Machine learning to predict building energy performance in different climates

• Published in: IOP conference series. Earth and environmental science 2022-09, Vol.1078 (1), p.12137
• Main Authors: Aruta, G, Ascione, F, Boettcher, O, De Masi, R F, Mauro, G M, Vanoli, G P
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Autoregressive models; building performance simulation; Buildings; Climate; Construction; Construction industry; Deep learning; Design optimization; Digital twins; Digitization; Energy; Energy transition; green buildings; Heating load; Learning algorithms; Machine learning; Neural networks; Software; space conditioning; Space heating; Thermal energy; Urban development; Urban sprawl; Weather; zero-energy buildings
• ISSN: 1755-1307; 1755-1315
• DOI: 10.1088/1755-1315/1078/1/012137

Digitalization is sweeping the world of buildings. Notably, the use of machine and deep learning techniques to develop buildings’ digital twins is becoming crucial to foster the energy transition of the construction sector and a sustainable urban growth. Digital twins can ensure a user-friendly, fast and reliable prediction of building energy loads and demands, thereby enabling a comprehensive optimization of planning, design and operation. Accordingly, this study investigates machine learning techniques to predict heating loads of a building in Rome (Italy, Mediterranean conditions, “Csa” climate in the Köppen and Geiger classification) and in Berlin (Germany, European backcountry, “Cfb”). Firstly, the real building, located in Benevento, is used to develop the artificial neural networks (ANNs), then implemented in MATLAB® to achieve meta-models of building energy behavior. NARX (nonlinear autoregressive model with exogenous inputs) networks are used and trained based on simulated data, provided by the well-known building simulation tool EnergyPlus using the software DesignBuilder® as interface. The meta-model inputs are related to weather conditions, while the required outputs concern the thermal energy load for space heating. The analysis is performed with reference to annual forecasts of energy demands. In all cases, the ANNs architecture is optimized to achieve the best fitness with EnergyPlus outputs. The results show that machine learning can be a precious and reliable tool to support energy design and operation of different buildings in different climates. Nonetheless, the meta-modeling procedure needs to be properly conducted by experts to set suitable frameworks and hyperparameter values of the ANNs, as well as to achieve a right and comprehensive interpretation of the results.