基于QM-DBSCAN的风力机数据清洗方法

兰州理工大学学报 ›› 2021, Vol. 47 ›› Issue (6): 50-55.

基于QM-DBSCAN的风力机数据清洗方法

郑玉巧^*,刘玉涵,何正文,董博,魏剑峰

兰州理工大学机电工程学院, 甘肃兰州 730050

收稿日期:2021-03-24 出版日期:2021-12-28 发布日期:2021-12-28
通讯作者: 郑玉巧(1977-),女,甘肃庄浪人,副研究员,博导.Email:zhengyuqiaolut@163.com
基金资助:
国家自然科学基金(51965034),兰州市人才创新创业项目(2018-RC-25)

A novel cleaning method for wind turbine data based on QM-DBSCAN

ZHENG Yu-qiao, LIU Yu-han, HE Zheng-wen, Dong Bo, Wei Jian-feng

School of Mechanical and Electrical Engineering, Lanzhou Univ. of Tech., Lanzhou 730050, China

Received:2021-03-24 Online:2021-12-28 Published:2021-12-28

摘要/Abstract

摘要： 针对风电场风速-功率异常数据难以清洗的问题,提出一种基于QM-DBSCAN算法的风电场数据清洗方法.首先选取最能代表风力机运行状况的风速-功率数据作为研究对象,根据异常数据的分布特征进行分类;然后分别利用四分位法、标准DBSCAN算法及基于QM-DBSCAN方法识别和剔除异常数;最后通过spearman系数进一步验证所提方法的有效性.研究结果表明:QM-DBSCAN方法的剔除效果最好,较四分位法和标准DBSCAN法的spearman系数分别提高0.003 5和0.004 7.

关键词: 风力机, 异常数据清洗, 四分位法, DBSCAN, QM-DBSCAN

Abstract: For the issue of wind Speed-Power data hard cleaning in wind farms, a novel method based on QM-DBSCAN is proposed. Firstly, the wind condition which can best represent the operating state of the wind turbine is selected as the research object, and the anomalous data are classified according to the distribution characteristics. Then, the quartile method, standard DBSCAN algorithm and QM-DBSCAN method were used to identify and eliminate the abnormal data. The Spearman correlation coefficient was adopted to verify the effectiveness of the proposed method. The results indicated that the QM-DBSCAN method had the best elimination effect, which was 0.003 5 and 0.004 7 higher than the quartile method and the DBSCAN method, respectively.

Key words: wind turbine, abnormal data cleaning, the Quartile Method, DBSCAN, QM-DBSCAN

中图分类号:

TK83

郑玉巧,刘玉涵,何正文,董博,魏剑峰. 基于QM-DBSCAN的风力机数据清洗方法[J]. 兰州理工大学学报, 2021, 47(6): 50-55.

ZHENG Yu-qiao, LIU Yu-han, HE Zheng-wen, Dong Bo, Wei Jian-feng. A novel cleaning method for wind turbine data based on QM-DBSCAN[J]. Journal of Lanzhou University of Technology, 2021, 47(6): 50-55.

参考文献

[1] 刘波,贺志佳,金昊.风力发电现状与发展趋势 [J].东北电力大学学报,2016,2(36):8-13.
[2] Council GWE.Global wind statistics [EB/OL].[2020-11-05].https://gwec.net/gwec-wind-power-industry-to-install-71-3-gw-in-
2020-showing-resilience-during-covid-19-crisis/.
[3] 娄建楼,胥佳,陆恒,等.基于功率曲线的风电机组数据清洗算法 [J].电力系统自动化,2016,40(10):116-121.
[4] 赵永宁,叶林,朱倩雯.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.
[5] 朱倩雯,叶林,赵永宁,等.风电场输出功率异常数据识别与重构方法研究 [J].电力系统保护与控制,2015,43(3):38-45.
[6] 邹同华,高云鹏,伊慧娟,等.基于Thompson tau-四分位和多点插值的风电功率异常数据处理 [J].电力系统自动化,2020,44(15):156-162.
[7] 张小奇,张振宇,孙骁强,等.基于机群划分方法的风电场理论发电功率计算研究 [J].高电压技术,2019,45(1):284-292.
[8] 丁明,张超,王勃,等.基于功率波动过程的风电功率短期预测及误差修正 [J].电力系统自动化,2019,43(3):2-12.
[9] 杨茂,翟冠强,苏欣.基于风特征分析的风电机组异常数据识别算法 [J].中国电机工程学报,2017,37(S1):144-151.
[10] 张东英,李伟花,刘燕华,等.风电场有功功率异常运行数据重构方法 [J].电力系统自动化,2014,38(5):14-18,24.
[11] SHEN X J,FU X J,ZHOU C C.A combined algorithm for cleaning abnormal data of wind turbine power curve based on change point grouping algorithm and quartile algorithm [J].IEEE Transactions On Sustainable Energy, 2019,10(1):46-54.
[12] LONG H,SANG L W,WU Z J,et al.Image-based abnormal data detection and cleaning algorithm via wind power curve [J].IEEE Transactions On Sustainable Energy, 2020,11(2):938-946.
[13] YING Z,ZHENG Q,TIAN S S.Study on the abnormal data rejection and normal condition evaluation applied in wind turbine farm [C]//7^th International Symposium on Precision Mechanical Measurements.Xiamen:SPIE,2016.
[14] 王钦,蒋怀光,文福拴,等.智能电网中大数据的概念、技术与挑战 [J].电力建设,2016,37(12):1-10.
[15] 宋董飞,徐华.DBSCAN算法研究及并行化实现 [J].计算机工程与应用,2018,54(24):52-56,122.