Predicting Indoor Temperature using Machine Learning

Modelling project


D. Yu, A. Abhari, A.S. Fung, K. Raahemifar, F. Mohammadi, “Predicting indoor temperature from smart thermostat and weather forecast data”, Proceedings of the Communications and Networking Symposium, Baltimore, 2018.

Danilo Yu


Using the ecobee thermostat data from sixteen Canadian and US houses, the prediction accuracy of the generalized regression neural network (GRNN) algorithm and the resilient back propagation neural network (ANN) algorithm were evaluated. The physical range of this model encompasses a single building.


residential building demand, load forecasting

Key Inputs

outdoor temperature, solar radiation, thermostat temperature setpoints, humidity, heating and cooling durations, fan duration

Key Outputs

indoor temperature

Registered developers

Danilo YuRyerson University