基于CEEMDAN和时间卷积网络的风向预测算法

张群; 侯玉强; 许剑冰; 赵巍; 李威; 刘福锁

doi:10.19912/j.0254-0096.tynxb.2023-0928

PDF(2763 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (10) : 512-520. DOI: 10.19912/j.0254-0096.tynxb.2023-0928

基于CEEMDAN和时间卷积网络的风向预测算法

张群, 侯玉强, 许剑冰, 赵巍, 李威, 刘福锁

作者信息 +

WIND DIRECTION PREDICTION ALGORITHM BASED ON CEEMDAN AND TIMPORAL CONVOLUTIONAL NETWORK

Zhang Qun, Hou Yuqiang, Xu Jianbing, Zhao Wei, Li Wei, Liu Fusuo

Author information +

文章历史 +

摘要

为提高风向预测精度,提出一种基于随机森林算法（RF）、分类回归树（CART）、完备自适应噪声经验模态分解（CEEMDAN）与时间卷积网络（TCN）的组合预测算法。其中,基于分类回归树法的输入重要性评测用于评测风向预测模型的输入相关度并进行筛选;随机森林算法用于对风向数据进行自适应处理;完备自适应噪声集成经验模态分解用于对输入风向数据进行分解并进行输入信息特征提取;最后,利用时间卷积网络搭建风向预测模型。实验结果表明,相较于其他8种对比模型,所提模型在四季度数据集上预测误差均小于4.95°,均获得了最高的预测精度。

Abstract

In order to improve the accuracy of wind direction prediction, a combined prediction algorithm based on decision tree method （CART）, random forest algorithm, complete adaptive noise empirical mode decomposition （CEEMDAN） and temporal convolutional network （TCN） is proposed. Among them, the input importance evaluation based on decision tree method is used to evaluate and screen the input relevance of wind direction perdiction models. Randon forest algorithm is used to classify and process wind direction data; The complete adaptive noise integrated empirical mode decomposition is used to decompose the input wind direction data and extract the input information features; Finally, the temporal convolutional network is used to build the wind direction prediction model. The experimental results show that compared to the other eight comparison models, the prediction errors of the proposed model for wind direction in the fourth quarter data set are less than 4.95°, and the highest prediction accuracy is achieved.

导出引用

张群, 侯玉强, 许剑冰, 赵巍, 李威, 刘福锁. 基于CEEMDAN和时间卷积网络的风向预测算法[J]. 太阳能学报. 2024, 45(10): 512-520 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0928

Zhang Qun, Hou Yuqiang, Xu Jianbing, Zhao Wei, Li Wei, Liu Fusuo. WIND DIRECTION PREDICTION ALGORITHM BASED ON CEEMDAN AND TIMPORAL CONVOLUTIONAL NETWORK[J]. Acta Energiae Solaris Sinica. 2024, 45(10): 512-520 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0928

