Evaluation of power generation quantity of Gökçekaya dam with artificial neural networks
Is this your thesis?
This record came from a bulk archive import. If it’s yours, link it to your profile.
Abstract (EN)
Energy is a power to work. Energy is always a need for building serve and product. Energy is a big factor providing economic growth. The economic growth is only possible with using the energy. For the researches, countries that using too much energy are the most developed countries at the same time. Developed countries' per capita energy is more than the developing countries' per capita energy. There is a positive relationship between per capita energy and development level. Hydrology power plants are the most important resources in use. It is very important to identify the acquirable energy from these plants in terms of energy planning. Therefore artificial neural nets are used in this study to fasten the generation of energy. Study is evaluated specific to Gokcekaya dam. Water level, reservoir storage and flow spent for energy of Gokcekaya dam determined with YSA model as an input, and generated energy amount is determined in YSA model as an output. As a result of this study, created models are compared with real energy amounts and afterwards yearlong energy generation is forecasted.
Author
Zeynep Burcu Akgürbüz
How to Cite
Zeynep Burcu Akgürbüz (Master Thesis). Evaluation of power generation quantity of Gökçekaya dam with artificial neural networks, 2017, Sakarya University.
Keywords
License
Tüm Hakları Saklıdır
This work is shared under the specified license terms.
More theses from Sakarya University
- Turkey according to the records of the House of Commons (1918-1922)(2011)
- Ömer Öngüt, his views and community through publications(2025)
- Mawlana Yaqub-i Charkhi And His tafsir(2024)
- Research of teachers' attitudes and self-efficacy perceptions towards distance education application(2024)
- Tiles in architect Vedat Tek's Istanbul buildings(2024)
- Financial performance evaluation and the relationship between stock returns: Hesitant Fuzzy AHP based approach(2020)
