
浏览全部资源
扫码关注微信
电力传输与功率变换控制教育部重点实验室(上海交通大学),上海市 200240
王耀健(1999—),男,硕士研究生,主要研究方向:风电负荷预测、电力系统优化规划、大数据与人工智能技术在电力系统中的应用。E-mail:wangyaojian@sjtu.edu.cn
顾洁(1971—),女,通信作者,博士,副教授,主要研究方向:大数据与人工智能技术在电力系统中的应用、电力市场及电力系统优化规划。E-mail:gujie@sjtu.edu.cn
温洪林(1995—),男,博士,主要研究方向:机器学习技术在电力系统中的应用、风电负荷预测、不确定性量化和决策。E-mail:linlin00@sjtu.edu.cn
收稿:2023-04-20,
修回:2023-11-04,
网络出版:2024-04-08,
纸质出版:2024-06-10
移动端阅览
王耀健,顾洁,温洪林等.基于在线高斯过程回归的短期风电功率概率预测[J].电力系统自动化,2024,48(11):197-207.
WANG Yaojian,GU Jie,WEN Honglin,et al.Short-term Wind Power Probability Prediction Based on Online Gaussian Process Regression[J].Automation of Electric Power Systems,2024,48(11):197-207.
王耀健,顾洁,温洪林等.基于在线高斯过程回归的短期风电功率概率预测[J].电力系统自动化,2024,48(11):197-207. DOI: 10.7500/AEPS20230420001.
WANG Yaojian,GU Jie,WEN Honglin,et al.Short-term Wind Power Probability Prediction Based on Online Gaussian Process Regression[J].Automation of Electric Power Systems,2024,48(11):197-207. DOI: 10.7500/AEPS20230420001.
预测未来几个小时的风电出力对于电力系统的安全经济运行以及风电参与电力市场至关重要。由于风电功率序列具有强随机性与非平稳性,需要对其不确定性进行刻画建模。同时,考虑到机组设备老化、叶片污染及风电场环境变化等因素会影响风电机组的出力特性,从而使得风电功率预测模型参数存在时变,增大了风电功率预测难度。文中提出了一种基于在线高斯过程的短期风电概率预测方法:首先,利用高斯过程回归模型对风电功率预测问题进行建模;然后,结合结构化内核插值与Woodbury恒等式,降低高斯过程计算复杂度,实现高斯过程的快速求解;最后,采用分块缓存与更新的方法实现高斯过程模型参数与超参数实时在线更新。经2014年全球能源预测大赛发布的风力发电数据验证,结果表明所提算法具有较好的预测性能,同时具有自适应性,可以有效应对模型参数时变问题。
Predicting the wind power output in the next few hours is crucial for the safe and economic operation of the power system as well as the participation of wind power in the electricity market. Due to the strong randomness and non-stationarity of the wind power sequence
it is necessary to characterize and model its uncertainty. Moreover
factors such as equipment aging
blade contamination
and changes in the wind farm environment can affect the output characteristics of wind turbines
thereby making the parameters of the wind power prediction model time-varying and increasing the difficulty of wind power prediction. This paper proposes a short-term wind power probability prediction method based on online Gaussian process. First
the Gaussian process regression model is used to model the wind power prediction problem. Then
the complexity of Gaussian process calculation is reduced by combining structured kernel interpolation with the Woodbury identity
which enables fast Gaussian process solving. Finally
the method of block caching and updating is adopted to realize the real-time online updating of parameters and hyperparameters for Gaussian process model. The wind power generation data released by the 2014 Global Energy Forecasting Competition is used to validate the proposed algorithm. The results show that the proposed algorithm has good prediction performance and adaptability to effectively deal with the problem of time-varying model parameters.
孟琰 , 肖居承 , 洪居华 , 等 . 计及需求响应不确定性的节点负荷准线:概念与模型 [J]. 电力系统自动化 , 2023 , 47 ( 13 ): 28 - 39 .
MENG Yan , XIAO Jucheng , HONG Juhua , et al . Nodal customer directrix load considering demand response uncertainty: concept and model [J]. Automation of Electric Power Systems , 2023 , 47 ( 13 ): 28 - 39 .
张亚超 , 刘开培 , 廖小兵 , 等 . 含大规模风电的电力系统多时间尺度源荷协调调度模型研究 [J]. 高电压技术 , 2019 , 45 ( 2 ): 600 - 608 .
ZHANG Yachao , LIU Kaipei , LIAO Xiaobing , et al . Multi-time scale source-load coordination dispatch model for power system with large-scale wind power [J]. High Voltage Engineering , 2019 , 45 ( 2 ): 600 - 608 .
KHOSRAVI A , NAHAVANDI S , CREIGHTON D . Prediction intervals for short-term wind farm power generation forecasts [J]. IEEE Transactions on Sustainable Energy , 2013 , 4 ( 3 ): 602 - 610 .
