On the Definition of Robustness and Resilience of AI Agents for Real-time Congestion Management
This work addresses the need for standardized evaluation of AI agents in critical real-time applications like congestion management, though it is incremental in applying existing perturbation methods to a specific domain.
The paper tackles the lack of detailed assessment methodologies for AI robustness and resilience in high-risk sectors by introducing a quantitative framework using Grid2Op to evaluate reinforcement learning agents in congestion management, demonstrating effectiveness in identifying vulnerabilities and improving performance.
The European Union's Artificial Intelligence (AI) Act defines robustness, resilience, and security requirements for high-risk sectors but lacks detailed methodologies for assessment. This paper introduces a novel framework for quantitatively evaluating the robustness and resilience of reinforcement learning agents in congestion management. Using the AI-friendly digital environment Grid2Op, perturbation agents simulate natural and adversarial disruptions by perturbing the input of AI systems without altering the actual state of the environment, enabling the assessment of AI performance under various scenarios. Robustness is measured through stability and reward impact metrics, while resilience quantifies recovery from performance degradation. The results demonstrate the framework's effectiveness in identifying vulnerabilities and improving AI robustness and resilience for critical applications.