A Novel Approach for Rotor Angle Instability Mitigation

Abstract

This paper proposes a novel data-driven approach for predicting and mitigating rotor angle instability in power systems. By utilizing Gaussian process regression (GPR) with a Matern 5/2 kernel, the algorithm effectively forecasts the necessary setpoint adjustments to maintain stability. This approach reduces the computational burden associated with traditional simulation-based methods. The proposed algorithm offers several advantages. First, it provides early insights to operators, allowing for timely corrective actions. Second, it can be applied to both high-inertia and hybrid/low-inertia networks. In hybrid or low inertia networks, corrective actions can be implemented to take advantage of the benefits provided by inverter-based power plants. Transient stability can be improved or regained by using proper inverter control. Third, it demonstrates the effectiveness of inverter-based power plants in enhancing transient stability, even in the presence of a large number of renewable energy sources. Overall, the proposed algorithm represents a significant advancement in data-driven stability analysis and offers a promising tool for ensuring the reliability and resilience of power systems.