可重構(gòu)智能超表面輔助的大規(guī)模機(jī)器類通信深度學(xué)習(xí)大規(guī)模MIMO信道估計(jì)

劉婷; 王媛; 辛元雪

doi:10.11999/JEIT240584

可重構(gòu)智能超表面輔助的大規(guī)模機(jī)器類通信深度學(xué)習(xí)大規(guī)模MIMO信道估計(jì)

doi: 10.11999/JEIT240584

劉婷^1, ,,
王媛²,
辛元雪³

1.
南京信息工程大學(xué)人工智能學(xué)院南京 2100044
2.
南京信息工程大學(xué)計(jì)算機(jī)學(xué)院南京 2100044
3.
河海大學(xué)信息科學(xué)與工程學(xué)院常州 213200

基金項(xiàng)目: 國(guó)家自然科學(xué)基金 (62101274)，江蘇省自然科學(xué)基金 (BK20210640)

詳細(xì)信息

作者簡(jiǎn)介:
劉婷：女，講師，研究方向?yàn)槌笠?guī)模連接無(wú)線傳輸技術(shù)

王媛：女，碩士生，研究方向?yàn)闊o(wú)線通信

辛元雪：女，副教授，研究方向?yàn)榇笠?guī)模MIMO頻譜效率、能量效率和新型雙工技術(shù)

通訊作者:
劉婷　liuting@nuist.edu.cn

中圖分類號(hào): TN929.5
計(jì)量
- 文章訪問(wèn)數(shù): 343
- HTML全文瀏覽量: 108
- PDF下載量: 81
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2024-07-09
- 修回日期: 2024-09-14
- 網(wǎng)絡(luò)出版日期: 2024-09-24
- 刊出日期: 2024-10-30

Deep Learning-enhanced Massive Channel Estimation for Reconfigurable Intelligent Surface-aided Massive Machine-Type Communication

1.
School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China
2.
School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China
3.
College of Information Science and Engineering, Hohai University, Changzhou 213200, China

Funds: The National Natural Science Foundation of China (62101274), The Natural Science Foundation of Jiangsu Province (BK20210640)

摘要

摘要: 大規(guī)模機(jī)器類通信 (mMTC) 是第5代移動(dòng)通信系統(tǒng)的重要應(yīng)用場(chǎng)景之一，可實(shí)現(xiàn)每平方公里近百萬(wàn)級(jí)設(shè)備的連接?？紤]到mMTC傳播環(huán)境的復(fù)雜性，該文引入可重構(gòu)智能超表面 (RIS) 進(jìn)行上行免授權(quán)的傳輸，由此級(jí)聯(lián)形成用戶與RIS、RIS與基站 (BS) 之間的信道鏈路，從而有效控制無(wú)線信號(hào)傳輸?shù)馁|(zhì)量。在此基礎(chǔ)上，建立Turbo譯碼消息傳遞思想下的降噪學(xué)習(xí)系統(tǒng)，通過(guò)大量的訓(xùn)練數(shù)據(jù)，以學(xué)習(xí)RIS輔助的級(jí)聯(lián)信道狀態(tài)信息，并對(duì)其進(jìn)行估計(jì)。此外，該文對(duì)RIS輔助的mMTC信道估計(jì)結(jié)果進(jìn)行了統(tǒng)計(jì)分析，以驗(yàn)證所提方案的準(zhǔn)確性。數(shù)值仿真結(jié)果和理論分析結(jié)果表明，該文方法優(yōu)于其他壓縮感知類的方法。
- 大規(guī)模機(jī)器類通信 /
- 免授權(quán)接入 /
- 可重構(gòu)智能超表面 /
- 深度學(xué)習(xí) /
- 信道估計(jì)
Abstract: Massive Machine-Type Communication (mMTC) is one of the typical scenarios of the fifth-generation mobile communications systems, and nearly one million devices per square kilometer can be connected under this circumstance. The Reconfigurable Intelligent Surface (RIS) is applied for the grant-free uplink transmission due to the complexity of the propagation environment in the scenario of massive connectivity. Then, the cascaded channel, i.e., the channel link between devices and the RIS, as well as the channel link between the RIS and the Base Station (BS), is formed. Consequently, the quality of the wireless signal transmission can be controlled effectively. On this basis, a denoising learning system is designed using the principle of turbo decoding message passing. The RIS-aided cascaded CSI is learned and estimated through a large number of training data. In addition, the statistical analysis of the RIS-assisted mMTC channel estimation is performed to verify the accuracy of the proposed scheme. Numerical simulation results and theoretical analyses show that the proposed technique is superior to other compressed-sensing-type methods.
- Massive Machine-Type Communication (mMTC) /
- Grant-free access /
- Reconfigurable Intelligent Surface (RIS) /
- Deep Learning (DL) /
- Channel estimation

