SABLE delivers a GPU sparse batched power flow solver with block-diagonal embedding that achieves up to 253x standalone speedup and 206x training throughput for AC optimal power flow learning models.
Parallel power flow solutions using a biconjugate gradient algorithm and a Newton method: A GPU-based approach,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SABLE: GPU-Based Power Flow Accelerator for Sparsity-Aware Batched Learning
SABLE delivers a GPU sparse batched power flow solver with block-diagonal embedding that achieves up to 253x standalone speedup and 206x training throughput for AC optimal power flow learning models.