基于低复杂度加法网络的非正交多址接入短报文多用户检测算法研究

王骥; 李子龙; 肖健; 李涣哲; 谢文武; 余超

doi:10.11999/JEIT231186

基于低复杂度加法网络的非正交多址接入短报文多用户检测算法研究

doi: 10.11999/JEIT231186

王骥¹,
李子龙²,
肖健¹,
李涣哲²,
谢文武^2, ,,
余超²

1.
华中师范大学物理科学与技术学院湖北武汉 430079
2.
湖南理工学院信息科学与工程学院湖南岳阳 414006

基金项目: 国家自然科学基金(62101205, 62372070)，湖北省重点研发计划(2023BAB061)，湖南省研究性创新项目(QL20230275, CX20231220)，湖南省自然科学基金(2023JJ50045)，湖南省大学生创新创业项目(S202310543040)

详细信息

作者简介:
王骥：男，副教授，研究方向为5G/6G无线通信

李子龙：男，硕士生，研究方向为深度强化学习

肖健：男，博士生，研究方向为AI、信号处理

谢文武：男，副教授，研究方向为5G&6G基带算法、NFC等

余超：男，讲师，研究方向为NOMA、凸优化

通讯作者:
谢文武　gavinxie@hnist.edu.cn

中图分类号: TN911
计量
- 文章访问数: 202
- HTML全文浏览量: 70
- PDF下载量: 27
- 被引次数: 0
出版历程
- 收稿日期: 2023-10-31
- 修回日期: 2024-03-15
- 网络出版日期: 2024-04-01
- 刊出日期: 2024-06-30

Research on Multi-User Detection Algorithm for Non-Orthogonal Multiple Access Short Message Based on Low Complexity Adder Network

1.
College of Physical Science and Technology, Central China Normal University, Wuhan 430079, China
2.
School of Information Science and Engineering, Hunan Institute of Science and Technology, Yueyang 414006, China

Funds: The National Natural Science Foundation of China (62101205, 62372070), The Key Research and Development Program of Hubei Province (2023BAB061), The Research and Innovation Projects in HunanProvince (QL20230275, CX20231220), Hunan Provincial Natural Science Foundation (2023JJ50045), Hunan Provincial College Students’ Innovation and Entrepreneurship Projects (S202310543040)

摘要

摘要: 针对非正交多址接入(NOMA)系统中，接收机使用串行干扰删除算法译码时需要已知干扰用户的调制方式而产生额外的信令开销问题，该文提出一种基于联合星座轨迹图和深度学习的NOMA短包传输干扰用户调制方式盲检测算法。考虑在通信设备部署神经网络时存在计算复杂度高和能量消耗大等不足，将原始卷积神经网络替换为深度加法网络，在调制检测准确率，计算延迟和能耗等方面进行了充分比较，使用时域过采样技术改善低信噪比下的识别率。最后分析并验证了功率分配，数据包长度对检测性能的影响。
- 非正交多址接入 /
- 调制检测 /
- 深度加法网络 /
- 过采样
Abstract: A joint constellation trace diagram and deep learning-based blind modulation detection scheme is proposed for Non-Orthogonal Multiple Access (NOMA) systems, which can avoid the required expensive signaling overhead in successive interference cancellation algorithms, especially for NOMA-based short packet transmission. Considering the high computational complexity and energy consumption for communication equipment in the deployment of neural network, the original convolutional network is replaced by the adder network. The modulation detection accuracy, computing delay and energy consumption are fully compared for two kinds of network architectures. Meanwhile, time-domain oversampling technology is used to improve the recognition rate under low signal-to-noise ratio. Finally, the influence of power allocation and data packet length on detection performance is analyzed and verified.
- Non-Orthogonal Multiple Access (NOMA) /
- Modulation detection /
- Deep adder network /
- Oversampling

HTML全文

图 1 两用户NOMA下行链路

下载: 全尺寸图片幻灯片

图 2 UN=16QAM, UF=QPSK, $ {\alpha _{{\text{ftpc}}}} = 0.5 $时联合星座图

下载: 全尺寸图片幻灯片

图 3 UN=16QAM, UF=QPSK, $ {\alpha _{{\text{ftpc}}}} = 0.5 $, D-SNR=6 dB时联合星座轨迹图

下载: 全尺寸图片幻灯片

图 4 ${\alpha _{{\text{ftpc}}}} = 0.5$, D-SNR=6 dB时联合星座直方统计图

下载: 全尺寸图片幻灯片

图 5 调制检测网络结构

下载: 全尺寸图片幻灯片

图 6 ConvNet与AdderNet的调制识别率比较

下载: 全尺寸图片幻灯片

图 7 UN=16QAM，不同数据包长度与功率分配下调制识别率比较

下载: 全尺寸图片幻灯片

表 1 NOMA系统仿真参数

参数名	参数值
数据包符号数	100
功率衰减因子	0.5
成型滤波器	平方根升余弦
滚降系数	0.5
信道衰落	瑞利分布
多径数	3
多普勒频移	20 Hz
多普勒频谱	Jakes
目标用户	16QAM/64QAM
干扰用户	None/QPSK/16QAM/64QAM

