Rüzgar Şiddetinin Yapay Sinir Ağları Yöntemleri ile Modellenmesi

Öz

Rüzgar enerjisi, güvenilir ve uygun maliyetli elektrik sağlama kapasitesi nedeniyle önde gelen yenilenebilir enerji kaynakları arasında yer almaktadır. Rüzgar enerjisi dönüşüm sistemlerinin karmaşıklığı, ileriye dönük analizlere dayalı yeni tekniklerin geliştirilmesini zorunlu kılmaktadır. Bu çalışmada, Yapay Sinir Ağları (YSA) yöntemi kullanarak Çanakkale İli Baba Burnu bölgesinde 2001, 2002 ve 2003 yıllarına ait rüzgar enerji potansiyelinin hesaplanmasına yönelik, rüzgar şiddeti tahmini ile ilgili bir çalışma yapılmış ve gelecekte o bölgede rüzgar enerjisi üretimine yönelik ön bilgi elde edilmiştir. Araştırma çalışması sonucunda, YSA model çıktıları ile gözlenen rüzgar şiddeti değerleri arasındaki ilişki katsayısının %91 olduğu saptanmıştır. Modelin başarısı irdelenmiş, 10 m yükseklikte rüzgar şiddeti tahmini ile ilgili 1,905m/s, karekök hata (RMSE) ve 1.38m/s, ortalama karekök hata (RMSEA) 0,07 olarak hesaplanmıştır. Araştırma sonucunda, RMSEA değerlerinin 0.05 ile 0.08 arasında olması gözlem ve model sonuçları arasında yeterli bir uyum olduğunu göstermektedir.

Anahtar Kelimeler

• : Rüzgar enerjisi
• Yapay sinir ağları
• karekök hata
• ortalama karekök hata

Modeling of Wind Intensity with Artificial Neural Networks Methods

Öz

Wind energy is among the leading renewable energy sources due to its capacity to provide reliable and cost-effective electricity. The complexity of wind energy conversion systems necessitates the development of new techniques based on prospective analysis. In this study, using Artificial Neural Networks (ANN), a study was conducted to calculate the wind energy potential of Çanakkale Province Baba Burnu region for the years 2001, 2002 and 2003, and preliminary information about wind energy production in that region in the future was obtained. As a result of the research study, it was determined that the correlation coefficient between the ANN model outputs and the observed wind speed values was 91%. The success of the model was examined, and it was calculated as 1.905m/s, root mean-square error (RMSE) and 1.38m/s, Root Mean Square Error of Approximation (RMSEA) of 0.07 for the wind force estimation at 10 m height. shows that there is sufficient agreement between the model results

Anahtar Kelimeler

• Wind energy
• Artificial Neural Network
• root square error
• root mean square error of approximation

Kaynakça

1. Ak, R., Vitelli, V. ve Zio, E. (2015). An Interval-Valued Neural Network Approach for Uncertainty Quantification in Short-Term Wind Speed Prediction. IEEE Transactions on Neural Networks and Learning Systems, 26(11). doi:10.1109/TNNLS.2015.2396933
2. Gao, S., Dong, L., Liao, X. ve Gao, Y. (2013). Very-short-term prediction of wind speed based on chaos phase space reconstruction and NWP. Chinese Control Conference, CCC içinde .
3. Gunduz, O. F. ve Aslan, Z. (2020). New generation energy resources and effect on total energy consumption. AIP Conference Proceedings içinde (C. 2213). doi:10.1063/5.0000083
4. Haykin, S. (1999). Neural networks: a comprehensive foundation by Simon Haykin. The Knowledge Engineering Review.
5. İlkılıç, Z. (2016). Türkiye’de Rüzgar Enerjisi ve Rüzgar Enerji Sistemlerinin Gelişimi. Batman Üniversitesi Yaşam Bilimleri Dergisi, 6(2/2).
6. Lawan, S. M., Abidin, W. A. W. Z., Chai, W. Y., Baharun, A. ve Masri, T. (2014). Different Models of Wind Speed Prediction; A Comprehensive Review. International Journal of Scientific & Engineering Research, 5(1).
7. Li, G., Shi, J. ve Zhou, J. (2011). Bayesian adaptive combination of short-term wind speed forecasts from neural network models. Renewable Energy, 36(1). doi:10.1016/j.renene.2010.06.049
8. Marugán, A. P., Márquez, F. P. G., Perez, J. M. P. ve Ruiz-Hernández, D. (2018). A survey of artificial neural network in wind energy systems. Applied Energy. doi:10.1016/j.apenergy.2018.07.084

