Improved DFIG-Based Power Quality Controller Based on Machine Learning Cascaded Neural Networks

Due to its numerous benefits, sources of clean energy are utilized to generate electricity. The most effective Renewable Energy Source (RES) for power generation is wind. Typically, power network and wind system are directly connected to supply power. Doubly Fed Induction Generator (DFIG) is widely utilized in Wind Energy Conversion Systems (WECSs) because of its compact shape, affordable price, high efficiency, and independent power regulation. Managing quality of power issues including swells, voltage sag, flickers, harmonics, etc., are challenges that are directly associated. Peripheral correction is necessary to improve the Power quality (PQ) in a power network using WECS. The novelty of this work lies in its unique approach to improving power quality in Wind Energy Conversion Systems (WECS) using a cascaded Artificial Neural Network (ANN). Pulse Width Modulation (PWM) generator provides required gate signal for the operation of PWM rectifier. Proportional Integral (PI) controller is employed to enhance, a Three Phase Voltage Source Inverter (3ϕ VSI) connected to grid. PWM rectifier, which is utilized in WECS employing DFIG, converts AC to DC with assistance of a PI controller. Making use of Bidirectional battery converter, battery charging and discharging is performed efficiently. The overall system is executed in MATLAB Simulink software and corresponding outcomes are attained. Total Harmonics Distortion (THD) value attained for proposed system is 1.76%.