基于AI的电网边缘协调的有限样本概率安全认证

中文摘要 AI 辅助

协调大量灵活的电网边缘设备可以减轻对耗时且资本密集的电网升级的需求，而基于AI的控制方法，如多智能体强化学习或模仿学习，在其实时决策可扩展性方面具有前景。然而，系统运营商仍然需要一种独立且严格的方法来决定给定的AI系统是否足够安全以进行部署。本文为闭环电网运行中的黑盒AI决策模型开发了一个有限样本概率安全认证框架。核心思想是将完整的输入-AI-电网评估工作流简化为在运营商定义的安全规范下的二元不安全结果，然后使用精确二项式推断来认证相应的不安全操作概率。给定一组留出的校准场景，该框架返回最紧的单侧上界证书和接受/拒绝部署标准，该标准控制错误安全认证的概率。由于认证针对的是可能偏离未来运行的校准分布，我们进一步将名义证书与物理可解释的样本空间对抗攻击相结合，这是AI中广泛使用的用于研究AI模型脆弱性的概念。对具有1,000个智能体AI模型（独立参数）的电网边缘灵活性协调的案例研究验证了有限样本安全保证以及将对抗攻击集成到滚动训练-认证-部署流程中的价值。

英文摘要

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 reduce the complete input--AI--grid evaluator workflow to a binary unsafe outcome under an operator-defined safety specification, and then use exact binomial inference to certify the corresponding unsafe operation probability. Given a set of held-out calibration scenarios, the framework returns the tightest one-sided upper certificate and an accept/reject deployment criterion that controls the probability of false safety certification. Because the certification is for the calibration distribution that may deviate from the future operation, we further combine the nominal certificate with physically interpretable sample-space adversarial attacks, a concept widely used in AI to investigate the fragility of AI models. Case studies on grid-edge flexibility coordination with 1{,}000-agent AI models (independent parameters) verify the finite-sample safety guarantee and the value of integrating adversarial attacks into a rolling-window training-certification-deployment flow.

发表机构

• University of Oxford（牛津大学）

机构由 AI 辅助整理，请以论文原文为准。