Multilayer LSTM Model for Wind Power Estimation in the Scada System

Abstract

Wind energy is clean energy that does not pollute the environment. However, the complex and variable operating environment of a wind turbine often makes it difficult to predict the instantaneous active power generated. In this study, a wind turbine active power estimation system based on a short-term memory network (LSTM) using time series analysis is proposed. The data obtained from the wind turbine SCADA system is used as input variables. In the proposed method, a multilayer LSTM architecture is designed to train the model. The first LSTM network consists of 64 units, and the second one consists of 32 units. This is followed by a dense layer consisting of 16 neurons. In the last layer, the architecture is finalized by using a linear activation function for the prediction process. The proposed deep learning (DL)-based LSTM prediction model takes into account environmental factors such as wind speed and wind direction for active power forecasting. The results show that the LSTM-based time series analysis method is capable of effectively capturing time series features among the data. Thus, the proposed architecture can realize high-accuracy active power forecasting.

Keywords

• Power forecasting
• Wind turbine energy
• Long short-term memory
• Regression
• Machine learning

References

1. [1] M. Saglam, C. Spataru, and O. A. Karaman, “Electricity demand forecasting with use of artificial intelligence: The case of Gokceada Island,” Energies, vol. 15, no. 16, p. 5950, 2022. https://doi.org/10.3390/en15165950
2. [2] Ş. Fidan and H. Çimen, “Rüzgâr Türbinlerinde Tork ve Kanat Eğim Açısı Kontrolü,” Batman Üniversitesi Yaşam Bilimleri Dergisi, vol. 11, pp. 12–26, 2021. Retrieved from https://dergipark.org.tr/en/pub/buyasambid/issue/63446/880791
3. [3] Yilmaz, M. (2018). Real measure of a transmission line data with load fore-cast model for the future. Balkan Journal of Electrical and Computer Engineering, 6(2), 141-145. https://doi.org/10.17694/bajece.419646
4. [4] Yilmaz, M. (2017, March). The Prediction of Electrical Vehicles' Growth Rate and Management of Electrical Energy Demand in Turkey. In 2017 Ninth annual IEEE green technologies conference (GreenTech) (pp. 118-123). IEEE. https://doi.org/10.1109/GreenTech.2017.23
5. [5] M. Saglam, C. Spataru, and O. A. Karaman, “Forecasting electricity demand in Turkey using optimization and machine learning algorithms,” Energies, vol. 16, no. 11, p. 4499, 2023. https://doi.org/10.3390/en16114499
6. [6] Z. Niu, Z. Yu, W. Tang, Q. Wu, and M. Reformat, “Wind power forecasting using attention-based gated recurrent unit network,” Energy (Oxf.), vol. 196, no. 117081, p. 117081, 2020. https://doi.org/10.1016/j.energy.2020.117081
7. [7] L. Donadio, J. Fang, and F. Porté-Agel, “Numerical weather prediction and artificial neural network coupling for wind energy forecast,” Energies, vol. 14, no. 2, p. 338, 2021. https://doi.org/10.3390/en14020338
8. [8] S. Hanifi, X. Liu, Z. Lin, and S. Lotfian, “A critical review of wind power forecasting methods—past, present and future,” Energies, vol. 13, no. 15, p. 3764, 2020. https://doi.org/10.3390/en13153764

