Grant-Free NOMA with Device Activity Learning Using Long Short-Term Memory

Xiaqing Miao; Dongning Guo; Xiangming Li

doi:10.1109/LWC.2020.2976992

Grant-Free NOMA with Device Activity Learning Using Long Short-Term Memory

Xiaqing Miao^*, Dongning Guo, Xiangming Li

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

29 Scopus citations

Abstract

Non-orthogonal multiple access (NOMA) is a promising technique for future cellular networks. A major challenge in the uplink of grant-free NOMA is to identify all active devices as well as to decode their data. In the Internet of Things (IoT), the on-off activities of devices are predictable to various degrees. In this letter, a deep learning algorithm is employed to predict the device activities in the current slot by exploiting the history data. The prediction results are applied as input priors to a modified orthogonal matching pursuit (OMP) algorithm for joint device identification and data detection. Numerical simulation results demonstrate that the error rate is reduced to at least ten times as compared with conventional compressed sensing based algorithms at the same signal-to-noise ratio.

Original language	English (US)
Article number	9017984
Pages (from-to)	981-984
Number of pages	4
Journal	IEEE Wireless Communications Letters
Volume	9
Issue number	7
DOIs	https://doi.org/10.1109/LWC.2020.2976992
State	Published - Jul 2020

Funding

Manuscript received January 8, 2020; revised February 22, 2020; accepted February 22, 2020. Date of publication February 28, 2020; date of current version July 9, 2020. The work of Xiaqing Miao and Xiangming Li was supported in part by the Joint Fund of NSFC and the General Purpose Technology Research Program under Grant U1836201 and Grant U1636125, and in part by NSFC under Grant 61771051. The work of Dongning Guo was supported by NSF under Grant CCF-1910168. The associate editor coordinating the review of this article and approving it for publication was P. D. Diamantoulakis. (Corresponding author: Dongning Guo.) Xiaqing Miao and Xiangming Li are with the School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China (e-mail: [email protected]; [email protected]).

Keywords

Internet of Things (IoT)
Non-orthogonal multiple access (NOMA)
deep learning
multiuser detection
orthogonal matching pursuit (OMP)

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/LWC.2020.2976992

Cite this

@article{95acadcee79c429b952373036043b74a,

title = "Grant-Free NOMA with Device Activity Learning Using Long Short-Term Memory",

abstract = "Non-orthogonal multiple access (NOMA) is a promising technique for future cellular networks. A major challenge in the uplink of grant-free NOMA is to identify all active devices as well as to decode their data. In the Internet of Things (IoT), the on-off activities of devices are predictable to various degrees. In this letter, a deep learning algorithm is employed to predict the device activities in the current slot by exploiting the history data. The prediction results are applied as input priors to a modified orthogonal matching pursuit (OMP) algorithm for joint device identification and data detection. Numerical simulation results demonstrate that the error rate is reduced to at least ten times as compared with conventional compressed sensing based algorithms at the same signal-to-noise ratio.",

keywords = "Internet of Things (IoT), Non-orthogonal multiple access (NOMA), deep learning, multiuser detection, orthogonal matching pursuit (OMP)",

author = "Xiaqing Miao and Dongning Guo and Xiangming Li",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2020",

month = jul,

doi = "10.1109/LWC.2020.2976992",

language = "English (US)",

volume = "9",

pages = "981--984",

journal = "IEEE Wireless Communications Letters",

issn = "2162-2337",

publisher = "IEEE Communications Society",

number = "7",

}

TY - JOUR

T1 - Grant-Free NOMA with Device Activity Learning Using Long Short-Term Memory

AU - Miao, Xiaqing

AU - Guo, Dongning

AU - Li, Xiangming

PY - 2020/7

Y1 - 2020/7

N2 - Non-orthogonal multiple access (NOMA) is a promising technique for future cellular networks. A major challenge in the uplink of grant-free NOMA is to identify all active devices as well as to decode their data. In the Internet of Things (IoT), the on-off activities of devices are predictable to various degrees. In this letter, a deep learning algorithm is employed to predict the device activities in the current slot by exploiting the history data. The prediction results are applied as input priors to a modified orthogonal matching pursuit (OMP) algorithm for joint device identification and data detection. Numerical simulation results demonstrate that the error rate is reduced to at least ten times as compared with conventional compressed sensing based algorithms at the same signal-to-noise ratio.

AB - Non-orthogonal multiple access (NOMA) is a promising technique for future cellular networks. A major challenge in the uplink of grant-free NOMA is to identify all active devices as well as to decode their data. In the Internet of Things (IoT), the on-off activities of devices are predictable to various degrees. In this letter, a deep learning algorithm is employed to predict the device activities in the current slot by exploiting the history data. The prediction results are applied as input priors to a modified orthogonal matching pursuit (OMP) algorithm for joint device identification and data detection. Numerical simulation results demonstrate that the error rate is reduced to at least ten times as compared with conventional compressed sensing based algorithms at the same signal-to-noise ratio.

KW - Internet of Things (IoT)

KW - Non-orthogonal multiple access (NOMA)

KW - deep learning

KW - multiuser detection

KW - orthogonal matching pursuit (OMP)

UR - http://www.scopus.com/inward/record.url?scp=85088131323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85088131323&partnerID=8YFLogxK

U2 - 10.1109/LWC.2020.2976992

DO - 10.1109/LWC.2020.2976992

M3 - Article

AN - SCOPUS:85088131323

SN - 2162-2337

VL - 9

SP - 981

EP - 984

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

IS - 7

M1 - 9017984

ER -

Grant-Free NOMA with Device Activity Learning Using Long Short-Term Memory

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this