Electric Load Forecasting for a Quicklime Company Using a Temporal Fusion Transformer
Algorithms · 10.03.2026 · 19 (3) · 208
DOI: 10.3390/a19030208 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 10.03.2026. Verfasst von Jersson X. Leon-Medina und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Colombian ministry of science innovation and technology-Minciencias, FONDO FRANCISCO JOSÉ DE CALDAS.
Abstract (Originalsprache)
Accurate short-term electric load forecasting is essential for the operation and management of energy-intensive manufacturing processes such as quicklime production, for which power demand is driven by stage-based operation, fixed schedules, and abrupt load transitions. This study presents a data-driven forecasting framework based on a Temporal Fusion Transformer (TFT) model applied to real industrial measurements collected during 2024 from an operating quicklime production plant. The dataset comprises hourly average power demand records (kW) measured at a plant level, stage-dependent motor operation, and a fixed working schedule from 08:00 to 18:00 (Monday to Friday), with weekends and non-operational hours characterized by near-zero load. Coke consumption during the calcination stage is included as an additional contextual variable. The TFT model is trained for multi-horizon forecasting and provides probabilistic prediction intervals through quantile regression. Weekly evaluations demonstrate that the proposed approach accurately captures start–stop behavior, peak-load periods, and structured inactivity intervals. In addition to point-wise accuracy metrics, cumulative energy is evaluated by integrating hourly power over the forecasting horizon, allowing the assessment of energy preservation at the operational level. The resulting energy deviation reaches 4.78% for the full horizon and 5.25% when restricted to active production hours, confirming strong consistency between predicted and actual cumulative energy. A comparative analysis against LSTM, GRU, and N-BEATS models shows that recurrent architectures achieve lower MAE and RMSE values, while the TFT model delivers superior cumulative energy consistency, highlighting a trade-off between instantaneous accuracy and operational energy fidelity. Overall, the results demonstrate that the proposed TFT-based framework provides a robust and practically relevant solution for short-term industrial electric load forecasting and decision support in stage-driven manufacturing systems under real operating conditions.
Förderung
- Colombian ministry of science innovation and technology-Minciencias
- FONDO FRANCISCO JOSÉ DE CALDAS
Zitieren
APA
Leon-Medina, J. X., Tibaduiza, D. A., Celys, C. P. S., Suarez, B. U., & Pozo, F. (2026). Electric Load Forecasting for a Quicklime Company Using a Temporal Fusion Transformer. Algorithms, 19(3), 208. https://doi.org/10.3390/a19030208
Vancouver
Leon-Medina JX, Tibaduiza DA, Celys CPS, Suarez BU, Pozo F. Electric Load Forecasting for a Quicklime Company Using a Temporal Fusion Transformer. Algorithms. 2026;19(3):208. doi:10.3390/a19030208
BibTeX
@article{LeonMedina2026,
author = {Leon-Medina, Jersson X. and Tibaduiza, Diego A. and Celys, Claudia Patricia Siachoque and Suarez, Bernardo Umbarila and Pozo, Francesc},
title = {Electric Load Forecasting for a Quicklime Company Using a Temporal Fusion Transformer},
journal = {Algorithms},
year = {2026},
volume = {19},
number = {3},
pages = {208},
doi = {10.3390/a19030208}
}
EUVIMED