一种基于粒子群算法的配电网低电压诊断模型研究
|
摘要
随着智能电网建设的发展,传统的基于检测技术的配电低电压原因诊断已变成基于数据挖掘的电力大数据分类技术,而着眼于低电压故障原因的数据分类研究在国内尚处于起步阶段,为此该文提出一种采用改进聚类算法和支持向量机分类算法的配电网低电压诊断模型。该模型首先采用Canopy-Kmeans的聚类算法基于配电网历史运行数据进行低电压原因的聚类分析并得出可能存在的低电压原因,然后采用经粒子群算法对支持向量机数据分类算法进行参数优化,最后使用结果参数优化的支持向量机算法对智能电表所采集的配电网实时运行数据进行低电压原因分类并最终输出低压故障原因的诊断结果。实验表明,采样基于粒子群优化的支持向量机诊断模型能够实现90%的低电压原因诊断准确度。
With the development of smart grid construction,traditional low-voltage cause diagnosis based on detection technology has become a data big data classification technology based on data mining,and data classification research focusing on the cause of low voltage failure is still in its infancy in China. For this reason,a low-voltage diagnostic model of distribution network using improved clustering algorithm and support vector machine classification algorithm is proposed. The model first uses Canopy-Kmeans clustering algorithm to analyze the low voltage causes based on the historical operation data of the distribution network and obtain the possible low voltage causes. Then the particle swarm optimization algorithm is used to support the SVM data classification algorithm. Parameter optimization,finally using the support vector machine algorithm of the result parameter optimization to classify the real-time operation data of the distribution network collected by the smart meter for low-voltage causes and finally output the diagnosis result of the lowvoltage fault. Experiments show that sampling based on particle swarm optimization based support vector machine diagnostic model can achieve 90% low-voltage cause diagnostic accuracy.
With the development of smart grid construction,traditional low-voltage cause diagnosis based on detection technology has become a data big data classification technology based on data mining,and data classification research focusing on the cause of low voltage failure is still in its infancy in China. For this reason,a low-voltage diagnostic model of distribution network using improved clustering algorithm and support vector machine classification algorithm is proposed. The model first uses Canopy-Kmeans clustering algorithm to analyze the low voltage causes based on the historical operation data of the distribution network and obtain the possible low voltage causes. Then the particle swarm optimization algorithm is used to support the SVM data classification algorithm. Parameter optimization,finally using the support vector machine algorithm of the result parameter optimization to classify the real-time operation data of the distribution network collected by the smart meter for low-voltage causes and finally output the diagnosis result of the lowvoltage fault. Experiments show that sampling based on particle swarm optimization based support vector machine diagnostic model can achieve 90% low-voltage cause diagnostic accuracy.
引文
[1]李兰芳,李鑫,黄嘉健,等.基于前推回代法的低电压台区成因数据分析[J].机电信息,2018(12):1-3.LI Lanfang,LI Xin,HUANG Jiajian,et al.Analysis of genesis data of low voltage platform based on forward pushback method[J].Mechanical and Electrical Information,2018(12):1-3.
[2]刘永亮.农村低电压治理典型办法与成效分析[J].内燃机与配件,2018(06):124-125.LIU Yongliang.Analysis of typical methods and effectiveness of rural low voltage control[J].Internal Combustion Engine&Parts,2018(06):124-125.
[3]李沛彧,柳杰.山西省农村电网“低电压”综合治理分析与研究[J].电工电气,2018(01):69-70+73.LI Pei,LIU Jie.Shanxi Province,rural power grid"low voltage"comprehensive treatment analysis and research[J].Electrotechnics Electric,2018(01):69-70+73.
[4]任子晖,王琦.基于优化DDAGSVM多类分类策略的电能质量扰动识别[J].电力系统保护与控制,2018,46(05):82-88.REN Zihui,WANG Qi.Power quality disturbance identification based on optimized ddagsvm multiclass classification strategy[J].Power System Protection and Control,2018,46(05):82-88.
[5]卢嗣斌,刘汉婕.分布式电源接入对解决农网低电压问题的研究[J].电力大数据,2018,21(08):43-47.Lu Yibin,Liu Hanqi.Research on Distributed Power Supply Access to Solve the Problem of Low Voltage in Rural Power Network[J].Power System and Big Data,2018,21(08):43-47.
