基于WRF模拟和注意力机制的短期风速预测

罗颖; 刘雨辰; 米立华; 韩艳; 王力东; 姜言

doi:10.19912/j.0254-0096.tynxb.2022-0686

PDF(2462 KB)

太阳能学报 ›› 2023, Vol. 44 ›› Issue (9) : 302-310. DOI: 10.19912/j.0254-0096.tynxb.2022-0686

基于WRF模拟和注意力机制的短期风速预测

罗颖¹, 刘雨辰¹, 米立华¹, 韩艳¹, 王力东¹, 姜言²

作者信息 +

SHORT-TERM WIND SPEED FORECAST BASED ON WRF SIMULATION AND ATTENTION MECHANISM

Luo Ying¹, Liu Yuchen¹, Mi Lihua¹, Han Yan¹, Wang Lidong¹, Jiang Yan²

Author information +

文章历史 +

摘要

提出一种结合中尺度数值天气预报（WRF）模式和注意力机制（AM）的短期风速预测模型。首先,利用WRF模式模拟多维数据,包括风速、风向、温度和湿度,作为后续算法的输入变量。其次,利用变分模态分解将WRF风速误差及其他相关气象因素分解成不同频率的子模态分量,降低原始数据的复杂性和非平稳特征。随后,使用自适应网格搜索算法对添加注意力机制的双向门限循环单元进行模型结构参数优化。最后,基于所提模型预测误差修正WRF风速。通过算例分析,所提模型在单步和多步预测中精度均优于对比模型,证明了模型的优越性。

Abstract

A short-term wind speed forecast model combining the weather research and forecast （WRF） and attention mechanism is proposed. Firstly, the WRF model is applied to simulate multiple data, including wind speed, wind direction, temperature, and humidity, which are regarded as input variables of the subsequent algorithm. Secondly, the errors of the wind speeds resulting from WRF and the other related variables are decomposed into sub-modal components with various frequencies by the variational mode decomposition （VMD） algorithm to reduce the complexity and non-stationary feature of the raw data. Thirdly, as for Bi-directional Gate Recurrent Unit （BIGRU） with attention mechanism （AM）, the adaptive grid search algorithm is adopted for the parameter optimization of the model structure. Finally, based on the proposed model, the errors are forecasted to correct the simulated wind speed of WRF. Through the analysis of examples, the accuracy of the proposed model is better than that of the comparative models in single-step and multi-step forecast, which proves the superiority of the model.

导出引用

罗颖, 刘雨辰, 米立华, 韩艳, 王力东, 姜言. 基于WRF模拟和注意力机制的短期风速预测[J]. 太阳能学报. 2023, 44(9): 302-310 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0686

Luo Ying, Liu Yuchen, Mi Lihua, Han Yan, Wang Lidong, Jiang Yan. SHORT-TERM WIND SPEED FORECAST BASED ON WRF SIMULATION AND ATTENTION MECHANISM[J]. Acta Energiae Solaris Sinica. 2023, 44(9): 302-310 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0686

