Hybrid Estimation Model (CNN-GRU) Based on Deep Learning for Wind Speed Estimation

Abstract

Nowadays, the need for energy is increasing day by day. In order to meet this demand, renewable energy sources that have a more environmentally friendly structure than fossil-based sources come to the fore. In recent years, researchers have been paying great attention to wind energy. Because it has the many economic and environmental advantages. In particular, wind speed is very important parameter for electric energy production form wind energy. Therefore, estimation of wind speed is very important for both investors and manufacturers. A hybrid model for wind speed estimation with deep learning methods is proposed in this study. The proposed model consists two main deep learning methods (Convolutional Neural Networks (CNN) and Gated Recurrent Unit (GRU)). The proposed model was applied in two case studies (weekly and monthly wind speed estimation). The reliability and accuracy of the proposed model were tested by performance criteria (MAPE, R2, RMSE). In order to measure the success of the model, a comparison was made with 5 different deep learning methods (CNN-LSTM, CNN-RNN, LSTM-GRU, LSTM, GRU). It has been observed that the CNN-GRU hybrid model, which was used for the first time in the field of wind speed forecasting, achieved a high percentage of success as a result of comparisons made.

Keywords

• Renewable energy
• Wind energy
• Wind speed estimation
• Deep learning methods
• Hybrid estimation model

References

1. [1] M. Tan, “Multi-step wind speed estimation based on artificial neural network using secondary separation technique”, Master’s Thesis, Tokat Gaziosmanpasa University, 2020.
2. [2] C. Emeksiz and M. M. Fındık, “Evaluation of Renewable Energy Resources for Sustainable Development in Turkey”, European Journal of Science and Technology, (26), 155-164, 2021.
3. [3] A. Yüksel, “A suitable site selection for sustainable bioenergy production facility by using novelty hybrid multi criteria decision making approach”, Master’s Thesis, Tokat Gaziosmanpasa University, 2020.
4. [4] Albostan, A., Çekiç, Y., and Levent, E., “Effect of Wind Energy on Turkey`s Energy Supply Security”, J. Fac. Eng. Arch. Gazi Univ., Vol 24, No 4, 641-649, 2009.
5. [5] REN21, Renewable Energy Global Status Report 2021. https://www.ren21.net/reports/global-status-report/ (accessed May. 03, 2022).
6. [6] X. He, L. Chu, R. C. Qiu, Q. Ai, Z. Ling, and J. Zhang, J. “Invisible units detection and estimation based on random matrix theory”, IEEE Transactions on Power Systems, 35(3), 1846-1855, 2019.
7. [7] B. Yang, T. Yu, H. Shu, J. Dong, and L. Jiang, “Robust sliding-mode control of wind energy conversion systems for optimal power extraction via nonlinear perturbation observers”, Applied Energy, 210, 711-723, 2018.
8. [8] B. Yang, X. Zhang, T. Yu, H. Shu, and Z. Fang, “Grouped grey wolf optimizer for maximum power point tracking of doubly-fed induction generator based wind turbine”, Energy Conversion and Management, 133, 427-443, 2017.

