TY - GEN
T1 - A bayesian-based neural network model for solar photovoltaic power forecasting
AU - Ciaramella, Angelo
AU - Staiano, Antonino
AU - Cervone, Guido
AU - Alessandrini, Stefano
N1 - Publisher Copyright:
© Springer International Publishing Switzerland 2016.
PY - 2016
Y1 - 2016
N2 - Solar photovoltaic power (PV) generation has increased constantly in several countries in the last ten years becoming an important component of a sustainable solution of the energy problem. In this paper, a methodology to 24 h or 48 h photovoltaic power forecasting based on a Neural Network, trained in a Bayesian framework, is proposed. More specifically, a multi-ahead prediction Multi-Layer Perceptron Neural Network is used, whose parameters are estimated by a probabilistic Bayesian learning technique. The Bayesian framework allows obtaining the confidence intervals and to estimate the error bars of the Neural Network predictions. In order to build an effective model for PV forecasting, the time series of Global Horizontal Irradiance, Cloud Cover, Direct Normal Irradiance, 2-m Temperature, azimuth angle and solar Elevation Angle are used and preprocessed by a Linear Predictive Coding technique. The experimental results show a low percentage of forecasting error on test data, which is encouraging if compared to state-of-the-art methods in literature.
AB - Solar photovoltaic power (PV) generation has increased constantly in several countries in the last ten years becoming an important component of a sustainable solution of the energy problem. In this paper, a methodology to 24 h or 48 h photovoltaic power forecasting based on a Neural Network, trained in a Bayesian framework, is proposed. More specifically, a multi-ahead prediction Multi-Layer Perceptron Neural Network is used, whose parameters are estimated by a probabilistic Bayesian learning technique. The Bayesian framework allows obtaining the confidence intervals and to estimate the error bars of the Neural Network predictions. In order to build an effective model for PV forecasting, the time series of Global Horizontal Irradiance, Cloud Cover, Direct Normal Irradiance, 2-m Temperature, azimuth angle and solar Elevation Angle are used and preprocessed by a Linear Predictive Coding technique. The experimental results show a low percentage of forecasting error on test data, which is encouraging if compared to state-of-the-art methods in literature.
UR - http://www.scopus.com/inward/record.url?scp=84977138112&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84977138112&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-33747-0_17
DO - 10.1007/978-3-319-33747-0_17
M3 - Conference contribution
AN - SCOPUS:84977138112
SN - 9783319337463
T3 - Smart Innovation, Systems and Technologies
SP - 169
EP - 177
BT - Advances in Neural Networks - Computational Intelligence for ICT
A2 - Esposito, Anna
A2 - Esposito, Anna
A2 - Morabito, Francesco Carlo
A2 - Pasero, Eros
A2 - Bassis, Simone
PB - Springer Science and Business Media Deutschland GmbH
T2 - International Workshop on Neural Networks, WIRN 2015
Y2 - 20 May 2015 through 22 May 2015
ER -