Journal of Intelligent Systems and Internet of Things

Journal DOI

https://doi.org/10.54216/JISIoT

Submit Your Paper

2690-6791ISSN (Online) 2769-786XISSN (Print)

Volume 17 , Issue 2 , PP: 392-403, 2025 | Cite this article as | XML | Html | PDF | Full Length Article

Deep Learning-Based BER Enhancement for 64x64 MIMO-FSO NOMA Systems Under Various Atmospheric Turbulence Senarios

Hasan Farooq Radeef 1 * , Lwaa F. Abdulameer 2

  • 1 Electronic and communication Department, Institute of Laser for Postgraduate Studies, University of Baghdad, Baghdad, Iraq; 3Department of Computer Networks, Information College of Engineering, Al-Nahrain University, Iraq - (hasan.ahmed2101p@ilps.uobaghdad.edu.iq)
  • 2 Department of Information and Communication, Al-khwarizmi College of Engineering, University of Baghdad, Iraq - (lwaa@kecbu.uobaghdad.edu.iq)
  • Doi: https://doi.org/10.54216/JISIoT.170225

    Received: January 23, 2025 Revised: March 28, 2025 Accepted: June 12, 2025
    Abstract

    The current exponential growth in the demand for bandwidth is the most urgent challenge for next-generation wireless systems. One of the most appropriate techniques to overcome this situation is Free-space optical (FSO) communication due to the provision of an ample bandwidth. The main disadvantage of FSO communication systems is that the optical beam, propagating through atmospheric turbulence, can be distorted to an unacceptable level. In this work, a 64x64 MIMO-FSO system with Non-Orthogonal Multiple Access (NOMA) and QPSK modulation scheme is assessed. We compare the Bit Error Rate (BER) performance of the system under 4 theoretical turbulence channel models: Log-Normal, Gamma-Gamma, Fisher-Snedecor, Negative Exponential, as well as 4 real seasonal LogCn² datasets. Classical Maximum Likelihood (ML) detection was compared against the deep learning-based ML detection using a Deep Neural Network (DNN) as well as an Autoencoder model. We found that the autoencoder model has outperformed the classical ML detection in terms of BER performance, especially for the weaker user, when NOMA is considered. It was also found that using real datasets that represent real turbulence conditions the proposed system is highly effective and can serve as intelligent fronthaul/backhaul solutions for dense IoT networks such as smart cities, autonomous vehicles, and industrial automation.

    Keywords :

    Massive MIMO , FSO , DNN , IoT , Intelligent Systems

    References

    [1]       Kumar, R. G. Sangeetha, and M. P. Sharma, “Advanced techniques for enhancing free space optical communication systems under varying atmospheric conditions,” Journal of Optical Communications, vol. 45, no. 3, pp. 123–134, 2023.

     

    [2]       M. A. Atiyah, L. F. Abdulameer, and G. Narkhedel, “PDF comparison based on various FSO channel models under different atmospheric turbulence,” Al-Khwarizmi Engineering Journal, vol. 19, no. 4, pp. 78–89, 2023.

     

    [3]       H. F. Radeef, L. F. Abdulameer, and H. M. Fadhil, “Machine learning for free space optical communication: A systematic review with emphasis on NOMA and massive MIMO integration,” Fusion: Practice and Applications, vol. 20, no. 2, pp. 65–76, 2025.

     

    [4]       D. A. Kumar and R. G. Sangeetha, “Power series based gamma–gamma fading MIMO/FSO link analysis with atmospheric turbulence and pointing errors,” Optical and Quantum Electronics, vol. 53, no. 505, 2021.

     

    [5]       M. A. Esmail et al., “Free space optic channel monitoring using machine learning,” Optics Express, vol. 29, pp. 10967–10981, 2021.

     

    [6]       L. J. S. Kumar, P. Krishnan, B. Shreya, and S. M. S. M., “Performance enhancement of FSO communication system using machine learning for 5G/6G and IoT applications,” Optik, vol. 252, Art. no. 168430, 2022.

     

    [7]       M. P. Bart et al., “Deep learning for enhanced free-space optical communications,” arXiv: 2208.07712, 2022.

