LAUSR

Operating wind power generation system at optimal power point is essential which is achieved by employing a Maximum Power Point Tracking (MPPT) control strategy. This literature focuses on developing a novel particle swarm optimization algorithm enhanced radial basis function neural network supported TSR based MPPT control strategy for Doubly Fed Induction Generator (DFIG) based wind power generation system. The proposed hybrid MPPT control strategy estimates the effective wind speed and estimates the optimal rotor speed of the wind power generation system to track the maximum power. The proposed controller extremely reduces the speed dissimilarity range of wind power generation system, which leads to rationalizing the pulse width inflection of DFIG rotor side converter. This in turn, increases the system's reliability and delivers an effective power tracking with reduced converter losses. Furthermore, by utilizing the proposed MPPT controller, the converter size can be reduced to 40%. Therefore, the overall cost of the system can be gradually decreased. To validate the performance of the proposed MPPT controller, an extensive simulation study has been carried out under medium and high wind speed conditions in MATLAB/Simulink. The obtained results have been justified using experimental analysis.