PREDICCIÓN DE POTENCIA FOTOVOLTAICA MEDIANTE REDES NEURONALES WAVELET

José Daniel Ortiz López, Luis J. Ricalde Castellanos, Braulio J. Cruz Jiménez, Ricardo J. Peón Escalante

Resumen


Resumen

En el presente trabajo se realiza la predicción de potencia de un sistema solar fotovoltaico implementando dos diferentes estructuras de redes neuronales, perceptrón multicapa y una red neuronal wavelet. El algoritmo de aprendizaje utiliza información proveniente de la irradiación, temperatura, humedad relativa y velocidad del viento. Los datos de entrenamiento se obtienen de una estación meteorológica ubicada cerca de un sistema fotovoltaico de 7 kW. El perceptrón multicapa tuvo como entradas las cuatro variables mencionadas anteriormente y como salida la potencia del sistema, la red Wavelet únicamente tuvo como entrada la irradiación y como salida la potencia generada por el sistema fotovoltaico. Se obtuvieron mejores resultados en la predicción de la red wavelet, siendo esta una de las principales aportaciones de este trabajo.

Palabras Claves: Fotovoltaico, perceptrón multicapa, red neuronal, wavelet.


PREDICTION OF PHOTOVOLTAIC POWER THROUGH WAVELET NEURAL NETWORKS


Abstract

This work presents the prediction of power of a solar photovoltaic system implementing two different neural networks, multilayer perceptron and wavelet neural network. The learning algorithm uses information from irradiance, temperature, relative humidity and wind speed. The training data are obtained from a weather station located near a 7 kW photovoltaic system. The multilayer perceptron had as inputs four variables previously mentioned and as output the power. The wavelet network only had as input the irradiation and as output, the power generated by the photovoltaic system. Better results were obtained in the prediction of the wavelet network, being this one of the main contributions of this work.

Keywords: Multilayer perceptron, neuronal network, photovoltaic, wavelet.


Texto completo:

1224-1236 PDF

Referencias


Almonacid, F., Fernandez, E., Mallick T., & Perez, P., High concentrator photovoltaic module simulation by neural networks using spectrally corrected direct normal irradiance and cell temperature. Energy. 84, pp. 336-343, 2015.

Holtschneider T. & Erlich I., Optimization of Electricity Pricing Considering Neural Network based Model of Consumers Demand Response. IEEE (CIASG). 154-160, 2013.

Haykin S., Neural networks and learning machines. Pearson. Canada, 1999.

Haykin S., Kalman filtering and neural networks. John Wiley & sons, USA, 2001.

Fernández E., Almonacid, F., Sarmah, N., Rodrigo, P., Mallick, T., & Pérez, P., A model based on artificial neural network for the prediction of the maximum power of a low concentration photovoltaic module for building integration. Solar Energy.100, pp. 148-158, 2014.

Hao, Y. & Wilamowski, B. (2011). Levenberg-Marquardt Training Industrial Electronics Handbook Intelligent Systems. (2a ed.). CRC Press, 2011.

Haykin S., Neural networks a comprehensive foundation. (2a ed.), 2005.

IMF, Tensions from the two-speed recovery unemployment, commodities, and capital flows. Washington D.C. USA, 2011.

Lopez J., Ramos, J., Zulueta, E., Fernandez, U., & Oterino, F. Systematic modeling of photovoltaic modules based on artificial neural networks”. Hydrogen energy. 41, pp. 1267-12687, 2016.

Martin O., Lopez M. & Martin F., Redes neuronales artificiales para la predicción de la calidad en soldadura por resistencia por puntos. Revista de Metalurgia. 45, pp. 345-353, 2006.

Ponce, P., Inteligencia artificial con aplicaciones a la ingeniería. Alfaomega, México, 2012.

Rosenblatt, F., Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Spartan Books, Washington DC, 1961.

Rubio, E., Ordoñez, L., Ricalde, L., De La Cruz, E., & Peón, R., Diseño de una micro red eléctrica inteligente con sistema fotovoltaico y celda de combustible. Pistas educativas. 120, pp. 516-532, 2016.

Rumelhart, D., Geoffrey, E., & Williams, R., Learning Internal Representations by Error Propagation. 1986. David E. Rumelhart, James L. McClelland and the PDP research, 1986.

Zhang, Q., Wavelet Network: The Radial Structure and an Efficient Initialization Procedure. Technical Report of Linköping University. LiTH-ISY-I-1423, 1992.

Yadav, A. & Chandel, S., Identification of relevant input variables for prediction of 1-minute time- step photovoltaic module power using artificial neural networks and multiple linear regression models. Renewable and Sustainable Energy Reviews. In press, 2017.


Enlaces refback

  • No hay ningún enlace refback.