基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测

doi:10.11930/j.issn.1004-9649.202302098

摘要/Abstract

摘要：

为进一步提升短期风电功率的预测精度，提出了一种基于互补集合经验模态分解-样本熵（complementary ensemble empirical mode decomposition-sample entropy，CEEMD-SE）的卷积神经网络（convolutional neural network，CNN）和长短期记忆-门控循环单元（long short term memory-gated recurrent unit，LSTM-GRU）的短期风电功率预测模型。首先，利用互补集合经验模态分解将原始风电功率序列分解为若干本征模态函数（intrinsic mode function，IMF）分量和一个残差（residual，RES）分量，利用样本熵算法将相近的分量进行重构；其次，搭建卷积神经网络和长短期记忆网络的并行网络结构，提取数据的局部特征和时序特征，并将特征融合后输入门控循环单元网络中进行学习预测；最后，通过算例进行验证，结果表明采用该模型后预测精度得到了有效提升，其均方根误差降低了15.06%、平均绝对误差降低了15.22%、决定系数提高了1.91%。

关键词: 短期风电功率预测, 互补集合经验模态分解, 样本熵, 长短期记忆网络, 门控循环单元

Abstract:

In order to further improve the accuracy of short-term wind power forecast, a CNN & LSTM-GRU based short-term wind power prediction model using CEEMD-SE algorithm is proposed. First, the original wind power output series are decomposed into several intrinsic mode function components and one residual component by complementary set empirical mode decomposition, and those components of similar mode are reconstructed by sample entropy algorithm. Next, the parallel network structure of convolutional neural network and long short term memory network is set up, and the local and temporal features of the data are extracted. And then the features are fused and input into the gated cyclic unit network for learning and prediction. Finally, the feasibility of the model is verified through case studies. The results show that the forecast accuracy has been improved effectively. The root mean square error and average absolute error, of the proposed model are reduced by 15.06% and 15.22% respectively, while coefficient of determination is up by 1.91%.

Key words: short-term wind power forecasting, complementary ensemble empirical mode decomposition, sample entropy, long short term memory network, gated recurrent unite

中图分类号:

TM614

杨国华, 祁鑫, 贾睿, 刘一峰, 蒙飞, 马鑫, 邢潇文. 基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测[J]. 中国电力, 2024, 57(2): 55-61.

Guohua YANG, Xin QI, Rui JIA, Yifeng LIU, Fei MENG, Xin MA, Xiaowen XING. Short-Term Wind Power Forecast Based on CNN&LSTM-GRU Model Integrated with CEEMD-SE Algorithm[J]. Electric Power, 2024, 57(2): 55-61.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202302098

https://www.electricpower.com.cn/CN/Y2024/V57/I2/55

图/表 8

图 1 LSTM网络结构

Fig.1 LSTM network structure

图 2 GRU网络结构

Fig.2 GRU network structure

图 3 CNN&LSTM-GRU预测模型结构

Fig.3 CNN&LSTM-GRU prediction model structure

图 4 预测流程

Fig.4 Flow chart of wind power forecast

表 1 IMF1-IMF10和RES的SE值

Table 1 SE values of IMF1-IMF10 and Res

分量	SE值	分量	SE值
IMF1	1.22372	IMF7	0.35957
IMF2	1.01075	IMF8	0.12358
IMF3	0.75592	IMF9	0.02324
IMF4	0.67636	IMF10	0.00304
IMF5	0.65487	RES	0.00046
IMF6	0.60424

图 5 CEEMD-SE分解后的各分量

Fig.5 Individual component after CEEMD-SE decomposition

表 2 各个模型预测结果对比

Table 2 Comparison of prediction results of various models

预测模型	RMSE/MW	MAE/MW	R²
PSO-SVR	2.505	1.947	0.928
LSTM	2.322	1.767	0.938
CNN-LSTM	2.198	1.656	0.944
CNN&LSTM-GRU	1.867	1.404	0.962

