针对现有方法模型简单、气象因素考虑不足和缺少异常数据检测等问题,提出一种基于相对密度离群因子（relative RDOF）异常检测和支持向量回归（SVR）组合的场地校准模型。首先,通过RDOF与四分位法对测风塔与风电机组距下垫面相同高度风速间的风速比进行异常数据检测,间接实现风速预处理;同时,根据测风塔与风电机组相同高度风切变序列的相关性,动态引入大气稳定度等级,与多种常规自然因素共同作为模型输入。然后,建立SVR场地校准模型修正风速。最后,通过算例验证,并与国际电工委员会（IEC）标准方法进行对比。结果表明,该方法可有效提升场地校准模型的风速修正精度。
Abstract
Aiming at the problems of simple model, insufficient consideration of meteorological factors and lack of abnormal detection, a site calibration model based on relative density outlier factor （relative density outlier factor, RDOF） anomaly detection and support vector regression （support vector regression,SVR） is proposed. Firstly, the RDOF and quartile methods are used to detect the abnormal data of the wind speed ratio at the same height between the wind tower and the wind turbine from the underlying surface, and the wind speed preprocessing is indirectly realized. At the same time, according to the correlation between the wind shear sequence at the same height of the wind tower and the wind turbine, the atmospheric stability grade is dynamically introduced, and a variety of conventional natural factors are used as model input. Then, the SVR site calibration model is established to correct the wind speed. Finally, it is verified by a calculation example and compared with the standard method of the International Electrotechnical Commission（IEC）. The results show that the method can effectively improve the accuracy of wind speed correction of site calibration model.
关键词
风力发电 /
异常检测 /
支持向量回归 /
大气稳定度 /
风速修正
Key words
wind power /
anomaly detection /
support vector regression /
atmospheric stability /
wind speed correction
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 许昌, 杨建川, 李辰奇, 等. 复杂地形风电场微观选址优化[J].中国电机工程学报, 2013, 33(31): 58-64, 7.
XU C, YANG J C, LI C Q, et al.Micro-location optimization of wind farm on complex terrain[J]. Proceedings of the CSEE, 2013, 33(31): 58-64, 7.
[2] IEC 61400-12-1, Wind energy generation systems-Part 12-1: power performance measurements of electricity producing wind turbines[S].
[3] CANDY B, ENGLISH S J, KEOGH S J.A comparison of the impact of QuikScat and WindSat wind vector products on met office analyses and forecasts[J]. IEEE transactions on geoscience and remote sensing, 2009, 47(6): 1632-1640.
[4] 李莉, 刘永前, 杨勇平, 等. 基于CFD流场预计算的短期风速预测方法[J]. 中国电机工程学报, 2013, 33(7): 27-32.
LI L, LIU Y Q, YANG Y P, et al.A short-term wind speed prediction method based on CFD flow field prediction[J]. Proceedings of the CSEE, 2013, 33(7): 27-32.
[5] 冯双磊, 王伟胜, 刘纯, 等. 风电场功率预测物理方法研究[J]. 中国电机工程学报, 2010, 30(2): 1-6.
FENG S L, WANG W S, LIU C, et al.Research on physical method of wind power prediction[J]. Proceedings of the CSEE, 2010, 30(2): 1-6.
[6] CELLURA M, CIRRINCIONE G, MARVUGLIA A, et al.Wind speed spatial estimation for energy planning in Sicily: introduction and statistical analysis[J]. Renewable energy, 2008, 33(6): 1237-1250.
[7] PELIKAN E, EBEN K, RESLER J, et al.Wind power forecast by an empirical model using NWP output[C]//International Conference on Environment and Electrical Engineering, Prague, Czech Republic: IEEE, 2010: 45-48.
[8] STATHOPOULOS C, KAPERONI A, GALANIS G, et al.Wind power prediction based on numerical and statistical models[J]. Journal of wind engineering & industrial aerodynamics, 2013, 112: 25-38.
