This study presents a hybrid UBEM by integrating the strengths of dynamic and statistical models. This novel model can generate hourly synthetic energy consumption data for urban building stocks by incorporating building characteristics and local weather data while ensuring the dynamic model’s reliability with parametric optimization. The methodology involves the following steps: (1) A dynamic model is created, and its key parameters are optimized according to monthly metered data. (2) The optimized dynamic model is then utilized to generate synthetic hourly energy consumption data. (3) Finally, statistical models are trained on synthetic data to analyze the impact of building characteristics and weather conditions on hourly building energy consumption. Once the proposed methodology is tested on a university campus, the optimization reduces the monthly simulation error to an 11.4% Coefficient of Variation of the Root Mean Square Error (CV-RMSE), and the final statistical model predicts the hourly building energy consumption with a 5.4% CV-RMSE.
