针对风电场各风电机组风速间复杂的时空相关性问题,提出一种基于（Ornstein-Uhlenbeck,OU）过程与Vine-Copula建模的多风电场短期风速预测方法。该方法首先根据风速的物理特性,研究风速与湍流强度之间的关系,并根据各季节风速的不同分布确立其相应的OU随机过程实现风速模拟;然后,通过构建Vine-Copula模型对风电场内多风电机组风速相关性进行分析;最后,将模拟值归一化处理后代入Vine-Copula的分位数回归模型,实现各风电机组的短期风速预测。应用OU随机过程,可为准确的风速预测奠定基础;通过Vine-Copula建模,可解决风速空间相关性问题。以中国北方某电场风电机组实测数据进行验证,在单步和多步预测中,所提方法的均方根误差RMSE相较于传统方法分别降低了2.68%、9.94%、23.79%、32.10%,提高了风速预测的准确性。
Abstract
Aiming at the complex temporal and spatial correlation of wind speed among wind turbines in wind farms, a short-term wind speed prediction method based on Ornstein-Uhlenbeck （OU） process and Vine-Copula modeling is proposed for multi-wind farms. Firstly, the relationship between wind speed and turbulence intensity is studied according to the physical characteristics of wind speed, and the corresponding OU random process is established according to the different distribution of wind speed in each season to simulate wind speed. Then, the Vine-Copula model is constructed to analyze the wind speed correlation of multiple wind turbines in the wind farm. Finally, the simulated values are normalized into the quantile regression model of Vine-Copula to realize the short-term wind speed prediction of each wind turbine. The application of OU stochastic process can lay a foundation for accurate wind speed prediction. The spatial correlation problem of wind speed can be solved by Vine-Copula modeling. Based on the measured data of a wind turbine in a power plant in North China, the root-mean-square error RMSE of the proposed method is reduced by 2.68%, 9.94%, 23.79% and 32.10%, respectively, compared with the traditional method, which improves the accuracy of wind speed prediction. Respectively, in single-step and multi-step prediction, which improves the accuracy of wind speed prediction compared with the
关键词
风电场 /
风电机组 /
风速 /
预测 /
随机过程 /
Vine-Copula /
奥恩斯坦-乌伦贝克过程
Key words
wind farm /
wind turbines /
wind speed /
prediction /
random processes /
Vine-Copula /
Ornstein-Uhlenbeck process
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 赵泽妮, 云斯宁, 贾凌云, 等. 基于统计模型的短期风能预测方法研究进展[J]. 太阳能学报, 2022, 43(11): 224-234.
ZHAO Z N, YUN S N, JIA L Y, et al.Recent progress in short-term forecasting of wind energy based on statistical models[J]. Acta energiae solaris sinica, 2022, 43(11): 224-234.
[2] 张家安, 刘东, 刘辉, 等. 基于风速波动特征提取的超短期风速预测[J]. 太阳能学报, 2022, 43(9): 308-313.
ZHANG J A, LIU D, LIU H, et al.Ultra short term wind speed prediction based on wind speed fluctuation feature extraction[J]. Acta energiae solaris sinica, 2022, 43(9): 308-313.
[3] 付文龙, 章轩瑞, 张海荣, 等. 基于INGO-SWGMN混合模型的超短期风速预测研究[J]. 太阳能学报, 2024, 45(5): 133-143.
FU W L, ZHANG X R, ZHANG H R, et al.Ultra-short-term wind speed prediction based on INGO-SWGMN hybrid model[J]. Acta energiae solaris sinica, 2024, 45(5): 133-143.
[4] SUN L, YOU F Q.Machine learning and data-driven techniques for the control of smart power generation systems: an uncertainty handling perspective[J]. Engineering, 2021, 7(9): 1239-1247.
[5] 李嘉文, 盛德仁, 李蔚, 等. 基于多目标优化和误差修正的短期风速预测[J]. 太阳能学报, 2022, 43(8): 273-280.
LI J W, SHENG D R, LI W, et al.Short-term wind speed prediction based on multi-objective optimization and error correction[J]. Acta energiae solaris sinica, 2022, 43(8): 273-280.
[6] 张董极, 肖琴. 基于复杂网络的风速预测新方法[J]. 太阳能学报, 2023, 44(3): 90-96.
ZHANG D J, XIAO Q.A new method of wind speed prediction based on complex network[J]. Acta energiae solaris sinica, 2023, 44(3): 90-96.