     

    [8]       S. A. Abd El-Mottaleb et al., “Machine learning FSO-SAC-OCDMA code recognition under different weather conditions,” Optical and Quantum Electronics, vol. 54, p. 851, 2022.

     

    [9]       S. Henna, A. A. Minhas, M. S. Khan, and M. S. Iqbal, “Ensemble consensus representation deep reinforcement learning for hybrid FSO/RF communication systems,” Optics Communications, vol. 530, Art. no. 129186, 2023.

     

    [10]    M. A. Esmail, “Performance monitoring of hybrid all-optical fiber/FSO communication systems,” Applied Sciences, vol. 13, no. 14, p. 8477, 2023.

     

    [11]    Lionis et al., “Experimental machine learning approach for optical turbulence and FSO outage performance modeling,” Electronics, vol. 12, no. 3, p. 506, 2023.

     

    [12]    S. A. A. El-Mottaleb, A. Elhefny, A. Métwalli et al., “Harnessing the power of ML for robust SISO and MIMO FSO communication systems in fog weather,” Optical and Quantum Electronics, vol. 56, p. 1065, 2024.

     

    [13]    M. S. N. Al-Imran, H. Nguyen, and Y. M. Jang, “Channel estimation of massive MIMO FSO communication system using deep attention residual U-Net,” ICT Express, 2024.

     

    [14]    P. A. Forsido, D. J. Gelmecha, and R. S. Singh, “Machine learning–based multiparameter performance predictions of ultra-dense WDM FSO–FTTx systems under diverse weather conditions,” International Journal of Optics, vol. 2025, Art. no. 6697110, 2025.

     

    [15]    H. Kaushal, V. K. Jain, and S. Kar, “Free-space optical channel models,” in Free Space Optical Communication, New Delhi, India: Springer, 2017, ch. 2, pp. 41–89.

     

    [16]    D. Benton, Y. Li, A. Billaud, and A. D. Ellis, “Spatial mode division multiplexing of free‑space optical communications using a pair of multiplane light converters and a micromirror array for turbulence emulation,” Photonics, vol. 11, no. 3, art. 241, 2024.

    Cite This Article As :
    Farooq, Hasan. , F., Lwaa. Deep Learning-Based BER Enhancement for 64x64 MIMO-FSO NOMA Systems Under Various Atmospheric Turbulence Senarios. Journal of Intelligent Systems and Internet of Things, vol. , no. , 2025, pp. 392-403. DOI: https://doi.org/10.54216/JISIoT.170225
    Farooq, H. F., L. (2025). Deep Learning-Based BER Enhancement for 64x64 MIMO-FSO NOMA Systems Under Various Atmospheric Turbulence Senarios. Journal of Intelligent Systems and Internet of Things, (), 392-403. DOI: https://doi.org/10.54216/JISIoT.170225
    Farooq, Hasan. F., Lwaa. Deep Learning-Based BER Enhancement for 64x64 MIMO-FSO NOMA Systems Under Various Atmospheric Turbulence Senarios. Journal of Intelligent Systems and Internet of Things , no. (2025): 392-403. DOI: https://doi.org/10.54216/JISIoT.170225
    Farooq, H. , F., L. (2025) . Deep Learning-Based BER Enhancement for 64x64 MIMO-FSO NOMA Systems Under Various Atmospheric Turbulence Senarios. Journal of Intelligent Systems and Internet of Things , () , 392-403 . DOI: https://doi.org/10.54216/JISIoT.170225
    Farooq H. , F. L. [2025]. Deep Learning-Based BER Enhancement for 64x64 MIMO-FSO NOMA Systems Under Various Atmospheric Turbulence Senarios. Journal of Intelligent Systems and Internet of Things. (): 392-403. DOI: https://doi.org/10.54216/JISIoT.170225
    Farooq, H. F., L. "Deep Learning-Based BER Enhancement for 64x64 MIMO-FSO NOMA Systems Under Various Atmospheric Turbulence Senarios," Journal of Intelligent Systems and Internet of Things, vol. , no. , pp. 392-403, 2025. DOI: https://doi.org/10.54216/JISIoT.170225