Heating energy demand estimation of the EU building stock: Combining building physics and artificial neural networks

The aim of this study is to present a novel data-driven approach for heating energy demand calculations of the EU building stock. To develop an efficient bottom-up model that takes into account building physics parameters and details of the building stock make-up, while remaining computationally efficient, an artificial neural network (ANN) is trained on a dataset of precise building-physics models. A high accuracy and good accordance with measured consumption from Eurostat confirmed the adequacy of the adopted methodology, additionally emphasizing the importance of considering the actual indoor air temperature (set-point temperature), the amount of heated floor space and the fuel poverty in specific EU countries. In addition to the country level, the implemented bottom-up approach is suitable for assessing the energy demand at regional level. Overall, the present approach is considered as an accurate and reliable tool to be used in future research and sets a solid basis for evaluation studies on the long-term impact of building renovation with respect to energy savings and reductions of greenhouse gas emissions.

VELJKOVIC Ana;  POHORYLES Daniel;  BOURNAS Dionysios; 

2023-12-15

ELSEVIER SCIENCE SA

JRC133641

0378-7788 (online),   

https://www.sciencedirect.com/science/article/pii/S0378778823007041,    https://publications.jrc.ec.europa.eu/repository/handle/JRC133641,   

10.1016/j.enbuild.2023.113474 (online),