Neural network-based peak power and throughput analysis of optical OFDM waveforms with 1024-QAM for high-capacity computer networks
-
Fateh Bahadur Kunwar
und
Aziz Nanthaamornphong
Abstract
This work presents a neural network-based framework for peak power suppression and throughput enhancement in optical OFDM systems employing 1024-QAM modulation for high-capacity computer networks. Optical OFDM signals inherently suffer from high peak-to-average power ratio (PAPR), which leads to nonlinear distortions in the optical channel and degrades bit error rate (BER) performance. To address this challenge, a convolutional neural network (CNN)-based scheme is proposed and evaluated under different subcarrier configurations. The analysis demonstrates that the proposed method consistently achieves significantly lower PAPR values, recording only 1.8 dB, 3.5 dB, and 5.5 dB at a complementary cumulative distribution function (CCDF) of 10−3 for 64, 256, and 512 subcarriers, respectively. In comparison, conventional schemes such as SLM, PTS, SVM, and RNN exhibit considerably higher PAPR levels. Similarly, BER performance analysis shows that the proposed method achieves target BER of 0.001 at 7 dB and 9 dB SNR for 256 and 512 subcarriers, representing up to 13 dB improvement over traditional techniques. These results confirm the robustness, scalability, and efficiency of the proposed NN framework in reducing peak power and improving signal reliability. The findings highlight its potential for integration into next-generation optical communication and computer networking systems requiring high spectral efficiency and energy efficiency.
-
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. Cinemre, I, Aydin, V, Hacioglu, G. PAPR reduction through Gaussian pre-coding in DCO-OFDM systems. Opt Quant Electron 2024;56:958. https://doi.org/10.1007/s11082-024-06911-9.Suche in Google Scholar
2. Niwareeba, R, Cox, MA, Cheng, L. PAPR reduction in optical OFDM using lexicographical permutations with low complexity. IEEE Access 2022;10:1706–13. https://doi.org/10.1109/ACCESS.2021.3138193.Suche in Google Scholar
3. Kumar, A, Rajagopal, K, Alruwais, N, Mesfer Alshahrani, H, Mahgoub, H, Othman, KM. PAPR reduction using SLM-PTS-CT hybrid PAPR method for optical NOMA waveform. Heliyon 2023;9. https://doi.org/10.1016/j.heliyon.2023.e20901.Suche in Google Scholar PubMed PubMed Central
4. Niwareeba, R, Cox, MA, Cheng, L. Adaptive-mode PAPR reduction algorithm for optical OFDM systems leveraging lexicographical permutations. Electronics 2023;12:2797. https://doi.org/10.3390/electronics12132797.Suche in Google Scholar
5. Mayakannan, A, Arvind, C, Dhinakar, P, Sasikala, G, Sathyasri, B, Srihari, K, et al.. Neural network-based regression assisted PAPR reduction method for OFDM systems. Sādhanā 2022;47:242. https://doi.org/10.1007/s12046-022-02024-9.Suche in Google Scholar
6. Kumar, A, Nanthaamornphong, A. Genetic algorithm-based PTS with CNN for PAPR and BER reduction in FBMC systems under fading channels. Ain Shams Eng J 2025;16. https://doi.org/10.1016/j.asej.2025.103434.Suche in Google Scholar
7. Ashraf, M, Abid, F, Din, IU, Rasheed, J, Yesiltepe, M, Yeo, SF, et al.. A hybrid CNN and RNN variant model for music classification. Appl Sci 2023;13:1476. https://doi.org/10.3390/app13031476.Suche in Google Scholar
8. Kumar, A, Gaur, N, Aly, AA, Nanthaamornphong, A. PAPR reduction of OTFS using an automatic amplitude reduction neural network with vendermonde matrix-based PTS and SLM algorithms. J Wireless Com Network 2024, 84. https://doi.org/10.1186/s13638-024-02414-z.Suche in Google Scholar
9. Bianca, S de C da Silva, Souto, VDP, Souza, RD, Mendes, LL. 2024. A survey of PAPR techniques based on machine learning. Sensors 1918;24. https://doi.org/10.3390/s24061918.Suche in Google Scholar PubMed PubMed Central
10. Bitra, H, Raj, N. OTFS: PAPR reduction using nonlinear companding transform. Int J Electron Lett 2023;12:281–94. https://doi.org/10.1080/21681724.2023.2289480.Suche in Google Scholar
11. Kumar, A, Gaur, N, Chakravarty, S, Nanthaamornphong, A. Reducing the PAPR of OTFS modulation using hybrid PAPR algorithms. Wirel Pers Commun 2023;133:2503–23. https://doi.org/10.1007/s11277-024-10885-y.Suche in Google Scholar
12. Bitra, H, Ponnusamy, P, Chintagunta, S, Pragadeshwaran, S. Nonlinear companding transforms for reducing the PAPR of OTFS signal. Phys Commun 2022;53. https://doi.org/10.1016/j.phycom.2022.101729.Suche in Google Scholar
13. Kumar, A, Nanthaamornphong, A, Gaur, N. Optimizing PAPR performance for 6G OTFS waveform using adaptive genetic PTS method for Rician fading channels. EURASIP J Appl Signal Process 2025;2025:22. https://doi.org/10.1186/s13634-025-01234-7.Suche in Google Scholar
14. Gopal, A, Krishna Reddy, D, Chintagunta, S. Symbol interferometry and companding transform for PAPR reduction of OTFS signal. ETRI J 2024;46:595–603. https://doi.org/10.4218/etrij.2023-0142.Suche in Google Scholar
15. Aziz, N, Kumar, A, Alamro, H, Alruwais, N, Allafi, R, Nemri, N, et al.. Enhancing OTFS modulation for 6G through hybrid PAPR reduction technique for different sub-carriers. Fractals 2024;32:2540014. https://doi.org/10.1142/s0218348x25400146.Suche in Google Scholar
16. Kumar, A, Aziz, N. NN-PTS: a neural network-assisted PAPR reduction technique for OTFS with high-order modulation. High Energy Density Phys 2025;56. https://doi.org/10.1016/j.hedp.2025.101225.Suche in Google Scholar
17. Mizutani, K, Ohta, M, Ueda, Y, Yamashita, K. A PAPR reduction of OFDM signal using neural networks with tone injection scheme. In: 2007 6th international conference on information, communications & signal processing, Singapore; 2007. p. 1–5.10.1109/ICICS.2007.4449855Suche in Google Scholar
18. Gendia, A, Muta, O. OFDM PAPR reduction via time-domain scattered sampling and hybrid batch training of synchronous neural networks. Electronics 2021;10:1708. https://doi.org/10.3390/electronics10141708.Suche in Google Scholar
19. Al Ahsan, R, Wuttisittikulkij, L. Artificial neural network (ANN) based classification of high and low PAPR OFDM signals. In: 2021 36th international technical conference on circuits/systems, computers and communications (ITC-CSCC), Jeju, Korea (South); 2021. p. 1–4.10.1109/ITC-CSCC52171.2021.9501484Suche in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
