Differential Evolution Based IDWNN Controller for Fault Ride-Through of Grid-Connected Doubly Fed Induction Wind...

Area of Science:

• Electrical Engineering
• Renewable Energy Systems
• Control Systems

Background:

• Wind turbines (WTs) are crucial for increasing power output and grid stability.
• Doubly fed induction generators (DFIGs) in WTs traditionally use crowbar systems for fault protection.
• Crowbar systems limit DFIGs' ability to supply reactive power during grid faults.

Purpose of the Study:

• To develop a novel heuristic controller for grid-connected wind turbines with DFIGs.
• To enhance the low-voltage ride-through (LVRT) capability of wind turbines during grid faults.
• To ensure WTs provide necessary reactive power support to the grid post-fault.

Main Methods:

• Implementation of a heuristic controller module.
• Utilizing differential evolution and neural network architecture (specifically, a double wavelet neural network).
• Simulation of a wind farm case study (1.5 MW WTs, 25 kV distribution, 120 kV grid).

Main Results:

• The proposed controller effectively enhances DFIG converter performance during grid faults.
• The heuristic controller eliminates the need for traditional crowbar systems.
• Wind turbines successfully supply reactive power to the grid during fault conditions, aiding voltage stability.

Conclusions:

• The novel heuristic controller improves LVRT performance without additional hardware.
• The differential evolution-tuned double wavelet neural network controller is effective for DFIG-based WTs.
• This approach ensures grid stability by maintaining reactive power supply during faults.