Comparative analysis of deep learning and tree-based models in power demand prediction: Accuracy, interpretability, and computational efficiency
Journal of Building Physics · 2025-07 · 49 (1) · 127-169
DOI: 10.1177/17442591251333144 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Building Physics, online erschienen am 10.06.2025. Verfasst von Bowen Yang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil and Environmental Engineering, University of Alberta, Edmonton, AB, Canada. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Research and development have demonstrated that effective building energy prediction is significant for enhancing energy efficiency and ensuring grid reliability. Many machine learning (ML) models, particularly deep learning (DL) approaches, are widely used for power or peak demand forecasting. However, evaluating prediction models solely based on accuracy is insufficient, as complex models often suffer from low interpretability and high computational costs, making them difficult to implement in real-world applications. This study proposes a multi-perspective evaluation analysis that includes prediction accuracy (both overall and at different power levels), interpretability (global/local perspectives and model structure), and computational efficiency. Three popular DL models—recurrent neural network, gated recurrent unit, long short-term memory, and three tree-based models—random forecast, extreme gradient boosting, and light gradient boosting machine—are analyzed due to their popularity and high prediction accuracy in the field of power demand prediction. The comparison reveals the following: (1) The best-performing prediction model changes under different power demand levels. In scenarios with lower power usage patterns, tree-based models achieve an average CV-RMSE of 13.62%, which is comparable to the 12.17% average CV-RMSE of DL models. (2) Global and local interpretations indicate that past power use and time-related features are the most important. Tree-based models excel at identifying which specific lagged features are more significant. (3) The DL model behavior can be interpreted by visualizing the hidden state at each layer to reveal how the model captures temporal dynamics across different time steps. However, tree-based models are more intuitive to interpret using straightforward decision rules and structures. This study provides guidance for applying ML algorithms to load forecasting, offering multiple perspectives on model selection trade-offs.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Civil and Environmental Engineering, University of Alberta, Edmonton, AB, Canada.
ORCID-Profile: Bowen Yang
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Yang, B., Gül, M., & Chen, Y. (2025). Comparative analysis of deep learning and tree-based models in power demand prediction: Accuracy, interpretability, and computational efficiency. Journal of Building Physics, 49(1), 127-169. https://doi.org/10.1177/17442591251333144
Vancouver
Yang B, Gül M, Chen Y. Comparative analysis of deep learning and tree-based models in power demand prediction: Accuracy, interpretability, and computational efficiency. Journal of Building Physics. 2025;49(1):127-169. doi:10.1177/17442591251333144
BibTeX
@article{Yang2025,
author = {Yang, Bowen and Gül, Mustafa and Chen, Yuxiang},
title = {Comparative analysis of deep learning and tree-based models in power demand prediction: Accuracy, interpretability, and computational efficiency},
journal = {Journal of Building Physics},
year = {2025},
volume = {49},
number = {1},
pages = {127--169},
doi = {10.1177/17442591251333144}
}
EUVIMED