利用混合深度学习算法的时空风速预测

贵向泉; 孟攀龙; 孙林花; 秦三杰; 刘靖红

doi:10.19912/j.0254-0096.tynxb.2023-1954

PDF(2634 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (3) : 668-678. DOI: 10.19912/j.0254-0096.tynxb.2023-1954

利用混合深度学习算法的时空风速预测

贵向泉¹, 孟攀龙¹, 孙林花², 秦三杰³, 刘靖红¹

作者信息 +

SPATIO-TEMPORAL WIND SPEED FORECASTING BASED ON HYBRID DEEP LEARNING ALGORITHM

Gui Xiangquan¹, Meng Panlong¹, Sun Linhua², Qin Sanjie³, Liu Jinghong¹

Author information +

文章历史 +

摘要

风速预测的准确性始终不理想,为解决风速复杂的时空相关性和非线性问题,提出一种新颖的混合深度学习模型。首先,采用二次分解法将输入序列分解为具有不同频率振动模式的模态分量（IMF）;使用图卷积神经网络（GCN）和双向长短期记忆网络（BiLSTM）来预测高频分量;使用自适应图时空Transformer网络（ASTTN）来预测低频分量,以充分考虑输入序列的时空相关性。最后将高频分量和低频分量合并叠加,得到最终的预测结果。将该模型应用于甘肃省某风电场进行风速预测,实验结果表明,所提出混合深度学习模型能有效提高风速预测的准确性。

Abstract

The accuracy of wind speed forecasting is crucial for the efficient operation and dispatch of power grid systems. To tackle the complex spatio-temporal correlations and nonlinearity of wind speed, a novel hybrid deep learning model is proposed. Firstly, a secondary decomposition method is employed to decompose the input sequence into intrinsic mode functions （IMFs） with different frequency vibration modes. Graph convolutional network （GCN） and a bidirectional long short-term memory （BiLSTM） network are used to predict the high-frequency components. An adaptive graph spatio-temporal transformer network （ASTTN） is employed to predict the low-frequency components, fully considering the spatio-temporal correlation of the input sequence. Finally, the high-frequency and low-frequency components are combined and superimposed to obtain the ultimate prediction results. The model is applied to wind speed forecasting in a wind farm in Gansu Province, and experimental results demonstrate that the proposed hybrid deep learning model effectively enhances the accuracy of wind speed forecasting.

导出引用

贵向泉, 孟攀龙, 孙林花, 秦三杰, 刘靖红. 利用混合深度学习算法的时空风速预测[J]. 太阳能学报. 2025, 46(3): 668-678 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1954

Gui Xiangquan, Meng Panlong, Sun Linhua, Qin Sanjie, Liu Jinghong. SPATIO-TEMPORAL WIND SPEED FORECASTING BASED ON HYBRID DEEP LEARNING ALGORITHM[J]. Acta Energiae Solaris Sinica. 2025, 46(3): 668-678 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1954

