In recent years, the strong growth in solar power generation industries is requiring an increasing need to predict the profile of solar power production over the day, in order to develop high efficient and optimized stand-alone and grid connected photovoltaic systems. Moreover, the opportunities offered by battery energy storage systems coupled with PV systems, require the load power to be forecasted as well, in order to optimize the size of the entire system composed by PV panels and storage. In this work is proposed a predictive model based on feed-forward neural network trained with Levenberg-Marquardt back-propagation learning algorithm, to forecast solar irradiation and load power consumption using past values of these vectors, as well as exogenous inputs like ambient temperature or wind speed.
Solar radiation and load power consumption forecasting using neural network
Brenna, Morris;Foiadelli, Federica;Longo, Michela;Zaninelli, Dario
2017-01-01
Abstract
In recent years, the strong growth in solar power generation industries is requiring an increasing need to predict the profile of solar power production over the day, in order to develop high efficient and optimized stand-alone and grid connected photovoltaic systems. Moreover, the opportunities offered by battery energy storage systems coupled with PV systems, require the load power to be forecasted as well, in order to optimize the size of the entire system composed by PV panels and storage. In this work is proposed a predictive model based on feed-forward neural network trained with Levenberg-Marquardt back-propagation learning algorithm, to forecast solar irradiation and load power consumption using past values of these vectors, as well as exogenous inputs like ambient temperature or wind speed.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.