Adaptive repetition scheme with machine learning for 3GPP NB-IoT

Li Sheng Chen; Wei Ho Chung; Ing Yi Chen; Sy Yen Kuo

doi:10.1109/PRDC.2018.00046

Adaptive repetition scheme with machine learning for 3GPP NB-IoT

Li Sheng Chen
, Wei Ho Chung
, Ing Yi Chen
, Sy Yen Kuo

資訊工程系

研究成果: 書籍/報告/會議論文中的章節 › 會議投稿 › 同行評審

10 引文斯高帕斯（Scopus）

摘要

In NB-IoT systems, UEs with poor signal quality employ more repetitions to compensate for additional signal attenuation. Excessively high CE levels and repetitions of UEs lead to wastage of valuable wireless resources, whereas inadequate CE levels and repetitions result in data retrieval failure at the receiving end. Therefore, a machine learning-based adaptive repetition scheme for a 3GPP NB-IoT system is proposed in this work to effectively improve overall network transmission efficiency. The results of simulation show the effect of the discount factor? on the convergence behavior of the proposed scheme, with a lower discount factor value denoting the myopic behavior of the proposed scheme, which results from the fact that it places more emphasis on immediate rewards. And the propose scheme is capable of effectively improving the average spectral efficiency.

原文	English
主出版物標題	Proceedings - 2018 IEEE 23rd Pacific Rim International Symposium on Dependable Computing, PRDC 2018
發行者	IEEE Computer Society
頁面	252-256
頁數	5
ISBN（電子）	9781538657003
DOIs	https://doi.org/10.1109/PRDC.2018.00046
出版狀態	Published - 2 7月 2018
事件	23rd IEEE Pacific Rim International Symposium on Dependable Computing, PRDC 2018 - Taipei, Taiwan 持續時間: 4 12月 2018 → 7 12月 2018

出版系列

名字	Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC
卷	2018-December
ISSN（列印）	1541-0110

Conference

Conference	23rd IEEE Pacific Rim International Symposium on Dependable Computing, PRDC 2018
國家/地區	Taiwan
城市	Taipei
期間	4/12/18 → 7/12/18

文獻附註

Publisher Copyright:
© 2018 IEEE.

存取文件

10.1109/PRDC.2018.00046

其它文件與鏈接

Link to publication in Scopus

引用此

Chen, L. S., Chung, W. H., Chen, I. Y., & Kuo, S. Y. (2018). Adaptive repetition scheme with machine learning for 3GPP NB-IoT. 於 Proceedings - 2018 IEEE 23rd Pacific Rim International Symposium on Dependable Computing, PRDC 2018 (頁 252-256). 文章 8639638 (Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC; 卷 2018-December). IEEE Computer Society. https://doi.org/10.1109/PRDC.2018.00046

@inproceedings{a918f92e65f640159b638d97b96f5425,

title = "Adaptive repetition scheme with machine learning for 3GPP NB-IoT",

abstract = "In NB-IoT systems, UEs with poor signal quality employ more repetitions to compensate for additional signal attenuation. Excessively high CE levels and repetitions of UEs lead to wastage of valuable wireless resources, whereas inadequate CE levels and repetitions result in data retrieval failure at the receiving end. Therefore, a machine learning-based adaptive repetition scheme for a 3GPP NB-IoT system is proposed in this work to effectively improve overall network transmission efficiency. The results of simulation show the effect of the discount factor? on the convergence behavior of the proposed scheme, with a lower discount factor value denoting the myopic behavior of the proposed scheme, which results from the fact that it places more emphasis on immediate rewards. And the propose scheme is capable of effectively improving the average spectral efficiency.",

keywords = "Adaptive Repetition, Machine Learning, Narrowband Internet-of-Things (NB-IoT)",

author = "Chen, \{Li Sheng\} and Chung, \{Wei Ho\} and Chen, \{Ing Yi\} and Kuo, \{Sy Yen\}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 23rd IEEE Pacific Rim International Symposium on Dependable Computing, PRDC 2018 ; Conference date: 04-12-2018 Through 07-12-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/PRDC.2018.00046",

language = "???core.languages.en\_GB???",

series = "Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC",

publisher = "IEEE Computer Society",

pages = "252--256",

booktitle = "Proceedings - 2018 IEEE 23rd Pacific Rim International Symposium on Dependable Computing, PRDC 2018",

