高级搜索

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

基于元学习算法的IRS-OTFS通信系统信道估计

张祖凡 段佳慧 王国仲

张祖凡, 段佳慧, 王国仲. 基于元学习算法的IRS-OTFS通信系统信道估计[J]. 电子与信息学报. doi: 10.11999/JEIT230669
引用本文: 张祖凡, 段佳慧, 王国仲. 基于元学习算法的IRS-OTFS通信系统信道估计[J]. 电子与信息学报. doi: 10.11999/JEIT230669
ZHANG Zufan, DUAN Jiahui, WANG Guozhong. Channel Estimation of IRS-OTFS Communication System Based on Meta-learning Algorithm[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT230669
Citation: ZHANG Zufan, DUAN Jiahui, WANG Guozhong. Channel Estimation of IRS-OTFS Communication System Based on Meta-learning Algorithm[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT230669

基于元学习算法的IRS-OTFS通信系统信道估计

doi: 10.11999/JEIT230669
基金项目: 国家自然科学基金(62202077),重庆市教育委员会科学技术研究计划重大项目(KJZD-M201900601)
详细信息
    作者简介:

    张祖凡:男,教授,研究方向为无线通信、移动社交网络、机器学习等

    段佳慧:女,硕士生,研究方向为无线通信、智能反射表面等

    王国仲:男,博士生,研究方向为无线通信、智能反射表面等

    通讯作者:

    段佳慧 929027253@qq.com

  • 中图分类号: TN929.5

Channel Estimation of IRS-OTFS Communication System Based on Meta-learning Algorithm

Funds: The National Natural Science Foundation of China (62202077), The Major Project of Science and Technology Research Program of Chongqing Education Commission of China (KJZD-M201900601)
  • 摘要: 针对高多普勒场景下智能反射表面(IRS)辅助多用户通信系统存在的信道估计传输开销大的问题,该文结合正交时频空间(OTFS)调制特点构造一种IRS-OTFS通信系统,充分发挥IRS和OTFS的性能优势,并在此基础上提出一种学习率自适应的模型无关元学习(MAML)算法。对IRS-OTFS多用户信道估计任务做离线训练,根据各任务的收敛速度自适应地调整学习率,防止训练失衡,并利用信道之间的相关性和MAML算法的少样本、泛化特性得到全局模型和适应性模型,快速学习新用户信道的传输特性,降低传输开销,提高信道估计准确性。理论分析和仿真结果表明,该算法在信道传输条件相同的情况下,将传输开销降低了大约50%,并相对于基准算法有4.8dB左右的性能提升。
  • 图  1  系统模型

    图  2  OTFS系统调制过程图

    图  3  OTFS收发端符号图案

    图  4  基于MAML算法的IRS辅助多用户系统信道估计框架

    图  5  本文算法在不同SNR下的NMSE

    图  6  不同信噪比和算法下的NMSE

    图  7  不同训练用户数下本文算法的NMSE

    图  8  不同信道估计算法的NMSE

    图  9  不同信道估计算法的WSR

    1  学习率自适应的MAML算法信道估计步骤

     输入:多用户训练任务集(包括支持集$ {\boldsymbol{D}}_k^{{\mathrm{sup}}} $和查询集$ {\boldsymbol{D}}_k^{{\mathrm{que}}} $),
     $ {{\boldsymbol{D}}^{{\mathrm{sup}}}} = {\left\{ {{\boldsymbol{D}}_k^{{\mathrm{sup}}}} \right\}_{k = 1,2, \cdots ,K}} $, $ {{\boldsymbol{D}}^{{\mathrm{que}}}} = {\left\{ {{\boldsymbol{D}}_k^{{\mathrm{que}}}} \right\}_{k = 1,2, \cdots ,K}} $;目标
     用户数据集$ {{\boldsymbol{D}}^T} $,学习率参数$ \alpha (0) $,$ \beta $,$ \gamma $
     元训练阶段:
     1: for 迭代轮次$ t $ do
     2:  for 每个信道估计任务$ k $ do
     3:   根据式(19)更新当前训练任务的内循环学习率$ {\alpha _k}(t) $
     4:   根据式(21)更新当前用户信道估计任务的适应性参数
        $ {\varphi _k}(t) $
     5:  end for
     6:  根据式(22)更新得到全局模型参数$ {\theta ^*} $
     7: end for
     针对新用户信道任务的微调阶段:
     8: 初始化目标任务的模型参数为$ {\theta ^*} $
     9: for 微调次数 do
     10:   根据式(23)更新新用户的模型参数$ {\varphi _T} $
     11:end for
     输出:全局模型参数$ {\theta ^*} $;目标用户的适应性模型参数$ {\varphi _T} $
    下载: 导出CSV

