The purpose of this paper is to evaluate the performance of a novel office temperature control system. To make occupants more comfortable with less energy, we have been developing a new system that uses an inexpensive infrared camera to evaluate occupants’ thermal sensation and optimize room temperature. The system (1) detects the positions of a person’s face, nose, and hands in a thermal image taken by an infrared camera and measures temperatures in those areas; (2) predicts thermal sensation using measured skin temperatures; and (3) adjusts an HVAC set-point temperature based on the predicted sensation to optimize occupant thermal comfort. We compared the comfort and energy performance of the new system to conventional control using a fixed setpoint of 72.0 °F (22.2 °C) in a small conference room. The results indicate that the conventional control often overcooled the occupants, whereas our system reduced cooling energy consumption and made the occupants more thermally neutral and comfortable than the conventional control.

To improve occupant comfort and save energy in buildings, we have developed a closed-loop air conditioning (AC) sensor-controller that predicts occupant thermal sensation from the thermographic measurement of skin temperature distribution, then uses this information to reduce overcooling (cooling-energy overuse that discomforts occupants) by regulating AC output. Taking measures to protect privacy, it combines thermal-infrared (TIR) and color (visible spectrum) cameras with machine vision to measure the skin-surface temperature profile. Since the human thermoregulation system uses skin blood flow to maintain thermoneutrality, the distribution of skin temperature can be used to predict warm, neutral, and cool thermal states. We conducted a series of human-subject thermal-sensation trials in cold-to-hot environments, measuring skin temperatures and recording thermal sensation votes. We then trained random-forest classification machine-learning models (classifiers) to estimate thermal sensation from skin temperatures or skin-temperature differences. The estimated thermal sensation was input to a proportional integral (PI) control algorithm for the AC, targeting a sensation level between neutral and warm. Our sensor-controller includes a sensor assembly, server software, and client software. The server software orients the cameras and transmits images to the client software, which in turn assesses occupant skin temperature distribution, estimates occupant thermal sensation, and controls AC operation. A demonstration conducted in a conference room in an office building near Houston, TX showed that our system reduced overcooling, decreasing AC load by 42% when the room was occupied while improving occupant comfort (fraction of “comfortable” votes) by 15 percentage points.