A dynamic-pretraining and online-adaptation HVAC controller with physics losses and long-term setpoint scoring achieves roughly 0.03-0.18°C average error and transfers between similar real buildings in about a week.
Development of an ann-based building energy model for information-poor buildings using transfer learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Model-Based Transfer Learning for Dynamic HVAC Control
A dynamic-pretraining and online-adaptation HVAC controller with physics losses and long-term setpoint scoring achieves roughly 0.03-0.18°C average error and transfers between similar real buildings in about a week.