Optimizing Wind Turbine Control with Energy Valley Algorithm
Author Information
Author(s): Elnaghi Basem E., Ismaiel Ahmed M., El Sayed Abdel-Kader Fathy, Abelwhab M. N., Mohammed Reham H.
Primary Institution: Suez Canal University
Hypothesis
The Energy Valley Optimizer Approach (EVOA) can enhance the performance of adaptive fuzzy logic controllers (AFLCs) for DFIG-based wind turbines.
Conclusion
The EVOA-AFLC significantly outperforms other optimization techniques, achieving better speed tracking and reduced errors in wind power applications.
Supporting Evidence
- EVOA-AFLC improved speed tracking by 86.3% compared to MPA-PI.
- EVOA-AFLC achieved a 71.2% reduction in average integral absolute errors compared to GA-AFLC.
- EVOA-AFLC demonstrated faster convergence and better performance metrics than C-BO and GA-based controllers.
Takeaway
This study shows that a new method can help wind turbines work better by making them faster and more accurate at capturing energy from the wind.
Methodology
The study used experimental assessments with the DSpace DS1104 control board to validate the performance of EVOA-based AFLCs against other optimization techniques.
Limitations
The study may not account for all real-world conditions affecting wind turbine performance.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website