[论文解读] PowerGraph: A power grid benchmark dataset for graph neural networks
PowerGraph 提供一个公开的、基于图的级联故障数据集,覆盖 IEEE 与 UK 电网,用于图级任务和可解释性,支持 GNN 基准测试和边的真实解释。
Power grids are critical infrastructures of paramount importance to modern society and, therefore, engineered to operate under diverse conditions and failures. The ongoing energy transition poses new challenges for the decision-makers and system operators. Therefore, developing grid analysis algorithms is important for supporting reliable operations. These key tools include power flow analysis and system security analysis, both needed for effective operational and strategic planning. The literature review shows a growing trend of machine learning (ML) models that perform these analyses effectively. In particular, Graph Neural Networks (GNNs) stand out in such applications because of the graph-based structure of power grids. However, there is a lack of publicly available graph datasets for training and benchmarking ML models in electrical power grid applications. First, we present PowerGraph, which comprises GNN-tailored datasets for i) power flows, ii) optimal power flows, and iii) cascading failure analyses of power grids. Second, we provide ground-truth explanations for the cascading failure analysis. Finally, we perform a complete benchmarking of GNN methods for node-level and graph-level tasks and explainability. Overall, PowerGraph is a multifaceted GNN dataset for diverse tasks that includes power flow and fault scenarios with real-world explanations, providing a valuable resource for developing improved GNN models for node-level, graph-level tasks and explainability methods in power system modeling. The dataset is available at https://figshare.com/articles/dataset/PowerGraph/22820534 and the code at https://github.com/PowerGraph-Datasets.
研究动机与目标
- 提供一个基于数据驱动的工具,用于在线检测电网中的严重级联故障。
- 在 PyTorch Geometric 中公开可用于图级任务的数据集。
- 在电网图上支持二分类、多类分类和回归。
- 利用物理基础仿真的边掩码(真实边掩码)来支持可解释性基准测试。
提出的方法
- 使用 Cascades AC 基于物理的级联故障模型,在多组测试电网(IEEE24、IEEE39、UK、IEEE118)上模拟多样化的停电场景。
- 将每个停电前状态表示为一个图,其节点为母线、边为输电线,且对母线特征和边特征进行归一化。
- 生成一个按 DNS 结果标注的图数据集,用于不同任务(二分类、多类分类、回归)。
- 提供与级联阶段边对应的地面真相边解释,支持可解释性基准测试。
- 在图级任务上对 GNN 架构(GCN、GINe、GAT、Transformer)进行基准测试,并将可解释性方法与地面真相掩码进行对比分析。
![Figure 1 : Workflow of the Cascades [ 23 ] model, used to simulate cascading failures in power grids. Separate runs of Cascades are performed for the different test power grids namely, IEEE24, IEEE39, UK, and IEEE118.](https://ar5iv.labs.arxiv.org/html/2402.02827/assets/x1.png)
实验结果
研究问题
- RQ1GNN 是否能够从停电前的电网状态预测级联故障的发生(二分类)?
- RQ2GNN 是否能够区分详细的级联场景(多类分类)并预测最终 DNS(回归)?
- RQ3带边特征的电网图级任务中,不同 GNN 架构的性能如何?
- RQ4哪些可解释性方法能够如实将级联边识别为地面真相解释?
主要发现
- GCN、GINe、GAT 和 Transformer 在 PowerGraph 电网上的图分类任务中取得高性能;考虑边特征的模型优于忽略边特征的模型。
- Transformer 基于的模型在二分类和多类分类任务上在数据集上达到最先进结果。
- 回归模型在较小的电网上表现强劲,但在较大电网上滞后,表明需要在架构上取得进展以准确预测 DNS 的幅值。
- PowerGraph 是第一個具有地面真相解释的实际世界 GNN 数据集,用于电力系统的图级任务,可实现可解释性基准测试。
- 如 Saliency、Integrated Gradients、GradCAM、Occlusion 等可解释性方法在大多数数据集上显示出较高的平衡准确性和 fidelity+,但性能因电网规模和方法而异。

阅读本论文
在 Nubint 阅读器中打开原文,边读边就任意段落提问。
在 Nubint 中阅读本论文本解读由 AI 根据论文原文生成,引用前请核对原文。