HTML全文

圖 1 RIS輔助的mMTC上行傳輸系統(tǒng)示意圖

下載: 全尺寸圖片幻燈片

圖 2 信道估計(jì)深度學(xué)習(xí)架構(gòu)圖

下載: 全尺寸圖片幻燈片

圖 3 聯(lián)合GAN和DnCNN的降噪模塊圖

下載: 全尺寸圖片幻燈片

圖 4 不同系統(tǒng)模型下的信道估計(jì)性能比較，$ M = 32 $

下載: 全尺寸圖片幻燈片

圖 5 RIS輔助系統(tǒng)的MSE性能比較，$ M = 64 $

下載: 全尺寸圖片幻燈片

圖 6 不同RIS單元數(shù)量下的MSE性能比較，$ M = 64 $

下載: 全尺寸圖片幻燈片

圖 7 不同學(xué)習(xí)層數(shù)下的MSE性能比較

下載: 全尺寸圖片幻燈片

參考文獻(xiàn)(19)

[1]	YOU Xiaohu, WANG Chengxiang, HUANG Jie, et al. Towards 6G 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]	IMT-2030 (6G) 推進(jìn)組. 6G無(wú)線系統(tǒng)設(shè)計(jì)原則和典型特征白皮書[R]. 2023. IMT-2030 (6G) Promotion Group. White paper on 6G wireless system design principles and typical characteristics[R]. 2023.
[3]	尤肖虎, 許威, 相紅, 等. 6G發(fā)展趨勢(shì)與候選關(guān)鍵技術(shù)分析[J]. 信息通信技術(shù), 2023, 17(6): 11–20,27. doi: 10.3969/j.issn.1674-1285.2023.06.003. YOU Xiaohu, XU Wei, XIANG Hong, et al. 6G network evolution and key candidate technologies[J]. Information and Communications Technologies, 2023, 17(6): 11–20,27. doi: 10.3969/j.issn.1674-1285.2023.06.003.
[4]	ELHOUSHY S, IBRAHIM M, and HAMOUDA W. Cell-free massive MIMO: A survey[J]. IEEE Communications Surveys & Tutorials, 2022, 24(1): 492–523. doi: 10.1109/COMST.2021.3123267.
[5]	LIU Ting, JIN Shi, WEN Chaokai, et al. Generalized channel estimation and user detection for massive connectivity with mixed-ADC massive MIMO[J]. IEEE Transactions on Wireless Communications, 2019, 18(6): 3236–3250. doi: 10.1109/TWC.2019.2912370.
[6]	朱秋明, 倪浩然, 華博宇, 等. 無(wú)人機(jī)毫米波信道測(cè)量與建模研究綜述[J]. 移動(dòng)通信, 2022, 46(12): 2–11. doi: 10.3969/j.issn.1006-1010.20221114-0001. ZHU Qiuming, NI Haoran, HUA Boyu, et al. A survey of UAV millimeter-wave channel measurement and modeling[J]. Mobile Communications, 2022, 46(12): 2–11. doi: 10.3969/j.issn.1006-1010.20221114-0001.
[7]	張?jiān)阼? 江浩. 智能超表面使能無(wú)人機(jī)高能效通信信道建模與傳輸機(jī)理分析[J]. 電子學(xué)報(bào), 2023, 51(10): 2623–2634. doi: 10.12263/DZXB.20221352. ZHANG Zaichen and JIANG Hao. Channel modeling and characteristics analysis for high energy-efficient RIS-assisted UAV communications[J]. Acta Electronica Sinica, 2023, 51(10): 2623–2634. doi: 10.12263/DZXB.20221352.
[8]	PAN Cunhua, ZHOU Gui, ZHI Kangda, et al. An overview of signal processing techniques for RIS/IRS-aided wireless systems[J]. IEEE Journal of Selected Topics in Signal Processing, 2022, 16(5): 883–917. doi: 10.1109/JSTSP.2022.3195671.
