Jaya algoritması ile optimize edilmiş yapay sinir ağlarını kullanarak Türkiye’de elektrik enerjisi tüketiminin tahmini

Abstract

In this study, Turkey's electric energy consumption was predicted by using artificial neural networks with Jaya algorithm. As shown in Fig. A, three-layer ANN model encompassing GDP, population, and import-export values as entry parameters was formed with electric energy consumption as the exit parameter. Jaya algorithm was employed for network training. Figure A. Proposed ANN model for electric energy consumptionPurpose: The main objective of the present study was to apply ANN (artificial neural network) model with the Jaya algorithm to estimate electric energy consumption (EEC) in Turkey. Theory and Methods:The model estimates EEC based on gross domestic product (GDP), population, import, and export data. Data from 1980 to 2008 were used to develop the model and data from 2009 to 2014 were used to evaluate the model's predictive ability. 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. After defining the best model according to various error criteria, EEC values for Turkey were predicted under two different scenarios.Results: Simulation results show that, ANN-Jaya modeling performed better results than ANN-TLBO or ANN-ABC modeling. According to the root mean square error values obtained for the test set, the proposed ANN-Jaya model performed 58.9% and 43.9% better than the ANN-ABC and ANN-TLBO models, respectively. Conclusion:In this study, the EEC in Turkey between 1980 and 2023 was modeled based on GDP, population, import, and export indicators under two different scenarios. The two scenarios showed that the future EEC of Turkey would vary between 311.5 and 333.6 TWh in 2023.