Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Gated Graph Attention Networks for Predicting Duration of Large Scale Power Outages Induced by Natural Disasters

Chenghao Duan, Chuanyi Ji, Anwar Walid, Scott Ganz

Abstract

The occurrence of large-scale power outages induced by natural disasters has been on the rise in a changing climate. Such power outages often last extended durations, causing substantial financial losses and socioeconomic impacts to customers. Accurate estimation of outage duration is thus critical for enhancing the resilience of energy infrastructure under severe weather. We formulate such a task as a machine learning (ML) problem with focus on unique real-world challenges: high-order spatial dependency in the data, a moderate number of large-scale outage events, heterogeneous types of such events, and different impacts in a region within each event. To address these challenges, we develop a Bimodal Gated Graph Attention Network (BiGGAT), a graph-based neural network model, that integrates a Graph Attention Network (GAT) with a Gated Recurrent Unit (GRU) to capture the complex spatial characteristics. We evaluate the approach in a setting of inductive learning, using large-scale power outage data from six major hurricanes in the Southeastern United States. Experimental results demonstrate that BiGGAT achieves a superior performance compared to benchmark models.

Gated Graph Attention Networks for Predicting Duration of Large Scale Power Outages Induced by Natural Disasters

Abstract

The occurrence of large-scale power outages induced by natural disasters has been on the rise in a changing climate. Such power outages often last extended durations, causing substantial financial losses and socioeconomic impacts to customers. Accurate estimation of outage duration is thus critical for enhancing the resilience of energy infrastructure under severe weather. We formulate such a task as a machine learning (ML) problem with focus on unique real-world challenges: high-order spatial dependency in the data, a moderate number of large-scale outage events, heterogeneous types of such events, and different impacts in a region within each event. To address these challenges, we develop a Bimodal Gated Graph Attention Network (BiGGAT), a graph-based neural network model, that integrates a Graph Attention Network (GAT) with a Gated Recurrent Unit (GRU) to capture the complex spatial characteristics. We evaluate the approach in a setting of inductive learning, using large-scale power outage data from six major hurricanes in the Southeastern United States. Experimental results demonstrate that BiGGAT achieves a superior performance compared to benchmark models.
Paper Structure (15 sections, 4 equations, 3 figures, 3 tables, 1 algorithm)

This paper contains 15 sections, 4 equations, 3 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related work
  3. Method
  4. Variables
  5. Field data
  6. Problem formulation
  7. Bimodal gated graph attention network
  8. Bimodal graph node embedding
  9. Gated graph attention mechanism
  10. Experiment setting
  11. Inductive learning
  12. Results
  13. Inductive learning model performance
  14. Generalization of GRU and error analysis
  15. Conclusion

Figures (3)

  • Figure 1: Spatial heterogeneity and dependency of power outages from six hurricanes: (a) Florence, (b) Irma, (c) Laura, (d) Michael, (e) Sally, (f) Zeta. Dark lines: wind boundaries (64, 50, and 34 knots). Clusters on regions with different impacts: Red - significantly impacted counties; Yellow - less impacted counties. Clustered by wind and outage duration.
  • Figure 2: Overall BiGGAT structure: Node features are fed into the Bimodal Embedding, then passed through the Gated Graph Attention mechanism. The aggregated messages are transformed to outputs by a Linear Readout layer.
  • Figure 3: Model performance comparison for (a) Florence, (b) Irma, (c) Laura, (d) Michael, (e) Sally, and (f) Zeta. Each subplot shows classification accuracy, Macro F1, and balanced accuracy for XGB, RF, GAT, BiGAT, and BiGGAT.