Research On Multi-user Resource Allocation Technology Based On Mobile Edge Computing

Mobile Edge Computing(MEC)sinks cloud Computing power into the Edge network,providing users with the Computing,storage and network resources they need,which has greatly reduced the task execution delay and energy consumption of Mobile devices.However,the limited computing resources of MEC servers and the increasing demand for Internet-connected devices and user resources make it increasingly important to allocate resources rationally.In addition,when the user is in the mobile state,the network environment is dynamically changing,which will affect the communication delay between the mobile device and the MEC server,and it is difficult to guarantee the quality of user experience.Therefore,the mobile edge computing network needs to develop a reasonable resource allocation method to improve the quality of user experience.Based on this,this paper studies the resource allocation of mobile devices in static environment and dynamic environment under multi-user scenarios respectively.The main research contents are as follows:(1)Concerning the multi-user resource allocation in static environment,the total system cost is minimized under the constraints of limited computing resources and battery energy of mobile devices.The total cost of the system is optimized by designing reasonable unloading strategy and power optimization method.First,each user gets the offload strategy by comparing the task local computing energy consumption and the task offload computing energy consumption.Secondly,according to the unloading decision,the optimization problem is decomposed into the local computation cost minimization problem and the unloading computation cost minimization problem under the time delay constraints and resource constraints.Finally,the local computing task was allocated CPU clock frequency according to the convex optimization theory,and the power of unloading task was optimized by using the whale optimization algorithm based on chaotic reverse learning and dynamic weight factor.Simulation results show that the proposed algorithm can effectively reduce the total overhead of the system.(2)For the multi-user resource allocation problem in dynamic environment,the influence of user mobility on task offloading,task delay constraint and resource limitation of mobile devices are considered,and the system total cost minimization problem model is established.To solve this optimization problem,a resource allocation algorithm based on user mobility is proposed.Firstly,each user obtained the offloading decision by comparing the local computing delay and the task cutoff delay.Secondly,the local computing task was assigned CPU clock frequency by referring to the convex optimization theory,and the power of the offloading task was allocated by using the whale optimization algorithm based on Cauchy mutation and adaptive weight.The simulation results show that the algorithm can effectively reduce the total cost of the system and improve the performance of the system compared with the local calculation of all tasks.