基于NWP信息的SSA优化EEMD-LSTM风电超短期功率预测

依沙克&#x000b7;司马义; 陈昊; 张正强; 徐帅; 刘莘轶; 于立军

doi:10.19912/j.0254-0096.tynxb.2024-0534

PDF(2218 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (8) : 176-183. DOI: 10.19912/j.0254-0096.tynxb.2024-0534

基于NWP信息的SSA优化EEMD-LSTM风电超短期功率预测

依沙克·司马义¹, 陈昊^1,2, 张正强¹, 徐帅², 刘莘轶³, 于立军²

作者信息 +

ULTRA-SHORT-TERM WIND POWER PREDICTION BASED ON NWP INFORMATION USING SSA OPTIMIZED EEMD-LSTM

Yishake·Simayi¹, Chen Hao^1,2, Zhang Zhengqiang¹, Xu Shuai², Liu Xinyi³, Yu Lijun²

Author information +

文章历史 +

摘要

该研究建立一种组合风电功率预测模型,结合集合经验模态分解（EEMD）、麻雀搜索算法（SSA）和长短期记忆神经网络（LSTM）算法。模型通过 EEMD 对风功率时间序列进行分解,克服了传统分解方法的模态混叠现象;利用涵盖风速、风向、气压与湿度等气象变量数值天气预报特征和测风塔信息与功率输出建立映射关系;通过 SSA 算法对基于 LSTM 神经网络构建的预测模型进行超参数优化,显著提升模型的预测精度。经验证,本模型在预测性能上优于其他组合模型,均方根误差提升达到5.81%及7.09%。

Abstract

A combined wind power prediction model incorporating ensemble empirical mode decomposition （EEMD）, sparrow search algorithm （SSA）, and long short-term memory （LSTM） neural networks is proposed. The model decomposes the wind power time series through EEMD, overcoming the mode mixing phenomenon of traditional decomposition methods; Establish a mapping relationship between numerical weather prediction features covering meteorological variables such as wind speed, wind direction, air pressure, and humidity, as well as wind measurement tower information and power output; By using SSA algorithm to perform hyperparameter optimization on the prediction model based on LSTM neural network, the prediction accuracy of the model is significantly improved. The validation results demonstrate that this model outperforms other combined models, achieving improvements in root mean square error （RMSE） of 5.81% to 7.09%.

导出引用

依沙克·司马义, 陈昊, 张正强, 徐帅, 刘莘轶, 于立军. 基于NWP信息的SSA优化EEMD-LSTM风电超短期功率预测[J]. 太阳能学报. 2025, 46(8): 176-183 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0534

Yishake·Simayi, Chen Hao, Zhang Zhengqiang, Xu Shuai, Liu Xinyi, Yu Lijun. ULTRA-SHORT-TERM WIND POWER PREDICTION BASED ON NWP INFORMATION USING SSA OPTIMIZED EEMD-LSTM[J]. Acta Energiae Solaris Sinica. 2025, 46(8): 176-183 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0534

