Deep Learning-Based Modulation Detection for NOMA Systems

Since the signal with strong power should be demodulated first for successive interference cancellation (SIC) demodulation in non-orthogonal multiple access (NOMA) systems, the base station (BS) must inform modulation mode of the far user terminal (UT). To avoid unnecessary signaling overhead in this process, a blind detection algorithm of NOMA signal modulation mode is designed in this paper. Taking the joint constellation density diagrams of NOMA signal as the detection features, deep residual network was built for classification, so as to detect the modulation mode of NOMA signal. In view of the fact that the joint constellation diagrams are easily polluted by high intensity noise and loses its real distribution pattern, the wavelet denoising method is adopted to improve the quality of constellations. The simulation results represent that the proposed algorithm can achieve satisfactory detection accuracy in NOMA systems. In addition, the factors affecting the recognition performance are also verified and analyzed.

[1]  Daejung Yoon,et al.  Blind Signal Classification for Non-Orthogonal Multiple Access in Vehicular Networks , 2018, IEEE Transactions on Vehicular Technology.

[2]  Anass Benjebbour,et al.  Non-orthogonal Multiple Access (NOMA) with Successive Interference Cancellation for Future Radio Access , 2015, IEICE Trans. Commun..

[3]  Guan Gui,et al.  Deep Learning for an Effective Nonorthogonal Multiple Access Scheme , 2018, IEEE Transactions on Vehicular Technology.

[4]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[5]  Xiaohu You,et al.  AI for 5G: research directions and paradigms , 2018, Science China Information Sciences.

[6]  Yang Peng,et al.  Dynamic User Grouping-Based NOMA Over Rayleigh Fading Channels , 2019, IEEE Access.

[7]  Xiao Yu Gu.  Research on Modulation Recognition Algorithm of Digital Communication Signal Based on Wavelet Denoising , 2014 .

[8]  Yoshihisa Kishiyama,et al.  Performance of non-orthogonal access with SIC in cellular downlink using proportional fair-based resource allocation , 2012, 2012 International Symposium on Wireless Communication Systems (ISWCS).

[9]  Yu Wang,et al.  Deep Learning-Based Cooperative Automatic Modulation Classification Method for MIMO Systems , 2020, IEEE Transactions on Vehicular Technology.

[10]  Shi Rong,et al.  Modulation Classification Based on Cyclic Spectral Features for Co-Channel Time-Frequency Overlapped Two-Signal , 2009, 2009 Pacific-Asia Conference on Circuits, Communications and Systems.

[11]  Martin Haenggi,et al.  Superposition Coding Strategies: Design and Experimental Evaluation , 2012, IEEE Transactions on Wireless Communications.

[12]  Guixia Kang,et al.  A Machine-Learning-Based Blind Detection on Interference Modulation Order in NOMA Systems , 2018, IEEE Communications Letters.

[13]  Jerry M. Mendel,et al.  Maximum-likelihood classification for digital amplitude-phase modulations , 2000, IEEE Trans. Commun..

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[16]  Jin Zhang,et al.  Spectrum Analysis and Convolutional Neural Network for Automatic Modulation Recognition , 2019, IEEE Wireless Communications Letters.

[17]  Yu-Dong Yao,et al.  Modulation Classification Based on Signal Constellation Diagrams and Deep Learning , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Fumiyuki Adachi,et al.  Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions , 2019, IEEE Wireless Communications.

[19]  Timothy J. O'Shea,et al.  Deep architectures for modulation recognition , 2017, 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN).

[20]  Pingzhi Fan,et al.  On the Performance of Non-Orthogonal Multiple Access in 5G Systems with Randomly Deployed Users , 2014, IEEE Signal Processing Letters.

[21]  Yoshihisa Kishiyama,et al.  Performance of Non-orthogonal Multiple Access with SIC in Cellular Downlink Using Proportional Fair-Based Resource Allocation , 2015, IEICE Trans. Commun..