9. [9] L. Liu and Y. Liang, “Wind power forecast optimization by integration of CFD and Kalman filtering,” Energy Sources Recovery Util. Environ. Eff., vol. 43, no. 15, pp. 1880–1896, 2021. https://doi.org/10.1080/15567036.2019.1668080
10. [10] J. M. González-Sopeña, V. Pakrashi, and B. Ghosh, “An overview of performance evaluation metrics for short-term statistical wind power forecasting,” Renew. Sustain. Energy Rev., vol. 138, no. 110515, p. 110515, 2021. https://doi.org/10.1016/j.rser.2020.110515
11. [11] V. Cerqueira, L. Torgo, and C. Soares, “Machine learning vs statistical methods for time series forecasting: Size matters,” 2019. https://doi.org/10.48550/arXiv.1909.13316
12. [12] I. Aydin, S. B. Celebi, S. Barmada, and M. Tucci, “Fuzzy integral-based multi-sensor fusion for arc detection in the pantograph-catenary system,” Proc. Inst. Mech. Eng. Pt. F: J. Rail Rapid Transit, vol. 232, no. 1, pp. 159–170, 2018. https://doi.org/10.1177/0954409716662090
13. [13] Ö. A. Karaman, “Performance evaluation of seasonal solar irradiation models—case study: Karapınar town, Turkey,” Case Stud. Therm. Eng., vol. 49, no. 103228, p. 103228, 2023. https://doi.org/10.1016/j.csite.2023.103228
14. [14] A. Çalışkan, S. Demirhan, and R. Tekin, “Comparison of different machine learning methods for estimating compressive strength of mortars,” Constr. Build. Mater., vol. 335, no. 127490, p. 127490, 2022. https://doi.org/10.1016/j.conbuildmat.2022.127490
15. [15] Öztekin, A., & Erçelebi, E. (2019). An efficient soft demapper for APSK signals using extreme learning machine. Neural Computing and Applications, 31, 5715-5727. https://doi.org/10.1007/s00521-018-3392-6
16. [16] S. B. Çelebi and B. G. Emiroğlu, “Leveraging deep learning for enhanced detection of Alzheimer’s disease through morphometric analysis of brain images,” Trait. Du Signal, vol. 40, no. 4, pp. 1355–1365, 2023. https://doi.org/10.18280/ts.400405
17. [17] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. https://doi.org/10.1145/2939672.2939785
18. [18] Demir, S., & Sahin, E. K. (2023). Predicting occurrence of liquefaction-induced lateral spreading using gradient boosting algorithms integrated with particle swarm optimization: PSO-XGBoost, PSO-LightGBM, and PSO-CatBoost. Acta Geotechnica, 18(6), 3403-3419. https://doi.org/10.1007/s11440-022-01777-1
19. [19] S. Hochreiter, “The vanishing gradient problem during learning recurrent neural nets and problem solutions,” Internat. J. Uncertain. Fuzziness Knowledge-Based Systems, vol. 06, no. 02, pp. 107–116, 1998. https://doi.org/10.1142/S0218488598000094
20. [20] Yilmaz, A., & Poli, R. (2022). Successfully and efficiently training deep multi-layer perceptrons with logistic activation function simply requires initializing the weights with an appropriate negative mean. Neural Networks, 153, 87-103. https://doi.org/10.1016/j.neunet.2022.05.030
21. [21] J. F. Torres, A. Galicia, A. Troncoso, and F. Martínez-Álvarez, “A scalable approach based on deep learning for big data time series forecasting,” Integr. Comput. Aided Eng., vol. 25, no. 4, pp. 335–348, 2018. https://doi.org/10.3233/ICA-180580
22. [22] J. Zhang, J. Yan, D. Infield, Y. Liu, and F.-S. Lien, “Short-term forecasting and uncertainty analysis of wind turbine power based on long short-term memory network and Gaussian mixture model,” Appl. Energy, vol. 241, pp. 229–244, 2019. https://doi.org/10.1016/j.apenergy.2019.03.044
23. [23] S. Zhang, Y. Wang, M. Liu, and Z. Bao, “Data-based line trip fault prediction in power systems using LSTM networks and SVM,” IEEE Access, vol. 6, pp. 7675–7686, 2018. https://doi.org/10.1109/ACCESS.2017.2785763.
24. [24] S. Fidan, H. Oktay, S. Polat, and S. Ozturk, “An artificial neural network model to predict the thermal properties of concrete using different neurons and activation functions,” Adv. Mater. Sci. Eng., vol. 2019, pp. 1–13, 2019. https://doi.org/10.1155/2019/3831813
