风速波动特征复杂,对其精确建模对于风电系统安全、稳定、经济运行具有重要意义。为提高风速建模的精度,提出一种风速波动的非独立增量过程（PWNI）建模方法。首先,对风速时序波动特征进行分析,分别阐述风速的短期波动特征和长期波动特征;然后,针对风速短期波动特征,应用统计方法对一定风速范围的时序变化特征进行分析,建立其短期波动模型,并基于长短期记忆神经网络（LSTM）对风速范围进行外推,从而在全风速范围内建立精确的短期波动模型;其次,针对风速长期波动特征,利用权重分析法将其引入模型中,建立考虑长期波动特征的优化模型。以中国华北张家口地区某风电场运行数据为算例,验证了所提建模方法的有效性,算例结果表明,所提方法能实现对风速多尺度波动特征的准确描述。
Abstract
The characteristics of wind speed fluctuation are complex, and accurate modeling for wind speed fluctuation characteristics is of great significance to the safe, stable and economic operation of wind power system. In order to improve the accuracy of wind speed modeling, a non-independent incremental process modeling method for wind speed fluctuation is proposed in this paper. Firstly, the time series fluctuation characteristics of wind speed are analyzed, and the short-term fluctuation characteristics and long-term fluctuation characteristics of wind speed are described respectively. Then, according to the short-term fluctuation characteristics of wind speed, the statistical method is used to analyze the time-series variation characteristics of a certain wind speed range, establish its short-term fluctuation model, and extrapolate the wind speed range based on LSTM neural network, so as to establish an accurate short-term fluctuation model in the whole wind speed range; According to the long-term fluctuation characteristics of wind speed, the weight analysis method is used to introduce it into the model, and an optimization model considering the long-term fluctuation characteristics is established. The validity of the modeling method is verified by taking the operation data of a wind farm in Zhangjiakou, North China as an example.
关键词
风电场 /
风速 /
统计方法 /
时序 /
波动性建模 /
非独立增量过程
Key words
wind farm /
wind speed /
statistical methods /
time series /
fluctuation modeling /
non-independent incremental process
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] DAYAL K K, CATER J E, KINGAN M J, et al.Wind resource assessment and energy potential of selected locations in Fiji[J]. Renewable energy, 2021, 172:219-237.
[2] MASSERAN N.Modeling the fluctuations of wind speed data by considering their mean and volatility effects[J]. Renewable and sustainable energy reviews, 2016, 54: 777-784.
[3] GUO Z H, ZHAO J, ZHANG W Y, et al.A corrected hybrid approach for wind speed prediction in Hexi Corridor of China[J]. Energy, 2011, 36(3): 1668-1679.
[4] BARCONS J, AVILA M, FOLCH A.Diurnal cycle RANS simulations applied to wind resource assessment[J]. Wind energy, 2019, 22(2):269-282.
[5] 万书亭, 万杰. 基于量化指标和概率密度分布的风电功率波动特性研究[J]. 太阳能学报, 2015, 36(2): 362-368.
WAN S T, WAN J.Research on wind power fluctuation characteristics based on quantitative index and probability density distribution[J]. Acta energiae solaris sinica, 2015, 36(2): 362-368.
[6] 崔杨, 杨海威, 李鸿博. 基于高斯混合模型的风电场群功率波动概率密度分布函数研究[J]. 电网技术, 2016, 40(4): 1107-1112.
CUI Y, YANG H W, LI H B.Probability density distribution function of wind power fluctuation of a wind farm group based on the Gaussian mixture model[J]. Power system technology, 2016, 40(4):1107-1112.
[7] XIN P Z, LIU Y, YANG N, et al.Probability distribution of wind power volatility based on the moving average method and improved nonparametric kernel density estimation[J]. Global energy interconnection, 2020, 3(3): 247-258.
[8] GUO P, CHEN S, CHU J C, et al.Wind direction fluctuation analysis for wind turbines[J]. Renewable energy, 2020, 162: 1026-1035.
[9] 白格平, 任国瑞, 苏雁飞, 等. 乌兰察布地区风资源波动性及聚合特性分析[J]. 电网与清洁能源, 2022, 38(7): 81-91, 106.
