Email this article A COMPARATIVE STUDY OF FEATURE SELECTION METHODS FOR WIND SPEED
About this article
Received: 21/01/22 Revised: 19/04/22 Published: 21/04/22Authors
1. Nguyen Thi Hoai Thu
, Hanoi University of Science and Technology2. Pham Nang Van, Hanoi University of Science and Technology
3. Nguyen Vu Nhat Nam, Hanoi University of Science and Technology
4. Pham Hai Minh, Hanoi University of Science and Technology
5. Phan Quoc Bao, Hanoi University of Science and Technology
Abstract
Forecasting wind speed or capacity of wind power is playing an important role to serve the problem of resource mobilization of the power system. However, forecasting is still a difficult problem because there are many factors affecting wind speed. In this paper, our goals are using some feature selection methods to find the best approach as well as to select the meteorological parameters that have great influence on wind speed, thereby helping to improve our predictive model. Pearson’s Correlation, Random Forest, Boruta were 3 feature selection methods to be used on 2 weather datasets in 2 different locations. Firstly, each data was analyzed with separate autocorrelation and partial autocorrelation analysis. From this, the hysteresis characteristics of the data were obtained then added to the methods. Following that, we carried out and compared the performance of the feature selection methods based on the evaluation criteria of each method. The results show that the wind speed depends heavily on the lags closest to it and in different geographical locations gives different results.
Keywords
Full Text:
PDFReferences
[1] T. H. T. Nguyen, T. Nakayama, and M. Ishida, “Optimal capacity design of battery and hydrogen system for the DC grid with photovoltaic power generation based on the rapid estimation of grid dependency,” Int. J. Electr. Power Energy Syst., vol. 89, pp. 27-39, Jul. 2017, doi: 10.1016/j.ijepes.2016.12.012.
[2] Y. Jiang and G. Huang, “Short-term wind speed prediction: Hybrid of ensemble empirical mode decomposition, feature selection and error correction,” Energy Convers. Manag., vol. 144, pp. 340-350, Jul. 2017, doi: 10.1016/j.enconman.2017.04.064.
[3] C. Zhang, H. Wei, J. Zhao, T. Liu, T. Zhu, and K. Zhang, “Short-term wind speed forecasting using empirical mode decomposition and feature selection,” Renew. Energy, vol. 96, pp. 727-737, Oct. 2016, doi: 10.1016/j.renene.2016.05.023.
[4] I. M. Müller, “Feature selection for energy system modeling: Identification of relevant time series information,” Energy AI, vol. 4, p. 100057, Jun. 2021, doi: 10.1016/j.egyai.2021.100057.
[5] T. N. Lal, O. Chapelle, J. Weston, and A. Elisseeff, “Embedded Methods,” in Feature Extraction: Foundations and Applications, I. Guyon, M. Nikravesh, S. Gunn, and L. A. Zadeh, Eds. Berlin, Heidelberg: Springer, 2006, pp. 137-165, doi: 10.1007/978-3-540-35488-8_6.
[6] S. Matharaarachchi, M. Domaratzki, and S. Muthukumarana, “Assessing feature selection method performance with class imbalance data,” Mach. Learn. Appl., p. 100170, Oct. 2021, doi: 10.1016/j.mlwa.2021.100170.
[7] U. Stańczyk, “Feature Evaluation by Filter, Wrapper, and Embedded Approaches,” in Feature Selection for Data and Pattern Recognition, U. Stańczyk and L. C. Jain, Eds. Berlin, Heidelberg: Springer, 2015, pp. 29-44, doi: 10.1007/978-3-662-45620-0_3.
[8] K. P. Senthil and D. Lopez, “Feature Selection used for Wind Speed Forecasting with Data Driven Approaches,” J. Eng. Sci. Technol. Rev., vol. 8, no. 5, pp. 124-127, Oct. 2015, doi: 10.25103/jestr.085.17.
[9] A. Jović, K. Brkić, and N. Bogunović, “A review of feature selection methods with applications,” in 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), May 2015, pp. 1200-1205, doi: 10.1109/MIPRO.2015.7160458.
[10] Y. Saeys, I. Inza, and P. Larranaga, “A review of feature selection techniques in bioinformatics,” Bioinformatics, vol. 23, no. 19, pp. 2507-2517, Oct. 2007, doi: 10.1093/bioinformatics/btm344.
[11] W. Liu and J. Wang, “Recursive elimination-election algorithms for wrapper feature selection,” Appl. Soft Comput., p. 107956, Oct. 2021, doi: 10.1016/j.asoc.2021.107956.
[12] J. Guenther and O. Sawodny, “Feature Selection for Thermal Comfort Modeling based on Constrained LASSO Regression,” IFAC-Pap., vol. 52, no. 15, pp. 400-405, 2019, doi: 10.1016/j.ifacol.2019.11.708.
[13] L. Breiman, “Bagging predictors,” Mach. Learn., vol. 24, no. 2, pp. 123-140, Aug. 1996, doi: 10.1007/BF00058655.
[14] Jerome Friedman Trevor Hastie Robert Tibshirani, The elements of statistical learning: Data Mining, Inference and Prediction, 2nd ed. Springer 2009. [Ebook] Available: https://link.springer.com/book/10.1007/978-0-387-84858-7
[15] L. Breiman and J. H. Friedman, Classification And Regression Trees, Taylor and Francis group, 2017 [Ebook]. Available: https://www.taylorfrancis.com/books/mono/10.1201/9781315139470/classification-regression-trees-leo-breiman-jerome-friedman-richard-olshen-charles-stone. [Accessed Oct. 10, 2021].
[16] W. Kirch, Ed., “Pearson’s Correlation Coefficient,” in Encyclopedia of Public Health, Dordrecht: Springer Netherlands, 2008, pp. 1090-1091, doi: 10.1007/978-1-4020-5614-7_2569.
[17] M. Aria, C. Cuccurullo, and A. Gnasso, “A comparison among interpretative proposals for Random Forests,” Mach. Learn. Appl., vol. 6, p. 100094, Dec. 2021, doi: 10.1016/j.mlwa.2021.100094.
[18] H. Kaneko, “Examining variable selection methods for the predictive performance of regression models and the proportion of selected variables and selected random variables,” Heliyon, vol. 7, no. 6, p. e07356, Jun. 2021, doi: 10.1016/j.heliyon.2021.e07356.
[19] Meteoblue, “Weather History Download Basel”, 2021 [Online]. Available: https://www.meteoblue.com/en/weather/archive/export/basel_switzerland_2661604?daterange=2021-10-06%20-%202021-10-13&domain=NEMSAUTO&min=2021-10-06&max=2021-10-13&utc_offset=2&timeResolution=hourly&temperatureunit=CELSIUS&velocityunit=KILOMETER_PER_HOUR&energyunit=watts&lengthunit=metric°ree_day_type=10%3B30&gddBase=10&gddLimit=30. [Accessed Dec. 27, 2021].
[20] Japan Meteorological Agency, “History weather data in Osaka,” 2021 [Online]. Available: https://www.data.jma.go.jp/obd/stats/etrn/index.php?prec_no=62&block_no=47772&year=2014&month=01&day=01&view=p1 [Accessed Dec. 27, 2021].
[21] L. Breiman, “Random Forest”, Mach. Learn., vol. 45, no. 1, pp. 5-32, 2001, doi: 10.1023/A:1010933404324.DOI: https://doi.org/10.34238/tnu-jst.5487
Refbacks
- There are currently no refbacks.