基于动态网格生成技术和k-means算法的电力客户行为分析方法  被引量:4

Analysis method of power customer behavior based on dynamic grid generation technology and k-means algorithm

在线阅读下载全文

作  者:孔繁春 王婷 李旭东 KONG Fanchun;WANG Ting;LI Xudong(Inner Mongolia Power Marketing Service&Operation Management Center,Hohhot 010000,China)

机构地区:[1]内蒙古电力营销服务与运营管理中心,内蒙古呼和浩特010000

出  处:《电子设计工程》2022年第15期127-131,共5页Electronic Design Engineering

摘  要:针对电力客户用电行为分析的收敛性不好、可靠性不高的问题,提出基于动态网格生成技术和k-means算法的电力客户行为分析方法。根据电力客户行为的确定性和非确定性特征量挖掘电力客户行为特征,结合指向性增益控制方法分析电力客户行为分布大数据的动态网格特征参数,通过动态网格生成技术,构建电力客户行为的融合关联特征量,采用先验概率密度特征分析方法,建立电力客户行为的输出可靠性状态参数集,结合最小期望和均方误差估计方法,实现对电力客户行为的特征提取,采用k-means聚类方法聚类提取电力客户行为特征,实现对电力客户行为的优化挖掘和量化分析。仿真测试结果表明,采用该方法进行电力客户行为特征量化分析的准确性较高,可靠性较好,提高了电力客户行为特征挖掘和检测识别的能力。Aiming at the problems of poor convergence and low reliability of power customer behavior analysis,a power customer behavior analysis method is proposed based on dynamic grid generation technology and k-means algorithm.According to the deterministic and non deterministic characteristics of power customer behavior,the characteristics of power customer behavior are mined.Combined with the directional gain control method,the dynamic grid characteristic parameters of big data of power customer behavior distribution are analyzed.Through the dynamic grid generation technology,the fusion associated characteristic quantity of power customer behavior is constructed,and the prior probability density characteristic analysis method is used to establish the power customer behavior model combined with the minimum expectation and mean square error estimation method,the feature extraction of power customer behavior is realized.The k-means clustering method is used to cluster the extracted power customer behavior features to realize the optimal mining and quantitative analysis of power customer behavior.The simulation test results show that the method has high accuracy and reliability,and improves the ability of power customer behavior feature mining,detection and recognition.

关 键 词:动态网格 K-MEANS算法 特征提取 数据聚类 

分 类 号:TM76[电气工程—电力系统及自动化]

 

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