[论文解读] Times Series Forecasting for Urban Building Energy Consumption Based on Graph Convolutional Network

Yuqing Hu, Xiaoyuan Cheng+4 more|arXiv (Cornell University)|May 27, 2021

Energy Load and Power Forecasting参考文献 53被引用 5

一句话总结

本文提出一种基于图卷积网络的模型（ST-GCN），通过捕捉建筑间的相互依赖关系和时空动态特性，以提升城市建筑能耗预测的准确性。在亚特兰大市中心一所大学校园的实证研究中，ST-GCN模型优于传统时间序列模型，通过嵌入物理知识，展现出更高的预测精度与可解释性。

ABSTRACT

The world is increasingly urbanizing and the building industry accounts for more than 40% of energy consumption in the United States. To improve urban sustainability, many cities adopt ambitious energy-saving strategies through retrofitting existing buildings and constructing new communities. In this situation, an accurate urban building energy model (UBEM) is the foundation to support the design of energy-efficient communities. However, current UBEM are limited in their abilities to capture the inter-building interdependency due to their dynamic and non-linear characteristics. Those models either ignored or oversimplified these building interdependencies, which can substantially affect the accuracy of urban energy modeling. To fill the research gap, this study proposes a novel data-driven UBEM synthesizing the solar-based building interdependency and spatial-temporal graph convolutional network (ST-GCN) algorithm. Especially, we took a university campus located in downtown Atlanta as an example to predict the hourly energy consumption. Furthermore, we tested the feasibility of the proposed model by comparing the performance of the ST-GCN model with other common time-series machine learning models. The results indicate that the ST-GCN model overall outperforms all others. In addition, the physical knowledge embedded in the model is well interpreted. After discussion, it is found that data-driven models integrated engineering or physical knowledge can significantly improve the urban building energy simulation.

研究动机与目标

• 为解决现有城市建筑能耗模型在捕捉动态、非线性建筑间依赖关系方面的局限性。
• 开发一种数据驱动模型，将物理知识与图卷积网络相结合，以提升预测精度。
• 在真实城市能源场景中，评估所提出的ST-GCN模型相较于传统时间序列机器学习模型的性能表现。

提出的方法

• 基于太阳辐射暴露和建筑间距，构建反映建筑关系的空间图，以编码物理层面的相互依赖关系。
• 采用时空图卷积网络（ST-GCN）来建模建筑之间的时序动态与空间相关性。
• 利用亚特兰大市中心一所大学校园的逐小时能耗数据对模型进行训练。
• 将物理知识（如太阳辐照度和建筑朝向）嵌入图结构中，以提升模型的可解释性与性能。
• ST-GCN框架利用图卷积层，随时间聚合邻近建筑的特征信息。
• 通过均方根误差（RMSE）和平均绝对误差（MAE）等指标，将模型性能与LSTM、GRU和XGBoost等标准时间序列模型进行对比评估。

实验结果

研究问题

• RQ1 图卷积网络能否有效建模城市能耗预测中的建筑间依赖关系？
• RQ2 将物理知识（如太阳辐射暴露）整合进模型，能否提升数据驱动能耗模型的预测精度与可解释性？
• RQ3 所提出的ST-GCN模型是否在城市建筑能耗预测中优于传统时间序列模型？

主要发现

• ST-GCN模型在所有对比模型中实现了最低的RMSE和MAE，表明其具有更优的预测精度。
• 在图结构中引入物理知识显著提升了模型的可解释性与性能表现。
• 该模型有效捕捉了传统模型无法表征的复杂非线性建筑间依赖关系。
• 在案例研究中，ST-GCN模型在不同时间尺度和气象条件下均表现出良好的鲁棒性。
• 结果证实，将工程与物理知识融入数据驱动模型，可显著提升城市能耗模拟的准确性。