| Phase: |
Theme |
| Theme: | Wind (T14) |
| Status: | Active |
| Start Date: | 2025-01-01 |
| End Date: | 2026-06-30 |
Project Overview
This project targets the development of advanced data-driven artificial intelligence (AI)-enabled impedance modeling and stability analysis tools for wind farms. The proposed data-driven AI-enabled approach can effectively capture the nonlinear dynamics of complex wind farms, even with limited knowledge of the control system parameters. Furthermore, it accounts for modern wind farms' inherent uncertainties and structural complexity. Hence, it facilitates accurate assessment and prediction of potential instabilities and control system oscillations across a broad range of typical operating conditions. The proposed approach can potentially establish the foundations for entirely new tools for dynamic analysis and control of complex renewable energy resources systems via advanced AI and machine learning methods.
Outputs
| Title |
Category |
Date |
Authors |
| Adaptive Liquid Time-Constant Equivalent Dynamic Model with Transfer Learning for Active Distribution Networks with Grid-Forming IBRs | Publication | 2026-08-01 | Ahmed Moetasem, Yasser Mohamed |
| Data-Driven Impedance Identification of Wind Farms Using Kolmogorov-Arnold Networks with Transfer LearningImpact factor: 3.8 | Publication | 2026-05-26 | Ahmed Moetasem, Yasser Mohamed |
| Liquid Time-Constant Networks with Transfer Learning for Adaptive Data-Driven Impedance Identification of Hybrid Power Generation SystemsImpact factor: 5.0 (from HQP) | Publication | 2026-02-20 | Ahmed Moetasem, Yasser Mohamed |