Combining physics-based and data-driven modeling for building energy systems

Building energy modeling plays a vital role in optimizing the operation of building energy systems by providing accurate predictions of the building’s real-world conditions. In this context, various techniques have been explored, ranging from traditional physics-based models to data-driven models. Recently, researchers are combining physics-based and data-driven models into hybrid approaches. This includes using the physics-based model output as additional data-driven input, learning the residual between physics-based model and real data, learning a surrogate of the physics-based model, or fine-tuning a surrogate model with real data. However, a comprehensive comparison of the inherent advantages of these hybrid approaches is still missing. The primary objective of this work is to evaluate four predominant hybrid approaches in building energy modeling through a real-world case study, with focus on indoor thermodynamics. To achieve this, we devise three scenarios reflecting common levels of building documentation and sensor availability, assess their performance, and analyze their explainability using hierarchical Shapley values. The real-world study reveals three notable findings. First, greater building documentation and sensor availability lead to higher prediction accuracy for hybrid approaches. Second, the performance of hybrid approaches depends on the type of building room, but the residual approach using a Feedforward Neural Network as data-driven sub-model performs best on average across all rooms. This hybrid approach also demonstrates a superior ability to leverage the simulation from the physics-based sub-model. Third, hierarchical Shapley values prove to be an effective tool for explaining and improving hybrid models while accounting for input correlations. • We enhance the understanding of hybrid building energy models by investigating and comparing four predominant hybrid approaches across three challenging real-world scenarios, each characterized by varying levels of building documentation and sensor data availability. • We apply a hierarchical Shapley value framework to an agglomerative clustering analysis using Pearson’s distance metric, providing valuable insights into the nature of hybrid models while accounting for the correlations. This also allows to investigate potential model biases of the physics-based part such as a bias at higher outdoor temperatures. • We examine and compare performance of the four hybrid approaches in a limited training data setting, offering a detailed analysis of their dependency on data quantity and their robustness under constrained conditions.