Power regression prediction for wind turbines in multi-meteorological scenarios based on CEEMDAN-CNN-LSTM integration

doi:10.3969/j.issn.2097-0706.2025.09.005

Abstract

Abstract:

To enhance the prediction accuracy of wind turbine output power under diverse meteorological conditions， a power regression prediction method based on complete ensemble empirical mode decomposition with adaptive noise （CEEMDAN）， convolutional neural network（CNN）， and long short-term memory（LSTM） network was proposed. The CEEMDAN algorithm was employed to decompose the original wind power data into intrinsic mode functions（IMFs） and a residual（RES）. Five meteorological factors， including wind speed， were incorporated， and CNN was applied to extract features. LSTM networks were used to perform regression prediction for each subsequence. The prediction results were then superimposed and reconstructed to obtain the final predicted values. Prediction accuracy was evaluated using mean absolute error and root mean square error. Simulation results indicated that the CEEMDAN-CNN-LSTM model significantly outperformed the random forest-LSTM（RF-LSTM） and support vector machine-LSTM（SVM-LSTM） models in prediction accuracy， with notably improved performance and generalization capability under complex meteorological conditions and extreme weather events.

Key words: wind turbine, power prediction, meteorological factors, extreme weather, complete ensemble empirical mode decomposition with adaptive noise, convolutional neural network, long short-term memory network, intrinsic mode function

CLC Number:

TK89

HUANGFU Chenmeng, RUAN Hebin, XU Junjun. Power regression prediction for wind turbines in multi-meteorological scenarios based on CEEMDAN-CNN-LSTM integration[J]. Integrated Intelligent Energy, 2025, 47(9): 38-50.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Table 1

Experimental results of CEEMDAN-CNN-LSTM with different parameter settings

LSTM隐藏层数	单元数	$ε M A E$ /kW	$ε R M S E$ /kW	运行时间/s
1	20	9.647	13.527	29
2	20	10.871	14.838	30
3	20	16.469	22.744	42
1	35	9.616	13.736	57
1	65	8.500	11.340	106
1	100	8.153	11.145	158
1	150	19.641	23.569	207

Table 1

Table 2

Comparison of prediction performance evaluation metrics across models with consistent LSTM parameters

模型	$ε M A E$ /kW	$ε R M S E$ /kW	运行时间/s
LSTM	18.430	26.814	46
CNN-LSTM	15.193	23.671	51
CEEMDAN-CNN-LSTM	8.153	11.145	158

Table 2

Fig.6

Table 3

Comparison of prediction performance evaluation metrics for different models

模型	$ε M A E$ /kW	$ε R M S E$ /kW	运行时间/s
RF-LSTM	19.851	28.452	104
SVM-LSTM	17.521	23.671	109
VMD-GRU	20.163	26.779	116
TCN-Wpsformer	59.319	75.602	87
CEEMDAN-CNN-LSTM	8.153	11.145	158

Table 3

Table 4

Fig.7

Table 5

Prediction performance evaluation metrics under different meteorological conditions

聚类	$ε M A E$ /kW	$ε R M S E$ /kW
1	16.462 01	20.340 26
2	13.911 06	19.213 95
3	22.675 20	25.793 31

