Research And Implementation Of Secure Computing Offloading Based On Mobile Edge Computing

The past decades have witnessed an explosive growth in Mobile Internet,and newly Internet of Things applications requiring intensive computation resources to meet their computing needs.However,Smart Device(SD)has limited computing power and they can't meet the low-latency computing needs with limited energy consumption.Mobile edge computing(MEC)is considered to be one of the most efficient solutions to this problem.MEC enables SD to actively offload computation workloads to computational servers(MECS)deployed at the edge of networks,while MECS completed the calculation,the results are returned to SD,which greatly reduces the computing delay of users.However,due to the open nature of the wireless channel,there exists a risk of malicious eavesdropping in the transmission process of SD's computing offloading.This thesis designs a MEC-based security computing offloading strategy for single MECS network and secure computing offloading network based on dual-connection technology.The main research contributions are as follows:1.In single MECS networks,this thesis proposes an optimal computing offloading strategy to minimize the global latency and satisfy the SD's security requirements while completing the SD's computing workloads with limited computing resources.By studying the inherent characteristics of the initial problem,this thesis presents a layered structure of proposed algorithm,through which the optimal solution of the original problem can be obtained accurately.At the same time,through a series of simulations,it is found that only SD's security requirements and eavesdropper's eavesdropping ability can affect the workloads of SD's computing offloading,thus indirectly affecting the global optimal value.2.In the secure computing offloading network based on dual-connection technology,this thesis further extends to two MECS based on the research of single MECS network,also proposed a joint optimization problem of SD and two MECS for computing workloads allocation and security requirements to minimize network latency.Since the initial problem is a non-convex optimization problem,this thesis proposes a corresponding algorithm by layering the problem.This algorithm can efficiently obtain the optimal solution of the initial problem.Compared with the linear search algorithm,the proposed algorithm can significantly reduce the computational time.3.Because the simulation results of the above two parts are based on the simulation platform of MATLAB,this paper builds a simulation system based on MATLAB.According to its inherent GUI function,data results are displayed graphically at the same time.