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

Abstract

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 called decision trees. The multicell converter is employed as the grid side converter (GSC) of WECS to attenuate harmonics created by nonlinear load. For stacked multicell converters (SMCs), a method of capacitor voltage balance based on PD-PWM approach is proposed.