Predicting Basin Stability of Power Grids using Graph Neural Networks

Nauck, Christian; Lindner, Michael; Schürholt, Konstantin; Zhang, Haoming; Schultz, Paul; Kurths, Jürgen; Isenhardt, Ingrid; Hellmann, Frank

doi:10.48550/arxiv.2108.08230

Cited by 2 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on statistical properties of real-world power grids, a synthetic powergrid generation model was proposed as a statistical benchmark for the trade-off analysis between cost-optimization and redundancy in power-grid design, 36 a framework used in several works to analyze the power-grid resilience to random perturbations. [37][38][39][40] In this work, we analyze the power-grid vulnerability to targeted attacks (edge removals). Using solely data of the network structure of the power grid, we measure the energy efficiency in the power grid and evaluate its vulnerability to the removal of central edges (according to different centrality measures).…”

Section: Articlementioning

confidence: 99%

Power-grid vulnerability and its relation with network structure

Dias

Montanari

Macau

2023

Chaos: An Interdisciplinary Journal of Nonlinear Science

View full text Add to dashboard Cite

Interconnected systems with critical infrastructures can be affected by small failures that may trigger a large-scale cascade of failures, such as blackouts in power grids. Vulnerability indices provide quantitative measures of a network resilience to component failures, assessing the break of information or energy flow in a system. Here, we focus on a network vulnerability analysis, that is, indices based solely on the network structure and its static characteristics, which are reliably available for most complex networks. This work studies the structural connectivity of power grids, assessing the main centrality measures in network science to identify vulnerable components (transmission lines or edges) to attacks and failures. Specifically, we consider centrality measures that implicitly model the power flow distribution in power systems. This framework allow us to show that the efficiency of the power flow in a grid can be highly sensitive to attacks on specific (central) edges. Numerical results are presented for randomly generated power-grid models and established power-grid benchmarks, where we demonstrate that the system’s energy efficiency is more vulnerable to attacks on edges that are central to the power flow distribution. We expect that the vulnerability indices investigated in our work can be used to guide the design of structurally resilient power grids.

show abstract

Section: Articlementioning

confidence: 99%

Power-grid vulnerability and its relation with network structure

Dias

Montanari

Macau

2023

Chaos: An Interdisciplinary Journal of Nonlinear Science

View full text Add to dashboard Cite

show abstract

“…Although the experimental results show that this model can somehow generalize to unseen topologies, the framework is quite complex and relies on a custom formulation of the power flow problem. Most importantly, the GNN is used to implement only a specific operation within the whole pipeline, namely to compute ∆θ i and ∆|V | i from ∆P i , ∆Q i , which is the same type of operation performed by the NR method with a linear approximation in (11).…”

Section: Mlp Designmentioning

confidence: 99%

“…A few recent works have proposed to represent power systems as graphs and used graph neural networks (GNNs) to solve power flow related tasks [5]- [11]. GNNs are neural network models that directly exploit the topology of the graph to implement localized computations, which are independent from the global structure of power systems.…”

Section: Introductionmentioning

confidence: 99%

Power Flow Balancing with Decentralized Graph Neural Networks

Hansen,

Anfinsen,

Bianchi

2021

Preprint

View full text Add to dashboard Cite

We propose an end-to-end framework based on a Graph Neural Network (GNN) to balance the power flows in a generic grid. The optimization is framed as a supervised vertex regression task, where the GNN is trained to predict the current and power injections at each grid branch that yield a power flow balance. By representing the power grid as a line graph with branches as vertices, we can train a GNN that is more accurate and robust to changes in the underlying topology. In addition, by using specialized GNN layers, we are able to build a very deep architecture that accounts for large neighborhoods on the graph, while implementing only localized operations. We perform three different experiments to evaluate: i) the benefits of using localized rather than global operations and the tendency to oversmooth when using deep GNN models; ii) the resilience to perturbations in the graph topology; and iii) the capability to train the model simultaneously on multiple grid topologies and the consequential improvement in generalization to new, unseen grids. The proposed framework is efficient and, compared to other solvers based on deep learning, is robust to perturbations not only to the physical quantities on the grid components, but also to the topology.

show abstract

Predicting Basin Stability of Power Grids using Graph Neural Networks

Cited by 2 publications

References 36 publications

Power-grid vulnerability and its relation with network structure

Power-grid vulnerability and its relation with network structure

Power Flow Balancing with Decentralized Graph Neural Networks

Contact Info

Product

Resources

About