A Novel Bio-Inspired Optimization Algorithm Design for Wind Power Engineering Applications Time-Series Forecasting.

Area of Science:

• Renewable Energy Systems
• Climate Change Adaptation
• Artificial Intelligence in Energy

Background:

• Climate change is altering wind patterns, leading to unpredictable wind power generation.
• Accurate wind power forecasting is crucial for grid stability and efficient energy management.
• Existing forecasting models struggle with the dynamic nature of wind patterns.

Purpose of the Study:

• To propose a novel Recurrent Neural Network (RNN) forecasting model integrated with a Dynamic Fitness Al-Biruni Earth Radius (DFBER) algorithm.
• To enhance the accuracy and reliability of wind power data pattern prediction.
• To compare the proposed model's performance against established optimization algorithms.

Main Methods:

• Development of a Recurrent Neural Network (RNN) model.
• Integration of the Dynamic Fitness Al-Biruni Earth Radius (DFBER) algorithm for parameter optimization.
• Comparative analysis using metrics like RRMSE, NSE, MAE, MBE, r, R2, and WI.
• Statistical validation using ANOVA and Wilcoxon Signed-Rank tests.

Main Results:

• The proposed RNN-DFBER model demonstrated superior performance over BER, JAYA, FHO, WOA, GWO, and PSO models.
• The model achieved higher accuracy and better agreement in predicting wind power data patterns.
• Statistical analyses confirmed the significance and reliability of the RNN-DFBER model's results.

Conclusions:

• The RNN-DFBER model offers a more effective approach to wind power forecasting.
• This advanced model can improve the predictability and performance of wind power systems.
• The findings support the use of integrated AI and optimization algorithms for renewable energy forecasting.