Applicability of levenberg-marquardt algorithm for power generation analysis of the system photovoltaic
DOI:
https://doi.org/10.14488/1676-1901.v17i4.2542Keywords:
Photovoltaic Solar Energy. Artificial Neural Networks. Levemberg– Marquardt Algorithm. Transfer function logsigmoide. Transfer function purelin.Abstract
This paper talk about the applicability of artificial neural networks for power generation analysis for a photovoltaic system connected to the grid. First, the characteristics and mathematical potential of data processing presented by networks are described. Then, several configurations are tested in order to find the most appropriate one. Data from 2014 were used for energy generation, room temperature, module temperature, solar radiation incidence and time of day. The application used the Levenberg-Marquardt algorithms to obtain the network parameters and the criterion of the mean square error to measure the performance. The training was reealized with 5, 10, 15, 20, 25, 30 and 60 neurons in the hidden layer. The transfer functions were logsigmoid and purelin. The best result was obtained with 25 neurons, with a correlation coefficient of 0.98.Downloads
References
BOUSFIELD, P. M. Uso de uma rede neural para a previsão do volume de lodo gerado em estações de tratamento de efluente: um estudo de caso, 2008. Universidade da região de Joinville. Disponível em:. .
CHATZIAGORAKIS.P., GEORGOULAS. PAPADOPOULOU, S. ELMASIDES,C., GIAOURIS, D., Seferlis, P., Sirakoulis, CH.G., KARAFYLLIDIS, I., PAPADOPOULOS, A. I., STERGIOPOULOS, F., ZIOGOU, C., IPSAKIS, D., Voutetakis, S. e ANDREADIS, I. Application of Neural Networks Solar Radiation Prediction for Hybrid Renewable Energy Systems. Engineering Applications of Neural Networks, v. 459, p. 133-144, 2014.
CHOW, S. K. H.; LEE, E. W. M.; LI, D. H. W. Short-term prediction of photovoltaic energy generation by intelligent approach. Energy and Buildings, v. 55, p. 660–667, 2012. Elsevier B.V. Disponível em: <http://linkinghub.elsevier.com/retrieve/pii/S037877881200415X>. https://doi.org/10.1016/j.enbuild.2012.08.011
FIORIN, D. V; MARTINS, F. R.; SCHUCH, N. J. Aplicacões de redes neurais e previsões de disponibilidade de recursos energéticos solares. Revista Brasileira de Ensino de Física, v. 33, n. 1, p. 1309 1 – 1309 20, 2011. http://dx.doi.org/10.1590/S1806-11172011000100009
GILMAN, A. Dobos; KASBERG, M. P50/P90. Analysis for solar energy systems using the system advisor model, NREL, May 13-17, 2012. Disponível em:< http://www.nrel.gov/docs/fy12osti/54488.pdf>.
HAGAN, Martin T.; DEMUTH, Howard B.; BEALE, Mark Hudson; JESÚS, Orlando De. Neural network design. 2. ed. eBook, 2014.
MEKKI, A., ALOUI, F., DHOUIB, A., SAYADI, S. Effects of Phanerochaete chrysosporium on biologic activity of soil amended with olive mill wastewaters. Journal of Soil Science and Environmental Management, v. 3, n.1, p. 1-8, 2012. DOI: 10.5897/JSSEM11.092.
MELLIT, A.; KALOGIROU, S. A.; HONTORIA, L.; SHAARI, S. Artificial intelligence techniques for sizing photovoltaic systems: a review. Renewable and Sustainable Energy Reviews, v. 13, n. 2, p. 406–419, 2009. Disponível em: <http://linkinghub.elsevier.com/retrieve/pii/S1364032108000051>. DOI: 10.1016/j.rser.2008.01.006
MELLIT, A.; KALOGIROU, S. A. ANFIS-based modelling for photovoltaic power supply system: A case study. Renewable Energy, v. 36, n. 1, p. 250–258, 2011. Elsevier Ltd. Disponível em:<http://linkinghub.elsevier.com/retrieve/pii/S0960148110002843>. DOI: 10.1016/j.renene.2010.06.028.
MELLIT, A.; KALOGIROU, S. A. Artificial intelligence techniques for photovoltaic applications: a review. Progress in Energy and Combustion Science, v. 34, n. 5, p. 574–632, 2008. https://doi.org/10.1016/j.pecs.2008.01.001
NREL. National renewable energy laboratory: research cell efficiency records. 2016. Disponível em: <http://www.nrel.gov/ncpv/>. Acesso em: junho de 2016.
RÜTHER, R. e DACOREGIO, M., 2000. Performance assessment of a 2 kwp grid-connected, building-integrated, amorphous silicon photovoltaic installation in Brazil. Prog. Photovolt. Res. Appl. n. 8, p. 257 - 266. DOI: 10.1002/(SICI)1099-159X(200003/04)8:2<257::AID-PIP292>3.0.CO;2-P
RÜTHER, R., 1998. Experiences and operational results of the first grid-connected, building-integrated, thin-film photovoltaic installation in Brazil. WCPEC2 - 2nd World Conference on Photovoltaic Solar Energy Conversion. Vienna, Austria.
YADAV, A. K.; CHANDEL, S. . Artificial Neural Network based Prediction of Solar Radiation for Indian Stations. International Journal of Computer Applications, v. 50, n. 9, p. 1–4, 2012. DOI:10.5120/7796-0907.
Published
How to Cite
Issue
Section
License
The Journal reserves the right to make spelling and grammatical changes, aiming to keep a default language, respecting, however, the style of the authors.
The published work is responsibility of the (s) author (s), while the Revista Produção Online is only responsible for the evaluation of the paper. The Revista Produção Online is not responsible for any violations of Law No. 9.610 / 1998, the Copyright Act.
The journal allows the authors to keep the copyright of accepted articles, without restrictions
This work is licensed under a Creative Commons License .
