SHORT-TERM POWER FORECASTING BY STATISTICAL METHODS FOR PHOTOVOLTAIC PLANTS IN SOUTH ITALY

Maria Grazia De Giorgi, Paolo Maria Congedo, Maria Malvoni, Marco Tarantino
Abstract:
Statistical methods based on Multiregression Analysis and Artificial Neural Networks (ANNs) have been developed in order to predict power production of a 960 kWp grid-connected photovoltaic (PV) plant in the campus of the University of Salento, Italy.
The neural network has been used only as a statistic model based on time series of PV power and meteorological variables, as module temperature, ambient temperature and irradiance on module’s plain. In particular, a sensitivity analysis has been carried out in order to find those weather parameters with the best impact on the forecasting.
Keywords:
forecasting, photovoltaic power, Artificial Neural Networks, prediction, Multiregression Analysis
Download:
IMEKO-TC19-2013-034.pdf
DOI:
-
Event details
IMEKO TC:
TC19
Event name:
Protecting Environment, Climate Changes and Pollution Control
Title:
4th Symposium on Environmental Instrumentation and Measurements
Place:
Lecce, ITALY
Time:
03 June 2013 - 04 June 2013