}

Chen, LS, Chung, WH, Chen, IY & Kuo, SY 2018, Adaptive repetition scheme with machine learning for 3GPP NB-IoT. 於 Proceedings - 2018 IEEE 23rd Pacific Rim International Symposium on Dependable Computing, PRDC 2018., 8639638, Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC, 卷 2018-December, IEEE Computer Society, 頁 252-256, 23rd IEEE Pacific Rim International Symposium on Dependable Computing, PRDC 2018, Taipei, Taiwan, 4/12/18. https://doi.org/10.1109/PRDC.2018.00046

Adaptive repetition scheme with machine learning for 3GPP NB-IoT. / Chen, Li Sheng; Chung, Wei Ho; Chen, Ing Yi 等.
Proceedings - 2018 IEEE 23rd Pacific Rim International Symposium on Dependable Computing, PRDC 2018. IEEE Computer Society, 2018. p. 252-256 8639638 (Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC; 卷 2018-December).

研究成果: 書籍/報告/會議論文中的章節 › 會議投稿 › 同行評審

TY - GEN

T1 - Adaptive repetition scheme with machine learning for 3GPP NB-IoT

AU - Chen, Li Sheng

AU - Chung, Wei Ho

AU - Chen, Ing Yi

AU - Kuo, Sy Yen

PY - 2018/7/2

Y1 - 2018/7/2

N2 - In NB-IoT systems, UEs with poor signal quality employ more repetitions to compensate for additional signal attenuation. Excessively high CE levels and repetitions of UEs lead to wastage of valuable wireless resources, whereas inadequate CE levels and repetitions result in data retrieval failure at the receiving end. Therefore, a machine learning-based adaptive repetition scheme for a 3GPP NB-IoT system is proposed in this work to effectively improve overall network transmission efficiency. The results of simulation show the effect of the discount factor? on the convergence behavior of the proposed scheme, with a lower discount factor value denoting the myopic behavior of the proposed scheme, which results from the fact that it places more emphasis on immediate rewards. And the propose scheme is capable of effectively improving the average spectral efficiency.

AB - In NB-IoT systems, UEs with poor signal quality employ more repetitions to compensate for additional signal attenuation. Excessively high CE levels and repetitions of UEs lead to wastage of valuable wireless resources, whereas inadequate CE levels and repetitions result in data retrieval failure at the receiving end. Therefore, a machine learning-based adaptive repetition scheme for a 3GPP NB-IoT system is proposed in this work to effectively improve overall network transmission efficiency. The results of simulation show the effect of the discount factor? on the convergence behavior of the proposed scheme, with a lower discount factor value denoting the myopic behavior of the proposed scheme, which results from the fact that it places more emphasis on immediate rewards. And the propose scheme is capable of effectively improving the average spectral efficiency.

KW - Adaptive Repetition

KW - Machine Learning

KW - Narrowband Internet-of-Things (NB-IoT)

UR - https://www.scopus.com/pages/publications/85062822571

U2 - 10.1109/PRDC.2018.00046

DO - 10.1109/PRDC.2018.00046

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85062822571

T3 - Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC

SP - 252

EP - 256

BT - Proceedings - 2018 IEEE 23rd Pacific Rim International Symposium on Dependable Computing, PRDC 2018

PB - IEEE Computer Society

T2 - 23rd IEEE Pacific Rim International Symposium on Dependable Computing, PRDC 2018

Y2 - 4 December 2018 through 7 December 2018

ER -

Chen LS, Chung WH, Chen IY, Kuo SY. Adaptive repetition scheme with machine learning for 3GPP NB-IoT. 於 Proceedings - 2018 IEEE 23rd Pacific Rim International Symposium on Dependable Computing, PRDC 2018. IEEE Computer Society. 2018. p. 252-256. 8639638. (Proceedings of IEEE Pacific Rim International Symposium on Dependable Computing, PRDC). doi: 10.1109/PRDC.2018.00046

Adaptive repetition scheme with machine learning for 3GPP NB-IoT

摘要

出版系列

Conference

文獻附註

存取文件

其它文件與鏈接

指紋

引用此