A Task Offloading Decision and Resource Allocation Algorithm Based on DDPG in Mobile Edge Computing

Abstract

Abstract In mobile edge computing, the mobile device can offload tasks to the server near the edge of the mobile network for execution, thereby reducing the delay of task execution and the energy consumption of mobile device. However, limited resource of the edge server prevents the mobile device to offload all tasks to the edge servers for execution. To solve the problems, a mobile edge computing model of multi-users and single edge server is constructed in this paper. In order to minimize the weighted total cost composed of mobile device energy consumption and time delay under the constraints of task execution delay, computing resource and storage resource of the edge server, we propose a task offloading decision and resource allocation algorithm OADDPG based on Deep Deterministic Policy Gradient (DDPG). A special reward function is designed to make the reward value for correlating negatively with the total cost. We can get the lowest total cost when the algorithm reaches the maximum reward value. Experiment results show that the proposed algorithm can effectively reduce the weighted total cost of mobile devices and improve the success rate of task execution.