基于CAWR-LSTM-TRF模型的超短期风电功率预测

潘鹏程; 张帅; 刘晖; 陈子介

doi:10.19912/j.0254-0096.tynxb.2024-2231

PDF(2639 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (3) : 452-461. DOI: 10.19912/j.0254-0096.tynxb.2024-2231

基于CAWR-LSTM-TRF模型的超短期风电功率预测

潘鹏程^1,2, 张帅^1,2, 刘晖³, 陈子介⁴

作者信息 +

ULTRA-SHORT-TERM WIND POWER FORECASTING BASED ON CAWR-LSTM-TRF MODEL

Pan Pengcheng^1,2, Zhang Shuai^1,2, Liu Hui³, Chen Zijie⁴

Author information +

文章历史 +

摘要

为提高风电超短期预测精度,提出一种长短期记忆神经网络（LSTM）算法与Transformer（TRF）模型相结合的超短期风电功率组合预测模型。为避免预测模型陷入局部最优解,引入余弦退火热重启（CAWR）策略对模型进行优化。首先,利用噪声密度聚类（DBSCAN）和随机森林（RF）进行异常数据清洗与填补。其次,采用CAWR-LSTM-TRF组合模型提取风电功率特征。最后,进行超短期风电功率预测。研究结果表明：与LSTM-TRF模型相比,经CAWR优化的LSTM-TRF组合预测模型的对称平均绝对百分比误差平均降低了0.46个百分点。因此,所提模型具有较高预测精度和较好预测性能。

Abstract

To improve the accuracy of the ultra-short term wind power prediction, an ultra-short-term wind power prediction model based on a Long Short-Term Memory （LSTM） neural network algorithm combined with the Transformer （TRF） model is proposed. The cosine annealing with warm restarts （CAWR） strategy is introduced to optimize the proposed prediction model to prevent the prediction model from converging to local optima. Firstly, the density-based spatial clustering of applications with noise （DBSCAN） and random forest （RF） methods are employed for anomaly detection and data imputation. Secondly, the CAWR-LSTM-TRF combined model is utilized to extract wind power features. Finally, the experiments for ultra-short-term wind power forecasting are conducted. The results of the study show that the symmetric mean absolute percentage error of the combined LSTM-TRF prediction model optimized by CAWR is reduced by an average of 0.46 percentage points compared to the LSTM-TRF model. Therefore, the proposed model achieves higher prediction accuracy and superior forecasting performance.

导出引用

潘鹏程, 张帅, 刘晖, 陈子介. 基于CAWR-LSTM-TRF模型的超短期风电功率预测[J]. 太阳能学报. 2026, 47(3): 452-461 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2231

Pan Pengcheng, Zhang Shuai, Liu Hui, Chen Zijie. ULTRA-SHORT-TERM WIND POWER FORECASTING BASED ON CAWR-LSTM-TRF MODEL[J]. Acta Energiae Solaris Sinica. 2026, 47(3): 452-461 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2231

