Method and device for identifying and processing abnormality indices of distribution network based on big data
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A processing method and processing device technology, applied in data processing applications, character and pattern recognition, instruments, etc., can solve problems such as weak analysis methods, achieve low time complexity, improve accuracy, and improve data quality.
Pending Publication Date: 2019-01-04
WENZHOU ELECTRIC POWER BUREAU +2
View PDF0 Cites 14 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, with the gradual accumulation of public change operation data, traditional analysis methods are becoming increasingly weak. Therefore, an analysis method that
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0064]The identification and processing method of abnormal indicators of distribution network based on big data includes the following steps:
[0065] Step A: collect the public transformer current, voltage, and power and send them to the power consumption information collection system through the electric energy meter, and store the public transformer operation data in the HBase database of the power consumption information collection system;
[0066] Step B: Load the public change operation data from the HBase library into the distributed memory;
[0067] Step C: Use the iForest algorithm to identify outliers in the operating data and delete them, specifically:
[0068] C1. Perform random sampling without replacement on the operating data;
[0069] C2. Construct an iTree tree according to the sample data, that is, randomly select a dimension, randomly select a value in this dimension as the division point, put the data in the dimension smaller than the division point in the...
Embodiment 2
[0091] This application also proposes a device for identifying and processing abnormal indicators of distribution networks based on big data, including:
[0092] The data acquisition module collects the operation data of the public transformer and sends it to the power consumption information collection system for the HBase database of the power consumption information collection system to store the public transformer operation data;
[0093] The data loading module loads the public variable operation data from the HBase library to the distributed memory;
[0094] The data elimination module uses the iForest algorithm to identify abnormal values of the operating data and delete them;
[0095] The data clustering module clusters the remaining data subsets with the k-means algorithm;
[0096] In the data processing module, after clustering, the average values at the corresponding dimensions of each category are used to fill in the deleted outliers.
[0097] Specifically, t...
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 method for identifying and processing abnormal indexes of distribution network based on large data. The method comprises the following steps: collecting real-time data of special bus transformer operation of distribution network and sending the real-time data to an intelligent operation and maintenance management and control system of distribution network; storing the real-time data in a distributed database HBase; the SPARK being used to load the running real-time data from the HBase database into the memory, the outlier of the running data being identified and deleted by the iForest algorithm, and the remaining data subset being deleted by k-Means algorithm clustering; after clustering, the average value at the corresponding dimension of each category is used tofill the deleted outliers. The device adopted by the method comprises a data acquisition module, a loading module, a culling module, a clustering module and a processing module. The invention utilizes the distributed database HBASE to store the real-time data of the dedicated metering operation, and timely finds out the defects of the real-time data of the distribution network operation and makescorrections through the efficient analysis of the massive data by the distributed and parallel computing framework SPARK of the big data.
Description
technical field [0001] The invention belongs to the field of analysis of distribution network indicators, and in particular relates to a method and device for identifying and processing abnormal indicators of distribution network based on big data. Background technique [0002] The distribution network is at the end of the entire power grid, and it is the window of the power enterprise to the society. The operation and management of the distribution network is directly related to thousands of households, and its social responsibility and influence are huge. With the continuous development of society, higher and higher requirements are put forward for the lean management of distribution network. The distribution network has the characteristics of many points, long lines, and wide areas. With the development of power consumption information systems and the increasingly advanced collection devices, most public distribution transformers in the distribution network have the condi...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more