Bayes Optimizasyonu Ve Topluluk Öğrenmesine Dayalı Kısa Dönem Rüzgar Gücü Tahmin Yaklaşımı

Abstract

Rüzgar enerjisi çalışmalarında, rüzgâr santralleri için kısa dönem enerji üretim miktarının tahmini ve piyasaya verilecek üretim teklifinin belirlenmesi önemli bir rol oynamaktadır. Çalışmada Türkiye’de bulunan ve kurulu gücü 3600 kW olan rüzgar türbinin saatlik kısa dönem rüzgar enerjisi tahmini yapılmıştır. Tahmin sonuçları mevsimsel ve yıllık olarak değerlendirilmiştir. Kısa dönem rüzgar gücü tahmini için bayes optimizasyonu, destek vektör regresyonu, gauss süreç regresyonu, karar ağacı, stacking ve bagging algoritmalarının birleşiminden oluşan yeni hibrit modeller geliştirilmiştir. Önerilen tahmin yaklaşımında farklı regresyon algoritmaları ile bayes optimizasyon yöntemi ve topluluk algoritmaları birleştirilerek tahmin hatalarının azaltılması amaçlanmıştır. Çalışmada temel öğrenen olarak seçilen regresyon algoritmalarının hiper parametre seçiminde diğer rüzgar tahmin çalışmalarından farklı olarak ilk defa bayes optimizasyonu kullanılmıştır. Temel öğreniciler içerisinde en düşük hata değerlerine sahip bayes algoritması ile optimize edilmiş karar ağacı ve gauss süreç regresyonu, torbalama ve istifleme ile birleştirilmiştir. Topluluk öğrenmesi algoritmalarının etkinliği istatistiksel ölçüm yöntemleri olan Normalize Mutlak Ortalama Hata (NMAE), Normalize Ortalama Hata Kareleri Kökü (NRMSE) ve determinasyon katsayısı (𝐑^𝟐) ile ölçülmüştür. Sonuçlara göre bayes algoritması ile optimize edilmiş karar ağacı ile oluşturulan torbalama yöntemi yıllık ortalama NRMSE, NMAE, 𝐑^𝟐 kriterleri sırasıyla 11.045 %, 4.880 %, 0.899 değerlerini almış ve hem yıllık hem de mevsimlik sonuçlar açısından en iyi performansa sahip model seçilmiştir.

Keywords

• Yenilenebilir enerji
• Rüzgar gücü tahmini
• Bayes Optimizasyonu
• Topluluk öğrenmesi

Short-Term Wind Power Prediction Approach Based On Bayesian Optimization and Ensemble Learning

Abstract

In wind energy studies, predicting the short-term energy generation amount for wind power plants and determining the production offer to be placed on the market play an important role. In this study an hourly short-term wind power estimation of a wind turbine located in Turkey with an installed power of 3600 kW has been made. Estimation results were evaluated on a seasonal and annual basis. New hybrid models have been developed for short-term wind power prediction, consisting of Bayesian Optimization (BO), Support Vector Regression (SVR), Gaussian Process Regression (GPR), Decision Tree (DT), stacking, and bagging algorithms. In the proposed prediction approach, it is aimed to reduce prediction errors by combining different regression algorithms with the BO method and ensemble algorithms. Unlike other wind prediction studies, BO was used for the first time in the hyperparameter selection of the regression algorithms selected as the basic learner in the study. Bayesian optimized decision tree (BO-DT) with the lowest error values among the base learners, and Bayesian optimized gaussian process regression (BO-GPR) combined with bagging and stacking. The efficiency of ensemble learning algorithms was measured by the statistical measurement methods Normalized Absolute Mean Error (NMAE), Normalized Root of Mean Squares Error (NRMSE), and determination coefficient (R²). According to the results, the bagging method created with the BO-DT took the annual average NRMSE, NMAE, R² criteria of 11.045%, 4.880%, 0.899, respectively, and the model with the best performance was selected in terms of both annual and seasonal results.

