A decomposition-ensemble prediction method of building thermal load with enhanced electrical load information

Abstract

Accurate thermal load forecasting is essential for intelligent building energy management. The lack of meteorological data and the variability of thermal load often result in low prediction accuracy of thermal load. This paper proposes a novel decomposition-ensemble prediction model to predict thermal load accurately when the meteorological parameters are missing. The model combines the variational mode decomposition technology and the gated recurrent unit algorithm, in which the information of electrical load is extracted and considered to assist the thermal load prediction. The two datasets of an office building and a museum building are employed to train and test the model. The case results demonstrate that the variational mode decomposition method can effectively decrease the prediction uncertainty for thermal load series. The advantages of the proposed model have better prediction performance than the basic and hybrid models.