Workflow Offloading Algorithm For Saving Mobile Terminals' Energy Consumption In Edge Computing Environments

With the increasing number of mobile devices and the amount of data that needs to be processed,the energy requirements of applications are increasing,and traditional cloud computing cannot meet the smooth execution of existing high-energy applications.The cloud computing model turned to the edge computing model is a new trend in the past five years.In the edge computing environment,the mobile device can not only access the edge server,but also map its own tasks to the edge server through offloading.One of the main purposes of the offloading is to reduce the energy consumption of the mobile device,and the mobile device can consumption optimization has long been recognized as an important step in achieving device intelligence and overcoming low battery life.In order to reduce the energy consumption of mobile devices,firstly,this paper divides the program into several interconnected partitions in a priority manner,and then optimally maps the tasks that need to be offloading in each partition to the edge servers.When the task is mapped to the edge server,this paper proposes a dynamic voltage and frequency adjustment technology to reduce the energy consumption of mobile devices.In order to solve the two problems of priority division and task mapping,the main work of this paper is as follows:(1)By determining the priority of each subtask,the tasks of the same priority are divided into the same partition;(2)based on The task mapping scheme of the genetic algorithm assigns the task to the current optimal edge server for execution;(3)reduces the movement under the delay constraint condition by dynamic voltage and frequency adjustment techniques while satisfying the maximum tolerance time ofthe task,equipment energy consumption.The simulation results show that:(1)the task mapping scheme based on genetic algorithm saves 54.7%compared with the local execution of the task;(2)under the task independent delay,the genetic algorithm based on dynamic voltage saves 57.18%compared with the local execution of the task.(3)Under the overall delay of the task,the dynamic voltage-based genetic algorithm saves 61.15%compared to the task execution locally.