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 - http://www.scopus.com/inward/record.url?scp=85100838783&partnerID=8YFLogxK
U2 - 10.1109/JLT.2021.3058591
DO - 10.1109/JLT.2021.3058591
M3 - Article
AN - SCOPUS:85100838783
VL - 39
SP - 3081
EP - 3087
JO - Journal of Lightwave Technology
JF - Journal of Lightwave Technology
SN - 0733-8724
IS - 10
ER -