Paper
4 April 2023 Satellite network routing planning method based on reinforcement learning
Deng Yong, Yao Feng
Author Affiliations +
Proceedings Volume 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications; 126175N (2023) https://doi.org/10.1117/12.2666566
Event: Ninth Symposium on Novel Photoelectronic Detection Technology and Applications (NDTA 2022), 2022, Hefei, China
Abstract
In the process of satellite network data transmission, routing which determines the overall performance of the satellite network plays a very important role. However, time-varying network topology and limited network resources bring great challenges to the design of satellite network routing algorithms. Considering the constraints of limited link resources and storage resources of satellite network with highly dynamic topology, an integer programming model is constructed to transform the routing planning problem into a single path multicommodity flow problem, and a routing strategy based on Q-Learning is proposed to solve the problem. Finally, compared with CGR routing algorithm, the routing algorithm based on Q-Learning has better performance in average delay.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Deng Yong and Yao Feng "Satellite network routing planning method based on reinforcement learning", Proc. SPIE 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications, 126175N (4 April 2023); https://doi.org/10.1117/12.2666566
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Satellites

Data transmission

Satellite communications

Network architectures

Mathematical modeling

Computer programming

Systems modeling

Back to Top