Wavelet Processing for Neural Network Training Applied to Solar Radiation Forecasting

Andres Ussa Caycedo; Robinson Jimenez Moreno; Dario Amaya Hurtado

doi:10.15866/irecos.v10i6.6356

Wavelet Processing for Neural Network Training Applied to Solar Radiation Forecasting

Andres Ussa Caycedo⁽¹⁾, Robinson Jimenez Moreno⁽²⁾, Dario Amaya Hurtado^(3*)

^(*) Corresponding author

Authors' affiliations

DOI: https://doi.org/10.15866/irecos.v10i6.6356

Abstract

Photovoltaic power systems connected to the electrical grid are becoming an important element in the adoption of solar energy as a meaningful power source. However, radiation nonlinear behavior considerably affects photovoltaic systems performance and certainty. Solar radiation forecasting analysis is presented as an alternative to improve photovoltaic systems’ certainty and robustness. The training of an autoregressive neural network applied to solar radiation forecasting supported by wavelet processing is presented in this paper. Solar radiation data from 2010 to 2012 corresponding to Cajicá, Colombia is used as input data to the system in order to get predicted radiation data from the following year. Validation of the results is performed by analysis of the real 2013 radiation data through mean squared error and linear regression. The results showed an accuracy of 93%, indicating that the proposed system can be used as a tool for the design of photovoltaic power systems in Colombia.
Copyright © 2015 Praise Worthy Prize - All rights reserved.

Keywords

Artificial Neural Networks; Time Series Forecasting; Wavelet Transform; Energy-Environment Modelling

Full Text:

PDF

References

Jones, G. and L.Bouamane, ‘Power from Sunshine’: A Business History of Solar Energy. Harvard Business School Working Paper. [Online] No 12-105, 2012. [date of reference July 12th of 2014]. Available at: http://nrs.harvard.edu/urn-3:HUL.InstRepos:9056763

O’Driscoll, P. and Vergano, D., Fossil fuels are to blame, world scientists conclude. USA Today [Online]. 2007. [date of reference July 11th of 2014]. Available at:

http://usatoday30.usatoday.com/weather/climate/globalwarming/2007-01-30-ipcc-report_x.htm

IEA. Solar Energy Perspectives [Online],OECD Publishing, 2011. [date of reference July 11th of 2014]. doi: 10.1787/9789264124585-en

Tolabi, H.B.,Moradi, M. and Ayob, S.B., A review on classification and comparison of different models in solar radiation estimation. International Journal of Energy Research. [Online].38(6), pp. 689–701, 2014. [date of reference July 10th of 2014].
http://dx.doi.org/10.1002/er.3161

Mellit, A. and Kalogirou, S.A., Artificial intelligence techniques for photovoltaic applications: A review.Progress in Energy and Combustion Science. [Online] 34(5), pp. 574–632, 2008. [date of reference July 10th of 2014].
http://dx.doi.org/10.1016/j.pecs.2008.01.001

Abolohom, A., Omar, N., A machine learning approach to anaphora resolution in Arabic, (2014) International Review on Computers and Software (IRECOS), 9 (12), pp. 1956-1963.
http://dx.doi.org/10.15866/irecos.v9i12.4786

Pedro, H. and Coimbra, C., Assessment of forecasting techniques for solar power production with no exogenous inputs. Solar Energy. [Online] 86(7), pp. 2017–2028, 2012.[date of reference July 10th of 2014].
http://dx.doi.org/10.1016/j.solener.2012.04.004

Kardakos, E.G.,Alexiadis,M.C.,Vagropoulos, S.I.,Simoglou, C.K.,Biskas, P.N. and Bakirtzis, A.G., Application of time series and artificial neural network models in short-term forecasting of PV power generation, 48th International Universities’ Power Engineering Conference (UPEC), pp. 1–6, 2013.
http://dx.doi.org/10.1109/upec.2013.6714975

Tan, C. and Pedersen, C.N. Financial Time Series Forecasting Using Improved Wavelet Neural Network, M.S. Thesis, DatalogiskInstitut, Aarhus Universitet, 2009.

Bhaskar,K. and Singh, S.N., AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network. IEEE Transactions on Sustainable Energy. [Online] 3(2), pp. 306–315, 2012.[date of reference July 9th of 2014].
http://dx.doi.org/10.1109/tste.2011.2182215

Yong, Z., Hong, L.,Liqun,L. and XiaoFeng, G., The MPPT Control Method by Using BP Neural Networks in PV Generating System, International Conference on Industrial Control and Electronics Engineering (ICICEE), pp. 1639–1642, 2012.
http://dx.doi.org/10.1109/icicee.2012.433

Ciabattoni,L.,Ippoliti, G., Longhi, S.,Cavalletti, M. and Rocchetti, M., Solar irradiation forecasting using RBF networks for PV systems with storage, IEEE International Conference on Industrial Technology (ICIT), pp. 699–704, 2012.
http://dx.doi.org/10.1109/icit.2012.6210020

Rizwan, M. , Jamil,M. and Kothari, D.P., Generalized Neural Network Approach for Global Solar Energy Estimation in India. IEEE Transactions on Sustainable Energy. [Online] 3(3), pp. 576–584,2012. [date of reference July 9th of 2014].
http://dx.doi.org/10.1109/TSTE.2012.2193907

Charfi, I., Atri, M., Spatio-Temporal Wavelet Based Video Compression: a Simulink Implementation for Acceleration, (2015) International Review on Computers and Software (IRECOS), 10 (5), pp. 513-519.
http://dx.doi.org/10.15866/irecos.v10i5.6099

