On Performance of Deep Reinforcement Learning-based Listen-Before-Talk (LBT) Scheme

Minjeong Lee; Jaewook Lee; Hochan Lee; Taeyun Kim; Sangheon Pack

doi:10.1109/icoin50884.2021.9333903

On Performance of Deep Reinforcement Learning-based Listen-Before-Talk (LBT) Scheme

Minjeong Lee, Jaewook Lee, Hochan Lee, Taeyun Kim, Sangheon Pack

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

1 Citation (Scopus)

Abstract

Licensed assisted access (LAA) is a promising system to overcome the limited radio resource by sharing the unlicensed band with wireless local area networks (WLANs), and the listen-before-talk (LBT) scheme is a key technology for providing fairness between LAA and WLAN. Recently, deep reinforcement learning (DRL) has been investigated to improve the performance of LBT; however, such approaches assume that there is no processing delay and thus the optimal decision can be immediately done. In this paper, we evaluate the performance of the DRL-based LBT (DRL-LBT) scheme when different processing delays are considered for DRL. Evaluation results demonstrate that the throughput fairness index and the total throughput of DRL-LBT with the processing delay can be degraded up to by 9.4% and 10.0%, respectively, compared with an ideal case without any processing delay.

Original language	English
Title of host publication	35th International Conference on Information Networking, ICOIN 2021
Publisher	IEEE Computer Society
Pages	72-75
Number of pages	4
ISBN (Electronic)	9781728191003
DOIs	https://doi.org/10.1109/icoin50884.2021.9333903
Publication status	Published - 2021 Jan 13
Event	35th International Conference on Information Networking, ICOIN 2021 - Jeju Island, Korea, Republic of Duration: 2021 Jan 13 → 2021 Jan 16

Publication series

Name	International Conference on Information Networking
Volume	2021-January
ISSN (Print)	1976-7684

Conference

Conference	35th International Conference on Information Networking, ICOIN 2021
Country/Territory	Korea, Republic of
City	Jeju Island
Period	21/1/13 → 21/1/16

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Deep Reinforcement Learning (DRL)
Licensed assisted access (LAA)
Listen-before-talk (LBT)

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems

Access to Document

10.1109/icoin50884.2021.9333903

Cite this

Lee, M., Lee, J., Lee, H., Kim, T., & Pack, S. (2021). On Performance of Deep Reinforcement Learning-based Listen-Before-Talk (LBT) Scheme. In 35th International Conference on Information Networking, ICOIN 2021 (pp. 72-75). Article 9333903 (International Conference on Information Networking; Vol. 2021-January). IEEE Computer Society. https://doi.org/10.1109/icoin50884.2021.9333903

On Performance of Deep Reinforcement Learning-based Listen-Before-Talk (LBT) Scheme. / Lee, Minjeong; Lee, Jaewook; Lee, Hochan et al.
35th International Conference on Information Networking, ICOIN 2021. IEEE Computer Society, 2021. p. 72-75 9333903 (International Conference on Information Networking; Vol. 2021-January).

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

Lee, M, Lee, J, Lee, H, Kim, T & Pack, S 2021, On Performance of Deep Reinforcement Learning-based Listen-Before-Talk (LBT) Scheme. in 35th International Conference on Information Networking, ICOIN 2021., 9333903, International Conference on Information Networking, vol. 2021-January, IEEE Computer Society, pp. 72-75, 35th International Conference on Information Networking, ICOIN 2021, Jeju Island, Korea, Republic of, 21/1/13. https://doi.org/10.1109/icoin50884.2021.9333903

