A Machine Learning Based Signal Demodulator in NOMA-VLC

Bangjiang Lin; Qiwei Lai; Zabih Ghassemlooy; Xuan Tang

doi:10.1109/JLT.2021.3058591

A Machine Learning Based Signal Demodulator in NOMA-VLC

Bangjiang Lin, Qiwei Lai, Zabih Ghassemlooy, Xuan Tang^*

^*Corresponding author for this work

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

64 Citations (Scopus)

99 Downloads (Pure)

Abstract

Non-orthogonal multiple access (NOMA) is a promising scheme to improve the spectral efficiency, user fairness, and overall throughput in visible light communication (VLC) systems. However, the error propagation (EP) problem together with linear and nonlinear distortions induced by multipath, limited modulation bandwidth and nonlinearity of light emitting diode significantly limit the transmission performance of NOMA-VLC systems. In addition, having accurate channel state information, which is important in the recovery of NOMA signal, in mobile wireless VLC systems is challenging. In this work, we propose a convolutional neural network (CNN) based demodulator for NOMA-VLC, in which signal compensation and recovery are jointly realized. Both simulation and experiment results show that, the proposed CNN based demodulator can effectively compensate for both the linear and nonlinear distortions, thus achieving improved bit error ratio (BER) performances compared with the successive interference cancellation (SIC) and joint detection based receivers. Compared to SIC, the performance gains are 1.9, 2.7 and 2.7 dB for User1 for power allocation ratios (PARs) of 0.16, 0.25 and 0.36, respectively, which are 4, 4 and 2.6 dB for User2 for PARs of 0.16, 0.25 and 0.36, respectively.

Original language	English
Pages (from-to)	3081-3087
Number of pages	7
Journal	Journal of Lightwave Technology
Volume	39
Issue number	10
Early online date	10 Feb 2021
DOIs	https://doi.org/10.1109/JLT.2021.3058591
Publication status	Published - 15 May 2021

Keywords

artificial neural networks
convolution
convolutional neural network (CNN)
demodulation
NOMA
non-orthogonal multiple access (NOMA)
optical distortion
optical filters
resource management
visible light communications (VLC)
Convolutional neural network (CNN)

Access to Document

10.1109/JLT.2021.3058591

ML for NOMA-VLC final_ZGAccepted author manuscript, 674 KB

Cite this

@article{5f972fe583be46e0969e7718fc852e8d,

title = "A Machine Learning Based Signal Demodulator in NOMA-VLC",

abstract = "Non-orthogonal multiple access (NOMA) is a promising scheme to improve the spectral efficiency, user fairness, and overall throughput in visible light communication (VLC) systems. However, the error propagation (EP) problem together with linear and nonlinear distortions induced by multipath, limited modulation bandwidth and nonlinearity of light emitting diode significantly limit the transmission performance of NOMA-VLC systems. In addition, having accurate channel state information, which is important in the recovery of NOMA signal, in mobile wireless VLC systems is challenging. In this work, we propose a convolutional neural network (CNN) based demodulator for NOMA-VLC, in which signal compensation and recovery are jointly realized. Both simulation and experiment results show that, the proposed CNN based demodulator can effectively compensate for both the linear and nonlinear distortions, thus achieving improved bit error ratio (BER) performances compared with the successive interference cancellation (SIC) and joint detection based receivers. Compared to SIC, the performance gains are 1.9, 2.7 and 2.7 dB for User1 for power allocation ratios (PARs) of 0.16, 0.25 and 0.36, respectively, which are 4, 4 and 2.6 dB for User2 for PARs of 0.16, 0.25 and 0.36, respectively.",

keywords = "artificial neural networks, convolution, convolutional neural network (CNN), demodulation, NOMA, non-orthogonal multiple access (NOMA), optical distortion, optical filters, resource management, visible light communications (VLC), Convolutional neural network (CNN)",

author = "Bangjiang Lin and Qiwei Lai and Zabih Ghassemlooy and Xuan Tang",

note = "the Science and Technology Program of Quanzhou under Grant 2019C010R, Grant 2020G18, and Grant 2020C069, in part by the Science and Technology Program of Fujian Province under Grant 2019T3020 and Grant 2018H2001, in part by the Science and Technology Program of Sichuan Province under Grant 2020YFSY0021, in part by the STS Project of CAS and Fujian Province under Grant 2020T3026, in part by the Chunmiao Project of Haixi Institutes, CAS, and in part by the Innovation and Entrepreneurship Project of Industrial Park Management Committee of Wuping, Fujian.",