中图分类号： TM614

参考文献

[1] ZHANG S, CHEN Y, XIAO J, et al.Hybrid wind speed forecasting model based on multivariate data secondary decomposition approach and deep learning algorithm with attention mechanism[J]. Renewable energy, 2021, 174: 688-704.
[2] XU X, NIU D, XIAO B, et al.Policy analysis for grid parity of wind power generation in China[J]. Energy policy, 2020, 138: 111225.
[3] 王俊, 李霞, 周昔东, 等. 基于VMD和LSTM的超短期风速预测[J]. 电力系统保护与控制, 2020, 48(11): 45-52.
WANG J, LI X, ZHOU X D, et al.Ultra-short-term wind speed prediction based on VMD-LSTM[J]. Power system protection and control, 2020, 48(11): 45-52.
[4] WANG C, LIU Z, WEI H, et al.Hybrid deep learning model for short-term wind speed forecasting based on time series decomposition and gated recurrent unit[J]. Complex system modeling and simulation, 2021, 1(4): 308-321.
[5] 向玲, 刘佳宁, 苏浩, 等. 基于CEEMDAN二次分解和LSTM的风速多步预测研究[J]. 太阳能学报, 2022, 43(8): 334-339.
XIANG L, LIU J N, SU H, et al.Research on multi-step wind speed forecast based on CEEMDAN secondary decomposition and LSTM[J]. Acta energiae solaris sinica, 2022, 43(8): 334-339.
[6] LI Z L, YU J, ZHANG X L, et al.A Multi-Hierarchical attention-based prediction method on time series with spatio-temporal context among variables[J]. Physica A: statistical mechanics and its applications, 2022, 602: 127664.
[7] NGUYEN T H T, PHAN Q B. Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization[J]. Energy reports, 2022, 8: 53-60.
[8] HAN Y, MI L, 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.
[9] 臧海祥, 张越, 程礼临, 等. 基于ICEEMDAN-LSTM和残差注意力的短期太阳辐照度预测[J]. 太阳能学报, 2023, 44(12): 175-181.
ZANG H X, ZHANG Y, CHENG L L, et al.Short term solar radiation forecasting based on ICEEMDAN-LSTM and residual attention[J]. Acta energiae solaris sinica, 2023, 44(12): 175-181.
[10] ZHOU F, HUANG Z, ZHANG C.Carbon price forecasting based on CEEMDAN and LSTM[J]. Applied energy, 2022, 311: 118601.
[11] 王维高, 魏云冰, 滕旭东. 基于VMD-SSA-LSSVM的短期风电预测[J]. 太阳能学报, 2023, 44(3): 204-211.
WANG W G, WEI Y B, TENG X D.Short-term wind power forecasting based on VMD-SSA-LSSVM[J]. Acta energiae solaris sinica, 2023, 44(3): 204-211.
[12] 蒋玉英, 陈心雨, 李广明, 等. 图神经网络及其在图像处理领域的研究进展[J]. 计算机工程与应用, 2023, 59(7): 15-30.
JIANG Y Y, CHEN X Y, LI G M, et al.Graph neural network and its research progress in field of image processing[J]. Computer engineering and applications, 2023, 59(7): 15-30.
[13] 万升, 杨健, 宫辰. 基于图神经网络的高光谱图像分类研究进展[J]. 电子学报, 2023, 51(6): 1687-1709.
WAN S, YANG J, GONG C.Advances of hyperspectral image classification based on graph neural networks[J]. Acta electronica sinica, 2023, 51(6): 1687-1709.
[14] 陈晋音, 熊海洋, 马浩男, 等. 基于对比学习的图神经网络后门攻击防御方法[J]. 通信学报, 2023, 44(4): 154-166.
CHEN J Y, XIONG H Y, MA H N, et al.CLB-Defense: based on contrastive learning defense for graph neural network against backdoor attack[J]. Journal on communications, 2023, 44(4): 154-166.
[15] KIM T, VECCHIETTI L F, CHOI K, et al.Machine learning for advanced wireless sensor networks: a review[J]. IEEE sensors journal, 2021, 21(11): 12379-12397.
[16] 张程, 林谷青, 匡宇. 基于MEEMD-QUATRE-BILSTM的短期光伏出力区间预测[J]. 太阳能学报, 2023, 44(11): 40-54.
ZHANG C, LIN G Q, KUANG Y.Short-term PV output interval prediction based on MEEMD-QUATRE-BILSTM[J]. Acta energiae solaris sinica, 2023, 44(11): 40-54.
[17] JOSEPH L P, DEO R C, PRASAD R, et al.Near real-time wind speed forecast model with bidirectional LSTM networks[J]. Renewable energy, 2023, 204: 39-58.
[18] FENG A, TASSIULAS L.Adaptive graph spatial-temporal transformer network for traffic forecasting[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management. Atlanta, USA, 2022: 3933-3937.
[19] WU Z H, PAN S R, LONG G D, et al.Graph WaveNet for deep spatial-temporal graph modeling[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence. Macao, China, 2019: 1907-1913.