtual Reality(VR),but also can not meet the requirements of extremely short latency applications such as Internet of Vehicles and Augmented Reality(AR).The introduction of Mobile Edge Computing(MEC)and Device-to-Device(D2D)technologies in Fifth-generation(5G)networks can effectively alleviate the above problems.Both MEC data center and D2D device can be used as computing platforms.How to migrate tasks to the best location is an urgent problem to be solved.Researchers have not reached a consensus on how to design a rea-sonable offloading strategy and objectively evaluate and calculate the offloading performance due to the calculation of the factors influencing the migration and the diversity of assessment indicators.At present,the research on computing offloading for 5G networks is still in its infancy,and the calculation and offloading strategy in traditional mobile cloud computing is not applicable to the scenarios of edge computing.Therefore,there is still much room for development and research on the edge offloading strategy of 5G networks.This topic mainly designs a calculation and offloading framework that combines horizontal offloading and vertical offloading.Based on this framework,a MEC offloading strategy based on multiple attribute decision-making is proposed.In addition,aiming at the business scenario of D2D communication,D2D offloading strategy based on multi-constraint shortest path is designed.Both strategies address the three core issues of whether,when,and where to migrate.This paper first introduces the background and significance of the topic,analyzes the latest edge computing offloading strategy at home and abroad,and clarifies the research content and goals of this topic.Then introduced the technology of computing offloading.Aiming at the calculation and offloading of horizontal and vertical directions in 5G networks,the framework of computing offloading is designed and the flow of computing migration is illustrated.Based on this framework,a multi-attribute decision-making model is established by analyzing the influence factors of offloading.Based on this model,a MEC offloading strategy is formulated.Through the simulation experiments,the validity of MEC offloading strategy.Secondly,it analyzes the characteristics of D2D calculation and offloading,summarizes the constraints that need to be considered,designs the utility function about time and energy consumption,establishes the D2D calculation offloading model,and proposes the D2D calculation offloading strategy based on the multi-constraint shortest path.Comparative experiments verify the effectiveness of this offloading strategy.Finally,the thesis is summarized,the existing problems are analyzed,and the future research plan is formulated.