Benchmarking performance of machine-learning methods for building energy demand modelling

Abstract

The relevance, relative importance and colinearity of input parameters to the results of building energy demand forecasts were investigated. Two calendar years of historical data including weather variables and days of the week were used. The study also aimed to assess the performance of multiple-linear-regression, support-vector-machine and artificial-neural-network models for predicting the daily heating, ventilation and air-conditioning energy consumption of a commercial building in France. Mean absolute error, root-mean-square error and coefficient of variation of root-mean-square error were selected as the performance criteria. The results showed that the best performance was achieved through the artificial-neural-network model according to all performance measures. Besides, the other two models were not able to meet the prediction requirements for energy consumption in a building since their coefficient-of-variation-of-root-mean-square-error values were not below 30%. The results also indicated that there was multiple colinearity between the number of degree days and outdoor temperature. Furthermore, the most significant parameter for daily energy consumption was found to be the number of degree days, followed by global radiation, sunshine rate and the day of the week.