CN110335169B - Low-voltage user accurate identification method based on multi-source data fusion - Google Patents

Abstract

The invention discloses a method for accurate identification of low-voltage users based on multi-data fusion, which relates to the field of electricity metering. fused multi-source data to obtain a fused list; perform preliminary filtering according to the fused list to obtain a fused list of suspected low-voltage users; perform a call test on the fused list of suspected low-voltage users; The data is judged to generate a list of suspected low-voltage users after the call and test; the final list of low-voltage users is determined by checking the two lists obtained at the end. The present invention not only saves the time for grid enterprises to conduct low-voltage list statistics independently, but also saves the input of labor cost for statistics of low-voltage user lists; The list is more accurate and reliable.

Description

A method for accurate identification of low-voltage users based on multi-source data fusion

technical field

The invention relates to the field of power metering, in particular to a method for accurate identification of low-voltage users based on multi-source data fusion.

Background technique

With the gradual increase of residential electricity consumption, the quality of electricity service of power supply enterprises has also been put on the agenda. In many network areas, there are complex lines in the station area, and the transformers are overloaded and overloaded. In order to better meet the power demand of users and serve users, power supply companies need to promptly discover a series of problems that users have in the process of power consumption, typically low voltage problem. This application relies on the metering automation system to carry out low-voltage detection. Through various sources of low-voltage user lists, the corresponding fusion algorithm is applied to perform data fusion. At the same time, the generated low-voltage user list is combined with the metering automation system to perform point-to-point call testing and finally determine the low voltage of the network area. User list.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a method for accurate identification of low-voltage users based on multi-source data fusion, thereby overcoming the time-consuming and labor-intensive shortcomings of the traditional method of obtaining a list of low-voltage users.

In order to achieve the above purpose, the present invention provides a method for accurate identification of low-voltage users based on multi-source data fusion, comprising the following steps:

S1. Collect and integrate low-voltage user multi-source data;

S2. Integrate the multi-source data of the low-voltage users to obtain a fused list of suspected low-voltage users, and perform preliminary filtering on the fused list of suspected low-voltage users for voltage users that use electricity normally, and obtain a fusion-processed suspected low-voltage user list. List of low voltage users;

S3. Perform a call test on the merged list of suspected low-voltage users, and generate a list of suspected low-voltage users after the call and test according to the user voltage data after the call and test;

S4. Check the list of suspected low-voltage users after the fusion processing and the list of suspected low-voltage users after calling and testing, and generate a final list of low-voltage users.

Further, the low-voltage user multi-source data is collected and integrated according to the low-voltage judgment source, including:

(1) Collect 12398 or 95598 complaint information, classify and process the complaint information, set users who complained due to low voltage as suspected low voltage users, and conduct statistics on suspected low voltage users to generate suspected low voltage users list;

(2) Collect the list of suspected low-voltage users checked out by the on-site operation and maintenance staff of the power supply bureau in their daily work;

(3) Relying on the measurement automation system to set low voltage judgment conditions, the measurement automation measurement system analyzes and determines the user voltage data, obtains preliminary low voltage users, counts the preliminary low voltage users and generates a list of suspected low voltage users;

(4) Analyze and process the user voltage data in the concentrator, determine low-voltage users, and generate a list of suspected low-voltage users.

Further, the function of the concentrator is expanded: a function of determining whether the recorded user voltage data is low voltage is added to the concentrator, and for users whose user voltage data is low voltage, the concentrator generates alarm information, and report the low-voltage user, and the main station of the metering automation system generates a list of suspected low-voltage users according to the reported low-voltage users.

Further, according to the requirements of distributed processing information, the function of extending the concentrator is specifically set as:

(1) The concentrator stores 384 points of meter load records, that is, 96 points per day for 6 days;

(2) The concentrator selects the measurement point and selects the time period for the meter load record data collection through parameters;

(3) The concentrator reports the time points and data corresponding to the high and low voltage of each measurement point in one day to the main station of the metering automation system;

(4) According to the low voltage and high voltage thresholds, the concentrator judges the recorded voltage data to form an alarm and reports it to the main station of the metering automation system; the alarm is generated regularly as needed, such as daily; The time points and number of high and low voltage thresholds.

