Enhancing MPPT performance of a grid-connected Doubly-Fed induction generator-based wind power plant using hybrid...

Area of Science:

• Renewable Energy Systems
• Control Engineering
• Artificial Intelligence in Power Systems

Background:

• Grid-connected wind power plants, especially those using Doubly-Fed Induction Generators (DFIGs), face challenges in maintaining Maximum Power Point Tracking (MPPT) efficiency due to fluctuating wind speeds, parameter uncertainties, and grid disturbances.
• Optimizing energy capture from variable wind resources is crucial for the economic viability and grid integration of wind power.

Purpose of the Study:

• To develop and evaluate an effective control technique for enhancing the MPPT performance of a grid-connected DFIG-based wind power plant.
• To address the limitations of existing control methods in handling rapid wind speed variations and grid disturbances.

Main Methods:

• A modified dynamic DFIG-based wind turbine system was modeled.
• A hybrid Adaptive Neuro-Fuzzy Inference System (ANFIS) integrated with a Proportional-Integral (PI) controller was developed for the back-to-back converter.
• Real-world wind speed and power generation data from the Adama II wind power plant in Ethiopia were used for training and validation.

Main Results:

• The proposed ANFIS-PI controller achieved a Maximum Power Point Tracking (MPPT) of 2.22 MW, outperforming the Fuzzy Logic Controller (FLC)-PI which reached 2.2 MW.
• The maximum power coefficient was improved to 0.5504 with the ANFIS-PI, compared to 0.5473 with the FLC-PI, against a baseline of 0.4109.
• Simulations were conducted using MATLAB-Simulink R2024a.

Conclusions:

• The hybrid ANFIS-PI controller offers a superior control strategy for enhancing MPPT performance in DFIG-based wind power plants under dynamic wind conditions.
• The developed technique demonstrates significant improvements in power capture and efficiency, contributing to more reliable and efficient wind energy integration.