Transfer learning for cross-building forecasting of building energy and indoor air temperature in model predictive control applications
Published in Journal of Building Engineering, 2025
Download the paper here When applying Model Predictive Control (MPC) for Heating, Ventilation and Air Conditioning (HVAC) systems in buildings, accurate forecasting of short-term energy demand and indoor air condition profiles is essential. However, new or retrofitted buildings lack sufficient operation data to develop precise data-driven models. This study investigates transfer learning techniques to enhance the forecasting performance of black-box models under limited data conditions. Specifically, we leverage synthetic data from an open-source EnergyPlus building model to pre-train three neural network models, which are then transferred to a real building and fine-tuned with limited measurements. The results indicate that incorporating synthetic data into the pre-training phase significantly enhances the forecasting accuracy for building and HVAC energy, as well as indoor air temperature profiles, over a 12-h horizon with 15-min intervals. The study underscores the potential of combining transfer learning with synthetic data to address data limitations, extending the applicability of learning-based MPC in real-world buildings. Recommended citation: Dou, H., Zhang, K., 2025. Transfer learning for cross-building forecasting of building energy and indoor air temperature in model predictive control applications. Journal of Building Engineering 111, 113341. https://doi.org/10.1016/j.jobe.2025.113341 Read more