Short-term Prediction of Wind Power Considering Turbulence Intensity

被引：0
|
作者：
Huang R. [1 ]
Du W. [1 ]
Wang H. [1 ]
机构：
[1] School of Electrical and Electronic Engineering, North China Electric Power University, Changping District, Beijing
来源：
Dianwang Jishu/Power System Technology | 2019年 / 43卷 / 06期
关键词：
TCN; Time sequence modeling; Turbulence intensity; Wind power prediction;
D O I：
10.13335/j.1000-3673.pst.2019.0080
中图分类号：
学科分类号：
摘要：
Wind energy has the nature of uncertainty, uncontrollability and intermittency. In order to improve accuracy of wind power prediction, this paper proposes a prediction method based on temporal convolutional network (TCN) considering turbulence intensity. In this method, to better characterize wind speed fluctuation, turbulence intensity is added to meteorological data, and the latest TCN architecture is introduced to improve prediction accuracy. Comparison between the two cases of adding and not adding turbulence intensity is performed to verify validity of the model, and the effects of back propagation (BP) neural network and long short-term memory (LSTM) network prediction are compared. The prediction results with actual data show that the proposed method has the advantages of simple network structure, direct information extraction, adjustable memory length and high prediction accuracy. © 2019, Power System Technology Press. All right reserved.
引用
收藏
页码：1907 / 1913
页数：6
相关论文
共 25 条
  • [1] Qian Z., Pei Y., Cao L., Et al., Review of wind power forecasting method, High Voltage Engineering, 42, 4, pp. 1047-1060, (2016)
  • [2] Jung J., Broadwater R.P., Current status and future advances for wind speed and power forecasting, Renewable and Sustainable Energy Reviews, 31, pp. 762-777, (2014)
  • [3] Chen H., Gao S., Wang Y., Et al., Wind power forecasting method based on generalized autoregressive conditional heteroskedasticity with skewness and kurtosis model, Proceedings of CSEE, 37, 12, pp. 3456-3461, (2017)
  • [4] Zhou W., Zhong J., Sun H., Et al., An interval rolling estimation method for daily wind power forecast errors based on hidden Markov model, Automation of Electric Power Systems, 42, 21, pp. 90-95, (2018)
  • [5] Peng L., Lili Y., Short-term wind speed forecasting based on non-stationary time series analysis and ARCH model, Proceedings of the 2011 International Conference on Multimedia Technology (ICMT), pp. 2549-2553, (2011)
  • [6] Ye R., Guo Z., Liu R., Et al., Wind speed and wind power forecasting method based on wavelet packet decomposition and improved Elman neural network, Transactions of China Electrotechnical Society, 32, 21, pp. 103-111, (2017)
  • [7] Meng A., Lu H., Hu H., Et al., Hybrid wavelet PACHET-CSO-ENN approach for short-term wind power forecasting, ACTA Energiae Solaris Sinica, 36, 7, pp. 1645-1651, (2015)
  • [8] Fan G., Wang W., Liu C., Artificial neural network based wind power short term prediction system, Power System Technology, 32, 22, pp. 72-76, (2008)
  • [9] Zeng M., Li S., Wang L., Et al., Wind power prediction model based on the combined optimization algorithm of ARMA model and BP neural networks, East China Electric Power, 41, 2, pp. 347-352, (2013)
  • [10] Zhou S., Mao M., Su J., Prediction of wind power based on principal component analysis and artificial neural network, Power System Technology, 35, 9, pp. 128-132, (2011)
123