Estimates of hydroelectric energy generation in Turkey with Jaya algorithm-optimized artificial neural networks

The main purpose of this study was to establish an artificial neural network (ANN) model trained by a Jaya algorithm, and use the predict Turkey’s future hydroelectric energy generation (HEG). Population, gross domestic product (GDP), installed capacity, consumption, electricity demand (GEED), average yearly temperature (AYT) data were inputted as independent variables in model. ANN-Jaya compared with ANN models other two high performance optimization methods, namely back-propagation (BP) bee colony (ABC) algorithms, test its accuracy. converged smaller error values than obtained ANN-BP ANN-ABC for both training datasets. When relative (RE) calculated set are taken into account, performs 19.3% better 31.2% ANN-BP. Therefore, HEG projections made out year 2030 using low scenario. According developed projections, Turkey will be range 104.81–124.66 TWh. present results affirm that can modeled accurately technique method shown advantageous predicting HEG.