Enhancing Transient Stability of DFIG-Based Wind Turbine Systems Using Deep Learning-Controlled Resistance-Based Fault Current Limiters

Document Type : Original Article


1School of Mechanical Engineering,Northwestern Polytechnical University, Xi'an 710072, Shaanxi, China 2 School of Mechanical Engineering, Nanyang Technological University, 639798, Singapore


This research addresses the challenge of grid stability when integrating renewable energy, especially wind power. It focuses on enhancing transient stability in doubly fed induction generator (DFIG) wind energy systems using advanced strategies like fault current limiters and deep learning. The study includes a thorough analysis of fault scenarios, simulations, and solution evaluations, highlighting the crucial need for maintaining stability in renewable energy grids. As wind energy demand rises, optimizing system performance is vital. Many wind turbines rely on DFIGs, necessitating robust fault ride-through. A passive fault current limiter is introduced to enhance DFIG system transient stability. This limiter, devoid of active controllers, offers intrinsic resilience. The research introduces a novel algorithm to calculate optimal fault current limiter resistance, maintaining voltage within ±10% of the reference level. Transient stability is evaluated through simulations involving symmetric and asymmetric faults, incorporating deep learning. MATLAB/Simulink confirms the efficacy of the proposed limiter and algorithm in boosting transient stability for DFIG-based wind energy systems. The study underscores the role of fault current limiters and deep learning in seamlessly integrating renewable energy into power grids.