Stability- and Safety-Guaranteed Artificial Intelligence: Enhancing Renewable-Dominated Power System Operation and Control

Abstract

As renewable energy becomes the dominant generation resource in modern power systems, system stability and safety pose critical challenges due to increased uncertainty, reduced inertia, and escalating system complexity. Artificial intelligence (AI) provides unprecedented capabilities for real-time control, predictive optimization, and adaptive decision making, yet its adoption in safety-critical power system applications is hampered by concerns over robustness, interpretability, and the absence of formal guarantees. This article outlines how stability- and safety-guaranteed AI approaches can bridge this gap to enable reliable integration of renewables. In this article, we review emerging methods that embed physics, control theory, and optimization constraints in AI models for power systems, discuss advances in certifiable robustness and Lyapunov-based learning, and chart the path for deployment in renewable-dominated grids. The article concludes with policy, regulatory, and research recommendations for ensuring that AI not only accelerates the clean energy transition but also preserves resilience and trust in critical infrastructure.