Study On Data Unloading Optimization Strategy Based On Minimizing Energy Consumption In Mobile Environment

With the development of cloud computing,big data and the improvement of user's performance requirements for mobile terminals,it is an inevitable choice to transfer the complex computing and storage requirements of mobile terminals to cloud or near cloud for processing.Furthermore,in the case of limited battery energy of mobile devices,how to reduce the energy consumption of mobile terminals,improve energy utilization and enhance user experience is one of the urgent problems to be solved in the development of green network.This paper mainly studies the optimization of energy consumption in data unloading process.Considering that the mobile terminal can improve the energy utilization rate by sending data when the wireless channel is in good condition,a data unloading energy optimization strategy based on optimal stopping theory is proposed:In mobile cloud computing,an optimal unloading strategy based on secretary problem is proposed to minimize the average energy consumption per unit of data.By constructing a data transmission queue model with multiple applications,and based on the Secretary Problem with the smallest absolute rank mean of the selected candidates,this paper proposes a rule of excellence list after leaving off k candidates,and proves that the rule has an optimal k value.The experimental results show that the proposed optimization strategy has smaller average energy consumption per unit data,better energy consumption efficiency and better detection efficiency.In mobile edge computing,an unloading strategy based on optimal stopping theory is proposed to minimize the average energy consumption per unit data.By constructing the task model of n mobile terminals unloading data to m base stations,the local energy consumption,unloading energy consumption and base station energy consumption are jointly optimized.The original inequality constraints are transformed into equality constraints by augmented Lagrange multiplier method,and the convergence of the optimal stopping rule is further proved in this paper.The experimental results show that the proposed optimization strategy has smaller average energy consumption per unit data and higher average data delivery rate.