Development and Optimization of Artificial Neural Network Algorithms in the Prediction of Ambient Temperature

Projet de modélisation
Échelles spatiales
Échelles temporelles

The cloud-based smart dual fuel switching system (SDFSS) for hybrid heating, ventilation and air conditioning (HVAC) systems being developed enables flexible and cost-optimized control between the natural gas furnace and air source heat pump (ASHP), allowing simultaneous reduction in energy costs and greenhouse gas (GHG) emissions. This study introduces a novel approach to obtaining the outdoor temperature that could potentially replace smart sensors with a data-driven model utilizing weather station data at time resolutions of 2 minutes and 1 hour.  This model is applicable world-wide but more appropriate for cold North American Climate due to the nature of our Smart Dual Fuel Switching System.


Demirezen, G., & Fung, A. S. (2019). Application of artificial neural network in the prediction of ambient temperature for a cloud-based smart dual fuel switching system. Energy Procedia, 158, 3070-3075.


hvac industry, thermostat companies

Intrants clés

ambient temperature from various weather stations, weather related parameters such as wind speed, humidity

Extrants clés

Ambient Temperature