基于SSA-VMD-LIESN的短期风电功率预测方法研究

杨宁宁; 王怡昕; 吴朝俊; 马芝瑞

doi:10.19912/j.0254-0096.tynxb.2024-0027

PDF(2464 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (5) : 440-447. DOI: 10.19912/j.0254-0096.tynxb.2024-0027

基于SSA-VMD-LIESN的短期风电功率预测方法研究

杨宁宁¹, 王怡昕¹, 吴朝俊^2,3, 马芝瑞¹

作者信息 +

RESEARCH ON SHORT-TERM WIND POWER PREDICTION METHOD BASED ON SSA-VMD-LIESN

Yang Ningning¹, Wang Yixin¹, Wu Chaojun^2,3, Ma Zhirui¹

Author information +

文章历史 +

摘要

短期风电功率预测精度提升可增强电力系统调节能力与消纳水平,并为风电优化决策提供数据支撑。为了提高短期风电功率的预测精度,提出一种基于SSA-VMD-LIESN的预测模型。首先通过麻雀搜寻算法（SSA）求解最优的变分模态分解（VMD）参数,将复杂的风电功率历史数据分解为不同频率的模态分量。随后通过样本熵计算反映其复杂程度,并将具有相似特征的分量融合重构。最后结合具有良好非线性预测能力的泄漏积分型回声状态网络（LIESN）,构成SSA-VMD-LIESN预测模型,并将预测结果与传统LIESN、长短期记忆网络（LSTM）以及BP神经网络进行对比分析。研究结果表明,该模型训练快速,具有较好的短期风电功率预测能力。

Abstract

Accurate short-term wind power prediction is conducive to improving the power system regulation ability, enhancing the wind power consumption level, and providing a basis for reliable wind power optimization decisions. In order to improve the accuracy of short-term wind power prediction, the paper proposes a prediction model based on SSA-VMD-LIESN. Firstly, the optimal variational modal decomposition （VMD） parameters are solved by the sparrow search algorithm （SSA） to decompose the complex wind power historical data into modal components of different frequencies. Subsequently, the complexity is reflected by sample entropy calculation, and the components with similar characteristics are fused and reconstructed. Finally, the SSA-VMD-LIESN prediction model is composed by combining the Leaky-Integrator Echo State Network （LIESN） with good nonlinear prediction ability, and the prediction results are compared and analyzed with the traditional LIESN, the long short-term memory network （LSTM）, and the BP neural network. The results show that the model trains quickly and has good short-term wind power prediction capability.

导出引用

杨宁宁, 王怡昕, 吴朝俊, 马芝瑞. 基于SSA-VMD-LIESN的短期风电功率预测方法研究[J]. 太阳能学报. 2025, 46(5): 440-447 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0027

Yang Ningning, Wang Yixin, Wu Chaojun, Ma Zhirui. RESEARCH ON SHORT-TERM WIND POWER PREDICTION METHOD BASED ON SSA-VMD-LIESN[J]. Acta Energiae Solaris Sinica. 2025, 46(5): 440-447 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0027

