Photovoltaic Power Prediction Using Recurrent Neural Networks

  • Rim Ben Ammar
  • Abdelmajid Oualha
Part of the Green Energy and Technology book series (GREEN)


The intermittent characteristic of the photovoltaic power, due to the variability of the weather conditions, involves many problems in grid energy management. Therefore, the PV power forecasting becomes crucial to ensure grid stability and economic dispatch. Artificial neural network (ANN) techniques present alternative approaches to solve nonlinear problems in various areas. They can be trained and applied for prediction. A particular type of ANN namely the recurrent neural network (RNN) has shown powerful capabilities for PV power forecasting. The paper investigates and compares the efficiency of several RNN architectures specifically the modified Elman, Jordan and the hybrid model combining the latest topologies.

The useful data for prediction are acquired from the National Institute of Meteorology. The performance of these topologies is validated by calculating the Root Mean Squared Error, the Mean Absolute Error and the Correlation Factor. The results show that forecasting with the modified Elman outperforms the Jordan and the hybrid networks.


Artificial neural network PV power Forecasting Prediction Recurrent neural network Elman Jordan 


  1. Abdulkarim, S. A. (2016). Time series prediction with simple recurrent neural networks. Bayero Journal of Pure and Applied Sciences, 9, 19–24.CrossRefGoogle Scholar
  2. Babalola, O. S., Komolafe, O. A., Jegede, O. O., & Ayoola, M. A. (2014). Photovoltaic generating system parameter sizing for building. Journal of Energy Technologies and Policy, 4, 65–73.Google Scholar
  3. Casaca de Rocha Vaz, A. G. (2014). Photovoltaic forecasting with artificial neural networks. Ph.D. Thesis, Faculty of Sciences, University of Lisboa.Google Scholar
  4. Carcano, E. C., Bartolinia, P., Musellib, M., & Piroddic, L. (2008). Jordan recurrent neural network versus IHACRES in modelling daily stream flows. Journal of Hydrology, 362, 291–307, Elsevier.Google Scholar
  5. Cervone, G., Harding, L. C., Alessandrini, S., & Monache, L. D. (2017). Short term photovoltaic power forecasting using artificial neural networks and an analog ensemble. Renewable Energy, 108, 274–286.CrossRefGoogle Scholar
  6. Chow, S. K. H., Lee, E. W. M., & Li, D. H. W. (2012). Short-term prediction of photovoltaic energy generation by intelligent approach. Energy Build, 55, 660–667.CrossRefGoogle Scholar
  7. De Giorgi, M. G., Maria, C. P., & Malvoni, M. (2014). Photovoltaic power forecasting using statistical methods: Impact of weather data. IET Science Measurement and Technology, 8, 90–97.CrossRefGoogle Scholar
  8. De Mulder, W., Bethard, S., & Moens, M. F. (2015). A survey on the application of recurrent neural networks to statistical language modeling. Computer Speech & Language, 30, 61–98.CrossRefGoogle Scholar
  9. Dolara, A., Grimaccia, F., Leva, S., Mussetta, M., & Ogliari, E. (2015). A physical hybrid artificial neural network for short term forecasting of PV plant power output. Energies, 8, 1138–1153.CrossRefGoogle Scholar
  10. Dragomir, F., & Dragomirb, O. E. (2014). Forecasting of photovoltaic power generation by RBF neural networks. Advanced Materials Research, 918, 200–205.CrossRefGoogle Scholar
  11. Du, K. L., & Swamy, M. N. S. (2014). Neural networks and statistical learning. London/Heidelberg/New York/Dordrecht: Springer.CrossRefGoogle Scholar
  12. Husaini, N. A., Ghazali, R., Nawi, N. M., & Ismail, K. H. (2011). Jordan Pi-Sigma neural network for temperature prediction. Communications in Computer and Information Science, 151, 547–558.CrossRefGoogle Scholar
