In a real-building benchmark, residual learning with a quantile neural network outperforms other hybrid physics/data approaches for probabilistic indoor temperature prediction, and conformalized quantile regression improves interval calibration.
Probabilistic indoor temperature forecasting: A new approach using bernstein- polynomial normalizing flows
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SY 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Integrating Physics-Based and Data-Driven Approaches for Probabilistic Building Energy Modeling
In a real-building benchmark, residual learning with a quantile neural network outperforms other hybrid physics/data approaches for probabilistic indoor temperature prediction, and conformalized quantile regression improves interval calibration.