Deep Reinforcement Learning-Based Relay Selection Algorithm in Free-Space Optical Cooperative Communications

doi:10.3390/app12104881

CORC > 长春光学精密机械与物理研究所 > 中国科学院长春光学精密机械与物理研究所

	Deep Reinforcement Learning-Based Relay Selection Algorithm in Free-Space Optical Cooperative Communications
	S. J. Gao; Y. T. Li and T. W. Geng
刊名	Applied Sciences-Basel
	2022
卷号	12 期号:10 页码:14
DOI	10.3390/app12104881
英文摘要	Relay-aided free-space optical (FSO) communication systems have the ability of mitigating the adverse effects of link disruption by dividing a long link into several short links. In order to solve the relay selection (RS) problem in a decode and forward (DF) relay-aided FSO system, we model the relay selection scheme as a Markov decision process (MDP). Based on a dueling deep Q-network (DQN), the DQN-RS algorithm is proposed, which aims at maximizing the average capacity. Different from relevant works, the switching loss between relay nodes is considered. Thanks to the advantage of maximizing cumulative rewards by deep reinforcement learning (DRL), our simulation results demonstrate that the proposed DQN-RS algorithm outperforms the traditional greedy method.
URL标识	查看原文
语种	英语
内容类型	期刊论文
源URL	[http://ir.ciomp.ac.cn/handle/181722/66510]
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	S. J. Gao,Y. T. Li and T. W. Geng. Deep Reinforcement Learning-Based Relay Selection Algorithm in Free-Space Optical Cooperative Communications[J]. Applied Sciences-Basel,2022,12(10):14.
APA	S. J. Gao,&Y. T. Li and T. W. Geng.(2022).Deep Reinforcement Learning-Based Relay Selection Algorithm in Free-Space Optical Cooperative Communications.Applied Sciences-Basel,12(10),14.
MLA	S. J. Gao,et al."Deep Reinforcement Learning-Based Relay Selection Algorithm in Free-Space Optical Cooperative Communications".Applied Sciences-Basel 12.10(2022):14.