Building Energy Load Prediction By Using LS-SVM
This paper presents a least square support vector machine (LS-SVM) model to predict the heating and cooling
loads of a building based on simulation data for building energy performance. The dataset used in this study include the
overall height, relative compactness, surface area, wall area, roof area, orientation, glazing area, and glazing area distribution
of building. By using these variables as inputs, heating and cooling loads of building are estimated. There are a lot of
machine learning methods such as artificial neural networks (ANN) for this purpose in the literature. We investigate the
performance of LS-SVM as an estimator, which is a modified version of support vector machines (SVM). According to
obtained results, it is shown that the proposed LS-SVM based method can predict heating and cooling loads of building with
a very high accuracy rate.
Keywords— Heating Load, Cooling Load, Least Square Support Vector Machines.