Photovoltaic energy production forecast using support vector regression

AbstractForecasting models for photovoltaic energy production are important tools for managing energy flows. The aim of this study was to accurately predict the energy production of a PV plant in Italy, using a methodology based on support vector machines . The model uses historical data of solar irradiance, environmental temperature and past energy production to predict the PV energy production for the next day with an interval of 15 min. The technique used is based on $$\nu $$ν-SVR, a support vector regression model where you can choose the number of support vectors. The forecasts of energy production obtained with the proposed methodology are very accurate, with the $$R^{2}$$R2 coefficient exceeding 90 % . The quality of the predicted values strongly depends on the goodness of the weather forecast, and the $$R^{2}$$R2 value decreases if the predictions of irradiance and temperature are not very accurate.

[1]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[2]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[3]  Renato De Leone,et al.  Support Vector Machines for Robust Regression , 2012, CTW.

[4]  Francesco Grimaccia,et al.  Artificial Intelligence Forecast of PV Plant Production for Integration in Smart Energy Systems , 2012 .

[5]  Gerhard-Wilhelm Weber,et al.  On numerical optimization theory of infinite kernel learning , 2010, J. Glob. Optim..

[6]  J. Weston,et al.  Support vector regression with ANOVA decomposition kernels , 1999 .

[7]  Pierluigi Maponi,et al.  Reducing Power Consuption in Hydrometric Level Sensor Network Using Support Vector Machines , 2013, PECCS 2013.

[8]  Renato De Leone.  Support Vector Regression for Time Series Analysis , 2010, OR.

[9]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[10]  Alexander J. Smola,et al.  Guest editorial: model selection and optimization in machine learning , 2011, Machine Learning.

[11]  H.-D. Musikowski,et al.  Forecasting Photovoltaic Energy Using a Fourier Series Based Method , 2008 .

[12]  Ethem Alpaydin,et al.  Multiple Kernel Learning Algorithms , 2011, J. Mach. Learn. Res..

[13]  Henrik Madsen,et al.  Online short-term solar power forecasting , 2009 .

[14]  Simon Haykin,et al.  Support vector machines for dynamic reconstruction of a chaotic system , 1999 .

[15]  Pierluigi Maponi,et al.  Reducing Power Consumption in Hydrometric Level Sensor Networks using Support Vector Machines , 2013, PECCS.

[16]  Sebastian Nowozin,et al.  Infinite Kernel Learning , 2008, NIPS 2008.

[17]  Bernhard Schölkopf,et al.  Shrinking the Tube: A New Support Vector Regression Algorithm , 1998, NIPS.

[18]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[19]  Gerhard-Wilhelm Weber,et al.  Infinite kernel learning via infinite and semi-infinite programming , 2010, Optim. Methods Softw..

[20]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.

[21]  Chih-Jen Lin,et al.  Training v-Support Vector Regression: Theory and Algorithms , 2002, Neural Computation.

[22]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[23]  C. Schwaegerl.  Advanced Architectures and Control Concepts for More Microgrids , 2008 .

[24]  Renato De Leone,et al.  Support Vector Machine for Robust Regression , 2012 .

[25]  Yoshihisa Uchida,et al.  Forecast of Power Production of a Photovoltaic Power Plant in Japan with Multilayer Perceptron Artificial Neural Networks and Support Vector Machines , 2011 .

[26]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[27]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[28]  Francesco Grimaccia,et al.  Hybrid Predictive Models for Accurate Forecasting in PV Systems , 2013 .

[29]  Eleonora D'Andrea,et al.  One day-ahead forecasting of energy production in solar photovoltaic installations: An empirical study , 2012, Intell. Decis. Technol..

[30]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[31]  Joao Gari da Silva Fonseca,et al.  Photovoltaic power production forecasts with support vector regression: A study on the forecast horizon , 2011, 2011 37th IEEE Photovoltaic Specialists Conference.