Enhanced Harmonics Reactive Power Control Strategy Based on Multilevel Inverter Using ML-FFNN for Dynamic Power Load...

Area of Science:

• Electrical Engineering
• Renewable Energy Systems
• Control Theory

Background:

• The global shift to renewable energy sources (RES) necessitates improved efficiency and stability at the point of common coupling (PCC).
• Harmonics, voltage unbalance, and lack of inertia in microgrids cause power quality issues and instability at the PCC.
• Traditional passive filters and Synchronous Reference Frame (SRF) control methods have limitations in addressing these challenges.

Purpose of the Study:

• To develop and evaluate an intelligent control scheme for harmonic suppression and reactive power compensation in renewable energy systems.
• To enhance the stability and power quality at the point of common coupling (PCC).
• To minimize errors in voltage regulation using a multi-layer feed forward neural network (ML-FFNN).

Main Methods:

• Implementation of a multi-layer feed forward neural network (ML-FFNN) for intelligent control.
• Utilizing sine pulse width modulation (SPWM) for multilevel inverter gate signals.
• Employing Synchronous Reference Frame (SRF) control as a baseline for comparison.
• Simulations conducted in MATLAB Simulink to validate the proposed method.

Main Results:

• The proposed ML-FFNN-based control scheme demonstrated superior performance in harmonic suppression and reactive power compensation compared to SRF methods.
• The intelligent control technique achieved significant reductions in Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE).
• MATLAB Simulink simulations confirmed the effectiveness and efficiency of the proposed control strategy.

Conclusions:

• The developed ML-FFNN-based control technique offers a more effective solution for harmonic and reactive power control in renewable energy systems.
• This intelligent approach enhances power quality and stability at the point of common coupling (PCC).
• The study highlights the potential of advanced neural network control for future microgrid and renewable energy integration.