基于CEEMDAN-GRA-PCC-ATCN的短期风电功率预测

doi:10.6040/j.issn.1672-3961.0.2022.242

摘要/Abstract

摘要：

为提高风电功率的预测精度, 提出基于数据分解和输入变量选择的短期风电功率预测方法。利用自适应噪声完备集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)对原始风电功率和风速数据进行分解, 平缓数据波动以提取内部隐藏信息。通过排列熵算法(permutation entropy, PE)将风电功率分量简化重构以降低模型复杂度。为提升输入变量与风电功率之间的关联程度, 剔除冗杂信息, 降低输入数据维度, 结合Pearson相关系数(Pearson correlation coefficient, PCC)和灰色关联分析(grey relation analysis, GRA)对各风电重构功率分量的输入变量进行选择。最后利用基于注意力的时序卷积网络(attention-based temporal convolutional network, ATCN)对各重构功率分量进行预测, 将各预测值叠加得到最终结果。试验结果表明, 基于CEEMDAN-GRA-PCC-ATCN的短期风电功率预测方法能够提取更多风电数据内部的关键信息, 降低输入数据的维度, 强化输入变量与风电功率之间的关联性, 有效提高预测精度。

关键词: 风电功率预测, 时序卷积网络, 自适应噪声完备集成经验模态分解, 灰色关联分析, Pearson相关系数, 注意力机制

Abstract:

To improve the accuracy of wind power prediction, a short-term wind power prediction method based on data decomposition and input variable selection was proposed. The complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was used to decompose the original wind power and wind speed data, and smooth data fluctuation to extract internal hidden information. The wind power components were simplified and reconstructed by permutation entropy (PE) algorithm to reduce the model complexity. To enhance the correlation between the input variables and wind power, eliminate redundant information and reduce the dimensionality of the input data, the Pearson correlation coefficient (PCC) and gray relation analysis (GRA) were combined to select the input variables for each reconstructed wind power component. The attention-based temporal convolutional network was used to predict the reconstructed power components, and the predicted values were superimposed to obtain the final result. The experimental results showed that the short-term wind power prediction method based on CEEMDAN-GRA-PCC-ATCN could extract more internal key information of wind power data, reduce the dimension of input data, strengthen the correlation between input variables and wind power, and effectively improve the prediction accuracy.

Key words: wind power prediction, TCN, CEEMDAN, grey relation analysis, Pearson correlation coefficient, attention mechanism

中图分类号:

TM614

武新章,梁祥宇,朱虹谕,张冬冬. 基于CEEMDAN-GRA-PCC-ATCN的短期风电功率预测[J]. 山东大学学报 (工学版), 2022, 52(6): 146-156.

Xinzhang WU,Xiangyu LIANG,Hongyu ZHU,Dongdong ZHANG. Short-term wind power prediction based on CEEMDAN-GRA-PCC-ATCN[J]. Journal of Shandong University(Engineering Science), 2022, 52(6): 146-156.

