Journal of Fundamentals of Renewable Energy and Applications
Open Access

Abstract

Estimation of Energy to be produced in Hydroelectric Power Plants by Using Artificial Neural Networks and Innovative Sen Method

Gokmen Ceribasi* and Ahmet Iyad Ceyhunlu

The most common type of renewable energy resources is hydroelectric energy plants. In this type of energy plants, knowing flow rate and head level enables to make estimations about power generation and future energy planning. It is very important to make both short-term and long-term estimations in hydroelectric power plants for a good power generation planning. Therefore, in this study Innovative Sen Method has been used for long-term power generation estimations and Artificial Neural Networks have been used for short-term power generation estimations at Dogancay 1 and Dogancay 2 hydroelectric power plants, located in Central Sakarya Basin of Turkey. In Innovative Sen Method, daily total energy generation levels from 2014 to 2018 have been used; and in short-term estimation, Phyton software has been used for Artificial Neural Networks. Short-term estimation was made until year of 2030. As a result of study, high R2 and low MSE values at Artificial Neural Networks model showed accuracy of model for Dogancay 1 and Dogancay 2 hydroelectric power plants located on Sakarya River. As a result of innovative Sen Method, a prospective decreasing trend has been observed in energy generation of Dogancay 1 and Dogancay 2 hydroelectric power plants.