Backend
Improving Learned AC-OPF Feasibility under Distribution Shift with PF-in-the-Loop Correction
arXiv eess.SY0 views
arXiv:2610.36236v1 Announce Type: new Abstract: Learning-based AC-OPF enables fast dispatch, yet its feasibility can degrade under distribution shift. We analyze three state-of-the-art methods and identify a shared deployment-time limitation: none use feedback from the power-flow (PF)-realized state to ensure feasibility of the predicted control. Using a simple PF-in-the-loop feasibility restoration filter, we empirically show that such feedback substantially improves hard feasibility across four out-of-distribution scenarios with modest runtime overhead.
Source：https://arxiv.org/abs/2610.36236PreviousGhost in the Code: Offline Séance with Programming Language SpiritsNextDistribution Grid Reconfiguration and Restoration via Linearizable Multi-phase Power Flow Modeling
Related posts
Streamlining GitHub Activity: Why Lost Filters Impact Software Engineering Measurement
0dev.to Productivity
The Roofline Model for LLM Inference
0dev.to Machine Learning
Deduplicate Your RAG Corpus Without Losing Its Citations
0dev.to Machine Learning
scm2cpp-learn: 44 scikit-learn estimators, same results, up to ~1000x faster
0dev.to Machine Learning
Marvell is buying Lumentum for $115B: what the optical bet means for AI cluster power, and what a fixed 4.5x exchange ratio really locks in
0dev.to Machine Learning
Terminal-Bench 2.0 vs 2.1 on Hugging Face: A 2.1 Score Is Ranked First on the 2.0 Board
0dev.to Machine Learning