Distributed Photovoltaic Power Outlier Detection Based on Quantile Regression Neural Network

doi:10.16183/j.cnki.jsjtu.2023.412

Abstract

Abstract:

The distributed photovoltaic power generation system is widely dispersed and lacks a scientific and standardized operation and maintenance management system. Due to the limited availability of data, it is difficult to accurately detect abnormal conditions in photovoltaic devices caused by fluctuations in weather. In this paper, according to the operation and maintenance status and data characteristics of distributed photovoltaic, a quantile regression neural network (QRNN)-based method is proposed for detecting photovoltaic power outliers. First, the solar irradiance characteristics of sunny days are analyzed, and the influence of rainy weather is excluded by using a sunny day screening method. Then, the power output correlation of different power stations is analyzed to identify the photovoltaic stations with high power output correlation, which is used as a horizontal reference. Subsequently, the curves of the power output of the stations tested on different sunny days are compared vertically to eliminate the interfering factors such as weather and environmental conditions. The measured active power data is fed into the QRNN model to establish the normal active power range for the photovoltaic system, whose threshold is used to detect photovoltaic power outliers. The simulation results of actual photovoltaic system data show that the method proposed can eliminate the meteorological influence, accurately identify the faulty photovoltaic system, and promote the fine operation and maintenance of distributed photovoltaic.

Key words: distributed photovoltaic power generation, power outlier detection, sunny day screening, quantile regression neural network (QRNN), power output correlation

CLC Number:

TM615

WANG Xiaoqian, ZHOU Yusheng, MAO Yuanjun, LI Bin, ZHOU Wenqing, SU Sheng. Distributed Photovoltaic Power Outlier Detection Based on Quantile Regression Neural Network[J]. Journal of Shanghai Jiao Tong University, 2025, 59(6): 836-844.

