Feature extraction and an interpretable hierarchical model for annual hourly electricity consumption profile of commercial buildings in China

Understanding and modeling building electricity consumption is paramount for demand-side decarbonization. Using a data-driven approach, this study proposes a hierarchical model to generate annual hourly electricity consumption profiles for commercial buildings, to facilitate energy system design and renewable energy integration. Electricity consumption profiles and the corresponding weather data from 55 commercial buildings across all five climate zones in China were collected to address the scarcity of relevant open datasets. Furthermore, periodicity and correlation analyses of the collected dataset indicate that the annual electricity consumption profiles can be decomposed into daily fluctuations primarily influenced by climate change and intraday fluctuations, which are predominantly affected by building schedules. Based on these features, suitable algorithms were selected to address the issues independently in these two temporal paradigms, forming a hierarchical model. A regression tree was used to reveal the relationships between daily consumption and weather data as well as the climate zone label. Additionally, k-means clustering was employed to extract typical intra-day consumption patterns, followed by the deployment of a classification tree to predict intra-day pattern labels under specific conditions. In the cross-validation, the proposed hierarchical model achieved a high coefficient of determination (R2) of 0.941, which further improved to 0.949 after incorporating residual regression, demonstrating its high accuracy. Compared to the single-step gradient boosting decision tree (GBDT) model (R2 = 0.951), the proposed hierarchical model exhibited comparable accuracy and offered better interpretability and lower overall complexity, making it a favorable choice for engineering applications. This study provides insights into the development of a data-driven model for building electricity consumption profiles.