Estimation of Hydroelectric Power Generation Forecasting and Analysis of Climate Factors with Deep Learning Methods: A Case Study in Yozgat Province in Turkey
Uložené v:
| Názov: | Estimation of Hydroelectric Power Generation Forecasting and Analysis of Climate Factors with Deep Learning Methods: A Case Study in Yozgat Province in Turkey |
|---|---|
| Autori: | Feyza Nur Çakıcı, Suleyman Sungur Tezcan, Hıdır Düzkaya |
| Zdroj: | Gazi Üniversitesi Fen Bilimleri Dergisi, Vol 12, Iss 4, Pp 819-831 (2024) Volume: 12, Issue: 4819-831 Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Gazi University Journal of Science Part C: Design and Technology |
| Informácie o vydavateľovi: | Gazi Universitesi Fen Bilimleri Dergisi Part C: Tasarim ve Teknoloji, 2024. |
| Rok vydania: | 2024 |
| Predmety: | Elektrik Enerjisi Üretimi (Yenilenebilir Kaynaklar Dahil, Fotovoltaikler Hariç), Q1-390, Science (General), Science, Hydroelectric generation, climate data, deep learning methods, power forecasting, Electrical Energy Generation (Incl. Renewables, Excl. Photovoltaics), hydroelectric generation, TA1-2040, Engineering (General). Civil engineering (General) |
| Popis: | Hydroelectric power is a significant renewable energy source for the development of countries. However, climatic data can impact power generation in hydroelectric power plants. Hydroelectric power forecasting is conducted in this study using Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and hybrid LSTM-SVR models based on climatic data. The dataset consists of climate data from the Yozgat Meteorology Directorate in Turkey from 2007 to 2021 and power data obtained from the Süreyyabey Hydroelectric Power Plant in Yozgat. The correlation coefficient examines the relationship between climate data and monthly hydroelectric power generation. The hyper-parameters of the models are adjusted using the Bayesian Optimization (BO) method. The performance of monthly hydroelectric power prediction models is assessed using metrics such as correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE). When trained using 11 and 12 climate parameters, the SVR model exhibits an R-value close to 1, and MAE and RMSE values close to 0 are observed. Additionally, regarding training time, the SVR model achieves accurate predictions with the shortest duration and the least error compared to other models. |
| Druh dokumentu: | Article |
| Popis súboru: | application/pdf |
| ISSN: | 2147-9526 |
| DOI: | 10.29109/gujsc.1517800 |
| Prístupová URL adresa: | https://doaj.org/article/d041e7d2d66e44d38633e89cd46205ab https://avesis.gazi.edu.tr/publication/details/881a4aba-83e7-4b4a-876e-bac2c843e150/oai https://dergipark.org.tr/tr/pub/gujsc/issue/89546/1517800 |
| Prístupové číslo: | edsair.doi.dedup.....4e9956b6d50acf79d929bf136bd2913b |
| Databáza: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | Hydroelectric power is a significant renewable energy source for the development of countries. However, climatic data can impact power generation in hydroelectric power plants. Hydroelectric power forecasting is conducted in this study using Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and hybrid LSTM-SVR models based on climatic data. The dataset consists of climate data from the Yozgat Meteorology Directorate in Turkey from 2007 to 2021 and power data obtained from the Süreyyabey Hydroelectric Power Plant in Yozgat. The correlation coefficient examines the relationship between climate data and monthly hydroelectric power generation. The hyper-parameters of the models are adjusted using the Bayesian Optimization (BO) method. The performance of monthly hydroelectric power prediction models is assessed using metrics such as correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE). When trained using 11 and 12 climate parameters, the SVR model exhibits an R-value close to 1, and MAE and RMSE values close to 0 are observed. Additionally, regarding training time, the SVR model achieves accurate predictions with the shortest duration and the least error compared to other models. |
|---|---|
| ISSN: | 21479526 |
| DOI: | 10.29109/gujsc.1517800 |