中图分类号： TK89

参考文献

[1] 戴宝华, 王德亮, 曹勇, 等. 2022年中国能源行业回顾及2023年展望[J]. 当代石油石化, 2023, 31(1): 2-9.
DAI B H, WANG D L, CAO Y, et al.China’s energy industry: 2022 review and 2023 prospect[J]. Petroleum & petrochemical today, 2023, 31(1): 2-9.
[2] 唐坚, 唐庆宏, 姚禹歌, 等. 风电调频能力的潜力分析[J]. 动力工程学报, 2022, 42(11): 1138-1145.
TANG J, TANG Q H, YAO Y G, et al.Potential analysis of frequency regulation ability of wind power in the view of energy[J]. Journal of Chinese Society of Power Engineering, 2022, 42(11): 1138-1145.
[3] 姜贵敏, 陈志军, 李笑竹, 等. 基于EEMD-ACS-LSSVM的短期风电功率预测[J]. 太阳能学报, 2020, 41(5): 77-84.
JIANG G M, CHEN Z J, LI X Z, et al.Short-term prediction of wind power based on EEMD-ACS-LSSVM[J]. Acta energiae solaris sinica, 2020, 41(5): 77-84.
[4] 曾娜梅, 霍志红, 许昌, 等. 基于改进HHT的分钟级超短期风速预测[J]. 动力工程学报, 2021, 41(4): 309-315, 329.
ZENG N M, HUO Z H, XU C, et al.Minute-scale ultra-short-term wind speed prediction based on improved HHT[J]. Journal of Chinese Society of Power Engineering, 2021, 41(4): 309-315, 329.
[5] 杨宇晴, 张怡. 基于mRMR和VMD-AM-LSTM的短期风功率预测[J]. 控制工程, 2022, 29(1): 10-17.
YANG Y Q, ZHANG Y.Short-term wind power prediction based on mRMR and VMD-AM-LSTM[J]. Control engineering of China, 2022, 29(1): 10-17.
[6] 任东方, 马家庆, 何志琴, 等. 基于AVMD-CNN-GRU-Attention的超短期风功率预测研究[J]. 太阳能学报, 2024, 45(6): 436-443.
REN D F, MA J Q, HE Z Q, et al.Research on ultra-short-term wind power forecast based on AVMD-CNN-GRU-Attention[J]. Acta energiae solaris sinica, 2024, 45(6): 436-443.
[7] 马伟, 乔颖, 谢丽蓉, 等. 考虑气象特征波动划分阈值的双目标短期风功率预测[J]. 高电压技术, 2022, 48(10): 4154-4162.
MA W, QIAO Y, XIE L R, et al.Short-term wind power prediction with dual targets considering the threshold of meteorological characteristic fluctuation partition[J]. High voltage engineering, 2022, 48(10): 4154-4162.
[8] 王瑞, 徐新超, 逯静. 基于特征选择及ISSA-CNN-BiGRU的短期风功率预测[J]. 工程科学与技术, 2024, 56(3): 228-239.
WANG R, XU X C, LU J.Short-term wind power prediction based on feature selection and ISSA-CNN-BiGRU[J]. Advanced engineering sciences, 2024, 56(3): 228-239.
[9] 谢丽蓉, 王斌, 包洪印, 等. 基于EEMD-WOA-LSSVM的超短期风电功率预测[J]. 太阳能学报, 2021, 42(7): 290-296.
XIE L R, WANG B, BAO H Y, et al.Super-short-term wind power forecasting based on EEMD-WOA-LSSVM[J]. Acta energiae solaris sinica, 2021, 42(7): 290-296.
[10] WU Z H, HUANG N E.Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in adaptive data analysis, 2009, 1(1): 1-41.
[11] 孙东阳, 于继轩, 阮俊霖, 等. 基于制氢装置效率特性的风储制氢电厂优化控制策略[J]. 电力自动化设备, 2023, 43(12): 53-61.
SUN D Y, YU J X, RUAN J L, et al.Optimal control strategy of wind-energy storage hydrogen production power plant based on efficiency characteristics of hydrogen production device[J]. Electric power automation equipment, 2023, 43(12): 53-61.
[12] 薛建凯. 一种新型的群智能优化技术的研究与应用: 麻雀搜索算法[D]. 上海: 东华大学, 2020.
XUE J K.Research and application of a novel swarm intelligenceoptimization technique: sparrow search algorithm[D]. Shanghai: Donghua University, 2020.
[13] 张雲钦, 程起泽, 蒋文杰, 等. 基于EMD-PCA-LSTM的光伏功率预测模型[J]. 太阳能学报, 2021, 42(9): 62-69.
ZHANG Y Q, CHENG Q Z, JIANG W J, et al.Photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta energiae solaris sinica, 2021, 42(9): 62-69.
[14] 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797-3802.
ZHU Q M, LI H Y, WANG Z Q, et al.Short-term wind power forecasting based on LSTM[J]. Power system technology, 2017, 41(12): 3797-3802.
[15] NB/T 31046—2022, 风电功率预测系统功能规范[S].
NB/T 31046—2022, Function specification of wind power forecasting system[S].
[16] 金吉, 王斌, 喻敏, 等. 基于分形特征的自适应EEMD及其在风功率预测中的应用[J]. 太阳能学报, 2023, 44(5): 416-424.
JIN J, WANG B, YU M, et al.Adaptive EEMD on basis of fraction characteristics and its application on wind power forecasting[J]. Acta energiae solaris sinica, 2023, 44(5): 416-424.
[17] 项晓宇, 朱敏捷, 周灵刚, 等. 基于机器学习的短期规上行业工业增加值预测[J]. 南京师大学报(自然科学版), 2023, 46(2): 99-106.
XIANG X Y, ZHU M J, ZHOU L G, et al.Short-term industrial added value prediction of the above-scale industry based on machine learning[J]. Journal of Nanjing Normal University (natural science edition), 2023, 46(2): 99-106.