Environmental factors, such as climate change, have serious consequences for existing buildings, including increased resource consumption and footprint, adverse health effects, and reduced comfort for the occupants. To promote sustainability and address climate change, architecture must embrace digitalization. Buildings can be built digitally, analyzed in real time, optimized for energy consumption, and utilized to reduce carbon emissions and achieve zero energy consumption using digital twin technology. Currently, Lebanon’s residents are turning to solar power to generate renewable energy as a result of a lack of energy supplied by the government. In this study, a digital twin model was designed using an artificial neural network (ANN) to investigate the energy consumption of residential buildings. The main idea was to assist architects and engineers in forecasting energy consumption for different design materials by selecting the most effective alternate design for materials with building envelope characteristics, such as exterior walls, roof insulation, and windows, to minimize the consumption of energy in a residential building, hence resulting in a green building. The data simulations used in the digital twin model were carried out using Quick Energy Simulation Tool (eQuest) software; 1540 simulation results were used for different thicknesses of insulation material, values of conductivity, and window types. The digital twins were designed using an artificial neural network model. The results of the investigation and the accompanying eQuest output results were found to be precise and very similar.

This paper presents a Smart Building Energy Model of Residential Building using Artificial Neural Network model (ANN) to assist architects and engineers in selecting the optimum alternative design of building envelope parameters such that external wall and roof insulation material types and window types that minimizes the cost of energy consumption of a residential building to transform it to a green building. Up to 1540 Simulations using different material thickness and conductivity values of material insulation properties and windows types are carried out in eQuest software for simulation.. The simulations results are implemented to create an artificial neural network inverse model (ANN) with Matlab/Simulink and the performance is investigated. The results from the artificial neural network outputs and the corresponding eQuest simulation outputs were found very close. In addition, the Mean absolute percentage error (MAPE) is equal to 0.49% , demonstrating a best correlation between outputs and target value, the results show a great solution with good accuracy to predict the energy consumption of residential building for several other building envelope optimization parameters. .