Power Failure Cascade Prediction using Graph Neural Networks
This addresses power grid reliability for grid operators, though it appears incremental as it applies existing GNN methods to a specific domain problem.
The paper tackles the problem of predicting power failure cascades in electrical grids by proposing a flow-free graph neural network model that predicts grid states throughout cascade processes. The model outperforms specialized influence models across various loading profiles and reduces computational time by almost two orders of magnitude.
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.