Predicting Cascade Failures in Interdependent Urban Infrastructure Networks

2025-02-26

AI Summary

To address the challenge of predicting cascading failures (CFs) arising from interdependencies among urban multi-sector infrastructure systems (e.g., power, transportation, and telecommunications), this paper proposes I³, the first graph neural network model that jointly models intra-system propagation dynamics and cross-system dependency coupling. Methodologically, I³ introduces an initial node enhancement pretraining strategy to mitigate graph convolutional over-smoothing, and integrates dual graph autoencoder (GAE) encoders, global pooling, heterogeneous graph modeling, and a structure-aware propagation module. Evaluated on real-world urban infrastructure datasets, I³ achieves state-of-the-art performance: +31.94% in AUC, +22.73% in F1-score, and −28.52% in RMSE for cascade size prediction. Moreover, it is the first method to enable precise identification of phase-transition points and single-network bias correction.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Cascading failures (CF) entail component breakdowns spreading through infrastructure networks, causing system-wide collapse. Predicting CFs is of great importance for infrastructure stability and urban function. Despite extensive research on CFs in single networks such as electricity and road networks, interdependencies among diverse infrastructures remain overlooked, and capturing intra-infrastructure CF dynamics amid complex evolutions poses challenges. To address these gaps, we introduce the extbf{I}ntegrated extbf{I}nterdependent extbf{I}nfrastructure CF model ($I^3$), designed to capture CF dynamics both within and across infrastructures. $I^3$ employs a dual GAE with global pooling for intra-infrastructure dynamics and a heterogeneous graph for inter-infrastructure interactions. An initial node enhancement pre-training strategy mitigates GCN-induced over-smoothing. Experiments demonstrate $I^3$ achieves a 31.94% in terms of AUC, 18.03% in terms of Precision, 29.17% in terms of Recall, 22.73% in terms of F1-score boost in predicting infrastructure failures, and a 28.52% reduction in terms of RMSE for cascade volume forecasts compared to leading models. It accurately pinpoints phase transitions in interconnected and singular networks, rectifying biases in models tailored for singular networks. Access the code at https://github.com/tsinghua-fib-lab/Icube.

Problem

• Predicting cascading failures in interdependent urban infrastructure networks.
• Addressing overlooked interdependencies among diverse infrastructure systems.
• Improving accuracy in forecasting infrastructure failures and cascade volumes.

Innovation

• Dual GAE with global pooling for intra-infrastructure dynamics
• Heterogeneous graph for inter-infrastructure interactions
• Node enhancement pre-training to mitigate GCN over-smoothing