Secondary-Side Heating Component Inference: Dataset and Reproducibility Package

The archive provides all year-2023 hourly data required to reproduce the results:

District heating (DH)

Domestic hot water (DHW)

Air-handling unit (AHU) fan electricity

Space heating (SH)

Floor heating (FH)

Outdoor temperature

These measurements support the construction of the residual target rt+r_t^{+}rt+, weak labels, and subsystem-specific training/validation used in the paper.

The package also includes:

Preprocessing scripts and notebooks (data alignment, quality control, residual target, and weekly structure checks)

Weak labeling pipeline for DHW and AHU, including confidence weights

Model training and statistical validation notebooks

Regression, identifiability, and separation metrics

Code to reproduce all figures in Section 3.6 (e.g., R² plots, mutual information, distributional distances, Δ-metrics)

All materials are provided under the Creative Commons Attribution 4.0 International (CC-BY-4.0) license and may be reused with proper attribution.

This dataset enables full transparency and reproducibility of the proposed weakly supervised heating-component inference framework and serves as a reference benchmark for future research in data-driven building-energy analytics.