Summary
International Symposium on Nonlinear Theory and Its Applications
2022
Session Number:B3L-D
Session:
Number:B3L-D-02
An Application of Reinforcement Learning to Ground Station Selection in Satellite-Terrestrial Optical Communication
Keigo Makizoe , Atsuhiro Yumoto , Koji Oshima , Kenji Suzuki , Mikio Hasegawa,
pp.335-338
Publication Date:12/12/2022
Online ISSN:2188-5079
DOI:10.34385/proc.71.B3L-D-02
PDF download (907.4KB)
Summary:
Optical satellite communications, one of the fundamental technologies for a non-terrestrial network in Beyond 5G/6G, enable high-capacity communications. It is affected by the interruption of optical communications due to clouds on the communication path. Satellite can mitigate the interruption by switching its destination ground station to another, though it brings additional delays in acquiring the beam. In this study, we propose a ground station selection method using a reinforcement learning algorithm to realize a fast and stable satellite-terrestrial optical communication system. We show its effectiveness through simulation evaluation using pseud and real data.