图/表 12

图1

图2

图3

图4

表1

表2

图5

图6

图7

表3

图8

表4

参考文献 22

1	WISER R , RAND J , SEEL J , et al. Expert elicitation survey predicts 37% to 49% declines in wind energy costsby 2050[J]. Nature Energy, 2021, 6 (5): 555- 565. doi: 10.1038/s41560-021-00810-z
2	梁志祥, 刘晓明, 牟颖, 等. 基于深度学习的新能源爬坡事件预测方法[J]. 山东大学学报(工学版), 2019, 49 (5): 24- 28.
	LIANG Zhixiang , LIU Xiaoming , MU Ying , et al. Prediction method of wind power and PV ramp event based on deep learning[J]. Journal of Shandong University(Engineering Science), 2019, 49 (5): 24- 28.
3	王飞, 徐健, 李伟, 等. 基于分布式储能系统的风储滚动优化调度方法[J]. 山东大学学报(工学版), 2017, 47 (6): 89- 94.
	WANG Fei , XU Jian , LI Wei , et al. Rolling optimal dispatch method of wind power based on distributed energy storage system[J]. Journal of Shandong University(Engineering Science), 2017, 47 (6): 89- 94.
4	王飞, 宋士瞻, 曹永吉, 等. 基于连续小波变换的风光发电资源多尺度评估[J]. 山东大学学报(工学版), 2018, 48 (5): 124- 130.
	WANG Fei , SONG Shizhan , CAO Yongji , et al. Multi-scale assessment of wind-solar generation resources basedon continuous wavelet transform[J]. Journal of Shandong University(Engineering Science), 2018, 48 (5): 124- 130.
5	DONG Xiaochong , SUN Yingyun , LI Ye , et al. Spatio-temporal convolutional network based power forecasting of multiple wind farms[J]. Journal of Modern Power Systems and Clean Energy, 2022, 10 (2): 388- 398. doi: 10.35833/MPCE.2020.000849
6	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.
	HANG Zifen , JING Qianming , ZHANG Yankai , et al. Review of wind power forecasting methods and new trends[J]. Power System Protection and Control, 2019, 47 (24): 178- 187.
7	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- 67.
	NIU Dongxiao , JI Huizheng . The method of error quantification analysis is introduced into the physical predictionmodel of wind power[J]. Automation of Electric Power System, 2020, 44 (8): 57- 67.
8	郑紫宸, 符杨, 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- 1260.
	ZHENG Zichen , FU Yang , SHI Shuai , et al. Offshore wind power forecasting considering meteorological similarity and NWP correction[J]. Power System Technology, 2019, 43 (4): 1253- 1260.
9	宋家康, 彭勇刚, 蔡宏达, 等. 考虑多位置NWP和非典型特征的短期风电功率预测研究[J]. 电网技术, 2018, 42 (10): 3234- 3242.
	SONG Jiakang , PENG Yonggang , CAI Hongda , et al. Study on short-term wind power forecasting considering multi-location NWP and atypical characteristics[J]. Power System Technology, 2018, 42 (10): 3234- 3242.
10	LI Menglin , YANG Ming , YU Yixiao , et al. A wind speed correction method based on modified hidden markov model for enhancing wind power forecast[J]. IEEE Transactions on Industry Applications, 2022, 58 (1): 656- 666.
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 prediction based on modified ARIMA-GARCH model[J]. Power System Technology, 2017, 41 (6): 1808- 1814.
12	YANG Jingxian . A novel short-term multi-input-multi-output prediction model of wind speed and wind power with LSSVM based on improved ant colony algorithm optimization[J]. Cluster Computing, 2019, 22 (2): 3293- 3300.
13	ZHANG Hao , LIU Yongqian , YAN Jie , et al. Improved deep mixture density network for regional wind power probabilistic forecasting[J]. IEEE Transactions on Power Systems, 2020, 35 (4): 2549- 2560.
14	麻常辉, 冯江霞, 蒋哲, 等. 基于时间序列和神经网络法的风电功率预测[J]. 山东大学学报(工学版), 2014, 44 (1): 85- 89.
	MA Changhui , FENG Jiangxia , JIANG Zhe , et al. Wind power prediction based on times-series and BP-ANN[J]. Journal of Shandong University (Engineering Science), 2014, 44 (1): 85- 89.
15	YU Yixiao , YANG Ming , HAN Xueshan , et al. A regional wind power probabilistic forecast method based on deep quantile regression[J]. IEEE Transactions on Industry Applications, 2021, 57 (5): 4420- 4427.
16	邓亚平, 段建东, 贾颢, 等. 基于布谷鸟算法优化独立循环神经网络深度学习的超短期风电功率预测[J]. 电网与清洁能源, 2021, 37 (9): 18- 26.
	DENG Yaping , DUAN Jiandong , JIA Hao , et al. Ultra-short-term wind power prediction based on deep learning with independent recurrent neural network via cuckoo algorithm optimized[J]. Power System and Clean Energy, 2021, 37 (9): 18- 26.
17	王晓东, 鞠邦国, 刘颖明, 等. 基于QR-NFGLSTM与核密度估计的风电功率概率预测[J]. 太阳能学报, 2022, 43 (2): 479- 485.
	WANG Xiaodong , JU Bangguo , LIU Yingming , et al. Probability prediction of wind power based on QR-NFGLSTM and kernel density estimation[J]. Acta Energiae Solaris Sinica, 2022, 43 (2): 479- 485.
18	康文豪, 徐天奇, 王阳光, 等. 基于CEEMDAN-精细复合多尺度熵和Stacking集成学习的短期风电功率预测[J]. 水利水电技术, 2022, 53 (2): 163- 172.
	KANG Wenhao , XU Tianqi , WANG Yangguang , et al. CEEMDAN-refined composite multiscale entropy and stacking ensemble learning-based short-term wind power prediction[J]. Water Resources and Hydropower Engineering, 2022, 53 (2): 163- 172.
19	李福东, 曾旭华, 魏梅芳, 等. 基于聚类分析和混合自适应进化算法的短期风电功率预测[J]. 电力系统保护与控制, 2020, 48 (22): 3213- 3220.
	LI Fudong , ZENG Xuhua , WEI Meifang , et al. Short-term wind power forecasting based on cluster analysis andahybrid evolutionary-adaptive methodology[J]. Power System Protection and Control, 2020, 48 (22): 3213- 3220.
20	杨锡运, 马雪, 张洋, 等. 基于EMD与加权马尔可夫链QR法的风电功率区间预测[J]. 太阳能学报, 2020, 41 (2): 66- 72.
	YANG Xiyun , MA Xue , ZHANG Yang , et al. Probabilistic intervals forecasting of wind power based on EMD weighted Markov chain QR method[J]. Acta Energiae Solaris Sinica, 2020, 41 (2): 66- 72.
21	杨锡运, 康宁, 杨雨薇, 等. 基于EEMD的SOA-KELM风电功率概率性短期区间预测[J]. 动力工程学报, 2019, 39 (11): 926- 933.
	YANG Xiyun , KANG Ning , YANG Yuwei , et al. Probabilistic short-term interval forecast of wind power based on EEMD and SOA-KELM model[J]. Journal of Chinese Society of Power Engineering, 2019, 39 (11): 926- 933.
22	廖雪超, 伍杰平, 陈才圣, 等. 结合注意力机制与LSTM的短期风电功率预测模型[J]. 计算机工程, 2022, 48 (9): 286- 297.
	LIAO Xueychao , WU Jieping , CHEN Caisheng , et al. Short-term wind power prediction model combining attention mechanism and LSTM[J]. Computer Engineering, 2022, 48 (9): 286- 297.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