Further, the S2 specifically includes the following steps:

S21. Integrate the four types of suspected low-voltage user lists collected by S1, extract the four types of suspected low-voltage user lists according to the low-voltage type and time point of the user, and remove the four types of suspected low-voltage users at the same time. Duplicate suspected low-voltage user lists in the user list to generate a merged suspected low-voltage user list;

S22. According to the fused list of suspected low-voltage users, relying on the metering automation system, extract the historical voltage curve and characteristic information of the suspected low-voltage users in the fused list of suspected low-voltage users in the metering automation system;

S23, analyze and process the historical voltage curve and characteristic information of the suspected low-voltage users respectively, and obtain a low-voltage user and a voltage user with normal power consumption through preliminary judgment;

S24 , marking the voltage users with normal power consumption in the merged list of suspected low-voltage users, to obtain a list of suspected low-voltage users after fusion processing.

Further, the S23 is specifically: if there is a low-voltage voltage curve and characteristic information in the historical actual voltage curve and characteristic information of the suspected low-voltage user, it is preliminarily determined that the suspected low-voltage user is a low-voltage user; if The historical actual voltage curve and characteristic information of the suspected low-voltage user If there is no low-voltage voltage curve and characteristic information in the actual voltage curve, it is preliminarily determined that the suspected low-voltage user is a voltage user with normal power consumption.

Further, the S3 includes the following steps:

S31, issuing an instruction for collecting voltage data to the collecting terminal through the metering automation system;

S32, the station concentrator receives the voltage data collection command, and collects the user's voltage data for the electric energy meter under the station area according to the voltage data collection command;

S33, the concentrator uses its own expansion function to analyze the collected user voltage data according to the collected voltage data of the electric energy meter to determine whether it is a low-voltage user, and mark it accordingly in the list of suspected low-voltage users obtained in S2, Generate a list of suspected low-voltage users after the test call.

Further, the checking method is as follows: removing duplicated voltage users with normal power consumption in the list of suspected low-voltage users after fusion processing and the list of suspected low-voltage users after calling and testing.

Compared with the existing technology, the traditional method of obtaining the list of low-voltage users is to rely solely on the metering automation main station to call and measure the voltage data of the entire network area, and at the same time rely on the metering automation main station to determine all the voltage data called and measured. process, and determine the list of low-voltage users in the network area; this method is time-consuming and labor-intensive. The present invention is a method for accurate identification of low-voltage users based on multi-source data fusion, which integrates the multi-source data of low-voltage users that can be collected by power grid enterprises in daily production work, and performs corresponding multi-source data fusion. Obtain the merged list; perform preliminary filtering according to the merged list to obtain a list of suspected low-voltage users after fusion processing; perform a call test on the merged list of suspected low-voltage users, and generate a call test based on the user voltage data after the call and test After checking the list of suspected low-voltage users, the final list of low-voltage users is checked according to the two final lists. Compared with the traditional method of determining the list of low-voltage users in the network area, the present invention not only saves the power grid enterprise from carrying out low-voltage users separately. It saves the time for voltage list statistics, and saves the labor cost of statistics of low-voltage user lists. At the same time, the low-voltage user list is determined and integrated from the perspective of multi-source data fusion, which makes the low-voltage user list more accurate and reliable.

Description of drawings

In order to illustrate the technical solutions of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only an embodiment of the present invention, which is very important in the art. For those of ordinary skill, other drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is a flowchart of a method for accurate identification of low-voltage users based on multi-source data fusion according to the present invention.

