| 154 | 0 | 90 |
| 下载次数 | 被引频次 | 阅读次数 |
针对在不同湍流强度下，非对称限幅光正交频分复用调制技术(Asymmetrically Clipped Optical-Orthogonal Frequency Division Multiplexing,ACO-OFDM)的误码率影响较为显著的问题，提出了一种基于深度学习的ACO-OFDM空间光通信系统极化码译码的方法。先建立了大气信道模型，然后将ACO-OFDM技术与极化码编码结合，最后将多层神经网络译码技术应用于系统中。仿真结果表明，四相调幅下，强湍流条件的多层神经网络译码器优于传统译码，字符信噪比20 d B时误码率差达10-3．十六相调幅下，三种湍流强度时多层神经网络译码器均优于传统译码，弱湍流字符信噪比20 d B时差达10-5．所提出的方法在一定程度上验证了深度学习结合空间光通信系统中的极化码更能提升系统数据传输的准确率。
Abstract：To solve the problem that the BER impact of Asymmetrically Clipped Optical-Orthogonal Frequency Division Multiplexing( ACO-OFDM) is more significant under different turbulence intensities,this paper proposes a deep learning method based on the polar code for ACO-OFDM spatial optical communication system. Firstly,it establishes an atmospheric model of the channel,then it combines the ACO-OFDM modulation technique with the polar code channel coding technique and finally it applies the deep learning Multilayer Perceptron( MLP) decoding technique to the system. The results of simulation indicate that the MLP decoder with strong turbulence condition under 4 Quadrature Amplitude Modulation modulation outperforms the conventional decoding,with a BER difference of up to 10-3at a character signal-to-noise ratio of20 d B. With 16 Quadrature Amplitude Modulation,the MLP decoder surpasses the traditional decoder across all three turbulence intensities,achieving a bit error rate difference of up to 10-5at a signal-to-noise ratio of 20dB under weak turbulence. To some extent,the proposed method proves that deep learning combined with ACO-OFDM space optical communication system polarization code decoding can improve the accuracy of data transmission in the system.
[1]Mohsan S A H,Khan M A,Amjad H. Hybrid FSO/RF networks:A review of practical constraints,applications and challenges[J]. Optical Switching and Networking,2023,47:100697.
[2]Alnajjar S H,Ali M H,Abass A K. Enhancing performance of hybrid FSO/fiber optic communication link utilizing multi-channel configuration[J]. Journal of Optical Communications,2022,43(1):165~170.
[3]Brakensiek J,Gopi S,Makam V. Generic reed-solomon codes achieve list-decoding capacity[C]//Proceedings of the55th Annual ACM Symposium on Theory of Computing. 2023:1488~1501.
[4]Beelen P,Puchinger S,Rosenkilde J. Twisted Reed-Solomon codes[J]. IEEE Transactions on Information Theory,2022,68(5):3047~3061.
[5]Con R,Shpilka A,Tamo I. Reed Solomon codes against adversarial insertions and deletions[J]. IEEE Transactions on Information Theory,2023,69(5):2991~3000.
[6]Yu L,Lin S J,Hou H,et al. Reed-Solomon coding algorithms based on Reed-Muller transform for any number of parities[J]. IEEE Transactions on Computers,2023,72(9):2677~2688.
[7]Tu L T,Nguyen T N,Duy T T,et al. Broadcasting in cognitive radio networks:A fountain codes approach[J]. IEEE Transactions on Vehicular Technology,2022,71(10):11289~11294.
[8]Nguyen N L,Tu L T,Nguyen T N,et al. Performance on cognitive broadcasting networks employing fountain codes and maximal ratio transmission[J]. Radio engineering,2023,32(1):1~10.
[9]He X,Cai K. Basis-finding algorithm for decoding fountain codes for DNA-based data storage[J]. IEEE Transactions on Information Theory,2023,69(6):3691~3707.
[10]Bocharova I E,Kudryashov B D,Ovsyannikov E P,et al. Design and analysis of NB QC-LDPC codes over small alphabets[J]. IEEE Transactions on Communications,2022,70(5):2964~2976.
[11]Hyla J,Su?ek W,Izydorczyk W,et al. Efficient ldpc encoder design for iot-type devices[J]. Applied Sciences,2022,12(5):2558.
[12]Mohan N,Ghassemlooy Z,Li E,et al. The BER performance of a FSO system with polar codes under weak turbulence[J]. IET Optoelectronics,2022,16(2):72~80.
[13]Selvi M,Jeeva S,Jaswanth J. Review of Performance of LDPC Codes for Various OFDM Systems[C]//2024 5th International Conference on Mobile Computing and Sustainable Informatics(ICMCSI). IEEE,2024:864~869.
[14]Youssef A A,Bootstrapped low complex iterative LDPC decoding algorithms for free-space optical communication links[J]. EURASIP Journal on Wireless Communications and Networking,2023,2023(1):78.
[15]Kong S,Analysis of the Encoding and Decoding Process of Polar Code[J]. Highlights in Science. Engineering and Technology. 2023. 53:144~152.
[16]XU W,TAN X,YAIR B,et al. Deep learning-aided belief propagation decoder for polar codes[J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems,2020,10(2):189~203.
[17]DOAN N,HASHEMI A S,ERCAN F,et al. Neural dynamic successive cancellation flip decoding of polar codes[C]//2019 IEEE International Workshop on Signal Processing Systems(Si PS). Nanjing,China:IEEE,2019:631~42.
[18]Berti N,Baudin K,Fusaro A,et al. Interplay of thermalization and strong disorder:Wave turbulence theory,numerical simulations,and experiments in multimode optical fibers[J]. Physical Review Letters,2022,129(6):063901.
[19]Chen J G,Vassilicos J C. Scalings of scale-by-scale turbulence energy in non-homogeneous turbulence[J]. Journal of Fluid Mechanics,2022,938:A7.
[20]李晓峰．星地激光通信链路原理与技术[M]．北京:国防工业出版社，2007.
[21]杜凡丁．自由空间光通信中脊髓码改进编码译码方法与级联方法研究[D]．重庆:重庆理工大学，2022.
[22]饶瑞中．光在湍流大气中的传播[M]．合肥:安徽科学技术出版社，2005.
[23]Hesham H,Ismail T. Hybrid NOMA-based ACO-FBMC/OQAM for next-generation indoor optical wireless communications using Li Fi technology[J]. Optical and Quantum Electronics,2022,54(3):201.
[24]Arikan E. Channel polarization:A method for constructing capacity-achieving codes for symmetric binary-input memoryless channels[J]. IEEE Transactions on information Theory,2009,55(7):3051~3073.
[25]Arikan E. A performance comparison of polar codes and Reed-Muller codes[J]. IEEE Communications Letters,2008,12(6):447~449.
基本信息:
中图分类号:TN929.1;TP18
引用信息:
[1]黎明,刘康睿,瞿家顺,等.基于深度学习的极化码在光通信系统性能分析[J].湖北师范大学学报(自然科学版),2025,45(03):26-32.
2025-09-25
2025-09-25