Predicting Solar and Wind Power Production with the Weather Map Data Approach

Renewable energy technologies, such as solar and wind power, play a pivotal role in addressing the growing energy demands of the modern world while mitigating environmental concerns. However, the intermittent and weather-dependent nature of these energy sources presents a significant challenge in harnessing their full potential. This research aims to enhance the precision of forecasting solar and wind power production, thus addressing the current technology deficit in this area. The aim of this research is to develop advanced predictive models that can accurately forecast solar and wind power production. The problem statement is formulated as follows: “To predict solar and wind power generation with high precision by leveraging meteorological data and advanced data analytics techniques.” This research methodology involves the fusion of historical weather data, machine learning algorithms, and time series analysis, specifically employing the comparative predictions of AutoRegressive Integrated Moving Average (ARIMA) and F- Prophet model. The results highlight the successful development of ARIMA and F-Prophet based predictive models for solar and wind power generation. These models exhibit remarkable accuracy in short-term forecasting, demonstrating their effectiveness in addressing the intermittent nature of renewable energy sources. Key numerical results indicate prediction accuracies exceeding 90% for both solar and wind power.