Estimates of Energy Consumption Using Neural Networks with the Grey Wolf Optimizer Algorithm for Turkey

Abstract

The primary objective of this study was to apply the ANN (artificial neural network) model with the grey wolf optimizer (GWO) algorithm to estimate energy consumption of Turkey. Gross domestic product, population, import, and export data were selected as independent variables in the model. To assess the applicability and accuracy of the proposed method, ANN-GWO was compared with the ANN models trained with artificial bee colony (ABC) and back propagation (BP) algorithms. Solutions indicate that the ANN-GWO model is superior to ANN-ABC and ANN-BP models. Using the ANN-GWO model, future estimation of Turkey's energy consumption was projected up to 2023 according to two different scenarios. The forecasted results were compared with projections by the MENR (Ministry of Energy and Natural Resources) and other related studies in the literature. The results show that energy consumption can be modeled using the proposed model and the ANN-GWO can be used to predict future energy consumption.

Keywords

• Grey Wolf Optimizer Algorithm
• Artificial Bee Colony Algorithm; Back Propagation Algorithm; Energy Consumption/Demand; Neural Networks; Turkey
• Artificial Bee Colony Algorithm
• Back Propagation Algorithm
• Energy Consumption/Demand
• Neural Networks; Turkey