Online Long-Term Voltage Stability Margin Estimation for IBR/DER Dominated Power System with Integrated VSM-Aware TSO-DSO Framework

A team led by Ahmed Alkhonain from Iowa State University has published a paper on arXiv proposing a machine learning-based framework for online long-term voltage stability margin (VSM) estimation in modern power systems increasingly dominated by inverter-based resources (IBRs) and distributed energy resources (DERs). The approach leverages physics-informed ML to derive an explicit analytical VSM expression from offline transmission and distribution (T&D) co-simulation data under probabilistic loading and generation mix scenarios, while accounting for unbalanced distribution modeling. This closed-form VSM representation is then linearized and embedded into the transmission system operator (TSO) optimization problem, enabling real-time enforcement of minimum VSM constraints without sacrificing computational speed.

The framework further enhances operational efficiency by incorporating VSM sensitivities into both transmission and distribution optimization, allowing system operators to prioritize the most influential reactive power resources for voltage support. Validation on the IEEE 30-bus transmission network integrated with multiple IEEE 37-node distribution feeders demonstrated that the approach successfully achieves desired VSM enhancement while maintaining high estimation accuracy. This work addresses a critical challenge as IBRs and DERs fundamentally alter traditional voltage stability characteristics, providing a practical tool for grid operators to maintain reliability in increasingly decentralized and renewable-heavy power systems.