Intelligent Control Strategies for DFIG-Based Wind Energy Systems: A Comparative Analysis of Type-1 Fuzzy, Interval Type-2 Fuzzy, and ANN Approaches

Abstract

In this study, we investigate and compare three advanced control strategies, Type-1 Fuzzy Logic Control (T1FLC), Interval Type-2 Fuzzy Logic Control (IT2FLC), and Artificial Neural Networks (ANN), applied to Doubly-Fed Induction Generators (DFIGs) in Wind Energy Conversion Systems (WECS). As wind energy plays an increasingly critical role in renewable power generation, efficient and robust control of DFIGs is essential to ensure grid stability, reliability, and optimal energy extraction under variable wind conditions. T1FLC offers simplicity and robustness but may suffer from limited adaptability. IT2FLC improves upon this by managing higher levels of uncertainty and noise through the use of fuzzy sets with an additional degree of freedom. ANN-based control, on the other hand, leverages data-driven learning and non-linear mapping to achieve high performance but may require significant training and tuning. Simulations conducted in MATLAB/Simulink evaluate the performance of each controller under dynamic wind profiles, measuring key metrics such as rotor speed regulation, electromagnetic torque response, and power output stability. This comparative study provides insights for selecting suitable control schemes for DFIG-based wind energy systems under varying operational conditions.