Abstract
The prediction of wind power is crucial to ensuring the reliability and economic efficiency of wind power generation systems, as well as to maintaining balance and efficient operation of power systems. However, due to the non-stationary and chaotic nature of wind speeds, predicting wind power is a challenging task. Recently, various solutions have been proposed, e.g., SARIMA-based models and BP neural network-based models, which have successfully predicted periodicity and short-term wind power generation, but their performances are limited. In this paper, we select the top-eight most significant attributes from a public wind power dataset, i.e., wind direction, hub temperature, bearing shaft temperature, gearbox bearing temperature, gearbox oil temperature, rotor speed, reactive power and active power. We then train eight supervised machine learning models, i.e., Linear Regression, Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), Ridge and Lasso Regression, Decision Tree, and Gradient Boosting, to predict the wind power output of the next 70 days. Experimental results showed that the XGBoost model outperforms others (R-squared score = 0.96, accuracy = 95.39%, MAE = 39.43, and cross-validation score = 0.98). Compared to the state-of-the-art performance achieved by the Random Forest model, XGBoost has improved the prediction accuracy by 4.69% points.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yude, B.: Scheduling optimization and emission analysis of clean energy under the background of dual carbon. Electric. Measur. Instrum., 1–10 (2022)
Bianco, V., Manca, O., Nardini, S.: Electricity consumption forecasting in Italy using linear regression models. Energy 34(9), 1413–1421 (2009)
Shi, H., Yang, J., Ding, M., Wang, J.: A short-term wind power prediction method based on wavelet decomposition and BP neural network. Dianli Xitong Zidonghua/Autom. Electr. Power Syst. 35(16), 44–48 (2011)
Ma, Q., Yang, Y.-H., Liu, W.-Y., Qi, Z., Guo, J.-Z.: Power system transient stability assessment with combined SVM method mixing multiple input features. Zhongguo Dianji Gongcheng Xuebao/Proc. Chin. Soc. Electric. Eng. 25(6), 17–23 (2005)
Li, Y.-c., Fang, T.-j., Yu, E.-k.: Study of support vector machines for short-term load forecasting. Proc. CSEE, 55–59 (2003)
Yangguang, W., Min, X., Xiaoliang, D., Cheng, B.: Random forest model of wind power forecasting based on wavelet transform. Electr. Eng. 542(8), 48–52+52 (2021)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Binbin, Z., et al.: Photovoltaic power prediction in distribution network based on ARIMA model time series. Renew. Energy Resour. 37(6), 820–823 (2019)
Wei, W., et al.: Wind power forecast based on LSTM cyclic neural network. Renew. Energy Resour. 38(9), 1187–1191 (2020)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
García Hinde, Ó., Gómez Verdejo, V., Martínez-Ramón, M.: Forecast-informed power load profiling: a novel approach. Eng. Appl. Artif. Intell. 96, 103948 (2020)
Jing, Y., Li-juan, L., Zhen-xu, T.: Short-term traffic flow forecasting based on CNN-XGBoost. Comput. Eng. Des. 41(4), 1080–1086 (2020)
Sun, C., Lu, Q., Zhu, S., Zheng, W., Cao, Y., Wang, J.: Ultra-short-term power load forecasting based on two-layer XGBoost algorithm considering the influence of multiple features. Gaodianya Jishu/High Voltage Eng. 47(8), 2885–2895 (2021)
Zhu, K., Geng, J., Wang, K.: A hybrid prediction model based on pattern sequence-based matching method and extreme gradient boosting for holiday load forecasting. Electr. Power Syst. Res. 190, 106841 (2021)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016)
Chen, Z., Guerrero, J.M., Blaabjerg, F.: A review of the state of the art of power electronics for wind turbines. IEEE Trans. Power Electron. 24(8), 1859–1875 (2009)
Zhao, Y., Ye, L., Zhu, Q.: Characteristics and processing method of abnormal data clusters caused by wind curtailments in wind farms. Dianli Xitong Zidonghua/Autom. Electr. Power Syst. 38(21), 39–46 (2014)
Deng, C.-L., et al.: Prediction of the efficacy of radiotherapy and chemotherapy for cervical squamous cell carcinoma based on random forests. Ruan Jian Xue Bao/J. Softw. 32(12), 3960–3976 (2021)
Xiaogang, W., Jie, Y., Chang, G., Yajie, T., Chouwei, N., Qingfeng, J.: Ultra-short-term power integration forecasting method for wind-solar-hydro based on improved GRU-CNN. Electr. Power, 1–9 (2023)
Xie, G.-C., Duan, L., Jiang, W.-P., Xiao, S., Xu, Y.-F.: Pedestrian volume prediction for campus public area based on multi-scale temporal dependency. Ruan Jian Xue Bao/J. Softw. 32(3), 831–844 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Liu, C., Li, J., Wang, H. (2024). Predicting Wind Turbine Power Output Based on XGBoost. In: Li, J., Zhang, B., Ying, Y. (eds) 6GN for Future Wireless Networks. 6GN 2023. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 553. Springer, Cham. https://doi.org/10.1007/978-3-031-53401-0_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-53401-0_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53400-3
Online ISBN: 978-3-031-53401-0
eBook Packages: Computer ScienceComputer Science (R0)