Special transformer industry missort identification method based on power utilization characteristics and outlier detection
A technology of outlier detection and power consumption characteristics, applied in character and pattern recognition, data processing applications, instruments, etc., can solve problems such as inability to effectively identify users, and achieve the effect of improving recognition efficiency
Pending Publication Date: 2020-10-30
ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY +2
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This kind of classification is usually carried out on the basis of the industry information of special transformer power users, without identifying the authenticity of the industry information. That is to say, neither the traditional special transformer industry classification method nor the load feature mining method can effectively identify Users with wrong industry information
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0063] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings.
[0064] Such as figure 1 as shown, figure 1 It is the calculation process of the present invention: firstly, the daily power consumption data of a certain industry in a certain industry are collected for 365 days a year, and its daily power consumption is normalized; then the 365-dimensional daily power consumption data is The electrical data is input into the PCA dimensionality reduction algorithm, sorted according to the size of the eigenvalues of the principal components, and the principal component vectors with larger eigenvalues that retain the characteristics of electricity consumption are selected as the characteristic data after dimensionality reduction; The LOF coefficient of the feature data in the new feature space, and the elbow method is used to determine the threshold of the LOF coefficient; finally, the specific us...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a special transformer industry missort identification method based on power utilization characteristics and outlier detection, and relates to the field of power operation and maintenance. At present, users with wrong information in the special transformer industry cannot be effectively identified.acquiring daily power consumption data of special transformer users in a certain industry in a regional range within 365 days of a year, and normalizing the daily power consumption of the special transformer users; inputting the 365-dimensional daily power consumption data intoa PCA dimension reduction algorithm, sorting according to the sizes of the principal part characteristic values, and selecting and reserving a principal part vector with a relatively large characteristic value for representing the power consumption characteristic as the characteristic data after dimension reduction; then calculating an LOF coefficient of the feature data of the special transformer user after dimension reduction in a new feature space, and determining an LOF coefficient threshold by adopting an elbow method; and finally, selecting the special transformer users of which the LOFcoefficients are greater than a threshold value as industry classification error suspected users to be checked. According to the technical scheme, identification of special transformer users with wrong archive classification in one industry can be completed quickly and accurately according to typical power utilization information of different industries.
Description
technical field [0001] The invention relates to the field of electric power operation and maintenance, in particular to a method for identifying wrong households in special transformation industries based on power consumption characteristics and outlier detection. Background technique [0002] The power consumption characteristics of power users in different industries are not the same. If the industry is not differentiated, it is only to analyze the load characteristics of power users as a whole. It is difficult to accurately grasp the power consumption characteristics of each user. The accuracy is not high. To optimize the optimization and efficient management of electricity consumption behavior, it is necessary to start from various industries and analyze the load characteristics and electricity consumption habits of various industries. [0003] The traditional method of classifying the special transformer industry usually divides the special transformer types according t...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06Q50/06G06K9/62
CPCG06Q50/06G06F18/2135
Inventor 姚力陆春光徐韬章江铭倪琳娜陈嘉林英鹤王建波
Owner ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY