Artificial Intelligence-Assisted Fractional-Order Robust Control For Power Quality Enhancement in Dfig-Based Wind Energy Conversion Systems

Abstract

The increasing integration of renewable energy resources into modern power systems has intensified the need for advanced control strategies capable of maintaining system stability and improving power quality under dynamic operating conditions. Among renewable technologies, Doubly Fed Induction Generator (DFIG)-based Wind Energy Conversion Systems (WECS) have gained widespread attention due to their high efficiency, variable-speed operation, and reduced converter rating. However, fluctuations in wind speed and grid disturbances adversely affect voltage regulation, frequency stability, reactive power compensation, and harmonic performance.

This paper proposes an Artificial Intelligence-assisted Fractional-Order Robust Controller (AI-FORC) for enhancing the dynamic performance of a DFIG-based WECS. The proposed controller integrates fractional-order control with intelligent optimization techniques to improve rotor speed regulation, active and reactive power control, and DC-link voltage stability while minimizing total harmonic distortion (THD). A comprehensive MATLAB/Simulink model of the DFIG wind energy conversion system, including rotor-side converter, grid-side converter, and intelligent control algorithms, is developed to evaluate controller performance under varying wind speeds and loading conditions.

Simulation results demonstrate that the proposed AI-FORC significantly improves transient response, reduces steady-state error, suppresses oscillations, and enhances power quality compared with conventional PI and Sliding Mode Controllers. The proposed approach achieves superior voltage stability, improved reactive power compensation, lower THD, and better overall system reliability, making it suitable for next-generation smart grid applications involving renewable energy integration.