Advertisement

Improved Local Weather Forecasts Using Artificial Neural Networks

  • Morten Gill Wollsen
  • Bo Nørregaard Jørgensen
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 373)

Abstract

Solar irradiance and temperature forecasts are used in many different control systems. Such as intelligent climate control systems in commercial greenhouses, where the solar irradiance affects the use of supplemental lighting. This paper proposes a novel method to predict the forthcoming weather using an artificial neural network. The neural network used is a NARX network, which is known to model non-linear systems well. The predictions are compared to both a design reference year as well as commercial weather forecasts based upon numerical modelling. The results presented in this paper show that the network outperforms the commercial forecast for lower step aheads (< 5). For larger step aheads the network’s performance is in the range of the commercial forecast. However, the neural network approach is fast, fairly precise and allows for further expansion with higher resolution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    ConWX: Conwx, http://www.conwx.com/ (accessed: January 5, 2015)
  2. 2.
    DMI: Dmi verification (in Danish), http://www.dmi.dk/vejr/til-lands/regionaludsigten/verifikation/ (accessed: January 8, 2015)
  3. 3.
    Heaton, J.: Encog machine learning framework, http://www.heatonresearch.com/encog (accessed: December 23, 2014)
  4. 4.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2(5), 359–366 (1989), http://linkinghub.elsevier.com/retrieve/pii/0893608089900208 CrossRefGoogle Scholar
  5. 5.
    Lee, Y., Member, S., Cha, Y.T., Member, S., Park, H.: Short-term load forecasting using an artificial neural network. Transactions on Power Systems 7(1), 124–132 (1992)CrossRefGoogle Scholar
  6. 6.
    Lund, H.: The Design Reference Year User Manual, A Report of Task 9: Solar Radiation and Pyranometer Studies (1995)Google Scholar
  7. 7.
    Maqsood, I., Khan, M., Abraham, A.: An ensemble of neural networks for weather forecasting. Neural Computing and Applications 13(2), 112–122 (2004), http://link.springer.com/10.1007/s00521-004-0413-4 CrossRefGoogle Scholar
  8. 8.
    Office, N.A.: Almanac for Computers 1990. U.S. Government Printing Office, 1990 (1989)Google Scholar
  9. 9.
    Powell, K.M., Sriprasad, A., Cole, W.J., Edgar, T.F.: Heating, cooling, and electrical load forecasting for a large-scale district energy system. Energy 74, 877–885 (2014), http://linkinghub.elsevier.com/retrieve/pii/S036054421400886X CrossRefGoogle Scholar
  10. 10.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Cognitive Modeling (1988)Google Scholar
  11. 11.
    Shank, D.B., Hoogenboom, G., McClendon, R.: Dewpoint temperature prediction using artificial neural networks. Journal of Applied Meteorology and Climatology 47(6), 1757–1769 (2008)CrossRefGoogle Scholar
  12. 12.
    Smith, B.A., Hoogenboom, G., McClendon, R.W.: Artificial neural networks for automated year-round temperature prediction. Computers and Electronics in Agriculture 68(1), 52–61 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Morten Gill Wollsen
    • 1
  • Bo Nørregaard Jørgensen
    • 1
  1. 1.Centre for Energy Informatics, The Maersk Mc-Kinney Moller InstituteUniversity of Southern DenmarkOdense MDenmark

Personalised recommendations