Table 5

Fig.8

Table 6

Prediction performance evaluation metrics under different extreme weather events

极端天气	模型	样本数	$ε M A E$ /kW	$ε R M S E$ /kW
大风	CEEMDAN-CNN-LSTM	1 190	14.750	17.595
	RF-LSTM	1 190	25.148	30.055
	SVM-LSTM	1 190	25.834	30.642
	VDM-GRU	1 190	41.660	49.205
	TCN-Wpsformer	1 190	36.291	44.831
高温	CEEMDAN-CNN-LSTM	108	5.654	7.011
	RF-LSTM	108	8.422	10.204
	SVM-LSTM	108	8.802	11.386
	VDM-GRU	108	10.351	13.247
	TCN-Wpsformer	108	12.593	12.594
低温	CEEMDAN-CNN-LSTM	8 564	10.683	14.011
	RF-LSTM	8 564	14.669	19.307
	SVM-LSTM	8 564	13.178	17.087
	VDM-GRU	8 564	20.781	25.319
	TCN-Wpsformer	8 564	22.375	27.645
寒潮	CEEMDAN-CNN-LSTM	87	14.133	17.956
	RF-LSTM	87	19.661	25.506
	SVM-LSTM	87	15.770	21.544
	VDM-GRU	87	14.749	19.055
	TCN-Wpsformer	87	59.889	69.342

