Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning

Ju Hyung Lee; Hyowoon Seo; Jihong Park; Mehdi Bennis; Young Chai Ko; Joongheon Kim

doi:10.1109/VTC2022-Spring54318.2022.9860594

Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning

Ju Hyung Lee, Hyowoon Seo, Jihong Park, Mehdi Bennis, Young Chai Ko, Joongheon Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. However, such wide coverage rather makes it difficult to apply existing multiple access protocols, such as random access channel (RACH). To overcome this issue, in this paper, we propose a novel random access solution for LEO SAT networks, called as S-RACH. In contrast to existing standardized protocols, S-RACH is a model-free approach using deep reinforcement learning (DRL). Compared to RACH, we show from various simulations that our proposed S-RACH yields around 2x lower average access delay.

Original language	English
Title of host publication	2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665482431
DOIs	https://doi.org/10.1109/VTC2022-Spring54318.2022.9860594
Publication status	Published - 2022
Event	95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring - Helsinki, Finland Duration: 2022 Jun 19 → 2022 Jun 22

Publication series

Name	IEEE Vehicular Technology Conference
Volume	2022-June
ISSN (Print)	1550-2252

Conference

Conference	95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring
Country/Territory	Finland
City	Helsinki
Period	22/6/19 → 22/6/22

Bibliographical note

Funding Information:
ACKNOWLEDGEMENT This research was funded by the National Research Foundation of Korea (2022R1A2C2004869).

Publisher Copyright:
© 2022 IEEE.

ASJC Scopus subject areas

Computer Science Applications
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1109/VTC2022-Spring54318.2022.9860594

Cite this

Lee, J. H., Seo, H., Park, J., Bennis, M., Ko, Y. C., & Kim, J. (2022). Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning. In 2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings (IEEE Vehicular Technology Conference; Vol. 2022-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VTC2022-Spring54318.2022.9860594

Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning. / Lee, Ju Hyung; Seo, Hyowoon; Park, Jihong et al.
2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. (IEEE Vehicular Technology Conference; Vol. 2022-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lee, JH, Seo, H, Park, J, Bennis, M, Ko, YC & Kim, J 2022, Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning. in 2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings. IEEE Vehicular Technology Conference, vol. 2022-June, Institute of Electrical and Electronics Engineers Inc., 95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring, Helsinki, Finland, 22/6/19. https://doi.org/10.1109/VTC2022-Spring54318.2022.9860594

Lee JH, Seo H, Park J, Bennis M, Ko YC, Kim J. Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning. In 2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. (IEEE Vehicular Technology Conference). doi: 10.1109/VTC2022-Spring54318.2022.9860594

@inproceedings{bc3fe9b7c07540308d09cfdf51fbf72b,

title = "Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning",

abstract = "A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. However, such wide coverage rather makes it difficult to apply existing multiple access protocols, such as random access channel (RACH). To overcome this issue, in this paper, we propose a novel random access solution for LEO SAT networks, called as S-RACH. In contrast to existing standardized protocols, S-RACH is a model-free approach using deep reinforcement learning (DRL). Compared to RACH, we show from various simulations that our proposed S-RACH yields around 2x lower average access delay.",

author = "Lee, {Ju Hyung} and Hyowoon Seo and Jihong Park and Mehdi Bennis and Ko, {Young Chai} and Joongheon Kim",

note = "Funding Information: ACKNOWLEDGEMENT This research was funded by the National Research Foundation of Korea (2022R1A2C2004869). Publisher Copyright: {\textcopyright} 2022 IEEE.; 95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring ; Conference date: 19-06-2022 Through 22-06-2022",

year = "2022",

doi = "10.1109/VTC2022-Spring54318.2022.9860594",

language = "English",

series = "IEEE Vehicular Technology Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings",

}

TY - GEN

T1 - Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning

AU - Lee, Ju Hyung

AU - Seo, Hyowoon

AU - Park, Jihong

AU - Bennis, Mehdi

AU - Ko, Young Chai

AU - Kim, Joongheon

PY - 2022

Y1 - 2022

N2 - A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. However, such wide coverage rather makes it difficult to apply existing multiple access protocols, such as random access channel (RACH). To overcome this issue, in this paper, we propose a novel random access solution for LEO SAT networks, called as S-RACH. In contrast to existing standardized protocols, S-RACH is a model-free approach using deep reinforcement learning (DRL). Compared to RACH, we show from various simulations that our proposed S-RACH yields around 2x lower average access delay.

AB - A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. However, such wide coverage rather makes it difficult to apply existing multiple access protocols, such as random access channel (RACH). To overcome this issue, in this paper, we propose a novel random access solution for LEO SAT networks, called as S-RACH. In contrast to existing standardized protocols, S-RACH is a model-free approach using deep reinforcement learning (DRL). Compared to RACH, we show from various simulations that our proposed S-RACH yields around 2x lower average access delay.

UR - http://www.scopus.com/inward/record.url?scp=85137804625&partnerID=8YFLogxK

U2 - 10.1109/VTC2022-Spring54318.2022.9860594

DO - 10.1109/VTC2022-Spring54318.2022.9860594

M3 - Conference contribution

AN - SCOPUS:85137804625

T3 - IEEE Vehicular Technology Conference

BT - 2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring

Y2 - 19 June 2022 through 22 June 2022

ER -

Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this