Investiation of Meteorological Parameters Affecting Wind Speed Using Different Regression Techniques

Abstract

Wind energy is the most preferred source among renewable energy sources due to its many advantages. In order to use wind energy efficiently in wind farms, the wind speed must be predicted precisely and reliably. However, there are many meteorological factors that affect the wind speed. For this reason, wind speed estimation was carried out using real-time wind speed, humidity, pressure and temperature data measured from the measurement station established in the campus of the Faculty of Engineering and Architecture of Tokat Gaziosmanpasa University. In particular, simple linear regression, multiple linear regression and multiple non-linear regression methods were used to establish a mathematical connection between meteorological data and wind speed. In this study, which aims to estimate the wind speed accurately and reliably, it has been determined that the multiple non-linear regression method comes to the fore and makes estimation with a lower error rate. As a result of the year-based analyzes, the lowest error (Root mean square error, RMSE) was observed in the Temperature-Humidity group with 0.062, and the highest error was observed in the Temperature-Pressure group with 0.068 RMSE.

Keywords

• Renewable energy
• Wind speed estimation
• Regression analysis

Farklı Regresyon Teknikleri Kullanarak Rüzgar Hızına Etkiyen Meteorolojik Parametrelerin İncelenmesi

Abstract

Rüzgar enerjisi sahip olduğu birçok avantajdan dolayı yenilenebilir enerji kaynakları arasında en çok tercih edilen kaynak olmaktadır. Rüzgar çiftliklerinde rüzgar enerjisinin verimli kullanılabilmesi için rüzgar hızının hassas ve güvenilir bir şekilde tahmin edilmesi gerekmektedir. Fakat rüzgar hızına etkiyen birçok meteorolojik faktör vardır. Bu nedenle Tokat Gaziosmanpaşa Üniversitesi Mühendislik ve Mimarlık Fakültesi yerleşkesinde kurulan ölçüm istasyonundan ölçülen gerçek zamanlı rüzgar hızı, nem, basınç ve sıcaklık verileri kullanılarak rüzgar hızı tahminlemesi gerçekleştirilmiştir. Özellikle meteorolojik veriler ile rüzgar hızı arasında matematiksel bir bağlantı kurmak için basit lineer regresyon, çoklu lineer regresyon ve çoklu non-lineer regresyon yöntemleri kullanılmıştır. Rüzgar hızının doğru ve güvenilir bir şekilde tahminlenmesi amaçlanan bu çalışmada çoklu non-lineer regresyon yönteminin ön plana çıktığı ve daha düşük hata oranı ile tahminleme yaptığı belirlenmiştir. Yıl bazlı yapılan analizler sonucunda ise en düşük hata (ortalama karesel hatanın karekökü, RMSE) 0.062 ile Sıcaklık-Nem grubunda, en yüksek hata ise 0.068 ile Sıcaklık-Basınç grubunda görülmüştür.

Keywords

• Yenilenebilir enerji
• Rüzgar hızı tahmini
• Regresyon analizi

References

1. Ambach, D., Schmid, W., 2017. A new high-dimensional time series approach for wind speed, wind direction and air pressure forecasting. Energy 135:833-850.
2. Bayazıt, M., 1981. Hidrolojide İstatistik Yöntemler, İTÜ Matbaası, Gümüşsuyu, İstanbul.
3. Bayazıt, M., Yeğen, O.B., 2005. Mühendisler İçin İstatistik, Birsen Yayınevi, İstanbul.
4. Cadenas, E., Rivera, W., 2009. Short term wind speed forecasting in La Venta, Oaxaca, Mexico, using artificial neural networks. Renew Energy 34:274–8.
5. Chang, G.W., Lu, H.J., Chang, Y.R., Lee, Y.D., 2017. An improved neural network-based approach for short-term wind speed and power forecast. Renew Energy 105:301–11.
6. Da, L., Dongxiao, N., Hui, W., Leilei, F., 2014. Short-term wind speed forecasting using wavelet transform and support vector machines optimized by genetic algorithm. Renew Energy 62:592–7.
7. Deane, J.P., Drayton, G., Ó Gallachóir, B.P., 2014. The impact of sub-hourly modelling in power systems with significant levels of renewable generation. Appl Energy 113:152–8.
8. Erdem, E., Shi, J., 2011. ARMA based approaches for forecasting the tuple of wind speed and direction. Appl. Energy 88 (4):1405-1414.

