A physics-guided diffusion model produces synthetic power flow samples that are more AC-feasible and slightly closer to ground truth than unconstrained diffusion on IEEE 5, 24, and 118 bus systems.
A large synthetic dataset for machine learning applications in power transmission grids,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Constrained Diffusion Models for Synthesizing Representative Power Flow Datasets
A physics-guided diffusion model produces synthetic power flow samples that are more AC-feasible and slightly closer to ground truth than unconstrained diffusion on IEEE 5, 24, and 118 bus systems.