用图神经网络捕捉多栋建筑间能耗关联，提升预测精度。
BuildSTG: A Multi-building Energy Load Forecasting Method using Spatio-Temporal Graph Neural Network
- 基于建筑特征与环境构建时空图，编码空间依赖关系
- 多层图卷积结合注意力机制，显著优于传统模型
- 可解释图结构，识别真实建筑相似性与关联模式
由于运行数据的广泛可用，数据驱动方法在建筑能耗预测中表现出强大能力。具有相似特征的建筑通常共享能耗模式，这体现在其运行数据中的空间依赖关系上，而传统预测方法难以捕捉此类关系。为此，我们提出一种基于时空图神经网络的多建筑预测方法，包含图表示、图学习和可解释性三个部分。首先，根据建筑特征与环境因素构建图结构；其次，设计一种融合注意力机制的多层级图卷积架构进行能耗预测；最后，引入方法解释优化后的图结构。在Building Data Genome Project 2数据集上的实验表明，该方法在性能上显著优于XGBoost、SVR、FCNN、GRU和Naive等基线模型，展现出更强的鲁棒性、泛化能力与可解释性，有效捕捉有意义的建筑相似性与空间关系。
原文摘要 · Abstract (English)
Due to the extensive availability of operation data, data-driven methods show strong capabilities in predicting building energy loads. Buildings with similar features often share energy patterns, reflected by spatial dependencies in their operational data, which conventional prediction methods struggle to capture. To overcome this, we propose a multi-building prediction approach using spatio-temporal graph neural networks, comprising graph representation, graph learning, and interpretation. First, a graph is built based on building characteristics and environmental factors. Next, a multi-level graph convolutional architecture with attention is developed for energy prediction. Lastly, a method interpreting the optimized graph structure is introduced. Experiments on the Building Data Genome Project 2 dataset confirm superior performance over baselines such as XGBoost, SVR, FCNN, GRU, and Naive, highlighting the method's robustness, generalization, and interpretability in capturing meaningful building similarities and spatial relationships.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。