基于动态深度学习的风电功率在线预测方法

赵洪山; 杨铎; 刘欣雨; 倪恒毅; 张扬帆; 林诗雨

doi:10.19912/j.0254-0096.tynxb.2024-0885

PDF(4215 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (9) : 171-180. DOI: 10.19912/j.0254-0096.tynxb.2024-0885

基于动态深度学习的风电功率在线预测方法

赵洪山¹, 杨铎¹, 刘欣雨¹, 倪恒毅¹, 张扬帆², 林诗雨¹

作者信息 +

ONLINE WIND POWER FORECASTING METHOD BASED ON DYNAMIC DEEP LEARNING

Zhao Hongshan¹, Yang Duo¹, Liu Xinyu¹, Ni Hengyi¹, Zhang Yangfan², Lin Shiyu¹

Author information +

文章历史 +

摘要

为适应风电出力的随机性,提出一种基于动态深度学习的风电功率在线预测方法。首先,构建基于双向长短期记忆网络和双向门控循环单元的风电功率基准预测模型,根据训练数据集设置初始参数与权重;其次,采用快速霍夫丁漂移检测方法进行风电状态监测,根据检测结果动态更新深度学习模型;最后,引入随机森林回归模型对预测功率误差进行校正,并通过时间窗实现模型的滚动在线预测。验证结果表明,所提算法相较于Transformev方法均方根误差（RMSE）提高5.68%,平均绝对误差（MAE）提高18.56%,相关系数（R²）提高2.06%,具有较好的预测性能,充分证明所提出的方法能有效提升风电功率预测的准确性。

Abstract

Accurate wind power forecasting is crucial for the reliability of grid scheduling decisions. To address the variability in wind power output, a wind power online forecasting method based on dynamic deep learning is proposed. Initially, a benchmark model utilizing bidirectional Long Short-Term Memory（LSTM） networks and bidirectional Gated Recurrent Units（GRU） is developed, with parameters and weights tailored to the training dataset. Subsequently, a fast Hoeffding drift detection method is used for wind power state monitoring, and the deep learning model is dynamically updated based on the detection results. Finally, a Random Forest regression model is integrated to correct the predicted power errors, enabling rolling online forecasting through sequential time windows. Validation results indicate that the proposed algorithm improves the root mean square error（RMSE） by 5.68%, the mean absolute error（MAE） by 18.56%, and the coefficient of determination（R²） by 2.06% compared to the Transformer, demonstrating good predictive performance and further enhancing the accuracy of wind power forecasting.

导出引用

赵洪山, 杨铎, 刘欣雨, 倪恒毅, 张扬帆, 林诗雨. 基于动态深度学习的风电功率在线预测方法[J]. 太阳能学报. 2025, 46(9): 171-180 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0885

Zhao Hongshan, Yang Duo, Liu Xinyu, Ni Hengyi, Zhang Yangfan, Lin Shiyu. ONLINE WIND POWER FORECASTING METHOD BASED ON DYNAMIC DEEP LEARNING[J]. Acta Energiae Solaris Sinica. 2025, 46(9): 171-180 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0885

