风电场风功率异常数据清洗与质控技术对比分析

袁瑞瑞; 张逸飞; 刘建宏; 雍佳; 潘娅英

doi:10.16516/j.ceec.2025-056

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

风电场风功率异常数据清洗与质控技术对比分析

极端气候事件下的能源与交通韧性 | 更新时间：2026-10-14

- 风电场风功率异常数据清洗与质控技术对比分析
- Comparative Study on Abnormal Data Cleaning and Quality Control Technologies for Wind Power in Wind Farms
- 南方能源建设 2026年13卷第3期页码：119-128
- 作者机构：
  
  1. 中国气象局旱区特色农业气象灾害监测预警与风险管理重点实验室,宁夏,银川,750002
  2. 宁夏气象服务中心,宁夏,银川,750002
  3. 国华（宁夏）新能源有限公司,宁夏,银川,750002
  4. 浙江省气象服务中心,浙江,杭州,310057
- 作者简介：
  
  袁瑞瑞，BRID: 00182.00.37983ORCID: 0009-0006-2307-89291996-，女，工程师，硕士，主要从事专业气象服务工作（e-mail）yuanrr_818@163.com
  刘建宏，（e-mail）ljh826123@icloud.com
- 基金信息：
  
  浙江省自然科学基金项目“基于人工智能技术的浙江省电网设备台风灾害影响风险评估及动态风险预报”（LZJMY25D050006）;宁夏气象局指令性项目“基于人工智能的风电场风速预报订正关键技术研究”（CAMP-202508）;宁夏科技创新团队项目“宁夏智能数字预报技术研究与应用”（2024CXTD006）
- DOI：10.16516/j.ceec.2025-056
  中图分类号： TM614;P49
- 纸质出版：2026
- 稿件说明：
移动端阅览
袁瑞瑞, 张逸飞, 刘建宏, 等. 风电场风功率异常数据清洗与质控技术对比分析[J]. 南方能源建设, 2026, 13(3): 119-128.

.
袁瑞瑞, 张逸飞, 刘建宏, 等. 风电场风功率异常数据清洗与质控技术对比分析[J]. 南方能源建设, 2026, 13(3): 119-128. DOI： 10.16516/j.ceec.2025-056.

. DOI： 10.16516/j.ceec.2025-056.

摘要

目的

风电场风速功率数据中通常包含大量异常数据，有效的数据清洗可以提高数据质量，使新能源功率预测、发电量预测等结果更加精确。

方法

收集宁夏典型风电场风速及功率数据，绘制风速-功率散点分布图，探讨数据分布特征和异常数据产生原因；对比DBSCAN算法和方差变化率判据对异常数据的识别清洗效果，并分别与四分位法结合，构建“DBSCAN-四分位”“方差变化率-四分位”组合模型，同时将 DBSCAN 算法与方差变化率判据相互组合，构建“DBSCAN-方差变化率”“方差变化率-DBSCAN”组合模型，开展组合模型的清洗质控研究，并与单一模型对比。

结果

研究表明：（1）风电场风速-功率散点图中异常数据点可大致分为底部堆积型数据、中部堆积型数据和其他离散型数据3类；（2）DBSCAN算法或方差变化率判据的单一模型能够有效识别清洗大部分异常数据，但仍有局部区域离散点未能被识别；（3）组合模型相比单一模型，能够进一步识别少部分离群特征不明显的异常数据，其中，DBSCAN-四分位的组合模型，清洗后风速与功率相关系数最高，相对于建模曲线的均方根误差最低，清洗效果最佳。

结论

通过对比单一模型、组合模型对风电场运行异常数据的清洗效果，证明了组合模型对于提高风电场数据质量的可靠性，研究结果为能源需求预测、风电消纳水平评估、风电场运行管理等提供重要参考。

Abstract

Objective

Wind speed and power data from wind farms often contain a large amount of abnormal data. Effective data cleaning can improve data quality and make results such as renewable energy power forecasting and power generation forecasting more accurate.

