Please wait a minute...
浙江大学学报(工学版)
Journal of ZheJiang University (Engineering Science)  2022, Vol. 56 Issue (4): 816-822    DOI: 10.3785/j.issn.1008-973X.2022.04.022
    
Deep learning aided multi-user detection for up-link grant-free NOMA
Yang-zhao CHEN(),Wei-na YUAN*()
School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
Download: HTML     PDF(931KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A joint active user detection and data detection framework based on deep neural network (DNN) was proposed by combining the symbolic features of transmitted data in order to solve the problem of multi-user detection in uplink grant-free non-orthogonal multiple access (grant-free NOMA). The more general and practical scenario was considered, in which the user was randomly active in each time slot. The DNN solution result was used as a priori input of the modified orthogonal matching pursuit (OMP) algorithm in order to improve the user detection and date detection performance. The simulation results show that the proposed multi-user detection scheme has better user activity and data detection performance than the traditional greedy tracking algorithm and dynamic compressed sensing (DCS) multi-user detection algorithm.

Key words： massive machine type communication      grant-free transmission      non-orthogonal multiple access      compressed sensing      deep neural network     
Received: 20 May 2021      Published: 24 April 2022
CLC:  TN 929  
Fund:  国家自然科学基金资助项目（61501187）
Corresponding Authors: Wei-na YUAN     E-mail: 15957114952@163.com;wnyuan_ice@163.com
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Yang-zhao CHEN
Wei-na YUAN
Cite this article:

Yang-zhao CHEN,Wei-na YUAN. Deep learning aided multi-user detection for up-link grant-free NOMA. Journal of ZheJiang University (Engineering Science), 2022, 56(4): 816-822.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2022.04.022     OR     https://www.zjujournals.com/eng/Y2022/V56/I4/816


深度学习辅助上行免调度NOMA多用户检测方法

针对上行免调度非正交多址接入（NOMA）场景中多用户检测的问题，通过结合传输数据的符号特征，提出基于深度神经网络（DNN）的联合活跃用户检测和数据检测框架. 考虑更一般化的实际场景，即用户在每个时隙中随机活跃. 将DNN求解结果作为改进的正交匹配追踪(OMP)算法先验输入，修正提升活跃用户检测和数据检测性能. 仿真结果表明，提出的多用户检测方案比传统的贪婪追踪及动态压缩感知（DCS）多用户检测算法具有更好的用户活跃性及数据检测性能.