风电功率分量	排列熵值
F₁	0.986
F₂	0.853
F₃	0.654
F₄	0.545
F₅	0.467
F₆	0.424
F₇	0.402
F₈	0.395
Q	0.389

重构功率分量	原始功率分量
I₁	F₁
I₂	F₂
I₃	F₃
I₄	F₄
I₅	F₅+F₆+F₇+F₈+Q

重构功率分量	风速分量
I₁	S₁
I₂	S₂, S₃
I₃	S₃, S₄
I₄	S₃, S₄
I₅	S₆, S₇, S₈, Y

预测模型	E_RMSE/ MW	E_MAPE/ %	E_MAE/ MW	R²
LSTM	1.641	11.23	1.219	0.816
TCN	1.289	10.81	1.152	0.887
ATCN	1.179	9.18	1.023	0.905
EMD-GRA-PCC-ATCN	0.964	8.36	0.885	0.937
CEEMDAN-ATCN	0.929	6.61	0.720	0.941
CEEMDAN-GRA-PCC-ATCN	0.891	6.01	0.659	0.946

[1]	侯月武,刘兆英,张婷,李玉鑑,孙长明. 基于改进的DUNet遥感图像道路提取[J]. 山东大学学报 (工学版), 2022, 52(4): 29-37.
[2]	梁晔,马楠,刘宏哲. 图像依赖的显著图融合方法[J]. 山东大学学报 (工学版), 2021, 51(4): 1-7.
[3]	张沁洋,李旭,姚春龙,李长吾. 结合句法依存信息的方面级情感分类[J]. 山东大学学报 (工学版), 2021, 51(2): 83-89.
[4]	张俊三,程俏俏,万瑶,朱杰,张世栋. MIRGAN: 一种基于GAN的医学影像报告生成模型[J]. 山东大学学报 (工学版), 2021, 51(2): 9-18.
[5]	张月芳,邓红霞,呼春香,钱冠宇,李海芳. 融合残差块注意力机制和生成对抗网络的海马体分割[J]. 山东大学学报 (工学版), 2020, 50(6): 76-81.
[6]	廖南星,周世斌,张国鹏,程德强. 基于类激活映射-注意力机制的图像描述方法[J]. 山东大学学报 (工学版), 2020, 50(4): 28-34.
[7]	蔡国永,贺歆灏,储阳阳. 基于空间注意力和卷积神经网络的视觉情感分析[J]. 山东大学学报 (工学版), 2020, 50(4): 8-13.