FSO通信系统中应用机器学习算法的研究进展

柳海楠; 邵宇丰; 王安蓉; 朱耀东; 杨林捷; 陈超; 李文臣; 胡文光

doi:10.13756/j.gtxyj.2025.240040

您当前的位置：

首页 >

文章列表页 >

FSO通信系统中应用机器学习算法的研究进展

光通信系统与网络技术 | 更新时间：2025-05-08

- FSO通信系统中应用机器学习算法的研究进展
- Research Progress of Machine Learning Algorithms Applied in FSO Communication Systems
- 光通信研究 2025年第2期
- 作者机构：
  
  1.重庆三峡学院　电子与信息工程学院，重庆　 404100
  2.嘉兴大学　信息科学与工程学院，浙江　嘉兴　 314001
- 作者简介：
  
  柳海楠（1998-），女，河南洛阳人。硕士，主要研究方向为自由空间光通信。
  邵宇丰，教授。E-mail：syufeng@163.com
- 基金信息：
  
  重庆市基础研究与前沿探索资助项目(cstc2018jcyjAX0038;cstc2016jcyjA0246);重庆市教委科学技术研究计划重大资助项目(KJZD-M201901201);国家自然科学基金资助项目(61107064);浙江省重点研发计划资助项目(2017C01043)
- DOI：10.13756/j.gtxyj.2025.240040
  中图分类号： TN929
- 收稿：2024-04-02，
  
  修回：2024-05-15，
  
  纸质出版：2025-04-10
- 稿件说明：
移动端阅览
柳海楠，邵宇丰，王安蓉，等. FSO通信系统中应用机器学习算法的研究进展[J].光通信研究，2025(2)：240040.

Liu H N, Shao Y F, Wang A R, et al. Research Progress of Machine Learning Algorithms Applied in FSO Communication Systems[J]. Study on Optical Communications, 2025(2): 240040.
柳海楠，邵宇丰，王安蓉，等. FSO通信系统中应用机器学习算法的研究进展[J].光通信研究，2025(2)：240040. DOI： 10.13756/j.gtxyj.2025.240040.

Liu H N, Shao Y F, Wang A R, et al. Research Progress of Machine Learning Algorithms Applied in FSO Communication Systems[J]. Study on Optical Communications, 2025(2): 240040. DOI： 10.13756/j.gtxyj.2025.240040.

摘要

自由空间光（FSO）通信作为一种速率高、延迟低、带宽大及支持快速链路部署的有效传输技术，近年来在面向大数据传输的无线通信领域日益受到业界重视。但是，FSO信号链路的通信性能易受天气条件和大气状态（尤其是大气湍流）的影响，从而导致信号收发质量及系统传输性能恶化。为提升FSO通信系统的收发及传输性能，近年来研究人员已开始在FSO通信系统中应用若干先进机器学习算法来优化信号检测和信道建模的过程，并取得了新的研究进展。文章综述了FSO通信系统中在信号检测、信道估计和辅助光学补偿等方面应用典型机器学习算法的研究情况，对比分析了使用不同典型机器学习算法的应用特点，并探讨了FSO通信系统中应用机器学习算法的未来发展趋势。

Abstract

Free-Space Optical (FSO) communication

as an effective transmission technology with high speed

low latency

large bandwidth

and support for rapid link deployment

has been increasingly valued in the field of wireless communication aimed at big data transmission in recent years. However

the communication performance of FSO signal link is susceptible to weather conditions and atmospheric states (especially atmospheric turbulence)

resulting in degradation of signal reception and transmission quality as well as system performance. In order to enhance the reception

transmission

and overall performance of FSO communication systems

researchers have begun to apply various advanced machine learning algorithms to optimize the signal detection and channel modeling processes in FSO communication systems. In this article

the research progress of applying typical machine learning algorithms in FSO communication systems in signal detection

channel estimation

auxiliary optical compensation

and other aspects are reviewed. We compare and analyze the application characteristics of different typical machine learning algorithms

and discuss the future development trends of applying machine learning algorithms in FSO communication systems.

关键词

Keywords

references

Chowdhury M Z , Hossan M T , Islam A , et al . A Comparative Survey of Optical Wireless Technologies: Architectures and Applications [J ] . IEEE Access , 2018 , 6 : 9819 - 9840 .