[9]	TANG Wankai, DAI Junyan, CHEN Mingzheng, et al. MIMO transmission through reconfigurable intelligent surface: System design, analysis, and implementation[J]. IEEE Journal on Selected Areas in Communications, 2020, 38(11): 2683–2699. doi: 10.1109/JSAC.2020.3007055.
[10]	NGUYEN N T, NGUYEN V D, NGUYEN H V, et al. Spectral efficiency analysis of hybrid relay-reflecting intelligent surface-assisted cell-free massive MIMO systems[J]. IEEE Transactions on Wireless Communications, 2023, 22(5): 3397–3416. doi: 10.1109/TWC.2022.3217828.
[11]	HE Jinglian, YU Kaiqiang, SHI Yuanming, et al. Reconfigurable intelligent surface assisted massive MIMO with antenna selection[J]. IEEE Transactions on Wireless Communications, 2022, 21(7): 4769–4783. doi: 10.1109/TWC.2021.3133272.
[12]	BASHARAT S, HASSAN S A, PERVAIZ H, et al. Reconfigurable intelligent surfaces: Potentials, applications, and challenges for 6G wireless networks[J]. IEEE Wireless Communications, 2021, 28(6): 184–191. doi: 10.1109/MWC.011.2100016.
[13]	LIESEGANG S, ZAPPONE A, MU?OZ O, et al. Rate optimization for RIS-aided mMTC networks in the finite blocklength regime[J]. IEEE Communications Letters, 2023, 27(3): 921–925. doi: 10.1109/LCOMM.2022.3231717.
[14]	CHEN Zhen, HUANG Lei, XIA Shuqiang, et al. Parallel channel estimation for RIS-assisted internet of things[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(8): 9762–9773. doi: 10.1109/TITS.2024.3364248.
[15]	CHEN Jianqiao, MA Nan, XU Xiaodong, et al. Efficient two-level block-structured sparse Bayesian learning-based channel estimation for RIS-assisted MIMO IoT systems[J]. IEEE Internet of Things Journal, 2024, 11(14): 24933–24947. doi: 10.1109/JIOT.2024.3387885.
[16]	HOU Tianwei, LIU Yuanwei, SONG Zhengyu, et al. Reconfigurable intelligent surface aided NOMA networks[J]. IEEE Journal on Selected Areas in Communications, 2020, 38(11): 2575–2588. doi: 10.1109/JSAC.2020.3007039.
[17]	SAGIR B, AYDIN E, and ILHAN H. Deep-learning-assisted IoT-based RIS for cooperative communications[J]. IEEE Internet of Things Journal, 2023, 10(12): 10471–10483. doi: 10.1109/JIOT.2023.3239818.
[18]	NGUYEN C, HOANG T M, and CHEEMA A A. Channel estimation using CNN-LSTM in RIS-NOMA assisted 6G network[J]. IEEE Transactions on Machine Learning in Communications and Networking, 2023, 1: 43–60. doi: 10.1109/TMLCN.2023.3278232.
[19]	BAI Yanna, CHEN Wei, AI Bo, et al. Prior information aided deep learning method for grant-free NOMA in mMTC[J]. IEEE Journal on Selected Areas in Communications, 2022, 40(1): 112–126. doi: 10.1109/JSAC.2021.3126071.