[6]李嫄源,袁梅,王瑶等.SVM与PSO相结合的电机轴承故障诊断[J].重庆大学学报,2018,41(01):99-107.LI Yuyuan,YUAN Mei,WANG Yao,et al.Fault diagnosis of motor bearing based on SVM and PSO[J].Journal of Chongqing University,2018,41(01):99-107.
[7]王凌云,李开成,肖厦颖,等.基于稀疏分解的复合电能质量扰动分类[J].电测与仪表,2018,55(01):14-20+33.WANG Lingyun,LI Kaicheng,XIAO Xaling,et al.Classification of complex power quality disturbances based on sparse decomposition[J].Electric Measurement&Instrumentation,2018,55(01):14-20+33.
[8]林培杰,陈志聪,吴丽君,等.一种PSO-SVM的光伏阵列故障检测与分类[J].福州大学学报(自然科学版),2017,45(05):652-658.LIN Peijie,CHEN Zhicong,WU Lijun,et al.A PSO-SVMphotovoltaic array fault detection and classification[J].Journal of Fuzhou University(Natural Science Edition),2017,45(05):652-658.
[9]林顺富,谢潮,汤波,等.数据挖掘在电能质量监测数据分析中的应用[J].电测与仪表,2017,54(09):46-51.LIN Shunfu,XIE Chao,TANG Bo,et al.THE DATA MININGAPPLICATION IN THE POWER QUALITY MONITORING DATAANALYSIS[J].Electrical Measurement&Instrumentation,2017,54(09):46-51.
[10]许元斌,李国辉,郭昆,等.基于改进的并行K-Means算法的电力负荷聚类研究[J].计算机工程与应用,2017,53(17):260-265.XU Yuanbin,LI Guohui,GUO Kun,et al.Research on parallel clustering of power load based on improved K-Means algorithm[J].Computer Engineering and Applications,2017,53(17):260-265.
[11]张华赢,朱正国,姚森敬,等.基于大数据分析的暂态电能质量综合评估方法[J].南方电网技术,2015,9(06):80-86.ZHANG Huaying,ZHU Zhengguo,YAO Senjing,et al.Comprehensive assessment method of transient power quality based on big data analysis[J].China Southern Power Grid,2015,9(06):80-86.
[12]韩俊,谈健,黄河,等.基于改进K-means聚类算法的供电块划分方法[J].电力自动化设备,2015,35(06):123-129.HAN Jun,TAN Jian,HUANG He,et al.Power-supplying block partition based on improved K-means clustering algorithm[J].Electric Power Automation Equipment,2015,35(06):123-129.
[13]马聪,高峰,田昊,等.适用于并网系统低电压穿越的电压检测算法[J].电力系统自动化,2015,39(05):122-127.MA Cong,GAO Feng,TIAN Hao,et al.A Voltage Detection Method for Low Voltage Ride Through of Grid-connected System[J].Automation of Electric Power Systems,2015,39(05):122-127.
[14]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(02):90-95.LIU Aiguo,XUE Yuntao,HU Jianglu,et al.Ultra-short-term wind power forecasting based on SVM optimized by GA[J].Power System Protection and Control,2015,43(02):90-95.
[15]余长俊,张燃.云环境下基于Canopy聚类的FCM算法研究[J].计算机科学,2014,41(S2):316-319.YU Changjun,ZHANG Ran.Research on FCM algorithm based on canopy clustering in cloud environment[J].Computer Science,2014,41(S2):316-319.
[2]刘永亮.农村低电压治理典型办法与成效分析[J].内燃机与配件,2018(06):124-125.LIU Yongliang.Analysis of typical methods and effectiveness of rural low voltage control[J].Internal Combustion Engine&Parts,2018(06):124-125.
[3]李沛彧,柳杰.山西省农村电网“低电压”综合治理分析与研究[J].电工电气,2018(01):69-70+73.LI Pei,LIU Jie.Shanxi Province,rural power grid"low voltage"comprehensive treatment analysis and research[J].Electrotechnics Electric,2018(01):69-70+73.
