Uplink NOMA signal transmission with convolutional neural networks approach

doi:10.23919/JSEE.2020.000068

Journal of Systems Engineering and Electronics ›› 2020, Vol. 31 ›› Issue (5): 890-898.doi: 10.23919/JSEE.2020.000068

• Electronics Technology • Previous Articles Next Articles

Uplink NOMA signal transmission with convolutional neural networks approach

Chuan LIN¹(), Qing CHANG^1,*(), Xianxu LI²()

¹ School of Electronic and Information Engineering, Beihang University, Beijing 100191, China
² State Grid Information and Telecommunication Branch, Beijing 100761, China

Received:2020-03-16 Online:2020-10-30 Published:2020-10-30
Contact: Qing CHANG E-mail:lclkzjp@hotmail.com;changq@263.net;lixianxu@buaa.edu
About author:LIN Chuan was born in 1988. He received his B.S. degree in communication engineering from Guilin University of Electronic Technology, Guilin, China in 2010 and M.S. degree in communication and information system from Xidian University, Xi'an, China. He is now studying toward his Ph.D. degree in the School of Electronic and Information Engineering, Beihang University. His research interests include wireless communication and deep learning. E-mail: lclkzjp@hotmail.com|CHANG Qing was born in 1962. He received his B.S. degree in mathematics from Beijing Normal University in 1982 and M.S. degree in mathematics and Ph.D. degree in communication and information system from Beihang University in 1991 and 1995 respectively. Since 2000, he has been a professor with the School of Electronic and Information Engineering, Beihang University. He is the dean of the Teaching-Research Section of Communication and Information System in his school. He is the author of one book, over 30 articles, and over ten patents. His research interests include satellite communication and navigation, and wireless networks. E-mail: changq@263.net|LI Xianxu was born in 1988. He received his B.S. degree in communication and information system from Beijing University of Posts and Telecommunications, Beijing, China in 2010 and Ph.D. degree in communication and information system from Beihang University, Beijing, China in 2017. He is now working for State Grid Information and Telecommunication Branch. His research interests include navigation, satellite networks and network coding. E-mail: lixianxu@buaa.edu
Supported by:
the National Natural Science Foundation of China(61471021);This work was supported by the National Natural Science Foundation of China (61471021)

Abstract

Abstract:

Non-orthogonal multiple access (NOMA), featuring high spectrum efficiency, massive connectivity and low latency, holds immense potential to be a novel multi-access technique in fifthgeneration (5G) communication. Successive interference cancellation (SIC) is proved to be an effective method to detect the NOMA signal by ordering the power of received signals and then decoding them. However, the error accumulation effect referred to as error propagation is an inevitable problem. In this paper, we propose a convolutional neural networks (CNNs) approach to restore the desired signal impaired by the multiple input multiple output (MIMO) channel. Especially in the uplink NOMA scenario, the proposed method can decode multiple users' information in a cluster instantaneously without any traditional communication signal processing steps. Simulation experiments are conducted in the Rayleigh channel and the results demonstrate that the error performance of the proposed learning system outperforms that of the classic SIC detection. Consequently, deep learning has disruptive potential to replace the conventional signal detection method.

Key words: non-orthogonal multiple access (NOMA), deep learning (DL), convolutional neural networks (CNNs), signal detection

Chuan LIN, Qing CHANG, Xianxu LI. Uplink NOMA signal transmission with convolutional neural networks approach[J]. Journal of Systems Engineering and Electronics, 2020, 31(5): 890-898.

