Research On Collaborative Optimization Of Communication And Computation Resources Based On Mobile Edge Computing

With the continuous integration of new-generation technologies such as the Internet of Things(Io T),cloud computing,and big data into all aspects of industrial R&D,production,service,and management,the need for cross-domain integrated applications is becoming increasingly urgent.However,most existing Io T applications are still closed-loop for specific fields.The lack of cross-domain application sharing and resource optimization has become an important factor restricting the development of the Io T.This article focus on the collaborative resource optimization for computation offloading based on edge computing.First,we propose a remote health monitoring model for Internet of Medical Things(Io MT).This model divides the Io MT into intra-Wireless Body Area Networks(WBANs)and beyond-WBANs.Highlighting the characteristics of Io MT,the cost of patients depends on medical criticality,Age of Information(Ao I)and energy consumption.Cooperative game and non-cooperative game are utilized to allocation resources for intra-WBANs and beyond-WBANs,respectively.Then,we propose a partial computing offloading model for Internet of Vehicles.An adaptive task scheduling algorithm is developed to determine offloading ratio and channel resource allocation.Considering users’ incentive compatibility and rationality,the payoff for offloading services is decided based on the game between users and operators.Third,we propose a dynamic service placement model,where multiple edge servers cooperate to build a pervasive edge computing network.In order to adapt to the high mobility of users and resolve the shortcomings of the limited storage capacity of edge servers,a Lyapunov optimization based service migration strategy is proposed to stable the storage queues of edge servers,improving the robustness of the computation offloading system.Finally,experimental results based on real traffic data demonstrate that our proposed collaborative resource optimization strategy can be applied to different scenarios.In addition,our proposed solution greatly promotes performance of computation offloading in mobile Io T,and outperform other methods from various aspects.