    表  1  仿真参数表

    参数
    载波频率(GHz)28
    BS端天线数32
    IRS无源反射元件数32
    批大小20
    内优化学习率$ {10^{ - 3}} $
    外优化学习率$ {10^{ - 4}} $
    卷积层数目16
    下载: 导出CSV

    表  2  卷积层参数设置表

    层数 $ {C^{(l)}} $ $ N_{{\mathrm{SF}}}^{(l)} $ $ W_x^{(l)} $ $ W_y^{(l)} $
    conv1,onv9 2 32 3 3
    conv2~conv7 32 32 3 3
    conv10~conv15 32 32 3 3
    conv8, onv16 32 2 3 3
    下载: 导出CSV
  • [1] HAN Yu, TANG Wankai, JIN Shi, et al. Large intelligent surface-assisted wireless communication exploiting statistical CSI[J]. IEEE Transactions on Vehicular Technology, 2019, 68(8): 8238–8242. doi: 10.1109/TVT.2019.2923997
    [2] HUANG Chongwen, ZAPPONE A, ALEXANDROPOULOS G C, et al. Reconfigurable intelligent surfaces for energy efficiency in wireless communication[J]. IEEE Transactions on Wireless Communications, 2019, 18(8): 4157–4170. doi: 10.1109/TWC.2019.2922609
    [3] WU Qingqing, ZHANG Shuowen, ZHENG Beixiong, et al. Intelligent reflecting surface-aided wireless communications: A tutorial[J]. IEEE Transactions on Communications, 2021, 69(5): 3313–3351. doi: 10.1109/TCOMM.2021.3051897
    [4] NIU Hehao, LIN Zhi, AN Kang, et al. Active RIS assisted rate-splitting multiple access network: Spectral and energy efficiency tradeoff[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(5): 1452–1467. doi: 10.1109/JSAC.2023.3240718
    [5] LIN Zhi, NIU Hehao, AN Kang, et al. Refracting RIS-aided hybrid satellite-terrestrial relay networks: Joint beamforming design and optimization[J]. IEEE Transactions on Aerospace and Electronic Systems, 2022, 58(4): 3717–3724. doi: 10.1109/TAES.2022.3155711
    [6] ASIF M, IHSAN A, KHAN W U, et al. Energy-efficient beamforming and resource optimization for STAR-IRS enabled hybrid-NOMA 6G communications[J]. IEEE Transactions on Green Communications and Networking, 2023, 7(3): 1356–1368. doi: 10.1109/TGCN.2023.3281414
    [7] WANG Peilan, FANG Jun, YUAN Xiaojun, et al. Intelligent reflecting surface-assisted millimeter wave communications: Joint active and passive precoding design[J]. IEEE Transactions on Vehicular Technology, 2020, 69(12): 14960–14973. doi: 10.1109/TVT.2020.3031657
    [8] CAO Yashuai, LV Tiejun, and NI Wei. Intelligent reflecting surface aided multi-user mmWave communications for coverage enhancement[C]. IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications, London, UK, 2020: 1–6.
    [9] WANG Yong, LIN Zhi, NIU Hehao, et al. Secure satellite transmission with active reconfigurable intelligent surface[J]. IEEE Communications Letters, 2022, 26(12): 3029–3033. doi: 10.1109/LCOMM.2022.3207190
    [10] HADANI R, RAKIB S, TSATSANIS M, et al. Orthogonal time frequency space modulation[C]. IEEE Wireless Communications and Networking Conference (WCNC), San Francisco, USA, 2017: 1–6.
    [11] HADANI R, RAKIB S, MOLISCH A F, et al. Orthogonal time frequency space (OTFS) modulation for millimeter-wave communications systems[C]. IEEE MTT-S International Microwave Symposium (IMS), Honololu, USA, 2017: 681–683.
    [12] THOMAS A, DEKA K, SHARMA S, et al. IRS-assisted OTFS system: Design and analysis[J]. IEEE Transactions on Vehicular Technology, 2023, 72(3): 3345–3358. doi: 10.1109/TVT.2022.3217140
    [13] 蒋占军, 刘庆达. 高速移动通信系统中OTFS信道估计算法研究[J]. 电子与信息学报, 2021, 43(10): 2878–2885. doi: 10.11999/JEIT200683

