Power Losses Reduction of Stacked Multicell Converter Fed Wind Energy Conversion System (WECS) Using Hybrid Methodology

This paper proposes a hybrid method for reduction of power losses of multicell converter in wind energy conversion system (WECS). The proposed methodology is the Artificial Intelligence (AI) based phase disposition pulse width modulation (PD-PWM). The Artificial Intelligence (AI) is the Gradient Boosting Decision Tree algorithm (GBDT). Hence it is named as GBDT-PD-PWM. Gradient boosting is a machine learning system that creates a prediction model in the group of weak prediction models, often decision trees. The multicell converter is employed as the grid side converter (GSC) of WECS to attenuate harmonics created by nonlinear load. For stacked multicellular converters (SMCs), a method of capacitor voltage balance based on PD-PWM approach is proposed. This technique is also known as "optimal transition voltage balancing system," which employs optimal switching transitions. This proposed method is the further development of the optimal state voltage balancing method (OSVB), where the number of switching is not optimized. The performance of the proposed technique is implemented in the MATLAB platform and compared with the existing methods. The performance of the proposed system is evaluated under the fault condition. The power loss of the proposed is less compared to the existing method, which is revealed from the simulation outcome.