Development and implementation of a thermostat learning algorithm

AbstractIn this paper, the thermostat keypress actions with concurrent occupancy, temperature, and relative humidity data in private office spaces were analyzed. We observed that the occupants interact with their thermostats infrequently (on average once every 56 h of occupancy); and when they did so, occupants changed the temperature setpoint on average by 1°C. We observed that about one third of the thermostat overrides were either to decrease the setpoints during the heating season or to increase the setpoints during the cooling season. The temperatures leading to the thermostat overrides changed by ∼3°C seasonally. It was noted that the frequency of thermostat interactions can be approximated as a univariate logistic regression model that inputs the indoor temperature as the predictor variable. A recursive algorithm was formulated to develop univariate thermostat use models inside building controllers. It was implemented inside four commercial controllers serving seven private office spaces to choose ...