In this study, a novel data-driven methodology is proposed to measure and verify energy efficiency savings, with a special focus on commercial buildings and facilities. The presented approach involves building use characterization by analysing typical consumption profile patterns and studying the building’s weather dependency. The characterization is then used to design a model able to provide accurate dynamic estimations of the achieved energy savings for the analyzed buildings. The method was tested on synthetic datasets generated using the building energy simulation software EnergyPlus and monitoring data from real-world buildings. The results obtained with the proposed methodology showed up to 10% CV(RMSE) improvement compared to a benchmark model. Similar accuracy was retained when the training data was reduced to less than a full operating year.

>>> Access the full article here