留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于Bi-LSTM及贝叶斯似然比检验的GEO与LEO卫星组合频谱感知

杨凯 胡圣波 张欣

杨凯, 胡圣波, 张欣. 基于Bi-LSTM及贝叶斯似然比检验的GEO与LEO卫星组合频谱感知[J]. 空间科学学报, 2023, 43(3): 567-575. doi: 10.11728/cjss2023.03.2022-0017
引用本文: 杨凯, 胡圣波, 张欣. 基于Bi-LSTM及贝叶斯似然比检验的GEO与LEO卫星组合频谱感知[J]. 空间科学学报, 2023, 43(3): 567-575. doi: 10.11728/cjss2023.03.2022-0017
YANG Kai, HU Shengbo, ZHANG Xin. Spectrum Sensing for Combined GEO and LEO Satellites Based on Bi-LSTM and Bayesian Likelihood Ratio Test (in Chinese). Chinese Journal of Space Science, 2023, 43(3): 567-575 doi: 10.11728/cjss2023.03.2022-0017
Citation: YANG Kai, HU Shengbo, ZHANG Xin. Spectrum Sensing for Combined GEO and LEO Satellites Based on Bi-LSTM and Bayesian Likelihood Ratio Test (in Chinese). Chinese Journal of Space Science, 2023, 43(3): 567-575 doi: 10.11728/cjss2023.03.2022-0017

基于Bi-LSTM及贝叶斯似然比检验的GEO与LEO卫星组合频谱感知

doi: 10.11728/cjss2023.03.2022-0017
基金项目: 国家自然科学基金项目(61561009)和贵州省教育厅项目(KY [2017]031, KY [2020]007)共同资助
详细信息
    作者简介:

    胡圣波:E-mail:hsb@nssc.ac.cn

  • 中图分类号: TN927

Spectrum Sensing for Combined GEO and LEO Satellites Based on Bi-LSTM and Bayesian Likelihood Ratio Test

  • 摘要: 目前的频谱感知算法以模型驱动为主,其感知性能过于依赖预定的统计模型,这使得其在信道环境复杂的卫星通信场景中的部署变得困难。对LEO卫星过境期间的信噪比波动情况进行分析,结果显示信噪比的波动达到14 dB。针对该复杂场景提出了一种基于双向长短期记忆网络及贝叶斯似然比检验联合的频谱感知算法。该算法不需要任何主信号的先验知识,可自动从主信号中学习隐藏特征并做出决策。基于Neyman-Pearson准则,在神经网络输出端设计了一种基于阈值的检测方案,可方便地控制恒定的虚警概率。仿真结果表明,所提算法在信噪比为–14 dB的情况下,仍能达到83%的检测性能,且始终优于卷积神经网络、多层感知机和基于模型驱动的能量检测算法。

     

  • 图  1  认知卫星通信场景及所提的频谱感知模型

    Figure  1.  Scenario of cognitive satellite communications and the proposed spectrum sensing model

    图  2  信噪比随仰角$ \alpha $波动曲线

    Figure  2.  Curve of SNR fluctuation with elevation $ \alpha $

    图  3  Bi-LSTM神经网络架构

    Figure  3.  Architecture of Bi-LSTM neural network

    图  4  基于Bi-LSTM及贝叶斯似然比检验联合的频谱感知算法流程

    Figure  4.  Flow diagram of the spectrum sensing algorithm based on Bi-LSTM and Bayesian likelihood ratio test

    图  5  不同全连接层数下$ {P_{\text{D}}} $随信噪比变化曲线

    Figure  5.  $ {P_{\text{D}}} $ versus SNR with different number of FC layers

    图  6  不同训练样本数下$ {P_{\text{D}}} $随信噪比的变化曲线

    Figure  6.  $ {P_{\text{D}}} $ versus SNR curves with different numbers of training samples

