Application of Jaya algorithm-trained artificial neural networks for prediction of energy use in the nation of Turkey


UZLU E.

ENERGY SOURCES PART B-ECONOMICS PLANNING AND POLICY, vol.14, no.5, pp.183-200, 2019 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 14 Issue: 5
  • Publication Date: 2019
  • Doi Number: 10.1080/15567249.2019.1653405
  • Journal Name: ENERGY SOURCES PART B-ECONOMICS PLANNING AND POLICY
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.183-200
  • Keywords: Artificial neural network, teaching-learning-based optimization, artificial bee colony algorithm, Jaya algorithm, energy consumption, demand, PARTICLE SWARM OPTIMIZATION, LEARNING-BASED OPTIMIZATION, BEE COLONY ALGORITHM, DESIGN OPTIMIZATION, ELECTRICITY CONSUMPTION, DEMAND ESTIMATION, TERM, GA, MODEL, SIZE
  • Karadeniz Technical University Affiliated: No

Abstract

In this study, a novel artificial neural network (ANN)-Jaya algorithm hybrid artificial intelligence model was developed to estimate Turkey's future energy use. The model estimates energy consumption based on gross domestic product (GDP), population, import data, and export data. The Jaya algorithm used in our model's development is a simple and powerful metaheuristic algorithm that overcomes the complexity of difficult optimization problems; it provides optimal results quickly owing to its ease of applicability and simple structure. Our ANN-Jaya model's performance was compared with the performance of artificial bee colony (ABC) and teaching learning based optimization (TLBO) algorithm-trained ANN models. According to the root mean square error (RMSE) values obtained for the test set, the proposed ANN-Jaya model performed 36.7% and 46.2% better than the ANN-ABC and ANN-TLBO models, respectively. After defining the optimal configurations, three energy consumption prediction scenarios were developed and compared with previously published forecasts.