|本期目录/Table of Contents|

[1]崔胜胜,孙剑锋,马 斌,等.智能电表数据和监督学习检测非技术损失的研究[J].工业仪表与自动化装置,2020,(01):122-126.
 CUI Shengsheng,SUN Jianfeng,MA Bin,et al.Research on smart electric meter data and supervisory learning to detect non-technical loss[J].Industrial Instrumentation & Automation,2020,(01):122-126.
点击复制

智能电表数据和监督学习检测非技术损失的研究

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2020年01期
页码:
122-126
栏目:
出版日期:
2020-02-15

文章信息/Info

Title:
Research on smart electric meter data and supervisory learning to detect non-technical loss
作者:
崔胜胜1孙剑锋1马 斌1汪 涛2李立伟2于洋洋2
1. 国网青海省电力公司电力科学研究院,西宁 810000;
2. 北京智芯微电子科技有限公司,北京 100192.
Author(s):
CUI Shengsheng1 SUN Jianfeng1 MA Bin1 WANG Tao2 LI Liwei2YU Yangyang2
1. State Grid Qinghai Electric Power Company Research Institute, Xining 810000, China;
2. Beijing Smartchip Microelectronics Technology Co., Ltd., Beijing 100192, China.
关键词:
智能电表数据监督学习检测非技术损失
Keywords:
smart meter data supervised learning detection non-technical loss
分类号:
TM614
DOI:
-
文献标志码:
A
摘要:
为提高智能电表数据融合检测能力,提出基于监督学习的智能电表数据检测非技术损失评估方法,在智能电表检测非技术损失阵列中进行智能电表损失数据采集,构建大数据挖掘的统计分析模型,采用监督学习检测方法检测智能电表数据的非技术损失数值,实现智能电表检测非技术损失数据快速提取,根据特征提取结果实现智能电表数据融合和损失检测。仿真结果表明,采用该方法进行智能电表数据融合和监督学习检测的准确性较高,信息融合度较高,提高了智能电表非技术损失的评估和状态监测能力。
Abstract:
In order to improve the ability of data fusion and detection of smart meters,a method of evaluating the non-technical loss of smart meters based on supervised learning is proposed.The data of smart meters’ loss is collected in the array of non-technical loss detection of smart meters.A statistical analysis model of large data mining is constructed.The method of supervised learning detection is used to detect the non-technical loss value of smart meters’ data to realize intelligence. The non-technical loss data of energy meter detection is extracted quickly,and the real smart meter data fusion and loss detection are based on the result of feature extraction.The simulation results show that the method has high accuracy in data fusion and supervisory learning detection of smart meters,and high degree of information fusion,which improves the ability of evaluating and monitoring the non-technical losses of smart meters.

参考文献/References:

[1] 李勇,陈雨,蔡晔,等.基于信息物理接口矩阵的IEC61850变电站自动化系统可靠性分析[J].电力自动化设备,2019, 39(01):84-90+98.

[2] 冯艳,吕文,万淑娟,等.大规模新能源分布对目标网架的影响分析研究[J].电气时代,2017,13(09):49-51.
[3] 姚垚,张沛超.基于市场控制的空调负荷参与平抑微网联络线功率波动的方法[J].中国电机工程学报,2018,38(3): 782-791.
[4] 陆兴华,郑永涛. 基于非线性时间序列分析的电力系统负荷预测模型[J].电力与能源, 2016,37(2): 197-201.
[5] 徐舒玮,邱才明,张东霞,等.基于深度学习的输电线路故障类型辨识[J].中国电机工程学报,2019,39(01):65-74+321.
[6] 贾亦敏,史丽萍,严鑫.改进人工鱼群算法优化小波神经网络的变压器故障诊断[J].河南理工大学学报(自然科学版), 2019,38(02):103-109.
[7] 李相敏,康壮.基于双交叉耦合电容反馈的超低功耗高线性LNA[J].自动化与仪器仪表,2018,7(03):326-330.
[8] 侯晓芳,王欢,李瑛.一种基于HIVE和分布式集群的大量数据高效处理方法研究[J].中国电子科学研究院学报, 2018,13(3):315-320.
[9] 荣德生,段志田.一种改进型交错并联高增益Boost变换器[J].电源学报,2017,15(5):16-24.?
[10] 晓侃,王琼.一种基于RBF自适应神经模糊推理的短期智能电表非技术损失数据预测方法[J].中南民族大学学报(自然科学版),2018,37(03):112-115.
[11] 孙新程,孔建寿,刘钊.基于核主成分分析与改进神经网络的智能电表非技术损失数据中期预测模型[J].南京理工大学学报,2018,42(03):259-265.
[12] 蒙园,张建华,龙日尚.基于交替条件期望的短期负荷概率密度预测[J].华北电力大学学报(自然科学版),2018, 45(01):58-65.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2019-07-17
作者简介:崔胜胜(1993),男,河南商丘人,本科,助理工程师,主要研究方向为电能计量。
更新日期/Last Update: 2020-01-10