基于样本熵和CNN-MGM混合模型的超短期风速预测

张楠; 朱永奇; 郑创; 孙娜; 薛小明

doi:10.19912/j.0254-0096.tynxb.2024-1646

PDF(1499 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (1) : 645-653. DOI: 10.19912/j.0254-0096.tynxb.2024-1646

基于样本熵和CNN-MGM混合模型的超短期风速预测

张楠^1,2, 朱永奇¹, 郑创¹, 孙娜^1,3, 薛小明¹

作者信息 +

ULTRA-SHORT-TERM WIND SPEED PREDICTION BASED ON SAMPLE ENTROPY AND CNN-MGM HYBRID MODEL

Zhang Nan^1,2, Zhu Yongqi¹, Zheng Chuang¹, Sun Na^1,3, Xue Xiaoming¹

Author information +

文章历史 +

摘要

针对风速具有不稳定性和间歇性等特点,提出一种混合风速预测模型,该模型集成卷积神经网络（CNN）、最小门控存储网络（MGM）、鲸鱼优化算法（WOA）和时变滤波器经验模式分解（TVFEMD）。首先采用TVFEMD对原始风速序列进行分解,获得若干子序列;随后基于样本熵对分量复杂度进行评估,并对复杂度最高的分量实施TVFEMD二次分解。最后,将得到的各子序列输入混合预测模型进行建模与预测,从而获得对应的子序列预测结果,进而得出最终预测结果。实验结果表明,与其他模型对比,所提模型的平均绝对误差下降2.3%~8.6%,并在不同数据集中得到验证,这证明了混合模型在预测中的有效性。

Abstract

A hybrid wind speed prediction model is proposed to address the instability and intermittency of wind speed, which integrates convolutional neural networks （CNN）,minimum gated storage networks （MGM）, whale optimization algorithms （WOA）, and time-varying filter based empirical mode decomposition （TVFEMD）. TVFEMD is used decomposition to decompose the original wind speed data into multiple subsequences. Guided by sample entropy, use TVFEMD to decompose the sequence with the highest complexity twice. Then, the decomposed subsequences are input into the WOA algorithm optimized hybrid model for prediction, and the prediction results of each subsequence are obtained to produce the final result. The experimental results show that compared with other models, the average absolute error of the proposed model has decreased by 2.3%-8.6%, and the same effect has been achieved in different datasets, verifying the effectiveness of the mixed model in wind speed prediction.

导出引用

张楠, 朱永奇, 郑创, 孙娜, 薛小明. 基于样本熵和CNN-MGM混合模型的超短期风速预测[J]. 太阳能学报. 2026, 47(1): 645-653 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1646

Zhang Nan, Zhu Yongqi, Zheng Chuang, Sun Na, Xue Xiaoming. ULTRA-SHORT-TERM WIND SPEED PREDICTION BASED ON SAMPLE ENTROPY AND CNN-MGM HYBRID MODEL[J]. Acta Energiae Solaris Sinica. 2026, 47(1): 645-653 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1646