Baiwa R , Verma P . Performance Analysis of FSO System for Advanced Modulation Formats under Different Weather Conditions [C ] // 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS) . Madurai, India : IEEE , 2018 : 1490 - 1495 .

Wang J B , Xie X X , Jiao Y , et al . Optimal Odd-periodic Complementary Sequences for Diffuse Wireless Optical Communications [J ] . Optical Engineering , 2012 , 51 ( 9 ): 095002 .

邢莉娟 , 李卓 , 王卓 . 自由空间光通信中极化码的应用研究 [J ] . 光通信研究 , 2024 ( 3 ): 230058 .

Xing L J , Li Z , Wang Z . Research on Application of Polar Codes in Free Space Optical Communication [J ] . Study on Optical Communications , 2024 ( 3 ): 230058 .

赵辉 , 刘亮 , 韩利利 , 等 . 自由空间光通信中的带符号光正交空间调制 [J ] . 光通信研究 , 2024 ( 3 ): 230075 .

Zhao H , Liu L , Han L L , et al . Signed Optical Quadrature Spatial Modulation in Free Space Optical Communication [J ] . Study on Optical Communications , 2024 ( 3 ): 230075 .

庞婕 . 不同天气条件下自由空间光通信关键技术研究 [D ] . 苏州 : 苏州大学 , 2020 .

Pang J . Research on Key Technologies of Free Space Optical Communication under Different Weather Conditions [D ] . Suzhou, China : Soochow University , 2020 .

Shao Y , Yu N , Wang A , et al . Research on Full Duplex FSO Access System with Hybrid 16PSK/256QAM-OFDM Downlink and Duobinary Uplink Signals [J ] . Optics Communications , 2024 , 550 : 129956 .

Amirabadi M A . A Deep Learning based Solution for Imperfect CSI Problem in Correlated FSO Communication Channel [EB/OL ] . ( 2019-09-12 ) [ 2024-04-02 ] . https://arxiv.org/abs/1909.11002v1 https://arxiv.org/abs/1909.11002v1 .

Lohani S , Knutson E M , Glasser R T . Generative Machine Learning for Robust Free-space Communication [J ] . Communications Physics , 2020 , 3 : 177 .

Lionis A , Peppas K , Nistazakis H E , et al . Using Machine Learning Algorithms for Accurate Received Optical Power Prediction of an FSO Link over a Maritime Environment [J ] . Photonics , 2021 , 8 ( 6 ): 212 .

Liu Y . A Modified Approach on MMSE MIMO Interference Cancellation Detection of Free Space Optical Communication [C ] // 2018 10th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA) . Changsha, China : IEEE , 2018 : 8337361 .

Ali Khalighi M , Uysal M . Survey on Free Space Optical Communication: a Communication Theory Perspective [J ] . IEEE Communications Surveys & Tutorials , 2014 , 16 ( 4 ): 2231 - 2258 .

Dabiri M T , Sadough S M S . Generalized Blind Detection of OOK Modulation for Free-space Optical Communication [J ] . IEEE Communications Letters , 2017 , 21 ( 10 ): 2170 - 2173 .

Amirabadi M A , Kahaei M H , Nezamalhosseini S A , et al . Deep Learning for Channel Estimation in FSO Communication System [J ] . Optics Communications , 2020 , 459 : 124989 .

Darwesh L , Kopeika N S . Deep Learning for Improving Performance of OOK Modulation over FSO Turbulent Channels [J ] . IEEE Access , 2020 , 8 : 155275 - 155284 .

Li J W , You S L , Shiu R K , et al . A Deep Neural Network Equalizer for FSO Transmission System [C ] // 2021 30th Wireless and Optical Communications Conference (WOCC) . Taipei, China : IEEE , 2021 : 9602965 .

Israr A , Khan F . Optimal Modulation Technique for MIMO FSO Link [J ] . Wireless Personal Communications , 2019 , 109 ( 2 ): 695 - 714 .

Wang C X , Wu S , Bai L , et al . Recent Advances and Future Challenges for Massive MIMO Channel Measurements and Models [J ] . Science China Information Sciences , 2016 , 59 ( 2 ): 1 - 16 .

