裘愉涛,张磊,周开运,严慜,孙金通,龙寰
QIU Yutao,ZHANG Lei,ZHOU Kaiyun,YAN Min,SUN Jintong,LONG Huan

• 1:国网浙江省电力有限公司
• 2:国网浙江省电力有限公司湖州供电公司
• 3:东南大学电气工程学院

摘要(Abstract)：

光伏电站SCADA（数据采集与监视控制）系统记录着大量的运维数据，这些数据对光伏电站日常运维具有重要意义。然而，由极端天气、传感器损坏等问题造成的异常数据会极大地降低数据质量，进而影响光伏功率预测以及光伏电站日常运维。因此提出一种基于图像特征检测和双阈值处理的异常数据识别算法，将数值型数据映射为图像，进而将异常数据识别问题转换为图像处理问题。首先，将异常数据划分负值异常、离散异常和堆积异常，基于图像数据密度识别离散异常数据。然后，基于Canny边缘检测和Hough变换识别堆积异常数据，并提出双阈值图像处理机制以提高算法的通用性。最后，基于真实数据集，将该算法与传统的统计算法进行对比，验证了所提算法的普适性。
The supervisory control and data acquisition(SCADA) system of photovoltaic(PV) power plants records a substantial volume of operational and maintenance data that is crucial for the routine maintenance. However, abnormal data resulting from extreme weather, sensor failures, and other factors significantly degrade data quality, thus affecting PV power forecasting and routine maintenance. To address this, this paper introduces an anomaly data identification algorithm based on image feature detection and dual-threshold processing. This method maps numerical data to images, transforming the anomaly detection problem into an image processing problem. First, abnormal data is categorized into negative value anomalies, discrete anomalies, and stacked anomalies. Discrete anomalies are identified based on the density of image data. Next, stacked anomalies are detected using Canny edge detection and Hough transform, with a dual threshold image processing mechanism introduced to enhance the method's generalizability. Finally, the proposed method is compared with traditional statistical methods using a real-world dataset, demonstrating its adaptability.

关键词(KeyWords)： 光伏电站;异常数据识别;图像处理;Canny边缘检测;Hough变换;双阈值
photovoltaic power plant;anomaly data identification;image processing;Canny edge detection;Hough transform;dual threshold

Abstract:

Keywords:

基金项目(Foundation): 江苏省碳达峰碳中和科技创新专项（BE20230932）;; 国网浙江省电力有限公司科技项目（B311UZ23000A）

作者(Author): 裘愉涛,张磊,周开运,严慜,孙金通,龙寰
QIU Yutao,ZHANG Lei,ZHOU Kaiyun,YAN Min,SUN Jintong,LONG Huan