    图  7  不同调制方式下$ {P_{\text{D}}} $随信噪比的变化曲线

    Figure  7.  $ {P_{\text{D}}} $ versus SNR curves with different modulation types

    图  8  信噪比为–14 dB情况下的ROC曲线

    Figure  8.  ROC curves with SNR=–14 dB

    图  9  不同频谱感知算法下PD随信噪比的变化曲线

    Figure  9.  PD versus SNR with different SS algorithms

    图  10  LEO卫星过境期间${P_{\rm D}}$ 的变化曲线

    Figure  10.  Change curves of ${P_{\rm D}}$ during the transit of LEO satellites

    表  1  仿真参数

    Table  1.   Simulation parameters

    参数名
    调制类型 GMSK
    GES发送功率$ P_{{\text{ges}}}^{\text{t}} $/dBm 40
    LEO接收机噪声温度$ {T_{{\text{leo}}}} $/K 175
    GES发送天线增益$ G_{{\text{ges}}}^{\text{t}} $/dB 30
    LEO接收天线增益$ G_{{\text{leo}}}^{\text{r}} $/dB 10
    工作频率$ f $/GHz 29.9
    带宽$ B $/MHz 24
    大气吸收传播因子$ {A_{\text{g}}} $/dB 0.75
    云雾衰减传播因子$ {A_{\text{c}}} $/dB 1.25
    训练轮数 20
    损失函数 Cross entropy loss
    优化器 Adam
    训练集样本数 32000
    验证集样本数 3200
    测试集样本数 8000
    下载: 导出CSV
  • [1] YOU X H, WANG C X, HUANG J, et al. Towards 6 G wireless communication networks: vision, enabling technologies, and new paradigm shifts[J]. Science China Information Sciences, 2021, 64(1): 110301 doi: 10.1007/s11432-020-2955-6
    [2] LIU R, ZHU S B, LI C Q. Review of cognitive satellite communication technology[C]//2020 IEEE 9 th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). Chongqing: IEEE, 2020: 1378-1385
    [3] LIU C, LIU X M, LIANG Y C. Deep CNN for spectrum sensing in cognitive radio[C]//ICC 2019 - 2019 IEEE International Conference on Communications (ICC). Shanghai: IEEE, 2019: 1-6
    [4] NI T, DING X J, WANG Y F, et al. Spectrum sensing via temporal convolutional network[J]. China Communications, 2021, 18(9): 37-47 doi: 10.23919/JCC.2021.09.004
    [5] TIAN J J, PEI Y Y, HUANG Y D, et al. Modulation-constrained clustering approach to blind modulation classification for MIMO systems[J]. IEEE Transactions on Cognitive Communications and Networking, 2018, 4(4): 894-907 doi: 10.1109/TCCN.2018.2879370
    [6] JIANG C X, ZHANG H J, REN Y, et al. Machine learning paradigms for next-generation wireless networks[J]. IEEE Wireless Communications, 2017, 24(2): 98-105 doi: 10.1109/MWC.2016.1500356WC
    [7] CLANCY C, HECKER J, STUNTEBECK E, et al. Applications of machine learning to cognitive radio networks[J]. IEEE Wireless Communications, 2007, 14(4): 47-52 doi: 10.1109/MWC.2007.4300983
    [8] HAN D, SOBABE G C, ZHANG C J, et al. Spectrum sensing for cognitive radio based on convolution neural network[C]//2017 10 th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). Shanghai: IEEE, 2017: 1-6
    [9] THILINA K M, CHOI K W, SAQUIB N, et al. Machine learning techniques for cooperative spectrum sensing in cognitive radio networks[J]. IEEE Journal on Selected Areas in Communications, 2013, 31(11): 2209-2221 doi: 10.1109/JSAC.2013.131120
    [10] TANG Y J, ZHANG Q Y, LIN W. Artificial neural network based spectrum sensing method for cognitive radio[C]//2010 6 th International Conference on Wireless Communications Networking and Mobile Computing (WiCOM). Chengdu: IEEE, 2010: 1-4
    [11] ZHANG M, DIAO M, GUO L M. Convolutional neural networks for automatic cognitive radio waveform recognition[J]. IEEE Access, 2017, 5: 11074-11082 doi: 10.1109/ACCESS.2017.2716191
    [12] WANG J, TANG J, XU Z Y, et al. Spatiotemporal modeling and prediction in cellular networks: a big data enabled deep learning approach[C]//IEEE INFOCOM 2017 - IEEE Conference on Computer Communications. Atlanta: IEEE, 2017: 1-9
    [13] SHAWEL B S, WOLDEGEBREAL D H, POLLIN S. Convolutional LSTM-based long-term spectrum prediction for dynamic spectrum access[C]//2019 27 th European Signal Processing Conference (EUSIPCO). A Coruna: IEEE, 2019: 1-5
    [14] WU T. CNN and RNN-based deep learning methods for digital signal demodulation[C]//Proceedings of the 2019 International Conference on Image, Video and Signal Processing. Shanghai: Association for Computing Machinery, 2019: 122-127
    [15] XIE J D, FANG J, LIU C, et al. Deep learning-based spectrum sensing in cognitive radio: a CNN-LSTM approach[J]. IEEE Communications Letters, 2020, 24(10): 2196-2200 doi: 10.1109/LCOMM.2020.3002073
    [16] GIUFFRIDA G, DIANA L, DE GIOIA F, et al. CloudScout: a deep neural network for on-board cloud detection on hyperspectral images[J]. Remote Sensing, 2020, 12(14): 2205 doi: 10.3390/rs12142205
    [17] LI F L, LI Z Q, LI G X, et al. Efficient wideband spectrum sensing with maximal spectral efficiency for LEO mobile satellite systems[J]. Sensors, 2017, 17(1): 193
    [18] ZHANG C, JIANG C X, JIN J, et al. Spectrum sensing and recognition in satellite systems[J]. IEEE Transactions on Vehicular Technology, 2019, 68(3): 2502-2516 doi: 10.1109/TVT.2019.2893388
    [19] SENGIJPTA S K. Fundamentals of statistical signal processing: estimation theory[J]. Technometrics, 1995, 37(4): 465-466
    [20] ZHENG S L, CHEN S C, QI P H, et al. Spectrum sensing based on deep learning classification for cognitive radios[J]. China Communications, 2020, 17(2): 138-148 doi: 10.23919/JCC.2020.02.012
    [21] SAEED N, ELZANATY A, ALMORAD H, et al. CubeSat communications: recent advances and future challenges[J]. IEEE Communications Surveys & Tutorials, 2020, 22(3): 1839-1862
    [22] O’SHEA T J, WEST N. Radio machine learning dataset generation with GNU radio[C]//Proceedings of the 6 th GNU Radio Conference. Boulder: GRCon, 2016
  • 加载中
图(10) / 表(1)
计量
  • 文章访问数:  339
  • HTML全文浏览量:  153
  • PDF下载量:  128
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-05-05
  • 修回日期:  2022-11-29
  • 网络出版日期:  2022-12-10

目录

    /

    返回文章
    返回