Development of a method to predict building energy consumption through an artificial neural network approach

The main objective of this study is to develop a more accurate method to estimate the energy consumption of commercial buildings at the design stage. The study is based on the simplified model presented in the Regulation for Energy Efficiency Labelling of Commercial Buildings in Brazil. The first step was to evaluate the feasibility and relevance of more complex statistical modelling techniques, such as the neural network. The second step of the assessment consisted of applying the Latin Hypercube sampling technique to combine the effects of several input parameters. Therefore, results of this work may have a profound impact as artificial neural network may be applied in the future in the Brazilian regulation and many other countries.