EUVIMEDEUVIMED entdecken
Crossref

A Novel Hybrid Model for Dynamic Line Rating Using Artificial Neural Networks

A. Alarcon, I. Sanz, A. Lostale, P. Inda, M.G. Cañete, S. Borroy, A.P. Talayero

Energies and Quality Journal · 2026-07 · 4 (2) · 113-117

DOI: 10.24084/eqj26-287 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies and Quality Journal, 2026-07. Verfasst von A. Alarcon und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamic Line Rating (DLR) is a smart grid technology that calculates the real-time, maximum power capacity (ampacity) of transmission lines based on current environmental conditions. DLR allows higher, safe power flows, making a better use of the line’s actual capacity and thus allowing for the integration of more renewables. This document presents a hybrid architecture that combines the physical IEEE 738 standard with advanced deep learning techniques, Long Short-Term Memory Neural Networks (LSTM) and Physics‑Informed Neural Networks (PINNs), to predict the thermal ampacity of overhead transmission lines. The architecture of the neural networks is capable of learning complex patterns from historical climatological data. This enables the model to capture the temporal and stochastic evolution of environmental conditions. Through this data‑driven learning process, the DLR system can significantly reduce the reliance on field sensors, and in some cases even operate with minimal or no sensing infrastructure, by inferring the necessary conditions directly from historical and meteorological inputs. While the traditional IEEE 738 approach is deterministic and static, providing only point estimates under fixed conditions, modern power system operation demands dynamic forecasts, uncertainty management, and physical consistency, motivating the integration of physical models with deep learning. Key words. Ampacity, Climatological Conditions, Sensorless, Grid congestions.

Zitieren

APA

Alarcon, A., Sanz, I., Lostale, A., Inda, P., Cañete, M., Borroy, S., & Talayero, A. (2026). A Novel Hybrid Model for Dynamic Line Rating Using Artificial Neural Networks. Energies and Quality Journal, 4(2), 113-117. https://doi.org/10.24084/eqj26-287

Vancouver

Alarcon A, Sanz I, Lostale A, Inda P, Cañete M, Borroy S, et al. A Novel Hybrid Model for Dynamic Line Rating Using Artificial Neural Networks. Energies and Quality Journal. 2026;4(2):113-117. doi:10.24084/eqj26-287

BibTeX
@article{Alarcon2026,
  author = {Alarcon, A. and Sanz, I. and Lostale, A. and Inda, P. and Cañete, M.G. and Borroy, S. and Talayero, A.P.},
  title = {A Novel Hybrid Model for Dynamic Line Rating Using Artificial Neural Networks},
  journal = {Energies and Quality Journal},
  year = {2026},
  volume = {4},
  number = {2},
  pages = {113--117},
  doi = {10.24084/eqj26-287}
}
Kostenlos starten →