中图分类号： TM614

参考文献

[1] MA K K, ZHANG W Y, GUO Z H, et al.A hybrid forecasting model for very short-term wind speed prediction based on secondary decomposition and deep learning algorithms[J]. Earth science informatics, 2023, 16(3): 2421-2438.
[2] 张金良, 刘子毅, 孙安黎. 计及误差信息的自适应超短期风速预测模型[J]. 太阳能学报, 2024, 45(3): 18-28.ZHANG J L, LIU Z Y, SUN A L. Adaptive ultra-short-term wind speed prediction model considering error information[J]. Acta energiae solaris sinica, 2024, 45(3): 18-28.
[3] HUANG Y, ZHANG B Z, PANG H Z, et al.Spatio-temporal wind speed prediction based on Clayton Copula function with deep learning fusion[J]. Renewable energy, 2022, 192: 526-536.
[4] 李嘉文, 盛德仁, 李蔚, 等. 基于多目标优化和误差修正的短期风速预测[J]. 太阳能学报, 2022, 43(8): 273-280.LI J W, SHENG D R, LI W, et al. Short-term wind speed prediction based on multi-objective optimization and error correction[J]. Acta energiae solaris sinica, 2022, 43(8): 273-280.
[5] 姚万业, 黄璞, 姚吉行, 等. 一种基于深度学习的FRS-CLSTM风速预测模型[J]. 太阳能学报, 2020, 41(9): 324-330.YAO W Y, HUANG P, YAO J X, et al. A FRS-CLSTM wind speed prediction model based on deep learning[J]. Acta energiae solaris sinica, 2020, 41(9): 324-330.
[6] WEI Y, GAO X L.Transmission line galloping prediction based on GA-BP-SVM combined method[J]. IEEE access, 2021, 9: 107680-107687.
[7] 全一鸣, 喻敏, 王文波, 等. 基于分形优化的VMD和GA-BP的短期风速预测[J]. 太阳能学报, 2023, 44(7): 436-446.QUAN Y M, YU M, WANG W B, et al. Short-term wind speed prediction based on fractal optimization of VMD-GA-BP[J]. Acta energiae solaris sinica, 2023, 44(7): 436-446.
[8] 李明, 刘东岳, 赵良伟, 等. 基于EEMD-SVM-ELM模型的月降水量预测研究[J]. 水电能源科学, 2024, 42(5): 19-23.LI M, LIU D Y, ZHAO L W, et al. Monthly precipitation prediction based on EEMD-SVM-ELM model[J]. Water resources and power, 2024, 42(5): 19-23.
[9] LI M Y, FU Y J.Prediction of supply chain financial credit risk based on PCA-GA-SVM model[J]. Sustainability, 2022, 14(24): 16376.
[10] 魏昱洲, 许西宁. 基于LSTM长短期记忆网络的超短期风速预测[J]. 电子测量与仪器学报, 2019, 33(2): 64-71.WEI Y Z, XU X N. Ultra-short-term wind speed prediction model using LSTM networks[J]. Journal of electronic measurement and instrumentation, 2019, 33(2): 64-71.
[11] QUAN Y, WEI Q, XIAO Y C.Influence of average time interval and observation spacing of wind speed records on prediction results of extreme wind speed[J]. Natural hazards, 2024, 120(1): 805-824.
[12] 姚越, 刘达. 基于注意力机制的卷积神经网络-长短期记忆网络的短期风电功率预测[J]. 现代电力, 2022, 39(2): 212-218.YAO Y, LIU D. Short-term wind power forecasting based on attention mechanism of CNN-LSTM[J]. Modern electric power, 2022, 39(2): 212-218.
[13] XIONG D Z, FU W L, WANG K, et al.A blended approach incorporating TVFEMD, PSR, NNCT-based multi-model fusion and hierarchy-based merged optimization algorithm for multi-step wind speed prediction[J]. Energy conversion and management, 2021, 230: 113680.
[14] WANG F, TONG S, SUN Y Q, et al.Wind process pattern forecasting based ultra-short-term wind speed hybrid prediction[J]. Energy, 2022, 255: 124509.
[15] YANG Y, CHEN Y H, WANG Y C, et al.Modelling a combined method based on ANFIS and neural network improved by DE algorithm: a case study for short-term electricity demand forecasting[J]. Applied soft computing, 2016, 49: 663-675.
[16] 罗竹梅, 李俊, 郭涛, 等. 低速海流能俘能装置阵列优化布置研究[J]. 太阳能学报, 2024, 45(11): 561-569.LUO Z M, LI J, GUO T, et al. Study on array optimal arrangement of energy capture device in low velocity ocean current[J]. Acta energiae solaris sinica, 2024, 45(11): 561-569.
[17] 张越, 臧海祥, 韩海腾, 等. 基于FSN-MCCN-SA-BiLSTM的短期风速预测[J]. 太阳能学报, 2024, 45(8): 529-536.ZHANG Y, ZANG H X, HAN H T, et al. Short-term wind speed forecasting based on FSN-MCCN-SA-BiLSTM[J]. Acta energiae solaris sinica, 2024, 45(8): 529-536.
[18] 陈斌, 李泽科, 余斯航, 等. 基于CA-WOA-BP算法的调度数据网鲁棒性预测[J]. 南方电网技术, 2025, 19(2): 10-18.CHEN B, LI Z K, YU S H, et al. Robustness prediction of dispatching data network based on CA-WOA-BP algorithm[J]. Southern power system technology, 2025, 19(2): 10-18.
[19] LI H, LI Z, MO W.A time varying filter approach for empirical mode decomposition[J]. Signal processing, 2017, 138: 146-158.
[20] RICHMAN J S, MOORMAN J R.Physiological time-series analysis using approximate entropy and sample entropy[J]. American journal of physiology-heart and circulatory physiology, 2000, 278(6): H2039-H2049.
[21] LECUN Y, BOSER B, DENKER J S, et al.Backpropagation applied to handwritten zip code recognition[J]. Neural computation, 1989, 1(4): 541-551.
[22] MIRJALILI S, LEWIS A.The whale optimization algorithm[J]. Advances in engineering software, 2016, 95: 51-67.
[23] 邱文智, 张文煜, 郭振海, 等. 基于二次分解和乌鸦搜索算法优化组合模型的超短期风速预测[J]. 太阳能学报, 2024, 45(3): 73-82.QIU W Z, ZHANG W Y, GUO Z H, et al. Ultra-short-term wind speed forecasting based on optimalcombination modelof secondary decompositionand crow search algorithm[J]. Acta energiae solaris sinica, 2024, 45(3): 73-82.