中图分类号： TM614

参考文献

[1] 闵富红, 马汉媛, 王耀达. 含功率扰动电力系统混沌振荡的动态滑模控制[J]. 通信学报, 2019, 40(1): 119-129.
MIN F H, MA H Y, WANG Y D.Surface sliding mode controller for chaotic oscillation in power system with power disturbance[J]. Journal on communications, 2019, 40(1): 119-129.
[2] SUN W, WANG Y W.Short-term wind speed forecasting based on fast ensemble empirical mode decomposition, phase space reconstruction, sample entropy and improved back-propagation neural network[J]. Energy conversion and management, 2018, 157: 1-12.
[3] 王福忠, 王帅峰, 张丽. 基于VMD-LSTM与误差补偿的光伏发电超短期功率预测[J]. 太阳能学报, 2022, 43(8): 96-103.
WANG F Z, WANG S F, ZHANG L.Ultra short term power prediction of photovoltaic power generation based on VMD-LSTM and error compensation[J]. Acta energiae solaris sinica, 2022, 43(8): 96-103.
[4] 张群, 唐振浩, 王恭, 等. 基于长短时记忆网络的超短期风功率预测模型[J]. 太阳能学报, 2021, 42(10): 275-281.
ZHANG Q, TANG Z H, WANG G, et al.Ultra-short-term wind power prediction model based on long and short term memory network[J]. Acta energiae solaris sinica, 2021, 42(10): 275-281.
[5] 刘芳, 汪震, 刘睿迪, 等. 基于组合损失函数的BP神经网络风力发电短期预测方法[J]. 浙江大学学报(工学版), 2021, 55(3): 594-600.
LIU F, WANG Z, LIU R D, et al.Short-term forecasting method of wind power generation based on BP neural network with combined loss function[J]. Journal of Zhejiang University (engineering science), 2021, 55(3): 594-600.
[6] 张扬科, 李刚, 李秀峰. 基于典型代表电站和改进SVM的区域光伏功率短期预测方法[J]. 电力自动化设备, 2021, 41(11): 205-210.
ZHANG Y K, LI G, LI X F.Short-term forecasting method for regional photovoltaic power based on typical representative power stations and improved SVM[J]. Electric power automation equipment, 2021, 41(11): 205-210.
[7] 李卓, 叶林, 戴斌华, 等. 基于IDSCNN-AM-LSTM组合神经网络超短期风电功率预测方法[J]. 高电压技术, 2022, 48(6): 2117-2127.
LI Z, YE L, DAI B H, et al.Ultra-short-term wind power prediction method based on IDSCNN-AM-LSTM combination neural network[J]. High voltage engineering, 2022, 48(6): 2117-2127.
[8] 武新章, 王泽宇, 代伟, 等. 基于异质聚类与Stacking的双集成光伏发电功率预测[J]. 电网技术, 2023, 47(1): 275-284.
WU X Z, WANG Z Y, DAI W, et al.Bi-ensembled photovoltaic(PV) power prediction based on heterogeneous clustering and stacking[J]. Power system technology, 2023, 47(1): 275-284.
[9] JAEGER H.The “echo state” approach to analysing and training recurrent neural networks-with an erratum note[J]. Bonn, germany: german national research center for information technology GMD technical report, 2001, 148(34): 13.
[10] JAEGER H, LUKOŠEVIČIUS M, POPOVICI D, et al. Optimization and applications of echo state networks with leaky- integrator neurons[J]. Neural networks, 2007, 20(3): 335-352.
[11] 那晓栋, 王嘉宁, 刘墨燃, 等. 基于层次化可塑性回声状态网络的混沌时间序列预测[J]. 控制与决策, 2023, 38(1): 133-142.
NA X D, WANG J N, LIU M R, et al.Hierarchical plasticity echo state network for chaotic time series prediction[J]. Control and decision, 2023, 38(1): 133-142.
[12] 许美玲, 王依雯. 基于改进差分进化和回声状态网络的时间序列预测研究[J]. 自动化学报, 2021, 47(7): 1589-1597.
XU M L, WANG Y W.Time series prediction based on improved differential evolution and echo state network[J]. Acta automatica sinica, 2021, 47(7): 1589-1597.
[13] 徐正阳, 路志英, 刘洪. 基于泄漏积分型回声状态网络的在线学习光伏功率预测[J]. 电力系统及其自动化学报, 2018, 30(2): 1-7.
XU Z Y, LU Z Y, LIU H.Online-learning PV power forecasting based on leaky-integrator echo state network[J]. Proceedings of the CSU-EPSA, 2018, 30(2): 1-7.
[14] HAN L, ZHANG R C, WANG X S, et al.Multi-step wind power forecast based on VMD-LSTM[J]. IET renewable power generation, 2019, 13(10): 1690-1700.
[15] WU Y, ZHANG D N, LIU Z H, et al.Short-term PV power prediction based on VMD-SE-TCAN model[J]. Journal of computers, 2022, 33(2): 25-36.
[16] 莫宏毅, 徐振洋, 刘鑫, 等. 基于SSA-VMD的爆破振动信号趋势项去除方法[J]. 振动与冲击, 2023, 42(11): 304-312.
MO H Y, XU Z Y, LIU X, et al.Trend removal method of blasting vibration signal based on SSA-VMD[J]. Journal of vibration and shock, 2023, 42(11): 304-312.
[17] DRAGOMIRETSKIY K, ZOSSO D.Variational mode decomposition[J]. IEEE transactions on signal processing, 2014, 62(3): 531-544.
[18] 肖烈禧, 张玉, 周辉, 等. 基于IAOA-VMD-LSTM的超短期风电功率预测[J]. 太阳能学报, 2023, 44(11): 239-246.
XIAO L X, ZHANG Y, ZHOU H, et al.Ultra short term wind power prediction based on IAOA-VMD-LSTM[J]. Acta energiae solaris sinica, 2023, 44(11): 239-246.
[19] XUE J K, SHEN B.A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems science & control engineering, 2020, 8(1): 22-34.
[20] 张家安, 刘东, 刘辉, 等. 基于风速波动特征提取的超短期风速预测[J]. 太阳能学报, 2022, 43(9): 308-313.
ZHANG J A, LIU D, LIU H, et al.Ultra short term wind speed prediction based on wind speed fluctuation feature extraction[J]. Acta energiae solaris sinica, 2022, 43(9): 308-313.
[21] 范思远, 姚显双, 曹生现, 等. 基于延迟回声状态网的光伏电池板温度预测方法[J]. 自动化学报, 2020, 46(12): 2701-2710.
FAN S Y, YAO X S, CAO S X, et al.Temperature prediction of photovoltaic panels based on delayed echo state network[J]. Acta automatica sinica, 2020, 46(12): 2701-2710.
[22] 岳文琦. 基于改进的DeepESN软测量建模方法及应用[J]. 测控技术, 2021, 40(10): 63-68.
YUE W Q.Dynamic soft sensor modeling and its application based on improved DeepESN[J]. Measurement & control technology, 2021, 40(10): 63-68.
[23] 伦淑娴, 林健, 姚显双. 基于小世界回声状态网的时间序列预测[J]. 自动化学报, 2015, 41(9): 1669-1679.
LUN S X, LIN J, YAO X S.Time series prediction with an improved echo state network using small world network[J]. Acta automatica sinica, 2015, 41(9): 1669-1679.