1.华北电力大学控制与计算机工程学院, 河北 保定 071003
2.保定市综合能源系统状态检测与优化调控重点实验室(华北电力大学), 河北 保定 071003
陈文颖(1980),女,通信作者,副教授,博士,研究方向为风力发电系统优化与控制,51651854@ncepu.edu.cn;
吴梦达(2001),男,硕士研究生,研究方向为风电功率预测技术,wmd201247@163.com。
收稿:2025-07-07,
网络首发:2025-10-24,
纸质出版:2026-08-20
移动端阅览
陈文颖,吴梦达.基于时空特征挖掘的EIF-WaveNet乡村小型分布式风电集群功率预测[J].南方电网技术,2026,20(08):18-28.
CHEN Wenying,WU Mengda.Power Prediction for Small-Scale Distributed Wind Turbine Clusters in Rural Areas Based on EIF-WaveNet with Spatiotemporal Feature Mining[J].Southern Power System Technology,2026,20(08):18-28.
陈文颖,吴梦达.基于时空特征挖掘的EIF-WaveNet乡村小型分布式风电集群功率预测[J].南方电网技术,2026,20(08):18-28. DOI: 10.13648/j.cnki.issn1674-0629.2026.08.002.
CHEN Wenying,WU Mengda.Power Prediction for Small-Scale Distributed Wind Turbine Clusters in Rural Areas Based on EIF-WaveNet with Spatiotemporal Feature Mining[J].Southern Power System Technology,2026,20(08):18-28. DOI: 10.13648/j.cnki.issn1674-0629.2026.08.002.
针对乡村地区小型分布式风电面临的地形复杂、风速及功率数据噪声干扰显著等问题,为提升其超短期功率预测精度,提出了一种融合改进孤立森林数据清洗与时空特征挖掘的WaveNet预测算法。首先,采用改进孤立森林算法(enhanced isolation forest,EIF)进行数据清洗,该算法集成了动态分位数阈值优化、路径长度窗口平滑及多模态校正策略,有效识别并剔除异常数据点。随后,利用最大互信息系数(maximal information coefficient,MIC)筛选高相关特征输入并引入时间注意力机制结合Transformer模块捕获关键时间依赖性,同时应用空间注意力机制与图卷积网络(graph convolutional network,GCN)建模风机间的空间关联性,进行时空特征融合。接着,构建基于WaveNet架构的超短期单机功率预测模型,以其膨胀卷积和跳跃连接精准捕捉融合特征序列的动态模式并输出单机功率预测结果。最后,考虑各机组的位置权重与空间相关性,聚合单机预测结果输出集群总功率。以某村庄部署的3台单机容量为10 kW的小型分布式风电场为实例,验证结果表明所提方法具有较高预测精度。
To address the challenges of complex terrain
significant noise interference in wind speed and power data for small-scale distributed wind farms in rural areas
an improved WaveNet prediction algorithm integrating enhanced isolation forest data cleaning and spatiotemporal feature mining is proposed to enhance ultra-short-term power prediction accuracy. Firstly
an enhanced isolation forest (EIF) algorithm is employed for data cleaning. This algorithm incorporates dynamic quantile threshold optimization
path length window smoothing
and a multimodal correction strategy to effectively identify and eliminate anomalous data points. Subsequently
the maximal information coefficient (MIC) is utilized to screen highly correlated input features. A temporal attention mechanism combined with a Transformer module captures critical temporal dependencies
while a spatial attention mechanism integrated with a graph convolutional network (GCN) models spatial correlations among wind turbines for spatiotemporal feature fusion. Next
an ultra-short-term single-turbine power prediction model based on WaveNet architecture is constructed,which accurately captures the dynamic patterns of the fused feature sequence through its dilated convolution and skip connections
and outputs the single-turbine power prediction results. Finally
the total cluster power output is aggregated from single-turbine prediction results by considering the positional weights and spatial correlations of each turbine. A case study is conducted on three-small-turbine distributed wind farms with a single turbine capacity of 10 kW deployed in a certain rural area. The results demonstrate that the proposed method achieves high prediction accuracy.