Figures/Tables 10

Tab.1

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Tab.2

Fig.6

Tab.3

Fig.7

References 26

[1]	GE L J, LIU H X, YAN J, et al. A virtual data collection model of distributed PVs considering spatio-temporal coupling and affine optimization reference[J]. IEEE Transactions on Power Systems, 2023, 38(4): 3939-3951.
[2]	尹德扬, 梅飞, 郑建勇, 等. 分布式光伏系统最优运维周期确定方法[J]. 电力自动化设备, 2022, 42(5): 135-141.
	YIN Deyang, MEI Fei, ZHENG Jianyong, et al. Determination method of optimal operation and maintenance cycles for distributed photovoltaic system[J]. Electric Power Automation Equipment, 2022, 42(5): 135-141.
[3]	CHENG C, LIU M, YI H, et al. Tendency-aided data-driven method for hot spot detection in photovoltaic systems[J]. IEEE Journal of Emerging and Selected Topics in Industrial Electronics, 2022, 3(4): 901-910.
[4]	PILLAI D S, RAJASEKAR N. A comprehensive review on protection challenges and fault diagnosis in PV systems[J]. Renewable and Sustainable Energy Reviews, 2018, 91: 18-40.
[5]	JAIN P, POON J, SINGH J P, et al. A digital twin approach for fault diagnosis in distributed photovoltaic systems[J]. IEEE Transactions on Power Electronics, 2020, 35(1): 940-956.
[6]	CHEN Z C, WU L J, CHENG S Y, et al. Intelligent fault diagnosis of photovoltaic arrays based on optimized kernel extreme learning machine and I-V characteristics[J]. Applied Energy, 2017, 204: 912-931.
[7]	李光辉, 段晨东, 武珊. 基于半监督机器学习法的光伏阵列故障诊断[J]. 电网技术, 2020, 44(5): 1908-1913.
	LI Guanghui, DUAN Chendong, WU Shan. Fault diagnosis of PV array based on semi-supervised machine learning[J]. Power System Technology, 2020, 44(5): 1908-1913.
[8]	CHEN S Q, YANG G J, GAO W, et al. Photovoltaic fault diagnosis via semisupervised ladder network with string voltage and current measures[J]. IEEE Journal of Photovoltaics, 2021, 11(1): 219-231.
[9]	KUMAR U, MISHRA S, DASH K. An IoT and semi-supervised learning-based sensorless technique for panel level solar photovoltaic array fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3521412.
[10]	王于波, 郝玲, 徐飞, 等. 分布式光伏集群发电功率波动模式识别与超短期概率预测[J]. 上海交通大学学报, 2024, 58(9): 1334-1343. doi: 10.16183/j.cnki.jsjtu.2023.048
	WANG Yubo, HAO Ling, XU Fei, et al. Aggregated distributed photovoltaic power fluctuating pattern recognition and ultra-short-term probabilistic forecasting[J]. Journal of Shanghai Jiao Tong University, 2024, 58(9): 1334-1343.
[11]	欧一鸣, 苏雍贺, 靳健, 等. 基于知识图谱的分布式光伏运维方案匹配方法[J]. 计算机集成制造系统, 2021, 27(7): 1860-1870. doi: 10.13196/j.cims.2021.07.002
	OU Yiming, SU Yonghe, JIN Jian, et al. Matching method for distributed photovoltaic maintenance scheme based on knowledge graph[J]. Computer Integrated Manufacturing Systems, 2021, 27(7): 1860-1870.
[12]	叶林, 崔宝丹, 李卓, 等. 光伏电站高比例异常运行数据组合识别方法[J]. 电力系统自动化, 2022, 46(20): 74-82.
	YE Lin, CUI Baodan, LI Zhuo, et al. Combined identification method for high proportion of abnormal operation data in photovoltaic power station[J]. Automation of Electric Power Systems, 2022, 46(20): 74-82.
[13]	陈宇轩, 张耀, 徐杨, 等. 基于Boosting集成框架的新能源发电功率异常值检测方法[J]. 电网技术, 2023, 47(8): 3261-3268.
	CHEN Yuxuan, ZHANG Yao, XU Yang, et al. Outlier detection method of new energy power based on boosting integration framework[J]. Power System Technology, 2023, 47(8): 3261-3268.
[14]	丛伟伦, 张博, 夏亚东, 等. 基于马尔可夫链的光伏电站遮挡实时诊断算法[J]. 太阳能学报, 2020, 41(4): 67-72.
	CONG Weilun, ZHANG Bo, XIA Yadong, et al. Diagnosis algorithm for real-time shaded analysis of photovoltaic power station based on Markov chain[J]. Acta Energiae Solaris Sinica, 2020, 41(4): 67-72.
[15]	曹仟妮, 贾孟硕, 沈沉. 针对复杂安装条件的光伏电站光伏板异常状态检测技术[J]. 中国电机工程学报, 2022, 42(5): 1917-1925.
	CAO Qianni, JIA Mengshuo, SHEN Chen. A fault detection scheme for PV modules in large scale PV stations with complex installation conditions[J]. Proceedings of the CSEE, 2022, 42(5): 1917-1925.
[16]	JORDAN D C, HANSEN C. Clear-sky detection for PV degradation analysis using multiple regression[J]. Renewable Energy, 2023, 209: 393-400.
[17]	SHI Y C, HE W G, ZHAO J, et al. Expected output calculation based on inverse distance weighting and its application in anomaly detection of distributed photovoltaic power stations[J]. Journal of Cleaner Production, 2020, 253: 119965.
[18]	ZHOU N, XU X Y, YAN Z, et al. Spatio-temporal probabilistic forecasting of photovoltaic power based on monotone broad learning system and copula theory[J]. IEEE Transactions on Sustainable Energy, 2022, 13(4): 1874-1885.
[19]	WANG H, ZHANG N, DU E S, et al. An adaptive identification method of abnormal data in wind and solar power stations[J]. Renewable Energy, 2023, 208: 76-93.
[20]	李翠明, 王宁, 张晨. 基于改进遗传算法的光伏板清洁分级任务规划[J]. 上海交通大学学报, 2021, 55(9): 1169-1174. doi: 10.16183/j.cnki.jsjtu.2020.254
	LI Cuiming, WANG Ning, ZHANG Chen. Hierarchical mission planning for cleaning photovoltaic panels based on improved genetic algorithm[J]. Journal of Shanghai Jiao Tong University, 2021, 55(9): 1169-1174.
[21]	陆双, 彭曙蓉, 杨云皓, 等. 基于平均影响值-启发式前向搜索的异常光伏用户识别方法[J]. 电力自动化设备, 2022, 42(2): 106-111.
	LU Shuang, PENG Shurong, YANG Yunhao, et al. Identification method of abnormal photovoltaic users based on mean impact value and heuristic forward searching[J]. Electric Power Automation Equipment, 2022, 42(2): 106-111.
[22]	李芬, 周尔畅, 孙改平, 等. 一种新型天气分型方法及其在光伏功率预测中的应用[J]. 上海交通大学学报, 2021, 55(12): 1510-1519. doi: 10.16183/j.cnki.jsjtu.2021.264
	LI Fen, ZHOU Erchang, SUN Gaiping, et al. A novel weather classification method and its application in photovoltaic power prediction[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1510-1519.
[23]	李彬, 彭曙蓉, 彭君哲, 等. 基于深度学习分位数回归模型的风电功率概率密度预测[J]. 电力自动化设备, 2018, 38(9): 15-20.
	LI Bin, PENG Shurong, PENG Junzhe, et al. Wind power probability density forecasting based on deep learning quantile regression model[J]. Electric Power Automation Equipment, 2018, 38(9): 15-20.
[24]	TAYLOR J W. A quantile regression neural network approach to estimating the conditional density of multiperiod returns[J]. Journal of Forecasting, 2000, 19(4): 299-311.
[25]	ZHAO Y Y, LIU Q, LI D S, et al. Hierarchical anomaly detection and multimodal classification in large-scale photovoltaic systems[J]. IEEE Transactions on Sustainable Energy, 2019, 10(3): 1351-1361.
[26]	LIU F T, TING K M, ZHOU Z H. Isolation forest[C]// 2008 8th IEEE International Conference on Data Mining. Pisa, Italy: IEEE, 2008: 413-422.

异常状态	具体原因	出力数据表征
故障	接线错误,阵列间短路开路	等比例或随机下降
老化	组件和线路电阻老化	等比例下降
遮挡	灰尘、树叶、建筑、树木等	等比例或随机下降
扩容	用户私自扩容骗取发电补贴	增加
限电	对新能源上网消纳能力有限	降低

置信度/%	气候	算法	可靠性/%	敏锐性/W
90	晴朗日	QRNN	99.90	67.3
	晴朗日	QRLSTM	74.40	184.9
	未筛选晴朗日	QRNN	73.78	204.5
	未筛选晴朗日	QRLSTM	80.36	315.8
80	晴朗日	QRNN	92.36	24.7
	晴朗日	QRLSTM	51.60	121.1
	未筛选晴朗日	QRNN	63.31	85.0
	未筛选晴朗日	QRLSTM	57.73	161.6

气候	算法	R_FP/%	R_D/%
晴朗日	QRNN	2.25	95.15
未筛选晴朗日	QRNN	10.26	89.31
晴朗日	iForest	39.60	91.42
未筛选晴朗日	iForest	44.34	85.13
晴朗日	LOF	15.79	92.53
未筛选晴朗日	LOF	7.62	45.63