Application of ANN for the prediction of building energy consumption at different climate zones with HDD and CDD

Abstract

In order to find a fast and effective method to predict building energy consumption at different climate zones, this paper used artificial neural network (ANN) for this prediction with 20 input parameters, including 18 building envelope performance parameters, heating degree day (HDD) and cooling degree day (CDD). A backpropagation neural network has been preferred and the data have been presented to network by being normalized. Application studies of seven cases were carried out with ANN and conventional methods. Results show that ANN predicts building energy consumption easily and quickly, which gives satisfactory results with successful prediction rate of over 96%, compared with conventional methods, and the application of this ANN is extended largely to be used in other climate zones with the consideration of HDD and CDD as parts of input parameters.