RT journal article
T1 Evaluating and analyzing the performance of PV power output forecasting using different models of machine-learning techniques considering prediction accuracy
A1 Bouakkaz, Abderraouf
A1 Lahsasna, Adel
A1 Gil Mena, Antonio José
A1 Haddad, Salim
A1 Ferrari, Mario Luigi
A1 Jiménez Castaneda, Rafael
A2 Ingeniería Eléctrica
K1 Solar energy
K1 Power production
K1 Energy forecasting
K1 Machine learning
K1 Cross-validation
K1 Accuracy of predictions
AB Solar energy as a clean, renewable, and sustainable energy source has considerable potential to meet global energy needs. However, theintermittent and uncertain character of the solar energy source makes the power balance management a very challenging task. To overcome theseshortcomings, providing accurate information about future energy production enables better planning, scheduling, and ensures effective strategies tomeet energy demands. The present paper aims to assess the performance of PV power output forecasting in PV systems using various machinelearning models, such as artificial neural networks (ANN), linear regression (LR), random forests (RF), and Support Vector Machines (SVM). Theselearning algorithms are trained on two different datasets with different time steps: in the first one, a historical weather forecast with a one hour timestep, and in the second one, a dataset of on-site measurements with a 5-minute time step. To provide a reliable estimation of prediction accuracy fordifferent learning algorithms, a k-fold cross-validation (CV) is applied. Through a comparison analysis, an assessment of the accuracy of thesealgorithms based on various metrics such as RMSE, MAE, and MRE is performed, providing a detailed evaluation of their performance. Resultsobtained from this study demonstrate that the random forest algorithm (RF) outperformed other algorithms in predicting PV output, achieving thesmallest prediction error, where the best values for RMSE, MRE, MAE, and R² for the weather dataset were 0.856 W, 0.256%, 0.364 W, and 0.99999,respectively, while thevalues for RMSE, MRE, MAE, and R² for the on-site measurements dataset were 8.525 W, 11.163%, 3.922 W, and 0.99922,respectively.
PB Diponegoro university Indonesia - Center of Biomass and Renewable Energy (CBIORE)
SN 2252-4940
YR 2025
FD 2025
LK http://hdl.handle.net/10498/36372
UL http://hdl.handle.net/10498/36372
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 10-may-2026