Keywords

• Bayesian Optimization
• Ensemble Learning
• Renewable energy
• Wind power prediction

References

1. Acikgoz, H., Yildiz, C., Sekkeli, M., (2020). An extreme learning machine based very short-term wind power forecasting method for complex terrain. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 42(22), 2715-2730, DOI:10.1080/15567036.2020.1755390.
2. Ahmad, M.W., Mourshed, M., Rezgui, Y., (2018). Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression. Energy, 164, 465-474.
3. Alade, I.O., Abd Rahman, M.A., Saleh, T.A., (2019). Predicting the specific heat capacity of alumina/ethylene glycol nanofluids using support vector regression model optimized with Bayesian algorithm. Solar Energy, 183, 74–82.
4. Bağcı, E., (2019). Türkiye’de Yenilenebilir Enerji Potansiyeli, Üretimi, Tüketimi ve Cari İşlemler Dengesi İlişkisi. R&S- Research Studies Anatolia Journal, 2 (4), 101-117. DOI: 10.33723/rs.501940.
5. Banik, R., Das, P., Ray, S., Biswas, A., (2020). Wind power generation probabilistic modeling using ensemble learning techniques. Materials Today: Proceedings, 26, 2157–2162.
6. Bishop, C., (2006). Pattern Recognition and Machine Learning. Information Science and Statistics. Springer.
7. Breiman, L., (1996). Bagging predictors. Machine learning, 24, 123–140.
8. Breiman. L., Friedman, J.H., Olshen, R.A., (1984). CART: Classification and Regression Trees. Biometrics, 40, 358–380.

