Deep neural network-based dynamic mapping strategy for low earth orbit satellite channel estimation

LIU Yifei; CUI Gaofeng; PAN Mingyu; WANG Weidong

doi:null

您当前的位置：

首页 >

文章列表页 >

Deep neural network-based dynamic mapping strategy for low earth orbit satellite channel estimation

更新时间：2026-03-03

- Deep neural network-based dynamic mapping strategy for low earth orbit satellite channel estimation
- Chinese Journal on Internet of Things (2026)
- 作者机构：
  
  北京邮电大学电子工程学院，北京 100876
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(62171052)
- DOI：
  CLC： TN927.2
- Received：15 May 2025，
  
  Revised：2025-07-23，
  
  Accepted：07 August 2025，
- 稿件说明：
移动端阅览
LIU Yifei, CUI Gaofeng, PAN Mingyu, et al. Deep neural network-based dynamic mapping strategy for low earth orbit satellite channel estimation[J/OL]. Chinese Journal on Internet of Things, 2026.
DOI：

LIU Yifei, CUI Gaofeng, PAN Mingyu, et al. Deep neural network-based dynamic mapping strategy for low earth orbit satellite channel estimation[J/OL]. Chinese Journal on Internet of Things, 2026. DOI：

摘要

在低轨卫星（LEO

low earth orbit）通信系统中，针对星地链路高速运动引发的时延动态变化以及低信噪比的信道环境，传统的信道估计算法性能表现较差等问题，在正交频分复用（OFDM

Orthogonal Frequency Division Mul-tiplexing）的框架下，提出一种基于深度神经网络（DNN

deep neural networks）与信道响应分块合并结合的低轨卫星通信系统的信道估计算法，可有效提升低轨卫星非地面网络（NTN

non-terrestrial networks）通信环境中数据传输的可靠性与稳定性。该算法将频域导频信道响应矩阵进行分块平均，并结合深度神经网络，在不同时延与噪声的信道场景下，自适应得到导频信道响应分块合并数的最优映射。将该算法与现有的信道估计算法在动态随机时延情况下的误码率性能曲线进行仿真对比。仿真结果表明，该算法相对于传统信道估计算法，在添加动态随机时延情况下，同一信噪比下误码率更低，具有较强的鲁棒性，同时相比于现有的神经网络信道估计算法，能适应较大时延与时延变化情况，具有更强的泛化性。

Abstract

In low-earth-orbit (LEO) satellite communication systems

addressing the poor performance of traditional channel estimation algorithms under dynamic delay variations and low signal-to-noise ratio (SNR) caused by high-speed satellite-terrestrial motion

this paper proposes a deep neural network (DNN)-based channel estimation algorithm combined with sub-block merging of channel responses under an orthogonal frequency-division multiplexing (OFDM) framework. This method enhances the reliability and stability of data transmission in non-terrestrial networks (NTN). The algorithm divides the frequency-domain pilot channel response matrix into sub-blocks for averaging and employs a DNN to adaptively determine the optimal sub-block merging number under different channel conditions with varying delay and noise. The bit error rate (BER) performance of this algorithm is compared through simulations against existing channel estimation methods under dynamically randomized delays. Results demonstrate that the proposed algorithm achieves lower BER at identical SNR levels than traditional methods

exhibiting stronger robustness. Compared to existing neural network-based channel estimation algorithms

it adapts better to larger delays and dynamic delay variations

showing superior generalization capability.

关键词

Keywords

references

苏昭阳，刘留，艾渤，等 . 面向低轨卫星的星地信道模型综述 [J ] . 电子与信息学报， 2024 ， 46 ( 05 )： 1684 - 1702 .

SU Z Y , LIU L , AI B , et al . Survey of satellite-terrestrial channel modeling for low earth orbit satellites [J ] . Journal of Electronics & Information Technology , 2024 , 46 ( 05 ): 1684 - 1702 .

张更新，廖磊瑶，何元智 . 面向空天地海一体化的卫星通信关键技术研究 [J ] . 电信科学， 2024 ， 40 ( 06 )： 11 - 24 .

ZHANG G X , LIAO L Y , HE Y Z . Research on key technologies of satellite communications for space-air-ground-sea integration [J ] . Telecommunications Science , 2024 , 40 ( 06 ): 11 - 24 .