WAN C , XU Z , PINSON P , et al . Optimal prediction intervals of wind power generation [J]. IEEE Transactions on Power Systems , 2014 , 29 ( 3 ): 1166 - 1174 .
董骁翀 , 孙英云 , 蒲天骄 , 等 . 基于时序混合密度网络的超短期风电功率概率预测 [J]. 电力系统自动化 , 2022 , 46 ( 14 ): 93 - 100 .
DONG Xiaochong , SUN Yingyun , PU Tianjiao , et al . Ultra-short-term probabilistic forecasting of wind power based on temporal mixture density network [J]. Automation of Electric Power Systems , 2022 , 46 ( 14 ): 93 - 100 .
MAROÑAS J , HAMELIJNCK O , KNOBLAUCH J , et al . Transforming Gaussian processes with normalizing flows [EB/OL]. [ 2023-04-01 ]. http://arxiv.org/abs/2011.01596.pdf http://arxiv.org/abs/2011.01596.pdf .
YAN J , LI K , BAI E W , et al . Hybrid probabilistic wind power forecasting using temporally local Gaussian process [J]. IEEE Transactions on Sustainable Energy , 2016 , 7 ( 1 ): 87 - 95 .
KOU P , GAO F , GUAN X H . Sparse online warped Gaussian process for wind power probabilistic forecasting [J]. Applied Energy , 2013 , 108 : 410 - 428 .
WEN H L , MA J H , GU J , et al . Sparse variational Gaussian process based day-ahead probabilistic wind power forecasting [J]. IEEE Transactions on Sustainable Energy , 2022 , 13 ( 2 ): 957 - 970 .
MØLLER J K , NIELSEN H A , MADSEN H . Time-adaptive quantile regression [J]. Computational Statistics & Data Analysis , 2008 , 52 ( 3 ): 1292 - 1303 .
DOWELL J , PINSON P . Very-short-term probabilistic wind power forecasts by sparse vector autoregression [J]. IEEE Transactions on Smart Grid , 2016 , 7 ( 2 ): 763 - 770 .
杨楠 , 黄禹 , 叶迪 , 等 . 基于NACEMD和改进非参数核密度估计的风功率波动性概率分布研究 [J]. 电网技术 , 2019 , 43 ( 3 ): 910 - 917 .
YANG Nan , HUANG Yu , YE Di , et al . Study on probability distribution of wind power fluctuation based on NACEMD and improved nonparametric kernel density estimation [J]. Power System Technology , 2019 , 43 ( 3 ): 910 - 917 .
YAN J , LI K , BAI E W , et al . Hybrid probabilistic wind power forecasting using temporally local Gaussian process [J]. IEEE Transactions on Sustainable Energy , 2016 , 7 ( 1 ): 87 - 95 .
YAMASHITA T , SATO N , KINO H , et al . Crystal structure prediction accelerated by Bayesian optimization [J]. Physical Review Materials , 2018 , 2 : 013803 .
NGUYEN-TUONG D , PETERS J , SEEGER M . Local Gaussian process regression for real time online model learning and control [C]// Proceedings of the 21st International Conference on Neural Information Processing Systems , December 8-10 , 2008 , Vancouver, Canada : 1193 - 1200 .
BUI T D , NGUYEN C V , TURNER R E . Streaming sparse Gaussian process approximations [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems , December 4-9 , 2017 , Long Beach, USA : 3301 - 3309 .
万灿 , 宋永华 . 新能源电力系统概率预测理论与方法及其应用 [J]. 电力系统自动化 , 2021 , 45 ( 1 ): 2 - 16 .
WAN Can , SONG Yonghua . Theories, methodologies and applications of probabilistic forecasting for power systems with renewable energy sources [J]. Automation of Electric Power Systems , 2021 , 45 ( 1 ): 2 - 16 .
BAUER P , THORPE A , BRUNET G . The quiet revolution of numerical weather prediction [J]. Nature , 2015 , 525 ( 7567 ): 47 - 55 .
高杨 . 关于风力发电机组功率曲线的影响因素的分析 [EB/OL].[ 2023-03-20 ]. https://kns.cnki.net/kcms2/article/abstract?v=yO8aEz8cbf1_-LK4hqcEWOQdfZ2mH2-GskocwfzYsH9pc-TK CaaLu_n8TdVdYD4f_eT_LRiGfWDNLGVgck3bKOUI4kcKa4_wxI_9cmQpdFBvdSnAeVoxgVP1kuc4Wqcy2p0WmtH3qeJZw-s_ xaqlug==&uniplatform=NZKPT&language=CHS https://kns.cnki.net/kcms2/article/abstract?v=yO8aEz8cbf1_-LK4hqcEWOQdfZ2mH2-GskocwfzYsH9pc-TKCaaLu_n8TdVdYD4f_eT_LRiGfWDNLGVgck3bKOUI4kcKa4_wxI_9cmQpdFBvdSnAeVoxgVP1kuc4Wqcy2p0WmtH3qeJZw-s_xaqlug==&uniplatform=NZKPT&language=CHS .
