An adaptive graph neural network with spatial attention and residual spatiotemporal convolutions enables short-term voltage stability assessment in power grids under time-varying topologies.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.SY 2verdicts
UNVERDICTED 2representative citing papers
A diffusion-based generative ML paradigm is introduced to proactively generate and rank high-risk contingencies for voltage stability using physical information from operating points, with experiments on IEEE-6 to IEEE-118 systems.
citing papers explorer
-
Adaptive Spatial-Temporal Graph Learning-Enabled Short-Term Voltage Stability Assessment against Time-Varying Topological Conditions
An adaptive graph neural network with spatial attention and residual spatiotemporal convolutions enables short-term voltage stability assessment in power grids under time-varying topologies.
-
A Diffusion-based Generative Machine Learning Paradigm for Dynamic Contingency Screening
A diffusion-based generative ML paradigm is introduced to proactively generate and rank high-risk contingencies for voltage stability using physical information from operating points, with experiments on IEEE-6 to IEEE-118 systems.