year = "2021",

month = may,

day = "15",

doi = "10.1109/JLT.2021.3058591",

language = "English",

volume = "39",

pages = "3081--3087",

journal = "Journal of Lightwave Technology",

issn = "0733-8724",

publisher = "IEEE",

number = "10",

}

TY - JOUR

T1 - A Machine Learning Based Signal Demodulator in NOMA-VLC

AU - Lin, Bangjiang

AU - Lai, Qiwei

AU - Ghassemlooy, Zabih

AU - Tang, Xuan

N1 - the Science and Technology Program of Quanzhou under Grant 2019C010R, Grant 2020G18, and Grant 2020C069, in part by the Science and Technology Program of Fujian Province under Grant 2019T3020 and Grant 2018H2001, in part by the Science and Technology Program of Sichuan Province under Grant 2020YFSY0021, in part by the STS Project of CAS and Fujian Province under Grant 2020T3026, in part by the Chunmiao Project of Haixi Institutes, CAS, and in part by the Innovation and Entrepreneurship Project of Industrial Park Management Committee of Wuping, Fujian.

PY - 2021/5/15

Y1 - 2021/5/15

N2 - Non-orthogonal multiple access (NOMA) is a promising scheme to improve the spectral efficiency, user fairness, and overall throughput in visible light communication (VLC) systems. However, the error propagation (EP) problem together with linear and nonlinear distortions induced by multipath, limited modulation bandwidth and nonlinearity of light emitting diode significantly limit the transmission performance of NOMA-VLC systems. In addition, having accurate channel state information, which is important in the recovery of NOMA signal, in mobile wireless VLC systems is challenging. In this work, we propose a convolutional neural network (CNN) based demodulator for NOMA-VLC, in which signal compensation and recovery are jointly realized. Both simulation and experiment results show that, the proposed CNN based demodulator can effectively compensate for both the linear and nonlinear distortions, thus achieving improved bit error ratio (BER) performances compared with the successive interference cancellation (SIC) and joint detection based receivers. Compared to SIC, the performance gains are 1.9, 2.7 and 2.7 dB for User1 for power allocation ratios (PARs) of 0.16, 0.25 and 0.36, respectively, which are 4, 4 and 2.6 dB for User2 for PARs of 0.16, 0.25 and 0.36, respectively.

AB - Non-orthogonal multiple access (NOMA) is a promising scheme to improve the spectral efficiency, user fairness, and overall throughput in visible light communication (VLC) systems. However, the error propagation (EP) problem together with linear and nonlinear distortions induced by multipath, limited modulation bandwidth and nonlinearity of light emitting diode significantly limit the transmission performance of NOMA-VLC systems. In addition, having accurate channel state information, which is important in the recovery of NOMA signal, in mobile wireless VLC systems is challenging. In this work, we propose a convolutional neural network (CNN) based demodulator for NOMA-VLC, in which signal compensation and recovery are jointly realized. Both simulation and experiment results show that, the proposed CNN based demodulator can effectively compensate for both the linear and nonlinear distortions, thus achieving improved bit error ratio (BER) performances compared with the successive interference cancellation (SIC) and joint detection based receivers. Compared to SIC, the performance gains are 1.9, 2.7 and 2.7 dB for User1 for power allocation ratios (PARs) of 0.16, 0.25 and 0.36, respectively, which are 4, 4 and 2.6 dB for User2 for PARs of 0.16, 0.25 and 0.36, respectively.

KW - artificial neural networks

KW - convolution

KW - convolutional neural network (CNN)

KW - demodulation

KW - NOMA

KW - non-orthogonal multiple access (NOMA)

KW - optical distortion

KW - optical filters

KW - resource management

KW - visible light communications (VLC)

KW - Convolutional neural network (CNN)

UR - https://www.scopus.com/pages/publications/85100838783

U2 - 10.1109/JLT.2021.3058591

DO - 10.1109/JLT.2021.3058591

M3 - Article

AN - SCOPUS:85100838783

SN - 0733-8724

VL - 39

SP - 3081

EP - 3087

JO - Journal of Lightwave Technology

JF - Journal of Lightwave Technology

IS - 10

ER -

A Machine Learning Based Signal Demodulator in NOMA-VLC

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this