    JIANG Zhanjun and LIU Qingda. Study on OTFS channel estimation algorithms in high-speed mobile communication systems[J]. Journal of Electronics & Information Technology, 2021, 43(10): 2878–2885. doi: 10.11999/JEIT200683
    [14] RAVITEJA P, HONG Yi, VITERBO E, et al. Practical pulse-shaping waveforms for reduced-cyclic-prefix OTFS[J]. IEEE Transactions on Vehicular Technology, 2019, 68(1): 957–961. doi: 10.1109/TVT.2018.2878891
    [15] GUNTURU A, GODALA A R, SAHOO A K, et al. Performance analysis of OTFS waveform for 5G NR mmWave communication system[C]. IEEE Wireless Communications and Networking Conference (WCNC), Nanjing, China, 2021: 1–6.
    [16] WANG Zhaorui, LIU Liang, and CUI Shuguang. Channel estimation for intelligent reflecting surface assisted multiuser communications: Framework, algorithms, and analysis[J]. IEEE Transactions on Wireless Communications, 2020, 19(10): 6607–6620. doi: 10.1109/TWC.2020.3004330
    [17] LIU Chang, LIU Xuemeng, NG D W K, et al. Deep residual learning for channel estimation in intelligent reflecting surface-assisted multi-user communications[J]. IEEE Transactions on Wireless Communications, 2022, 21(2): 898–912. doi: 10.1109/TWC.2021.3100148
    [18] ELBIR A M and COLERI S. Federated learning for channel estimation in conventional and RIS-assisted massive MIMO[J]. IEEE Transactions on Wireless Communications, 2022, 21(6): 4255–4268. doi: 10.1109/TWC.2021.3128392
    [19] SINGH G, SRIVASTAVA A, and BOHARA V A. Visible light and reconfigurable intelligent surfaces for beyond 5G V2X communication networks at road intersections[J]. IEEE Transactions on Vehicular Technology, 2022, 71(8): 8137–8151. doi: 10.1109/TVT.2022.3174131
    [20] MISHRA H B, SINGH P, PRASAD A K, et al. OTFS channel estimation and data detection designs with superimposed pilots[J]. IEEE Transactions on Wireless Communications, 2022, 21(4): 2258–2274. doi: 10.1109/TWC.2021.3110659
    [21] RAVITEJA P, PHAN K T, and HONG Yi. Embedded pilot-aided channel estimation for OTFS in delay-Doppler channels[J]. IEEE Transactions on Vehicular Technology, 2019, 68(5): 4906–4917. doi: 10.1109/TVT.2019.2906357
    [22] BAIK S, OH J, HONG S, et al. Learning to forget for meta-learning via task-and-layer-wise attenuation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(11): 7718–7730. doi: 10.1109/TPAMI.2021.3102098
    [23] LIU Shikun, JOHNS E, and DAVISON A J. End-to-end multi-task learning with attention[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019: 1871–1880.
    [24] PAN Cunhua, REN Hong, WANG Kezhi, et al. Multicell MIMO communications relying on intelligent reflecting surfaces[J]. IEEE Transactions on Wireless Communications, 2020, 19(8): 5218–5233. doi: 10.1109/TWC.2020.2990766
  • 加载中
图(9) / 表(3)
计量
  • 文章访问数:  154
  • HTML全文浏览量:  61
  • PDF下载量:  50
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-07-04
  • 修回日期:  2023-12-14
  • 网络出版日期:  2023-12-26

目录

    /

    返回文章
    返回