H. ZHAO , Y. ZHANG , K. WEI , et al . Channel estimation for 5G non-terrestrial [C ] // Proceedings of 2024 5th Information Communication Technologies Conference (ICTC) . Nanjing, China : IEEE , 2024 : 210 - 215 .

W-Y . YEO, D-J. LEE, et al. Uplink time synchronization based on time drift measurements in non-terrestrial networks[J ] . IEEE Access , 2024 , 12 : 168877 - 168893 .

X. HUANG , L. CHEN , X. CHEN , et al . Wireless channel estimation and equalization based on deep learning [C ] // Proceedings of 2024 10th IEEE International Conference on Intelligent Data and Security (IDS) . NYC, NY, USA : IEEE , 2024 : 47 - 52 .

H. FENG , Y. XU , Y. ZHAO , et al . Deep learning-based joint channel estimation and CSI feedback for RIS-assisted communications [J ] . IEEE Communications Letters , 2024 , 28 ( 8 ): 1860 - 1864 .

S. YALLAPU, S. P , K. R. S , et al . Robust channel estimation and performance evaluation of OFDM through AWGN channel [C ] // Proceedings of 2024 2nd International Conference on Device Intelligence, Computing and Communication Technologies (DICCT) . Dehradun, India : IEEE , 2024 : 514 - 517 .

Z. HUANG , D. HE , Z. WANG , et al . Two-stage LMMSE/DNN receiver for high-order modulation [J ] . IEEE Communications Letters , 2023 , 27 ( 8 ): 2068 - 2072 .

R A , S P M , KULKARNI K . 5G Channel Estimation for Downlink SISO Channels Using Convolutional Neural Networks [C ] // 2025 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) . Bangalore : India , 2025 : 1 - 5 .

王义元，常俊，卢中奎，等 . 深度学习辅助的5G OFDM系统的信道估计 [J ] . 电讯技术， 2024 ， 64 ( 01 )： 36 - 42 .

WANG Y Y , CHANG J , LU Z K , et al . Deep learning-assisted channel estimation for 5G OFDM systems [J ] . Telecommunications Technology , 2024 , 64 ( 01 ): 36 - 42 .

A. AMROUCHE . DNN-based Arabic printed characters classification [C ] // Proceedings of 2024 2nd International Conference on Electrical Engineering and Automatic Control (ICEEAC) . Setif, Algeria : IEEE , 2024 : 1 - 5 .

D. CUI , G. SUN , X. ZHAN , et al . Dangerous behavior image recognition algorithm of smart port based on deep neural network [C ] // Proceedings of 2023 9th Annual International Conference on Network and Information Systems for Computers (ICNISC) . Wuhan, China : IEEE , 2023 : 94 - 98 .

MATOS J B P , LIMA FILHO E B , BESSA I , et al . Counterexample guided neural network quantization refinement [J ] . IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems , 2024 , 43 ( 4 ): 1121 - 1134 .

CHENG Q , HU X , XIAO H , ZHOU Y , DUAN S . High-Performance Method and Architecture for Attention Computation in DNN Inference [J ] . IEEE Transactions on Biomedical Circuits and Systems , 2025 , 19 ( 2 ): 404 - 415 .

LEE S , KIM J , KIM Y . Accuracy Performance Analysis of Quantized DNN Models Using Approximate 4-2 Compressor Based Multipliers [C ] // 2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) . Fukuoka : Japan , 2025 : 1031 - 1033 .

B. R. SRI , T. S. BALAKRISHNAN . Classification of pests in agricultural farms using convolutional neural network compared to artificial neural network [C ] // Proceedings of 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT) . Kamand, India : IEEE , 2024 : 1 - 4 .

QIAO Y , TENG S , LUO J , SUN P , LI F , TANG F . On-Orbit DNN Distributed Inference for Remote Sensing Images in Satellite Internet of Things [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 5 ): 5687 - 5703 .

WANG Q , CHEN S , YANG C , LI Z , WANG Y , CHEN T . Minimizing Energy and Latency in LEOS-Assisted Open RAN Architecture Toward AI of Things [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 11 ): 16813 - 16828 .

