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

The paper introduces a finite‑sample probabilistic safety certification framework for black‑box AI decision models used in closed‑loop grid operation. It transforms the AI‑grid evaluation into a binary unsafe outcome under a safety specification and applies exact binomial inference to provide a tight one‑sided upper bound on the unsafe operation probability, using held‑out calibration scenarios. The framework also incorporates physically interpretable sample‑space adversarial attacks to address distribution shifts and is validated through case studies involving 1,000‑agent AI models for grid‑edge flexibility coordination.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• reinforcement-learning
• safety