引入注意力机制的LSTM-FCN海上风电功率预测

张昊立; 张菁; 倪建辉; 陈龙; 高典

doi:10.19912/j.0254-0096.tynxb.2023-0238

PDF(1986 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (6) : 444-450. DOI: 10.19912/j.0254-0096.tynxb.2023-0238

引入注意力机制的LSTM-FCN海上风电功率预测

张昊立, 张菁, 倪建辉, 陈龙, 高典

作者信息 +

LSTM-FCN OFFSHORE WIND POWER FORECASTING WITH INTRODUCTION OF ATTENTION MECHANISM

Zhang Haoli, Zhang Jing, Ni Jianhui, Chen Long, Gao Dian

Author information +

文章历史 +

摘要

提出一种注意力机制与LSTM-FCN网络结合的海上风电预测模型,在数据中引入风切变物理量来更准确地预测海上风电发电功率。选用公共数据集网站Zenodo内某海上风电场数据中2组风力机数据进行分析和预测验证。对数据集进行标准化预处理后,用AMLSTM-FCN网络和CNN网络、LSTM网络、LSTM-FCN网络进行对比实验,其中AMLSTM-FCN网络在2份风力机数据预测中,RMSE、MAPE、MAE分别为：5号风力机：6.9434、14.01%、48.6636,6号风力机：2.6933、7.12%、17.2536,在相同时段上采用去除风切变的数据训练网络,得到的预测结果从4个指标中看出预测准确度下降。实验表明AMLSTM-FCN网络在海上风电功率预测中有更高的预测精度,以及风切变也对海上风电功率有显著影响。

Abstract

An offshore wind power prediction model combined with LSTM-FCN network is proposed, in which wind shear physical quantities are introduced into the data to more accurately predict offshore wind power generation. Two sets of wind turbine data from an offshore wind farm data website in Zenodo were selected for analysis and prediction verification. After standardized preprocessing of the dataset, AMLSTM-FCN network and CNN network, LSTM network, LSTM-FCN network were used to do the comparison experiments, in which AMLSTM-FCN network was predicted in 2 wind turbine data, RMSE, MAPE, MAE are respectively for No. 5 wind turbine： 6.9434, 14.01%, 48.6636, for No. 6 wind turbine： 2.6933, 7.12%, 17.2536, the data training network without wind shear data is used in the same time period. The obtained prediction results show that the prediction accuracy decreases from the four indexes. Experiments show that AMLSTM-FCN networks have higher prediction accuracy in offshore wind power prediction, and wind shear also has a significant impact on offshore wind power.

导出引用

张昊立, 张菁, 倪建辉, 陈龙, 高典. 引入注意力机制的LSTM-FCN海上风电功率预测[J]. 太阳能学报. 2024, 45(6): 444-450 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0238

Zhang Haoli, Zhang Jing, Ni Jianhui, Chen Long, Gao Dian. LSTM-FCN OFFSHORE WIND POWER FORECASTING WITH INTRODUCTION OF ATTENTION MECHANISM[J]. Acta Energiae Solaris Sinica. 2024, 45(6): 444-450 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0238