中图分类号： TM614

参考文献

[1] 史彭珍, 魏霞, 张春梅, 等. 基于VMD-BOA-LSSVM-AdaBoost的短期风电功率预测[J]. 太阳能学报, 2024, 45(1): 226-233.
SHI P Z, WEI X, ZHANG C M, et al.Short-term wind power prediction based on VMD-BOA-LSSVM-AdaBoost[J]. Acta energiae solaris sinica, 2024, 45(1): 226-233.
[2] 苏连成, 朱娇娇, 李英伟. 基于时间卷积网络残差校正的短期风电功率预测[J]. 太阳能学报, 2023, 44(7): 427-435.
SU L C, ZHU J J, LI Y W.Short-term wind power prediction based on temporal convolutional network residual correction model[J]. Acta energiae solaris sinica, 2023, 44(7): 427-435.
[3] 周海, 刘建锋, 周健, 等. 基于改进降噪自编码器和多元时序聚类的海上风电功率预测[J]. 太阳能学报, 2023, 44(3): 129-138.
ZHOU H, LIU J F, ZHOU J, et al.Offshore wind power prediction based on improved denoising auto-encoder and multivariate time series clustering[J]. Acta energiae solaris sinica, 2023, 44(3): 129-138.
[4] 闫家铭, 毕天姝, 胥国毅, 等. 海上风电经VSC-HVDC并网改进频率控制策略[J]. 华北电力大学学报(自然科学版), 2021, 48(2): 11-19.
YAN J M, BI T S, XU G Y, et al.An improved frequency control strategy for offshore wind farm connected by VSC-HVDC[J]. Journal of North China Electric Power University (natural science edition), 2021, 48(2): 11-19.
[5] 叶林, 赵金龙, 路朋, 等. 考虑气象特征与波动过程关联的短期风电功率组合预测[J]. 电力系统自动化, 2021, 45(4): 54-62.
YE L, ZHAO J L, LU P, et al.Combined prediction of short-term wind power considering correlation of meteorological features and fluctuation process[J]. Automation of electric power systems, 2021, 45(4): 54-62.
[6] LIU H, DUAN Z, LI Y F, et al.A novel ensemble model of different mother wavelets for wind speed multi-step forecasting[J]. Applied energy, 2018, 228: 1783-1800.
[7] 苗长新, 王霞, 李昊, 等. 基于数值天气预报风速误差修正的风电功率日前预测[J]. 电网技术, 2022, 46(9): 3455-3464.
MIAO C X, WANG X, LI H, et al.Day-ahead prediction of wind power based on NWP wind speed error correction[J]. Power system technology, 2022, 46(9): 3455-3464.
[8] 林铮, 刘可真, 沈赋, 等. 考虑海上风电多机组时空特性的超短期功率预测模型[J]. 电力系统自动化, 2022, 46(23): 59-66.
LIN Z, LIU K Z, SHEN F, et al.Ultra-short-term power prediction model considering spatial-temporal characteristics of offshore wind turbines[J]. Automation of electric power systems, 2022, 46(23): 59-66.
[9] 张亚超, 刘开培, 廖小兵, 等. 含大规模风电的电力系统多时间尺度源荷协调调度模型研究[J]. 高电压技术, 2019, 45(2): 600-608.
ZHANG Y C, LIU K P, LIAO X B, et al.Multi-time scale source-load coordination dispatch model for power system with large-scale wind power[J]. High voltage engineering, 2019, 45(2): 600-608.
[10] WAN C, XU Z, PINSON P, et al.Probabilistic forecasting of wind power generation using extreme learning machine[J]. IEEE transactions on power systems, 2014, 29(3): 1033-1044.
[11] LI P B, WANG X W, YANG J J.Short-term wind power forecasting based on two-stage attention mechanism[J]. IET renewable power generation, 2020, 14(2): 297-304.
[12] 程启明, 陈路, 程尹曼, 等. 基于EEMD和LS-SVM模型的风电功率短期预测方法[J]. 电力自动化设备, 2018, 38(5): 27-35.
CHENG Q M, CHEN L, CHENG Y M, et al.Short-term wind power forecasting method based on EEMD and LS-SVM model[J]. Electric power automation equipment, 2018, 38(5): 27-35.
[13] JIA X D, JIN C, BUZZA M, et al.A deviation based assessment methodology for multiple machine health patterns classification and fault detection[J]. Mechanical systems and signal processing, 2018, 99: 244-261.
[14] KO M S, LEE K, KIM J K, et al.Deep concatenated residual network with bidirectional LSTM for one-hour-ahead wind power forecasting[J]. IEEE transactions on sustainable energy, 2021, 12(2): 1321-1335.
[15] 肖白, 张博, 王辛玮, 等. 基于组合模态分解和深度学习的短期风电功率区间预测[J]. 电力系统自动化, 2023, 47(17): 110-117.
