A ground-truth-aware simulation framework is introduced that separates the latent physical state from a corrupted sensing layer and compares practical control policies with an oracle controller. The model includes 20 zones, models occupancy-driven CO2 and ventilation-energy trade-offs, sensor drift, and missing data, allowing to assess the impact of sensing errors on closed-loop performance.
This is important as it highlights the need to account for data quality when evaluating digital twins, which affects the reliability of building control and other systems.
Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.