下载: 导出CSV

表 2 AdderNet与ConvNet性能指标

网络	加法次数	乘法次数	指令延迟	能耗(pJ)	参数量
AdderNet	32.6 M	0	65.2 M	29.34 M	7.2 k
ConvNet	16.3 M	16.3 M	97.8 M	74.98 M	7.2 k

下载: 导出CSV

参考文献(29)

[1]	ELGARHY O, REGGIANI L, ALAM M M, et al. Energy efficiency and latency optimization for IoT URLLC and mMTC use cases[J]. IEEE Access, 2024, 12: 23132–23148. doi: 10.1109/ACCESS.2024.3364349.
[2]	SHAHAB M B, ABBAS R, SHIRVANIMOGHADDAM M, et al. Grant-free non-orthogonal multiple access for IoT: A survey[J]. IEEE Communications Surveys & Tutorials, 2020, 22(3): 1805–1838. doi: 10.1109/COMST.2020.2996032.
[3]	SONG Ge, FANG Xiaojie, and SHA Xuejun. The extended hybrid carrier-based multiple access technology for high mobility scenarios[J]. China Communications, 2024, 21(1): 53–68. doi: 10.23919/JCC.fa.2023-0352.202401.
[4]	张宏莉, 韩玲, 王星妍. 5G非正交多址关键技术研究和性能评估[J]. 信息通信技术与政策, 2022, 49(6): 85–90. doi: 10.12267/j.issn.2096-5931.2022.06.015. ZHANG Hongli, HAN Ling, and WANG Xingyan. Study on 5G non-orthogonal multiple access technology & performance evaluation[J]. Information and Communications Technology and Policy, 2022, 49(6): 85–90. doi: 10.12267/j.issn.2096-5931.2022.06.015.
[5]	DING Zhiguo, LEI Xianfu, KARAGIANNIDIS G K, et al. A survey on non-orthogonal multiple access for 5G networks: Research challenges and future trends[J]. IEEE Journal on Selected Areas in Communications, 2017, 35(10): 2181–2195. doi: 10.1109/JSAC.2017.2725519.
[6]	DAI Linglong, WANG Bichai, YUAN Yifei, et al. Non-orthogonal multiple access for 5G: Solutions, challenges, opportunities, and future research trends[J]. IEEE Communications Magazine, 2015, 53(9): 74–81. doi: 10.1109/MCOM.2015.7263349.
[7]	SAITO Y, KISHIYAMA Y, BENJEBBOUR A, et al. Non-Orthogonal Multiple Access (NOMA) for cellular future radio access[C]. 2013 IEEE 77th Vehicular Technology Conference (VTC Spring), Dresden, Germany, 2013: 1–5. doi: 10.1109/VTCSpring.2013.6692652.
[8]	MALI M D and CHORAGE S S. Spectrally efficient Multiple Input Multiple Output (MIMO) Non-Orthogonal Multiple Access (NOMA) technique for future wireless communication[C]. 2022 2nd Asian Conference on Innovation in Technology (ASIANCON), Ravet, India, 2022: 1–5. doi: 10.1109/ASIANCON55314.2022.9908664.
[9]	蔡昕. 单通道时频混叠数字通信信号盲分离方法研究[D]. [博士论文], 国防科技大学, 2021. doi: 10.27052/d.cnki.gzjgu.2021.000088. CAI Xin. Researches on blind separation of single channel time-frequency overlapped digital communication signals[D]. [Ph. D. dissertation], National University of Defense Technology, 2021. doi: 10.27052/d.cnki.gzjgu.2021.000088.
[10]	WEI Wen and MENDEL J M. Maximum-likelihood classification for digital amplitude-phase modulations[J]. IEEE Transactions on Communications, 2000, 48(2): 189–193. doi: 10.1109/26.823550.
[11]	CHOI M, YOON D, and KIM J. Blind signal classification for non-orthogonal multiple access in vehicular networks[J]. IEEE Transactions on Vehicular Technology, 2019, 68(10): 9722–9734. doi: 10.1109/TVT.2019.2932407.
[12]	LI Tao, LI Yongzhao, and DOBRE O A. Modulation classification based on fourth-order Cumulants of superposed signal in NOMA systems[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 2885–2897. doi: 10.1109/TIFS.2021.3068006.
[13]	ZHANG Ningbo, CHENG Kai, and KANG Guixia. A machine-learning-based blind detection on interference modulation order in NOMA systems[J]. IEEE Communications Letters, 2018, 22(12): 2463–2466. doi: 10.1109/LCOMM.2018.2874218.
[14]	LASELVA S. 人工智能在5G和6G网络中的应用[J]. 软件和集成电路, 2023(6): 8–9. doi: 10.19609/j.cnki.cn10-1339/tn.2023.06.022. LASELVA S. The application of artificial intelligence in 5G and 6G networks[J]. Software and Integrated Circuit, 2023(6): 8–9. doi: 10.19609/j.cnki.cn10-1339/tn.2023.06.022.