中图分类号： TM614

参考文献

[1] 国家能源局发布2023年全国电力工业统计数据[J]. 电力科技与环保, 2024, 40(1): 95.
National energy administration releases 2023 national electric power industry statistical data[J]. Electric power technology and environmental protection, 2024, 40(1): 95.
[2] 符杨, 郑紫宸, 时帅, 等. 考虑气象相似性与数值天气预报修正的海上风功率预测[J]. 电网技术, 2019, 43(4): 1253-1259.
FU Y, ZHENG Z C, SHI S, et al.Offshore wind power forecasting considering meteorological similarity and NWP correction[J]. Power system technology, 2019, 43(4): 1253-1259.
[3] 杨茂, 董昊. 基于数值天气预报风速和蒙特卡洛法的短期风电功率区间预测[J]. 电力系统自动化, 2021, 45(5): 79-85.
YANG M, DONG H.Short-term wind power interval prediction based on wind speed of numerical weather prediction and Monte Carlo method[J]. Automation of electric power systems, 2021, 45(5): 79-85.
[4] 廖文宇, 郭鹏, 赵冰, 等. 基于小波分解与ARMA-BayesLSTM组合模型的风向短期预测[J]. 电力科学与工程, 2023, 39(5): 17-23.
LIAO W Y, GUO P, ZHAO B, et al.Short-term prediction of wind direction based on wavelet decomposition and ARMA-BayesLSTM combined model[J]. Electric power science and engineering, 2023, 39(5): 17-23.
[5] AL-MUSAYLH M S, DEO R C, ADAMOWSKI J F, et al. Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia[J]. Advanced engineering informatics, 2018, 35: 1-16.
[6] MASSERAN N, RAZALI A M, IBRAHIM K, et al.Fitting a mixture of von Mises distributions in order to model data on wind direction in Peninsular Malaysia[J]. Energy conversion and management, 2013, 72: 94-102.
[7] 王跃龙, 张燕, 韩志惠, 等. 基于小波去噪的BP神经网络短期风功率预测方法设计[J]. 电工技术, 2023(2): 32-35.
WANG Y L, ZHANG Y, HAN Z H, et al.Design of BP neural network short-term wind power prediction method based on wavelets denoising[J]. Electric engineering, 2023(2): 32-35.
[8] 朱成名, 魏云冰, 蒋成成, 等. 基于PSO-BP神经网络的风电功率备用容量估计模型[J]. 电子科技, 2021, 34(12): 36-41.
ZHU C M, WEI Y B, JIANG C C, et al.Estimation model of wind power reserve capacity based on PSO-BP neural network[J]. Electronic science and technology, 2021, 34(12): 36-41.
[9] 王佶宣, 邓斌, 王江. 基于经验模态分解与RBF神经网络的短期风功率预测[J]. 电力系统及其自动化学报, 2020, 32(11): 109-115.
WANG J X, DENG B, WANG J.Short-term wind power prediction based on empirical mode decomposition and RBF neural network[J]. Proceedings of the CSU-EPSA, 2020, 32(11): 109-115.
[10] 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): 275-281.
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): 275-281.
[11] 唐振浩, 赵赓楠, 曹生现, 等. 一种基于数据解析的混合风向预测算法[J]. 太阳能学报, 2021, 42(9): 349-356.
TANG Z H, ZHAO G N, CAO S X, et al.A data analystic based hybrid wind direction prediction algorithm[J]. Acta energiae solaris sinica, 2021, 42(9): 349-356.
[12] 张瀚, 满丹丹, 王航. 基于VMD-AOA-GRU的超短期风向预测[J]. 自动化应用, 2023, 64(3): 66-70.
ZHANG H, MAN D D, WANG H.Ultra short-term wind direction prediction based on VMD-AOA-GRU[J]. Automation application, 2023, 64(3): 66-70.
[13] QIU X H, REN Y, SUGANTHAN P N, et al.Empirical Mode decomposition based ensemble deep learning for load demand time series forecasting[J]. Applied soft computing, 2017, 54: 246-255.
[14] 贾东卫, 任永峰, 李莉美, 等. 基于集合经验模态分解的微电网混合储能优化配置[J]. 太阳能学报, 2023, 44(2): 239-246.
JIA D W, REN Y F, LI L M, et al.Research on optimization of hybrid energy storage capacity using ensemble empirical mode decomposition and fuzzy control[J]. Acta energiae solaris sinica, 2023, 44(2): 239-246.
[15] 迟捷, 邹华, 林荣恒. 融合小波分解的Lasso光伏净负荷预测方法[J]. 电力信息与通信技术, 2023, 21(5): 9-16.
CHI J, ZOU H, LIN R H.Lasso photovoltaic net load forecasting method based on wavelet decomposition[J]. Electric power information and communication technology, 2023, 21(5): 9-16.
[16] 贾伟青, 任永峰, 薛宇, 等. 基于小波包-模糊控制的混合储能平抑大型风电场功率波动[J]. 太阳能学报, 2021, 42(9): 357-363.
JIA W Q, REN Y F, XUE Y, et al.Wavelet packet-fuzzy control of hybrid energy storage for power fluctuation smoothing of large wind farm[J]. Acta energiae solaris sinica, 2021, 42(9): 357-363.
[17] 岳有军, 刘英翰, 赵辉, 等. 基于CEEMDAN-SE和DBN的短期电力负荷预测[J]. 电测与仪表, 2020, 57(17): 59-65.
YUE Y J, LIU Y H, ZHAO H, et al.Short-term load forecasting based on CEEMDAN-SE and DBN[J]. Electrical measurement & instrumentation, 2020, 57(17): 59-65.
[18] 刘友波, 吴浩, 刘挺坚, 等. 集成经验模态分解与深度学习的用户侧净负荷预测算法[J]. 电力系统自动化, 2021, 45(24): 57-64.
LIU Y B, WU H, LIU T J, et al.User-side net load forecasting method integrating empirical mode decomposition and deep learning[J]. Automation of electric power systems, 2021, 45(24): 57-64.
[19] 阮志峰. 基于随机森林算法的电力电子互感器状态评估模型[J]. 自动化应用, 2023, 64(7): 159-161, 165.
RUAN Z F.State evaluation model of power electronic transformer based on random forest algorithm[J]. Automation application, 2023, 64(7): 159-161, 165.
[20] 陈小艳, 刘畅, 于凤, 等. 基于神经网络算法和随机森林模型的烧结矿质量预测[J]. 工业技术创新, 2023, 10(1): 24-30.
CHEN X Y, LIU C, YU F, et al.Sinter quality prediction based on neural network algorithm and random forest model[J]. Industrial technology innovation, 2023, 10(1): 24-30.
[21] 周思思, 李勇, 郭钇秀, 等. 考虑时序特征提取与双重注意力融合的TCN超短期负荷预测[J]. 电力系统自动化, 2023, 47(18): 193-205.
ZHOU S S, LI Y, GUO Y X, et al.Ultra-short-term load forecasting based on temporal convolutional network considering temporal feature extraction and dual attention fusion[J]. Automation of electric power systems, 2023, 47(18): 193-205.
[22] 邢晨, 张照贝. 基于改进时间卷积网络的短期光伏出力概率预测方法[J]. 太阳能学报, 2023, 44(2): 373-380.
XING C, ZHANG Z B.Short-term probabilistic forecasting method of photovoltaic output power based on improved temporal convolutional network[J]. Acta energiae solaris sinica, 2023, 44(2): 373-380.