SOURCE-LINKED INTELLIGENCE

Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Coordinating large population of flexible grid-edge devices can alleviate the need for time-consuming and capital-intensive network upgrades, and AI-based control methods such as multi-agent reinforcement learning or imitation learning are promising in their real-time decision scalability. However, system operators still need an independent and rigorous way to decide whether a given AI system is safe enough for deployment. This paper develops a finite-sample probabilistic safety certification framework for black-box AI decision models in closed-loop grid operation. The central idea is to reduc

Read original source ↗ Open in workspace

recordType

paper

region

Global