Algorithm of task offloading and resource allocation based on reinforcement learning in edge computing
Jianan Zhao, Xiaohui Hu, Xinxin Du · 2021 IEEE 5th Information Technology,Networking,Electronic and Automation Control Conference (ITNEC) · 2021
With the development of new technologies, resource-poor mobile devices cannot withstand low-latency, high-computing applications. In order to reduce the burden of such applications on the devices, mobile edge computing is a new type of technology that will store and Computing resources are moved closer to users to improve response time and relieve backhaul pressure, so that users with resource-limited devices can offload more complex tasks to the edge server (MEC), and let the MEC handle these tasks. Consider the problem of resource optimization, this paper proposes a resource allocation algorithm based on Deep Deterministic Policy Gradient (DDPG). The algorithm has the ability to quickly find the optimal decision while maximizing long-term benefits. The simulation results show that the algorithm has high performance in finding the optimal resource allocation decision.