Graph topology estimation of power grids using pairwise mutual information of time series data

2025/05/07 by Speckhard, Daniel T.
#Applications (stat.AP) #Computational Engineering #FOS: Computer and information sciences #FOS: Physical sciences #Finance #Information Theory (cs.IT) #Physics and Society (physics.soc-ph) #and Science (cs.CE)

paper · doi:10.48550/arxiv.2505.11517

Abstract

The topology of a power grid is estimated using an information theoretic approach. By modeling the grid as a graph and using voltage magnitude data of individual nodes in the grid, the mutual information between pairs of nodes is computed using different approximation methods. Using the well-known Chow-Liu algorithm, a maximum spanning tree based on mutual information is computed to estimate the power grid topology. This manuscript explores the application of this method to different datasets and explores the domain of applicability. The data quality, precision, time windows, frequency and the method for calculating the mutual information are varied to see the effect on the successful reconstruction of the graph and it's leaf nodes. Success is shown for IEEE networks generated with MATPOWER and data generated using GridLAB-D. The algorithm is then cross-validated on IEEE networks.

Citations

• A Real-World Energy Management Dataset from a Smart Company Building for Optimization and Machine Learning
• Training speedups via batching for geometric learning: an analysis of static and dynamic algorithms
• Improved Physics-Informed Neural Network based AC Power Flow for Distribution Networks
• PowerGraph: A power grid benchmark dataset for graph neural networks
• A Physics Informed Machine Learning Method for Power System Model Parameter Optimization
• Band-gap regression with architecture-optimized message-passing neural networks
• Learning Distribution Grid Topologies: A Tutorial
• Neural Architecture Search for Energy Efficient Always-on Audio Models
• GraphiT: Encoding Graph Structure in Transformers
• A Review of Graph Neural Networks and Their Applications in Power Systems
• Graph Neural Networks for Social Recommendation
• Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
• Learning with End-Users in Distribution Grids: Topology and Parameter\n Estimation
• Exact Topology and Parameter Estimation in Distribution Grids with\n Minimal Observability
• Neural Architecture Search with Reinforcement Learning
• Minimax Estimation of Functionals of Discrete Distributions
• MATPOWER: Steady-State Operations, Planning, and Analysis Tools for Power Systems Research and Education
• On Information and Sufficiency
• A Comprehensive Survey on Graph Neural Networks

Related

• Topology Estimation in Bulk Power Grids: Guarantees on Exact Recovery
• Learning Topology of the Power Distribution Grid with and without Missing Data
• Graph Algorithms for Topology Identification using Power Grid Probing
• Topology Estimation using Graphical Models in Multi-Phase Power\n Distribution Grids
• Exploration of Graph Computing in Power System State Estimation