Comparative Study of Neural Network and Tree-Based Models in Solar Irradiance Prediction

Abstract

Solar Photovoltaic Systems have become the most promising technology for clean energy generation in recent years. Solar irradiation is one of the critical factors that affect Photovoltaic output. Since the Photovoltaic output varies significantly during the day, accurate solar irradiation forecasting is essential for predicting Photovoltaic output. Many machine-learning models have been used to forecast solar irradiation in the last few decades. This paper evaluates the performance of two basic machine-learning models: Artificial Neural Networks and Tree-based methods for solar irradiance prediction. Two neural networks such as Multilayer Perceptron, Radial Basis Function Neural Network, and three tree-based models such as Classification and Regression Tree, Alternating Model Tree, and Random Forest are applied to predict the solar irradiance using the NASA Solar Irradiation dataset. The performance of those methods is assessed using various metrics like the Correlation Coefficient, Mean Absolute Error, and Root Mean Squared Error. The experimental results show that the tree-based ensemble methods perform significantly better than neural network models for solar irradiance prediction.