Photovoltaic (PV) power production increased drastically in Europe throughout the last years. Since about the 6% of electricity in Italy comes from PV, an accurate and reliable forecasting of production would be needed for an efficient management of the power grid. We investigate the possibility to forecast daily PV electricity production up to ten days without using on-site measurements of meteorological variables. Our study uses a PV production dataset of 65 Italian sites and it is divided in two parts: first, an assessment of the predictability of meteorological variables using weather forecasts; second, an analysis of predicting solar power production through data-driven modelling. We calibrate Support Vector Machine (SVM) models using available observations and then we apply the same models on the weather forecasts variables to predict daily PV power production. As expected, cloud cover variability strongly affects solar power production, we observe that while during summer the forecast error is under the 10% (slightly lower in south Italy), during winter it is abundantly above the 20%.
De Felice, M., Petitta, M., Ruti, P.M. (2015). Short-term predictability of photovoltaic production over Italy. RENEWABLE ENERGY, 80, 197-204 [10.1016/j.renene.2015.02.010].
Short-term predictability of photovoltaic production over Italy
Petitta M.;
2015-01-01
Abstract
Photovoltaic (PV) power production increased drastically in Europe throughout the last years. Since about the 6% of electricity in Italy comes from PV, an accurate and reliable forecasting of production would be needed for an efficient management of the power grid. We investigate the possibility to forecast daily PV electricity production up to ten days without using on-site measurements of meteorological variables. Our study uses a PV production dataset of 65 Italian sites and it is divided in two parts: first, an assessment of the predictability of meteorological variables using weather forecasts; second, an analysis of predicting solar power production through data-driven modelling. We calibrate Support Vector Machine (SVM) models using available observations and then we apply the same models on the weather forecasts variables to predict daily PV power production. As expected, cloud cover variability strongly affects solar power production, we observe that while during summer the forecast error is under the 10% (slightly lower in south Italy), during winter it is abundantly above the 20%.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.