Detailed ways

The technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

As shown in Figure 1, the method for accurate identification of low-voltage users based on multi-source data fusion provided by the present invention includes the following steps:

S1. Collect and integrate low-voltage user multi-source data; specifically, integrate the low-voltage user list according to the source of the low-voltage user list, and collect and integrate the suspected low-voltage user list according to the following sources:

(1) Collect complaint information such as 12398 or 95598, classify and process the complaint information, set users who complained due to low voltage as suspected low voltage users, and collect statistics on suspected low voltage users to generate a list of suspected low voltage users;

(2) Collect the list of suspected low-voltage users checked out by the on-site operation and maintenance staff of the power supply bureau in their daily work;

(3) Relying on the measurement automation system to set low voltage judgment conditions, the measurement automation system analyzes and determines the user voltage data, obtains preliminary low voltage users, counts the preliminary voltage users and generates a list of suspected low voltage users;

(4) Analyze and process the user voltage data in the concentrator, determine low-voltage users, and generate a list of suspected low-voltage users;

Specifically, the function of the concentrator is expanded, and the function of judging whether the recorded user voltage data is low voltage is added to the concentrator. For users whose user voltage data is low voltage, the concentrator generates an alarm message and sends the low voltage to the user. The user reports, and the main station of the metering automation system generates a list of suspected low-voltage users according to the reported low-voltage users.

Among them, the functions of the extended concentrator are extended and designed in accordance with the requirements of distributed processing information under the framework of the 2013 Statute of China Southern Network, and the following settings are added:

(1) The concentrator stores 384 points of meter load records, that is, 96 points per day for 6 days;

(2) The concentrator selects the measurement point and selects the time period for the meter load record data collection through parameters;

(3) The concentrator reports the time points and data corresponding to the high and low voltage of each measuring point in one day to the main station of the metering automation system;

(4) According to the low voltage and high voltage thresholds, the concentrator judges the recorded voltage data to form an alarm and reports it to the main station of the metering automation system; the alarm is generated regularly as needed, such as daily; The time points and number of high and low voltage thresholds.

S2. Integrate multi-source data of low-voltage users to obtain a fused list of suspected low-voltage users, and preliminarily filter the voltage users with normal power consumption on the fused list of suspected low-voltage users, and obtain a fusion-processed suspected low-voltage user User list. specific:

S21. Integrate the four types of suspected low-voltage user lists collected by S1, extract the four types of suspected low-voltage user lists according to the low-voltage type and time point of the user, and remove the four types of suspected low-voltage users at the same time. Duplicate suspected low-voltage user lists in the user list to generate a merged suspected low-voltage user list;

S22. According to the merged list of suspected low-voltage users and relying on the metering automation system, extract the historical voltage curve and characteristic information of the suspected low-voltage users in the merged list of suspected low-voltage users in the metering automation system;

S23. Analyze and process the historical voltage curve and characteristic information of the suspected low-voltage user respectively: if there is a low-voltage voltage curve and characteristic information in the historical voltage curve and characteristic information of the suspected low-voltage user, the low-voltage voltage curve and characteristic information Information: If the voltage curve shows a user voltage curve lower than 198V, and the monthly cumulative time of the user characteristic information showing low voltage exceeds 10 hours, the suspected low-voltage user is determined to be a low-voltage user; if the voltage curve and characteristics of the suspected low-voltage user If there is no low-voltage voltage curve and characteristic information in the information, it is determined that the suspected low-voltage user is a voltage user with normal electricity consumption;

S24 , marking the voltage users with normal power consumption in the merged list of suspected low-voltage users, to obtain a list of suspected low-voltage users after fusion processing.

S3. Perform a call test on the merged list of suspected low-voltage users, and generate a list of suspected low-voltage users after the call and test according to the user voltage data after the call and test. specific:

Carry out point-to-point voltage data call test for the low-voltage users in the list of suspected low-voltage users obtained by S2; issue the voltage data collection command to the acquisition terminal through the metering automation system; The user's voltage data collection is carried out for the electric energy meter under the station area; the concentrator uses its own expansion function to analyze the collected user voltage data according to the collected voltage data of the electric energy meter to determine whether it is a low-voltage user, and obtain in S2. Make corresponding marks in the list of suspected low-voltage users, and generate a list of suspected low-voltage users after the test call.