图 6 各模型预测结果曲线

Fig.6 Prediction result curve of each model

参考文献 25

1	向玲, 邓泽奇, 赵玥. 基于LPF-VMD和KELM的风速多步预测模型[J]. 电网技术, 2019, 43 (12): 4461- 4467.
	XIANG Ling, DENG Zeqi, ZHAO Yue. Multi-step wind speed prediction model based on LPF-VMD and KELM[J]. Power System Technology, 2019, 43 (12): 4461- 4467.
2	姜兆宇, 贾庆山, 管晓宏. 多时空尺度的风力发电预测方法综述[J]. 自动化学报, 2019, 45 (1): 51- 71.
	JIANG Zhaoyu, JIA Qingshan, GUAN Xiaohong. A review of multi-temporal-and-spatial-scale wind power forecasting method[J]. Acta Automatica Sinica, 2019, 45 (1): 51- 71.
3	王瑞, 陈泽坤, 逯静. 基于VMD和IBA-LSSVM的短期风电功率预测[J]. 河海大学学报(自然科学版), 2021, 49 (6): 575- 582.
	WANG Rui, CHEN Zekun, LU Jing. Short term prediction of wind power based on VMD and IBA-LSSVM[J]. Journal of Hohai University (Natural Sciences), 2021, 49 (6): 575- 582.
4	陈子含, 滕伟, 胥学峰, 等. 基于图卷积网络和风速差分拟合的中长期风功率预测[J]. 中国电力, 2023, 56 (10): 96- 105.
	CHEN Zihan, TENG Wei, XU Xuefeng, et al. Medium and long term wind power prediction based on graph convolutional network and wind velocity differential fitting[J]. Electric Power, 2023, 56 (10): 96- 105.
5	杜宇龙, 徐天奇, 李琰, 等. 基于自适应扩散核密度分布的风电功率预测误差分析研究[J]. 智慧电力, 2021, 49 (11): 51- 58.
	DU Yulong, XU Tianqi, LI Yan, et al. Analysis of wind power prediction error based on adaptive diffusion kernel density distribution[J]. Smart Power, 2021, 49 (11): 51- 58.
6	沙骏, 徐雨森, 刘冲冲, 等. 基于变分模态分解和分位数卷积-循环神经网络的短期风功率预测[J]. 中国电力, 2022, 55 (12): 61- 68.
	SHA Jun, XU Yusen, LIU Chongchong, et al. Short-term wind power prediction based on variational modal decomposition and quantile convolution-recurrent neural network[J]. Electric Power, 2022, 55 (12): 61- 68.
7	陈峰, 余轶, 徐敬友, 等. 基于Bayes-LSTM网络的风电出力预测方法[J]. 电力系统保护与控制, 2023, 51 (6): 170- 178.
	CHEN Feng, YU Yi, XU Jingyou, et al. Prediction method of wind power output based on a Bayes-LSTM network[J]. Power System Protection and Control, 2023, 51 (6): 170- 178.
8	WANG Y, ZHANG N, KANG C Q, et al. An efficient approach to power system uncertainty analysis with high-dimensional dependencies[J]. IEEE Transactions on Power Systems, 2018, 33 (3): 2984- 2994. DOI
9	牛东晓, 纪会争. 风电功率物理预测模型引入误差量化分析方法[J]. 电力系统自动化, 2020, 44 (8): 57- 65.
	NIU Dongxiao, JI Huizheng. Quantitative analysis method for errors introduced by physical prediction model of wind power[J]. Automation of Electric Power Systems, 2020, 44 (8): 57- 65.
10	杨茂, 黄宾阳. 基于灰色缓冲算子-卡尔曼滤波双修正的风电功率实时预测研究[J]. 可再生能源, 2017, 35 (1): 101- 109.
	YANG Mao, HUANG Binyang. Wind power real-time prediction based on grey buffer operator-Kalman filtering dual correction research[J]. Renewable Energy Resources, 2017, 35 (1): 101- 109.
11	丁藤, 冯冬涵, 林晓凡, 等. 基于修正后ARIMA-GARCH模型的超短期风速预测[J]. 电网技术, 2017, 41 (6): 1808- 1814.
	DING Teng, FENG Donghan, LIN Xiaofan, et al. Ultra-short-term wind speed forecasting based on improved ARIMA-GARCH model[J]. Power System Technology, 2017, 41 (6): 1808- 1814.
12	杨茂, 黄宾阳, 江博. 基于概率分布量化指标和灰色关联决策的风电功率实时预测研究[J]. 中国电机工程学报, 2017, 37 (24): 7099- 7107, 7424.
	YANG Mao, HUANG Binyang, JIANG Bo. Real-time wind power prediction based on probability distribution and gray relational decision-making[J]. Proceedings of the CSEE, 2017, 37 (24): 7099- 7107, 7424.
13	杨德友, 高子昂, 李音璇. 基于双变量经验模态分解和最小二乘支持向量机的风电功率区间预测[J]. 电力建设, 2019, 40 (5): 118- 127.
	YANG Deyou, GAO Ziang, LI Yinxuan. Interval prediction of wind power based on bivariate empirical mode decomposition and least squares support vector machine[J]. Electric Power Construction, 2019, 40 (5): 118- 127.
14	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. DOI
15	李俊卿, 李秋佳. 基于Kriging和长短期记忆网络的风电功率预测方法[J]. 太阳能学报, 2020, 41 (11): 241- 247.
	LI Junqing, LI Qiujia. Wind power prediction method based on Kriging and LSTM network[J]. Acta Energiae Solaris Sinica, 2020, 41 (11): 241- 247.
16	王依宁, 解大, 王西田, 等. 基于PCA-LSTM模型的风电机网相互作用预测[J]. 中国电机工程学报, 2019, 39 (14): 4070- 4081.
	WANG Yining, XIE Da, WANG Xitian, et al. Prediction of interaction between grid and wind farms based on PCA-LSTM model[J]. Proceedings of the CSEE, 2019, 39 (14): 4070- 4081.
17	牛哲文, 余泽远, 李波, 等. 基于深度门控循环单元神经网络的短期风功率预测模型[J]. 电力自动化设备, 2018, 38 (5): 36- 42.
	NIU Zhewen, YU Zeyuan, LI Bo, et al. Short-term wind power forecasting model based on deep gated recurrent unit neural network[J]. Electric Power Automation Equipment, 2018, 38 (5): 36- 42.
18	肖迁, 李文华, 李志刚, 等. 基于改进的小波-BP神经网络的风速和风电功率预测[J]. 电力系统保护与控制, 2014, 42 (15): 80- 86.
	XIAO Qian, LI Wenhua, LI Zhigang, et al. Wind speed and power prediction based on improved wavelet-BP neural network[J]. Power System Protection and Control, 2014, 42 (15): 80- 86.
19	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 Jixuan, DENG Bin, WANG Jiang. 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.
20	HE Y Y, WANG Y. Short-term wind power prediction based on EEMD–LASSO–QRNN model[J]. Applied Soft Computing, 2021, 105, 107288. DOI
21	周小麟, 童晓阳. 基于CEEMD-SBO-LSSVR的超短期风电功率组合预测[J]. 电网技术, 2021, 45 (3): 855- 864.
	ZHOU Xiaolin, TONG Xiaoyang. Ultra-short-term wind power combined prediction based on CEEMD-SBO-LSSVR[J]. Power System Technology, 2021, 45 (3): 855- 864.
22	LI X Y, DAI K W, WANG Z P, et al. Lithium-ion batteries fault diagnostic for electric vehicles using sample entropy analysis method[J]. Journal of Energy Storage, 2020, 27, 101121. DOI
23	曾亮, 狄飞超, 兰欣, 等. 基于CEEMD-CNN-BiGRU-RF模型的短期风电功率预测[J]. 可再生能源, 2022, 40 (2): 190- 195.
	ZENG Liang, DI Feichao, LAN Xin, et al. Short-term wind power prediction based on CEEMD-CNN-BiGRU-RF model[J]. Renewable Energy Resources, 2022, 40 (2): 190- 195.
24	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.
	JIA Rui, YANG Guohua, ZHENG Haofeng, et al. Combined wind power prediction method based on CNN-LSTM & GRU with adaptive weights[J]. Electric Power, 2022, 55 (5): 47- 56.
25	KISVARI A, LIN Z, LIU X L. Wind power forecasting–A data-driven method along with gated recurrent neural network[J]. Renewable Energy, 2021, 163, 1895- 1909. DOI