BAI G P, REN G R, SU Y F, et al.Analysis of characteristics of wind resource fluctuation and aggregation in Ulanqab[J]. Power system and clean energy, 2022, 38(7): 81-91, 106.
[10] 郭鹏, 陈思. 基于运行数据的风电机组本地风向波动特性及偏航控制研究[J]. 太阳能学报, 2020, 41(6): 77-85.
GUO P, CHEN S.Research of local wind direction fluctuation characteristic and yaw control based on SCADA wind turbine data[J]. Acta energiae solaris sinica, 2020, 41(6):77-85.
[11] CALIF R, EMILION R, SOUBDHAN T.Classification of wind speed distributions using a mixture of Dirichlet distributions[J]. Renewable energy, 2011, 36(11): 3091-3097.
[12] CALIF R.PDF models and synthetic model for the wind speed fluctuations based on the resolution of Langevin equation[J]. Applied energy, 2012, 99: 173-182.
[13] 叶林, 饶日晟, 杨丹萍, 等. 基于波动互相关系数的风能资源评估组合模型[J]. 中国电机工程学报, 2017, 37(3): 712-720.
YE L, RAO R S, YANG D P, et al.A combined wind resource assessment model based on fluctuation cross-correlation coefficient[J]. Proceedings of the CSEE, 2017, 37(3): 712-720.
[14] 舒磊. 基于神经网络与时间序列的风速预测研究[D]. 西安: 西安工业大学, 2021.
SHU L.Wind speed prediction based on neural network and time series[D]. Xi’an: Xi’an Technological University, 2021.
[15] 王蔚卿. 基于波动过程模式识别的风速超短期预测模型[D]. 北京: 华北电力大学, 2020.
WANG W Q.An ultra-short-term wind speed forecasting model based on fluctuation process pattern recognition[D]. Beijing: North China Electric Power University, 2020.
[16] LIU H, DUAN Z, CHEN C.Wind speed big data forecasting using time-variant multi-resolution ensemble model with clustering auto-encoder[J]. Applied energy, 2020, 280: 115975.
[17] TAN J, WU Q W, ZHANG M L, et al.Wind power scenario generation with non-separable spatio-temporal covariance function and fluctuation-based clustering[J]. International journal of electrical power & energy systems, 2021, 130: 106955.
[18] LIU C Y, ZHANG X M, MEI S W, et al.Numerical weather prediction enhanced wind power forecasting: rank ensemble and probabilistic fluctuation awareness[J]. Applied energy, 2022, 313:118769.
[19] 张家安, 仇实, 宋关羽, 等. 考虑时序波动的风速分布描述方法[J]. 太阳能学报, 2020, 41(8): 330-336.
ZHANG J A, QIU S, SONG G Y, et al.Wind speed distribution description method considering time series fluctuation[J]. Acta energiae solaris sinica, 2020, 41(8): 330-336.
[20] GUALTIERI G.A comprehensive review on wind resource extrapolation models applied in wind energy[J]. Renewable and sustainable energy reviews, 2019, 102: 215-233.
[21] HE R Y, YANG H X, SUN H Y, et al.A novel three-dimensional wake model based on anisotropic Gaussian distribution for wind turbine wakes[J]. Applied energy, 2021, 296:117059.
[22] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[23] GRAVES A.Supervised Sequence Labelling with Recurrent Neural Networks[J]. Studies in computational intelligence, 2012, 385: 5-13.
[24] SONG J Y, ZHU A B, TU Y, et al.Effects of different feature parameters of sEMG on human motion pattern recognition using multilayer perceptrons and LSTM neural networks[J]. Applied sciences, 2020, 10(10):3358.
[25] VALSARAJ P, THUMBA D A, ASOKAN K, et al.Symbolic regression-based improved method for wind speed extrapolation from lower to higher altitudes for wind energy applications[J]. Applied energy, 2020, 260: 114270.
[26] LU P, YE L, ZHAO Y N, et al.Feature extraction of meteorological factors for wind power prediction based on variable weight combined method[J]. Renewable energy, 2021, 179: 1925-1939.
基金
河北省自然科学基金（E2020202142）
PDF(3686 KB)