XIAO B, ZHANG B, WANG X W, et al.Short-term wind power interval prediction based on combined mode decomposition and deep learning[J]. Automation of electric power systems, 2023, 47(17): 110-117.
[16] 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.
[17] 周育才, 肖添, 谢七月, 等. 基于聚类的HPO-BILSTM光伏功率短期预测[J]. 太阳能学报, 2024, 45(4): 512-518.
ZHOU Y C, XIAO T, XIE Q Y, et al.Clustering-based HPO-BILSTM short-term prediction of PV power[J]. Acta energiae solaris sinica, 2024, 45(4): 512-518.
[18] 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.
[19] CHO K, VAN MERRIENBOER B, GULCEHRE C, et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. Computer Science, 2014.
[20] 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.
[21] 徐清妍, 何丽, 朱泓西. 改进Hoeffding不等式的概念漂移检测方法[J]. 计算机工程与应用, 2020, 56(19): 55-61.
XU Q Y, HE L, ZHU H X.Improved detection method of concept drift based on the Hoeffding inequality[J]. Computer engineering and applications, 2020, 56(19): 55-61.
[22] 孟凡兴, 韩萌, 李春鹏, 等. 概念漂移检测与适应方法综述[J]. 计算机工程与应用, 2024, 60(4): 75-88.
MENG F X, HAN M, LI C P, et al.Survey of concept drift detection and adaptation methods[J]. Computer engineering and applications, 2024, 60(4): 75-88.
[23] 黄宇, 顾智勇, 李永玲, 等. 基于时间模式注意力机制的CNN-BiGRU短期负荷预测[J]. 华北电力大学学报(自然科学版), 2023, 50(6): 11-20.
HUANG Y, GU Z Y, LI Y L, et al.Short-term power load forecasting based on temporal pattern attention mechanism of CNN-BiGRU[J]. Journal of North China Electric Power University (natural science edition), 2023, 50(6): 11-20.
[24] 丁婷婷, 杨明, 于一潇, 等. 基于误差修正的短期风电功率集成预测方法[J]. 高电压技术, 2022, 48(2): 488-496.
DING T T, YANG M, YU Y X, et al.Short-term wind power integration prediction method based on error correction[J]. High voltage engineering, 2022, 48(2): 488-496.
[25] 张国珍, 王其乐, 叶天泽, 等. 基于随机森林和LSTM-自编码算法的风机高温降容状态智能检测方法[J]. 华北电力大学学报(自然科学版), 2021, 48(3): 81-88.
ZHANG G Z, WANG Q L, YE T Z, et al.Intelligent detection method of high-temperature capacity reduction of wind turbine based on random forest and LSTM-autoencoder[J]. Journal of North China Electric Power University (natural science edition), 2021, 48(3): 81-88.
[26] 郭鹏, 姜漫利, 李航涛. 基于运行数据和高斯过程回归的风电机组发电性能分析与监测[J]. 电力自动化设备, 2016, 36(8): 14-19, 29.
GUO P, JIANG M L, LI H T.Performance analysis and monitoring based on SCADA data and Gaussian process regression for wind turbine power generation[J]. Electric power automation equipment, 2016, 36(8): 14-19, 29.
[27] 于群, 霍筱东, 何剑, 等. 基于斯皮尔曼相关系数和系统惯量的中国电网停电事故趋势预测[J]. 中国电机工程学报, 2023, 43(14): 5372-5381.
YU Q, HUO X D, HE J, et al.Trend prediction of power blackout accidents in Chinese power grid based on Spearman's correlation coefficient and system inertia[J]. Proceedings of the CSEE, 2023, 43(14): 5372-5381.
[28] 刘家敏, 李聪睿, 周志浩, 等. 基于WD-CS-SVM的超短期风电功率组合预测[J]. 电力工程技术, 2019, 38(5): 24-29.
LIU J M, LI C R, ZHOU Z H, et al.Combination ultra-short-term prediction of wind power based on WD-CS-SVM[J]. Electric power engineering technology, 2019, 38(5): 24-29.
[29] 符杨, 任子旭, 魏书荣, 等. 基于改进LSTM-TCN模型的海上风电超短期功率预测[J]. 中国电机工程学报, 2022, 42(12): 4292-4303.
FU Y, REN Z X, WEI S R, et al.Ultra-short-term power prediction of offshore wind power based on improved LSTM-TCN model[J]. Proceedings of the CSEE, 2022, 42(12): 4292-4303.
[30] 刘世鹏, 宁德军, 马崛. 针对光伏发电功率预测的LSTformer模型[J]. 计算机工程与应用, 2024, 60(9): 317-325.
LIU S P, NING D J, MA J.LSTformer model for photovoltaic power prediction[J]. Computer engineering and applications, 2024, 60(9): 317-325.