郑子淮,杨明,于一潇,钱建国,解慧力,李乐乐
ZHENG Zihuai,YANG Ming,YU Yixiao,QIAN Jianguo,XIE Huili,LI Lele

• 1:国网浙江省电力有限公司台州供电公司
• 2:山东大学电气工程学院

摘要(Abstract)：

极端天气下的风电出力短时间内波动剧烈，极易发生风电爬坡事件，但是现有研究成果对于极端天气下风电功率爬坡预测的准确性和可靠性不高。为此，提出一种极端天气下基于Informer-SDT-xLSTM协同机制的风电功率爬坡预测方法。构建了Informer神经网络模型进行风电功率预测，通过考虑bump事件的旋转门算法对风电功率初步预测结果进行了爬坡检测，提取爬坡段极值信息，基于扩展的长短时记忆神经网络对爬坡检测结果进行极值修正进而得出较为准确的预测结果。在某风电场站对提出的方法进行验证，结果表明此预测模型较准确地检测了极端天气下的风电功率爬坡事件，可有效解决极端天气下风电功率爬坡预测偏差较大的问题。
Under extreme weather conditions, wind power output fluctuates drastically within a short period, making wind power ramping highly likely to occur. However, existing studies still exhibit limited accuracy and reliability in predicting wind power ramping under extreme weather. To address this issue, a wind power ramping prediction method based on an Informer-SDT-x LSTM collaborative mechanism is proposed. An Informer neural network model is first developed for wind power forecasting. The preliminary forecasting results are then subjected to ramping detection using spinning door transformation(SDT) considering bump events, from which extrema within ramping segments are extracted. Subsequently, an extended long short-term memory(xLSTM) network is employed to correct the extrema detected in the ramping segments, thereby improving prediction accuracy. The proposed method is validated using data from a wind farm. Results demonstrate that the model can accurately detect wind power ramping under extreme weather conditions and effectively reduce prediction deviations associated with such events.

关键词(KeyWords)： 风电功率预测;爬坡预测;极值修正;旋转门算法;bump事件修正;长短时记忆神经网络
wind power forecasting;ramping forecast;extremum correction;SDT;bump event correction;LSTM

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金（52177095）;; 国网浙江省电力有限公司科技项目（5211TZ240002）

作者(Author): 郑子淮,杨明,于一潇,钱建国,解慧力,李乐乐
ZHENG Zihuai,YANG Ming,YU Yixiao,QIAN Jianguo,XIE Huili,LI Lele

DOI: 10.19585/j.zjdl.202604006

参考文献(References)：

• [1]张元赫，杨明，王勃，等.极端大风天气事件对风力发电的影响[J].电网与清洁能源，2025,41(5):95-103.ZHANG Yuanhe,YANG Ming,WANG Bo,et al.A study on the impacts of extreme gale events on wind power generation[J].Power System and Clean Energy,2025,41(5):95-103.
• [2]唐冬来，周强，宋卫平，等.基于网格聚类的峡谷风电短期功率预测方法[J].供用电，2023,40(1):80-87.TANG Donglai,ZHOU Qiang,SONG Weiping,et al.Short term power prediction method of canyon wind power based on grid clustering[J].Distribution&Utilization,2023,40(1):80-87.
• [3]VIET D T,VAN PHUONG V,DUONG M Q,et al.Models for short-term wind power forecasting based on improved artificial neural network using particle swarm optimization and genetic algorithms[J]. Energies,2020,13(11):2873.
• [4]于一潇.时空特征深度挖掘的风电集群发电功率短期概率预测方法研究[D].济南：山东大学，2020.YU Yixiao. Research of short-term regional wind power probabilistic prediction based on deep excavation of spatial and temporal features[D]. Jinan:Shandong University,2020.
• [5]范高锋，王伟胜，刘纯，等.基于人工神经网络的风电功率预测[J].中国电机工程学报，2008,28(34):118-123.FAN Gaofeng,WANG Weisheng,LIU Chun,et al.Wind power prediction based on artificial neural network[J].Proceedings of the CSEE,2008,28(34):118-123.
• [6]景惠甜.基于深度学习的风电功率预测研究[D].徐州：中国矿业大学，2021.JING Huitian.Research on wind power forecasting based on deep learning[D].Xuzhou:China University of Mining and Technology,2021.
• [7]时帅，张皓，黄冬梅，等.考虑爬坡特征量的海上风电短期分区功率预测[J].太阳能学报，2024,45(12):258-268.SHI Shuai,ZHANG Hao,HUANG Dongmei,et al.Shortterm zoning power prediction of offshore wind power considering climbing feature quantities[J].Acta Energiae Solaris Sinica,2024,45(12):258-268.
• [8]唐新姿，顾能伟，黄轩晴，等.风电功率短期预测技术研究进展[J].机械工程学报，2022,58(12):213-236.TANG Xinzi,GU Nengwei,HUANG Xuanqing,et al.Progress on short term wind power forecasting technology[J]. Journal of Mechanical Engineering,2022,58(12):213-236.
• [9]司雅昕，刘训强，苏向敬，等.海上风电功率预测研究综述[J].浙江电力，2025,44(11):59-71.SI Yaxin,LIU Xunqiang,SU Xiangjing,et al.A review of offshore wind power forecasting studies[J].Zhejiang Electric Power,2025,44(11):59-71.
• [10]陶玉波.风力发电场短期风速预测系统的研究与设计[D].昆明：昆明理工大学，2012.TAO Yubo.Research and design of short-term wind speed forecasting system for wind farm[D].Kunming:Kunming University of Science and Technology,2012.
• [11]周伊，肖先勇，赵清华，等.基于组合数据清洗与改进注意力机制的光伏发电功率预测[J].供用电，2024,41(10):31-37.ZHOU Yi,XIAO Xianyong,ZHAO Qinghua,et al.Photovoltaic power forecasting based on combined data cleaning and improved attention mechanism[J].Distribution&Utilization,2024,41(10):31-37.
• [12]唐雅洁，龚迪阳，林达，等.基于SAX-MHA-GCN的区域分布式光伏超短期功率预测[J].浙江电力，2025,44(8):88-98.TANG Yajie,GONG Diyang,LIN Da,et al.Ultra-shortterm power forecasting for regional DPV systems based on SAX-MHA-GCN[J].Zhejiang Electric Power,2025,44(8):88-98.
• [13]XIA B B,HUANG Q Y,WANG H,et al. Wind power prediction in view of ramping events based on classified spatiotemporal network[J].Frontiers in Energy Research,2022,9:754274.
• [14]CORNEJO-BUENO L, CAMACHO-G??MEZ C,AYBAR-RUIZ A,et al.Wind power ramp event detection with a hybrid neuro-evolutionary approach[J]. Neural Computing and Applications,2020,32(2):391-402.
• [15]宋万鹏，杨明，金媛媛.基于SMOTE采样和KNN算法的预测模型分析[J].集成电路应用，2023,40(4):76-78.SONG Wanpeng,YANG Ming,JIN Yuanyuan.Analysis of prediction model based on SMOTE sampling and KNN algorithm[J].Applications of IC,2023,40(4):76-78.
• [16]童林，官铮，王立威，等.基于时序分解与误差修正的新能源爬坡事件预测[J].浙江大学学报（工学版），2022,56(2):338-346.TONG Lin,GUAN Zheng,WANG Liwei,et al.New energy ramp event prediction based on time series decomposition and error correction[J].Journal of Zhejiang University(Engineering Science),2022,56(2):338-346.
• [17]康田雨.风电极端爬坡事件预测与风险评估[D].南宁：广西大学，2022.KANG Tianyu. Extreme climbing event prediction and risk assessment of wind power[D].Nanning:Guangxi University,2022.
• [18]宗阳.风电功率爬坡事件检测及预测方法研究[D].南京：南京信息工程大学，2020.ZONG Yang.Research on detection and prediction method of wind power ramping events[D].Nanjing:Nanjing University of Information Science&Technology,2020.
• [19]付泽斌.基于贝叶斯深度学习的新型电力系统爬坡需求预测方法研究[J].电工技术，2025(7):25-28.FU Zebin.Research on a new power system climbing demand prediction method based on Bayesian deep learning[J].Electric Engineering, 2025(7):25-28.
• [20]臧海祥，赵勇凯，张越，等.基于低风速功率修正和损失函数改进的超短期风电功率预测[J].电力系统自动化，2024,48(7):248-257.ZANG Haixiang,ZHAO Yongkai,ZHANG Yue,et al.Ultra-short-term wind power prediction based on power correction under low wind speed and improved loss function[J].Automation of Electric Power Systems,2024,48(7):248-257.
• [21]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.Shortterm wind power forecasting method based on model learning offset correction[J].Automation of Electric Power Systems,2025,49(16):96-108.
• [22]ZHENG H Y,KUSIAK A.Prediction of wind farm power ramp rates:a data-mining approach[J].Journal of Solar Energy Engineering,2009,131(3):031011.
• [23]BOSSAVY A,GIRARD R,KARINIOTATKIS G.Forecasting uncertainty related to ramps of wind power production[C]//European Wind Energy Conference and Exhibition 2010,EWEC 2010.European Wind Energy Association,2010,2:9 pages-ISBN 9781617823107.
• [24]KIM S,HUR J.A scenario-based wind power forecasting using multivariate probabilistic power curves for power grid congestion risk management under extreme grid conditions[J]. Thermal Science and Engineering Progress,2025,64:103827.
• [25]陈思怡，苏小玲，赵正奎，等.考虑功率耦合特性的构网型风机频率稳定分析方法[J].电力电容器与无功补偿，2025,46(2):1-8.CHEN Siyi,SU Xiaoling,ZHAO Zhengkui,et al. Frequency stability analysis method of grid-forming wind turbine considering power coupling characteristics[J].Power Capacitor&Reactive Power Compensation,2025,46(2):1-8.
• [26]韩砚海，张浩松，杨德健，等.预防双馈风机调频期间失速的功率轨迹预设策略[J].智慧电力，2024,52(2):108-114.HAN Yanhai,ZHANG Haosong,YANG Dejian,et al.Power trajectory preset strategy for preventing stall during frequency regulation of DFIG[J].Smart Power,2024,52(2):108-114.
• [27]ZHOU H Y,ZHANG S H,PENG J Q,et al. Informer:beyond efficient transformer for long sequence time-series forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2021,35(12):11106-11115.
• [28]张东英，代悦，张旭，等.风电爬坡事件研究综述及展望[J].电网技术，2018,42(6):1783-1792.ZHANG Dongying,DAI Yue,ZHANG Xu,et al.Review and prospect of research on wind power ramp events[J].Power System Technology,2018,42(6):1783-1792.
• [29]景惠甜，韩丽，高志宇.基于卷积神经网络特征提取的风电功率爬坡预测[J].电力系统自动化，2021,45(4):98-105.JING Huitian,HAN Li,GAO Zhiyu. Wind power ramp forecast based on feature extraction using convolutional neural network[J]. Automation of Electric Power Systems,2021,45(4):98-105.
• [30]FERRIRA C,GAMA J,MATIAS L,et al.A survey on wind power ramp forecasting[R].Argonne National Lab.(ANL),Argonne,IL(United States),2011.
• [31]KAMATH C.Using simple statistical analysis of historical data to understand wind ramp events[R].Lawrence Livermore National Lab.(LLNL),Livermore,CA(United States),2010.
• [32]CUI M J,ZHANG J,FLORITA A R,et al.An optimized swinging door algorithm for identifying wind ramping events[J]. IEEE Transactions on Sustainable Energy,2016,7(1):150-162.
• [33]MAKAROV Y V,LOUTAN C,MA J,et al.Operational impacts of wind generation on California power systems[J].IEEE Transactions on Power Systems,2009,24(2):1039-1050.
• [34]刘雅婷.考虑转折性天气的日前风电功率预测及爬坡事件检测方法研究[D].济南：山东大学，2023.LIU Yating.Research on the day-ahead wind power prediction and the detection of power ramp event considering transitional weather[D].Jinan:Shandong University,2023.
• [35]国家市场监督管理总局，国家标准化管理委员会.风电场接入电力系统技术规定第1部分：陆上风电：GB/T19963.1—2021[S].北京：中国标准出版社，2021.
• [36]郑天翔.基于功率预测的风电场功率爬坡事件优化控制方法研究[D].沈阳：沈阳工业大学，2023.ZHENG Tianxiang. Research on optimal control method of wind power ramp event based on power prediction[D].Shenyang:Shenyang University of Technology,2023.
• [37]WANG J N,ZHU H Q,ZHANG Y J,et al.A novel prediction model for wind power based on improved long short-term memory neural network[J].Energy,2023,265:126283.
• [38]KAMATH C. Associating weather conditions with ramp events in wind power generation[C]//2011 IEEE/PES Power Systems Conference and Exposition. March 20-23,2011,Phoenix,AZ,USA.IEEE,2011:1-8.
• [39]胡翔.基于数据驱动的风电功率爬坡检测和爬坡预测研究[D].成都：四川大学，2021.HU Xiang. Research on wind power ramp detection and prediction based on data driven[D]. Chengdu:Sichuan University,2021.
• [40]梁志，张哲，师宇，等.基于旋转门算法的风速和风功率爬坡事件的识别方法及特征分析[J].中国科学院大学学报（中英文），2024,41(6):821-829.LIANG Zhi,ZHANG Zhe,SHI Yu,et al. Detection method and characterization of ramp events of wind speed and wind power based on swinging door algorithm[J].Journal of University of Chinese Academy of Sciences,2024,41(6):821-829.