国家发展改革委 , 国家能源局 . 国家发展改革委 国家能源局 农业农村部关于组织开展“千乡万村驭风行动”的通知 [EB/OL]. ( 2024 - 03 - 25 ).https://zfxxgk.nea.gov.cn/2024 - 03/25/c_13 10769840.html.
杨茂 , 闫琦 , 苏欣 , 等 . 季节分型下一种面向风电功率日前预测的深度自适应滤波框架 [J]. 南方电网技术 , 2023 , 17 ( 6 ): 62 - 71 .
YANG Mao , YAN Qi , SU Xin , et al . A depth adaptive filtering framework for wind power day-ahead prediction under seasonal classification [J]. Southern Power System Technology , 2023 , 17 ( 6 ): 62 - 71 .
康田雨 , 覃智君 . 基于超参数优化和双重注意力机制的超短期风电功率预测 [J]. 南方电网技术 , 2022 , 16 ( 5 ): 44 - 53 .
KANG Tianyu , QIN Zhijun . An ultra-short-term wind power forecasting method based on hyperparameter optimization and dual-stage attention mechanism [J]. Southern Power System Technology , 2022 , 16 ( 5 ): 44 - 53 .
WANG Y , ZHANG Y , LIU H , et al . Wind turbine abnormal data cleaning method considering multi-scene parameter adaptation [C]// 2022 Asian Conference on Frontiers of Power and Energy (ACFPE) , October 21 - 23 , 2022 , Chengdu, China . New York : IEEE , 2022: 292 – 297 .
WU Y , LIU J , REN Z , et al . Cleaning and reconstruction of wind power anomaly data based on hierarchical clustering [C]// 2023 3rd New Energy and Energy Storage System Control Summit Forum (NEESSC) , September 26 - 28 , 2023 , Mianyang, China . New York : IEEE , 2023: 327 – 332 .
ZHANG F , ZHANG X , XU Z , et al . Cleaning of abnormal wind speed power data based on quartile RANSAC regression [J]. Energies , 2024 , 17 ( 22 ): 5697 .1 - 5697.14.
LAI G , LIAO L , ZHANG L , et al . Wind speed power data cleaning method for wind turbines based on fan characteristics and isolated forests [J]. Journal of Physics: Conference Series , 2023 , 2427 ( 1 ): 012001.1 - 012001.10 .
PAN Guangxu , ZHANG Haijing , JUN Wenjie , et al . A prediction method for ultra short-term wind power prediction basing on long short -term memory network and extreme learning machine [C]// 2020 Chinese Automation Congress (CAC) , November 6 - 8 , 2020 , Shanghai, China . New York : IEEE , 2020: 7608 – 7612 .
匡洪海 , 郭茜 . 基于多特征提取-卷积神经网络-长短期记忆网络的短期风电功率预测方法 [J]. 发电技术 , 2025 , 46 ( 1 ): 93 - 102 .
KUANG Honghai , GUO Qian . Short-term wind power prediction method based on multimodal feature extraction-convolutional neural network-long-short term memory network [J]. Power Generation Technology , 2025 , 46 ( 1 ): 93 - 102 .
CHEN Y . Research on application of neural networks to wind power prediction [J]. Journal of Physics: Conference Series , 2020 , 1533 ( 2 ): 022005.1 - 022005.11 .
任东方 , 马家庆 , 何志琴 , 等 . 基于AVMD-CNN-GRU-Attention的超短期风功率预测研究 [J]. 太阳能学报 , 2024 , 45 ( 6 ): 436 - 443 .