Table 6

References 35

[1]	郑李梦千, 朱利鹏, 文唯嘉, 等. 基于多重相关性学习的风电场SCADA数据修复及其功率预测应用[J]. 电力自动化设备, 2025, 45(3): 78-85.
	ZHENG Limengqian, ZHU Lipeng, WEN Weijia, et al. Multiple correlation learning-based wind farm SCADA data correction and its application in wind power prediction[J]. Electric Power Automation Equipment, 2025, 45(3): 78-85.
[2]	臧海祥, 李叶阳, 张越, 等. 基于组合分解和横向联邦学习的分布式超短期风电功率预测[J]. 电力自动化设备, 2025, 45(4): 45-52.
	ZANG Haixiang, LI Yeyang, ZHANG Yue, et al. Distributed ultra-short term wind power prediction based on combinatorial decomposition and horizontal federated learning[J]. Electric Power Automation Equipment, 2025, 45(4): 45-52.
[3]	柴荣繁, 王钊, 王勃, 等. 东北冰冻灾害演变特征及其对风电运行的影响[J/OL]. 电力系统自动化, 2024: 1-11 (2024-11-26)[2025-06-01]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=DLXT20241125001&dbname=CJFD&dbcode=CJFQ.
	CHAI Rongfan, WANG Zhao, WANG Bo, et al. Evolution characteristic of freezing disaster in Northeast China and its impact on wind power operation[J/OL]. Automation of Electric Power Systems, 2024: 1-11 (2024-11-26) [2025-06-01]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=DLXT20241125001&dbname=CJFD&dbcode=CJFQ.
[4]	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.
[5]	迟永宁, 梁伟, 张占奎, 等. 大规模海上风电输电与并网关键技术研究综述[J]. 中国电机工程学报, 2016, 36(14): 3758-3771.
	CHI Yongning, LIANG Wei, ZHANG Zhankui, et al. An overview on key technologies regarding power transmission and grid integration of large scale offshore wind power[J]. Proceedings of the CSEE, 2016, 36(14): 3758-3771.
[6]	徐武, 范鑫豪, 沈智方, 等. 多尺度特征提取的Transformer短期风电功率预测[J]. 太阳能学报, 2025, 46(2): 640-648.
	XU Wu, FAN Xinhao, SHEN Zhifang, et al. Short-term wind power prediction using Transformer with multi-scale feature extraction[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 640-648.
[7]	苏向敬, 程子凡, 聂良钊, 等. 基于AGCN-LSTM模型的海上风电场功率概率预测[J]. 电力系统自动化, 2024, 48(22): 140-149.
	SU Xiangjing, CHENG Zifan, NIE Liangzhao, et al. Power probability prediction for offshore wind farm based on AGCN-LSTM model[J]. Automation of Electric Power Systems, 2024, 48(22): 140-149.
[8]	王玲芝, 李晨阳, 刘婧, 等. 基于GRO-SSA-LSTM的短期光伏发电功率预测[J]. 太阳能学报, 2025, 46(2): 401-409.
	WANG Lingzhi, LI Chenyang, LIU Jing, et al. Short term photovoltaic power prediction based GRO-SSA-LSTM[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 401-409.
[9]	HAN L, JING H T, ZHANG R C, et al. Wind power forecast based on improved Long Short Term Memory network[J]. Energy, 2019, 189:116300.
[10]	江善和, 李伟, 徐小艳, 等. 基于变分模态分解改进生成对抗网络的短期风电功率预测[J]. 综合智慧能源, 2024, 46(2): 28-35. doi: 10.3969/j.issn.2097-0706.2024.02.004
	JIANG Shanhe, LI Wei, XU Xiaoyan, et al. Short-term wind power forecasting based on variational mode decomposition and generative adversarial networks[J]. Integrated Intelligent Energy, 2024, 46(2): 28-35. doi: 10.3969/j.issn.2097-0706.2024.02.004
[11]	胡宇晗, 朱利鹏, 李佳勇, 等. 融合深度误差反馈学习和注意力机制的短期风电功率预测[J]. 电力系统保护与控制, 2024, 52(4): 100-108.
	HU Yuhan, ZHU Lipeng, LI Jiayong, et al. Short-term wind power forecasting with the integration of a deep error feedback learning and attention mechanism[J]. Power System Protection and Control, 2024, 52(4): 100-108.
[12]	杨茂, 韩超, 张薇. 基于深度图聚类和特征重构的风电集群功率短期预测方法[J]. 电力自动化设备, 2025, 45(4): 53-59.
	YANG Mao, HAN Chao, ZHANG Wei. Short-term power prediction method for wind farm cluster based on deep graph clustering and feature reconstruction[J]. Electric Power Automation Equipment, 2025, 45(4): 53-59.
[13]	屈伯阳, 付立思. 基于NWP风速修正与VMD-DBO-DELM残差建模的风电功率预测研究[J]. 山东电力技术, 2025, 52(2): 32-45.