[4]任子晖,王琦.基于优化DDAGSVM多类分类策略的电能质量扰动识别[J].电力系统保护与控制,2018,46(05):82-88.REN Zihui,WANG Qi.Power quality disturbance identification based on optimized ddagsvm multiclass classification strategy[J].Power System Protection and Control,2018,46(05):82-88.
[5]卢嗣斌,刘汉婕.分布式电源接入对解决农网低电压问题的研究[J].电力大数据,2018,21(08):43-47.Lu Yibin,Liu Hanqi.Research on Distributed Power Supply Access to Solve the Problem of Low Voltage in Rural Power Network[J].Power System and Big Data,2018,21(08):43-47.
[6]李嫄源,袁梅,王瑶等.SVM与PSO相结合的电机轴承故障诊断[J].重庆大学学报,2018,41(01):99-107.LI Yuyuan,YUAN Mei,WANG Yao,et al.Fault diagnosis of motor bearing based on SVM and PSO[J].Journal of Chongqing University,2018,41(01):99-107.
[7]王凌云,李开成,肖厦颖,等.基于稀疏分解的复合电能质量扰动分类[J].电测与仪表,2018,55(01):14-20+33.WANG Lingyun,LI Kaicheng,XIAO Xaling,et al.Classification of complex power quality disturbances based on sparse decomposition[J].Electric Measurement&Instrumentation,2018,55(01):14-20+33.
[8]林培杰,陈志聪,吴丽君,等.一种PSO-SVM的光伏阵列故障检测与分类[J].福州大学学报(自然科学版),2017,45(05):652-658.LIN Peijie,CHEN Zhicong,WU Lijun,et al.A PSO-SVMphotovoltaic array fault detection and classification[J].Journal of Fuzhou University(Natural Science Edition),2017,45(05):652-658.
[9]林顺富,谢潮,汤波,等.数据挖掘在电能质量监测数据分析中的应用[J].电测与仪表,2017,54(09):46-51.LIN Shunfu,XIE Chao,TANG Bo,et al.THE DATA MININGAPPLICATION IN THE POWER QUALITY MONITORING DATAANALYSIS[J].Electrical Measurement&Instrumentation,2017,54(09):46-51.
[10]许元斌,李国辉,郭昆,等.基于改进的并行K-Means算法的电力负荷聚类研究[J].计算机工程与应用,2017,53(17):260-265.XU Yuanbin,LI Guohui,GUO Kun,et al.Research on parallel clustering of power load based on improved K-Means algorithm[J].Computer Engineering and Applications,2017,53(17):260-265.
[11]张华赢,朱正国,姚森敬,等.基于大数据分析的暂态电能质量综合评估方法[J].南方电网技术,2015,9(06):80-86.ZHANG Huaying,ZHU Zhengguo,YAO Senjing,et al.Comprehensive assessment method of transient power quality based on big data analysis[J].China Southern Power Grid,2015,9(06):80-86.
[12]韩俊,谈健,黄河,等.基于改进K-means聚类算法的供电块划分方法[J].电力自动化设备,2015,35(06):123-129.HAN Jun,TAN Jian,HUANG He,et al.Power-supplying block partition based on improved K-means clustering algorithm[J].Electric Power Automation Equipment,2015,35(06):123-129.
[13]马聪,高峰,田昊,等.适用于并网系统低电压穿越的电压检测算法[J].电力系统自动化,2015,39(05):122-127.MA Cong,GAO Feng,TIAN Hao,et al.A Voltage Detection Method for Low Voltage Ride Through of Grid-connected System[J].Automation of Electric Power Systems,2015,39(05):122-127.
[14]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(02):90-95.LIU Aiguo,XUE Yuntao,HU Jianglu,et al.Ultra-short-term wind power forecasting based on SVM optimized by GA[J].Power System Protection and Control,2015,43(02):90-95.
[15]余长俊,张燃.云环境下基于Canopy聚类的FCM算法研究[J].计算机科学,2014,41(S2):316-319.YU Changjun,ZHANG Ran.Research on FCM algorithm based on canopy clustering in cloud environment[J].Computer Science,2014,41(S2):316-319.