School of Science, East China University of Technology, Nanchang 330013, China
Show less
文章历史+
Received
Published
Revised
2025-08-27
2026-09-08
2026-01-09
Online Date
2026-09-18
PDF (18117K)
摘要
针对风电功率序列的非平稳性、强噪声干扰及特征冗余问题,为提高短期风电功率预测精度,创新性地提出了一种融合特征选择与多策略改进黏菌算法优化的多元变分模态分解-支持向量机(multi-strategy improved slime mould algorithm-multivariate variational mode decomposition-support vector machine, MISMA-MVMD-SVM)混合预测模型。首先,采用基于密度的噪声应用空间聚类算法(density-based spatial clustering of applications with noise, DBSCAN)检测风电功率异常值并对其进行修正,利用随机森林(random forest, RF)筛选与风电功率强相关的特征变量,降低输入冗余;其次,引入多元变分模态分解对功率序列及特征序列进行时频同步分解,得到相同数量且频率对齐的模态分量以降低数据波动性;进一步,融合Logistic-Tent混沌映射初始化、广义正态分布搜索、领导机制位置更新及自适应比例变异4种策略,得到多策略改进黏菌算法,提升传统黏菌算法的搜索能力;在此基础上,利用MISMA分阶段优化MVMD参数和SVM超参数,构建MISMA-MVMD-SVM预测模型;最后,以新疆哈密地区实测风力发电数据进行仿真实验分析,分别与不同模型进行对比实验,并设计消融实验验证各模块的有效性。实验结果表明,所提出的模型在预测精度及稳定性方面均表现出显著优势,为风电功率预测提供了一种高效、可靠的解决方案。
Abstract
To address the non-stationarity, strong noise interference, and feature redundancy in wind power sequences, a hybrid forecasting model integrating feature selection with the multi-strategy improved slime mould algorithm (MISMA)-optimized multivariate variational mode decomposition (MVMD) and support vector machine (SVM) has been proposed to improve the short-term wind power prediction accuracy. First, the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used to detect wind power outliers and correct them. Random forest (RF) was then employed to screen for feature variables strongly correlated with wind power output, thereby reducing input redundancy. Secondly, a multi-modal variational decomposition was introduced to perform time-frequency synchronous decomposition on power sequences and feature sequences, yielding an equal number of mode components with aligned frequencies to reduce data volatility. Furthermore, a multi-strategy improved slime mould algorithm was obtained by integrating the initialization of the Logistic-Tent chaotic map, generalized normal distribution search, leader mechanism position update, and adaptive proportional mutation strategy, thereby enhancing the search capability of the traditional slime mould algorithm. Based on this, MISMA was used to optimize the MVMD parameters and SVM hyperparameters in stages, and a MISMA-MVMD-SVM prediction model was constructed. Finally, simulation experiments were conducted using actual wind power generation data from the Hami region of Xinjiang, and comparisons were made with different models. Melting experiments were also designed to verify the effectiveness of each module. The experimental results showed that the proposed model demonstrated significant advantages in terms of prediction accuracy and stability, providing an efficient and reliable solution for wind power forecasting.
ZHANG Fan, YAN Qi-sheng.
Short-term Wind Power Forecasting Based on Feature Selection and MISMA-MVMD-SVM Model[J].
Science Technology and Engineering, 2026, 26(25): 10881-10895 DOI:10.12404/j.issn.1671-1815.2506211
步骤3 利用交替方向乘子法(alternate direction method of multiplier, ADMM)求解非约束变分优化问题,得到模式${\hat{\mathit{u}}}_{\mathit{z},\mathit{k}}\left(\mathit{\omega }\right)$,中心频率ωk,拉格朗日乘子${\hat{\mathrm{\lambda }}}_{\mathit{z}}\left(\mathrm{\omega }\right)$的更新方程,如式(3)~式(5)所示。
随着迭代次数的增加,传统黏菌算法的搜索能力逐渐降低,广义正态分布优化算法[22](generalized normal distribution optimization, GNDO)通过正态分布扰动来增强算法局部开发能力,因此采用GNDO中的局部开发策略来增强黏菌算法的搜索能力,得到位置更新公式如下。
HeChunlei, GuoJiaofeng, XuHaitang, et al. Preliminary exploration of the global energy transformation trend under the new situation: showing two parallel technological paths[J]. China Mining Magazine, 2025, 34(4): 137-143.
[3]
HuS, XiangY, ZhangH, et al. Hybrid forecasting method for wind power integrating spatial correlation and corrected numerical weather prediction[J]. Applied Energy, 2021, 293: 116951.
[4]
WangK, TangX Y, ZhaoS. Robust multi-step wind speed forecasting based on a graph-based data reconstruction deep learning method[J]. Expert Systems with Applications, 2024, 238: 121886.
