Wind Speed Prediction of Wind Turbine Based on the Internet of Machines and Spatial Correlation Weight

被引：0
|
作者：
Shen X. [1 ]
Zhou C. [1 ,2 ]
Fu X. [1 ]
机构：
[1] College of Electronic and Information Engineering, Tongji University, Shanghai
[2] Jiading Power Supply Company State Grid Shanghai Electric Power Company, Shanghai
来源：
Diangong Jishu Xuebao/Transactions of China Electrotechnical Society | 2021年 / 36卷 / 09期
关键词：
Internet of machines; Spatial correlation; Wind speed real prediction; Wind turbines;
D O I：
10.19595/j.cnki.1000-6753.tces.200226
中图分类号：
学科分类号：
摘要：
Real-time wind speed prediction can effectively improve the control performance and power generation of wind turbine, and realize the efficient use of wind energy. On the basis of analyzing the temporal-spatial propagation characteristics of wind speed in wind farms, a real-time prediction framework based on Internet of machines and the weight of spatial correlation is proposed in this paper. The prediction model and process is established, a Kalman filter algorithm is developed and comparison study is carried out with the persistent model and traditional spatial correlation prediction method. Case study result shows that on small time scale, the proposed method has better prediction accuracy than the persistent model, and the fault tolerance and robustness are superior to the traditional spatial correlation method. The feasibility and effectiveness of the proposed method is verified, and the prediction framework is capable of multi-time scale prediction such as minute level and ultra-short term wind speed forecasting. The research results can provide new insights for accurate real-time wind speed perception of wind turbines. © 2021, Electrical Technology Press Co. Ltd. All right reserved.
引用
收藏
页码：1782 / 1790and1817
相关论文
共 24 条
  • [1] Bottasso C L, Pizzinelli P, Riboldi C E D, Et al., LiDAR-enabled model predictive control of wind turbines with real-time capabilities, Renewable Energy, 71, 71, pp. 442-452, (2014)
  • [2] Wang Na, Johnson K E, Wright A D., FX-RLS-based feed forward control for LIDAR-enabled wind turbine load mitigation, IEEE Transactions on Control Systems Technology, 20, 5, pp. 1212-1222, (2012)
  • [3] Wang Na, Johnson K E, Wright A D., Comparison of strategies for enhancing energy capture and reducing loads using LIDAR and feed forward control, IEEE Transactions on Control Systems Technology, 21, 4, pp. 1129-1142, (2013)
  • [4] Mohammad A C, Sami F M, Trzynadlowski A M., Wind speed and wind direction forecasting using echo state network with nonlinear functions, Renweable Energy, 131, pp. 879-889, (2019)
  • [5] Guo Yifei, Gao Houlei, Wu Qiuwei, A combined reliability model of VSC-HVDC connected offshore wind farms considering wind speed correlation, IEEE Transactions on Sustainable Energy, 8, 4, pp. 1637-1646, (2017)
  • [6] Sun Guoqiang, Wei Zhinong, Zhai Weixing, Short term wind speed forecasting based on RVM and ARMA error correcting, Transactions of China Electrotechnical Society, 27, 8, pp. 187-193, (2012)
  • [7] Erdem E, Shi J., ARMA based approaches for forecasting the tuple of wind speed and direction, Applied Energy, 88, 4, pp. 1405-1414, (2011)
  • [8] Ak R, Fink O, Zio E., Two machine learning approaches for short-term wind speed time-series prediction, IEEE Transactions on Neural Networks and Learning Systems, 27, 8, pp. 1734-1747, (2016)
  • [9] Liu Xingjie, Cen Tianyun, Zheng Wenshu, Et al., Neural network wind speed prediction based on fuzzy rough set and improved clustering, Proceedings of the CSEE, 34, 19, pp. 3162-3169, (2014)
  • [10] Ak R, Vitelli V, Zio E., An interval-valued neural network approach for uncertainty quantification in short-term wind speed prediction, IEEE Transactions on Neural Networks and Learning Systems, 26, 11, pp. 2787-2800, (2015)
123