Prediction Of Photovoltaic Power Output Based on Real Data Using Adaptive Neuro Fuzzy Inference System and Artificial Neural Network

Abstract

This study discusses the performance of PV power output as it relates to different environmental factors such as solar irradiance and PV cells. Accurate forecast of solar power output is essential for effective energy management systems. A research study records data on parameters such as PV voltage output, PV current output, PV cell temperature, and solar irradiation. This information is then utilized to forecast PV power output. The prediction methods used include computational methods and AI techniques, particularly the Adaptive Neuro Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN). The research finds significant differences in Mean Squared Error (MSE) values. The computational method produces the highest MSE value of , whereas ANFIS and ANN achieve significantly lower MSE values of and , respectively.  Based on this analysis, it is concluded that the ANFIS configuration provides a more accurate forecast compared to the actual data.