Machine learning methods to forecast temperature in buildings

Efficient management of energy in buildings saves a very important amount of resources (both economic and technological). As a consequence, there is a very active research in this field. One of the keys of energy management is the prediction of the variables that directly affect building energy consumption and personal comfort. Among these variables, one can highlight the temperature in each room of a building. In this work we apply different machine learning techniques along with other classical ones for predicting the temperatures in different rooms. The obtained results demonstrate the validity of these techniques for predicting temperatures and, therefore, for the establishment of optimal policies of energy consumption.

► We compare linear and machine learning methods to predict indoor temperature.
► Clustering has been evaluated as a possible improvement of the methods.
► The MLP-NARX method obtained the best results with a mean error of nearly 0.1 °C.
► The best performing clustering algorithm was DBSCAN, but the improvement was small.