ChenTianyang, QianZheng, JingBo, et al. Research on short-term wind power forecasting model based on K-means++ and ELM[J]. Electrical Measurement & Instrumentation, 2024, 61(6): 45-50.
[7]
焦业峰. 基于改进支持向量机的风电功率短期预测方法[D]. 无锡: 江南大学, 2023.
[8]
JiaoYefeng. Short-term prediction method of wind power based on improved support vector machine[D]. Wuxi: Jiangnan University, 2023.
[9]
İnaçT, DokurE, YüzgeçU. A multi-strategy random weighted gray wolf optimizer-based multi-layer perceptron model for short-term wind speed forecasting[J]. Neural Computing and Applications, 2022, 34(17): 14627-14657.
[10]
JonkersJ, AvendanoD N, Van WallendaelG, et al. A novel day-ahead regional and probabilistic wind power forecasting framework using deep CNNs and conformalized regression forests[J]. Applied Energy, 2024, 361: 122900.
[11]
KhamariR C, ManiS, BodkheR G, et al. Enhancing wind power forecasting accuracy: a hybrid SNGF-RERNN-SCSO approach[J]. Solar Energy, 2025, 295: 113513.
SuXiangjing, ChengZifan, NieLiangzhao, et al. Power probability prediction for offshore wind farm based on AGCN-LSTM model[J]. Automation of Electric Power Systems, 2024, 48(22): 140-149.
ChenQingming, LiaoHongfei, SunYingkai, et al. Photovoltaic power prediction model based on GWO-GRU[J]. Acta Energiae Solaris Sinica, 2024, 45(7): 438-444.
XiYulian, LingZhouyue, XuXiaomin. Research on short-term wind power CEEMDAN-SMA-LSSVM prediction model[J]. Science Technology and Engineering, 2024, 24(6): 2396-2404.
ChenWenbin. Research and application of short-term wind power prediction based on particle swarm optimization algorithm improved deep extreme learning machine[D]. Nanchang: Nanchang University, 2024.
XiaMeng, YuHuijun. Short-term power load forecasting based on VMD-IOOA-BiGRU model and error compensation[J]. Science Technology and Engineering, 2025, 25(27): 11642-11650.
[24]
WangD, CuiX, NiuD. Wind power forecasting based on LSTM improved by EMD-PCA-RF[J]. Sustainability, 2022, 14(12): 7307.
LuJing, ZhangYanru, WangRui. Short-term wind power forecasting based on BWO-VMD and TCN-BiGRU[J]. Advanced Engineering Sciences, 2025, 57(3): 31-41.
[27]
YangT, YangZ, LiF, et al. A short-term wind power forecasting method based on multivariate signal decomposition and variable selection[J]. Applied Energy, 2024, 360: 122759.
CuiXiwen, ZhangXiaodan, NiuDongxiao. An ultra-short-term wind power point-interval prediction based on two-layer decomposition and MOISMA-SVM[J]. Computer Engineering, 2026, 52(3): 376-391.
[30]
RehmanN U, AftabH. Multivariate variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2019, 67(23): 6039-6052.
[31]
LiS, ChenH, WangM, et al. Slime mould algorithm: a new method for stochastic optimization[J]. Future Generation Computer Systems, 2020, 111: 300-323.
[32]
BeiJ, WangJ, SongH, et al. Slime mould algorithm with mechanism of leadership and self-phagocytosis for multilevel thresholding of color image[J]. Applied Soft Computing, 2024, 163: 111836.
[33]
ZhangY, JinZ, MirjaliliS. Generalized normal distribution optimization and its applications in parameter extraction of photovoltaic models[J]. Energy Conversion and Management, 2020, 224: 113301.
HanZimeng, WangQiuping, WangMengna. Enhanced slime mould algorithm with multi-strategy for parameter optimization of support vector machine[J]. Journal of Xi’an University of Technology, 2025, 41(4): 584-593.
[36]
YaoL, YuanP, TsaiC Y, et al. ESO: an enhanced snake optimizer for real-world engineering problems[J]. Expert Systems with Applications, 2023, 230: 120594.
CaoJiyuan, WangYanwen, ChenPeng, et al. Mine cable partial discharge denoising method based on multivariate variational mode decomposition and improved wavelet threshold[J]. Journal of China Coal Society, 2025, 50(4): 2293-2309.
ChenYicong, ZhangDahai, LiYuxin, et al. Multi-objective optimization based on DWT-MOSMA-SVM for short-term bus load forecasting[J]. Electric Power Construction, 2023, 44(3): 49-55.
YinGang, ZhuMiao, QuanPengcheng, et al. Research on CNN-LSTM-Attention aluminum electrolyzer electrolysis temperature prediction method based on PID search optimization[J]. Chinese Journal of Scientific Instrument, 2025, 46(1): 324-337.