Data-Driven Interaction Analysis of Line Failure Cascading in Power Grid Networks

TL;DR

This paper employs machine learning to model and predict line failure interactions in power grid networks, capturing both static and dynamic failure behaviors to improve understanding and forecasting of cascading failures.

Contribution

It introduces weighted l1-regularized logistic regression models for static and dynamic analysis of line failure interactions, including higher-order effects, in power grid networks.

Findings

Static model captures failure interactions near steady states.

Dynamic model predicts failure propagation over time.

Identifies groups of lines that tend to fail together.

Abstract

We use machine learning tools to model the line interaction of failure cascading in power grid networks. We first collect data sets of simulated trajectories of possible consecutive line failure following an initial random failure and considering actual constraints in a model power network until the system settles at a steady state. We use weighted $l_1$-regularized logistic regression-based models to find static and dynamic models that capture pairwise and latent higher-order lines' failure interactions using pairwise statistical data. The static model captures the failures' interactions near the steady states of the network, and the dynamic model captures the failure unfolding in a time series of consecutive network states. We test models over independent trajectories of failure unfolding in the network to evaluate their failure predictive power. We observe asymmetric, strongly positive, and negative interactions between different lines' states in the network. We use the static interaction model to estimate the distribution of cascade size and identify groups of lines that tend to fail together, and compare against the data. The dynamic interaction model successfully predicts the network state for long-lasting failure propagation trajectories after an initial failure.