REN Dongfang , MA Jiaqing , HE Zhiqin , et al . Research on ultra-short-term wind power forecast based on AVMD-CNN-GRU-Attention [J]. Acta Energiae Solaris Sinica , 2024 , 45 ( 6 ): 436 - 443 .
张程 , 林锦平 . 基于双重注意力卷积双向长短期记忆神经网络的电力系统状态估计 [J]. 南方电网技术 , 2026 , 20 ( 5 ): 59 - 70 .
ZHANG Cheng , LIN Jinping . Power system state estimation based on dual attention convolutional bidirectional long and short-term memory neural networks [J]. Southern Power System Technology , 2026 , 20 ( 5 ): 59 - 70 .
邵宜祥 , 刘剑 , 胡丽萍 , 等 . 一种改进组合神经网络的超短期风速预测方法研究 [J]. 发电技术 , 2024 , 45 ( 2 ): 323 - 330 .
SHAO Yixiang , LIU Jian , HU Liping , et al . Research on an ultra-short-term wind speed prediction method based on improved combined neural networks [J]. Power Generation Technology , 2024 , 45 ( 2 ): 323 - 330 .
AHILAN D T , GANITHA S , YARRAPRAGADA K R . Wind turbine power prediction via deep neural network using hybrid approach [J]. Proceedings of the Institution of Mechanical Engineers Part A Journal of Power and Energy , 2022 , 237 ( 3 ): 484 – 494 .
BASHIR T , WANG H , TAHIR M , et al . Wind and solar powe forecasting based on hybrid CNN-ABiLSTM, CNN-transformer-MLP Models [J]. Renewable Energy , 2025 ( 239 ): 122055.1 - 122055.10 .
FOURNIER Q , CARON G M , ALOISE D . A practical survey on faster and lighter transformers [J]. ACM Computing Surveys , 2023 , 55 ( 14 ): 1 – 40 .
WEI H , WANG W , KAO X . A novel approach to ultra-short-te-rm wind power prediction based on feature engineering and In-former [J]. Energy Reports , 2023 ( 9 ): 1236 – 1250 .
SHI Z , LI J , JIANG Z , et al . WGformer: a Weibull-Gaussian informer based model for wind speed prediction [J]. Engineering Applications of Artificial Intelligence , 2024 (131): 107891.1 - 107891.20.
李青 , 张新燕 , 摆志俊 , 等 . 基于MQ-WaveNet的风电集群发电功率多步概率预测 [J]. 电力系统自动化 , 2023 , 47 ( 8 ): 156 - 168 .
LI Qing , ZHANG Xinyan , BAI Zhijun , et al . Multi-step probability prediction of power generation for wind power clusters based on multi-horizon Quantile-WaveNet [J]. Automation of Electric Power Systems , 2023 , 47 ( 8 ): 156 - 168 .
ZHANG Y , ZHANG Z , HU Y , et al . GMD-Linear: integrating graph neural networks and wavenet for enhanced wind power forecasting [C]// 2024 12th International Conference on Information Systems and Computing Technology (ISCTech) , November 8 - 11 , 2024 , Xi'an, China . New York : IEEE , 2024: 1 – 5 .
LIU X , ZOU L , ZHANG L , et al . A multi-channel spatiotemporal SegNet model for short term wind power prediction with s-equence decomposition and reconstruction [J]. Results in Engineering , 2025 (27): 105797.1- 105797.17.
欧阳静 , 秦龙 , 王坚锋 , 等 . 基于PCA-ShapeDTW-QWGRU的分布式光伏集群短期功率预测 [J]. 太阳能学报 , 2024 , 45 ( 5 ): 458 - 467 .
OUYANG Jing , QIN Long , WANG Jianfeng , et al . Short-term power prediction for distributed PV clusters based on PCA-SHapeDTW-QWGRU [J]. Acta Energiae Solaris Sinica , 2024 , 45 ( 5 ): 458 - 467 .
