Neural Lyapunov Based Transient Stability Analysis of Networked Grid-Forming Inverters with Unknown Internal Dynamics

Le résumé fourni par la source

Evaluating transient stability of grid-forming inverters remains challenging and underexplored. Existing studies typically assume the system dynamics are explicitly known, while it is not the common case in the real-world applications. To address this limitation, a neural Lyapunov based learning framework is proposed in this paper to evaluate the transient stability of grid-forming inverters with unknown dynamics. Leveraging the universal approximation capability of neural networks, we model the unknown system dynamics as a forward neural network and train corresponding neural Lyapunov function with the help of learner-falsifier structure. The proposed approach enables transient stability evaluation without requiring explicit system models, making it more applicable to practical scenarios. Case studies are presented to validate the efficacy and reliability of the proposed method.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.