Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184499,
        author = {JOGESH CHAUDHARI and Manashwini Das},
        title = {Eigenvalue Sensitivity Analysis with Machine Learning for Power System Stability Enhancement under High PV Penetration},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {1653-1656},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184499},
        abstract = {This paper presents a novel framework that integrates eigenvalue sensitivity analysis with machine learning (ML) techniques to enhance the stability of power systems experiencing high photovoltaic (PV) penetration. The study focuses on the IEEE 9-bus test system, where one synchronous generator is replaced with an 85 MW PV inverter at Bus 3. The proposed methodology first linearizes the system under varying operating conditions to evaluate oscillatory modes and their sensitivities with respect to PV output and inverter control parameters such as phase-locked loop (PLL) and Q–V droop gains. Subsequently, a supervised ML surrogate model is trained to predict the critical mode’s damping ratio and frequency in real time, thereby enabling rapid control adjustments without requiring repeated online linearization. Results indicate that the introduction of PV generation reduces damping from 6.5% to 3.2% as penetration rises to 85 MW. Sensitivity analysis reveals that increasing Q–V droop and PLL gains effectively shifts eigenvalues toward stability. When applied in conjunction with ML prediction, damping margins can be restored to nearly 8%, with prediction errors below 0.2 percentage points. These findings highlight the potential of combining analytical and data-driven approaches for maintaining small-signal stability in PV-rich networks.},
        keywords = {Eigenvalue Sensitivity, Machine Learning, PV Penetration, Damping Ratio, IEEE 9-Bus System, Small-Signal Stability},
        month = {September},
        }