[1]常代娜,周杰.基于深度学习算法的OFDM信号检测[J].东南大学学报(自然科学版),2020,50(5):912-917.[doi:10.3969/j.issn.1001-0505.2020.05.017]
　Chang Daina,Zhou Jie.Deep learning-based signal detection in OFDM systems[J].Journal of Southeast University (Natural Science Edition),2020,50(5):912-917.[doi:10.3969/j.issn.1001-0505.2020.05.017]
点击复制

基于深度学习算法的OFDM信号检测()
分享到：

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
50
期数:
2020年第5期
页码:
912-917
栏目:
信息与通信工程
出版日期:
2020-09-20

文章信息/Info

Title:
Deep learning-based signal detection in OFDM systems
作者:
常代娜1; 周杰1; 2
1南京信息工程大学电子与信息工程学院, 南京 210044; 2新泻大学工学部电气电子工学科, 日本新泻 950-2181
Author(s):
Chang Daina1;  Zhou Jie1; 2
1School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
2Department of Electronic and Electrical Engineering, Niigata University, Niigata 950-2181, Japan
关键词:
深度学习;  信号检测;  正交频分复用(OFDM);  深度神经网络
Keywords:
deep learning;  signal detection;  orthogonal frequency division multiplexing(OFDM);  deep neural network
分类号:
TN929.5
DOI:
10.3969/j.issn.1001-0505.2020.05.017
摘要:
为了提高正交频分复用(OFDM)无线通信系统的信号检测能力,提出了一种基于深度学习(DL)算法的信号检测框架来代替系统信号检测模块.首先利用迫零(ZF)均衡器重构深度神经网络(DNN)的输入;然后在离线训练中增加预训练阶段,以导频符号和数据符号作为训练数据,为训练阶段提供良好的初始参数;最后在线信号检测通过加载离线训练获得的最优参数进行信号检测.实验结果表明:当信噪比(SNR)为25 dB时,无预训练阶段和无ZF均衡器的框架性能相对于完整的DL信号检测框架性能分别损失了2和4 dB;在导频符号数目减少和无循环前缀(CP)的情况下,DL框架的误码率相比传统方法均明显下降;在不同信道参数下,DL框架的性能损失比传统方法更小.ZF均衡器和预训练阶段均可提高DL框架性能,DL框架能更好地检测信号并具有较强的鲁棒性.
Abstract:
To improve the ability of signal detection in orthogonal frequency division multiplexing(OFDM)wireless communication systems, a deep learning(DL)-based signal detection frame was proposed to replace the signal detection module. First,the inputs of a deep neural network(DNN)were constructed by a zero force(ZF)equalizer. Then, the pre-training stage with the pilots and data signals as training data, was added in offline training to provide optimal initial parameters for the following training stage. Finally, the online signal detection was carried out by loading the optimal parameters obtained by offline training. The results show that when signal-to-noise ratio(SNR)is 25 dB, compared with the complete DL-based signal detection frame,the frame performance without pre-training stage and without ZF equalizer loses 2 and 4 dB, respectively. In the cases of the less pilots and the removal of cyclic prefix(CP), compared with the traditional method, the bit error rate of DL-based frame is significantly reduced. With different channel parameters, the performance loss of DL-based frame is smaller than that of the traditional method. Both the ZF equalizer and the pre-training stage can improve the performance of DL-based frame. The DL-based frame can better detect signals and has better robustness.

参考文献/References:

[1] Nachmani E, Be’Ery Y, Burshtein D. Learning to decode linear codes using deep learning[C]//2016 54th Annual Allerton Conference on Communication,Control,and Computing(Allerton). Monticello, IL, USA, 2016: 341-346. DOI:10.1109/allerton.2016.7852251.
[2] Gruber T, Cammerer S, Hoydis J, et al. On deep learning-based channel decoding[C]//2017 51st Annual Conference on Information Sciences and Systems(CISS). Baltimore, MD, USA, 2017: 1-6. DOI:10.1109/ciss.2017.7926071.
[3] Liang F, Shen C, Wu F. An iterative BP-CNN architecture for channel decoding[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12(1): 144-159. DOI:10.1109/jstsp.2018.2794062.
[4] Wang T Q, Wen C K, Jin S, et al. Deep learning-based CSI feedback approach for time-varying massive MIMO channels[J].IEEE Wireless Communications Letters, 2019, 8(2): 416-419. DOI:10.1109/lwc.2018.2874264.
[5] Wen C K, Shih W T, Jin S. Deep learning for massive MIMO CSI feedback[J]. IEEE Wireless Communications Letters, 2018, 7(5): 748-751. DOI: 10. 1109/LWC. 2018. 2818160.
[6] Soltani M, Pourahmadi V, Mirzaei A, et al. Deep learning-based channel estimation[J]. IEEE Communications Letters, 2019, 23(4): 652-655. DOI:10.1109/lcomm.2019.2898944.
[7] He H T, Wen C K, Jin S, et al. Deep learning-based channel estimation for beamspace mmWave massive MIMO systems[J]. IEEE Wireless Communications Letters, 2018, 7(5): 852-855. DOI:10.1109/lwc.2018.2832128.
[8] Yang Y W, Gao F F, Ma X L, et al. Deep learning-based channel estimation for doubly selective fading channels[J].IEEE Access, 2019, 7: 36579-36589. DOI:10.1109/access.2019.2901066.
[9] Huang H J, Yang J, Huang H, et al. Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system[J]. IEEE Transactions on Vehicular Technology, 2018, 67(9): 8549-8560. DOI:10.1109/tvt.2018.2851783.
[10] Baek M S, Kwak S, Jung J Y, et al. Implementation methodologies of deep learning-based signal detection for conventional MIMO transmitters[J]. IEEE Transactions on Broadcasting, 2019, 65(3): 636-642. DOI:10.1109/tbc.2019.2891051.
[11] Ye H, Li G Y, Juang B H. Power of deep learning for channel estimation and signal detection in OFDM systems[J]. IEEE Wireless Communications Letters, 2018, 7(1): 114-117. DOI:10.1109/lwc.2017.2757490.
[12] Samuel N, Diskin T, Wiesel A. Deep MIMO detection[C]// 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications(SPAWC). Sapporo, Japan, 2017: 1-5. DOI:10.1109/spawc.2017.8227772.
[13] Luong T V, Ko Y, Vien N A, et al. Deep learning-based detector for OFDM-IM[J]. IEEE Wireless Communications Letters, 2019, 8(4): 1159-1162. DOI:10.1109/lwc.2019.2909893.
[14] Chen Q, Zhang S, Xu S, et al. Efficient MIMO detection with imperfect channel knowledge-A deep learning approach [C]// 2019 IEEE Wireless Communications and Networking Conference(WCNC). Marrakesh, Morocco, 2019: 1-6. DOI:10.1109/WCNC.2019.8885582.

相似文献/References:

[1]程旭,周琳,张毅锋.基于多损失的生成式对抗目标跟踪算法[J].东南大学学报(自然科学版),2018,48(3):400.[doi:10.3969/j.issn.1001-0505.2018.03.004]
　Cheng Xu,Zhou Lin,Zhang Yifeng.Object tracking algorithm based on multiple loss generative adversary[J].Journal of Southeast University (Natural Science Edition),2018,48(5):400.[doi:10.3969/j.issn.1001-0505.2018.03.004]

备注/Memo

备注/Memo:
收稿日期: 2020-01-03.
作者简介: 常代娜(1995—),女,博士生;周杰(联系人),男,博士,教授,博士生导师,zhoujie45@hotmail.com.
基金项目: 国家自然科学基金面上资助项目(61771248,61971167).
引用本文: 常代娜,周杰.基于深度学习算法的OFDM信号检测[J].东南大学学报(自然科学版),2020,50(5):912-917. DOI:10.3969/j.issn.1001-0505.2020.05.017.
更新日期/Last Update: 2020-09-20