Yilmaz, S. and Oysal, Y., Fuzzy Wavelet Neural Network Models for Prediction and Identification of Dynamical Systems. IEEE Transactions on Neural Networks. [Online] 21(10), pp. 1599–1609, 2010. [date of reference July 8th of 2014].
http://dx.doi.org/10.1109/tnn.2010.2066285

Capizzi, G., Napoli,C. and Bonanno,F., Innovative Second-Generation Wavelets Construction With Recurrent Neural Networks for Solar Radiation Forecasting. IEEE Transactions on Neural Networks and Learning Systems. [Online] 23(11), pp. 1805–1815,2012. [date of reference July 8th of 2014].
http://dx.doi.org/10.1109/tnnls.2012.2216546

Mandal, P., Haque, A.U.,Madhira, S.T. and Al-Hakeem, D.I., Applying wavelets to predict solar PV output power using generalized regression neural network, North American Power Symposium (NAPS), pp. 1–5, 2013.
http://dx.doi.org/10.1109/naps.2013.6666912

Prediction of Worldwide Energy Resource, Near Real-time Daily Global Radiation and Meteorology. [Online]. [date of reference June 18th of 2014].Available at:

http://power.larc.nasa.gov/cgi-bin/cgiwrap/solar/timeseries.cgi

Minu, K.K., Lineesh, M.C. and John, C.J., Wavelet neural networks for nonlinear time series analysis. Applied Mathematical Sciences. [Online] 4(50), pp. 2485–2495, 2010. [date of reference July 7th of 2014]. Available at:

http://www.m-hikari.com/ams/ams-2010/ams-49-52-2010/lineeshAMS49-52-2010.pdf

Veitch, D. Wavelet Neural Networks and their Application in the Study of Dynamical Systems, M.S. Thesis, Department of Mathematics,Univeristy of York, UK, 2005.

Shukla, D. and Sahu, J.,Wavelets: Basic Concepts, International Journal of Electrical and Electronic Engineering & Telecommunications. [Online] 2(4), p. 34, 2013. Available at:

http://www.ijeetc.com/view.php?iid=68

Palle, M.-S. and Jorgensen, E.T., Comparison of Discrete and Continuous Wavelet Transforms,Computing Research Repository - CORR, 2007.
http://dx.doi.org/10.1007/978-1-4614-1800-9_34

Valens, C. A Really Friendly Guide to Wavelets. 1999.

James, W. A Primer on Wavelets and Their Scientific Applications. CRC Press, 1999.
http://dx.doi.org/10.1201/9781420050011

Jiang, D. and Liu, C., Machine Condition Classification Using Deterioration Feature Extraction and Anomaly Determination. IEEE Transactions on Reliability. [Online] 60(1), pp. 41–48, 2011. [date of reference July 6th of 2014].
http://dx.doi.org/10.1109/tr.2011.2104433

Pandey, A., Singh, D. and Sinha, S.K., Intelligent Hybrid Wavelet Models for Short-Term Load Forecasting. IEEE Transactions on Power Systems. [Online] 25(3), pp. 1266–1273,2010. [date of reference July 6th of 2014].
http://dx.doi.org/10.1109/TPWRS.2010.2042471

Dietz,S. Autoregressive Neural Network Processes - Univariate, Multivariate and Cointegrated Models with Application to the German Automobile Industry. [Online]. [date of reference July 16th of 2014] Available at: http://www.opus-bayern.de/uni-passau/volltexte/2011/2252/

Pucheta, J.A., Rivero, C.M., Herrera, M. R., Salas, C. A.,Patiño, H. D. and Kuchen, B. R.,A Feed-Forward Neural Networks-Based Nonlinear Autoregressive Model for Forecasting Time Series, Computación y Sistemas [Online] 2011. [date of reference July 13th of 2014] Available at: http://www.redalyc.org/resumen.oa?id=61520767008

Hao,Y. and Wilamowski, B.M., Levenberg–Marquardt Training. [Online] Industrial Electronics Handbook, CRC Press, 2(5), pp. 12–1 to 12–15,2011. [date of reference July 13th of 2014] Available at:

http://www.eng.auburn.edu/~wilambm/pap/2011/K10149_C012.pdf

Kuh,A. Mean squared error analysis of analog neural networks subject to drifting targets and noise, Conference Record of the Thirty-Second Asilomar Conference on Signals, Systems amp; Computers. [Online]1, pp. 683–684, 1998.
http://dx.doi.org/10.1109/acssc.1998.750949

Yang,Y. and Dong, L., Short-Term PV Generation System Direct Power Prediction Model on Wavelet Neural Network and Weather Type Clustering, 5th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC). [Online] 1, pp. 207–211, 2013.
http://dx.doi.org/10.1109/ihmsc.2013.56

Mandal, P., Madhira, S.T., Haque, A.U.,Meng, J.and Pineda,R.L., Forecasting Power Output of Solar Photovoltaic System Using Wavelet Transform and Artificial Intelligence Techniques, Procedia Computer Science. [Online] 12, pp. 332–337, 2012. [date of reference July 6th of 2014].
http://dx.doi.org/10.1016/j.procs.2012.09.080

Yang,X., Jiang, F. and Liu,H., Short-term solar radiation prediction based on SVM with similar data, 2nd IET Renewable Power Generation Conference (RPG 2013). [Online] pp. 1–4, 2013.
http://dx.doi.org/10.1049/cp.2013.1735

Refbacks

There are currently no refbacks.

Username
Password
Remember me