Predicting Active Solar Power with Machine Learning and Weather Data

Artificial intelligence (AI) is crucial in optimizing energy consumption, improving renewable energy systems, enhancing efficiency, and enabling sustainability efforts and smart grid management. It facilitates the development of predictive models, like in the study, optimizing renewable energy use and reducing environmental impact. Leveraging AI helps us make informed decisions, reduce waste, and promote sustainable practices across industries for a greener future. The study’s goal was to develop a predicting model for solar photovoltaic (PV) systems that could account for weather unpredictability. To accomplish this goal, we collected data from both the plant inverter and the weather measurement system and used machine learning techniques like linear regression, random forest, principal component analysis, and support vector regression with RBF kernel to examine the data and create a model that can accurately predict the power output. The developed model may be used in any location for preliminary testing and estimating, allowing solar energy to be captured more successfully and consistently in the face of changing weather circumstances. We obtained 0.87 as the highest R 2 value with 0.002 as a mean square error.