ARX Models Inspired By Physics As a Service For Building's Users

Lisa Scanu (1) , Stéphane Ploix (2) , Pierre Bernaud (3) , Étienne Wurtz (4)

1 G-SCOP_GCSP - Gestion et Conduite des Systèmes de Production
2 G-SCOP - Laboratoire des sciences pour la conception, l'optimisation et la production
3 DTS - Département des Technologies Solaires
4 CEA, LITEN, Service bâtiment et systèmes thermiques, Le Bourget du Lac, France

Recently, in the field of building energy efficiency, many works focused on model based energy management services but developing models consistent with a measured reality is still an issue. Fine physical models with many parameters cannot be adjusted while non-physical models cannot extrapolate to situations never met in the training data. In this paper, pure data models will be implemented with ARX models. In a second time, physical knowledge is added in order to improve the accuracy especially in the cross-validation process. These models are applied to a mono-zone study case in order to forecast the indoor CO2 concentration.

Mots clés: energy management; parameter estimation; building model; occupants / users; simulation

Domaines: Intelligence artificielle [cs.AI]

Lisa Scanu, Stéphane Ploix, Pierre Bernaud, Étienne Wurtz. ARX Models Inspired By Physics As a Service For Building's Users. 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Sep 2017, Bucharest, Romania, France. ⟨10.1109/IDAACS.2017.8095184⟩. ⟨hal-01917093⟩