Very short term Solar Irradiance Prediction for a microgrid system in Taiwan based on Hybrid of Support Vector Regression and Grey Theory

In recent years, energy crisis becomes a global issue. The use of renewable energy in electricity generation has increased significantly. Natural resource such as solar energy is available in large amount, but it is unpredictable. Solar Irradiance Prediction (SIP) is very important to estimate Photovoltaic (PV) power generation. The generated power of PV will affect power dispatch, scheduling, or even the stability of a microgrid system. This paper proposes to use the Hybrid of Support Vector Regression (SVR) and Grey Theory Models for very short term (VST) SIP (in the range of minutes). The proposed model has been validated with the actual measured data and will be implemented in the Energy Management System (EMS) of a microgrid system in Taiwan. Comparing to the models based on either the Grey theory or the SVR, the proposed method yields higher accuracy.

[1]  M. Karkoub,et al.  Modeling climate parameters for renewable energy applications in the UAE using neural networks , 2009, 2009 CIGRE/IEEE PES Joint Symposium Integration of Wide-Scale Renewable Resources Into the Power Delivery System.

[2]  Jan-Ming Ho,et al.  Travel time prediction with support vector regression , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[3]  J. Liu,et al.  Self-tuning weighted measurement fusion Wiener filter for autoregressive moving average signals with coloured noise and its convergence analysis , 2012 .

[4]  Xuegong Zhang,et al.  An Improved Support Vector Machine Using Class-Median Vectors * , .

[5]  Li Ying-zi,et al.  Forecast of power generation for grid-connected photovoltaic system based on grey model and Markov chain , 2008, 2008 3rd IEEE Conference on Industrial Electronics and Applications.

[6]  Weizhong Yan,et al.  Toward Automatic Time-Series Forecasting Using Neural Networks , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[7]  Antonio J. Serrano,et al.  Dosage individualization of erythropoietin using a profile-dependent support vector regression , 2003, IEEE Transactions on Biomedical Engineering.

[8]  Chi-Yo Huang,et al.  Short Term Wind Speed Predictions by Using the Grey Prediction Model Based Forecast Method , 2011, 2011 IEEE Green Technologies Conference (IEEE-Green).

[9]  Chia-Yon Chen,et al.  Applications of improved grey prediction model for power demand forecasting , 2003 .

[10]  Yi Lin,et al.  Grey Systems: Theory and Applications , 2010 .

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

[12]  Marimuthu Palaniswami,et al.  A Division Algebraic Framework for Multidimensional Support Vector Regression , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Q. Henry Wu,et al.  Electric Load Forecasting Based on Locally Weighted Support Vector Regression , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[14]  Gordon Reikard.  Predicting solar radiation at high resolutions: A comparison of time series forecasts , 2009 .

[15]  J. Deng,et al.  Introduction to Grey system theory , 1989 .

[16]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[17]  James A. Cadzow.  ARMA Modeling of Time Series , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Adedeji B. Badiru,et al.  Online Support Vector Regression With Varying Parameters for Time-Dependent Data , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[19]  Okyay Kaynak,et al.  Grey system theory-based models in time series prediction , 2010, Expert Syst. Appl..

[20]  A.J. Conejo,et al.  Day-ahead electricity price forecasting using the wavelet transform and ARIMA models , 2005, IEEE Transactions on Power Systems.

[21]  Cristian Rodriguez Rivero,et al.  Rainfall Forecasting Using Sub sampling Nonparametric Methods , 2013, IEEE Latin America Transactions.

[22]  Wei-Chang Yeh,et al.  New Parameter-Free Simplified Swarm Optimization for Artificial Neural Network Training and its Application in the Prediction of Time Series , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[23]  H. K. Chiang,et al.  Integral variable structure controller with grey prediction for synchronous reluctance motor drive , 2004 .

[24]  Nikolay I. Nikolaev,et al.  Recursive Bayesian Recurrent Neural Networks for Time-Series Modeling , 2010, IEEE Transactions on Neural Networks.

[25]  Philippe Poignet,et al.  Pathological Tremor and Voluntary Motion Modeling and Online Estimation for Active Compensation , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[26]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[27]  J. Torres,et al.  Forecast of hourly average wind speed with ARMA models in Navarre (Spain) , 2005 .

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

[29]  M H Purnomo,et al.  ARIMA Modeling of Tropical Rain Attenuation on a Short 28-GHz Terrestrial Link , 2010, IEEE Antennas and Wireless Propagation Letters.

[30]  Jing-Xu Liu,et al.  An empirical assessment on the robustness of support vector regression with different kernels , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[31]  C. Jin,et al.  Software reliability prediction based on support vector regression using a hybrid genetic algorithm and simulated annealing algorithm , 2011, IET Softw..