关键词： 大规模机器通信,  免调度传输,  非正交多址接入,  压缩感知,  深度神经网络 
Fig.1 Block diagram of proposed DNN-MUD method
QPSK传输符号 类别
$1 + i$ 1
$1 - i$ 2
$ - 1 + i$ 3
$ - 1 - i$ 4
0 5
Tab.1 Schematic table of transmission symbol feature mapping
参数 参数值
扩频序列长度 100
接入用户数 200
稀疏度 20
调制方式 QPSK
DNN层数 5
学习率 0.01
训练数据量 320000
批量大小 2 000
$ C $ 200
蒙特卡洛仿真次数 100
Tab.2 Simulation parameter table of Grant-free NOMA system
Fig.2 BER performance comparison under different SNR
Fig.3 BER performance of different algorithms under different SNR when users are randomly active
Fig.4 Comparison of BER performance of different algorithms under 300% load conditions
Fig.5 BER performance comparison against sparsity level
Fig.6 Probability of successful reconstruction of different algorithms under different SNR when users are randomly active
多用户检测算法 $t_{\rm{a}} $/s
LS 0.004 9
OMP 0.063 9
CoSaMP 0.615 7
SP 0.455 8
DCS 0.179 9
DPA-OMP中改进的OMP算法部分 0.048 5
DPA-OMP整体 0.253 5
Tab.3 Simulation running time of different multi-user detection algorithms
[1]   BOCKELMANN C, PRATAS N, NIKOPOUR H, et al Massive machine-type communications in 5G: physical and MAC-layer solutions[J]. IEEE Communications Magazine, 2016, 54 (9): 59- 65
doi: 10.1109/MCOM.2016.7565189
[2]   CIRIK A C, BALASUBRAMANYA N M, LAMPE L Multi-user detection using ADMM-based compressive sensing for uplink grant-free NOMA[J]. IEEE Wireless Communications Letters, 2018, 7 (1): 46- 49
doi: 10.1109/LWC.2017.2752165
[3]   HONG J, CHOI W, RAO B D Sparsity controlled random multiple access with compressed sensing[J]. IEEE Transactions on Wireless Communications, 2015, 14 (2): 998- 1010
doi: 10.1109/TWC.2014.2363165
[4]   TROPP J A, GILBERT A C Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007, 53 (12): 4655- 4666
doi: 10.1109/TIT.2007.909108
[5]   DAI W, MILENKOVIC O Subspace pursuit for compressive sensing signal reconstruction[J]. IEEE Transactions on Information Theory, 2009, 55 (5): 2230- 2249
doi: 10.1109/TIT.2009.2016006
[6]   NEEDELL D, TROPP J A Cosamp: iterative signal recovery from incomplete and inaccurate samples[J]. Applied and Computational Harmonic Analysis, 2009, 26 (3): 301- 321
doi: 10.1016/j.acha.2008.07.002
[7]   WEI C, LIU H, ZHANG Z, et al Approximate message passing-based joint user activity and data detection for NOMA[J]. IEEE Communications Letters, 2017, 21 (3): 640- 643
doi: 10.1109/LCOMM.2016.2624297
[8]   WANG B, DAI L, MIR T, et al Joint user activity and data detection based on structured compressive sensing for NOMA[J]. IEEE Communications Letters, 2016, 20 (7): 1473- 1476
[9]   ABEBE A T, KANG C G Iterative order recursive least square estimation for exploiting frame-wise sparsity in compressive sensing-based MTC[J]. IEEE Communications Letters, 2016, 20 (5): 1018- 1021
doi: 10.1109/LCOMM.2016.2539255
[10]   CUI Y, XU W, WANG Y, et al Side-information aided compressed multi-user detection for up-link grant-free NOMA[J]. IEEE Transactions on Wireless Communications, 2020, 19 (11): 7720- 7731
doi: 10.1109/TWC.2020.3015760
[11]   DU Y, CHENG C, DONG B, et al Block-sparsity-based multiuser detection for uplink grant-free NOMA[J]. IEEE Transactions on Wireless Communications, 2018, 17 (12): 7894- 7909
doi: 10.1109/TWC.2018.2872594
[12]   WANG B, DAI L, ZHANG Y, et al Dynamic compressive sensing-based multi-user detection for uplink grant-free NOMA[J]. IEEE Communications Letters, 2016, 20 (11): 2320- 2323
doi: 10.1109/LCOMM.2016.2602264
[13]   DU Y, DONG B, CHEN Z, et al Efficient multi-user detection for uplink grant-free NOMA: prior-information aided adaptive compressive sensing perspective[J]. IEEE Journal on Selected Areas in Communications, 2017, 35 (99): 2812- 2828
[14]   YE H, LI G Y, JUANG B Power of deep learning for channel estimation and signal detection in OFDM systems[J]. IEEE Wireless Communication Letters, 2017, 7 (1): 114- 117
[15]   GUAN G, HUANG H, SONG Y, et al Deep learning for an effective nonorthogonal multiple access scheme[J]. IEEE Transactions on Vehicular Technology, 2018, 67 (9): 8440- 8450
doi: 10.1109/TVT.2018.2848294
[16]   KIM W, AHN Y, SHIM B Deep neural network based active user detection for grant-free NOMA systems[J]. IEEE Transactions on Communications, 2019, 68 (4): 2143- 2155
[17]   MIAO X, GUO D, LI X Grant-free NOMA with device activity learning using long short-term memory[J]. IEEE Wireless Communication Letters, 2020, 9 (7): 981- 984
[18]   HOCHREITER S, SCHMIDHUBER J Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780
doi: 10.1162/neco.1997.9.8.1735
[19]   WANG J, KWON S, SHIM S Generalized orthogonal matching pursuit[J]. IEEE Transactions on Signal Processing, 2012, 60 (12): 6202- 6216
doi: 10.1109/TSP.2012.2218810
[20]   OYERINDE O O. Multiuser detector for uplink grant free NOMA systems based on modified subspace pursuit algorithm [C]// 2018 12th International Conference on Signal Processing and Communication Systems. [S. l. ]: IEEE, 2018: 1-6.
[21]   袁伟娜, 严秋 基于压缩感知的FBMC/OQAM系统信道估计方法[J]. 通信学报, 2019, 40 (12): 98- 104
YUAN Wei-na, YAN Qiu Channel estimation method based on compressive sensing for FBMC/OQAM system[J]. Journal on Communications, 2019, 40 (12): 98- 104
doi: 10.11959/j.issn.1000-436x.2019239
[1] Jia-hui XU,Jing-chang WANG,Ling CHEN,Yong WU. Surface water quality prediction model based on graph neural network[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(4): 601-607.
[2] Yi-zhe MAO,Guo-fang GONG,Xing-hai ZHOU,Fei WANG. Identification of TBM surrounding rock based on Markov process and deep neural network[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(3): 448-454.
[3] Shi-da CHEN,Qiang LIU,Liang HAN. Gradient sparsification compression approach to reducing communication in distributed training[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(2): 386-394.
[4] Wei-qi CHEN,Jing-chang WANG,Ling CHEN,Yong-qin YANG,Yong WU. Prediction model of multi-factor aware mobile terminal replacement based on deep neural network[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(1): 109-115.
[5] Jin-sheng JIANG,Hao-ran REN,Han-ye LI. Seismic data processing based on convolutional autoencoder[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(5): 978-984.
[6] Chang WANG,Yong-sheng ZHANG,Xu WANG,Ying YU. Remote sensing image change detection method based on deep neural networks[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(11): 2138-2148.