9. [9] M. W. Zafar, M. Shahbaz, A. Sinha, T. Sengupta, and Q. Qin, “How renewable energy consumption contribute to environmental quality? The role of education in OECD countries”, Journal of Cleaner Production, 268, 122149, 2020.
10. [10] S. K. Aggarwal and M. Gupta, “Wind power forecasting: a review of statistical models”, Int J Energy Sci., 3(1):1-10, 2013.
11. [11] E. Cadenas, and W. Rivera, “Wind speed forecasting in the south coast of Oaxaca, Mexico”, Renewable Energy, 32(12), 2116-2128, 2007.
12. [12] R. G. Kavasseri, and K. Seetharaman, “Day-ahead wind speed forecasting using f-ARIMA models”, Renewable Energy, 34(5), 1388-1393, 2009.
13. [13] E. Erdem, and J. Shi, “ARMA based approaches for forecasting the tuple of wind speed and direction”, Applied Energy, 88(4), 1405-1414, 2011.
14. [14] M. Ding, H. Zhou, H. Xie, M. Wu, K. Z. Liu, Y. Nakanishi, Y. and R. Yokoyama, “A time series model based on hybrid-kernel least-squares support vector machine for short-term wind power forecasting”, ISA Transactions, 108(2021), 58-68, 2021.
15. [15] J. L. Torres, A. Garcia, M. De Blas, and A. De Francisco, “Forecast of hourly average wind speed with ARMA models in Navarre (Spain)”, Solar Energy, 79(1), 65-77, 2005.
16. [16] S. A. Kalogirou, “Artificial neural networks in renewable energy systems applications: a review”, Renewable and Sustainable Energy Reviews, 5(4), 373-401, 2001.
17. [17] S. Yayla, E. Harmanci, “Estimation of target station data using satellite data and deep learning algorithms”, International Journal of Energy Research, 45(1), 961-974, 2021.
18. [18] G. Capizzi, C. Napoli, and F. Bonanno, “Innovative second-generation wavelets construction with recurrent neural networks for solar radiation forecasting”, IEEE Transactions on neural networks and learning systems, 23(11), 1805-1815, 2012.
19. [19] S. Li, “Wind power prediction using recurrent multilayer perceptron neural networks”, In 2003 IEEE Power Engineering Society General Meeting, Toronto, 2003.
20. [20] B. Yang, L. Zhong, J. Wang, H. Shu, X. Zhang, T. Yu, and L. Sun, “State-of-the-art one-stop handbook on wind forecasting technologies: An overview of classifications, methodologies, and analysis”, Journal of Cleaner Production, 283(2021), 124628, 2021.
21. [21] X. Zhao, N. Jiang, J. Liu, D. Yu, and J. Chang, “Short-term average wind speed and turbulent standard deviation forecasts based on one-dimensional convolutional neural network and the integrate method for probabilistic framework”, Energy Conversion and Management, 203(2020), 112239, 2020.
22. [22] H. Li, J. Wang, H. Lu, and Z. Guo, “Research and application of a combined model based on variable weight for short term wind speed forecasting”, Renewable Energy, 116(2018), 669-684, 2018.
23. [23] X. Mi, and S. Zhao, “Wind speed prediction based on singular spectrum analysis and neural network structural learning”, Energy Conversion and Management, 216(2020), 112956, 2020.
24. [24] L. Cheng, H. Zang, T. Ding, R. Sun, M. Wang, Z. Wei, and G. Sun, “Ensemble recurrent neural network based probabilistic wind speed forecasting approach”, Energies, 11(8), 1958, 2018.
25. [25] Q. Hu, R. Zhang, and Y. Zhou, “Transfer learning for short-term wind speed prediction with deep neural networks”, Renewable Energy, 85(2016), 83-95, 2016.
26. [26] J. Bedi, and D. Toshniwal, “Deep learning framework to forecast electricity demand”, Applied Energy, 238(2019), 1312-1326, 2019.
27. [27] O. Abedinia, M. Bagheri, M. S. Naderi, and N. Ghadimi, “A new combinatory approach for wind power forecasting”, IEEE Systems Journal, 14(3), 4614-4625, 2020.
28. [28] Z. Niu, Z. Yu, W. Tang, Q. Wu, and M. Reformat, “Wind power forecasting using attention-based gated recurrent unit network”, Energy, 196(2020), 117081, 2020.
29. [29] A. Mardani, A. Jusoh, E. K. Zavadskas, F. Cavallaro, and Z. Khalifah, “Sustainable and renewable energy: An overview of the application of multiple criteria decision making techniques and approaches”, Sustainability, 7(10), 13947- 13984, 2015.
30. [30] İ. Demir, “Wind speed estimation by effective parameters using different regression models”, Master’s Thesis, Tokat Gaziosmanpasa University, 2019.
31. [31] P. Carcagni, A. Cuna, and C. Distante, C., “A Dense CNN approach for skin lesion classification” arXiv preprint arXiv:1807.06416, 2018.
32. [32] O. Sevli, “Evrişimsel Sinir Ağları ile Bal Arısı Irklarının Tahminlenmesi”, In Proceedings on 2nd International Conference on Technology and Science, Vienna, 2019.
33. [33] X. W. Gao, R. Hui, and Z. Tian, “Classification of CT brain images based on deep learning networks”, Computer Methods and Programs in Biomedicine, 138, 49–56, 2017.
34. [34] B. Ari, A. Sengur, A. Ari, and D. Hanbay, “Apricot Plant Classification Based On Leaf Recognition by Using Convolutional Neural Networks”, International Conference on Natural Science and Engineering (ICNASE’16), Kilis, Turkey, 19- 20 March, 2016.
35. [35] E. Somuncu and N. A. Atasoy, “Evrişimli tekrarlayan sinir ağı ile metin görüntüleri üzerinde karakter tanıma uygulaması gerçekleştirilmesi”, Journal of the Faculty of Engineering & Architecture of Gazi University, 37(1), 17-27, 2022.
36. [36] C. Emeksiz and M. Tan, “Wind speed estimation using novelty hybrid adaptive estimation model based on decomposition and deep learning methods (ICEEMDAN-CNN)”, Energy 249, 123785, 2022, https://doi.org/10.1016/j.energy.2022.123785.
37. [37] Ü. Budak, “Detection of airport in satellite images”, Master’s Thesis, Fırat University, 2017.
38. [38] G. Hinton, S. Osindero, and Y. Teh, “A Fast Learning Algorithm for Deep Belief Nets, Neural Computation,” 18(7), 1527-1554, 2006.
39. [39] A. Ulu, “Deep Convolutıonal Neural Network Based Representatıons For Person Re-Identıfıcatıon”, Master’s Thesis, Istanbul Technıcal Unıversıty, 2016.
40. [40] M. Havaei, A. Davy, D. Warde-Farley, A. Biard, A. Courville, Y. Bengio, C. Pal, P. M. Jodoin, and H. Larochelle, “Brain tumor segmentation with deep neural networks,” Medical Image Analysis, 35, 18– 31, 2017.
41. [41] N. Alpaslan, A. i . Kara, B. Zencı̇r, and D. Hanbay, “Classification of breast masses in mammogram images using KNN,” Signal Processing and Communications Applications Conference (SIU), 1469-1472, Malatya, Türkiye,16-19 Mayıs 2015.
42. [42] P. Görgel and E. Kavlak, “Uzun kısa süreli hafıza ve evrişimsel sinir ağları ile rüzgar enerjisi üretim tahmini”, Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 11(1), 69-80, 2020.
43. [43] H. Ahmetoğlu and D. Resul, “Türkçe Otel Yorumlarıyla Eğitilen Kelime Vektörü Modellerinin Duygu Analizi ile İncelenmesi”, Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 24(2), 455-463, 2020.
44. [44] S. Kostadinov, “Understanding GRU Networks”, 2017. https://towardsdatascience.com/understanding-grunetworks 2ef37df6c9be. (accessed April. 22, 2022).
45. [45] R. Dey and F. M. Salem, “Gate-variants of gated recurrent unit (GRU) neural networks”, In 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS), Boston, 2017.