Machine learning based on raw ensemble predictions scheme for TWDM-PON
-
Fay F. Ridha
und
Ali H. Abdulhadi
Abstract
As optical communication systems have developed quickly, more sophisticated methods that were previously only used for long-distance transmissions having progressively navigated into systems with faster speeds are needed for a variety of applications, including mobile front haul and optical access networks. Machine learning (ML) is a technique that has garnered significant attention in the field of short-optical reach communications for applications such as passive optical network (PON), indoor wireless communications, and signal processing due to its adaptability, high accuracy, and implementation efficiency. This work focuses on ML and neural networks (NN) techniques that is applicable to complicated systems and optimization. The datasets for different classifiers and classification features need to be trained and tested utilizing raw ensemble predictions, a calibration phase starts after the raw ensemble predictions are finished in order to assess the accuracy of the predictions made in the preceding phase and make any necessary improvements. The proposed ML methods use a database, which was validated utilizing experimental derived data from the TWDM-PON system to estimate the Q-factor, logarithm of bit error rate (Log(BER)), and receiver sensitivity. The classifier accuracy of the mean absolute error (MAE), mean squared error (MSE), and the coefficient of determination (R2) results from simulations are performed utilizing Python.
-
Research ethics: The local Institutional Review Board deemed the study exempt from review if the IRB specifically exempted the study from review.
-
Informed consent: Informed consent was obtained from all individuals included in this study, or their legal guardians or wards.
-
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: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: Not applicable.
References
1. Mikaeil, AM, Hu, W, Ye, T, Hussain, SB. Performance evaluation of XG-PON based mobile front-haul transport in cloud-RAN architecture. J Opt Commun Netw 2017;9:984–94. https://doi.org/10.1364/jocn.9.000984.Suche in Google Scholar
2. Abdulla, EN, Abass, AK, Abdulkafi, AA. Asymmetric 160/80 Gbps TWDM PON utilizing dispersion compensation technique. J Opt 2022;52:1683–93. https://doi.org/10.1007/s12596-022-00991-0.Suche in Google Scholar
3. Abdulla, EN, Hussien, RA, Rashid, FF, Abdulkafi, AA, Abass, AK, Saleh, MA. Design and performance analysis of symmetrical 160 Gbps TWDM-PON utilizing bidirectional configuration. J Opt 2023;53:1106–19. https://doi.org/10.1007/s12596-023-01263-1.Suche in Google Scholar
4. Abdulla, EN, Abass, AK, Abdulkafi, AA. Asymmetric 160/80 Gb/s TWDM PON with supported transmission method utilizing FBG and DML. J Opt Commun 2022;8–12.10.1515/joc-2022-0225Suche in Google Scholar
5. Pakpahan, AF, Hwang, IS. Peer-to-Peer federated learning on software-defined optical access network. IEEE Access 2024;12:84435–51. https://doi.org/10.1109/access.2024.3411639.Suche in Google Scholar
6. Liang, S, Zhao, F, Jiang, W. A learning algorithm for TWDM-PON’ DWBA with 5G fronthaul networks. Opt Fiber Technol 2019;53:102039. https://doi.org/10.1016/j.yofte.2019.102039.Suche in Google Scholar
7. Al-Saidi, NM, Ali, MH, Al-Azzawi, WKH, Abass, AK. Secure optical communication using a new 5D chaotic stream segmentation. Int J Sustain Dev Plann 2022;17:1553–60. https://doi.org/10.18280/ijsdp.170519.Suche in Google Scholar
8. Mousa, E, Abdulla, EN, Adnan, SA. Enhancing network security based on 10G-EPON with the use of the Hill cipher algorithm. J Opt Commun 2025;1–13.10.1515/joc-2025-0201Suche in Google Scholar
9. Mushatet, AF, Fadil, EA, Abdulla, EN. High bit rate secure FSO system utilizing Hill coding. J Opt Commun 2025:1–14. https://doi.org/10.1515/joc-2025-0147.Suche in Google Scholar
10. Fadil, EA, Tahhan, SR, Rashid, FF, Abass, AK, Salman, LA, Abdulla, EN, et al.. Design and performance analysis of optical communication system utilizing optical chaos. J Opt 2024;53:2435–40. https://doi.org/10.1007/s12596-023-01401-9.Suche in Google Scholar
11. Radhi, SS, Hussien, RA, Abdulla, EN, Abass, AK, Rashid, FF. Design a secure TWDM-PON via the Hill cipher algorithm. Opt Contin 2025;4:1051–64. https://doi.org/10.1364/optcon.558674.Suche in Google Scholar
12. Abdulla, EN, Radhi, SS, Rashid, FF, Hussien, RA, Salih, MM, Abass, AK, et al.. Security improvement for TWDM-PON utilizing blowfish cryptography. Appl Opt 2024;63. https://doi.org/10.1364/ao.537254.Suche in Google Scholar
13. Musadaq, R, Abdulwahid, SN, Abd Alwahed, NN, Abdulla, EN. Security analysis of an image encryption algorithm based on Blowfish in GPON. J Opt Commun 2025;32–34.10.1515/joc-2025-0109Suche in Google Scholar
14. Muller, J, Patri, SK, Fehenberger, T, Mas-Machuca, C, Griesser, H, Elbers, JP. A QoT estimation method using EGN-assisted machine learning for network planning applications. In: 2021 Eur. Conf. Opt. Commun. ECOC; 2021.10.1109/ECOC52684.2021.9606064Suche in Google Scholar
15. Yu, J, Mo, W, Huang, YK, Ip, E, Kilper, DC. Model transfer of QoT prediction in optical networks based on artificial neural networks. J Opt Commun Netw 2019;11:C48–57. https://doi.org/10.1364/jocn.11.000c48.Suche in Google Scholar
16. Jiang, W, Qian, Q, Yong, W, Kumar, R, Wu, J, Zhang, H. Application of no-light fault prediction of PON based on deep learning method. Comput Commun 2023;208:210–19. https://doi.org/10.1016/j.comcom.2023.06.002.Suche in Google Scholar
17. Butt, RA, Faheem, M, Arfeen, A, Ashraf, MW, Jawed, M. Machine learning based dynamic load balancing DWBA scheme for TWDM PON. Opt Fiber Technol 2019;52:101964. https://doi.org/10.1016/j.yofte.2019.101964.Suche in Google Scholar
18. Hussien, RA, Radhi, SS, Rashid, FF, Abdulla, EN, Abass, AK. Design and performance analysis of secure optical communication system by implementing blowfish cipher algorithm. Results Opt 2024;16:100708. https://doi.org/10.1016/j.rio.2024.100708.Suche in Google Scholar
19. Systems, D. ITU-T. Recommendation TELECOMMUNICATION STANDARDIZATION SECTOR OF ITU-T G.989.2; 2020:2 p.Suche in Google Scholar
20. Abdulla, EN, Abdulla, N. Synthetic optical network dataset with Q-factor, BER, and receiver sensitivity metrics under EDFA-FBG conditions. Mendeley Data 2025. https://doi.org/10.17632/b46c6c9fj9.2.Suche in Google Scholar
21. Price, I, Sanchez-Gonzalez, A, Alet, F, Andersson, TR, El-Kadi, A, Masters, D, et al.. Probabilistic weather forecasting with machine learning. Nature 2025;637:84–90. https://doi.org/10.1038/s41586-024-08252-9.Suche in Google Scholar PubMed PubMed Central
22. Sbai, Z. Deep learning models and their ensembles for robust agricultural yield prediction in Saudi arabia. Sustain Times 2025;17:1–26. https://doi.org/10.3390/su17135807.Suche in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
