Enhancing the control of doubly fed induction generators using artificial neural networks in the presence of real wind profiles.

This study tackles the complex task of integrating wind energy systems into the electric grid, facing challenges such as power oscillations and unreliable energy generation due to fluctuating wind speeds. Focused on wind energy conversion systems, particularly those utilizing double-fed induction generators (DFIGs), the research introduces a novel approach to enhance Direct Power Control (DPC) effectiveness. Traditional DPC, while simple, encounters issues like torque ripples and reduced power quality due to a hysteresis controller. In response, the study proposes an innovative DPC method for DFIGs using artificial neural networks (ANNs). Experimental verification shows ANNs effectively addressing issues with the hysteresis controller and switching table. Additionally, the study addresses wind speed variability by employing an artificial neural network to directly control reactive and active power of DFIG, aiming to minimize challenges with varying wind speeds. Results highlight the effectiveness and reliability of the developed intelligent strategy, outperforming traditional methods by reducing current harmonics and improving dynamic response. This research contributes valuable insights into enhancing the performance and reliability of renewable energy systems, advancing solutions for wind energy integration complexities.