Figures/Tables 11

Fig 1

Fig 2

Fig 3

Table 1

Fig 4

Fig 5

Table 2

Fig 6

Fig 7

Fig 8

Fig 9

References 22

1	HIGUCHI K, BENJEBBOUR A. Non-orthogonal multiple access (NOMA) with successive interference cancellation for future radio access. IEICE Trans. on Communication, 2015, 98 (3): 403- 414.
2	O'SHEA T J, HOYDIS J. An introduction to machine learning communications systems. http://arxiv.org/pdf/1702.00832.pdf.
3	NACHMANI E, BE'ERY Y, BURSHTEIN D. Learning to decode linear codes using deep learning. Proc. of the 54th Annual Conference on Communication, Control and Computing, 2016. doi: 10.1109/ALLERTON.2016.7852251
4	GRUBER T, CAMMERER S, HOYDIS J, et al. On deep learning-based channel decoding. Proc. of the 51st Annual Conference on Information Sciences and Systems, 2017, 1- 6.
5	LIANG F, SHEN C, WU F. An iterative BP-CNN architecture for channel decoding. IEEE Journal of Selected Topics in Signal Processing, 2018, 12 (1): 144- 159. doi: 10.1109/JSTSP.2018.2794062
6	SUN B, FENG H. Efficient compressed sensing for wireless neural recording: a deep learning approach. IEEE Signal Processing Letters, 2017, 24 (6): 863- 867. doi: 10.1109/LSP.2017.2697970
7	JEON Y S, HONG S N, LEE N. Blind detection for MIMO systems with low-resolution ADCs using supervised learning. Proc. of the IEEE International Conference on Communications, 2017, 21- 25.
8	WANG C. Research and application of traffic sign detection and recognition based on deep learning. Proc. of the International Conference on Robots & Intelligent System, 2018, 21- 23.
9	O'SHEA T, ERPEK T, CLANCY T C. Deep learning-based MIMO communications. http://arxiv.org/pdf/1707.07980.
10	YE H, LI G Y, JUANG B H. Power of deep learning for channel estimation and signal detection in OFDM systems. IEEE Wireless Communication Letters, 2017, 7 (1): 114- 117.
11	XU Y, LI D Z, WANG Z Y. A deep learning method based on convolutional neural network for automatic modulation classification of wireless signals. Proc. of the 2nd EAI International Conference on Machine Learning & Intelligent Communications, 2017, 5- 6.
12	SAETAN W, THIPCHAKSURAT S. Application of deep learning to energy-efficient power allocation scheme for 5G SC-NOMA system with imperfect SIC. Proc. of the 16th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, 2019, 661- 664.
13	ZHANG Y H, WANG X M, XU Y Y. Energy-efficient resource allocation in uplink NOMA systems with deep reinforcement learning. Proc. of the 11th International Conference on Wireless Communications and Signal Processing, 2019, 1- 6.
14	HE C F, HU Y, CHEN Y, et al. Joint power allocation and channel assignment for NOMA with deep reinforcement learning. IEEE Journal on Selected Areas in Communications, 2019, 37 (10): 2200- 2210. doi: 10.1109/JSAC.2019.2933762
15	SAETAN W, THIPCHAKSURAT S. Power allocation for sum rate maximization in 5G NOMA system with imperfect SIC: a deep learning approach. Proc. of the 4th International Conference on Information Technology, 2019, 195- 198.
16	YE N, LI X M, YU H X, et al. DeepNOMA: a unified framework for NOMA using deep multi-task learning. IEEE Trans. on Wireless Communications, 2020, 19 (4): 2208- 2225. doi: 10.1109/TWC.2019.2963185
17	GUI G, HUANG H, JUANG B H, et al. Deep learning for an effective non-orthogonal multiple access scheme. IEEE Trans. on Vehicular Technology, 2018, 67 (9): 8440- 8450. doi: 10.1109/TVT.2018.2848294
18	KANG J M, KIM I M, CHUN C J. Deep learning-based MIMO-NOMA with imperfect SIC decoding. IEEE Systems Journal, 2020, 14 (3): 3414- 3417. doi: 10.1109/JSYST.2019.2937463
19	LIN C, CHANG Q, LI X X. A deep learning approach for MIMO-NOMA downlink signal detection. Sensors, 2019, 19 (11): 2526. doi: 10.3390/s19112526
20	KOLDA T G, BADER B W. Tensor decompositions and applications. SIAM Review, 2009, 51 (3): 455- 500. doi: 10.1137/07070111X
21	HUANG G, LIU Z, LAURENS V D M, et al. Densely connected convolutional networks. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, 2261- 2269.
22	KINGMA D, BA J. Adam: a method for stochastic optimization. Proc. of the 3rd International Conference on Learning Representations, 2015, 7- 9.

