Benchmarking Automated Machine Learning for Building Energy Performance Prediction: A Comparative Study with SHAP-Based Interpretability
Buildings · 01.01.2026 · 16 (1) · 185
DOI: 10.3390/buildings16010185 ↗Kurz gefasst
Fachartikel in der Zeitschrift Buildings, online erschienen am 01.01.2026. Verfasst von Zuyi Tang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The growing demand for energy-efficient buildings necessitates innovative approaches to reduce energy consumption during early design stages. While traditional physics-based simulations remain time- and expertise-intensive, automated machine learning (AutoML) offers a promising alternative by enabling data-driven building performance prediction with minimal human intervention. This study conducts a benchmark evaluation of AutoML’s potential in building energy applications through three objectives: (1) a literature review revealing AutoML’s nascent adoption (10 identified studies) and primary use cases (heating/cooling prediction, energy demand forecasting); (2) a benchmark comparing three AutoML frameworks (AutoGluon, H2O, Auto-sklearn) against baseline and ensemble ML models using R2, RMSE, MSE, and MAE metrics; and (3) SHAP (SHapley Additive exPlanations)-based interpretability analysis. Results demonstrate AutoGluon’s superior accuracy (R2 = 0.993, RMSE = 2.280 kWh/m2) in predicting energy performance, outperforming traditional methods. Key influential features, including solar heat gain coefficient (SHGC) and U-values, were identified through SHAP, offering actionable design insights. The primary novelty of this work lies in its two-step methodology: a focused review to identify pertinent AutoML frameworks, followed by a comparative benchmarking of these frameworks against traditional ML for early-stage prediction. This process substantiates AutoML’s potential to democratize energy modeling and deliver practical, interpretable workflows for architectural design.
Zitieren
APA
Tang, Z., Chen, J., & Cheng, J. (2026). Benchmarking Automated Machine Learning for Building Energy Performance Prediction: A Comparative Study with SHAP-Based Interpretability. Buildings, 16(1), 185. https://doi.org/10.3390/buildings16010185
Vancouver
Tang Z, Chen J, Cheng J. Benchmarking Automated Machine Learning for Building Energy Performance Prediction: A Comparative Study with SHAP-Based Interpretability. Buildings. 2026;16(1):185. doi:10.3390/buildings16010185
BibTeX
@article{Tang2026,
author = {Tang, Zuyi and Chen, Jinyu and Cheng, Jiayu},
title = {Benchmarking Automated Machine Learning for Building Energy Performance Prediction: A Comparative Study with SHAP-Based Interpretability},
journal = {Buildings},
year = {2026},
volume = {16},
number = {1},
pages = {185},
doi = {10.3390/buildings16010185}
}
EUVIMED