针对海上风电时空关联特性显著的特点,提出一种考虑机组出力特性差异的时空关联功率预测模型。首先,利用密度聚类算法对风电机组进行分类,识别不同出力模式的机组群体;其次,通过相关性分析筛选出具有代表性的机组集合,为后续建模提供关键输入特征;最后,基于轻量级梯度提升机开展功率预测建模,实现高效、精准的风电功率预测。经过与实际运行数据的比对,结果表明,该模型能有效提高功率预测精度,并在一定程度上增强预测模型的泛化能力。
Abstract
Focusing on the significant spatio-temporal correlation characteristics of offshore wind power, a spatio-temporal correlation power forecasting model considering the differences in unit output patterns is proposed. Firstly, the density-based clustering algorithm is used to classify the output characteristics of wind turbines, so as to identify the groups of units with different output patterns; secondly, a representative set of units is selected through correlation analysis, providing key inputs for modeling. Finally, a power forecasting model is constructed based on the light gradient boosting machine to achieve efficient and accurate predictions. After verification with actual operation data, the result shows that this model can effectively improve the accuracy of power forecasting and enhance the generalization ability of the forecasting model to a certain extent.
关键词
海上风电 /
功率预测 /
时空关联 /
出力特性 /
聚类 /
轻量梯度提升机
Key words
offshore wind power /
wind power forecasting /
spatio-temporal correlation /
output patterns /
clustering /
light gradient boosting machine
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 国家能源局. 2025年可再生能源并网运行情况[EB/OL].[2026-02-12].https://www.nea.gov.cn/20260212/742b8c6a078347b0b39de676c05c5d58/c.html.
National Energy Administration. Description of renewable energy integration in2025[EB/OL].[2026-02-12]. https://www.nea.gov.cn/20260212/742b8c6a078347b0b39de676c05c5d58/c.html.
[2] Díaz H, Guedes Soares C.Review of the current status, technology and future trends of offshore wind farms[J]. Ocean Engineering, 2020, 209: 107381.
[3] 符杨, 郑紫宸, 时帅, 等. 考虑气象相似性与数值天气预报修正的海上风功率预测[J]. 电网技术, 2019(4): 1253-1260.
Fu Y, Zheng Z C, Shi S, et al.Offshore wind power forecasting considering meteorological similarity and NWP correction[J]. Power System Technology, 2019(4): 1253-1260.
[4] 梅睿, 吕志勇, 顾文, 等. 基于主成分分析和谱聚类的短期风功率预测[J]. 现代电力, 2023, 40(1): 35-41.
Mei R, Lyu Z Y, Gu W, et al.Short-term wind power prediction based on principal component analysis and spectral clustering[J]. Modern Electric Power, 2023, 40(1): 35-41.
[5] 曾东, 杨兴旺, 吴继秀, 等. 海上风电场多时间尺度功率预测方法研究[J]. 电力系统装备, 2023(10): 5-8.
Zeng D, Yang X W, Wu J X, et al.Offshore wind farm more time scale power prediction method[J]. Electric Power System Equipment, 2023(10): 5-8.
[6] 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): 4859-4870.
Yu G Z, Lu L, Tang B, 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): 4859-4870.
[7] 黄玲玲, 石孝华, 符杨, 等. 基于DCGCN模型的海上风电场超短期功率预测[J]. 电力系统自动化, 2024, 48(15): 64-72.
Huang L L, Shi X H, Fu Y, et al.Ultra-short-term power prediction for offshore wind farms based on dual channel graph convolution network model[J]. Automation of Electric Power Systems, 2024, 48(15): 64-72.
[8] 符杨, 任子旭, 魏书荣, 等. 基于改进LSTM-TCN模型的海上风电超短期功率预测[J]. 中国电机工程学报, 2022, 42(12): 4292-4302.
Fu Y, Ren Z X, Wei S R, et al.Ultra-short-term power prediction of offshore wind power based on improved LSTM-TCN model[J]. Proceedings of the CSEE, 2022, 42(12): 4292-4302.
[9] 葛畅, 阎洁, 刘永前, 等. 海上风电场运行控制维护关键技术综述[J]. 中国电机工程学报, 2022, 42(12): 4278-4291.
Ge C, Yan J, Liu Y Q, et al.Review of key technologies for operation control and maintenance of offshore wind farm[J]. Proceedings of the CSEE, 2022, 42(12): 4278-4291.
[10] 罗朗川, 李汝辉, 曾东, 等. 基于RANSAC-DBSCAN的风速功率曲线异常数据清洗方法[J]. 太阳能学报, 2025, 46(4): 445-453.
Luo L C, Li R H, Zeng D, et al.Abnormal data cleaning method of wind speed-power curve based on RANSAC-DBSCAN[J]. Acta Energiae Solaris Sinica, 2025, 46(4): 445-453.
[11] Feng C, Cui M J, Hodge B M, et al.A data-driven multi-model methodology with deep feature selection for short-term wind forecasting[J]. Applied Energy, 2017, 190: 1245-1257.
[12] 乔宽龙, 董存, 车建峰, 等. 时空特性下基于图卷积神经网络的风电集群功率短期预测方法[J]. 太阳能学报, 2024, 45(5): 95-103.
Qiao K L, Dong C, Che J F, et al.Short-term prediction method of wind power clusters based on graph convolution neural network under spitio-temporal characteristics[J]. Acta Energiae Solaris Sinica, 2024, 45(5): 95-103.
[13] Székely G J, Rizzo M L, Bakirov N K.Measuring and testing dependence by correlation of distances[J]. The Annals of Statistics, 2007, 35(6): 2769-2794.
[14] 胡澜也, 蒋文博, 李艳婷. 基于LightGBM的风力发电机故障诊断[J]. 太阳能学报, 2021, 42(11): 255-259.
Hu L Y, Jiang W B, Li Y T.Fault diagnosis for wind turbine based on LightGBM[J]. Acta Energiae Solaris Sinica, 2021, 42(11): 255-259.
基金
中国长江三峡集团有限公司科研项目（NBZZ202300197）
PDF(1478 KB)
