BuildSTG: A Multi-building Energy Load Forecasting Method using Spatio-Temporal Graph Neural Network

Due to the extensive retention of building operation data, data-driven building load prediction methods have demonstrated powerful capabilities in forecasting building energy loads. Buildings with similar operating conditions, physical characteristics, and types often exhibit similar energy usage patterns, which are reflected in their operation data showing similar trends and spatial dependencies. However, conventional building load prediction methods have significant limitations in extracting these spatial dependencies. To address this challenge, this paper proposes a multi-building load prediction method based on spatio-temporal graph neural networks, which is divided into three main steps: graph representation, graph learning, and method interpretation. First, a graph representation method is developed that identifies building correlations based on intrinsic characteristics and environmental factors. Next, a multi-level spatiotemporal graph convolu-tional architecture with an attention mechanism is designed to predict energy loads for multiple buildings. Finally, a model interpretation method based on the optimal graph structure obtained from the training process is devel-Corresponding author Email address: ychen@eitech.edu.cn Experiments on the Building Data Genome Project 2 dataset validate that the proposed method outperforms commonly used baseline models like XGBoost, SVR, FCNN, GRU, and Na ıve in terms of prediction accuracy. Additionally, the model demonstrates strong robustness and generalization, performing reliably under uncertainty and unseen data. Visualization of the building similarity matrix confirms the model's interpretability, revealing its ability to group similar buildings and establish meaningful spatial dependencies, proving that the proposed Att-GCN method for learning spatial dependencies between buildings with similar energy usage patterns is both reasonable and interpretable. Introduction With urbanization increasing, building energy consumption and carbon emissions are growing. Construction and operation of buildings account for 34% of global energy use, with 30% from operations.