9. Gao, S., He, Y., Chen, H., 2009. Wind speed forecast for wind farms based on ARMAARCH model, in: 2009 International Conference on Sustainable Power Generation and Supply, IEEE, pp. 1-4.
10. Global wind energy council (GWEC), Global wind statistic. URL http://www.gwec.net. (Erişim Tarihi: 12.10.2021).
11. Guo Z.H., Jie W.J., Lu H.Y., Wang J.Z., 2011. A case study on a hybrid wind speed forecasting method using BP neural network. Knowl-Based Syst 24:1048–56.
12. Hu, J., Wang, J., Ma, K., 2015. A hybrid technique for short-term wind speed prediction. Energy 81:563–74.
13. Jiang, P., Li, C., 2018. Research and application of an innovative combined model based on a modified optimization algorithm for wind speed forecasting. Measurement 124:395-412.
14. Kavasseri R.G., Krithika S., 2009. Day-ahead wind speed forecasting using f-ARIMA models. Renew Energy 34:1388–93.
15. Kömürcü, M.İ., Özölçer, İ.H., Yüksek, Ö., Karasu, S., 2007. Determination of Bar Parameters Caused By Cross-Shore Sediment Movement. Ocean Eng 34 (5-6), 685-695.
16. Lacal Arantegui, R., Jäger-Waldau, A., 2018. Photovoltaics and wind status in the European Union after the Paris Agreement. Renew Sustain Energy Rev 81:2460–71. http://dx.doi.org/10.1016/j.rser.2017.06.052.
17. Li, C., Xiao, Z., Xia, X., Zou, W., Zhang, C., 2018. A hybrid model based on synchronous optimisation for multi-step short-term wind speed forecasting. Appl Energ 215:131-44.
18. Li G., Shi J., 2010. On comparing three artificial neural networks for wind speed forecasting. Appl Energy 87(7):2313–20.
19. Liu, H., Mi, X-w., Li, Y-f., 2018. Wind speed forecasting method based on deep learning strategy using empirical wavelet transform, long short term memory neural network and Elman neural network. Energy Convers Manag.156: 498-514.
20. Liu Q., Lei Q., Xu H., Yuan J., 2018. China’s energy revolution strategy into 2030. Resour Conserv Recycl;128:78–89. http://dx.doi.org/10.1016/j.resconrec.2017.09.028.
21. Liye, X., Wei, S., Yu, M., Jing, M., Congjun, J., 2017. Research and application of a hybrid wavelet neural network model with the improved cuckoo search algorithm for electrical power system forecasting. Appl Energy 198:203–22.
22. Lydia, M., Kumar, S.S., Selvakumar, A.I., Kumar, G.E.P., 2016. Linear and nonlinear autoregressive models for short-term wind speed forecasting. Energy Convers Manage. 112:115–24.
23. Meng, A., Ge, J., Yin, H., Chen, S., 2016. Wind speed forecasting based on wavelet packet decomposition and artificial neural networks trained by crisscross optimization algorithm. Energy Convers Manage 114:75–88.
24. Naik, J., Satapathy, P., Dash, P.K., 2018. Short-term wind speed and wind power prediction using hybrid empirical mode decomposition and kernel ridge regression. Appl Soft Comput 70:1167-1188.
25. Ping, J., Feng, L., Yiliao, S., 2017. A hybrid forecasting model based on date-framework strategy and improved feature selection technology for short-term load forecasting. Energy 119:694–709.
26. Ramasamy, P., Chandel, S.S., Yadav, A.K., 2015. Wind speed prediction in the mountainous region of India using an artificial neural network model. Renew Energy 80:338–47.
27. Ren, C., An, N., Wang, J., Li, L., Hu, B., 2014. Shang D. Optimal parameters selection for BP neural network based on particle swarm optimization: a case study of wind speed forecasting. Knowl Based Syst 56:226-39.
28. Schlink, U., Tetzlaff, G., 1998. Wind speed forecasting from 1 to 30 minutes. Theor Appl Ckinatol 60:191–8.
29. Version, D., 2011. The State-of-the-art in Short-term Prediction of Wind Power.
30. Vural, A., 2007. Aykırı Değerlerin Regresyon modellerine Etkileri ve Sağlam Kestiriciler. Marmara Üniversitesi Sosyal Bilimler Enstitüsü, (Yüksek Lisans Tezi), İstanbul.
31. Wang, J., Qin, S., Zhou, Q., Jiang, H., 2015. Medium-term wind speeds forecasting utilizing hybrid models for three different sites in Xinjiang, China. Renew. Energy 76:91-101.
32. Wang, S., Zhang, N., Wu, L., Wang, Y., 2016. Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method. Renew Energy 94:629-36.
33. Xiao, L.Y., Qian, F., Shao, W., 2017. Multi-step wind speed forecasting based on a hybrid forecasting architecture and an improved bat algorithm. Energy Convers Manage 143:410–30.
34. Yavuz, S., Deveci, M., 2013. İstatiksel Normalizasyon Tekniklerinin Yapay Sinir Ağın Performansına Etkisi. Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi (40), 167-187.
35. Yu, C., Li, Y., Zhang, M., 2017. An improved wavelet transform using singular spectrum analysis for wind speed forecasting based on Elman Neural Network. Energy Convers Manage 148:895–904.