Sustainability Base

Modeling occupant behavior in smart buildings to reduce energy usage in a more accurate fashion has garnered
much recent attention in the literature. Predicting occupant comfort in buildings is a related and challenging
problem. In some smart buildings, such as NASA Ames Sustainability Base, there are discrepancies between
occupants’ actual thermal discomfort and sensors based upon a weighted average of wet bulb, dry
bulb, and mean radiant temperature intended to characterize thermal comfort. In this paper we attempt to find
other contributing factors to occupant discomfort. For our experiment we use a dataset from a Building Automation
System (BAS) in NASA Sustainability Base. We choose one conference room for our experiment and empirically establish the thermal discomfort level for the room’s temperature sensor. We use various causality metrics and causal graphs to isolate candidate causes of the target room temperature. And we compare these feature sets according to their predictive capability of future instances of discomfort. Moreover, we establish a trade off between computational and statistical performance of adverse event prediction.