25. [25] I. Aydin, O. Yaman, M. Karakose, and S. B. Celebi, “Particle swarm based arc detection on time series in pantograph-catenary system,” in 2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings, 2014. https://doi.org/10.1109/INISTA.2014.6873642
26. [26] S. F. Stefenon, L. O. Seman, V. C. Mariani, and L. dos S. Coelho, “Aggregating prophet and seasonal trend decomposition for time series forecasting of Italian electricity spot prices,” Energies, vol. 16, no. 3, p. 1371, 2023. https://doi.org/10.3390/en16031371
27. [27] M. Ş. Üney and Ö. A. Karaman, “Load Frequency Control (LFC) of a Microgrid using PSCAD/EMTDC Simulation Program,” Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, vol. 8, no. 15, pp. 328–342, 2021. https://doi.org/10.54365/adyumbd.939716
28. [28] Ş. Fidan, M. Cebeci, and A. Gündoğdu, “Extreme Learning Machine Based Control of Grid Side Inverter for Wind Turbines,” Tehnički vjesnik, vol. 26, pp. 1492–1498, 2019. https://doi.org/10.17559/TV-20180730143757
29. [29] B. Zazoum, “Solar photovoltaic power prediction using different machine learning methods,” Energy Rep., vol. 8, pp. 19–25, 2022. https://doi.org/10.1016/j.egyr.2021.11.183
30. [30] W. Zou, C. Li, and P. Chen, “An inter type-2 FCR algorithm based T–S fuzzy model for short-term wind power interval prediction,” IEEE Trans. Industr. Inform., vol. 15, no. 9, pp. 4934–4943, 2019. doi: 10.1109/TII.2019.2910606.
31. [31] P. Du, J. Wang, W. Yang, and T. Niu, “A novel hybrid model for short-term wind power forecasting,” Appl. Soft Comput., vol. 80, pp. 93–106, 2019. https://doi.org/10.1016/j.asoc.2019.03.035
32. [32] X. Yuan, Q. Tan, X. Lei, Y. Yuan, and X. Wu, “Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine,” Energy (Oxf.), vol. 129, pp. 122–137, 2017. https://doi.org/10.1016/j.energy.2017.04.094
33. [33] S. Agatonovic-Kustrin and R. Beresford, “Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research,” J. Pharm. Biomed. Anal., vol. 22, no. 5, pp. 717–727, 2000. https://doi.org/10.1016/S0731-7085(99)00272-1
34. [34] B. Birecikli, Ö. A. Karaman, S. B. Çelebi, and A. Turgut, “Failure load prediction of adhesively bonded GFRP composite joints using artificial neural networks,” J. Mech. Sci. Technol., vol. 34, no. 11, pp. 4631–4640, 2020. https://doi.org/10.1007/s12206-020-1021-7
35. [35] H. A. N. Kubilay, G. Öztürk, and A. Aslan, “Yapay Sinir Ağları Kullanarak Yüzey Pürüzlülüğü Tespiti,” International Conference on Pioneer and Innovative Studies, vol. 1, pp. 487–492, 2023.
36. [36] H. Sun, C. Qiu, L. Lu, X. Gao, J. Chen, and H. Yang, “Wind turbine power modelling and optimization using artificial neural network with wind field experimental data,” Appl. Energy, vol. 280, no. 115880, p. 115880, 2020. https://doi.org/10.1016/j.apenergy.2020.115880
37. [37] Yilmaz, A., Simsek, C., Tozlu, B. H., Aydemir, O., & Karavelioglu, Y. (2022). Selection of suitable sensors of the electronic nose used for classification of myocardial infarction, stable coronary artery disease and healthy individuals. Selcuk University Journal of Engineering Sciences, 21(1), 39-43. https://sujes.selcuk.edu.tr/sujes/article/view/597
38. [38] S. B. Çelebi and B. G. Emiroğlu, “A novel deep dense block-based model for detecting Alzheimer’s disease,” Appl. Sci. (Basel), vol. 13, no. 15, p. 8686, 2023. https://doi.org/10.3390/app13158686
39. [39] ŞİMŞEK, C., YILMAZ, A., Tozlu, B. H., Aydemir, Ö., & Karavelioğlu, Y. (2022). Classification of Cardiovascular Diseases Using Electronic Nose Dataset with Artificial Neural Network Classifier. Avrupa Bilim ve Teknoloji Dergisi, (38), 479-483. https://doi.org/10.31590/ejosat.1165991
40. [40] S. B. Çelebi̇ and B. G. Emi̇roğlu, “Alzheimer Teşhisi için Derin Öğrenme Tabanlı Morfometrik Analiz,” Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol. 13, no. 3, pp. 1454–1467, 2023. https://doi.org/10.21597/jist.1275669
41. [41] F. Emmert-Streib, Z. Yang, H. Feng, S. Tripathi, and M. Dehmer, “An introductory review of deep learning for prediction models with big data,” Front. Artif. Intell., vol. 3, 2020. https://doi.org/10.3389/frai.2020.00004