中图分类号： TM614

参考文献

[1] HAN Y, MI L H, SHEN L, et al.A short-term wind speed prediction method utilizing novel hybrid deep learning algorithms to correct numerical weather forecasting[J]. Applied energy, 2022, 312: 118777.
[2] 向玲, 李京蓄, 王朋鹤, 等. 基于VMD-FIG和参数优化GRU的风速多步区间预测[J]. 太阳能学报, 2021, 42(10): 237-242.
XIANG L, LI J X, WANG P H, et al.Wind speed multistep interval forecasting based on VMD-FIG and parameter-optimized GRU[J]. Acta energiae solaris sinica, 2021, 42(10): 237-242.
[3] SUN G P, JIANG C W, CHENG P, et al.Short-term wind power forecasts by a synthetical similar time series data mining method[J]. Renewable energy, 2018, 115: 575-584.
[4] 刘擘龙, 张宏立, 王聪, 等. 基于序列到序列和注意力机制的超短期风速预测[J]. 太阳能学报, 2021, 42(9): 286-294.
LIU B L, ZHANG H L, WANG C, et al.Ultra-short-term wind speed prediction based on sequence-to-sequence and attention mechanism[J]. Acta energiae solaris sinica, 2021, 42(9): 286-294.
[5] TASCIKARAOGLU A, UZUNOGLU M.A review of combined approaches for prediction of short-term wind speed and power[J]. Renewable and sustainable energy reviews, 2014, 34: 243-254.
[6] CHEN G G, TANG B R, ZENG X J, et al.Short-term wind speed forecasting based on long short-term memory and improved BP neural network[J]. International journal of electrical power & energy systems, 2022, 134: 107365.
[7] DE MATTOS NETD P S G, DE OLIVEIRA J F L, DE O SANTOS D S J R, et al. An adaptive hybrid system using deep learning for wind speed forecasting[J]. Information sciences, 2021, 581: 495-514.
[8] DAYAL K K, BELLON G, CATER J E, et al.High-resolution mesoscale wind-resource assessment of Fiji using the Weather Research and Forecasting (WRF) model[J]. Energy, 2021, 232(8): 121047.
[9] SALCEDO-SANZ S, ORTIC-GARCIA E G, PDRTILLA-FIGUERAS A, et al. Hybridizing the fifth generation mesoscale model with artificial neural networks for short-term wind speed prediction[J]. Renewable energy, 2009, 34(6): 1451-1457.
[10] YANG D Z, WANG W T, HONG T.A historical weather forecast dataset from the European Centre for Medium-Range Weather Forecasts (ECMWF) for energy forecasting[J]. Solar energy, 2022, 232: 263-274.
[11] 姜言, 黄国庆, 彭新艳, 等. 基于GARCH的短时风速预测方法[J]. 西南交通大学学报, 2016, 51(4): 663-669, 742.
JIANG Y, HUANG G Q, PENG X Y, et al.Method of short-term wind speed forecasting based on generalized autoregressive conditional heteroscedasticity model[J]. Journal of Southwest Jiaotong University, 2016, 51(4): 663-669, 742.
[12] 吴志周, 范宇杰, 马万经. 基于灰色神经网络的点速度预测模型[J]. 西南交通大学学报, 2012, 47(2): 285-290.
WU Z Z, FAN Y J, MA W J.Spot speed prediction model based on grey neural network[J]. Journal of Southwest Jiaotong University, 2012, 47(2): 285-290.
[13] LI H M, WANG J Z, LI R R, et al.Novel analysis-forecast system based on multi-objective optimization for air quality index[J]. Journal of cleaner production, 2019, 208: 1365-1383.
[14] LIN L H, LI M, MA L, et al.Hybrid RNN-LSTM deep learning model applied to a fuzzy based wind turbine data uncertainty quantization method[J]. Ad hoc networks, 2021, 123: 102658.
[15] 谭海旺, 杨启亮, 邢建春, 等. 基于XGBoost-LSTM组合模型的光伏发电功率预测[J]. 太阳能学报, 2022, 43(8): 75-81.
TAN H W, YANG Q L, XING J C, et al.Photovoltaic power prediction based on combined XGBoost-LSTM model[J]. Acta energiae solaris sinica, 2022, 43(8): 75-81.
[16] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[17] HUANG G Y, LI X Y, ZHANG B, et al.PM_2.5 concentration forecasting at surface monitoring sites using GRU neural network based on empirical mode decomposition[J]. Science of the total environment, 2021, 768(3): 144516.
[18] PENG X S, WANG H Y, LANG J X, et al.EALSTM-QR:interval wind-power prediction model based on numerical weather prediction and deep learning[J]. Energy, 2021, 220: 119692.
[19] SEMERO Y K, ZHANG J H, ZHENG D H.PV power forecasting using an integrated GA-PSO-ANFIS approach and Gaussian process regression based feature selection strategy[J]. CSEE journal of power and energy systems, 2018, 4(2): 210-218.
[20] YANG R, LIU H, NIKITAS N, et al.Short-term wind speed forecasting using deep reinforcement learning with improved multiple error correction approach[J]. Energy, 2022, 239(part B): 122128.
[21] DRAGOMIRETSKIY K, ZOSSO D.Variational mode decomposition[J]. IEEE transactions on signal processing, 2014, 62(3): 531-544.
[22] CIFUENTES F, GONZÁLEZ C M, ARISTIZÁBAL B H. Insights to WRF-Chem sensitivity in a zone of complex terrain in the tropical Andes: effect of boundary conditions, chemical mechanisms,nesting,and domain configuration[J]. Atmospheric pollution research, 2021, 12(6): 101093.
[23] LIU X G, CAO J L, XIN D B.Wind field numerical simulation in forested regions of complex terrain: a mesoscale study using WRF[J]. Journal of wind engineering and industrial aerodynamics, 2022, 222: 104915.
[24] JIMÉNEZ-ESTEVE B, UDINA M, SOLER M R, et al. Land use and topography influence in a complex terrain area:a high resolution mesoscale modelling study over the Eastern Pyrenees using the WRF model[J]. Atmospheric research, 2018, 202: 49-62.
[25] SKAMAROCK W C, KLEMP J B, DUDHIA J, et al.A description of the advanced research WRF model version 4(NCAR Technical Notes NCAR/TN-556+STR)[M]. USA, University Corporation for Atmospheric Research, 2019.
[26] BELJAARS A C M. The parametrization of surface fluxes in large-scale models under free convection[J]. Quarterly journal of the Royal Meteorological Society, 1995, 121(522): 255-270.
[27] 郑小霞, 周国旺, 任浩翰, 等. 基于变分模态分解和排列熵的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(22): 22-28.
ZHENG X X, ZHOU G W, REN H H, et al.A rolling bearing fault diagnosis method based on variational mode decomposition and permutation entropy[J]. Journal of vibration and shock, 2017, 36(22): 22-28.
[28] MEI Z Y, ZHANG W, ZHANG L H, et al.Real-time multistep prediction of public parking spaces based on Fourier transform-least squares support vector regression[J]. Journal of intelligent transportation systems, 2020, 24(1): 68-80.
[29] WANG J Z, SONG Y L, LIU F, et al.Analysis and application of forecasting models in wind power integration: a review of multi-step-ahead wind speed forecasting models[J]. Renewable and sustainable energy reviews, 2016, 60: 960-981.