
浏览全部资源
扫码关注微信
中国农业大学信息与电气工程学院,北京市 100083
陈延旭(2001—),男,硕士研究生,主要研究方向:新能源发电功率预测技术。E-mail:chenyanxv@cau.edu.cn
潘世纪(2000—),男,硕士研究生,主要研究方向:新能源发电功率预测技术。E-mail:panshiji@cau.edu.cn
赵永宁(1990—),男,通信作者,副教授,博士生导师,主要研究方向:新能源发电技术、新能源并网调度控制。E-mail:zyn@cau.edu.cn
收稿日期:2024-10-18,
修回日期:2025-03-07,
网络出版日期:2025-06-30,
纸质出版日期:2025-08-25
移动端阅览
陈延旭,潘世纪,赵永宁等.基于模型学习偏移修正的短期风电功率预测方法[J].电力系统自动化,2025,49(16):96-108.
CHEN Yanxu,PAN Shiji,ZHAO Yongning,et al.Short-term Wind Power Forecasting Method Based on Model Learning Offset Correction[J].Automation of Electric Power Systems,2025,49(16):96-108.
陈延旭,潘世纪,赵永宁等.基于模型学习偏移修正的短期风电功率预测方法[J].电力系统自动化,2025,49(16):96-108. DOI: 10.7500/AEPS20241018001.
CHEN Yanxu,PAN Shiji,ZHAO Yongning,et al.Short-term Wind Power Forecasting Method Based on Model Learning Offset Correction[J].Automation of Electric Power Systems,2025,49(16):96-108. DOI: 10.7500/AEPS20241018001.
现有基于数据驱动的风电功率预测模型在建模过程中不可避免地存在学习偏移性问题,使得模型有偏向性地学习分布集中的部分数据样本,导致预测模型在实际应用中泛化能力较差。针对上述问题,提出一种基于模型学习偏移修正的短期风电功率预测方法。首先,通过挖掘差异化样本造成模型预测性能偏移的作用原理,对时序样本进行分类表征。之后,针对历史数据中难以预测的极端天气样本、异常样本和相似不平衡样本,分别采用场景生成、渐进式掩码检测和样本特征增强策略联合修正模型学习的偏移性。最后,利用Shapley值法对各类样本进行重要性评估,以验证该偏移修正策略的必要性与合理性。实际算例表明,所提方法可显著提升各类模型的短期风电功率预测精度,在多场景模式下均具备较好的泛化性。
Existing data-driven wind power forecasting models inevitably suffer from the learning offset problem in the modeling process
which leads to these models being biased to learn partial data samples with concentrated distribution
resulting in poor generalization ability in the practical applications. A short-term wind power forecasting method based on the model learning offset correction is proposed to address the aforementioned issue. Firstly
by exploring the principle of differential samples causing model prediction performance offset
temporal samples are classified and characterized. Subsequently
for extreme weather samples
abnormal samples
and similar imbalanced samples that are difficult to predict in historical data
the strategies of multi-scenario generation
progressive mask detection
and sample feature enhancement are used to jointly correct the offset in the model learning. Finally
the Shapley value method is used to evaluate the importance of various samples
in order to verify the necessity and rationality of the offset correction strategy. Actual cases show that the proposed method can significantly improve the short-term wind power forecasting accuracy of various models
and has good generalization in multi-scenario modes.
韩丽 , 于晓娇 , 喻洪波 , 等 . 基于波动趋势分段的风电功率区间预测 [J]. 电力系统自动化 , 2023 , 47 ( 18 ): 206 - 215 .
HAN Li , YU Xiaojiao , YU Hongbo , et al . Wind power interval prediction based on fluctuation trend segmentation [J]. Automation of Electric Power Systems , 2023 , 47 ( 18 ): 206 - 215 .
ZHAO Y N , PAN S J , ZHAO Y , et al . Ultra-short-term wind power forecasting based on personalized robust federated learning with spatial collaboration [J]. Energy , 2024 , 288 : 129847 .
杨茂 , 张书天 , 王勃 . 基于因果正则化极限学习机的风电功率短期预测方法 [J]. 电力系统保护与控制 , 2024 , 52 ( 11 ): 127 - 136 .
