Support vector regression for predicting building energy consumption in southern China

It is increasingly significant to predict building energy consumption in energy-saving decision making. This paper presents the method of support vector regress (SVR) to forecast building energy consumption in southern China. To improve the reliability of SVR in building energy consumption prediction, multiple parameters including weather data such as yearly mean outdoor drybulb temperature, relative humidity and global solar radiation and economic factors such as the ratio of urbanization, gross domestic product, household consumption level and total area of structure are taken as inputs. The performance of SVR with respect to two parameters, c and g, is explored using the k-fold cross validation with grid searching method based on radial-basis function kernel. Finally, the performance of the proposed model is checked by comparing the prediction model with statistic data taken from Chinese National Bureau of Statistics in 4 provinces of southern China using statistical error tests such as the mean square error (MSE) and the squared correlation coefficient (r2). With the analysis based on statistical error tests, the results show that the SVR method can estimate the building energy consumption with good accuracy with MSE less than 0.001 and r2 more than 0.99. (C) 2019 The Authors. Published by Elsevier Ltd.