A new study introduces adaptive data-driven models set to transform thermal comfort assessment and control in buildings. The research explores new approaches to predicting thermal comfort, a crucial factor influencing both occupant well-being and energy consumption in buildings.

A data-driven model was developed based on an extensive dataset of 61,710 samples from ASHRAE databases. The resulting models are two, on with higher accuracy, while the other, a simplified version, outperforms traditional regression models and the Predicted Mean Vote (PMV) approach.

What sets these models apart is their incorporation of adaptive processes and consideration of influential parameters such as air temperature, mean radiant temperature, relative humidity, air velocity, clothing insulation, metabolic rate, and outdoor monthly air temperature.