Advanced signal detection in optical OFDM-VLC with 256-QAM scheme: LSTM-aided BER and PSD optimization over Rayleigh channels
-
Fateh Bahadur Kunwar
,
Nishant Gaur
Abstract
This paper presents a comprehensive analysis of bit error rate (BER) and power spectrum density (PSD) performance for optical OFDM systems integrated with Visible Light Communication (VLC), employing various signal detection algorithms over Rayleigh fading channels. Simulation studies were conducted for 64, 256, and 512 subcarriers to evaluate BER under different SNR conditions. The proposed LSTM-based detection method achieved remarkable improvements, requiring only 6.1 dB, 8.1 dB, and 10.1 dB SNR, respectively, to attain a BER of 10−5, outperforming hybrid, QRM-MLD, MMSE, ZFE, and conventional optical OFDM by SNR gains ranging from 1.9 dB to 10.8 dB. Results also indicate that while increasing the number of subcarriers raises SNR demands, the LSTM detector consistently delivers superior performance, making it highly suitable for high-capacity advanced radio and VLC systems. Furthermore, PSD analysis demonstrates significant side lobe suppression, reducing out-of-band emissions from −100 dB down to −390 dB. This effective spectrum containment is crucial for minimizing spectral leakage in 5G, beyond-5G, and VLC frameworks, thereby enhancing spectrum utilization and overall system capacity. The study underscores the pivotal role of advanced detection methods like LSTM in improving throughput, reducing SNR requirements, and optimizing spectral efficiency for future optical OFDM-VLC communication systems.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: Not applicable.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: Not applicable.
-
Data availability: Not applicable.
References
1. Yao, H, Li, T, Song, Y, Ji, W, Liang, Y, Li, F. Low-complexity signal detection networks based on Gauss-Seidel iterative method for massive MIMO systems. EURASIP J. Adv. Signal Process. 2022;2022:51. https://doi.org/10.1186/s13634-022-00885-0.Search in Google Scholar
2. Kumar, A, Gaur, N, Gupta, M, Nanthaamornphong, A. Implementation of the deep learning method for signal detection in massive-MIMO-NOMA systems. Heliyon 2024;10:e25374. https://doi.org/10.1016/j.heliyon.2024.e25374.Search in Google Scholar PubMed PubMed Central
3. Huang, X, Yuan, Y, Li, J. MIMO signal detection based on IM-LSTMNet model. Electronics 2024;13:3153. https://doi.org/10.3390/electronics13163153.Search in Google Scholar
4. Altin, G. Deep neural network-based detection of index modulated MIMO-OFDM. Phys Commun 2022;52:101669. https://doi.org/10.1016/j.phycom.2022.101669.Search in Google Scholar
5. Jayawardana, PADN, Obaid, H, Yesilyurt, T, Tan, B, Lohan, ES. Machine-learning-based LOS detection for 5G signals with applications in airport environments. Sensors 2023;23:1470. https://doi.org/10.3390/s23031470.Search in Google Scholar PubMed PubMed Central
6. Yli-Kaakinen, J, Levanen, T, Valkonen, S, Pajukoski, K, Pirskanen, J, Renfors, M, et al.. Efficient fast-convolution-based waveform processing for 5G physical layer. IEEE J Sel Area Commun 2017;35:1309–26. https://doi.org/10.1109/JSAC.2017.2687358.Search in Google Scholar
7. Levanen, T, Pirskanen, J, Pajukoski, K, Renfors, M, Valkama, M. Transparent Tx and Rx waveform processing for 5G new radio Mobile communications. IEEE Wireless Commun 2019;26:128–36. https://doi.org/10.1109/MWC.2018.1800015.Search in Google Scholar
8. Kumar, A, Sharma, H, Gaur, N, Gour, N. PAPR analysis of 5G and B5G waveforms using advanced PAPR algorithms. IT Professional 2024;26:17–21. https://doi.org/10.1109/MITP.2024.3405824.Search in Google Scholar
9. Kumar, A, Nanthaamornphong, A, Alsharif, MH, Masud, M. SIC based RL for massive MIMO NOMA signal detection for different modulation schemes under diverse channel conditions. Sci Rep 2025;15:24641. https://doi.org/10.1038/s41598-025-06492-x.Search in Google Scholar PubMed PubMed Central
10. Ismail, H, Serhani, MA, Hussein, NM, Elhadef, M. RL-ECGNet: resource-aware multi-class detection of arrhythmia through reinforcement learning. Appl Intell 2023;53:30927–39. https://doi.org/10.1007/s10489-023-05147-6.Search in Google Scholar
11. Kumar, A, Alshahrani, HM, Alotaibi, F, Nanthaamornphong, A. A hybrid detection algorithm for 5G OTFS waveform for 64 and 256 QAM with Rayleigh and Rician channels. Open Eng 2024;14:20240008. https://doi.org/10.1515/eng-2024-0008.Search in Google Scholar
12. Wang, S, Ma, Z, Zhang, T. 5G OFDM Signal Design Approach for Target Detection. In: Dong, J, Zhang, L, (eds) Proceedings of the International Conference on Internet of Things, Communication and Intelligent Technology. IoTCIT 2022. Lecture Notes in Electrical Engineering, vol 1015. Singapore: Springer: 2023.10.1007/978-981-99-0416-7_20Search in Google Scholar
13. Kumar, A, Gaur, N, Nanthaamornphong, A. Signal detection of M-MIMO-orthogonal time frequency space modulation using hybrid algorithms: ZFE + MMSE and ZFE + MF. Results Eng 2024;24:103311. https://doi.org/10.1016/j.rineng.2024.103311.Search in Google Scholar
14. “Waveform design for 5G and beyond,” in 5G Networks: Fundamental Requirements, Enabling Technologies, and Operations Management, IEEE, 2018, pp.51–76.10.1002/9781119333142.ch2Search in Google Scholar
15. Kumar, A, Venkatesh, J, Gaur, N, Alsharif, MH, Jahid, A, Raju, K. Analysis of hybrid spectrum sensing for 5G and 6G waveforms. Electronics 2023;12:138. https://doi.org/10.3390/electronics12010138.Search in Google Scholar
16. Albreem, MA, Juntti, M, Shahabuddin, S, Abdallah, S, Alhabbash, A, Almajali, E. Data detection based on matrix decomposition for massive MIMO systems in realistic channel scenarios. Phys Commun 2023;57:101982. https://doi.org/10.1016/j.phycom.2022.101982.Search in Google Scholar
17. Gkonis, PK. A survey on machine learning techniques for massive MIMO configurations: application areas, performance limitations and future challenges. IEEE Access 2023;11:67–88. https://doi.org/10.1109/ACCESS.2022.3232855.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
