Utilizing-External-Data-for-Enhancing-Building-Energy-Demand-Estimation-2023

Building energy demand estimation plays a crucial role in constructing energy-efficient building stocks. However, most studies adopting a data-driven approach feel the deficiency of datasets with building-specific information in building energy estimation. Considering the great potential to enhance the quality of inference from datasets, the research objective of this study is to increase the accuracy of data-driven models by incorporating additional features obtained from external data sources, such as weather data, natural hazard risk maps, and demographic data. To that end, the original and external datasets are utilized in feature extraction, and the buildings’ energy consumption is estimated using a nonparametric regression model. The results show that an 6% error reduction was achieved through the inclusion of new features, which indicates that feature extraction can be valuable in building energy demand estimation.