Layer	Output size	DenseNOMA
Convolution	4×28	(4×7) conv, (1, 2) stride
Dense block 1	4×28	$\left[ {\begin{array}{*{20}{l}} {1 \times 1}\\ {3 \times 3} \end{array}} \right]$ conv × 2
Transition layer 1	4×284×14	(1×1) conv(2×2) Avg pool, (1, 2) stride
Dense block 2	4×14	$\left[ {\begin{array}{*{20}{l}} {1 \times 1}\\ {3 \times 3} \end{array}} \right]$ conv × 4
Transition layer 2	4×144×7	(1×1) conv(2×2) Avg pool, (1, 2) stride
Dense block 3	4×84×8	Padding$\left[ {\begin{array}{*{20}{l}} {1 \times 1}\\ {3 \times 3} \end{array}} \right]$ conv × 8
Transition layer 3	4×84×4	(1×1) conv(2×2) Avg pool, (1, 2) stride
Dense block 4	4×4	$\left[ {\begin{array}{*{20}{l}} {1 \times 1}\\ {3 \times 3} \end{array}} \right]$ conv × 4
Classification	1×116	(4×4) Avg pool228D fully-connected

Parameter	Value
Operating system	Windows 10
Programming	Python + Matlab
Framework	TensorFlow with GPU
Channel	Rayleigh + AWGN
UEs/cluster	2
Transmit antennas	1
Receive antennas	4
Modulation	Phase shift keying
Training symbol	20 480
Testing symbol	409 600
Sample/symbol	50
Power allocation factor	0.8

[1]	Chengzhi Yang, Zhiwei Xiong, Yang Guo, and Bolin Zhang. LPI radar signal detection based on the combination of FFT and segmented autocorrelation plus PAHT [J]. Systems Engineering and Electronics, 2017, 28(5): 890-899.
[2]	Hongwei Wang, Xiangyu Fan, You Chen, and Yuanzhi Yang. Wigner-Hough transform based on slice’s entropy and its application to multi-LFM signal detection [J]. Systems Engineering and Electronics, 2017, 28(4): 634-.
[3]	Rongling Lang, Xinyue Li, Fei Gao, and Liang Yang. Re-scaling and adaptive stochastic resonance as a tool for weak GNSS signal acquisition [J]. Journal of Systems Engineering and Electronics, 2016, 27(2): 290-296.
[4]	Yongjian Liu, Peng Xiao, Hongchao Wu, and Weihua Xiao. LPI radar signal detection based on radial integration of Choi-Williams time-frequency image [J]. Journal of Systems Engineering and Electronics, 2015, 26(5): 973-981.
[5]	Yunhe Cao, Shenghua Wang, Yu Wang, and Shenghua Zhou. Target detection for low angle radar based on multi-frequency order-statistics [J]. Journal of Systems Engineering and Electronics, 2015, 26(2): 267-273.
[6]	Weijian Liu, Wenchong Xie, Rongfeng Li, Fei Gao, Xiaoqin Hu, and Yongliang Wang. Adaptive detection in the presence of signal mismatch [J]. Journal of Systems Engineering and Electronics, 2015, 26(1): 38-.
[7]	Qiang Xie, Luping Xu, and Hua Zhang. X-ray pulsar signal detection using photon interarrival time [J]. Journal of Systems Engineering and Electronics, 2013, 24(6): 899-905.

Uplink NOMA signal transmission with convolutional neural networks approach

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 11

References 22

Related Articles 7

Recommended Articles

Metrics

Comments