基于滚动分解以及CLA-XGBoost模型的超短期风电功率预测

李练兵; 雒威; 程晴; 苏文勇; 陈业策; 卢志辉

doi:10.19912/j.0254-0096.tynxb.2025-0377

PDF(3146 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (7) : 153-162. DOI: 10.19912/j.0254-0096.tynxb.2025-0377

基于滚动分解以及CLA-XGBoost模型的超短期风电功率预测

李练兵¹, 雒威¹, 程晴², 苏文勇², 陈业策², 卢志辉²

作者信息 +

ULTRA-SHORT-TERM WIND POWER PREDICTION BASED ON ROLLING DECOMPOSITION AND CLA-XGBOOST MODEL

Li Lianbing¹, Luo Wei¹, Cheng Qing², Su Wenyong², Chen Yece², Lu Zhihui²

Author information +

文章历史 +

摘要

为进一步提高风电功率预测的准确性,提出一种基于滚动分解与CLA-XGBoost的预测模型。首先,对风电功率数据进行预处理并采用完全自适应噪声集合经验模态分解（CEEMDAN）对风电功率序列进行滚动分解,将其分解为多个模态变量;其次,将各模态变量分别输入至时空并行模型（CLA）与XGBoost模型中进行训练;最后,基于训练过程中的均方误差（MSE）的倒数对两模型的预测结果进行加权平均。对比分析结果表明,该模型可克服传统分解方法中测试数据信息泄露的弊端,在此基础上可显著提升预测精度与鲁棒性,可为高比例新能源电力系统的安全稳定运行提供更精准的预测信息。

Abstract

To further enhance the accuracy of wind power prediction, a prediction model based on rolling decomposition and CLA-XGBoost is proposed. Firstly, the wind power data is preprocessed, and the complete ensemble empirical mode decomposition with adaptive noise （CEEMDAN） is employed to perform rolling decomposition on the wind power sequence, decomposing it into multiple modal variables. Secondly, each modal variable is inputted into the spatiotemporal parallel model （CLA） and the XGBoost model for training. Finally, the prediction results of the two models are weighted and averaged based on the reciprocal of the mean squared error （MSE） during the training process. The comparative analysis results indicate that this model can overcome the disadvantage of information leakage in test data in traditional decomposition methods, and on this basis, it can significantly improve prediction accuracy and robustness, providing more precise prediction information for the safe and stable operation of high-proportion renewable energy power systems.

导出引用

李练兵, 雒威, 程晴, 苏文勇, 陈业策, 卢志辉. 基于滚动分解以及CLA-XGBoost模型的超短期风电功率预测[J]. 太阳能学报. 2026, 47(7): 153-162 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0377

Li Lianbing, Luo Wei, Cheng Qing, Su Wenyong, Chen Yece, Lu Zhihui. ULTRA-SHORT-TERM WIND POWER PREDICTION BASED ON ROLLING DECOMPOSITION AND CLA-XGBOOST MODEL[J]. Acta Energiae Solaris Sinica. 2026, 47(7): 153-162 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0377

