arXiv cs.AI· Milad Kazemi, Behzad Kazemtabrizi·· 1 天前AI 评分31
学习式约束选择何时在安全约束优化中真正有效？从 SCOPF 到机组组合的边界图
When Does Learned Constraint Selection Pay in Security-Constrained Optimisation? A Boundary Map from SCOPF to Unit Commitment
AI 导读
研究提出以“备用代价”（price of a spare）判断学习式约束选择是否优于固定伞集：在 PGLib-OPF 至 10,000 节点的 43 个网络上，SCOPF 场景中固定伞集中位仅 5 条约束且从未被超越，学习选择器虽在 case500 复现约 x80,000 加速，但仅比伞集快 0.25 ms 且在 4-5% 实例上违反约束。
正文 · 原文
Abstract:Learning-to-optimise methods for security-constrained optimal power flow (SCOPF) predict the security constraints that bind on each instance and solve only the reduced problem, with reported speed-ups of two to four orders of magnitude over the full problem. We ask whether learned selection beats the strongest learning-free alternative: a fixed umbrella set enforcing every constraint observed to bind in training. Our criterion, the price of a spare, answers this in advance: an enforced but inactive constraint is free, so the umbrella is exactly optimal wherever feasible, and learning can pay only where a spare decision carries a price. We test it systematically, including every PGLib-OPF network up to 10,000 buses. For SCOPF on a fixed network the umbrella is never beaten: its median size is five constraints across 43 networks, with no size trend, and our selector, while reproducing speed-ups of published magnitude (about x80,000 at case500), gains at most 0.25 ms over the umbrella and violates constraints on 4-5% of instances. Configuration diversity can break the umbrella's coverage on a small, densely meshed network but not at 2,000 buses, and we certify coverage with conformal risk control. In unit commitment, where a spare has a price, a static commitment loses 4-12% out of sample, and a predict-repair-reduce pipeline recovers it (cost gap 0.2-2.9%, fully feasible, 16-161x faster than the MILP). In our experiments, whether learning pays depends not on problem size but on whether a spare carries a price.
| Comments: | 10 pages, 6 figures, 4 tables |
| Subjects: | Systems and Control (eess.SY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.15142 [eess.SY] |
| (or arXiv:2611.15142v1 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15142 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Milad Kazemi [view email]
[v1]
Wed, 11 Nov 2026 07:31:18 UTC (28 KB)
来源：arXiv cs.AI · arxiv.org