DOI: 10.19585/j.zjdl.202505005

参考文献(References)：

• [1]黄强，郭怿，江建华，等“．双碳”目标下中国清洁电力发展路径[J].上海交通大学学报，2021,55(12):1499-1509.HUANG Qiang,GUO Yi,JIANC Jianhua,et al.Development pathway of china’s clean electricity under carbon peaking and carbon neutral ity goals[J].Journal of Shanghai Jiaotong University,2021,55(12):1499-1509.
• [2]习近平.在第七十五届联合国大会一般性辩论上的讲话[EB/OL].(2020-09-22).[2024-09-06].https：//www.gov.cn/xinwen/2020-09/22/content_5546168.htm.
• [3]国家能源局.国家能源局发布2023年全国电力工业统计数据[EB/OL].(2024-01-26)[2024-09-06].https：//www.nea.gov.cn/2024-01/26/c_1310762246.htm.
• [4]祁炜雯，张俊，吴洋，等.基于改进BP-Bagging算法的光伏电站故障诊断方法[J].浙江电力，2024,43(3):65-74.QI Weiwen,ZHANG Jun,WU Yang,et al.A fault diagnosis method for photovoltaic power plants based on an enhanced BP-Bagging algorithm[J].Zhejiang Electric Power,2024,43(3):65-74.
• [5]朱涛，杨欢红，肖峰，等.基于改进灰狼算法和TCN-QRF的超短期光伏出力概率预测[J].浙江电力，2024,43(8):85-93.ZHU Tao,YANG Huanhong,XIAO Feng,et al.Probabilistic forecasting of ultra-short-term PV output using the improved GWO and TCN-QRF[J]. Zhejiang Electric Power,2024,43(8):85-93.
• [6]龚莺飞，鲁宗相，乔颖，等.基于Copula理论的光伏功率高比例异常数据机器识别算法[J].电力系统自动化，2016,40(9):16-22.GONG Yingfei,LU Zongxiang,QIAO Ying,et al.Copula theory based machine identification algorithm of high proportion of outliers in photovoltaic power data[J].Automation of Electric Power Systems,2016,40(9):16-22.
• [7]杨茂，孟玲建，李大勇，等.基于类3σ准则的光伏功率异常数据识别[J].可再生能源，2018,36(10):1443-1448.YANG Mao,MENG Lingjian,LI Dayong,et al.Identification of abnormal data of photovoltaic power based on class3σ[J].Renewable Energy Resources,2018,36(10):1443-1448.
• [8]申佳灵，易婷，聂勤，等.几种电力数据异常检测算法的对比分析[J].智能城市，2023,9(2):1-4.SHEN Jialing,YI Ting,NIE Qin,et al.Comparative analysis of several power data anomaly detection algorithms[J].Intelligent City,2023,9(2):1-4.
• [9]汪欣，蔡旭，李征.结合交叉局部异常因子和注意力机制的超短期风电功率预测方法[J].电力系统保护与控制，2020,48(23):92-99.WANG Xin,CAI Xu,LI Zheng. Ultra-short-term wind power forecasting method based on a cross LOF preprocessing algorithm and an attention mechanism[J]. Power System Protection and Control,2020,48(23):92-99.
• [10]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):156-165.ZOU Tonghua,GAO Yunpeng,YI Huijuan,et al.Processing of wind power abnormal data based on Thompson tauquartile and multi-point interpolation[J]. Automation of Electric Power Systems,2020,44(15):156-165.
• [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] ZHENG L,HU W,MIN Y.Raw wind data preprocessing:a data-mining approach[J].IEEE Transactions on Sustainable Energy,2015,6(1):11-19.
• [13]杨茂，黄鑫.基于光照过程特征分析的光伏功率异常数据识别算法[J].电力系统自动化，2019,43(6):64-69.YANG Mao,HUANG Xin. Abnormal data identification algorithm for photovoltaic power based on characteristics analysis of illumination process[J].Automation of Electric Power Systems,2019,43(6):64-69.
• [14] 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.
• [15] SU Y H,LIANG Y,ZHANG Z K,et al. Image-based wind power curve data cleaning algorithm via the matching of deformation template[C]//2021 International Conference on Computer,Control and Robotics(ICCCR).January 8-10,2021. Shanghai,China.IEEE,2021:340-345.
• [16] LIANG G Y,SU Y H,CHEN F,et al.Wind power curve data cleaning by image thresholding based on class uncertainty and shape dissimilarity[J]. IEEE Transactions on Sustainable Energy,2021,12(2):1383-1393.
• [17] LONG H,XU S H,GU W. An abnormal wind turbine data cleaning algorithm based on color space conversion and image feature detection[J]. Applied Energy,2022,311:118594.
• [18]郝颖，冬雷，王丽婕，等.基于数学形态学去噪的光伏发电限电异常数据识别算法[J].中国电机工程学报，2022,42(21):7843-7854.HAO Ying,DONG Lei,WANG Lijie,et al.An abnormal data recognition algorithm based on mathematical morphology denoising theory for PV power generation[J].Proceedings of the CSEE,2022,42(21):7843-7854.
• [19]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.ZHAO Yongning,YE Lin,ZHU Qianwen.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.
• [20] NICKFARJAM A M,EBRAHIMPOUR-KOMLEH H,AMINI TEHRANI A A. Binary image matching using scale invariant feature and Hough transforms[C]//2018Advances in Science and Engineering Technology International Conferences(ASET). February 6-April 5,2018.Abu Dhabi.IEEE,2018:1-5.
• [21] XU Z K,KAKDE D,CHAUDHURI A.Automatic hyperparameter tuning method for local outlier factor,with applications to anomaly detection[C]//2019 IEEE International Conference on Big Data(Big Data). December 9-12,2019.Los Angeles,CA,USA.IEEE,2019:4201-4207.
• [22] YESILBUDAK M. Clustering analysis of multidimensional wind speed data using k-means approach[C]//2016IEEE international conference on renewable energy research and applications(ICRERA). November,20-23,2016,Birmingham,UK.IEEE,2016.
• [23] XU H Z,PANG G S,WANG Y J,et al.Deep isolation forest for anomaly detection[J]. IEEE Transactions on Knowledge and Data Engineering,2023,35(12):12591-12604.
• [24] REYNOLDS D.Gaussian mixture models[M].Encyclopedia of Biometrics. Boston,MA:Springer US,2009:659-663.