A. ALATAWI , H. R. SADJADPOUR , Z. REZKI , et al . Adaptive deep neural network for non-stationary wireless channels [C ] // Proceedings of 2024 11th International Conference on Wireless Networks and Mobile Communications (WINCOM) . Leeds, UK : IEEE , 2024 : 1 - 6 .

M. B. M , V. MALATHY , J. KAUR , et al . Exponential linear unit and Swish with deep neural network based resource allocation in wireless communication systems [C ] // Proceedings of 2024 International Conference on Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC) . Bengaluru, India : IEEE , 2024 : 1 - 5 .

M. PALESI , E. RUSSO , A. DAS , et al . Wireless enabled inter-chiplet communication in DNN hardware accelerators [C ] // Proceedings of 2023 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) . St . Petersburg, FL, USA : IEEE , 2023 : 477 - 483 .

WANG Q , et al . Energy-Efficient Resource Allocation in LEO-Assisted UAV Architecture for Internet of Things [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 8 ): 9614 - 9626 .

I. VAJS , P. IVANIŠ , D. DRAJIĆ , et al . CNN and LSTM neural networks for spectral efficiency improvements in LEO satellite networks [C ] // Proceedings of 2024 32nd Telecommunications Forum (TELFOR) . Belgrade, Serbia : IEEE , 2024 : 1 - 4 .

Y. WU , et al . MP-DPD: Low-complexity mixed-precision neural networks for energy-efficient digital predistortion of wideband power amplifiers [J ] . IEEE Microwave and Wireless Technology Letters , 2024 , 34 ( 6 ): 817 - 820 .

R. R. V. S. S. BHARATTEJ , et al . Application of computer software in chemical data processing using spider monkey optimization algorithm [C ] // Proceedings of 2024 Second International Conference on Networks, Multimedia and Information Technology (NMITCON) . Bengaluru, India : IEEE , 2024 : 1 - 4 .

GUPTA H , SRIVASTAVA N , BORMAN L . AI-Based Handover Decision Algorithm for Conditional Handover in Non-Terrestrial Networks (NTNs) [C ] // 2025 International Conference on Computing, Networking and Communications (ICNC) . Honolulu : USA , 2025 : 128 - 132 .

M. CARRATÙ , S. D. IACONO , G. DI LEO , et al . Smart water meter based on deep neural network and undersampling for PWNC detection [J ] . IEEE Transactions on Instrumentation and Measurement , 2023 , 72 : 1002211 .

M. AL-FAROUNI , B. PANDURI , M. A. ALKHAFAIJ , et al . Comparative approach on machine learning and deep learning techniques based diabetic retinopathy detection [C ] // Proceedings of 2024 Second International Conference on Networks, Multimedia and Information Technology (NMITCON) . Bengaluru, India : IEEE , 2024 : 1 - 5 .

A. K. GIZZINI , M. CHAFII , A. NIMR , et al . Enhancing least square channel estimation using deep learning [C ] // Proceedings of 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring) . Antwerp, Belgium : IEEE , 2020 : 1 - 5 .

R. ONISHI , T. SATO , T. IDE , et al . An evaluation of channel estimation method using deep learning for OFDM system [C ] // Proceedings of 2024 Fifteenth International Conference on Ubiquitous and Future Networks (ICUFN) . Budapest, Hungary : IEEE , 2024 : 50 - 54 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Lightweight parallel denoising network-based OTFS channel estimation algorithm

Channel estimation for ambient Internet of things

Channel estimation for double IRS-assisted millimeter wave MIMO systems based on tensor decomposition and manifold optimization

Survey on the research progress of generative adversarial networks for 6G

Uplink assisted downlink channel estimation method of extra-large scale MIMO-OTFS system

Related Author

WEI Jibo

ZHAO Haitao

ZHANG Hui

LIU Xiaoran

HAN Xueqing

XIONG Jun

WANG Gongpu

WANG Ruoheng

Related Institution

School of Internet of Things, Nanjing University of Posts and Telecommunications

College of Electronic Science and Technology, National University of Defense Technology

The State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University

School of Electronic and Information Engineering, Beijing Jiaotong University

School of Computer Science and Technology, Beijing Jiaotong University

⁰