Using Adaptive Safe Experimentation Dynamics Algorithm for Maximizing Wind Farm Power Production

This research presents a model-free strategy for increasing wind farm power generation based on the Adaptive Safe Experimentation Dynamics Algorithm (ASEDA). The ASEDA method is an improved version of the Safe Experimentation Dynamics (SED) algorithm that modifies the current tuning variable to resp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2022 57th International Universities Power Engineering Conference (UPEC) S. 1 - 4
Hauptverfasser: Ahmad, Mohd Ashraf, Jui, Julakha Jahan, Ghazali, Mohd Riduwan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 30.08.2022
Schlagworte:
Adaptation models
Heuristic algorithms
Linear programming
power generation
Prediction algorithms
renewable energy
safe experimentation dynamics
Wind energy generation
wind farm
Wind farms
Wind power generation
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This research presents a model-free strategy for increasing wind farm power generation based on the Adaptive Safe Experimentation Dynamics Algorithm (ASEDA). The ASEDA method is an improved version of the Safe Experimentation Dynamics (SED) algorithm that modifies the current tuning variable to respond to the changes in the objective function. The convergence accuracy is predicted to be enhanced further by adding the adaptive element to the modified SED equation. The ASEDA-based technique is used to determine the ideal control parameter for each turbine to maximize a wind farm's total power generation. A single single-row wind farm prototype with turbulence coupling among turbines is employed to validate the proposed approach. Simulation findings show that the ASEDA-based approach provides more total power generation than the original SED technique.
DOI:10.1109/UPEC55022.2022.9917785