42. [42] R. DiPietro and G. D. Hager, “Deep learning: RNNs and LSTM,” in Handbook of Medical Image Computing and Computer Assisted Intervention, Elsevier, 2020, pp. 503–519. https://doi.org/10.1016/B978-0-12-816176-0.00026-0
43. [43] S. Zaheer et al., “A multi parameter forecasting for stock time series data using LSTM and deep learning model,” Mathematics, vol. 11, no. 3, p. 590, 2023. https://doi.org/10.3390/math11030590
44. [44] M. Fazil, S. Khan, B. M. Albahlal, R. M. Alotaibi, T. Siddiqui, and M. A. Shah, “Attentional multi-channel convolution with bidirectional LSTM cell toward hate speech prediction,” IEEE Access, vol. 11, pp. 16801–16811, 2023. https://doi.org/10.1109/ACCESS.2023.3246388.
45. [45] V. Rai, G. Gupta, S. Joshi, R. Kumar, and A. Dwivedi, “LSTM-based adaptive whale optimization model for classification of fused multimodality medical image,” Signal Image Video Process., vol. 17, no. 5, pp. 2241–2250, 2023. https://doi.org/10.1007/s11760-022-02439-1
46. [46] Ö. A. Karaman, “Prediction of wind power with machine learning models,” Appl. Sci. (Basel), vol. 13, no. 20, p. 11455, 2023. https://doi.org/10.3390/app132011455
47. [47] X. Luo, D. Zhang, and X. Zhu, “Deep learning based forecasting of photovoltaic power generation by incorporating domain knowledge,” Energy (Oxf.), vol. 225, no. 120240, p. 120240, 2021. https://doi.org/10.1016/j.energy.2021.120240
48. [48] H. Chen and X. Chang, “Photovoltaic power prediction of LSTM model based on Pearson feature selection,” Energy Rep., vol. 7, pp. 1047–1054, 2021. https://doi.org/10.1016/j.egyr.2021.09.167
49. [49] Z. Ma et al., “Application of hybrid model based on double decomposition, error correction and deep learning in short-term wind speed prediction,” Energy Convers. Manag., vol. 205, no. 112345, p. 112345, 2020. https://doi.org/10.1016/j.enconman.2019.112345
50. [50] T. Ouyang, H. Huang, Y. He, and Z. Tang, “Chaotic wind power time series prediction via switching data-driven modes,” Renew. Energy, vol. 145, pp. 270–281, 2020. https://doi.org/10.1016/j.renene.2019.06.047
51. [51] Kaggle.com. [Online]. Available: https://www.kaggle.com/datasets/berkerisen/wind-turbine-scada-dataset,. [Accessed: 28-Oct-2023]
52. [52] P. Schober, C. Boer, and L. A. Schwarte, “Correlation coefficients: Appropriate use and interpretation,” Anesth. Analg., vol. 126, no. 5, pp. 1763–1768, 2018. https://doi.org/10.1213/ANE.0000000000002864
53. [53] V. Hodge and J. Austin, “A survey of outlier detection methodologies,” Artif. Intell. Rev., vol. 22, no. 2, pp. 85–126, 2004. https://doi.org/10.1023/B:AIRE.0000045502.10941.a9
54. [54] S. Shokrzadeh, M. Jafari Jozani, and E. Bibeau, “Wind turbine power curve modeling using advanced parametric and nonparametric methods,” IEEE Trans. Sustain. Energy, vol. 5, no. 4, pp. 1262–1269, 2014. https://doi.org/10.1109/TSTE.2014.2345059.
55. [55] S. G. K. Patro and K. K. Sahu, “Normalization: A Preprocessing Stage,” 2015. https://doi.org/10.48550/arXiv.1503.06462
56. [56] Bilal, M. A., Wang, Y., Ji, Y., Akhter, M. P., & Liu, H. (2023). Earthquake Detection Using Stacked Normalized Recurrent Neural Network (SNRNN). Applied Sciences, 13(14), 8121. https://doi.org/10.3390/app13148121
57. [57] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735.
58. [58] F. Shahid, A. Zameer, and M. Muneeb, “A novel genetic LSTM model for wind power forecast,” Energy (Oxf.), vol. 223, no. 120069, p. 120069, 2021. https://doi.org/10.1016/j.energy.2021.120069
59. [59] A. T. Mohan and D. V. Gaitonde, “A deep learning based approach to reduced Order Modeling for turbulent flow control using LSTM neural networks,” 2018. https://doi.org/10.48550/arXiv.1804.09269
60. [60] T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)-Arguments against avoiding RMSE in the literature,” Geoscientific model development, vol. 7, no. 3, pp. 1247–1250, 2014. https://doi.org/10.5194/gmd-7-1247-2014
61. [61] Öztekin, A., & Erçelebi, E. (2016). An early split and skip algorithm for fast intra CU selection in HEVC. Journal of Real-Time Image Processing, 12, 273-283. https://doi.org/10.1007/s11554-015-0534-2