Author(s): Mariana Akemi Ikegawa Bernabe; Rafael Gonzalez Perea; Juan Antonio Rodriguez Diaz; Jorge Garcia Morillo
Linked Author(s):
Keywords: Artificial intelligence; Deep learning; Energy resource management; Renewable energy; Time series forecasting; Transformer neural network
Abstract: This study evaluates a Transformer-based model for hourly, medium-term energy demand (ED) forecasting across four heterogeneous end-users: aquaculture, irrigation, port, and community. Using fuzzy logic (FL) and correlation analysis, 7 to 12 input variables. The model achieved high accuracy in all cases (R² > 97%), demonstrating robustness to diverse consumption patterns and input configurations. Slight differences were linked to data quality and demand variability. These results confirm the adaptability of Transformer architectures for reliable energy forecasting, supporting efficient resource management across multiple sectors.
Year: 2026