阮呈隆 , 李康平 , 李正辉 , 等 . 分布式光伏集群功率短期预测的空间互补特性初探 [J]. 电力系统自动化 , 2024 , 48 ( 3 ): 42 - 50 .
RUAN Chenglong , LI Kangping , LI Zhenghui , et al . Preliminary study on spatial complementarity characteristics of short-term power prediction for distributed photovoltaic clusters [J]. Automation of Electric Power Systems , 2024 , 48 ( 3 ): 42 - 50 .
王于波 , 郝玲 , 徐飞 , 等 . 分布式光伏集群发电功率波动模式识别与超短期概率预测 [J]. 上海交通大学学报 , 2024 , 58 ( 9 ): 1334 - 1343 .
WANG Yubo , HAO Ling , XU Fei , et al . Pattern recognition and ultra-short-term probabilistic forecasting of power fluctuating in aggregated distributed photovoltaics clusters [J]. Journal of Shanghai Jiaotong University , 2024 , 58 ( 9 ): 1334 - 1343 .
张翔颖 . 海量分布式光伏集群动态划分与短期功率预测技术研究 [D]. 南京 : 东南大学 , 2023 .
杨炜晨 , 苗世洪 , 刘志伟 , 等 . 面向分布式电源功率波动平抑的变频空调集群多时间尺度模型预测控制策略 [J]. 电工技术学报 , 2022 , 37 ( 19 ): 4848 - 4861 .
YANG Weichen , MIAO Shihong , LIU Zhiwei , et al . Multi-time-scale model predictive control of inverter air conditioner cluster for distributed power fluctuation stabilization [J]. Transactions of China Electrotechnical Society , 2022 , 37 ( 19 ): 4848 - 4861 .
李丽旻 . 乡村风电开发正当时 [N]. 中国能源报 , 2024 - 06 - 17 ( 014 ).
WANG W , YANG S , YANG Y . An improved data-efficiency algorithm based on combining isolation forest and mean shift for anomaly data filtering in wind power curve [J]. Energies , 2022 , 15 ( 13 ): 4918 .1 - 4918.12.
ZHANG X , SHEN X , OUYANG T . Extension of DBSCAN in online clustering: an approach based on three-layer granular models [J]. Applied Sciences , 2022 , 12 ( 19 ): 9402 .1 - 9402.22.
ZHANG Z , SUN Z , GUO X , et al . Short-term multi-step wind power prediction model based on Pt-Transformer neural network integrating spatio-temporal feature and sparse attention [J]. Electric Power Systems Research , 2025 ( 248 ): 111970.1 - 111970.9 .
WU M , FENG W , LI X , et al . Short-Term power load forecasting using an improved model integrating GCN and transformer [J]. Applied Sciences , 2025 , 15 ( 13 ): 7003 .1 - 7003.34.
WANG H , PENG C , LIAO B , et al . Wind power forecasting based on wavenet and multitask learning [J]. Sustainability , 2023 , 15 ( 14 ): 10816 .1 - 10816.22.
王家坤 , 司化涛 , 王希转 , 等 . 基于MQ-WaveNet的智慧新能源大规模风力发电智能控制 [J]. 可再生能源 , 2024 , 42 ( 10 ): 1341 - 1347 .
WANG Jiakun , SI Huatao , WANG Xizhuan , et al . The intelligent control of smart new energy large scale wind power generation based on MQ-WaveNet [J]. Renewable Energy Resources , 2024 , 42 ( 10 ): 1341 - 1347 .
陈海鹏 , 李赫 , 阚天洋 , 等 . 考虑风电时序特性的深度小波-时序卷积网络超短期风功率预测 [J]. 电网技术 , 2023 , 47 ( 4 ): 1653 - 1665 .
CHEN Haipeng , LI He , KAN Tianyang , et al . DWT-DTCNA ultra-short-term wind power prediction considering wind power timing characteristics [J]. Power System Technology , 2023 , 47 ( 4 ): 1653 - 1665 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621