Machine Learning-Driven Forecasting of Power Generation in Agri-Photovoltaics System

Solar PV technology is increasingly recognized as a pivotal solution in combating climate change and transitioning towards renewable energy. This paper delves into the intricate landscape PV energy, with a specific focus on predictive modeling of Agri-photovoltaic (APV). This paper implements several Machine Learning models such as Artificial Neural Network (ANN), Gaussian Process Regression (GPR), Linear Regression (LR), Decision Tree (DT), and Support Vector Machine (SVM) to predict the APV power generation of a APV project which is located in Gujarat, India. All models underwent evaluation using root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and the coefficient of determination (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>). Based on the model performance metrics, LR, GPR and ANN model surpassed all others for APV. The SVM model demonstrated characteristics of over fitting. Despite a few research studies predicting ground-mounted PV energy yield, there is limited to no research on APV energy yield prediction in the South Asian region. Hence, this paper presents a novel approach to forecasting APV energy yield using the above-mentioned machine learning regression models.