Research On Computing Resource Management Strategy In Mobile Edge Computing

Mobile edge computing(MEC),as a supplement to cloud computing,allows users to offload computing tasks to base stations equipped with MEC servers,realizing millisecond endto-end real-time task processing.The development of wireless technology and embedded processors supports smart terminal devices to perform computing tasks directly,thereby further improving the speed of response to user requests.However,computationally intensive tasks put energy pressure on energy-constrained terminal devices.In order to reduce the energy pressure of terminal devices and improve the performance of the MEC system,this thesis uses a variety of methods(such as cooperative computing,blockchain technology,etc.)to actively mobilize redundant resources in the MEC system,and proposes reasonable and flexible computing resource management strategy.Firstly,to solve the problem of the energy limitation of sensor nodes in wireless sensor networks,a three-node cooperative computing scheme for wireless sensor networks is proposed.This scheme improves the energy efficiency of sensor nodes by sharing resource in the network.The goal of this scheme is to find the task allocation that minimizes the energy consumption under the premise of satisfying the time delay constraint of the computing task.The energy efficiency optimization problem is described as an optimization problem,and then the optimization problem is solved by Lagrangian multiplier method and iterative algorithm.The simulation results show the superiority of the proposed scheme in terms of fairness and energy consumption,and explore the applicable scenarios of the two sub-schemes.This thesis further proposes a trade-off scheme for selecting sub-scheme based on channel state information.Then,for the problem of the lack of trust and incentive mechanism for cooperative computing between terminal devices in the Internet of Things,a blockchain-based cooperative computing scheme for terminal devices in the Internet of Things is proposed.The scheme uses blockchain technology to provide a safe and reliable cooperation platform,and provides a suitable incentive mechanism to encourage terminal devices to participate in cooperation.Specifically,the scheme uses the Kuhn-Munkres algorithm to achieve the optimal pairing between task owners and resource providers,and describes the computing resource transaction process through a two-stage Stackelberg game model.Finally,the scheme uses a Proof-ofReputation mechanism as a consensus mechanism,it avoids the waste of resources caused by mining task in the traditional blockchain system.The simulation results show that the proposed scheme comprehensively considers the utility of the two parties in the cooperative computing,guarantees the safety and fairness of the system,and reduces the total energy consumption of the system.