Enhancing buildings' energy efficiency prediction through advanced data fusion and fuzzy classification

Marc Grossouvre (1, 2, 3, 4) , Didier Rullière (1, 4, 3, 5) , Jonathan Villot (6, 7, 3, 4)

1 LIMOS - Laboratoire d'Informatique, de Modélisation et d'Optimisation des Systèmes
2 URBS
3 Mines Saint-Étienne MSE - École des Mines de Saint-Étienne
4 FAYOL-ENSMSE - Institut Henri Fayol
5 FAYOL-ENSMSE - Département Génie mathématique et industriel
6 FAYOL-ENSMSE - Département Génie de l’environnement pour les organisations
7 EVS - Environnement, Ville, Société

This study proposes a method to predict buildings' energy efficiency based on available descriptive information and without a physical visit, by merging diverse datasets and employing advanced classification techniques. By integrating geographical, structural, legal, and socio-economic data with Energy Performance Certificate (EPC) observations, our approach yields a rich learning set. Through variable selection methods like forward selection with KNN and simultaneous perturbation stochastic approximation for fuzzy KNN, we refine model variables. Comparing fuzzy and hard classification using KNN, Kriging or Random Forest approaches, we find fuzzy classification more adept at capturing nuanced energy inefficiency indicators. Our study highlights the importance of mass energy efficiency prediction for sustainable renovation efforts.

Mots clés: fuzzy classification; Kriging; constrained classification; spatial Prediction; energy efficiency; sustainability

Domaines: Méthodes et statistiques

Marc Grossouvre, Didier Rullière, Jonathan Villot. Enhancing buildings' energy efficiency prediction through advanced data fusion and fuzzy classification. Energy and Buildings, 2024, 313, pp.114243. ⟨10.1016/j.enbuild.2024.114243⟩. ⟨hal-04525194⟩