[15]	O’SHEA T J, ROY T, and CLANCY T C. Over-the-air deep learning based radio signal classification[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12(1): 168–179. doi: 10.1109/JSTSP.2018.2797022.
[16]	HOU Changbo, LIU Guowei, TIAN Qiao, et al. Multisignal modulation classification using sliding window detection and complex convolutional network in frequency domain[J]. IEEE Internet of Things Journal, 2022, 9(19): 19438–19449. doi: 10.1109/JIOT.2022.3167107.
[17]	张思成, 林云, 涂涯, 等. 基于轻量级深度神经网络的电磁信号调制识别技术[J]. 通信学报, 2020, 41(11): 12–21. doi: 10.11959/j.issn.1000-436x.2020237. ZHANG Sicheng, LIN Yun, TU Ya, et al. Electromagnetic signal modulation recognition technology based on lightweight deep neural network[J]. Journal on Communications, 2020, 41(11): 12–21. doi: 10.11959/j.issn.1000-436x.2020237.
[18]	STRUBELL E, GANESH A, and MCCALLUM A. Energy and policy considerations for deep learning in NLP[C]. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 2019: 3645–3650. doi: 10.18653/v1/P19-1355.
[19]	CHEN Hanting, WANG Yunhe, XU Chunjing, et al. AdderNet: Do we really need multiplications in deep learning?[C]. The IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020: 1465–1474. doi: 10.1109/CVPR42600.2020.00154.
[20]	王建新, 宋辉. 基于星座图的数字调制方式识别[J]. 通信学报, 2004, 25(6): 166–173. doi: 10.3321/j.issn:1000-436X.2004.06.023. WANG Jianxin and SONG Hui. Digital modulation recognition based on constellation diagram[J]. Journal on Communications, 2004, 25(6): 166–173. doi: 10.3321/j.issn:1000-436X.2004.06.023.
[21]	SHAFIQ M and GU Zhaoquan. Deep residual learning for image recognition: A survey[J]. Applied Sciences, 2022, 12(18): 8972. doi: 10.3390/app12188972.
[22]	OTAO N, KISHIYAMA Y, and HIGUCHI K. Performance of non-orthogonal access with SIC in cellular downlink using proportional fair-based resource allocation[C]. 2012 International Symposium on Wireless Communication Systems (ISWCS), Paris, France, 2012: 476–480. doi: 10.1109/ISWCS.2012.6328413.
[23]	崔荣涛, 李辉, 万坚, 等. 一种基于过采样的单通道MPSK信号盲分离算法[J]. 电子与信息学报, 2009, 31(3): 566–569. doi: 10.3724/SP.J.1146.2007.01792. CUI Rongtao, LI Hui, WAN Jian, et al. An over-sampling based blind separation algorithm of single channel MPSK signals[J]. Journal of Electronics & Information Technology, 2009, 31(3): 566–569. doi: 10.3724/SP.J.1146.2007.01792.
[24]	PENG Linning, ZHANG Junqing, LIU Ming, et al. Deep learning based RF fingerprint identification using differential constellation trace figure[J]. IEEE Transactions on Vehicular Technology, 2020, 69(1): 1091–1095. doi: 10.1109/TVT.2019.2950670.
[25]	IOFFE S and SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]. The 32nd International Conference on Machine Learning, Lille, France, 2015: 448–456. doi: 10.5555/3045118.3045167.
[26]	LOSHCHILOV I and HUTTER F. SGDR: Stochastic gradient descent with warm restarts[C]. 5th International Conference on Learning Representations, Toulon, France, 2017. doi: 10.48550/arXiv.1608.03983.
[27]	HOROWITZ M. 1.1 Computing's energy problem (and what we can do about it)[C]. 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), San Francisco, USA, 2014: 10–14. doi: 10.1109/ISSCC.2014.6757323.
[28]	施建锋, 杨照辉, 黄诺, 等. 面向6G的用户为中心网络研究综述[J]. 电子与信息学报, 2023, 45(5): 1873–1887. doi: 10.11999/ JEIT220242. SHI Jianfeng, YANG Zhaohui, HUANG Nuo, et al. A survey on user-centric networks for 6G[J]. Journal of Electronics & Information Technology, 2023, 45(5): 1873–1887. doi: 10.11999/JEIT220242.
[29]	张海君, 陈安琪, 李亚博, 等. 6G移动网络关键技术[J]. 通信学报, 2022, 43(7): 189–202. doi: 10.11959/j.issn.1000-436x.2022140. ZHANG Haijun, CHEN Anqi, LI Yabo, et al. Key technologies of 6G mobile network[J]. Journal on Communications, 2022, 43(7): 189–202. doi: 10.11959/j.issn.1000-436x.2022140.