Artificial neural network controlled DSTATCOM for mitigating power quality concerns in solar PV and wind system

Area of Science:

• Electrical Engineering
• Renewable Energy Systems
• Power Quality

Background:

• Growing global energy demand necessitates sustainable alternatives to depleting fossil fuels.
• Photovoltaic (PV) and wind power are key renewable energy sources, but their integration poses power quality challenges.
• Harmonic distortions from power electronics in PV and wind systems threaten grid stability.

Purpose of the Study:

• To propose and evaluate an Artificial Neural Network (ANN) based Distribution Static Synchronous Compensator (DSTATCOM) for mitigating power quality issues.
• To address the limitations of traditional DSTATCOM control methods in variable load conditions.
• To enhance the reliability and efficiency of integrated PV and wind power systems.

Main Methods:

• Development of a DSTATCOM control model utilizing an enhanced Artificial Neural Network (XANN) approach.
• Simulation of the proposed model in MATLAB to assess its performance.
• Validation of simulation results through real-time experimental setup.

Main Results:

• The XANN-based DSTATCOM effectively mitigates harmonic distortions in PV-wind power systems.
• The proposed model demonstrates superior performance, particularly under uneven and non-linear loading scenarios.
• Significant improvements in overall power quality were observed.

Conclusions:

• The ANN-based DSTATCOM, specifically the XANN approach, offers a robust solution for power quality enhancement in renewable energy systems.
• This technology is crucial for maximizing the potential of sustainable energy integration.
• The validated results confirm the efficacy of the proposed method for real-world applications.