High-Capacity Conductor Data-Based Models for Dynamic Rating of Electrical Lines
Julio J. Melero, M.Paz Comech, José F. Sanz Instituto Universitario de Investigación Mixto de la Energía y la Eficiencia de los Recursos de Aragón, ENERGAIA Universidad de Zaragoza-Fundación CIRCE, Zaragoza, Spain. 2026-06-27

Abstract

Accurate estimation of overhead conductor temperature is a key requirement for reliable dynamic line rating (DLR) and enhanced utilization of transmission networks. This paper presents a data-driven framework based on XGBoost
regression to predict conductor temperature from electrical loading and meteorological variables. Hyperparameters are optimized using an Optuna-based search with controlled model complexity to ensure robust generalization. Model interpretability is addressed through SHAP analysis, which confirms that the learned relationships are physically consistent with established IEEE 738 and CIGRÉ thermal principles. To quantify predictive uncertainty, conformal prediction is integrated, providing statistically valid temperature intervals that support risk-aware ampacity assessment. The proposed approach achieves high predictive accuracy on real-world data while delivering transparent and reliable uncertainty estimates. Results demonstrate that the framework is a practical and scalable solution for DLR applications, enabling increased line utilization without compromising thermal safety margins.

Key words: Overhead transmission lines, ampacity, conductor temperature, weather parameters, machine
learning.

References

[1] E. Fernandez, I. Albizu, A. J. Mazon, A. Etxegarai, G. Buigues, and R. Alberdi, "Power line monitoring for the
analysis of overhead line rating forecasting methods," in 2016 IEEE PES PowerAfrica, 2016, pp. 119–123. doi:
10.1109/PowerAfrica.2016.7556583.

[2] R. Martinez et al., "Dynamic rating management of overhead transmission lines operating under multiple weather conditions," Energies (Basel), vol. 14, no. 4, Feb. 2021, doi: 10.3390/en14041136.

[3] F. Ye and J. Teh, "Dynamic thermal rating in power systems: A comprehensive review of techniques,
implementation and reliability," Renewable and Sustainable Energy Reviews, vol. 226, p. 116392, Jan. 2026, doi:
10.1016/j.rser.2025.116392.

[4] X. Zhou, S. Wang, T. Li, J. Cao, Y. Zou, and X. Xiang, "Probabilistic Ampacity Rating of 500kV Overhead
Transmission Lines in Zhejiang Province," in 2018 IEEE 3rd International Conference on Integrated Circuits and
Microsystems (ICICM), 2018, pp. 98–103. doi: 10.1109/ICAM 2018.8596438.

[5] C. Holyk, H. D. Liess, S. Grondel, H. Kanbach, and F. Loos, "Simulation and measurement of the steady-state
temperature in multi-core cables," Electric Power Systems Research, vol. 116, pp. 54–66, Nov. 2014, doi:
10.1016/J.EPSR.2014.05.001.

[6] IEEE Std 738-2012; IEEE Standard for Calculating the Current-Temperature Relationship of Bare Overhead
Conductors. IEEE.Power and Energy Society: Piscataway, NJ, USA, 2013; pp. 1–72; Revision of IEEE Std 738-
2006/IEEE Std 738-2012/Cor 1-2013.

[7] Dale, D.; Vincent, M.; Rob, S.; Mark, B.; Dzevad, M.; Ralf, P.; Daniel, G.; Sidnei, U.; Kresimir, B.; Sven, H.; et al.
CIGRÉ 601; Guide For Thermal Rating Calculations of Overhead Lines; CIGRÉ: Paris, France, 2014.

[8] A. Arroyo et al., "Comparison between IEEE and CIGRÉ thermal behaviour standards and measured temperature on
a 132-kV overhead power line," Energies (Basel), vol. 8, no. 12, pp. 13660–13671, 2015, doi: 10.3390/en81212391.

[9] N. Viafora, K. Morozovska, S. H. H. Kazmi, T. Laneryd, P. Hilber, and J. Holbøll, "Day-ahead dispatch optimization with dynamic thermal rating of transformers and overhead lines," Electric Power Systems Research, vol. 171, pp. 194–208, Jun. 2019, doi: 10.1016/j.epsr.2019.02.026.

[10] L. Vejo et al., "Experimental Study of Dynamic Line Rating Applied to High-Temperature Low-Sag Conductors," Energies (Basel), vol. 18, no. 4, Feb. 2025, doi: 10.3390/en18040929.

[11] M. Jalilian, J. R. Riba, and P. Parvizi, "Aluminum Conductor Steel-Supported Conductors for the Sustainable
Growth of Power Line Capacity: A Review and Discussion," Sep. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/ma17184536.

[12] J. R. Riba, "The Role of AC Resistance of Bare Stranded Conductors for Developing Dynamic Line Rating
Approaches," Applied Sciences (Switzerland), vol. 14, no. 19, Oct. 2024, doi: 10.3390/app14198982.

[13] L. Vejo, "Current and temperature measurements for a HTLS Conductor based in Santander ," Dec. 2024,
Zenodo. doi: 10.5281/zenodo.14274381.

[14] T. ; T. R. ; F. J. H. Hastie, "Boosting and additive trees," in The Elements of Statistical Learning, 2nd ed., New York:
Springer, 2009, pp. 337–384.

[15] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proceedings of the ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Aug.
2016, pp. 785–794. doi: 10.1145/2939672.2939785.

[16] A. Gammerman, V. Vovk, and V. Vapnik, "Learning by transduction," in Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, in UAI'98. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 1998, pp. 148–155.

[17] A. N. Angelopoulos and S. Bates, "A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty
Quantification," Dec. 2022, [Online]. Available: http://arxiv.org/abs/2107.07511

[18] S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," in Proceedings of the 31st
International Conference on Neural Information Processing Systems, in NIPS'17. Red Hook, NY, USA: Curran Associates Inc., 2017, pp. 4768–4777.

[19] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, "Optuna: A Next-generation Hyperparameter Optimization
Framework," in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Jul. 2019, pp. 2623–2631. doi: 10.1145/3292500.3330701.