Method

This study collected wind speed and power data from typical wind farms in

Ningxia

plotted a scatter distribution diagram of wind speed versus power to investigate the data distribution characteristics and the reasons for abnormal data generation.We compared the effectiveness of the DBSCAN algorithm and the variance change rate criterion in identifying and cleaning abnormal data. Furthermore

we combined these methods with the quartile method approach to construct "DBSCAN-quartile method" and "variance change rate-quartile method" composite models. Additionally

we integrated the DBSCAN algorithm with the variance change rate criterion to develop "DBSCAN-variance change rate" and "variance change rate-DBSCAN" composite models. The data cleaning using these composite models was studied and compared with that of the single models.

Result

The study shows that: (1) Abnormal data points in the wind speed-power scatter plot of wind farms can be roughly classified into three categories: bottom clustered data

middle clustered data and other dispersed data. (2) Single models using either the DBSCAN algorithm or the variance change rate criterion effectively identify and clean most of the abnormal data

but some local dispersed points still remain undetected. (3) Compared with single models

composite models can further identify a small number of abnormal data with less obvious outlier characteristics. Among them

the "DBSCAN-quartile method" composite model has the highest correlation coefficient between wind speed and power after cleaning

and the lowest root mean square error relative to the modeling curve

showing the best cleaning effect.

Conclusion

By comparing the data cleaning effects of single models and composite models on the operational abnormal data of wind farms

the study demonstrates the reliability of composite models in improving the data quality of wind farms. The research results provide important references for energy demand forecasting

wind power accommodation level assessment and wind farm operation management.

关键词

Keywords

references

REN Z Y, GUO N, XIE T, et al. A study on the development patterns of clean energy in China and evaluation of its coordinated development with the economic system [J]. Power system and clean energy, 2024, 40(12): 128-134. DOI: 10.3969/j.issn.1674-3814.2024.12.016.

QIN X D, SONG R J, WANG A, et al. Research on adaptive SMPC scheduling strategy for wind-photovoltaic-thermal-storage system [J]. Inner Mongolia electric power, 2025, 43(4): 3-10. DOI: 10.19929/j.cnki.nmgdljs.2025.0043.

SHEN Y B. Meteorological issues and technological progress in the development of new energy systems [J]. Southern energy construction, 2025, 12(1): 31-42. DOI: 10.16516/j.ceec.2024-423.

HAN L, YIN C Y, DAI C, et al. Transient voltage operational risk of a high-proportion new energy sending system [J]. Power system protection and control, 2024, 52(1): 23-34. DOI: 10.19783/j.cnki.pspc.230311.

YUAN X F, YU C Y, BAO J L. A study on the broadband oscillation monitoring of wind-driven generators [J]. Power system and clean energy, 2025, 41(2): 107-112. DOI: 10.3969/j.issn.1674-3814.2025.02.013.

CHEN J Y, LI P Q, ZHONG W J. Identification of wind power abnormal data based on multi-model parallel integration framework [J]. Proceedings of the CSU-EPSA, 2023, 35(11): 133-142. DOI: 10.19635/j.cnki.csu-epsa.001253.

ZHANG P, ZUO P, XIE H, et al. Review of wind farm abnormal data identification and reconstruction techniques [J]. Electric power information and communication technology, 2023, 21(4): 16-24. DOI: 10.16543/j.2095-641x.electric.power.ict.2023.04.03.

YESILBUDAK M. Partitional clustering-based outlier detection for power curve optimization of wind turbines [C]// Anon. 2016 IEEE International Conference on Renewable Energy Research and Applications (ICRERA), Birmingham, UK, November 20-23, 2016. New York: IEEE, 2016: 1080-1084. DOI: 10.1109/TSTE.2012.2212470.

KUSIAK A, VERMA A. Monitoring wind farms with performance curves [J]. IEEE transactions on sustainable energy, 2013, 4(1): 192-199. DOI: 10.1109/TSTE.2012.2212470.

ZHAO Y N, YE L, WANG W S, et al. Data-driven correction approach to refine power curve of wind farm under wind curtailment [J]. IEEE transactions on sustainable energy, 2018, 9(1): 95-105. DOI: 10.1109/TSTE.2017.2717021.

YAN J, ZHANG H, LIU Y Q, et al. Uncertainty estimation for wind energy conversion by probabilistic wind turbine power curve modelling [J]. Applied energy, 2019, 239: 1356-1370. DOI: 10.1016/j.apenergy.2019.01.180.