中图分类号： TP391 TM614

参考文献

[1] 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.
[2] 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.
[3] 巩家豪. 东营风电场风电功率短期预测研究[D]. 北京: 华北电力大学, 2018.
GONG J H.Research on short-term wind power forecasting in Dongying wind farm[D]. Beijing: North China Electric Power University, 2018.
[4] 司华清. 基于支持向量机理论的风电预测算法研究[D]. 郑州: 华北水利水电大学, 2019.
SI H Q.Research on wind power forecasting algorithm based on support vector machine theort[D]. Zhengzhou: North China University of Water Resources and Electric Power, 2019.
[5] 刘晗, 王硕禾, 张嘉姗, 等. 基于深度时间卷积神经网络的风电功率预测[J]. 济南大学学报(自然科学版), 2022, 36(2): 127-135.
LIU H, WANG S H, ZHANG J S, et al.Wind power forecasting based on deep temporal convolutional networks[J]. Journal of University of Jinan (science and technology), 2022, 36(2): 127-135.
[6] 金宇悦, 康健, 陈永杰. 基于LSTM循环神经网络算法的风电预测技术[J]. 电子测试, 2022, 36(2): 49-51.
JIN Y Y, KANG J, CHEN Y J.Wind power forecasting technology based on LSTM recurrent neural network algorithm[J]. Electronic test, 2022, 36(2): 49-51.
[7] 赵婧宇, 池越, 周亚同. 基于SSA-LSTM模型的短期电力负荷预测[J]. 电工电能新技术, 2022, 41(6): 71-79.
ZHAO J Y, CHI Y, ZHOU Y T.Short-term load forecasting based on SSA-LSTM model[J]. Advanced technology of electrical engineering and energy, 2022, 41(6): 71-79.
[8] 段雪滢, 李小腾, 陈文洁. 基于改进粒子群优化算法的VMD-GRU短期电力负荷预测[J]. 电工电能新技术, 2022, 41(5): 8-17.
DUAN X Y, LI X T, CHEN W J.Improved particles swarm optimization algorithm-based VMD-GRU method for short-term load forecasting[J]. Advanced technology of electrical engineering and energy, 2022, 41(5): 8-17.
[9] 黄玲玲, 李锁, 符杨, 等. 基于风电机组状态的超短期海上风电功率预测[J]. 太阳能学报, 2022, 43(8): 391-398.
HUANG L L, LI S, FU Y, et al.Ultra-short term offshore wind power prediction based on condition-assessment of wind turbines[J]. Acta energiae solaris sinica, 2022, 43(8): 391-398.
[10] 康田雨, 覃智君. 基于超参数优化和双重注意力机制的超短期风电功率预测[J]. 南方电网技术, 2022, 16(5): 44-53.
KANG T Y, QIN Z J.An ultra-short-term wind power forecasting method based on hyperparameter optimization and dual-stage attention mechanism[J]. Southern power system technology, 2022, 16(5): 44-53.
[11] 武煜昊, 王永生, 徐昊, 等. 风电输出功率预测技术研究综述[J]. 计算机科学与探索, 2022, 16(12): 2653-2677.
WU Y H, WANG Y S, XU H, et al.Survey of wind power output power forecasting technology[J]. Journal of frontiers of computer science and technology, 2022, 16(12): 2653-2677.
[12] 綦方中, 卓可翔, 曹柬. 基于多层语义融合注意力机制的短期风电功率概率密度预测方法[J]. 太阳能学报, 2022, 43(11): 140-147.
QI F Z, ZHUO K X, CAO J.Short-term wind power probability density prediction method based on multi-level semantic attention mechanism[J]. Acta energiae solaris sinica, 2022, 43(11): 140-147.
[13] 冯蕊, 王彤, 齐宏志, 等. 基于双注意力机制时间序列预测RNN网络的电力负荷预测方法[J]. 电力大数据, 2022, 25(7): 1-9.
FENG R, WANG T, QI H Z, et al.Power load forecasting method based on dual attention mechanism time series forecasting RNN network[J]. Power systems and big data, 2022, 25(7): 1-9.
[14] KARIM F, MAJUMDAR S, DARABI H, et al.Multivariate LSTM-FCNs for time series classification[J]. Neural networks, 2019, 116: 237-245.
[15] 杨瑞, 全佩, 张康康. 风切变效应对风力机叶片结构性能的影响分析[J]. 机械设计与制造, 2021(5): 172-175.
YANG R, QUAN P, ZHANG K K.Analysis of influence of wind shear effect on structural performance of wind turbine blades[J]. Machinery design & manufacture, 2021(5): 172-175.
[16] 温斌荣, 魏莎, 魏克湘, 等. 风切变和塔影效应对风力机输出功率的影响[J]. 机械工程学报, 2018, 54(10): 124-132.
WEN B R, WEI S, WEI K X, et al.Influences of wind shear and tower shadow on the power output of wind turbine[J]. Journal of mechanical engineering, 2018, 54(10): 124-132.
[17] 刘磊, 石可重, 杨科, 等. 风切变对风力机气动载荷的影响[J]. 工程热物理学报, 2010, 31(10): 1667-1670.
LIU L, SHI K Z, YANG K, et al.Effect of wind shear on the aerodynamic load of wind turbine[J]. Journal of engineering thermophysics, 2010, 31(10): 1667-1670.
[18] 廖明夫, 徐可, 吴斌, 等. 风切变对风力机功率的影响[J]. 沈阳工业大学学报, 2008, 30(2): 163-167.
LIAO M F, XU K, WU B, et al.Effect of wind shear on wind turbine power[J]. Journal of Shenyang University of Technology, 2008, 30(2): 163-167.
[19] WU S, PUBLISHING I O P. Research on wind power ultra-short-term forecasting method based on PCA-LSTM[C]//Proceedings of the 6th International Conference on Energy Materials and Environment Engineering(ICEMEE). Wuhan, China, 2023.
[20] HUANG H, JIA R, SHI X Y, et al.Feature selection and hyper parameters optimization for short-term wind power forecast[J]. Applied intelligence, 2021, 51(10): 6752-6770.
[21] 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.
[22] ZHOU Q G, LV Q Q, ZHANG G F.A combined forecasting system based on modified multi-objective optimization for short-term wind speed and wind power forecasting[J]. Applied sciences, 2021, 11(20): 9383.
[23] 郑婷婷, 王海霞, 李卫东. 风电预测技术及其性能评价综述[J]. 南方电网技术, 2013, 7(2): 104-109.
ZHENG T T, WANG H X, LI W D.A review of the wind power forecasting technology and its performance evaluation[J]. Southern power system technology, 2013, 7(2): 104-109.
[24] 王陈恩, 殷豪, 陈顺, 等. 考虑空间耦合的少数据风电功率预测方法[J]. 南方电网技术, 2022, 16(6): 75-81.
WANG C E, YIN H, CHEN S, et al.Wind power forecasting method with few data considering spatial coupling[J]. Southern power system technology, 2022, 16(6): 75-81.
[25] AN G Q, JIANG Z Y, CHEN L B, et al.Ultra short-term wind power forecasting based on sparrow search algorithm optimization deep extreme learning machine[J]. Sustainability, 2021, 13(18): 10453.