[1]	陶磊, 罗萍萍, 林济铿. 基于深度学习的直流微电网虚假数据注入攻击二阶段检测方法[J]. 中国电力, 2024, 57(9): 11-19.
[2]	吴军英, 路欣, 刘宏, 张彬, 柴守亮, 刘蕴春, 王佳楠. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140.
[3]	朱沐雨, 马宏忠, 郭鹏宇, 宣文婧. 典型调峰/调频工况下储能电池组荷电状态估计[J]. 中国电力, 2024, 57(6): 18-26.
[4]	邵必林, 纪丹阳. 基于VMD-SE的电力负荷分量的多特征短期预测[J]. 中国电力, 2024, 57(4): 162-170.
[5]	高岩, 吴汉斌, 张纪欣, 张华铭, 张沛. 基于组合深度学习的光伏功率日前概率预测模型[J]. 中国电力, 2024, 57(4): 100-110.
[6]	陈铁, 张治藩, 李咸善, 陈一夫, 李鸿鑫. 基于混合模态分解和LSTM-CNN的变压器油中溶解气体浓度预测[J]. 中国电力, 2023, 56(1): 132-141.
[7]	冯裕祺, 李辉, 李利娟, 周彦博, 谭貌, 彭寒梅. 基于CNN-GRU的光伏电站电压轨迹预测[J]. 中国电力, 2022, 55(7): 163-171.
[8]	贾睿, 杨国华, 郑豪丰, 张鸿皓, 柳萱, 郁航. 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.
[9]	郑豪丰, 杨国华, 康文军, 刘志远, 刘世涛, 伍弘, 张鸿皓. 基于多负荷特征和TCN-GRU神经网络的负荷预测[J]. 中国电力, 2022, 55(11): 142-148.
[10]	杨胡萍, 余阳, 汪超, 李向军, 胡奕涛, 饶楚楚. 基于VMD-CNN-BIGRU的电力系统短期负荷预测[J]. 中国电力, 2022, 55(10): 71-76.
[11]	曾囿钧, 肖先勇, 徐方维, 郑林. 基于CNN-BiGRU-NN模型的短期负荷预测方法[J]. 中国电力, 2021, 54(9): 17-23.
[12]	赵会茹, 赵一航, 郭森. 基于互补集合经验模态分解和长短期记忆神经网络的短期电力负荷预测[J]. 中国电力, 2020, 53(6): 48-55.