EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Energy Demand Forecasting Using Temporal Variational Residual Network

Simachew Ashebir, Seongtae Kim

Forecasting · 12.08.2025 · 7 (3) · 42

DOI: 10.3390/forecast7030042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forecasting, online erschienen am 12.08.2025. Verfasst von Simachew Ashebir und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Alfred P. Sloan Foundation, NSF DMS-EiR.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The growing demand for efficient energy management has become essential for achieving sustainable development across social, economic, and environmental sectors. Accurate energy demand forecasting plays a pivotal role in energy management. However, energy demand data present unique challenges due to their complex characteristics, such as multi-seasonality, hidden structures, long-range dependency, irregularities, volatilities, and nonlinear patterns, making energy demand forecasting challenging. We propose a hybrid dimension reduction deep learning algorithm, Temporal Variational Residual Network (TVRN), to address these challenges and enhance forecasting performance. This model integrates variational autoencoders (VAEs), Residual Neural Networks (ResNets), and Bidirectional Long Short-Term Memory (BiLSTM) networks. TVRN employs VAEs for dimensionality reduction and noise filtering, ResNets to capture local, mid-level, and global features while tackling gradient vanishing issues in deeper networks, and BiLSTM to leverage past and future contexts for dynamic and accurate predictions. The performance of the proposed model is evaluated using energy consumption data, showing a significant improvement over traditional deep learning and hybrid models. For hourly forecasting, TVRN reduces root mean square error and mean absolute error, ranging from 19% to 86% compared to other models. Similarly, for daily energy consumption forecasting, this method outperforms existing models with an improvement in root mean square error and mean absolute error ranging from 30% to 95%. The proposed model significantly enhances the accuracy of energy demand forecasting by effectively addressing the complexities of multi-seasonality, hidden structures, and nonlinearity.

Förderung

  • Alfred P. Sloan Foundation
  • NSF DMS-EiR

Zitieren

APA

Ashebir, S., & Kim, S. (2025). Energy Demand Forecasting Using Temporal Variational Residual Network. Forecasting, 7(3), 42. https://doi.org/10.3390/forecast7030042

Vancouver

Ashebir S, Kim S. Energy Demand Forecasting Using Temporal Variational Residual Network. Forecasting. 2025;7(3):42. doi:10.3390/forecast7030042

BibTeX
@article{Ashebir2025,
  author = {Ashebir, Simachew and Kim, Seongtae},
  title = {Energy Demand Forecasting Using Temporal Variational Residual Network},
  journal = {Forecasting},
  year = {2025},
  volume = {7},
  number = {3},
  pages = {42},
  doi = {10.3390/forecast7030042}
}
Kostenlos starten →