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

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.

arXiv comment10 pages, 7 figures

References in corpus (15)

• Maps of random walks on complex networks reveal community structure
• Weak pairwise correlations imply strongly correlated network states in a neural population
• A model for cascading failures in complex networks
• The physics of higher-order interactions in complex systems
• The map equation
• Cascading Power Outages Propagate Locally in an Influence Graph that is not the Actual Grid Topology
• Inverse Ising inference using all the data
• A Markovian influence graph formed from utility line outage data to mitigate large cascades
• Obtaining statistics of cascading line outages spreading in an electric transmission network from standard utility data
• Vulnerability and co-susceptibility determine the size of network cascades
• Nonlocal effects and counter measures in cascading failures
• Maximum likelihood reconstruction for Ising models with asynchronous updates
• Interaction Graphs for Cascading Failure Analysis in Power Grids: A Survey
• Optimal noise-canceling networks
• Emergence of scale-free blackout sizes in power grids

Cited by in corpus (4)

• Machine Learning Applications in Cascading Failure Analysis in Power Systems: A Review
• Simplicial cascades are orchestrated by the multidimensional geometry of neuronal complexes
• Emergent synchrony in oscillator networks with adaptive arbitrary-order interactions
• Identification of pressure points in modern power systems using transfer entropy