Learning Dynamic Models of Black-Box Inverter-Based Resources in Power Grids

Yuzhang Lin – NYU

A critical challenge in modern grid stability is that inverter-based resources (IBRs) are often black boxes to utilities and system operators. Inverter manufacturers and plant developers understandably hesitate to disclose proprietary control strategies, leaving operators with limited visibility into internal dynamics. The problem is further compounded by the fact that IBRs can switch among multiple control modes, which are typically unknown to operators yet can exhibit dramatically different dynamic behaviors.
To address this challenge, we develop a comprehensive data-driven framework that uses only terminal measurements to discover unknown control modes and learn continuous-time models that accurately capture IBR dynamics under each mode. By leveraging physics-inspired deep learning, the proposed approach can learn a high-order, continuous-time, nonlinear state-space representation of the dynamics of black-box IBRs using their noisy terminal measurements during disturbances only. In addition, a physics-inspired deep unsupervised learning mechanism automatically identifies distinct control modes from historical disturbance data, enabling the learning of separate state-space models that represent the dynamics associated with each mode. High-fidelity simulation results demonstrate how the proposed framework can learn time-domain models of fully black-box IBRs and deliver highly accurate long-horizon predictions of their responses to grid disturbances, including but not limited to subsynchronous oscillations caused by PLL interactions in weak grids.