[7] 何锦华, 刘洋, 朱誉, 等. 融合物理信息的TPA-LSTM网络应用于台风条件下海上风电场风速多步预测[J]. 电网技术, 2023, 47(10): 4152-4161.
HE J H, LIU Y, ZHU Y, et al.Physics-informed TPA-LSTM network applied to multi-step wind speed prediction of offshore wind farms under typhoon conditions[J]. Power system technology, 2023, 47(10): 4152-4161.
[8] 贾凌云, 云斯宁, 赵泽妮, 等. 神经网络短期光伏发电预测的应用研究进展[J]. 太阳能学报, 2022, 43(12): 88-97.
JIA L Y, YUN S N, ZHAO Z N, et al.Recent progress of short-term forecasting of photovoltaic generation based on artificial neural networks[J]. Acta energiae solaris sinica, 2022, 43(12): 88-97.
[9] LIU X D, ZHANG L, WANG J G, et al.A unified multi-step wind speed forecasting framework based on numerical weather prediction grids and wind farm monitoring data[J]. Renewable energy, 2023, 211: 948-963.
[10] WANG J, YANG Z S.Ultra-short-term wind speed forecasting using an optimized artificial intelligence algorithm[J]. Renewable energy, 2021, 171: 1418-1435.
[11] ARENAS-LÓPEZ J P, BADAOUI M. Stochastic modelling of wind speeds based on turbulence intensity[J]. Renewable energy, 2020, 155: 10-22.
[12] ZÁRATE-MIÑANO R, MILANO F. Construction of SDE-based wind speed models with exponentially decaying autocorrelation[J]. Renewable energy, 2016, 94: 186-196.
[13] LOUKATOU A, HOWELL S, JOHNSON P, et al.Stochastic wind speed modelling for estimation of expected wind power output[J]. Applied energy, 2018, 228: 1328-1340.
[14] BENSOUSSAN A, BROUSTE A.Cox-Ingersoll-Ross model for wind speed modeling and forecasting[J]. Wind energy, 2016, 19(7): 1355-1365.
[15] LI Y T, PENG X H, ZHANG Y.Forecasting methods for wind power scenarios of multiple wind farms based on spatio-temporal dependency structure[J]. Renewable energy, 2022, 201: 950-960.
[16] HUANG Y, ZHANG B Z, PANG H Z, et al.Spatio-temporal wind speed prediction based on Clayton Copula function with deep learning fusion[J]. Renewable energy, 2022, 192: 526-536.
[17] KONSTANTELOS I, SUN M Y, TINDEMANS S H, et al.Using vine copulas to generate representative system states for machine learning[J]. IEEE transactions on power systems, 2019, 34(1): 225-235.
[18] DONG W C, SUN H X, TAN J X, et al.Regional wind power probabilistic forecasting based on an improved kernel density estimation, regular vine Copulas, and ensemble learning[J]. Energy, 2022, 238: 122045.
[19] SREEKUMAR S, KHAN N U, RANA A S, et al.Aggregated net-load forecasting using Markov-Chain Monte-Carlo regression and C-vine copula[J]. Applied energy, 2022, 328: 120171.
[20] 陈凡, 王浩, 刘海涛, 等. 基于改进Pair-Copula方法的多风电场风速时空相关性建模[J]. 可再生能源, 2023, 41(1): 60-66.
CHEN F, WANG H, LIU H T, et al.Temporal-spatial correlation modeling of wind speeds in multiple wind farms based on improved Pair-Copula method[J]. Renewable energy resources, 2023, 41(1): 60-66.
[21] 张博, 申建建, 程春田, 等. 基于C藤Copula理论的水风互补系统调峰方法[J]. 中国电机工程学报, 2022, 42(15): 5523-5535.
ZHANG B, SHEN J J, CHENG C T, et al.Peak-shaving method of hydro-wind power complementary system based on C-vine copula theory[J]. Proceedings of the CSEE, 2022, 42(15): 5523-5535.
[22] 邱宜彬, 李诗涵, 刘璐, 等. 基于场景D藤Copula模型的多风电场出力相关性建模[J]. 太阳能学报, 2019, 40(10): 2960-2966.
QIU Y B, LI S H, LIU L, et al.Correlation modeling of power output among multiple wind farms based on scenario D vine copula method[J]. Acta energiae solaris sinica, 2019, 40(10): 2960-2966.
[23] MA J R, FOULADIRAD M, GRALL A.Flexible wind speed generation model: Markov chain with an embedded diffusion process[J]. Energy, 2018, 164: 316-328.
基金
中央高校基本科研业务费专项资金（2021MS089）
PDF(7059 KB)
