Research Article
A Distributed Computation Offloading Strategy for Edge Computing Based on Deep Reinforcement Learning
@INPROCEEDINGS{10.1007/978-3-030-94763-7_6, author={Hongyang Lai and Zhuocheng Yang and Jinhao Li and Celimuge Wu and Wugedele Bao}, title={A Distributed Computation Offloading Strategy for Edge Computing Based on Deep Reinforcement Learning}, proceedings={Mobile Networks and Management. 11th EAI International Conference, MONAMI 2021, Virtual Event, October 27-29, 2021, Proceedings}, proceedings_a={MONAMI}, year={2022}, month={1}, keywords={Mobile edge computing Computation offloading Markov Decision Process Deep reinforcement learning}, doi={10.1007/978-3-030-94763-7_6} }- Hongyang Lai
Zhuocheng Yang
Jinhao Li
Celimuge Wu
Wugedele Bao
Year: 2022
A Distributed Computation Offloading Strategy for Edge Computing Based on Deep Reinforcement Learning
MONAMI
Springer
DOI: 10.1007/978-3-030-94763-7_6
Abstract
Mobile edge computing (MEC) has emerged as a new key technology to reduce time delay at the edge of wireless networks, which provides a new solution of distributed computing. But due to the heterogeneity and instability of wireless local area networks, how to obtain a generalized computing offloading strategy is still an unsolved problem. In this research, we deploy a real small-scale MEC system with one edge server and several smart mobile devices and propose a task offloading strategy for one subject device on optimizing time and energy consumption. We formulate the long-term offloading problem as an infinite Markov Decision Process (MDP). Then we use deep Q-learning algorithm to help the subject device to find its optimal offloading decision in the MDP model. Compared with a strategy with fixed parameters, our Q-learning agent shows better performance and higher robustness in a scenario with an unstable network condition.
