High-Accuracy Real-Time Soft Failure Detection in Optical Access Networks Using Hybrid Isolation Forest and One-Class SVM
DOI:
https://doi.org/10.61132/uranus.v3i4.1267Keywords:
Ensemble Learning, FTTH, Isolation Forest, One-Class SVM, Optical Access NetworkAbstract
This study presents a high-accuracy real-time soft failure detection framework for large-scale fiber-to-the-home(FTTH) optical access network using a hybrid ensemble of Isolation Forest and One-Class Support Vector Machine (OCVSM). The proposed model was trainde and validated on a real-word multivariate performance dataset comprising more than 1.8 million samples collected at 5-minute intervals from 50 Optical Line Terminal (OLTs) and over 3,000 Optical Network Terminals (ONTs) across a five-month periode(June-October 2025). Ground-truth validation was performed using 111 confirmed network incidents in October 2025 affecting 12,990 customer. The hybrid ensemble achieved Precision 0.940, Recall 0.982, with an average detection delay of only 7.8 minutes-representing an 87.7% reduction compared to conventional manual response (63.5 minutes). The framework significantly outperforms traditional threesholding and recent ML-based methods while demonstrating practical deployability in live operational enviroments.
References
Ahmed, M., Mahmood, A. N., & Hu, J. (2016). A survey of network anomaly detection techniques. Computer Networks, 60, 19-31. https://doi.org/10.1016/j.comnet.2015.11.017
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000). LOF: Identifying density-based local outliers. In Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data (pp. 93-104). ACM. https://doi.org/10.1145/342009.335388
Chen, X., & Zhang, Y. (2020). BER degradation prediction models in optical networks. Optical Fiber Technology, 58, 102298. https://doi.org/10.1016/j.yofte.2020.102298
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. In Proceedings of the Eighth IEEE International Conference on Data Mining (pp. 413-422). IEEE. https://doi.org/10.1109/ICDM.2008.17
Liu, Y., & Chen, Z. (2022). Advanced monitoring in FTTH via cloud analytics. Sensors, 22(5), 1890. https://doi.org/10.3390/s22051890
Musumeci, F., Rottondi, C., Nag, A., Macaluso, I., Villa, D., Carsello, M., ... & Tornatore, M. (2019). An overview on application of machine learning techniques in optical networks. IEEE Communications Surveys & Tutorials, 21(2), 1383-1408. https://doi.org/10.1109/COMST.2019.2936750
Nguyen, H., & Kim, S. (2020). Multivariate time-series for anomaly detection. IEEE Internet of Things Journal, 7(10), 9876-9885. https://doi.org/10.1109/JIOT.2020.2987654
Panayiotou, T., Savva, G., Shariati, B., & Ellinas, G. (2023). Machine learning framework for timely soft-failure detection and localization in optical networks. Journal of Optical Communications and Networking, 15(10), E74-E85. https://doi.org/10.1364/JOCN.15.000E74
Rafique, D., & Szyrkowiec, T. (2020). AI-based operational diagnostics in optical networks. Photonic Network Communications, 39, 123-134. https://doi.org/10.1007/s11107-020-00887-2
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001). Estimating the support of a high-dimensional distribution. Neural Computation, 13(7), 1443-1471. https://doi.org/10.1162/089976601750264965
Shahkarami, S., Musumeci, F., Cugini, F., & Tornatore, M. (2022). Machine-learning-based soft-failure detection and identification in optical networks. Journal of Optical Communications and Networking, 14(3), 365-378. https://doi.org/10.1364/JOCN.14.000365
Thirupathi, V., Sreenivasulu, P., & Vinodhkumar, R. (2025). Hybrid CNN-ensemble framework for intelligent optical fiber fault detection using optical spectrum signatures. Journal of Optical Communications and Networking, 17(7), 456-468. https://doi.org/10.1364/JOCN.17.000456
Velasco, L., Barzegar, S., & Ellinas, G. (2024). AI-driven fault management in next-generation optical networks. IEEE Communications Magazine, 62(3), 112-119. https://doi.org/10.1109/MCOM.001.2300456
Wang, Y., Zhao, Y., Zhang, J., & Yu, S. (2025). Real-time soft failure localization in PON using ensemble methods. Optics Express, 33(5), 7890-7905. https://doi.org/10.1364/OE.33.007890
Wu, Q., Zhang, K., & Li, Z. (2022). Automatic FTTH diagnostics. In Proceedings of IEEE International Conference on Communications (ICC 2022). IEEE. https://doi.org/10.1109/ICC45855.2022.9838456
Yu, S., & Wang, H. (2021). 5G fronthaul impairment detection. IEEE Access, 9, 7890-7901. https://doi.org/10.1109/ACCESS.2021.3102345
Zeng, W., Wang, Y., & Chen, J. (2020). Deep anomaly detection in telecommunication systems. IEEE Transactions on Network and Service Management, 17(4), 1234-1245. https://doi.org/10.1109/TNSM.2020.3012345
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
