Neural and mathematical modeling approaches for hourly long term loadforecasting

Filik Ü. B., GEREK Ö. N., KURBAN M.

ICIC Express Letters, vol.3, no.4, pp.1125-1130, 2009 (Scopus) identifier

  • Publication Type: Article / Article
  • Volume: 3 Issue: 4
  • Publication Date: 2009
  • Journal Name: ICIC Express Letters
  • Journal Indexes: Scopus
  • Page Numbers: pp.1125-1130
  • Keywords: Artificial neural network, Load forecasting, Mathematical modeling
  • Anadolu University Affiliated: Yes


In this work, a mathematical model and an Artificial Neural Network (ANN)approach are constructed for the hourly forecasting of long term electric energydemand. Unlike former studies, these methods produce long term load forecastingresults at an accuracy level of hourly precision. The proposed mathematicalmodel of the load is compared with a feed-forward ANN model output in the senseof Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Themathematical model provides a simple, intuitive and more generalized form,whereas the ANN model provides a specified model fine-tuned for the availabledata. The suitability of these methods is illustrated and verified using4-year-long real-life hourly load data taken from Turkish Electric PowerCompany. ICIC International © 2009.