Predicting and forecasting building energy performance using RSM and ANN

Climate change, unpredictability in occupant behavior, and the deterioration of building materials are all sources of uncertainty in the optimization process. This paper investigates Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) modeling in building energy estimation and proposes models that incorporate data classifications to improve performance. The RSM method allowed the development of some simple relationships to determine the best parameters and the design for a generic building by forecasting the energy results. To begin, one of the most widely used BIM tools, Revit, is used to create a virtual replica of an actual building. Then, an energy simulation program called Green Building Studio imports the model via Extensible Markup Language (Gbxml), and the RSM and ANN are performed for the obtained energy results with confirming an R 2. This study's energy analysis concludes that alternative parameters could provide more energy-efficient and cost-effective buildings compared to conventional design parameters. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.