Amirabadi M A , Kahaei M H , Nezamalhosseni S A . Low Complexity Deep Learning Algorithms for Compensating Atmospheric Turbulence in the Free Space Optical Communication System [J ] . IET Optoelectronics , 2022 , 16 ( 3 ): 93 - 105 .

Kumar L J S , Krishnan P , Shreya B , et al . Performance Enhancement of FSO Communication System Using Machine Learning for 5G/6G and IoT Applications [J ] . Optik , 2022 , 252 : 168430 .

黎天翼 , 黎明 , 周明欧 , 等 . 基于深度学习的ACO-OFDM自由空间光通信中信号检测 [J ] . 光电子·激光 , 2023 , 34 ( 1 ): 68 - 73 .

Li T Y , Li M , Zhou M O , et al . Signal Detection in ACO-OFDM Free-space Optical Communication Systems based on Deep Learning [J ] . Journal of Optoelectronics·Laser , 2023 , 34 ( 1 ): 68 - 73 .

Sha Y , Xu X , Yao N . Wireless Channel Model based on RBF Neural Network [C ] // 2008 Fourth International Conference on Natural Computation . Jinan, China : IEEE , 2008 : 4667066 .

刘留 , 李慧婷 , 张嘉驰 , 等 . 基于神经网络的时变无线信道仿真 [J ] . 北京交通大学学报 , 2020 , 44 ( 2 ): 74 - 82 .

Liu L , Li H T , Zhang J C , et al . Wireless Channel Simulation based on Neural Network [J ] . Journal of Beijing Jiaotong University , 2020 , 44 ( 2 ): 74 - 82 .

Huang J , Wang C X , Bai L , et al . A Big Data Enabled Channel Model for 5G Wireless Communication Systems [J ] . IEEE Transactions on Big Data , 2020 , 6 ( 2 ): 211 - 222 .

Song S , Liu Y , Xu T , et al . Demonstration of Channel-predictable Free Space Optical Communication System Using Machine Learning [C ] // 2021 Optical Fiber Communications Conference and Exhibition (OFC) . San Francisco, CA, USA : IEEE , 2021 : 9489588 .

Chen W , Zhang M , Wang D , et al . Deep Learning-based Channel Modeling for Free Space Optical Communications [J ] . Journal of Lightwave Technology , 2023 , 41 ( 1 ): 183 - 198 .

Wang Y , Zhu L , Feng W . Performance Study of Wavelength Diversity Serial Relay OFDM FSO System over Exponentiated Weibull Channels [J ] . Optics Communications , 2021 , 478 : 126470 .

Bart M P , Savino N J , Regmi P , et al . Deep Learning for Enhanced Free-space Optical Communications [J ] . Machine Learning: Science and Technology , 2023 , 4 ( 4 ): 045046 .

Ma H , Liu H , Zhang J , et al . Numerical Comparison of Adaptive Optics Correction based on Stochastic Parallel Gradient Descent and Phase Conjugate in Scintillation Conditions [J ] . Optik , 2020 , 208 : 164528 .

Li Z , Shang T , Liu X , et al . Advanced Multi-feedback Stochastic Parallel Gradient Descent Wavefront Correction in Free-space Optical Communication [J ] . Optics Communications , 2023 , 533 : 129268 .

Liu W , Jin D , Shi W , et al . Performance Analysis of Coherent Optical Communication based on Hybrid Algorithm [J ] . Optics & Laser Technology , 2022 , 149 : 107878 .

Peng J , Qi B , Li H , et al . AS-SPGD Algorithm to Improve Convergence Performance for Fiber Coupling in Free Space Optical Communication [J ] . Optics Communications , 2022 , 519 : 128397 .

Pasupathi T , Arputha V S J . Real Time Experimental Investigation of Adaptive Optics Compensation Technique for Free Space Optical Communication [J ] . Photonic Network Communications , 2022 , 44 ( 2 ): 102 - 115 .

浏览量

319

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

高维度光交换网络的故障定位策略研究

基于神经网络的三阶拉曼放大光传输系统建模

面向5G/6G移动前传网络的关键技术

基于机器学习的OTN业务时延估算方法研究

卫星物联网负载量估计及预测