Building Energy and Comfort Optimization

Buildings account for roughly 40% of global energy use, and the gap between how they are designed to perform and how they actually perform in practice remains stubbornly wide. Researchers working at the intersection of thermal engineering, control theory, and data science study how heat moves through building envelopes, how occupants behave in ways that defrost even careful design assumptions, and how shifting climate patterns will reshape energy demand over the coming decades. Model predictive control and artificial neural networks are increasingly used to close that performance gap in real time — adjusting heating, cooling, and ventilation to balance energy use against occupant comfort rather than treating the two as fixed trade-offs. Open questions center on how to build occupant behavior models that generalize across cultures and building types, and on how to ensure that optimization strategies designed for today's climate remain robust as outdoor conditions continue to change.

Works

145,208

Total citations

1,640,112

Keywords

Building Energy ConsumptionThermal ComfortEnergy SimulationModel Predictive ControlSustainable BuildingsOccupant Behavior