Optimizing PI Regulators for DFIGs in Wind Energy Using Artificial Intelligence

This paper presents a novel design approach aimed at maximizing the performance of proportional-integral (PI) regulators for a doubly-fed induction generator (DFIG) used in wind energy applications. Traditional methods for tuning PI regulators are often time-consuming and rely on trial and error. In this work, the tuning of PI regulators for the DFIG is formulated as a constrained nonlinear optimization problem. The proposed method, called Thermal Exchange Optimization (TEO), is inspired by Newton's law of cooling and is designed to optimize the control parameters of the PI regulators based on time-domain performance and operational constraints, thereby maximizing power extraction from the available wind resource. To evaluate the effectiveness of the TEO method, a comparative study with other similar algorithms is conducted. Statistical analysis using Friedman and Bonferroni-Dunn's tests demonstrates that the TEO method outperforms other reported metaheuristic methods, providing significant improvements in control performance for DFIGs in wind energy applications.