@inproceedings{4d0bed9fb9c642ab8556d05c19522b39,

title = "On Performance of Deep Reinforcement Learning-based Listen-Before-Talk (LBT) Scheme",

abstract = "Licensed assisted access (LAA) is a promising system to overcome the limited radio resource by sharing the unlicensed band with wireless local area networks (WLANs), and the listen-before-talk (LBT) scheme is a key technology for providing fairness between LAA and WLAN. Recently, deep reinforcement learning (DRL) has been investigated to improve the performance of LBT; however, such approaches assume that there is no processing delay and thus the optimal decision can be immediately done. In this paper, we evaluate the performance of the DRL-based LBT (DRL-LBT) scheme when different processing delays are considered for DRL. Evaluation results demonstrate that the throughput fairness index and the total throughput of DRL-LBT with the processing delay can be degraded up to by 9.4% and 10.0%, respectively, compared with an ideal case without any processing delay.",

keywords = "Deep Reinforcement Learning (DRL), Licensed assisted access (LAA), Listen-before-talk (LBT)",

author = "Minjeong Lee and Jaewook Lee and Hochan Lee and Taeyun Kim and Sangheon Pack",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 35th International Conference on Information Networking, ICOIN 2021 ; Conference date: 13-01-2021 Through 16-01-2021",

year = "2021",

month = jan,

day = "13",

doi = "10.1109/icoin50884.2021.9333903",

language = "English",

series = "International Conference on Information Networking",

publisher = "IEEE Computer Society",

pages = "72--75",

booktitle = "35th International Conference on Information Networking, ICOIN 2021",

}

TY - GEN

T1 - On Performance of Deep Reinforcement Learning-based Listen-Before-Talk (LBT) Scheme

AU - Lee, Minjeong

AU - Lee, Jaewook

AU - Lee, Hochan

AU - Kim, Taeyun

AU - Pack, Sangheon

PY - 2021/1/13

Y1 - 2021/1/13

N2 - Licensed assisted access (LAA) is a promising system to overcome the limited radio resource by sharing the unlicensed band with wireless local area networks (WLANs), and the listen-before-talk (LBT) scheme is a key technology for providing fairness between LAA and WLAN. Recently, deep reinforcement learning (DRL) has been investigated to improve the performance of LBT; however, such approaches assume that there is no processing delay and thus the optimal decision can be immediately done. In this paper, we evaluate the performance of the DRL-based LBT (DRL-LBT) scheme when different processing delays are considered for DRL. Evaluation results demonstrate that the throughput fairness index and the total throughput of DRL-LBT with the processing delay can be degraded up to by 9.4% and 10.0%, respectively, compared with an ideal case without any processing delay.

AB - Licensed assisted access (LAA) is a promising system to overcome the limited radio resource by sharing the unlicensed band with wireless local area networks (WLANs), and the listen-before-talk (LBT) scheme is a key technology for providing fairness between LAA and WLAN. Recently, deep reinforcement learning (DRL) has been investigated to improve the performance of LBT; however, such approaches assume that there is no processing delay and thus the optimal decision can be immediately done. In this paper, we evaluate the performance of the DRL-based LBT (DRL-LBT) scheme when different processing delays are considered for DRL. Evaluation results demonstrate that the throughput fairness index and the total throughput of DRL-LBT with the processing delay can be degraded up to by 9.4% and 10.0%, respectively, compared with an ideal case without any processing delay.

KW - Deep Reinforcement Learning (DRL)

KW - Licensed assisted access (LAA)

KW - Listen-before-talk (LBT)

UR - http://www.scopus.com/inward/record.url?scp=85100737642&partnerID=8YFLogxK

U2 - 10.1109/icoin50884.2021.9333903

DO - 10.1109/icoin50884.2021.9333903

M3 - Conference contribution

AN - SCOPUS:85100737642

T3 - International Conference on Information Networking

SP - 72

EP - 75

BT - 35th International Conference on Information Networking, ICOIN 2021

PB - IEEE Computer Society

T2 - 35th International Conference on Information Networking, ICOIN 2021

Y2 - 13 January 2021 through 16 January 2021

ER -

On Performance of Deep Reinforcement Learning-based Listen-Before-Talk (LBT) Scheme

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this