基于随机森林和专家系统的分布式光伏电站阴影遮挡诊断

doi:10.6040/j.issn.1672-3961.0.2020.404

摘要/Abstract

摘要： 针对分布式光伏电站阴影遮挡提出一种基于随机森林算法的人机协同判别方法。通过遮挡机理分析和逆变器遥测参数转换构建组串直流侧电流离散率、太阳高度角、太阳方位角及电站瞬时发电水平等关键特征参数,搭建随机森林遮挡诊断模型。基于网格搜索法和K折交叉验证法优化参数,通过准确率对比确定基于信息增益的分裂方式。对比支持向量、逻辑回归及决策树等主流算法模型,发现随机森林算法在遮挡诊断场景中具有较强的优势,结合专家系统得出诊断方位后,现场验证了“基于信息增益的随机森林和专家系统”方法的有效性。

关键词: 分布式光伏, 随机森林, 专家系统, 阴影遮挡诊断, 遮挡机理分析

Abstract: A human-machine collaborative discriminant method based on the random forest algorithm was proposed to diagnose distributed photovoltaic shadow occlusion. Key characteristic parameters, such as the current dispersion rate on the direct current side of the string, solar altitude angle, solar azimuth angle, and instantaneous power generation level of the power station, were constructed based on the analysis of the shadow occlusion mechanism and the conversion of inverter telemetry parameters. The random forest shadow occlusion diagnosis model was subsequently established. The parameters were optimized based on the grid search method and the K-fold cross-validation method, and the splitting method based on information gain was determined by comparing the accuracy with other machine learning algorithms, such as support vector machine, logistic regression, and decision tree. The random forest algorithm had obvious advantages in shadow occlusion diagnosis scenes. An expert system was combined to obtain the diagnosis position, and then the effectiveness of the method using the random forest algorithm based on information gain and an expert system was verified on site.

Key words: distributed photovoltaic, random forest, expert system, shadow occlusion diagnosis, analysis of shadow occlusion mechanism

中图分类号:

TP181

刘新锋, 张旖旎,徐惠三,宋玲,陈梦雅. 基于随机森林和专家系统的分布式光伏电站阴影遮挡诊断[J]. 山东大学学报 (工学版), 2021, 51(2): 98-104.

LIU Xinfeng, ZHANG YiNi, XU Huisan, SONG Ling, CHEN Mengya. Shadow occlusion diagnosis of distributed photovoltaic power station based on random forest and expert system[J]. Journal of Shandong University(Engineering Science), 2021, 51(2): 98-104.

