A novel combination model for ultra-short-term wind speed prediction

Area of Science:

• Renewable Energy Systems
• Computational Intelligence
• Data Science

Background:

• Accurate ultra-short-term wind speed forecasting is vital for efficient wind farm operation.
• Existing prediction models often lack sufficient precision due to data complexity.
• Parameter selection for decomposition techniques can be challenging.

Purpose of the Study:

• To develop a highly accurate ultra-short-term wind speed prediction model.
• To enhance the precision of wind speed forecasts for wind farm control.
• To address limitations in current forecasting methodologies.

Main Methods:

• Integration of Variational Mode Decomposition (VMD), Sparrow Search Algorithm (SSA), and Long Short-Term Memory (LSTM).
• Optimization of VMD parameters (modal components, penalty factor) using the Archimedean Optimization Algorithm (AOA).
• Optimization of LSTM parameters (hidden units, iterations, learning rate) using SSA.

Main Results:

• The proposed VMD-SSA-LSTM model demonstrated superior performance in ultra-short-term wind speed prediction.
• Validation using National Data Buoy Center (NDBC) data confirmed the model's effectiveness.
• Achieved an approximate prediction accuracy of 97%.

Conclusions:

• The developed model offers a novel and accurate approach for ultra-short-term wind speed forecasting.
• Adaptive parameter optimization significantly improves prediction model performance.
• This method provides a valuable tool for optimizing wind farm operations.