Enhancing Power Quality in Doubly Fed Induction Generator-Based Wind Energy Conversion Systems Using FOPID Controller

A doubly fed induction generator (DFIG) is the basis of the large-scale wind energy conversion system (WECS), which has become more and more popular in recent years due to its many technical and financial advantages. The stability and dependability of power systems have been adversely affected by the rapid integration of WECS with current power grids. To address this challenge, this study proposes an innovative control strategy for DFIG-based WECS using a fractional order proportional-integral-derivative (FOPID) controller. The proposed technique combines the Ebola optimization search algorithm (EOSA) and spiking neural network (SNN), which is termed the EOSA-SNN method. The primary objective of the proposed technique is to reduce total harmonic distortion (THD), increase the performance of reactive and active power regulation, and improve the performance of DFIG-driven WECS under variable wind conditions. The FOPID controller is used to regulate the rotor-side converter for optimal control, the EOSA is used to enhance the gain parameters of the FOPID controller, and the SNN is employed to predict the most suitable controller factor adjustments in response to dynamic wind and grid fluctuations. The proposed method is implemented and evaluated, and is compared with existing methods on the MATLAB platform, such as differential evolution (DE), salp swarm algorithm (SSA) and particle swarm optimization (PSO). The results demonstrate superior performance, achieving a THD of 2.1%, settling time of 0.036Formula: see texts, overshoot of 0.3%, rise time of 0.011Formula: see texts and a computational time of 3.41Formula: see texts, providing a faster, more accurate and energy-efficient solution for effective control of DFIG-driven wind energy systems (WES).