GAO Yang . Analysis of influencing factors on the power curve of wind turbines [EB/OL]. [ 2023-03-20 ]. https://kns.cnki.net/kcms2/article/abstract?v=yO8aEz8cbf1_-LK4hqcEWOQ dfZ2mH2-GskocwfzYsH9pc-TKCaaLu_n8TdVdYD4f_eT_LRiGf WDNLGVgck3bKOUI4kcKa4_wxI_9cmQpdFBvdSnAeVoxgVP1kuc4Wqcy2p0WmtH3qeJZw-s_xaqlug==&uniplatform=NZKP T&language=CHS https://kns.cnki.net/kcms2/article/abstract?v=yO8aEz8cbf1_-LK4hqcEWOQdfZ2mH2-GskocwfzYsH9pc-TKCaaLu_n8TdVdYD4f_eT_LRiGfWDNLGVgck3bKOUI4kcKa4_wxI_9cmQpdFBvdSnAeVoxgVP1kuc4Wqcy2p0WmtH3qeJZw-s_xaqlug==&uniplatform=NZKPT&language=CHS .
黄宸武 , 谌海莲 , 王文莉 , 等 . 风力机叶片污染影响分析及抗污翼型设计探讨 [J]. 可再生能源 , 2014 , 32 ( 4 ): 442 - 449 .
HUANG Chenwu , CHEN Hailian , WANG Wenli , et al . Analysis of contamination effect on aerodynamic performance of wind turbine blade and study on anti-contaminating airfoil design [J]. Renewable Energy Resources , 2014 , 32 ( 4 ): 442 - 449 .
STANTON S , MADDOX W J , DELBRIDGE I , et al . Kernel interpolation for scalable online Gaussian processes [EB/OL]. [ 2023-04-01 ]. http://arxiv.org/abs/2103.01454.pdf http://arxiv.org/abs/2103.01454.pdf .
SILVERMAN B W . Some aspects of the spline smoothing approach to non-parametric regression curve fitting [J]. Journal of the Royal Statistical Society , Series B(Methodological), 1985 , 47 ( 1 ): 1 - 52 .
YUNUS S . Scalable inference for structured Gaussian process models [D]. Cambridge, UK : University of Cambridge , 2012 .
HONG T , PINSON P , FAN S , et al . Probabilistic energy forecasting: global energy forecasting competition 2014 and beyond [J]. International Journal of Forecasting , 2016 , 32 ( 3 ): 896 - 913 .
GNEITING T , KATZFUSS M . Probabilistic forecasting [J]. Annual Review of Statistics and Its Application , 2014 , 1 : 125 - 151 .
MATHESON JAMES E , ROBERT L WINKLER . Scoring rules for continuous probability distributions [EB/OL]. [ 2023-04-01 ]. http://www.jstor.org/stable/2629907 http://www.jstor.org/stable/2629907 .
GAMA J , MEDAS P , CASTILLO G , et al . Learning with drift detection [C]// Proceedings of the 7th Brazilian Symposium on Artificial Intelligence , September 29-October 1 , 2004 , Sao Luis, Brazil .
BIFET A , GAVALDÀ R . Learning from time-changing data with adaptive windowing [C]// Proceedings of the 2007 SIAM International Conference on Data Mining , April 26-28 , 2007 , Minneapolis, USA .
HUANG D T J , KOH Y S , DOBBIE G , et al . Detecting volatility shift in data streams [C]// 2014 IEEE International Conference on Data Mining , December 14-17 , 2014 , Shenzhen, China .
BIFET A , READ J , PFAHRINGER B , et al . CD-MOA: change detection framework for massive online analysis [M]. Berlin, Germany : Springer Berlin Heidelberg , 2013 : 92 - 103 .
孟凡兴 , 韩萌 , 李春鹏 , 等 . 概念漂移检测与适应方法综述 [J/OL]. 计算机工程与应用 : 1 - 16 [ 2023-09-18 ]. http://kns.cnki.net/kcms/detail/11.2127.TP.20230817.1347.012.html http://kns.cnki.net/kcms/detail/11.2127.TP.20230817.1347.012.html .
MENG Fanxing , HAN Meng , LI Chunpeng , et al . A survey of concept drift detection and adaptation methods [J/OL]. Computer Engineering and Applications : 1 - 16 [ 2023-09-18 ]. http://kns.cnki.net/kcms/detail/11.2127.TP.20230817.13 47.012.html http://kns.cnki.net/kcms/detail/11.2127.TP.20230817.1347.012.html .
DETLEFSEN N S , JØRGENSEN M , HAUBERG S . Reliable training and estimation of variance networks [EB/OL]. [ 2023-09-18 ]. http://arxiv.org/abs/1906.03260.pdf http://arxiv.org/abs/1906.03260.pdf .
0
浏览量
0
下载量
4
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621