9. Chen, N., Qian, Z., Nabney, I., Meng, X., (2014). Wind power forecasts using Gaussian processes and numerical weather prediction. IEEE Trans. Power Syst., 29(2), 656-665.
10. Chen, N., Qian, Z., Meng, X., (2013). Short-term wind power forecasting using Gaussian processes. Proceedings of 23rd international joint conference on artificial intelligence, 3-9 August 2013. pp. 2790-2796.
11. Cornejo-Bueno, L., Garrido-Merchán, E.C., Hernández-Lobato, D., Salcedo-Sanz, S., (2018). Bayesian optimization of a hybrid system for robust ocean wave features prediction. Neurocomputing, 275, 818–828.
12. Deng, H., Fannon, D., Eckelman, M.J., (2018). Predictive modeling for US commercial building energy use: a comparison of existing statistical and machine learning algorithms using CBECS microdata. Energy Build, 163, 34-43.
13. Don, B., Cao, C., Lee, S.E., (2005). Applying support vector machines to predictbuilding energy consumption in tropical region. Energy Build, 37 (5). 545-553.
14. Erisen, B., (2019). Wind turbine scada dataset, Version 3. Available Online: https://www.kaggle.com/berkerisen/wind-turbine-scada- dataset (accessed on 10 August 2020).
15. Eroğlu, M., (2019). Enerji Hukuku. İstanbul: BAU.
16. Esfetang, N. N. & Kazemzadeh, R., (2018). A novel hybrid technique for prediction of electric power generation in wind farms based on WIPSO neural network and wavelet transform. Energy, 149, 662-674.
17. ETKB. (2019). Enerji ve Tabii Kaynaklar Bakanlığı, Available Online: https://enerji.gov.tr/bilgi-merkezi-enerji-elektrik (accessed on 4 January 2021).
18. Fu. C., Li. G.-Q., Lin. K.-P., Zhang. H.-J., (2019). Short-term wind power prediction based on improved chicken algorithm optimization support vector machine. Sustainability, 11, 512.
19. Gao, Z., Shi, J., Li, H., Chen, C., Tan, J., Liu, L., (2020). Substation Load Characteristics and Forecasting Model for Large-scale Distributed Generation Integration. IOP Conf. Series: Materials Science and Engineering, 782, 032044 doi:10.1088/1757-899X/782/3/032044
20. Hastie, T., Tibshirani, R., Friedman, J., (2009). The Elements of Statistical Learning: Data Mining. Inference. and Prediction. Second Edition. Springer Series in Statistics. Springer.
21. Heinermann, J. & Kramer, O., (2016). Machine learning ensembles for wind power prediction. Renewable Energy.89, 671-679.
22. Heo, Y. & Zavala, V.M., (2012). Gaussian process modeling for measurement and verification of building energy savings. Energy Build, 53, 7-18.
23. Karık, F., Sözen, A. & İzgeç, M.M., (2017). Rüzgâr gücü tahminlerinin önemi: Türkiye elektrik piyasasında bir uygulama. Politeknik Dergisi. 20(4), 851-861.
24. Kerem, A., (2018). Rüzgar Parametrelerinin Değişiminin İzlenmesi ve Yapay Zeka Algoritmaları Kullanarak Tahmini. Doktora Tezi. Gazi Üniversitesi
25. Lee, D. & Baldick, R., (2014). Short-term wind power ensemble prediction based on Gaussian processes and neural networks. IEEE Trans Smart Grid, 5(1), 501-510.
26. Li, C., Lin, S., Xu. F., Liu, D., Liu, J., (2018). Short-term wind power prediction based on data mining technology and improved support vector machine method: a case study in Northwest China. J. Cleaner Prod., 205(4), 909-922, 10.1016/j.jclepro.2018.09.143
27. Li, L.-L., Zhao, X., Tseng, M.-L., Tan, R.R., (2020). Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm. J Clean Prod. 242, 118447. 10.1016/j.jclepro.2019.118447
28. Li, Q., Meng, Q., Cai, J., Yoshino, H., Mochida, A., (2009). Applying support vector machine to predict hourly cooling load in the building. Appl Energy, 86(10), 2249- 2256.
29. Ma, Y.-J. & Zhai, M.-Y., (2019). A dual-step integrated machine learning model for 24h-ahead wind energy generation prediction based on actual measurement data and environmental factors. Appl Sci., 9, 21-25. 10.3390/app9102125
30. Mendes-Moreira, J.A., Soares, C., Jorge, A.M., Sousa, J.F.D., (2012). Ensemble approaches for regression: A survey. ACM Comput. Surv., 45(1), 1-10. http://dx.doi.org/10.1145/2379776.2379786
31. NOAA, 2018. National Weather Service Center Environmental Forecast Climate. Avaliable Online: https://www.ncdc.noaa.gov/cdo-web/ (accessed on 15 October 2020).
32. Öz, S. & Alyürük, M., (2020). Energy Sector Overview and Future Prediction for Turkey. Journal of Industrial Policy and Technology Management. 3(1). 2020. 59-69
33. Petropoulos, A., Chatzis, S.P., Siakoulis, V., Vlachogiannakis, N., (2017). A stacked generalization system for automated forex portfolio trading. Expert Syst. Appl., 90, 290–302. http://dx.doi.org/10.1016/j.eswa.2017.08.011
34. Rasmussen. C. E. &Williams, C. K. I., (2006). Gaussian Processes for Machine Learning. MIT Press, Cambridge, Massachusetts.
35. Serbes, G., Sakar, B.E, Gulcur, H.O., Aydin, N., (2015). An emboli detection system based on dual tree complex wavelet transform and ensemble learning. Appl. Soft Comput., 37 (2015) 87–94. http://dx.doi.org/10.1016/j.asoc.2015. 08.015
36. Shamaei, E. & Kaedi, M., (2016). Suspended sediment concentration estimation by stacking the genetic programming and neuro-fuzzy predictions. Appl. Soft Comput., 45, 187–196. http://dx.doi.org/10.1016/j.asoc.2016.03.009
37. Şenel, M.C. & Koç, E., (2015). Dünyada ve Türkiye’de Rüzgâr Enerjisi Durumu-Genel Değerlendirme. Mühendis ve Makina. 56(663), 46-56.
38. Tahir, M., El-Shatshat, R., Salama, M.M.A., (2018). Improved stacked ensemble based model for very short-term wind power forecasting. In: Proceedings – 53rd International universities power engineering conference (UPEC). Glasgow. 4–7 September.
39. TÜREB, (2021). Türkiye Rüzgar Enerjisi Birliği RES Veritabanı, Available Online: https://www.tureb.com.tr/ (accessed on 31 December 2020).
40. Van der Laan, M.J., Polley, E.C., Hubbard, A.E., (2007). Super learner. Statistical Applications in Genetics and Molecular Biology, 6(1) http://dx.doi.org/10.2202/1544-6115.1309
41. Wan, Z.Y. & Sapsis, T.P., (2017). Reduced-space Gaussian Process Regression for data-driven probabilistic forecast of chaotic dynamical systems. PhysicaD, 345, 40–55.
42. Wang, C., Li, S., Zhu, M., (2012). Bayesian network learning algorithm based on unconstrained optimization and ant colony optimization. Syst Eng Electron, 5, 784–90.
43. Wolpert, D.H., (1992). Stacked generalization. Neural Netw. 5 (2), 241–259. http://dx.doi.org/10.1016/S0893-6080(05)80023-1. YEKDEM, (2020). Yenilenebilir Enerji Kaynakları Destekleme Mekanizması (YEKDEM), Available Online:https://www.enerjiportali.com/wpcontent/uploads/2020/09/KSD_YEKDEM_2.09.2020-1-1.pdf (accessed on 8 January 2020).
44. Zendehboudi, A., Baseer, M.A., Saidur, R., (2018). Application of support vector machine models for forecasting solar and wind energy resources: a review. J. Clean. Prod., 199, 272-285.