Three different applications of genetic algorithm (GA) search techniques on oil demand estimation


Canyurt C. E., Ozturk H. K.

ENERGY CONVERSION AND MANAGEMENT, vol.47, pp.3138-3148, 2006 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 47
  • Publication Date: 2006
  • Doi Number: 10.1016/j.enconman.2006.03.009
  • Journal Name: ENERGY CONVERSION AND MANAGEMENT
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.3138-3148
  • Keywords: genetic algorithm, oil demand, oil consumption, oil planning, oil policy, future projections, Turkey, ENERGY SUPPLY-SYSTEMS, OPTIMIZATION
  • Gazi University Affiliated: No

Abstract

This present study develops three scenarios to analyze oil consumption and make future projections based on the Genetic algorithm (GA) notion, and examines the effect of the design parameters on the oil utilization values. The models developed in the non-linear form are applied to the oil demand of Turkey. The GA Oil Demand Estimation Model (GAO-DEM) is developed to estimate the future oil demand values based on Gross National Product (GNP), population, import, export, oil production, oil import and car, truck and bus sales figures. Among these models, the GA-PGOiTI model, which uses population, GNP, oil import, truck sales and import as design parameters/indicators, was found to provide the best fit solution with the observed data. It may be concluded that the proposed models can be used as alternative solution and estimation techniques for the future oil utilization values of any country. (c) 2006 Elsevier Ltd. All rights reserved.