中图分类号： TM614

参考文献

[1] 国家能源局. 国家能源局发布2025年1-11月份全国电力工业统计数据[N]. 北京: 国家能源局, 2025.
The National Energy Administration. The National Energy Administration releases national electricity industry statistics for January-November 2025[N]. Beijing: National Energy Administration, NEA, 2025.
[2] 彭小圣, 熊磊, 文劲宇, 等. 风电集群短期及超短期功率预测精度改进方法综述[J]. 中国电机工程学报, 2016, 36(23): 6315-6326, 6596.
PENG X S, XIONG L, WEN J Y, et al.A summary of the state of the art for short-term and ultra-short-term wind power prediction of regions[J]. Proceedings of the CSEE, 2016, 36(23): 6315-6326, 6596.
[3] 孙荣富, 张涛, 和青, 等. 风电功率预测关键技术及应用综述[J]. 高电压技术, 2021, 47(4): 1129-1143.
SUN R F, ZHANG T, HE Q, et al.Review on key technologies and applications in wind power forecasting[J]. High voltage engineering, 2021, 47(4): 1129-1143.
[4] 韩自奋, 景乾明, 张彦凯, 等. 风电预测方法与新趋势综述[J]. 电力系统保护与控制, 2019, 47(24): 178-187.
HAN Z F, JING Q M, ZHANG Y K, et al.Review of wind power forecasting methods and new trends[J]. Power system protection and control, 2019, 47(24): 178-187.
[5] 薛禹胜, 郁琛, 赵俊华, 等. 关于短期及超短期风电功率预测的评述[J]. 电力系统自动化, 2015, 39(6): 141-151.
XUE Y S, YU C, ZHAO J H, et al.A review on short-term and ultra-short-term wind power prediction[J]. Automation of electric power systems, 2015, 39(6): 141-151.
[6] 杨茂, 张罗宾. 基于数据驱动的超短期风电功率预测综述[J]. 电力系统保护与控制, 2019, 47(13): 171-186.
YANG M, ZHANG L B.Review on ultra-short term wind power forecasting based on data-driven approach[J]. Power system protection and control, 2019, 47(13): 171-186.
[7] 钱政, 裴岩, 曹利宵, 等. 风电功率预测方法综述[J]. 高电压技术, 2016, 42(4): 1047-1060.
QIAN Z, PEI Y, CAO L X, et al.Review of wind power forecasting method[J]. High voltage engineering, 2016, 42(4): 1047-1060.
[8] 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): 275-81.
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): 275-81.
[9] 贾睿, 杨国华, 郑豪丰, 等. 基于自适应权重的CNN-LSTM&GRU组合风电功率预测方法[J]. 中国电力, 2022, 55(5): 47-56, 110.
JIA R, YANG G H, ZHENG H F, et al.Combined wind power prediction method based on CNN-LSTM & GRU with adaptive weights[J]. Electric power, 2022, 55(5): 47-56, 110.
[10] 刘佳宁. 基于长短时记忆网络的超短期风速及风功率预测研究[D]. 保定: 华北电力大学, 2022.
Liu J N.Ultra-short-term wind speed and wind power forecasting based on LSTM[D]. Baoding: North China Electric Power University, 2022.
[11] 李丹, 方泽仁, 缪书唯, 等. 考虑训练样本分布不均衡的超短期风电功率概率预测[J]. 电网技术, 2024, 48(3): 1133-1147.
LI D, FANG Z R, MIAO S W, et al.Probability prediction of ultra-short-term wind power considering unbalanced distribution of training samples[J]. Power system technology, 2024, 48(3): 1133-1147.
[12] 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.
[13] 袁畅, 王森, 孙永辉, 等. 基于混合特征双重衍生和误差修正的风电功率超短期预测[J]. 电力系统自动化, 2024, 48(5): 68-76.
YUAN C, WANG S, SUN Y H, et al.Ultra-short-term forecasting of wind power based on dual derivation of hybrid features and error correction[J]. Automation of electric power systems, 2024, 48(5): 68-76.
[14] 臧海祥, 赵勇凯, 张越, 等. 基于低风速功率修正和损失函数改进的超短期风电功率预测[J]. 电力系统自动化, 2024, 48(7): 248-257.
ZANG H X, ZHAO Y K, ZHANG Y, et al.Ultra-short-term wind power prediction based on power correction under low wind speed and improved loss function[J]. Automation of electric power systems, 2024, 48(7): 248-257.
[15] 康逸群, 刘厦, 雷兢. 基于鲁棒稀疏宽度学习系统的短期风电功率预测[J]. 太阳能学报, 2024, 45(5): 32-43.
KANG Y Q, LIU S, LEI J.Short-term wind power prediction based on rubust sparsity broad learning system[J]. Acta energiae solaris sinica, 2024, 45(5): 32-43.
[16] 李丹, 王奇, 杨保华, 等. 基于独立稀疏SAE的多风电场超短期功率预测[J]. 电力系统及其自动化学报, 2022, 34(2): 23-30.
LI D, WANG Q, YANG B H, et al.Ultrashort-term power prediction of multiple wind farms based on independent sparse SAE[J]. Proceedings of the CSU-EPSA,2022,34(02):23-30.
[17] ESTER M, KRIEGEL H, SANDER J, et al.A density-based algorithm for discovering clusters in large spatial databases with noise[C]//Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining Protland, 1996: 226-231.
[18] 牟哲岳, 孙勇, 王瑞良, 等. 基于实测数据和机器学习的风电机组载荷预测模型[J]. 太阳能学报, 2023, 44(10): 414-419.
MOU Z Y, SUN Y, WANG R L, et al.Prediction model for wind turbine loads based on experimental data and machine learning[J]. Acta energiae solaris sinica, 2023, 44(10): 414-419.
[19] 胡锐, 乔加飞, 李永华, 等. 基于WOA-VMD-SSA-LSTM的中长期风电预测[J]. 太阳能学报, 2024, 45(9): 549-556.
HU R, QIAO J F, LI Y H, et al.Medium and long term wind power forecast based on WOA-VMD-SSA-LSTM[J]. Acta energiae solaris sinica, 2024,45(9): 549-556.
[20] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc, 2017: 6000-6010.
[21] 骆钊, 吴谕侯, 朱家祥, 等. 基于多尺度时间序列块自编码 Transformer神经网络模型的风电超短期功率预测[J]. 电网技术, 2023, 47(9): 3527-3537.
LUO Z, WU Y H, ZHU J X, et al.Wind power forecasting based on multi-scale time series block auto-encoder Transformer neural network model[J]. Power system technology, 2023, 47(9): 3527-3537.
[22] ZHOU J B, LU X J, XIAO Y X, et al. SDWPF: a dataset for spatial dynamic wind power forecasting challenge at KDD cup2022[EB/OL]. 2022: 2208.04360. https://arxiv.org/abs/2208.04360v1.
[23] 潘鹏程, 刘晖, 王仁明. 自适应密度聚类组合数据清洗的LSTM风电功率预测[J]. 电力系统及其自动化学报, 2024, 36(7): 59-66.
PAN P C, LIU H, WANG R M.LSTM wind power prediction based on adaptive density clustering combined with data cleansing[J]. Proceedings of the CSU-EPSA, 2024, 36(7): 59-66.