Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces BuilDyn, a Python package built on BuilDa, designed to generate training data with customizable excitation strategies for building thermal dynamics modeling. By actively exploring the control-driven system state space, BuilDyn addresses the limitations of existing datasets that primarily reflect stationary operation. Experiments demonstrate that ML models trained on BuilDyn-generated, excited data outperform those trained on non-excited data for building thermal dynamics modeling.
Forget passively observing building operations; actively *excite* your building models with control-oriented data generation to unlock better performance and generalization.
Machine learning (ML) is increasingly used for data-driven modeling of buildings to enable downstream tasks such as fault detection and diagnosis, and energy-efficient control. While recent work improves generalization across building characteristics, weather, and occupancy, generalization also depends on sufficient exploration of the control-driven system state space. Existing real-world datasets and simulation environments predominantly reflect stationary operation under fixed control policies, resulting in limited excitation and reduced robustness to unseen operating conditions. This paper introduces BuilDyn, a package based on BuilDa that enables customizable excitation strategies for control-oriented data generation. BuilDyn further supports sampling from representative building distributions and provides a Python interface for easy integration into machine learning pipelines. We demonstrate the benefits of BuilDyn by comparing the performance of data-driven ML models trained on non-excited and excited data for one building. With BuilDyn, we hope to advance scalable control-oriented modeling and support future directions such as transfer learning and building-specific foundation models.