	QU Boyang, FU Lisi. Research on wind power prediction based on NWP wind speed correction and VMD-DBO-DELM residual modeling[J]. Shandong Electric Power, 2025, 52(2): 32-45.
[14]	程先龙, 张杰, 李思莹, 等. 基于VMD-BP-BiLSTM的短期风电功率预测[J/OL]. 综合智慧能源, 2024: 1-10 (2024-12-12) [2025-06-01]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=SLDL20241211002&dbname=CJFD&dbcode=CJFQ.
	CHENG Xianlong, ZHANG Jie, LI Siying, et al. Short-term wind power forecast based on VMD-BP-BiLSTM[J/OL]. Huadian Technology, 2024: 1-10 (2024-12-12) [2025-06-01]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=SLDL20241211002&dbname=CJFD&dbcode=CJFQ.
[15]	高红均, 郭明浩, 刘俊勇, 等. 从四川高温干旱限电事件看新型电力系统保供挑战与应对展望[J]. 中国电机工程学报, 2023, 43(12): 4517-4538.
	GAO Hongjun, GUO Minghao, LIU Junyong, et al. Power supply challenges and prospects in new power system from Sichuan electricity curtailment events caused by high-temperature drought weather[J]. Proceedings of the CSEE, 2023, 43(12): 4517-4538.
[16]	卢睿, 熊小伏, 陈红州. 考虑台风时空特性的海上风电场群协同紧急防御策略[J]. 电力系统保护与控制, 2024, 52(12): 13-24.
	LU Rui, XIONG Xiaofu, CHEN Hongzhou. Collaborative emergency defense strategy for offshore wind farm clusters considering the spatial-temporal characteristics of a typhoon[J]. Power System Protection and Control, 2024, 52(12): 13-24.
[17]	阮前途, 叶荣. 保障极端天气下供需安全的新型电力系统电源规划[J]. 电力系统自动化, 2025, 49(4): 103-115.
	RUAN Qiantu, YE Rong. Power source planning of new power system for guaranteeing supply-demand security under extreme weather[J]. Automation of Electric Power Systems, 2025, 49(4): 103-115.
[18]	鞠冠章, 王靖然, 崔琛, 等. 极端天气事件对新能源发电和电网运行影响研究[J]. 智慧电力, 2022, 50(11): 77-83.
	JU Guanzhang, WANG Jingran, CUI Chen, et al. Impact of extreme weather events on new energy power generation and power grid operation[J]. Smart Power, 2022, 50(11): 77-83.
[19]	COLOMINAS M A, SCHLOTTHAUER G, TORRES M E. Improve complete ensemble EMD: A suitable tool for biomedical signal processing[J]. Biomedical Signal Processing and Control, 2014,14 :19-29.
[20]	刘瑞叶, 黄磊. 基于动态神经网络的风电场输出功率预测[J]. 电力系统自动化, 2012, 36(11): 19-22, 37.
	LIU Ruiye, HUANG Lei. Wind power forecasting based on dynamic neural networks[J]. Automation of Electric Power Systems, 2012, 36(11): 19-22, 37.
[21]	郑颖颖, 李鑫, 陈延旭, 等. 基于Stacking多模型融合的极端天气短期风电功率预测方法[J]. 高电压技术, 2024, 50(9): 3871-3882.
	ZHENG Yingying, LI Xin, CHEN Yanxu, et al. Short-term wind power forecasting method in extreme weather based on Stacking multi-model fusion[J]. High Voltage Engineering, 2024, 50(9): 3871-3882.
[22]	宋家康, 赵建勇, 孙海霞, 等. 基于多目标协同训练的风电功率预测提升算法[J]. 电力工程技术, 2023, 42(6): 232-240.
	SONG Jiakang, ZHAO Jianyong, SUN Haixia, et al. Wind power prediction and improvement algorithm based on multi-objective collaborative training[J]. Electric Power Engineering Technology, 2023, 42(6): 232-240.
[23]	刘雅婷, 杨明, 于一潇, 等. 基于多场景敏感气象因子优选及小样本学习与扩充的转折性天气日前风电功率预测[J]. 高电压技术, 2023, 49(7): 2972-2982.
	LIU Yating, YANG Ming, YU Yixiao, et al. Transitional-weather-considered day-ahead wind power forecasting based on multi-scene sensitive meteorological factor optimization and few-shot learning[J]. High Voltage Engineering, 2023, 49(7): 2972-2982.
[24]	李宇佳, 陈富豪, 阎洁, 等. 基于迁移学习和自编码器的极端天气自适应短期风电功率预测[J/OL]. 电力系统自动化, 2024: 1-13 (2024-11-29) [2025-06-01]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=DLXT20241128003&dbname=CJFD&dbcode=CJFQ.