中图分类号： TM614

参考文献

[1] 苏向敬, 朱敏轩, 宇海波, 等. 基于频谱注意力和无交叉联合分位数回归的海上风电功率超短期概率预测[J]. 电力系统保护与控制, 2024, 52(21): 103-116.
Su X J, Zhu M X, Yu H B, et al.Ultra-short-term probabilistic forecasting of offshore wind power based on spectral attention and non-crossing joint quantile regression[J]. Power System Protection and Control, 2024, 52(21): 103-116.
[2] 苏向敬, 程子凡, 聂良钊, 等. 基于AGCN-LSTM模型的海上风电场功率概率预测[J]. 电力系统自动化, 2024, 48(22): 140-149.
Su X J, Cheng Z F, Nie L Z, 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.
[3] 刘新宇, 蒲欣雨, 李继方, 等. 基于贝叶斯优化的VMD-GRU短期风电功率预测[J]. 电力系统保护与控制, 2023, 51(21): 158-165.
Liu X Y, Pu X Y, Li J F, et al.Short-term wind power prediction of a VMD-GRU based on Bayesian optimization[J]. Power System Protection and Control, 2023, 51(21): 158-165.
[4] Safari N, Chung C, Price G.A novel multi-step short-term wind power prediction framework based on chaotic time series analysis and singular spectrum analysis[J]. IEEE Transactions on Power Systems, 2018, 33(3): 2866-2875.
[5] 时帅, 张皓, 黄冬梅, 等. 考虑爬坡特征量的海上风电短期分区功率预测[J]. 太阳能学报, 2024, 45(12): 258-268.
Shi S, Zhang H, Huang D M, et al.Short-term zoning power prediction of offshore wind power considering climbing feature quantities[J]. Acta Energiae Solaris Sinica, 2024, 45(12): 258-268.
[6] Cui X W, Yu X Y, Niu D X.The ultra-short-term wind power point-interval forecasting model based on improved variational mode decomposition and bidirectional gated recurrent unit improved by improved sparrow search algorithm and attention mechanism[J]. Energy, 2024, 288: 129714.
[7] Sun H B, Cui Q, Wen J Y, et al.Short-term wind power prediction method based on CEEMDAN-GWO-Bi-LSTM[J]. Energy Reports, 2024, 11: 1487-1502.
[8] Wang C, Lin H, Hu H, et al.A hybrid model with combined feature selection based on optimized VMD and improved multi-objective coati optimization algorithm for short-term wind power prediction[J]. Energy, 2024, 293: 130684.
[9] Zhang D D, Chen B A, Zhu H Y, et al.Short-term wind power prediction based on two-layer decomposition and BiTCN-BiLSTM-attention model[J]. Energy, 2023, 285: 128762.
[10] Mei H W, Zhu Q Y, Cao W B.A TSFLinear model for wind power prediction with feature decomposition-clustering[J]. Renewable Energy, 2025, 248: 123142.
[11] 董雪, 赵宏伟, 赵生校, 等. 基于二次分解和多目标优化的超短期海上风电功率预测[J]. 高电压技术, 2022, 48(8): 3260-3270.
Dong X, Zhao H W, Zhao S X, et al.Ultra-short-term offshore wind power forecasting based on secondary decomposition and multi-objective optimization[J]. High Voltage Engineering, 2022, 48(8): 3260-3270.
[12] 向阳, 刘亚娟, 孙志伟, 等. 基于帝王蝶算法的CNN-GRU-LightGBM模型短期风电功率预测[J]. 太阳能学报, 2025, 46(1): 105-114.
Xiang Y, Liu Y J, Sun Z W, et al.Short term wind power prediction using CNN-GRU-LightGBM model based on emperor butterfly algorithm[J]. Acta Energiae Solaris Sinica, 2025, 46(1): 105-114.
[13] 柳天虹, 齐胜利, 裔扬, 等. 基于分位数回归的改进权重GRU风电功率区间预测[J]. 太阳能学报, 2024, 45(12): 291-298.
Liu T H, Qi S L, Yi Y, et al.Improved weighted GRU wind power interval prediction based on quantile regression[J]. Acta Energiae Solaris Sinica, 2024, 45(12): 291-298.
[14] 傅质馨, 王宝池, 刘皓明, 等. 基于风速-功率组合分解重构的海上风电功率预测[J]. 太阳能学报, 2024, 45(11): 418-426.
Fu Z X, Wang B C, Liu H M, et al.Offshore wind power forecasting based on wind speed-power combination decompositon[J]. Acta Energiae Solaris Sinica, 2024, 45(11): 418-426.
[15] 万思洋, 杨苹, 崔嘉雁, 等. 针对非平稳信号和高频噪声的自适应噪声完整集成经验模态分解-双向长短期记忆风功率预测模型[J]. 电网技术, 2025, 49(3): 1176-1184.
Wan S Y, Yang P, Cui J Y, et al.An improved CEEMDAN-BiLSTM model for wind power prediction addressing non-stationary signals and high-frequency noise[J]. Power System Technology, 2025, 49(3): 1176-1184.
[16] 虞伟, 黄浩, 金晨星, 等. 基于多头自注意力特征变换和CNN-LSTM的超短期风电功率预测[J]. 南方电网技术, 2026, 20(5): 71-80, 102.
Yu W, Huang H, Jin C X, et al.Ultra-short-term wind power forecasting based on multi-head self-attention feature transformation and CNN-LSTM[J]. Southern Power System Technology, 2026, 20(5): 71-80, 102.
[17] 李恺丽, 王剑斌, 沈怡俊, 等. 基于CEEMD-WOA-LSTM的光伏发电功率预测[J]. 热能动力工程, 2025, 40(2): 136-147.
Li K L, Wang J B, Shen Y J, et al.Prediction of photovoltaic power generation based on CEEMD-WOA-LSTM[J]. Journal of Engineering for Thermal Energy and Power, 2025, 40(2): 136-147.
[18] 顾晋豪, 俞斌, 白隆, 等. GMM聚类和ICEEMDAN-IBWO-BiLSTM短期光伏发电功率预测[J]. 中国测试, 2026, 52(2): 175-184.
Gu J H, Yu B, Bai L, et al.Short-term PV power prediction based on GMM and ICEEMDAN-IBWO-BiLSTM[J]. China Measurement & Test, 2026, 52(2): 175-184.
[19] 蒲海涛, 代英健. 基于注意力机制的ABG-GCA模型中长期风电功率预测[J]. 电工电气, 2025(2): 10-18.
Pu H T, Dai Y J.Medium and long term wind power prediction by ABG-GCA model based on attention mechanism[J]. Electrotechnics Electric, 2025(2): 10-18.
[20] 王永生, 李海龙, 关世杰, 等. 基于变换域分析和XGBoost算法的超短期风电功率预测模型[J]. 高电压技术, 2024, 50(9): 3860-3870.
Wang Y S, Li H L, Guan S J, et al.Ultra-short-term wind power prediction model based on transform domain analysis and XGBoost algorithm[J]. High Voltage Engineering, 2024, 50(9): 3860-3870.
[21] Zhou G Y, Hu G F, Zhang D X, et al.A novel algorithm system for wind power prediction based on RANSAC data screening and Seq2Seq-Attention-BiGRU model[J]. Energy, 2023, 283: 128986.
[22] Ju Y, Sun G Y, Chen Q H, et al.A model combining convolutional neural network and LightGBM algorithm for ultra-short-term wind power forecasting[J]. IEEE Access, 2019, 7: 28309-28318.