Energy-aware Dynamic Soft Real-time Task Offloading Algorithm in Mobile Edge Computing
Mobile edge computing can offload computation-intensive tasks to enhance the computational capability of a device and reduce energy consumption.However,existing algorithms cannot efficiently perform computation offloading and resource alloca-tion to reduce the execution cost(weighted sum of energy consumption and completion time)of the device under the soft real-time and parallel dependency constraints of the task,so this paper proposes a distributed computation offloading algorithm to determine the execution location,CPU frequency,and transmission power of the task to reduce the execution cost.In order to achieve the opti-mization goal,firstly,the original optimization problem is modeled as a convex optimization problem,and computational resources are pre-allocated according to the task's deadline,and finally the resource allocation and computational offloading decisions are de-rived by the distributed algorithm.The experimental results show that the algorithm proposed in this paper can effectively reduce the task execution cost as well as reduce the time of task timeout.