Research On Service Deployment Strategy Based On Asset Allocation Theory In Mobile Edge Computing

With the development of mobile Internet technology and the explosive growth of the number of user equipment,mobile edge computing(MEC)emerges as a computing paradigm that can perform computing offloading tasks at the edge of mobile networks.By providing computing and storage resources in the vicinity of the user equipment,mobile edge computing which is one of the key features of the 5G era has the advantages of high bandwidth,low latency,reduced user equipment's power consumption,and improves user experience quality.However,the biggest limitation of MEC server is its limited resource,it can only hold a limited number of services to finish tasks.Therefore,the issue how to optimize resource allocation and computing offloading to provide optimal benefit is significant to service providers.This thesis focuses on the service deployment strategy optimization in the mobile edge computing scenario,starting from resource allocation and computing offloading,and envisions a static service deployment model of the collaborative MEC service platform in the appropriate time segment T.In MEC,the service provider's profit is directly linked to the user's satisfaction,and the user's satisfaction is related to the average response time of the service.In this thesis,a benefit function is addressed to calculate the service provider's return with the average response time.Drawing on the concept of return and risk in asset allocation,the service deployment model is transformed into a risk-return model,the optimization of service deployment strategy is mapped to the resource allocation process,and the high-return and low-risk optimization goals are given too.Then,MOEA/D multi-objective optimization algorithm is used to solve the risk-return model in this thesis,and the Pareto front is used instead of the effective front.From the perspective of service providers,the using of asset allocation theory in service deployment strategy optimization is explored,and the inherent law between return and risk in service deployment model is investigated.Simulation experiments show that there is a positive correlation between the returns and risks in the service deployment strategy optimization problem,and the relative balance between risk and return can be achieved through the optimization of resource allocation and computing offloading.