Enhancing Dynamic Wind Power Forecasting Using Cluster-Based Intelligence Swarm Optimization Technique

The dynamic forecasting of wind power is critical for the efficient and reliable operation of wind farms. Accurate predictions in wind power can enhance energy production and distribution strategies. It also reduces energy costs and improves the overall efficiency of wind energy generation. In this paper, the Cluster-based Intelligence Swarm optimization technique for Dynamic Wind Power Forecasting (CISWP) is proposed. It combines cluster analysis and swarm intelligence optimization algorithms to forecast wind power based on meteorological data. The CISWP technique clusters meteorological data into groups. Next, it optimizes the forecasting model parameters for each cluster using swarm intelligence optimization (sperm whale algorithm). The performance of the CISWP technique is evaluated on the publicly available Spatial Dynamic Wind Power Forecasting SDWPF dataset. The SDWPF dataset contains hourly measurements of meteorological variables and wind power generation data from a wind. The results of our experiments show that the CISWP technique outperforms other clustering and optimization algorithms in terms of forecasting accuracy and reliability. The CISWP approach is a promising approach for wind power forecasting that can improve the efficiency and reliability of wind energy generation.