	LI Yujia, CHEN Fuhao, YAN Jie, et al. Adaptive short-term wind power forecasting for extreme weather based on transfer learning and AutoEncoder[J/OL]. Automation of Electric Power Systems, 2024: 1-13(2024-11-29) [2025-06-01]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=DLXT20241128003&dbname=CJFD&dbcode=CJFQ.
[25]	叶林, 李奕霖, 裴铭, 等. 寒潮天气小样本条件下的短期风电功率组合预测[J]. 中国电机工程学报, 2023, 43(2): 543-555.
	YE Lin, LI Yilin, PEI Ming, et al. Combined approach for short-term wind power forecasting under cold weather with small sample[J]. Proceedings of the CSEE, 2023, 43(2): 543-555.
[26]	卢雪平, 董存, 王铮, 等. 低温寒潮天气下的风电短期功率预测技术研究[J]. 电网技术, 2024, 48(12): 4833-4843.
	LU Xueping, DONG Cun, WANG Zheng, et al. Research on short-term wind power forecasting technology under low temperature and cold wave weather[J]. Power System Technology, 2024, 48(12): 4833-4843.
[27]	刘斌, 吉春霖, 曹丽君, 等. 基于自适应噪声完全集合经验模态分解与BiLSTM-Transformer的锂离子电池剩余使用寿命预测[J]. 电力系统保护与控制, 2024, 52(15): 167-177.
	LIU Bin, JI Chunlin, CAO Lijun, et al. Prediction of remaining service life of lithium-ion batteries based on complete ensemble empirical mode decomposition with adaptive noise and BiLSTM-Transformer[J]. Power System Protection and Control, 2024, 52(15): 167-177.
[28]	田莉莎, 严雄. 基于多重数据筛选的短期风电功率区间优化预测[J]. 山东电力技术, 2024, 51(5): 38-46, 62.
	TIAN Lisha, YAN Xiong. Optimized prediction of short-term wind power intervals based on multiple data screening[J]. Shandong Electric Power, 2024, 51(5): 38-46, 62.
[29]	贾树旺, 黄海, 吕洋, 等. 基于时频交叉注意力机制和多域特征融合的风电机组齿轮箱故障诊断研究[J]. 山东电力技术, 2025, 52(4): 11-19.
	JIA Shuwang, HUANG Hai, LYU Yang, et al. Research on fault diagnosis of wind turbine gearbox based on time-frequency cross attention mechanism and multi-domain feature fusion[J]. Shandong Electric Power, 2025, 52(4): 11-19.
[30]	杨茂, 张书天, 王勃, 等. 基于门控循环加权共形分位数回归的风电功率短期区间预测[J/OL]. 中国电机工程学报, 2024: 1-14(2024-09-11)[2025-06-01]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=ZGDC20240909004&dbname=CJFD&dbcode=CJFQ.
	YANG Mao, ZHANG Shutian, WANG Bo, et al. Short-term wind power interval prediction method based on gated recurrent weighted conformalized quantile regression[J/OL]. Proceedings of the CSEE, 2024: 1-14(2024-09-11)[2025-06-01]. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=ZGDC20240909004&dbname=CJFD&dbcode=CJFQ.
[31]	CSDN专栏. 风电机组运行数据集[EB/OL].(2023-10-01)[2025-06-01]. https://download.csdn.net/blog/column/12495091/134372421.
[32]	刘杰, 付雪娇, 蒋树旗, 等. 基于RF-LSTM网络的风电机组状态参数预测[J]. 控制工程, 2023, 30(11): 1965-1970.
	LIU Jie, FU Xuejiao, JIANG Shuqi, et al. Wind turbine state parameter prediction based on RF-LSTM network[J]. Control Engineering of China, 2023, 30(11): 1965-1970.
[33]	潘超, 王超, 孙惠, 等. 基于超参数优化和误差修正的STAGN超短期风电功率预测[J]. 电力系统保护与控制, 2025, 53(8): 117-129.
	PAN Chao, WANG Chao, SUN Hui, et al. STAGN ultra-short-term wind power forecasting based on hyperparameter optimization and error correction[J]. Power System Protection and Control, 2025, 53(8): 117-129.
[34]	徐武, 刘洋, 沈智方, 等. 基于改进局部自注意力机制的VMD-GRU模型短期风电功率预测[J]. 电网与清洁能源, 2023, 39(3): 83-92.
	XU Wu, LIU Yang, SHEN Zhifang, et al. Short-term wind power prediction based on VMD-GRU model with improved local self-attention mechanism[J]. Power System and Clean Energy, 2023, 39(3): 83-92.
[35]	徐钽, 谢开贵, 王宇, 等. 基于TCN-Wpsformer混合模型的超短期风电功率预测[J]. 电力自动化设备, 2024, 44(8): 54-61.
	XU Tan, XIE Kaigui, WANG Yu, et al. Ultra-short-term wind power forecasting based on TCN-Wpsformer hybrid model[J]. Electric Power Automation Equipment, 2024, 44(8): 54-61.

聚类	温度/℃	相对湿度/%	压力/hPa	风速/(m·s^-1)	风向/(°)
1	-4.2	35	837	4.2	90
2	-7.1	48	840	3.1	270
3	4.0	19	836	4.2	270