Constrained Support Vector Machines for photovoltaic in-feed prediction

In this paper, we introduce a constrained Support Vector Machine (SVM) to predict photovoltaic (PV) in-feed. We derive the SVM algorithm with linear constraints and test the method on German PV in-feed with constraints reflecting physical boundaries. We show that the new algorithm shows a significant better performance than a constrained ordinary least squares (OLS) estimator.

[1]  Peng Wang,et al.  Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines , 2011, IEEE Transactions on Industry Applications.

[2]  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.

[3]  Qing He,et al.  Extreme Support Vector Machine Classifier , 2008, PAKDD.

[4]  Benoît Frénay,et al.  Using SVMs with randomised feature spaces: an extreme learning approach , 2010, ESANN.

[5]  R. Shah,et al.  Least Squares Support Vector Machines , 2022 .

[6]  B. De Moor,et al.  Electric Load Forecasting , 2007, IEEE Control Systems.

[7]  Johan A. K. Suykens,et al.  Electric Load Forecasting: Using Kernel-Based Modeling for Nonlinear System Identification , 2007 .

[8]  Laurent Dubus,et al.  Analog Method for Collaborative Very-Short-Term Forecasting of Power Generation from Photovoltaic Systems , 2011 .

[9]  Hao Chen,et al.  Short-term photovoltaic power forecasting with weighted support vector machine , 2012, 2012 IEEE International Conference on Automation and Logistics.

[10]  David Atienza,et al.  Prediction and management in energy harvested wireless sensor nodes , 2009, 2009 1st International Conference on Wireless Communication, Vehicular Technology, Information Theory and Aerospace & Electronic Systems Technology.

[11]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[12]  S. Kavatza,et al.  A hybrid non-linear regression midterm energy forecasting method using data mining , 2003, 2003 IEEE Bologna Power Tech Conference Proceedings,.