FAN X Q, DU D J, FEI M R. Research on the intelligent identification method for abnormal measurement data of the wind power [J]. Instrumentation technology, 2017(1): 10-14. DOI: 10.19432/j.cnki.issn1006-2394.2017.01.003.

SUN Z X, SUN H X. Stacked denoising autoencoder with density-grid based clustering method for detecting outlier of wind turbine components [J]. IEEE access, 2019, 7: 13078-13091. DOI: 10.1109/ACCESS.2019.2893206.

CHEN J S. Anomaly detection and assessment method for operational condition of wind turbines based on the multivariate data reconstruction [D]. Chongqing: Chongqing University, 2019. DOI: 10.27670/d.cnki.gcqdu.2019.001224.

OUYANG T H, KUSIAK A, HE Y S. Modeling wind-turbine power curve: a data partitioning and mining approach [J]. Renewable energy, 2017, 102: 1-8. DOI: 10.1016/j.renene.2016.10.032.

CAO L X, LIU W M, GUO H Q. Cleaning and modeling of abnormal data of wind farm power curve [J]. Journal of Lanzhou University of Technology, 2022, 48(4): 64-70. DOI: 10.3969/j.issn.1673-5196.2022.04.010.

ZOU T H, GAO Y P, YI H J, et al. Processing of wind power abnormal data based on Thompson tau-quartile and multi-point interpolation [J]. Automation of electric power systems, 2020, 44(15): 156-162. DOI: 10.7500/AEPS20191231003.

LOU J L, XU J, LU H, et al. Wind turbine data-cleaning algorithm based on power curve [J]. Automation of electric power systems, 2016, 40(10): 116-121. DOI: 10.7500/AEPS20151014003.

HU Y, QIAO Y L. Wind power data cleaning method based on confidence equivalent boundary model [J]. Automation of electric power systems, 2018, 42(15): 18-23. DOI: 10.7500/AEPS20171109001.

ZHAO Y N, YE L, ZHU Q W. Characteristics and processing method of abnormal data clusters caused by wind curtailments in wind farms [J]. Automation of electric power systems, 2014, 38(21): 39-46. DOI: 10.7500/AEPS20131213010.

GONG Y X, GAO J H, LI Y, et al. Cleaning of abnormal data of wind turbine power based on DBSCAN [J]. Energy and environment, 2023(5): 60-63. DOI: 10.3969/j.issn.1672-9064.2023.05.017.

WU Y B, ZHANG J Z, DENG F J, et al. Anomaly data identification of wind power in wind farm with the criterion of variance change rate and quartile [J]. Electric power engineering technology, 2023, 42(4): 141-148. DOI: 10.12158/j.2096-3203.2023.04.015.

YUAN T K. Wind turbine fault prediction based on data mining [D]. Hangzhou: Zhejiang University, 2021. DOI: 10.27461/d.cnki.gzjdx.2021.000399.

YAN D H. Identification of low-voltage distribution network attribution relationship and phase information based on density clustering [J]. Southern energy construction, 2023, 10(5): 149-156. DOI: 10.16516/j.gedi.issn2095-8676.2023.05.018.

ZHENG Y Q, LIU Y H, HE Z W, et al. A novel cleaning method for wind turbine data based on QM-DBSCAN [J]. Journal of Lanzhou University of Technology, 2021, 47(6): 50-55. DOI: 10.3969/j.issn.1673-5196.2021.06.009.

HYNDMAN R J, FAN Y N. Sample quantiles in statistical packages [J]. The American statistician, 1996, 50(4): 361-365. DOI: 10.1080/00031305.1996.10473566.

MA L Y, GENG Y Z, YUAN N Z, et al. Abnormal data cleaning method of wind turbine based on quartile and CFSFDP [J]. Electric power science and engineering, 2023, 39(6): 9-16. DOI: 10.3969/j.ISSN.1672-0792.2023.06.002.

YE X, LU Z X, QIAO Y, et al. Identification and correction of outliers in wind farm time series power data [J]. IEEE transactions on power systems, 2016, 31(6): 4197-4205. DOI: 10.1109/TPWRS.2015.2512843.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

桂北低温冰冻天气对高山风力发电的影响分析

高空风能电站运维辅助系统研究与设计

基于DIgSILENT的风光储微电网系统对电网安全稳定影响分析

多元混合储能系统监测与预警技术综述

基于双工质气体压缩储能的供气系统