Optimum Power Forecasting Technique for Hybrid Renewable Energy Systems Using Deep Learning

Abstract

Power forecasting in large-scale electrical systems, comprising photovoltaic (PV), solar, and wind power, faces challenges due to geographical diffusion and temporal variations. Despite numerous studies, the disparity between predicted and actual generation remains a significant issue. This study utilizes historical power and atmospheric data from diverse plants, employing preprocessing techniques to enhance quality and reduce noise. K-Means clustering is applied to the dataset, optimizing deep learning training periods and increasing accuracy. A resilient hybrid deep learning model is proposed for microgrid (MG) power forecasting, encompassing preprocessing, model training, and assessment stages. Mathematical models for PV systems, battery storage, and wind systems, along with a K-means clustering algorithm, contribute to accurate forecasting. The recurrent neural network based on gated recurrent unit architecture outperforms traditional algorithms, demonstrating superior accuracy, and reduced errors in extensive experimental analyses. Pearson coefficients reveal associations between different power production forms, emphasizing the potential of hybrid renewable energy clusters to enhance forecasting. Case studies illustrate the partial controllability of concentrated solar power production, reducing overall renewable energy cluster unpredictability. The proposed method showcases the efficacy of the hybrid model in addressing challenges and improving accuracy in large-scale power forecasting.