A physics-informed DDPM with an auxiliary learned noise schedule reduces power imbalance in synthetic IEEE 14-bus and 30-bus data, though its claimed feasibility advantage over a GAN baseline is not supported by the reported table.
Data-driven power flow linearization: A regression ap- proach
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
-
Synthetic Power Flow Data Generation Using Physics-Informed Denoising Diffusion Probabilistic Models
A physics-informed DDPM with an auxiliary learned noise schedule reduces power imbalance in synthetic IEEE 14-bus and 30-bus data, though its claimed feasibility advantage over a GAN baseline is not supported by the reported table.