Machine Learning Method for Solar PV Output Power Prediction

Sharkawy, Abdel-Nasser; Ali, Mustafa M.; Mousa, Hossam H. H.; Ali, Ahmed S.; Abdel-Jaber, G. T.

doi:10.21608/svusrc.2022.157039.1066

Machine Learning Method for Solar PV Output Power Prediction

Document Type : Original research articles

Authors

¹ Mechatronics Engineering, Mechanical Engineering Department, Faculty of Engineering, South Valley University, Qena 83523, Egypt

² Mechatronics Engineering, Department of Mechanical Engineering, South Valley University, Qena 83523, Egypt

³ Department of Electrical Engineering, South Valley University, Qena 83523, Egypt

⁴ Mechatronics Engineering, Department of Mechanical Engineering, Assiut University, Assiut, Egypt

10.21608/svusrc.2022.157039.1066

Abstract

To deal with the challenges of the solar photovoltaic (PV) energy source due to the continuous variations of the climatic conditions such as temperature and solar radiation, output power prediction is one of the most important research trends nowadays. In this paper, a multilayer feedforward neural network (MLFFNN) is executed to foresee the power for a solar PV power station. The MLFFNN employs the temperature and radiation as the inputs and the power as the output. For training and testing the MLFFNN, data of 6 days are acquired from a real PV power station in Egypt. The first five days are employed to train the MLFFNN using Levenberg-Marquardt (LM) algorithm. While the data of the sixth day, are used to check the effectiveness and the generalization ability of the trained MLFFNN. The results prove that the trained MLFFNN is working very well and efficient to predict the PV output power correctly.

Keywords