[9] 刘兴杰, 岑添云, 郑文书, 等. 基于模糊粗糙集与改进聚类的神经网络风速预测[J]. 中国电机工程学报,2014, 34(19): 3162-3169.
LIU X J, CEN T Y, ZHENG W S, et al.Wind speed prediction based on fuzzy rough set and improved clustering based on neural network[J]. Proceedings of the CSEE, 2014, 34(19): 3162-3169.
[10] KOU P, WANG C, LIANG D L, et al.Deep learning approach for wind speed forecasts at turbine locations in a wind farm[J]. IET renewable power generation, 2020, 14(13): 2416-2428.
[11] BLANCHARD T, SAMANTA B.Wind speed forecasting using neural networks[J]. Wind engineering, 2020, 44(1): 33-48.
[12] 彭宇, 何永福, 王少军, 等. 飞行数据异常检测技术综述[J]. 仪器仪表学报, 2019, 40(3): 1-13.
PENG Y, HE Y F, WANG S J, et al.Review of anomaly detection technology[J]. Chinese journal of scientific instrument, 2019, 40(3): 1-13.
[13] NING J, CHEN L, CHEN J.Relative density-based outlier detection algorithm[C]//Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence, Shenzhen, China: AEIC 2018: 227-231.
[14] YU M, SUN S.Policy-based reinforcement learning for time series anomaly detection[J]. Engineering applications of artificial intelligence, 2020, 95, 103919.
[15] LI J, PEDRYCZ W, JAMAL I.Multivariate time series anomaly detection: a framework of Hidden Markov Models[J]. Applied soft computing journal, 2017, 60: 226-240.
[16] 徐宝清, 吴婷婷, 李文慧. 风能风切变指数计算方法的比选研究[J]. 农业工程学报, 2014, 30(16): 188-194.
XU B Q, WU T T, LI W H.Comparison and selection of calculation methods for wind energy wind shear index[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(16): 188-194.
[17] LABAN O N, MAGHANGA C M, JOASH K, et al.Determination of the surface roughness parameter and wind shear exponent of Kisii region from the on-site measurement of wind profiles[J]. Journal of energy, 2019,2019: 8264061.
[18] 康凌, 张宏升, 王志远, 等. 不同下垫面大气稳定度分类方法的对比研究[J]. 北京大学学报(自然科学版), 2011, 47(1): 66-70.
KANG L, ZHANG H S, WANG Z Y, et al.Comparison of classification methods of atmospheric stability over different underlying surfaces[J]. Acta scientiarum naturalium universitatis pekinensis, 2011, 47(1): 66-70.
[19] MORI Y.Evaluation of several “single-pass” estimators of the mean and the standard deviation of wind direction[J]. Journal of climate and applied meteorology, 1986, 25(10): 1387-1397.
[20] FARRUGIA P S, MICALLEF A.Vectorial statistics for the standard deviation of wind direction[J]. Meteorology and atmospheric physics, 2017, 129(5): 495-506.
[21] 刘霄, 赖旭. 复杂下垫面风电场风速垂直外推方法研究[J]. 太阳能学报, 2020, 41(6): 61-68.
LIU X, LAI X.Wind speed vertical extrapolation method for wind farms with complex underlying surface[J]. Acta energiae solaris sinica, 2020, 41(6): 61-68.
[22] 赵永宁, 叶林. 风电场弃风异常数据簇的特征及处理方法[J]. 电力系统自动化, 2014, 38(21): 39-46.
ZHAO Y N, YE L.Characteristics and processing method of wind abandoning abnormal data cluster in wind farm[J]. Automation of electric power systems, 2014, 38(21): 39-46.
[23] 宫彦双, 谷坛, 安超, 等. 基于Pearson相关系数的集输管道流动腐蚀主控因素分析[J]. 石油与天然气化工, 2021, 50(2): 93-99.
GONG Y S, GU T, AN C, et al.Analysis on main controlling factors of flow corrosion in gathering and transportation pipelines based on Pearson correlation coefficient[J]. Chemical engineering of oil and gas, 2021, 50(2): 93-99.
PDF(1950 KB)