YANG Mao , ZHANG Shutian , WANG Bo . Short-term wind power forecasting method based on a causal regularized extreme learning machine [J]. Power System Protection and Control , 2024 , 52 ( 11 ): 127 - 136 .
WANG Y , ZOU R M , LIU F , et al . A review of wind speed and wind power forecasting with deep neural networks [J]. Applied Energy , 2021 , 304 : 117766 .
HAKAMI A . Strategies for overcoming data scarcity, imbalance, and feature selection challenges in machine learning models for predictive maintenance [J]. Scientific Reports , 2024 , 14 : 9645 .
LIU Y L , WANG J Y , LIU L Q . Physics-informed reinforcement learning for probabilistic wind power forecasting under extreme events [J]. Applied Energy , 2024 , 376 : 124068 .
SCHWARTZ E , KARLINSKY L , SHTOK J , et al . Delta-encoder: an effective sample synthesis method for few-shot object recognition [C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems , December 3 , 2018, Red Hook, USA .
BLUDSZUWEIT H , DOMINGUEZ-NAVARRO J A , LLOMBART A . Statistical analysis of wind power forecast error [J]. IEEE Transactions on Power Systems , 2008 , 23 ( 3 ): 983 - 991 .
董骁翀 , 张姝 , 李烨 , 等 . 电力系统中时序场景生成和约简方法研究综述 [J]. 电网技术 , 2023 , 47 ( 2 ): 709 - 721 .
DONG Xiaochong , ZHANG Shu , LI Ye , et al . Review of power system temporal scenario generation and reduction methods [J]. Power System Technology , 2023 , 47 ( 2 ): 709 - 721 .
潘霄 , 张明理 , 刘德宝 , 等 . 基于鲁棒多标签生成对抗的风电场日前出力区间预测 [J]. 电力系统自动化 , 2022 , 46 ( 10 ): 216 - 223 .
PAN Xiao , ZHANG Mingli , LIU Debao , et al . Interval prediction of wind farm day-ahead output based on robust multi-label generative adversarial [J]. Automation of Electric Power Systems , 2022 , 46 ( 10 ): 216 - 223 .
MENG A B , ZHANG H T , YIN H , et al . A novel multi-gradient evolutionary deep learning approach for few-shot wind power prediction using time-series GAN [J]. Energy , 2023 , 283 : 129139 .
李辉 , 任洲洋 , 胡博 , 等 . 基于时序生成对抗网络的月度风光发电功率场景分析方法 [J]. 中国电机工程学报 , 2022 , 42 ( 2 ): 537 - 547 .
LI Hui , REN Zhouyang , HU Bo , et al . A sequential generative adversarial network based monthly scenario analysis method for wind and photovoltaic power [J]. Proceedings of the CSEE , 2022 , 42 ( 2 ): 537 - 547 .
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 .
米阳 , 卢长坤 , 申杰 , 等 . 基于条件生成对抗网络的风电功率极端场景生成 [J]. 高电压技术 , 2023 , 49 ( 6 ): 2253 - 2263 .
MI Yang , LU Changkun , SHEN Jie , et al . Wind power extreme scenario generation based on conditional generative adversarial network [J]. High Voltage Engineering , 2023 , 49 ( 6 ): 2253 - 2263 .
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/OL]. 高电压技术 [ 2024-10-12 ]. http://kns.cnki.net/KCMS/detail/detail.aspx?filename=GDYJ2024080800H&dbname=CJFD&dbcode=CJFQ http://kns.cnki.net/KCMS/detail/detail.aspx?filename=GDYJ2024080800H&dbname=CJFD&dbcode=CJFQ .
ZHENG Yingying , LI Xin , CHEN Yanxu , et al . Short-term wind power forecasting method in extreme weather based on Stacking multi-model fusion [J/OL]. High Voltage Engineering [ 2024-10-12 ]. http://kns.cnki.net/KCMS/detail/detail.aspx?filename=GDYJ2024080800H&dbname=CJFD&dbcode=CJFQ http://kns.cnki.net/KCMS/detail/detail.aspx?filename=GDYJ2024080800H&dbname=CJFD&dbcode=CJFQ .
SHEN L , WEI Y N , WANG Y Z , et al . AFMF: time series anomaly detection framework with modified forecasting [J]. Knowledge-Based Systems , 2024 , 296 : 111912 .
周嘉琪 , 毕利 . 基于GAN的光伏逆变器数据异常检测技术 [J]. 电力系统保护与控制 , 2022 , 50 ( 1 ): 133 - 140 .
ZHOU Jiaqi , BI Li . Abnormal detection technology of photovoltaic inverter data based on GAN [J]. Power System Protection and Control , 2022 , 50 ( 1 ): 133 - 140 .
ZHAN X W , HAN S , RONG N , et al . A hybrid transfer learning method for transient stability prediction considering sample imbalance [J]. Applied Energy , 2023 , 333 : 120573 .
AZHAR N A , POZI M S M , DIN A M , et al . An investigation of SMOTE based methods for imbalanced datasets with data complexity analysis [J]. IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 7 ): 6651 - 6672 .
TARAWNEH A S , HASSANAT A B A , ALMOHAMMADI K , et al . SMOTEFUNA: synthetic minority over-sampling technique based on furthest neighbour algorithm [J]. IEEE Access , 2020 , 8 : 59069 - 59082 .
XIA Z M , CHEN Y , XU C . Multiview PCA: a methodology of feature extraction and dimension reduction for high-order data [J]. IEEE Transactions on Cybernetics , 2022 , 52 ( 10 ): 11068 - 11080 .
朱玄烨 , 孔兵 , 陈红梅 , 等 . 困难样本采样联合对比增强的深度图聚类 [J]. 计算机应用研究 , 2024 , 41 ( 6 ): 1769 - 1777 .
ZHU Xuanye , KONG Bing , CHEN Hongmei , et al . Deep graph clustering with hard sample sampling joint contrastive augmentation [J]. Application Research of Computers , 2024 , 41 ( 6 ): 1769 - 1777 .
国家质量监督检验检疫总局 , 中国国家标准化管理委员会 . 冷空气等级 : GB/T 20484—2017 [S]. 北京 : 中国标准出版社 , 2017 .
General Administration of Quality Supervision , Inspection and Quarantine of the People’s Republic of China , Standardization Administration of the People’s Republic of China . Grade of cold air : GB/T 20484—2017 [S]. Beijing : Standards Press of China , 2017 .
周思思 , 李勇 , 郭钇秀 , 等 . 考虑时序特征提取与双重注意力融合的TCN超短期负荷预测 [J]. 电力系统自动化 , 2023 , 47 ( 18 ): 193 - 205 .
ZHOU Sisi , LI Yong , GUO Yixiu , et al . Ultra-short-term load forecasting based on temporal convolutional network considering temporal feature extraction and dual attention fusion [J]. Automation of Electric Power Systems , 2023 , 47 ( 18 ): 193 - 205 .
XIONG Y S , ZHANG P , DOU Y , et al . Focus on hard categories and hard examples: remote sensing image scene classification via expert model and hard example mining [J]. IEEE Geoscience and Remote Sensing Letters , 2021 , 19 : 8006505 .
张点 , 董云卫 . 基于掩膜自动编码器的对抗对比蒸馏算法 [J]. 计算机学报 , 2024 , 47 ( 10 ): 2274 - 2288 .
ZHANG Dian , DONG Yunwei . An adversarial contrastive distillation algorithm based on masked auto-encoder [J]. Chinese Journal of Computers , 2024 , 47 ( 10 ): 2274 - 2288 .
王丹平 , 陈之栩 , 涂孟夫 , 等 . 考虑大规模风电接入的备用容量计算 [J]. 电力系统自动化 , 2012 , 36 ( 21 ): 24 - 28 .
WANG Danping , CHEN Zhixu , TU Mengfu , et al . Reserve capacity calculation considering large-scale wind power integration [J]. Automation of Electric Power Systems , 2012 , 36 ( 21 ): 24 - 28 .
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