用图注意力网络预测飓风导致的大规模停电恢复时间
Graph Attention Network for Predicting Duration of Large-Scale Power Outages Induced by Natural Disasters
- 构建图神经网络捕捉电网区域间的空间依赖关系
- 在8个州501个县数据上准确率超93%，优于传统方法2%-15%
- 适合电力系统韧性研究与灾害应急决策者使用
飓风、野火和冬季风暴等自然灾害在美国引发了大规模停电，造成巨大经济与社会影响。准确预测停电恢复时间和影响范围对电网韧性至关重要。机器学习为利用地理空间与气象数据估算停电持续时间提供了可行框架。然而，实际场景中存在三大挑战：数据的空间依赖性、影响的空间异质性以及事件数据有限。本文提出一种基于图注意力网络（GAT）的新方法，通过无监督预训练加半监督学习的简单结构实现。模型使用四次重大飓风影响的8个东南部州共501个县的实地数据。结果表明，该模型整体性能与类别准确率均超过93%，在整体表现和各类别准确率上均比XGBoost、随机森林、GCN和简单GAT提升2%至15%。
原文摘要 · Abstract (English)
Natural disasters such as hurricanes, wildfires, and winter storms have induced large-scale power outages in the U.S., resulting in tremendous economic and societal impacts. Accurately predicting power outage recovery and impact is key to resilience of power grid. Recent advances in machine learning offer viable frameworks for estimating power outage duration from geospatial and weather data. However, three major challenges are inherent to the task in a real world setting: spatial dependency of the data, spatial heterogeneity of the impact, and moderate event data. We propose a novel approach to estimate the duration of severe weather-induced power outages through Graph Attention Networks (GAT). Our network uses a simple structure from unsupervised pre-training, followed by semi-supervised learning. We use field data from four major hurricanes affecting $501$ counties in eight Southeastern U.S. states. The model exhibits an excellent performance ($>93\%$ accuracy) and outperforms the existing methods XGBoost, Random Forest, GCN and simple GAT by $2\% - 15\%$ in both the overall performance and class-wise accuracy.
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。