基于自适应权重的CNN-LSTM&GRU组合风电功率预测方法

doi:10.11930/j.issn.1004-9649.202104023

中国电力 ›› 2022, Vol. 55 ›› Issue (5): 47-56,110.DOI: 10.11930/j.issn.1004-9649.202104023

基于自适应权重的CNN-LSTM&GRU组合风电功率预测方法

贾睿¹, 杨国华^1,2, 郑豪丰¹, 张鸿皓¹, 柳萱¹, 郁航¹

1. 宁夏大学物理与电子电气工程学院，宁夏银川 750021;
2. 宁夏电力能源安全重点实验室，宁夏银川 750004

收稿日期:2021-04-25 修回日期:2022-02-25 出版日期:2022-05-28 发布日期:2022-05-18
作者简介:贾睿（1997—），男，硕士研究生，从事电力系统风电功率预测技术研究，E-mail：3116044296@qq.com;杨国华（1972—），男，通信作者，教授，从事新能源电力系统自动化技术研究，E-mail：ygh@nxu.edu.cn
基金资助:
国家自然科学基金资助项目（71263043）；宁夏回族自治区自然科学基金资助项目（2021AAC03062）

Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights

JIA Rui¹, YANG Guohua^1,2, ZHENG Haofeng¹, ZHANG Honghao¹, LIU Xuan¹, YU Hang¹

1. School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, China;
2. Ningxia Key Laboratory of Electrical Energy Security, Yinchuan 750004, China

Received:2021-04-25 Revised:2022-02-25 Online:2022-05-28 Published:2022-05-18
Supported by:
This work is supported by National Natural Science Foundation of China (No.71263043), Natural Science Foundation of Ningxia Hui Autonomous Region (No.2021AAC03062).

摘要/Abstract

摘要： 准确预测风电功率可以提高电网运行的安全性和可靠性。为进一步提高短期风电功率预测精度，针对目前单一模型难以获得最优预测结果的问题，提出一种CNN-LSTM&GRU多模型组合短期风电功率预测方法。首先，利用卷积神经网络（convolutional neural network，CNN）提取数据局部特征，并结合长短期记忆（long short term memory，LSTM）网络构造出融合局部特征预提取模块的CNN-LSTM网络结构；然后，将其与门控循环单元（gated recurrent unit，GRU）网络并行，并通过自适应权重学习模块为CNN-LSTM模块和GRU模块的输出选择最佳权重，构建出CNN-LSTM&GRU组合的短期预测模型。最后，对中国西北某风电场的出力进行预测研究，结果表明：所提模型与单一模型或其他组合模型相比，指标误差更小，预测精度更高。

关键词: 短期风电功率预测, CNN-LSTM, GRU, 组合预测, 自适应权重学习

Abstract: Accurate wind power prediction can improve the safety and reliability of grid operation. To further enhance the accuracy of short-term wind power prediction, this paper proposes a CNN-LSTM&GRU multi-model combined prediction method considering the difficulty in obtaining optimal prediction results with a single model. Firstly, a convolutional neural network (CNN) is used to extract local features of data and combined with a long short-term memory (LSTM) network to construct a CNN-LSTM network structure that incorporates local feature pre-extraction modules. Then, the CNN-LSTM network is paralleled with a gated recurrent unit (GRU) network. An adaptive weight learning module is employed to select the best weights for the outputs of the CNN-LSTM module and the GRU module. In this way, the paper constructs a combined short-term prediction model based on CNN-LSTM&GRU. Finally, the model is applied to the power prediction of a wind farm in northwestern China. The experimental results show that the proposed model has a smaller mean absolute error (MAE), a smaller root mean square error (RMSE), and higher prediction accuracy than single models and other combined models.

Key words: short-term wind power prediction, CNN-LSTM, GRU, combined prediction, adaptive weight learning

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.

JIA Rui, YANG Guohua, ZHENG Haofeng, ZHANG Honghao, LIU Xuan, YU Hang. Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights[J]. Electric Power, 2022, 55(5): 47-56,110.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202104023