参考文献

[1] 姜安印, 刘博. 精准扶贫背景下光伏扶贫问题研究[J]. 农林经济管理学报, 2017, 16(6):789-794. JIANG Anyin, LIU Bo. Poverty alleviation in the context of precision poverty alleviation[J]. Journal of Agro-Forestry Economics and Management, 2017, 16(6):789-794.
[2] 李善寿. 阴影条件下光伏系统的失配分析与优化控制研究[D]. 合肥:合肥工业大学, 2016. LI Shanshou. Study on the analysis of mismatching and optimal control of PV system under shading conditions[D]. Hefei: Hefei University of Technology, 2016.
[3] 程泽,宋成,刘力. 遮挡下光伏组件中旁路二极管的研究[J]. 电力电子技术, 2017, 51(4):50-53. CHENG Ze, SONG Cheng, LIU Li. Study of bypass diode in photovoltaic module under shading condition[J]. Power Electronics, 2017, 51(4):50-53.
[4] 康开岚. 基于GSO的局部阴影光伏阵列最大功率点跟踪研究[D]. 兰州:兰州理工大学, 2017. KANG Kailan. Maximum power point tracking for PV array under partially shaded conditions based on glow-worm swarm optimization algorithm[D]. Lanzhou: Lanzhou University of Technology, 2017.
[5] 王凯丽, 张巧杰. 基于IPSO算法的光伏阵列多峰值MPPT研究[J]. 电气工程学报, 2016, 11(10):53-58. WANG Kaili, ZHANG Qiaojie. Research on multi-peak MPPT of photovoltaic array based on IPSO algorithm[J]. Journal of Electrical Engineering, 2016, 11(10):53-58.
[6] 胡义华,陈昊,徐瑞东,等. 光伏电池板在阴影影响下输出特性[J]. 电工技术学报, 2011, 26(1):123-128. HU Yihua, CHEN Hao, XU Ruidong, et al. PV module characteristics effected by shadow problem[J]. Trans-actions of China Electrotechnical Society, 2011, 26(1):123-128.
[7] 王丰, 孔鹏举, LEE F C,等. 基于分布式最大功率跟踪的光伏系统输出特性分析[J]. 电工技术学报, 2015, 30(24):133-140. WANG Feng, KONG Pengju, LEE F C, et al. Output characteristic analysis of distributed maximum power point tracking PV system[J].Transactions of China Electrotechnical Society, 2015, 30(24):133-140.
[8] 陈华宝, 韩伟, 张晓东. 基于功率预测的光伏组件阴影故障类型判定[J]. 电测与仪表, 2018, 55(7):122-129. CHEN Huabao, HAN Wei, ZHANG Xiaodong. Judgment on shadow fault type for photovoltaic module based on power prediction[J]. Electrical Measurement & Instrumentation, 2018, 55(7):122-129.
[9] 贾嵘, 李云桥, 张惠智,等.基于改进BP神经网络的光伏阵列多传感器故障检测定位方法[J].太阳能学报, 2018, 39(1):110-116. JIA Rong, LI Yunqiao, ZHANG Huizhi, et al. Multi-sensor fault detection and positioning method of photovoltaic array based on improved BP neural network[J]. Acta Energiae Solaris Sinica, 2018, 39(1):110-116.
[10] 胡义华, 陈昊, 徐瑞东,等. 基于最优传感器配置的光伏阵列故障诊断[J]. 中国电机工程学报, 2011, 31(33):19-30. HU Yihua, CHEN Hao, XU Ruidong, et al. Photovo-ltaic(PV)array fault diagnosis strategy based on optimal sensor placement[J]. Proceedings of the CSEE, 2011, 31(33):19-30.
[11] 唐萁, 朱永强, 郝嘉诚. 基于传感器最优布置的光伏阵列阴影诊断与定位[J]. 太阳能学报, 2018,39(2):513-519. TANG Qi, ZHU Yongqiang, HAO Jiacheng. Shadow diagnosis and localization of PV array based on optimal sensor collocation[J]. Acta Energiae Solaris Sinica, 2018, 39(2):513-519.
[12] 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.
[13] 郭宝柱. 光伏阵列热斑的红外图像处理的研究[D]. 天津:天津理工大学, 2016. GUO Baozhu. Research on infrared image processing of photovoltaic array of hot spot[D]. Tianjin: Tianjin University of Technology, 2016.
[14] TAKASHIMA T, YAMAGUCHI J, OYANI K, et al. Experimental studies of failure detection methods in PV module strings[J]. Solar Energy Materials and Solar Cells, 2009, 93(6/7):1079-1082.
[15] 李鹏鹏,周丹阳,姜朝明,等.基于随机森林算法的95598投诉预测方法研究[J].浙江电力,2020,39(4):57-62. LI Pengpeng, ZHOU Danyang, JIANG Chaoming, et al. Research on 95598 complaint prediction method based on random forest [J]. Zhejiang Electric Power, 2020, 39(4): 57-62.
[16] 罗艳,肖辅盛,王庭刚,等.基于随机森林的电网实时运行风险评估方法[J].信息技术,2020,44(4):23-26. LUO Yan, XIAO Fusheng, WANG Tinggang, et al. Real-time risk assessment method for power grid operation based on random forest[J]. Information Technology, 2020, 44(4):23-26.
[17] 曹正凤. 随机森林算法优化研究[D]. 北京:首都经济贸易大学, 2014. CAO Zhengfeng. Study on optimization of random forests algorithm[D]. Beijing: Capital University of Economics and Business, 2014.
[18] 王国安,米鸿涛,邓天宏,等. 太阳高度角和日出日落时刻太阳方位角一年变化范围的计算[J]. 气象与环境科学, 2007, 30(增刊9):161-164. WANG Guoan, MI Hongtao, DENG Tianhong, et al. Calculation of the change range of the sun high angle and the azimuth of sunrise and sunset in one year[J]. Meteorological and Environmental Sciences, 2007, 30(Suppl.9):161-164.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed