Neural network approach with teaching-learning-based optimization for modeling and forecasting long-term electric energy demand in Turkey

Kankal M., UZLU E.

NEURAL COMPUTING & APPLICATIONS, vol.28, 2017 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 28
  • Publication Date: 2017
  • Doi Number: 10.1007/s00521-016-2409-2
  • Journal Name: NEURAL COMPUTING & APPLICATIONS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Keywords: Electric energy demand, Teaching-learning-based optimization, Artificial bee colony, Backpropagation, Neural network, ARTIFICIAL BEE COLONY, CONSUMPTION, PREDICTION, ALGORITHM, DESIGN, HYDROPOWER, GENERATION
  • Bursa Uludag University Affiliated: No

Abstract

This paper studies the performance of an artificial neural network (ANN) with teaching-learning-based optimization (TLBO) for modeling electric energy demand (EED) in Turkey. The ANN with TLBO (ANN-TLBO) was compared to the ANN with backpropagation (ANN-BP) and the ANN with artificial bee colony algorithm (ANN-ABC) models. Gross domestic product, population, import, and export were selected as independent variables in the models. The results reveal that the ANN-TLBO models perform better than the ANN-BP and ANN-ABC models in EED estimation. The average root-mean-square error of the ANN-BP and ANN-ABC models was decreased by 42.3 and 39.3 % using the ANN-TLBO model, respectively. Different scenarios have been studied over a projected 6-year period, from 2013 to 2018, to forecast Turkey's EED. The results of the proposed model give excellent clues with regards to its use in future energy studies.