Applying machine learning algorithms to group the energy performance of existing buildings by different granularity level of energy data

Recent technology advancement has extended smart-metering capability, enabling measurement of fine-grained building energy consumption. These massive energy data provide options to apply machinelearning in building energy analysis. However, the energy details needed depend on the building feature being analyzed. Unlike system faults and user-related inefficiencies, degradation in building thermal performance results in a steady energy increase that can be reflected even with coarse-grained energy data. This study assesses whether energy data of low temporal resolution can be used to provide insight into building energy efficiency. It evaluates the application of machine learning in clustering buildings based on their thermal characteristics using energy data of different time intervals. Through k-means clustering, buildings are clustered using their hourly, daily, and monthly heating energy. The results indicate that all three granularities can identify buildings with high window transmittances and infiltration rates. These findings present an opportunity for applying machine learning not only for modern buildings with advanced metering systems but also for aging buildings that makes the majority of the existing building stock. The study presents a practical method to identify and prioritize buildings for energy retrofit, an important step toward an effective energy upgrade of a large-scale building using machine learning.