# Power Failure Cascade Prediction using Graph Neural Networks

arXiv: https://arxiv.org/abs/2404.16134 · HTML: https://mlsanity.com/paper/2404.16134/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 32 references that are in the map.
- First posted on arXiv 24 Apr 2024.

## Builds on (most cited first, 4 of 4)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fast Calculation of Probabilistic Power Flow: A Model-based Deep Learning Approach](https://mlsanity.com/paper/1906.06017/) (2019)
- [Cascading Power Outages Propagate Locally in an Influence Graph that is not the Actual Grid Topology](https://mlsanity.com/paper/1508.01775/) (2015)
- [GRNN-based Real-time Fault Chain Prediction](https://mlsanity.com/paper/2303.08864/) (2023)

## Built on by (most cited first, 4 of 4)

- [Cascading Failure Prediction via Causal Inference](https://mlsanity.com/paper/2410.19179/) (2024)
- [Real-Time Risky Fault-Chain Search using Time-Varying Graph RNNs](https://mlsanity.com/paper/2503.09775/) (2025)
- [Inductive Power Grid Cascading Failure Analysis with GRU-Gated Graph Attention](https://mlsanity.com/paper/2605.07010/) (2026)
- [EnergyEminence: Source-Aware Environmental Calibration and Evaluation in a Physics-Grounded Grid Digital Twin](https://mlsanity.com/paper/2609.36215/) (2026)

## Abstract (arXiv)

We consider the problem of predicting power failure cascades due to branch failures. We propose a flow-free model based on graph neural networks that predicts grid states at every generation of a cascade process given an initial contingency and power injection values. We train the proposed model using a cascade sequence data pool generated from simulations. We then evaluate our model at various levels of granularity. We present several error metrics that gauge the model's ability to predict the failure size, the final grid state, and the failure time steps of each branch within the cascade. We benchmark the graph neural network model against influence models. We show that, in addition to being generic over randomly scaled power injection values, the graph neural network model outperforms multiple influence models that are built specifically for their corresponding loading profiles. Finally, we show that the proposed model reduces the computational time by almost two orders of magnitude.