  13. Keles, C., Alagoz, B. B., Akcin, M., Kaygusuz, A., & Karabiber, A. (2013). A photovoltaic system model for matlab/simulink simulations. In 4th International Conference on Power Engineering, Energy and Electrical Drives.Google Scholar
  14. Kou, J., Liu, J., Li, Q., Fang, W., Chen, Z., Liu, L., & Guan, T. (2013). Photovoltaic power forecasting based on artificial neural network and meteorological data. In TENCON 2013–2013 IEEE Region 10 Conference, 31194,1–4.Google Scholar
  15. Pelland, S., Remund, J., Kleiss, J., Oozeki, T., & Brabandere, K. D. (2013). Photovoltaic and solar forecasting: State of the art. IEA Intenatioanl Energy Agency, 14, 1–36.Google Scholar
  16. Mandal, P., Teja, S. S., Ui Haque, A., Meng, J., & Mineda, R. L. (2012). Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques. Progress in Energy and Combustion Science, 12, 332–337. Elsevier.Google Scholar
  17. Mellit, A. (2009). Recurrent neural network-based forecasting of the daily electricity generation of a photovoltaic power system. In EVER’09, Monaco.Google Scholar
  18. Mellit, A., & Kalogirou, S. A. (2008). Artificial intelligence techniques for photovoltaic applications. Elsevier, 34, 574–632.Google Scholar
  19. Mellit, A., & Pavan, A. M. (2010). 24-h forecast of solar irradiance using artificial neural network, application for performance prediction of a grid-connected PV plant at Trieste. Solar Energy, 84, 221–226. Elsevier.Google Scholar
  20. Pham, D. T., & Liu, X. (1996). Training of Elman networks and dynamic system modelling. International Journal of Systems Science, 27, 221–226.CrossRefGoogle Scholar
  21. RamaKrishna, K., Ramam, V. A., & Rao, R. S. (2014). Mathematical neural network, MaNN. Models part IV, recurrent neural networks, RecNN. In bio-/chemical-tasks. Journal of Applicable Chemistry, 3(6), 2209–2311.Google Scholar
  22. Saberian, A., Hizam, H., Radzi, M. A. M., Abkadir, & M. Z. A., Mirzaei, M. (2014). Modelling and prediction of photovoltaic power output using artificial neural networks. International Journal of Photoenergy, 1–10.CrossRefGoogle Scholar
  23. Sathya, R., & Abraham, A. (2013). Comparison of supervised and unsupervised learning algorithms for pattern classification. International Journal of Advanced Research in Artificial Intelligence, 2(2), 34–38.CrossRefGoogle Scholar
  24. Wang, J., Wang, J., Fang, W., & Niu, H. (2016). Financial time series prediction using Elman recurrent random neural networks. Computational Intelligence and Neuroscience, 2016, 1–14.Google Scholar
  25. Wei, G. H., Qian, F., Chun, L. Y., Du, W., & Wang, L. (2007). Identification and control of nonlinear systems by a dissimilation particle swarm optimization-based Elman neural network. Nonlinear Analysis Real Word Applications, 9, 1345–1360.MathSciNetzbMATHGoogle Scholar
  26. Wysocki, A., & Lawryn, C. M. (2016). Elman neural network for modeling and predictive control of delayed dynamic systems. Archives of Control Sciences, 26, 117–142.MathSciNetCrossRefGoogle Scholar
  27. Yadav, H. K., Pal, Y., & Tripathi, M. M. (2015). Photovoltaic power forecasting methods in smart power grid. In Annual IEEE India Conference (INDICON), New Delhi.Google Scholar
  28. Zhou, W., Yang, H., & Fang, Z. (2007). A novel model for photovoltaic array performance prediction. Applied Energy, 84, 1187–1198. Elsevier.Google Scholar
  29. Zhu, H., Li, X.,Sun, Q., Nie, L., Yao, J., & Zhao, G. (2015). A power prediction method for photovoltaic power plant based on wavelet decomposition and artificial neural networks. Energies, 9, 11.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Rim Ben Ammar
    • 1
  • Abdelmajid Oualha
    • 1
  1. 1.Sfax Engineering SchoolUniversity of SfaxSfaxTunisia

Personalised recommendations