Enhanced Wind Power Forecasting Using a Hybrid Multi-Strategy Coati Optimization Algorithm and Backpropagation Neural...

Area of Science:

• Renewable Energy Systems
• Artificial Intelligence
• Computational Optimization

Background:

• Integrating intermittent wind power requires accurate forecasting for grid stability.
• Traditional backpropagation (BP) neural networks face challenges like slow convergence and local optima.

Purpose of the Study:

• To develop a novel hybrid framework, the Multi-Strategy Coati Optimization Algorithm (SZCOA)-optimized BP neural network (SZCOA-BP).
• To enhance the optimization efficiency and robustness of BP networks for wind power forecasting.

Main Methods:

• The SZCOA algorithm incorporates global exploration, local optima evasion, and refined exploitation strategies.
• The SZCOA was benchmarked on CEC2017, outperforming ICOA, DBO, and PSO.
• The SZCOA-BP model was applied to a real-world wind power dataset.

Main Results:

• SZCOA demonstrated superior convergence speed and solution accuracy on benchmarks.
• The SZCOA-BP model achieved an R² of 94.437% and reduced MAE to 10.948 on wind power data.
• SZCOA-BP significantly outperformed standard BP (R²: 81.167%, MAE: 18.891) and other hybrid models.

Conclusions:

• The SZCOA-BP framework offers a dominant solution for accurate and stable wind power forecasting.
• This approach provides a scalable method for optimizing complex renewable energy systems.
• The study supports global sustainable energy transition efforts through advanced forecasting techniques.