Recurrent neural network prediction of wind speed time series based on seasonal exponential adjustment

被引：0
|
作者：
Jiang M. [1 ]
Xu L. [1 ]
Zhang K. [1 ]
Ma Y. [1 ]
机构：
[1] College of Mathematics and Physics, Shanghai University of Electric Power, Shanghai
来源：
Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2022年 / 43卷 / 02期
关键词：
Combination forecasting; Gated recurrent unit network; Long short-term memory network; Neural network; Time series analysis; Wind speed prediction;
D O I：
10.19912/j.0254-0096.tynxb.2020-0389
中图分类号：
学科分类号：
摘要：
A novel method of wind speed prediction based on neural network with seasonal exponential adjustment is proposed. Based on the nonlinear relationships among historical wind speeds and the strong nonlinear fitting ability of neural network, the neural network combined with seasonal exponential adjustment is adopted to predict the wind speed time series. First, time series graph and augmented Dickey-Fuller method are used to test the stability of time series. The results show that time series is unstable. The instability indicates that the time series contains seasonal, trending, cyclic and irregular components. In this paper, this time series decomposition model is used to adjust the seasonal index of time series. Finally, LSTM and GRU neural networks are used to predict wind speed data, and the ideal prediction results are obtained. Compared with the results of raw wind speed data and the seasonal exponential adjustment with the addition model, the results of two neural network methods based on the seasonal exponential adjustment with the multiplication model achieve much higher accuracy of wind speed prediction. © 2022, Solar Energy Periodical Office Co., Ltd. All right reserved.
引用
收藏
页码：444 / 450
页数：6
相关论文
共 19 条
  • [1] YANG M, YANG Q Q, SU X., Ultra-short term probabilistic intervals forecasting of wind power based on optimization model of forecasting error distribution, Acta energy solaris sinica, 41, 2, pp. 85-92, (2020)
  • [2] SOMAN S, ZAREIPOUR H, MALIK O P, Et al., A review of wind power and wind speed forecasting methods with different time horizons, 2010 North American Power Symposium, (2010)
  • [3] ZHANG F M, WANG C H, XIE G H, Et al., Projection of global wind and solar energy over land under climate change scenarios during 2020-2030, Journal of arid meteorology, 36, 5, pp. 725-732, (2018)
  • [4] KARNAUSKAS K B, LUNDQUIST J K, ZHANG L., Southward shift of the global wind energy resource under high carbon dioxide emissions, Nature geoscience, 11, 1, pp. 38-43, (2018)
  • [5] LUO S, DING Q W, LI C, Et al., Analysis of chaotic charateristics of wind speed time series and nonlinear short-term prediction, Energy engineering, 5, pp. 50-56, (2019)
  • [6] YUAN Q Y, LI C, YANG Y., Nonlinear characteristic analysis of wind speed time series, Journal of engineering for thermal energy and power, 33, 8, pp. 135-143, (2018)
  • [7] GUO Z H, WU J, LU H Y., A case study on a hybrid wind speed forecasting method using BP neural network, Knowledge-based systems, 24, 7, pp. 1048-1056, (2011)
  • [8] WU J, WANG J Z, LU H Y., Short term load forecasting technique based on the seasonal exponential adjustment method and the regression model, Energy conversion and management, 70, pp. 1-9, (2013)
  • [9] CEVIK H H, CUNKAS M, POLAT K, Et al., A new multistage short-term wind power forecast model using decomposition and artificial intelligence methods, Physica A: Statistical mechanics and its applications, 534, (2019)
  • [10] CHEN J, ZENG G Q, ZHOU W N., Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimization, Energy conversion and management, 165, pp. 681-695, (2018)
12