基于改进自适应阈值的电能表数据降维方法  

Design of dimensionality reduction technology for electric energy meter data based on standardized processing and component analysis

在线阅读下载全文

作  者:李志新 卢树峰 王忠东 夏国芳 王思云 LI Zhixin;LU Shufeng;WANG Zhongdong;XIA Guofang;WANG Siyun(State Grid Jiangsu Electric Power Co.,Ltd.,Marketing Service Center,Nanjing 210019,China)

机构地区:[1]国网江苏省电力有限公司营销服务中心,南京210019

出  处:《自动化与仪器仪表》2025年第2期50-53,57,共5页Automation & Instrumentation

基  金:国网江苏省电力有限公司科技项目,基于全寿命周期数据的电能表质量分析技术研究(J2023141)。

摘  要:为了对电能表产生的复杂数据进行降维处理,以实现从海量数据中提取有效数据的目的,实验提出一种基于标准化处理与成分分析的电能表数据降维方法。该方法首先通过标准化实现对电能表复杂数据的预处理,以去除多余且冗杂的数据;接着利用增量成分分析法实现对预处理后数据的降维操作。结果表明,当目标维数为5时,所提算法在测试集上的降维准确率高达0.889;在验证集上,该算法的平均相对误差值远远小于0.20,且能够正确对电能表所产生的4种降维数据进行正确地识别。以上结果说明,所提出算法有效降低了数据的维度,并且能够保证后续对数据的正确识别,有助于推动智能电网的技术进步与能源管理的智能化。To reduce the dimensionality of complex data generated by electric energy meters and extract effective data from mas-sive amounts of data,a method for reducing the dimensionality of electric energy meter data based on standardization processing and component analysis is proposed in the experiment.This method first preprocesses complex data of electricity meters through standardi-zation to remove redundant and redundant data;The preprocessed data is then subjected to dimensionality reduction using the incre-mental component analysis approach.It was found that when the target dimension was 5,the IOCA algorithm achieved a dimensionali-ty reduction accuracy of up to 0.889 on the test set;On the validation set,the MRE value of the IOCA algorithm is far less than 0.20.The IOCA algorithm can correctly identify the four types of dimensionality reduction data generated by electricity meters.The above results indicate that the IOCA algorithm effectively reduces the dimensionality of data and ensures the correct identification of data in the future,which helps to promote the technological progress of smart grids and the intelligence of energy management.

关 键 词:标准化处理 成分分析 电能表 数据降维 能源管理 

分 类 号:TM215[一般工业技术—材料科学与工程] TP39[电气工程—电工理论与新技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象