Predicting Dynamic Stability from Static Features in Power Grid Models using Machine Learning

TL;DR

This paper combines network science metrics and machine learning to accurately predict power grid desynchronisation events caused by line failures, offering a new approach to assessing grid stability beyond traditional simulation models.

Contribution

It introduces a novel method integrating network metrics with machine learning to predict grid failures, demonstrating high accuracy and transferability across different synthetic power grid models.

Findings

Predictive models achieve over 0.996 precision in identifying desynchronisation events.

Few key network metrics govern grid robustness and vulnerability.

Transfer learning between different grid datasets is feasible with slight performance loss.

Abstract

A reliable supply with electric power is vital for our society. Transmission line failures are among the biggest threats for power grid stability as they may lead to a splitting of the grid into mutual asynchronous fragments. New conceptual methods are needed to assess system stability that complement existing simulation models. In this article we propose a combination of network science metrics and machine learning models to predict the risk of desynchronisation events. Network science provides metrics for essential properties of transmission lines such as their redundancy or centrality. Machine learning models perform inherent feature selection and thus reveal key factors that determine network robustness and vulnerability. As a case study, we train and test such models on simulated data from several synthetic test grids. We find that the integrated models are capable of predicting desynchronisation events after line failures with an average precision greater than $0.996$ when averaging over all data sets. Learning transfer between different data sets is generally possible, at a slight loss of prediction performance. Our results suggest that power grid desynchronisation is essentially governed by only a few network metrics that quantify the networks ability to reroute flow without creating exceedingly high static line loadings.