SciELO - Scientific Electronic Library Online

vol.23 issue4Estimating greenhouse gas emissions associated with achieving universal access to electricity for all households in South Africa author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand



Related links

  • On index processCited by Google
  • On index processSimilars in Google


Journal of Energy in Southern Africa

On-line version ISSN 2413-3051
Print version ISSN 1021-447X


SELCUK NOGAY, H.; AKINCI, Tahir Cetin  and  EIDUKEVICIUTE, Marija. Application of artificial neural networks for short term wind speed forecasting in Mardin, Turkey. J. energy South. Afr. [online]. 2012, vol.23, n.4, pp.2-7. ISSN 2413-3051.

Artificial neural network models were used for short term wind speed forecasting in the Mardin area, located in the Southeast Anatolia region of Turkey. Using data that was obtained from the State Meteorological Service and that encompassed a ten year period, short term wind speed forecasting for the Mardin area was performed. A number of different ANN models were developed in this study. The model with 60 neurons is the most successful model for short term wind speed forecasting. The mean squared error and approximation values for training of this model were 0.378088 and 0.970490, respectively. The ANN models developed in the study have produced satisfactory results. The most successful among those models constitutes a model that can be used by the Mardin Electric Utility Control Centre.

Keywords : artificial neural network; back propagation; forecasting; wind speed.

        · text in English     · English ( pdf )


Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License