Deep-Learning based Multiuser Detection for NOMA

In this paper, we study an application of deep learning to uplink multiuser detection (MUD) for non-orthogonal multiple access (NOMA) scheme based on Welch bound equality spread multiple access (WSMA). Several non-cooperating users, each with its own preassigned NOMA signature sequence (SS), transmit over the same resource. These SSs have low correlation among them and aid in the user separation at the receiver during MUD. Several subtasks such as equalizing, combining, slicing, signal reconstruction and interference cancellation are involved in MUD. The neural network (NN) considered in this paper replaces these well-defined receiver blocks with a single black box, i.e., the NN provides a one-shot approximation for these modules. We consider two different supervised feed-forward NN implementations, namely, a deep NN and a 2D-Convolutional NN, for MUD. Performance of these two NNs is compared with the conventional receivers. Simulation results show that by proper selection of the NN parameters, it is possible for the black box approximation to provide faster and better performance, compared to conventional MUD schemes, and it achieves almost the same symbol error rate as the ultimate one obtained by the complex maximum likelihood-based detectors.

[1]  Behrooz Makki,et al.  Download Elastic Traffic Rate Optimization via NOMA Protocols , 2019, IEEE Transactions on Vehicular Technology.

[2]  Soung Chang Liew,et al.  Deep Learning for Joint MIMO Detection and Channel Decoding , 2018, 2019 IEEE 30th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC).

[3]  Mohamed-Slim Alouini,et al.  A Survey of NOMA: Current Status and Open Research Challenges , 2019, IEEE Open Journal of the Communications Society.

[4]  Jae-Mo Kang,et al.  Deep Learning-Based MIMO-NOMA With Imperfect SIC Decoding , 2020, IEEE Systems Journal.

[5]  H. Vincent Poor,et al.  NOMA: An Information Theoretic Perspective , 2015, ArXiv.

[6]  Timothy N. Davidson,et al.  Flexible Codebook Design for Limited Feedback Systems Via Sequential Smooth Optimization on the Grassmannian Manifold , 2014, IEEE Transactions on Signal Processing.

[7]  Jing Wang,et al.  Uplink Nonorthogonal Multiple Access in 5G Systems , 2016, IEEE Communications Letters.

[8]  Zhiguo Ding,et al.  A General Power Allocation Scheme to Guarantee Quality of Service in Downlink and Uplink NOMA Systems , 2016, IEEE Transactions on Wireless Communications.

[9]  Uwe Meier,et al.  Wireless interference identification with convolutional neural networks , 2017, 2017 IEEE 15th International Conference on Industrial Informatics (INDIN).

[10]  H. Vincent Poor,et al.  A General MIMO Framework for NOMA Downlink and Uplink Transmission Based on Signal Alignment , 2015, IEEE Transactions on Wireless Communications.

[11]  Hamed Haddadi,et al.  Deep Learning in Mobile and Wireless Networking: A Survey , 2018, IEEE Communications Surveys & Tutorials.

[12]  Mehdi Bennis,et al.  Wireless Network Intelligence at the Edge , 2018, Proceedings of the IEEE.

[13]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[14]  Xiaohu You,et al.  Joint Neural Network Equalizer and Decoder , 2018, 2018 15th International Symposium on Wireless Communication Systems (ISWCS).

[15]  Ekram Hossain,et al.  Modeling and Analysis of Uplink Non-Orthogonal Multiple Access in Large-Scale Cellular Networks Using Poisson Cluster Processes , 2016, IEEE Transactions on Communications.

[16]  S. Moshavi,et al.  Multi-user detection for DS-CDMA communications , 1996, IEEE Commun. Mag..

[17]  Geoffrey Ye Li,et al.  Initial Results on Deep Learning for Joint Channel Equalization and Decoding , 2017, 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall).

[18]  Christopher Rose,et al.  Interference Avoidance Methods for Wireless Systems , 2004 .

[19]  Qing Chang,et al.  A Deep Learning Approach for MIMO-NOMA Downlink Signal Detection , 2019, Sensors.

[20]  Yao Xie,et al.  On Block Coherence of Frames , 2013, 1307.7544.

[21]  Anass Benjebbour,et al.  Non-Orthogonal Multiple Access (NOMA) for Cellular Future Radio Access , 2013, 2013 IEEE 77th Vehicular Technology Conference (VTC Spring).

[22]  Muhammad Imran,et al.  Non-Orthogonal Multiple Access (NOMA) for cellular future radio access , 2017 .

[23]  Myung-Sun Baek,et al.  Implementation Methodologies of Deep Learning-Based Signal Detection for Conventional MIMO Transmitters , 2019, IEEE Transactions on Broadcasting.

[24]  Humaira Nishat,et al.  A Study On Non Orthogonal Multiple Access (NOMA) For 5G , 2018 .

[25]  Derrick Wing Kwan Ng,et al.  Optimal Joint Power and Subcarrier Allocation for Full-Duplex Multicarrier Non-Orthogonal Multiple Access Systems , 2016, IEEE Transactions on Communications.

[26]  Geoffrey Ye Li,et al.  Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems , 2017, IEEE Wireless Communications Letters.

[27]  Kun Lu,et al.  A Survey of Non-Orthogonal Multiple Access for 5G , 2017, 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall).