王恩荣,苏向敬,龚骏豪,刘正羽,符杨
WANG Enrong,SU Xiangjing,GONG Junhao,LIU Zhengyu,FU Yang

• 1:上海电力大学电气工程学院
• 2:上海电力大学海上风电研究院
• 3:海上风电技术教育部工程研究中心(上海电力大学)

摘要(Abstract)：

台风天气易引发海上风电功率剧烈波动，严重威胁电力系统的安全稳定运行，实现精准的风电爬坡事件预测对保障电网安全具有重要意义。针对现有方法在挖掘海上风电场复杂动态时空关联方面存在不足、爬坡预测精度有限的问题，提出了一种面向台风天气的海上风电爬坡事件预测方法。首先，利用AGCN（自适应图卷积网络）挖掘复杂变化的海上风电场空间特征；其次，采用BiLSTM（双向长短期记忆网络）提取时间序列中的双向依赖关系，并引入AM（注意力机制）强化对重要特征和时序信息的学习；在此基础上，结合Bump事件合并与极值点修正策略对传统SDA（旋转门算法）进行改进，提升爬坡事件的检测精度；最后，基于上海某风电场SCADA数据的实验结果表明，所提出的AGCN-BiLSTM-AM组合模型能够有效挖掘海上风电场的复杂动态时空关系，在台风天气下风电爬坡事件预测中表现出较高的精度和良好的适用性。
Typhoon weather conditions induce severe fluctuations in offshore wind power generation, posing a significant threat to the secure and stable operation of power systems. Accurate prediction of wind power ramp events is therefore crucial for ensuring grid security. To address the limitations of existing methods in capturing the complex and dynamic spatiotemporal correlations of offshore wind farms and their limited ramp prediction accuracy, this paper proposes a novel prediction method for offshore wind power ramp events in typhoon weather conditions. Firstly, an adaptive graph convolutional network(AGCN) is employed to capture the complex and varying spatial features of the offshore wind farm. Secondly, a bidirectional long short-term memory(BiLSTM) network is adopted to extract bidirectional dependencies within the time series, while an attention mechanism(AM) is introduced to enhance the learning of critical features and temporal information. Building on this, the traditional swing door algorithm(SDA) is improved by incorporating a Bump event merging strategy and an extreme point correction strategy to enhance the detection accuracy of ramp events. Finally, experimental results based on SCADA data from a wind farm in Shanghai demonstrate that the proposed combined AGCN-BiLSTM-AM model can effectively capture the complex dynamic spatiotemporal relationships of the offshore wind farm, exhibiting high accuracy and strong applicability for predicting wind power ramp events under typhoon conditions.

关键词(KeyWords)： 台风天气;风电爬坡事件预测;自适应图卷积网络;双向长短期记忆网络;注意力机制
typhoon weather;wind power ramp event prediction;AGCN;BiLSTM;AM

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划(2023YFB2406900)

作者(Author): 王恩荣,苏向敬,龚骏豪,刘正羽,符杨
WANG Enrong,SU Xiangjing,GONG Junhao,LIU Zhengyu,FU Yang

DOI: 10.19585/j.zjdl.202602008

参考文献(References)：

• [1]刘吉臻，马利飞，王庆华，等.海上风电支撑我国能源转型发展的思考[J].中国工程科学，2021,23(1):149-159.LIU Jizhen,MA Lifei,WANG Qinghua,et al. Offshore wind power supports China’s energy transition[J].Strategic Study of CAE,2021,23(1):149-159.
• [2]夏云峰.2022年全球风电新增装机77.6 GW[J].风能，2023(5):56-60.XIA Yunfeng.In 2022,the new installed capacity of global wind power will be 77.6 GW[J].Wind Energy,2023(5):56-60.
• [3]谢善益，杨强，谢恩彦，等.考虑受端电网运行安全的台风条件下海上风电场协调运行策略[J].浙江电力，2023,42(10):17-24.XIE Shanyi,YANG Qiang,XIE Enyan,et al.The coordinated operation strategy for offshore wind farms with energy storage under typhoon conditions considering the operation safety demand of receiver grid[J].Zhejiang Electric Power,2023,42(10):17-24.
• [4]叶林，路朋，滕景竹，等.考虑风电功率爬坡的功率预测—校正模型[J].电力系统自动化，2019,43(6):49-56.YE Lin,LU Peng,TENG Jingzhu,et al.Power prediction and correction model considering wind power ramping events[J].Automation of Electric Power Systems,2019,43(6):49-56.
• [5]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.
• [6]屈尹鹏，徐箭，姜尚光，等.基于频繁模式挖掘的风电爬坡事件统计特性建模及预测[J].电力系统自动化，2021,45(1):36-43.QU Yinpeng,XU Jian,JIANG Shangguang,et al. Frequent pattern mining based modeling and forecasting for statistical characteristics of wind power ramp events[J].Automation of Electric Power Systems,2021,45(1):36-43.
• [7]ZHA X M,OUYANG T H,QIN L,et al. Selection of time window for wind power ramp prediction based on risk model[J]. Energy Conversion and Management,2016,126:748-758.
• [8]欧阳庭辉，查晓明，秦亮，等.基于相似性修正的风电功率爬坡事件预测方法[J].中国电机工程学报，2017,37(2):572-581.OUYANG Tinghui,ZHA Xiaoming,QIN Liang,et al.Wind power ramps prediction method based on amendment of similar events[J].Proceedings of the CSEE,2017,37(2):572-581.
• [9]张群，唐振浩，王恭，等.基于长短时记忆网络的超短期风功率预测模型[J].太阳能学报，2021,42(10):275-281.ZHANG Qun,TANG Zhenhao,WANG Gong,et al.Ultra-short-term wind power prediction model based on long and short term memory network[J]. Acta Energiae Solaris Sinica,2021,42(10):275-281.
• [10]CUI Y,CHEN Z H,HE Y J,et al.An algorithm for forecasting day-ahead wind power via novel long short-term memory and wind power ramp events[J].Energy,2023,263:125888.
• [11]ZHOU B B,SUN B,GONG X,et al.Ultra-short-term prediction of wind power based on EMD and DLSTM[C]//2019 14th IEEE Conference on Industrial Electronics and Applications(ICIEA). June 19-21,2019. Xi’an,China.IEEE,2019:1909-1913.
• [12]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.
• [13]段浩然.基于半监督生成对抗网络的风电功率与爬坡预测方法[D].长沙：湖南大学，2021.DUAN Haoran.Wind power and ramp prediction method based on semi-supervised generative adversarial network[D].Changsha:Hunan University,2021.
• [14]吕云龙，胡琴，熊俊杰，等.基于时空注意力卷积模型的超短期风电功率预测[J].电网技术，2024,48(5):2064-2073.L??Yunlong,HU Qin,XIONG Junjie,et al.Ultra-shortterm wind power prediction based on spatiotemporal attention convolution model[J]. Power System Technology,2024,48(5):2064-2073.
• [15]HE Y Y,ZHU C,AN X L.A trend-based method for the prediction of offshore wind power ramp[J].Renewable Energy,2023,209:248-261.
• [16]钟吴君，李培强，涂春鸣.基于尾流关联的动态超图风电功率超短期预测方法[J].中国电机工程学报，2025,45(12):4693-4707.ZHONG Wujun,LI Peiqiang,TU Chunming.Dynamic hypergraph wind power ultra short term prediction method based on wake correlation[J].Proceedings of the CSEE,2025,45(12):4693-4707.
• [17]LIAO W L,BAK-JENSEN B,PILLAI J R,et al.A review of graph neural networks and their applications in power systems[J].Journal of Modern Power Systems and Clean Energy,2022,10(2):345-360.
• [18]JI Shan，姜巍，景鑫.基于余弦相似度和图卷积网络的电力负荷预测方法[J].浙江电力，2025,44(1):68-75.JI Shan,JIANG Wei,JING Xin.A power load forecasting method using cosine similarity and a graph convolutional network[J].Zhejiang Electric Power,2025,44(1):68-75.
• [19]苏向敬，周汶鑫，李超杰，等.基于双重注意力LSTM神经网络的可解释海上风电出力预测[J].电力系统自动化，2022,46(7):141-151.SU Xiangjing,ZHOU Wenxin,LI Chaojie,et al.Interpretable offshore wind power output forecasting based on long short-term memory neural network with dual-stage attention[J].Automation of Electric Power Systems,2022,46(7):141-151.
• [20]郭燕玲，赵晶，周林，等.山东半岛风电爬坡事件的识别与天气分析研究[J].气候与环境研究，2017,22(1):97-107.GUO Yanling,ZHAO Jing,ZHOU Lin,et al.A study on the identification and synoptic analysis of wind ramp events in Shandong Peninsula[J]. Climatic and Environmental Research,2017,22(1):97-107.
• [21]余光正，陆柳，汤波，等.考虑转折性天气的海上风电功率超短期分段预测方法研究[J].中国电机工程学报，2022,42(13):4859-4871.YU Guangzheng,LU Liu,TANG Bo,et al.Research on ultra-short-term subsection forecasting method of offshore wind power considering transitional weather[J] Proceedings of the CSEE,2022,42(13):4859-4871.