It is used to derive five fuzzy ‘if-then’ rules that govern the processing a set of input variables to produce a single predicted output. The output is then compared to the measured values to test the accuracy of the model. Each input variable is linked to five parameterized Gaussian-shaped membership functions (MFs) that represent its fuzzy linguistic labels (i.e.very low, low, medium, high and very high). The details of the MF parameters and the learning algorithms involved are not discussed here as the emphasis is given to the specific case of building energy forecasting.