Evaluation of Machine Learning Models in Solar Radiation Prediction for Photovoltaic System Design

¹ Facultad de Ciencias de la Ingeniería y Aplicadas, Universidad Técnica de Cotopaxi, Ecuador
² Departamento de Ciencias Exactas, Universidad de las Fuerzas Armadas ESPE, Sangolquí, Ecuador
³ Department of Engineering Sciences, Universidad Tecnológica Israel, Quito, Ecuador
⁴ Departamento de Ingeniería Electrónica y Telecomunicaciones, Universidad Nacional de Piura, Perú

^* Corresponding author: edgar.salazar7619@utc.edu.ec

Abstract

This research evaluates machine learning models in predicting solar radiation, crucial for designing photovoltaic systems. Accuracy in solar forecasting is key to mitigating climate change and meeting energy demand. Advanced machine learning techniques were applied, surpassing traditional models in precision and efficiency, including SARIMA, Random Forests, SVM, ANN, and LSTM, assessed with metrics such as accuracy, sensitivity, precision, NME, R2, and execution time. After normalization, the SVM model achieved the highest overall score of 5.86. A photovoltaic system was sized using an SVM model with solar radiation data (2017-2020). Predictions calculated an average daily consumption of 4.89 kWh, a total daily energy of 109.88 kWh, and a solar panel area of 4.42 m2. The system’s peak power is 0.86 kWp, and the inverter power with a safety margin is 1.04 kW.