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

arXiv: https://arxiv.org/abs/2112.01061 · HTML: https://mlsanity.com/paper/2112.01061/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 2 Dec 2021.

## Builds on (most cited first, 11 of 11)

- [The physics of higher-order interactions in complex systems](https://mlsanity.com/paper/2110.06023/) (2021)
- [Inverse statistical problems: from the inverse Ising problem to data science](https://mlsanity.com/paper/1702.01522/) (2017)
- [Optimal structure and parameter learning of Ising models](https://mlsanity.com/paper/1612.05024/) (2016)
- [Learning graphical models from the Glauber dynamics](https://mlsanity.com/paper/1410.7659/) (2014)
- [Cascading Power Outages Propagate Locally in an Influence Graph that is not the Actual Grid Topology](https://mlsanity.com/paper/1508.01775/) (2015)
- [Emergence of scale-free blackout sizes in power grids](https://mlsanity.com/paper/2007.06967/) (2020)
- [Resilience of Locally Routed Network Flows: More Capacity is Not Always Better](https://mlsanity.com/paper/1608.04155/) (2016)
- [Vulnerability and co-susceptibility determine the size of network cascades](https://mlsanity.com/paper/1701.08790/) (2017)
- [Optimal noise-canceling networks](https://mlsanity.com/paper/1807.08376/) (2018)
- [Network Effects on Robustness of Dynamic Systems](https://mlsanity.com/paper/1909.06506/) (2019)
- [Line Failure Localization of Power Networks Part I: Non-cut Outages](https://mlsanity.com/paper/2005.10199/) (2020)

## Abstract (arXiv)

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 l1-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.