Machine learning algorithm for time-series-based forecasting of hazards in electric transmission lines
Keywords:
transmission line, time series, risk forecasting, Random Forest, Logistic Regression, Gradient Boosting, early warning, SCADA, machine learning, fault predictionAbstract
The paper proposes a time-series-based machine-learning method for forecasting hazardous conditions in electric transmission lines before the actual fault occurs. A physically motivated synthetic telemetry dataset of 8,640 observations sampled every five minutes over 30 days was generated. Voltage, current, temperature, frequency, power factor and active-power lag, rolling-statistics and trend features were extracted. Logistic Regression, Random Forest and Gradient Boosting were compared. For a 30-minute early-warning task, the proposed 0.4 Logistic Regression + 0.6 Random Forest ensemble achieved F1=0.8895 and ROC-AUC=0.9888. All 21 test-period events were preceded by an alarm 15–25 minutes before the simulated fault onset
References
Belagoune, S., Bali, N., Bakdi, A., Baadji, B., & Atif, K. (2021). Deep learning through LSTM classification and regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power systems. Measurement, 177, 109330. https://doi.org/10.1016/j.measurement.2021.109330.
Rafique, F., Fu, L., & Mai, R. (2021). End to end machine learning for fault detection and classification in power transmission lines. Electric Power Systems Research, 199, 107430. https://doi.org/10.1016/j.epsr.2021.107430.
Tunio, M. F. et al. (2025). Performance Comparison Between Deep Learning Models for Fault Classification in Transmission Lines Using Time Series Data. Energy Science & Engineering. https://doi.org/10.1002/ese3.70033.
Balakrishnan, P. (2020). A new intelligent scheme for power system faults detection and classification: A hybrid technique. International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, 33.
Wu, X. et al. (2020). A novel intelligent fault identification method based on random forests for HVDC transmission lines. Scientific Reports, 10, 5142.
Intelligent fault diagnosis in power systems using Random Forest and ensemble learning. (2026). Measurement: Energy, 10, 100098. https://doi.org/10.1016/j.meaene.2026.100098.
Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324.
Momeni, M., Norouzi Nasab, A., & Abasi, M. (2026). Fault detection, classification, and location in transmission lines compensated with Unified Interphase Power Controller (UIPC) based on random forest algorithm. Measurement, 258, 119020. https://doi.org/10.1016/j.measurement.2025.119020.
Fonseca, G. A. et al. (2022). Fault Classification in Transmission Lines Using Random Forest and Notch Filter. Journal of Control, Automation and Electrical Systems, 33, 598–609. https://doi.org/10.1007/s40313-021-00844-4.
Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. https://doi.org/10.1016/j.patrec.2005.10.010.
Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21, 6. https://doi.org/10.1186/s12864-019-6413-7.
Tabassi, E. (2023). Artificial Intelligence Risk Management Framework (AI RMF 1.0). NIST AI 100-1. National Institute of Standards and Technology. https://doi.org/10.6028/NIST.AI.100-1.
ISO. (2018). ISO 50001:2018 Energy management systems — Requirements with guidance for use. International Organization for Standardization.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