9. Moss, L. (2010). The 13 largest oil spills in history. Mother Nature Network.
10. Olah, G. A., Goeppert, A. ve Prakash, G. K. S. (2009). Chemical recycling of carbon dioxide to methanol and dimethyl ether: From greenhouse gas to renewable, environmentally carbon neutral fuels and synthetic hydrocarbons. Journal of Organic Chemistry. doi:10.1021/jo801260f
11. Palomares-Salas, J. C., Agüera-Pérez, A., González De La Rosa, J. J. ve Moreno-Muñoz, A. (2014). A novel neural network method for wind speed forecasting using exogenous measurements from agriculture stations. Measurement: Journal of the International Measurement Confederation, 55. doi:10.1016/j.measurement.2014.05.020
12. Philippopoulos, K. ve Deligiorgi, D. (2012). Application of artificial neural networks for the spatial estimation of wind speed in a coastal region with complex topography. Renewable Energy, 38(1). doi:10.1016/j.renene.2011.07.007
13. Pourmousavi Kani, S. A. ve Ardehali, M. M. (2011). Very short-term wind speed prediction: A new artificial neural network-Markov chain model. Energy Conversion and Management içinde (C. 52). doi:10.1016/j.enconman.2010.07.053
14. Proceedings of the 9th IASTED International Conference on Power and Energy Systems, PES 2007. (2007).Proceedings of the IASTED International Conference on Energy and Power Systems.
15. Quan, H., Srinivasan, D. ve Khosravi, A. (2014). Short-term load and wind power forecasting using neural network-based prediction intervals. IEEE Transactions on Neural Networks and Learning Systems, 25(2). doi:10.1109/TNNLS.2013.2276053
16. Robertson, C. ve Krauss, C. (2010). Gulf Spill Is the Largest of Its Kind, Scientist Say. The New York Times.
17. SAZLI, M. H. (2006). A brief review of feed-forward neural networks. Communications, Faculty Of Science, University of Ankara. doi:10.1501/0003168
18. Tolun, S., Menteş, S., Aslan, Z. ve Yükselen, M. A. (1995). The wind energy potential of Gökçeada in the Northern Aegean Sea. Renewable Energy, 6(7). doi:10.1016/0960-1481(95)00089-3
19. Erdemir, G., Akinci, T. C., & Aslan, Z. (2021). ANALYSES AND FORECASTING OF SOLAR ENERGY POTENTIAL BY USING ANN A CASE STUDY OF CENTRAL ANATOLIA-TURKEY. Fresenius Environmental Bulletin.
20. Çalişkan, M., Şubesi, E. Y. E. K., & Vekili, M. (2010). Türkiye rüzgar enerjisi potansiyeli. Devlet Meteoroloji İşleri Genel Müdürlüğü ve Türkiye Rüzgar Enerjisi Birliği (TÜREB)-Rüzgar Enerjisi Semineri.
21. URL1-https://www.tureb.com.tr/ (27.06.2022)
22. URL2-https://enerji.gov.tr/eigm-yenilenebilir-enerji-kaynaklar-ruzgar (27.06.2022)
23. URL3- https://temizenerji.org/2022/04/15/turkiyenin-ruzgar-kurulu-gucu-48-ildeki-santrallerle-yaklasik-11-bin-mwa-ulasti/ (15 Nisan 2022).
24. URL4- https://zenodo.org/record/3240040#.YrcFIHZByUk, Menteş, S., T. Kaytancı, Y. Ezber, Assessment of surface wind from the long term production run over Turkey, ( 27.07.2022).