https://www.electricpower.com.cn/CN/Y2022/V55/I5/47

参考文献

[1] 王恰. 2020—2060年中国风电装机规模及其CO₂减排预测[J]. 生态经济, 2021, 37(7): 13–21
WANG Qia. Forecast of China's wind power installed capacity and corresponding CO₂ reduction from 2020 to 2060[J]. Ecological Economy, 2021, 37(7): 13–21
[2] 黄鹏翔, 周云海, 徐飞, 等. 基于灵活性裕度的含风电电力系统源荷储协调滚动调度[J]. 中国电力, 2020, 53(11): 78–88
HUANG Pengxiang, ZHOU Yunhai, XU Fei, et al. Source-load-storage coordinated rolling dispatch for wind power integrated power system based on flexibility margin[J]. Electric Power, 2020, 53(11): 78–88
[3] HAGHI H V, LOTFIFARD S, QU Z H. Multivariate predictive analytics of wind power data for robust control of energy storage[J]. IEEE Transactions on Industrial Informatics, 2016, 12(4): 1350–1360.
[4] 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.
[5] YANG M, CHEN X X, DU J, et al. Ultra-short-term multi-step wind power prediction based on improved EMD and reconstruction method using Run-length analysis[J]. IEEE Access, 2018, 6: 31908–31917.
[6] 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
[7] 陈昊, 张建忠, 许超, 等. 基于多重离群点平滑转换自回归模型的短期风电功率预测[J]. 电力系统保护与控制, 2019, 47(1): 73–79
CHEN Hao, ZHANG Jianzhong, XU Chao, et al. Short-term wind power forecast based on MOSTAR model[J]. Power System Protection and Control, 2019, 47(1): 73–79
[8] 崔明建, 孙元章, 柯德平. 基于原子稀疏分解和BP神经网络的风电功率爬坡事件预测[J]. 电力系统自动化, 2014, 38(12): 6–11,26
CUI Mingjian, SUN Yuanzhang, KE Deping. Wind power ramp events forecasting based on atomic sparse decomposition and BP neural networks[J]. Automation of Electric Power Systems, 2014, 38(12): 6–11,26
[9] ZENDEHBOUDI A, BASEER M A, SAIDUR R. Application of support vector machine models for forecasting solar and wind energy resources: a review[J]. Journal of Cleaner Production, 2018, 199: 272–285.
[10] 赵睿智, 丁云飞. 基于MEEMD-KELM的短期风电功率预测[J]. 电测与仪表, 2020, 57(21): 92–98
ZHAO Ruizhi, DING Yunfei. Short-term prediction of wind power based on MEEMD-KELM[J]. Electrical Measurement & Instrumentation, 2020, 57(21): 92–98
[11] 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.
[12] 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
[13] HE Y Y, WANG Y. Short-term wind power prediction based on EEMD-LASSO-QRNN model[J]. Applied Soft Computing, 2021, 105: 107288.
[14] 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
[15] 曹有为, 闫双红, 刘海涛, 等. 基于降噪时序深度学习网络的风电功率短期预测方法[J]. 电力系统及其自动化学报, 2020, 32(1): 145–150
CAO Youwei, YAN Shuanghong, LIU Haitao, et al. Short-term wind power forecasting method based on noise-reduction time-series deep learning network[J]. Proceedings of the CSU-EPSA, 2020, 32(1): 145–150
[16] 庄家懿, 杨国华, 郑豪丰, 等. 基于多模型融合的CNN-LSTM-XGBoost短期电力负荷预测方法[J]. 中国电力, 2021, 54(5): 46–55
ZHUANG Jiayi, YANG Guohua, ZHENG Haofeng, et al. Short-term load forecasting method based on multi-model fusion using CNN-LSTM-XGBoost[J]. Electric Power, 2021, 54(5): 46–55
[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] R?DL S, MARSCHITZ I, MACHE C J, et al. One-year safe use of the Prismaflex HF20^? disposable set in infants in 220 renal replacement treatment sessions[J]. Intensive Care Medicine, 2011, 37(5): 884–885.
[19] 滕伟, 黄乙珂, 吴仕明, 等. 基于XGBoost与LSTM的风力发电机绕组温度预测[J]. 中国电力, 2021, 54(6): 95–103
TENG Wei, HUANG Yike, WU Shiming, et al. Wind turbine generator winding temperature prediction based on XGBoost and LSTM[J]. Electric Power, 2021, 54(6): 95–103
[20] 王增平, 赵兵, 纪维佳, 等. 基于GRU-NN模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(5): 53–58
WANG Zengping, ZHAO Bing, JI Weijia, et al. Short-term load forecasting method based on GRU-NN model[J]. Automation of Electric Power Systems, 2019, 43(5): 53–58
[21] 张沛. 基于神经网络的风电功率短期与超短期预测[D]. 济南: 山东大学, 2020.
ZHANG Pei. Short-term and ultra-short-term forecasting of wind power based on neural network[D]. Jinan: Shandong University, 2020.
[22] 刘芳. 基于改进BP神经网络的风电功率预测方法研究[D]. 杭州: 浙江大学, 2020.
LIU Fang. Wind power forecasting based on improved BP neural network[D]. Hangzhou: Zhejiang University, 2020.
[23] 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797–3802
ZHU Qiaomu, LI Hongyi, WANG Ziqi, et al. Short-term wind power forecasting based on LSTM[J]. Power System Technology, 2017, 41(12): 3797–3802
[24] 马嘉翼. 基于动态规律建模的风电功率预测方法研究[D]. 济南: 山东大学, 2019.
MA Jiayi. Research of wind power forecast based on empirical dynamic modeling[D]. Jinan: Shandong University, 2019.
[25] LI L L, CEN Z Y, TSENG M L, et al. Improving short-term wind power prediction using hybrid improved cuckoo search arithmetic - Support vector regression machine[J]. Journal of Cleaner Production, 2021, 279: 123739.
[26] 刘兴, 王艳, 纪志成. 基于随机森林的风电功率短期预测方法[J]. 系统仿真学报, 2021, 33(11): 2606–2614
LIU Xing, WANG Yan, JI Zhicheng. Short-term wind power prediction method based on random forest[J]. Journal of System Simulation, 2021, 33(11): 2606–2614

基于自适应权重的CNN-LSTM&GRU组合风电功率预测方法

Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

[1]	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.
[2]	陈庆斌, 杨耿煌, 耿丽清, 苏娟, 孙京生. 基于相似日选取和数据重构的短期光伏功率组合预测方法[J]. 中国电力, 2024, 57(12): 71-81.
[3]	龙禹, 王小英, 周琪, 姜楠, 罗欣. 考虑不同发展情境的江苏省中长期电力需求预测[J]. 中国电力, 2016, 49(7): 72-76.
[4]	杨锡运，任杰，肖运启. 基于粗糙集的光伏输出功率组合预测模型[J]. 中国电力, 2016, 49(12): 133-138.
[5]	陈武，肖先勇. 短期母线负荷优性组合预测方法及其在成都电网中的应用[J]. 中国电力, 2015, 48(8): 97-103.

模态框（Modal）标题

基于自适应权重的CNN-LSTM&GRU组合风电功率预测方法

Combined Wind Power Prediction Method Based on CNN-LSTM&GRU with Adaptive Weights

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics