Forecasting building thermal demand using machine learning

Corcoran, Lloyd, Carr, Daniel and Ugalde Loo, Carlos ORCID: https://orcid.org/0000-0001-6361-4454 2026. Forecasting building thermal demand using machine learning. Presented at: 17th International Conference on Applied Energy (ICAE2025), Bangkok, Thailand, 8-12 December 2025. Energy Proceedings. , vol.63 Applied Energy Innovation Institute (AEii), 10.46855/energy-proceedings-12177

PDF - Published Version Available under License Creative Commons Attribution. Download (1MB)

Abstract

Rising summer temperatures in the UK, alongside stricter building regulations on thermal efficiency, are increasing the importance of residential cooling demand. While very few households currently use active cooling, adoption is expected to grow, placing additional pressure on electricity networks. This paper presents a study combining physics-based modelling with machine learning to forecast building thermal demand using basic dwelling characteristics and weather data. Results show that the method achieves high accuracy in predicting the thermal demand of previously unseen dwellings—showcasing the potential extreme gradient boosting may have in forecasting cooling demand in a warming world.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Engineering
Publisher:	Applied Energy Innovation Institute (AEii)
ISSN:	2004-2965
Date of First Compliant Deposit:	15 April 2026
Last Modified:	09 Jun 2026 15:41
URI:	https://orca.cardiff.ac.uk/id/eprint/186400

Actions (repository staff only)

Edit Item