Uncertainty propagation under residual disturbances: a smart-home case study

Publikationstyp
Preprint
Date Issued
2026-05-15
Sprache
English
Author(s)
Pan, Guanru  
Regelungstechnik E-14  
Reinhardt, Dirk
Gros, Sebastien
Faulwasser, Timm  
Regelungstechnik E-14  
TORE-URI
https://hdl.handle.net/11420/63498
Citation
arXiv: 2605.15851 (2026)
Publisher DOI
10.48550/arXiv.2605.15851
ArXiv ID
2605.15851
This paper presents a data-driven framework for uncertainty propagation under unmeasured or statistically unmodeled (unstructured) disturbances. We consider residual disturbances, which consolidate all unstructured disturbances into a single quantity that can be estimated from data. Under mild assumptions, the resulting stochastic predictor is causal and distributionally consistent, enabling efficient uncertainty quantification through polynomial chaos expansions and higher-order Chebyshev inequalities. The proposed method is validated using experimental data from a smart home in Norway.
Subjects
eess.SY
DDC Class
600: Technology