S4. Check the list of suspected low-voltage users after the fusion processing and the list of suspected low-voltage users after calling and testing, and generate a final list of low-voltage users.

The method of checking is to remove the repeated voltage users with normal power consumption in the list of suspected low-voltage users after fusion processing and the list of suspected low-voltage users after calling and testing.

To sum up, the method of the present invention for accurate identification of low-voltage users based on multi-source data fusion, compared with the traditional method of judging the low-voltage user list in the network area, not only saves the time for the power grid enterprise to conduct low-voltage list statistics alone , and saves the input of labor costs for statistics of low-voltage user lists; at the same time, the low-voltage judgment and integration are carried out from the perspective of multi-source data fusion, which makes the low-voltage user list more accurate and reliable.

The above disclosure is only the specific embodiment of the present invention, but the protection scope of the present invention is not limited to this. should be included within the protection scope of the present invention.

Claims (4)

1. a method for accurate identification of low-voltage users based on multi-source data fusion, is characterized in that: comprise the following steps: S1. Collect and integrate low-voltage user multi-source data; S2. Integrate the multi-source data of the low-voltage users to obtain a fused list of suspected low-voltage users, and perform preliminary filtering on the fused list of suspected low-voltage users for voltage users that use electricity normally, and obtain a fusion-processed suspected low-voltage user list. List of low voltage users; The S2 specifically includes the following steps: S21. Integrate the four types of suspected low-voltage user lists collected by S1, extract the four types of suspected low-voltage user lists according to the low-voltage type and time point of the user, and remove the four types of suspected low-voltage users at the same time. Duplicate suspected low-voltage user lists in the user list to generate a merged suspected low-voltage user list; S22. According to the fused list of suspected low-voltage users, relying on the metering automation system, extract the historical voltage curve and characteristic information of the suspected low-voltage users in the fused list of suspected low-voltage users in the metering automation system; S23, analyze and process the historical voltage curve and characteristic information of the suspected low-voltage users respectively, and obtain a low-voltage user and a voltage user with normal power consumption through preliminary judgment; The S23 is specifically: if it is suspected that the historical actual voltage curve and characteristic information of the suspected low-voltage user has a low-voltage voltage curve and characteristic information, then preliminarily determine that the suspected low-voltage user is a low-voltage user; if the suspected low-voltage user is a low-voltage user; Historical actual voltage curve and characteristic information of low-voltage users If there is no low-voltage voltage curve and characteristic information in the actual voltage curve, it is preliminarily determined that the suspected low-voltage user is a voltage user with normal power consumption; S24. Mark the voltage users who use electricity normally in the merged list of suspected low-voltage users, and obtain a list of suspected low-voltage users after fusion processing; S3. Perform a call test on the merged list of suspected low-voltage users, and generate a list of suspected low-voltage users after the call and test according to the user voltage data after the call and test; The S3 includes the following steps: S31, issuing an instruction for collecting voltage data to the collecting terminal through the metering automation system; S32, the station concentrator receives the voltage data collection command, and collects the user's voltage data for the electric energy meter under the station area according to the voltage data collection command; S33, the concentrator uses its own expansion function to analyze the collected user voltage data according to the collected voltage data of the electric energy meter to determine whether it is a low-voltage user, and mark it accordingly in the list of suspected low-voltage users obtained in S2, Generate a list of suspected low-voltage users after the test call; S4. Check the list of suspected low-voltage users after fusion processing and the list of suspected low-voltage users after calling and testing, and generate a final list of low-voltage users; The checking method is as follows: removing the repeated voltage users with normal power consumption in the list of suspected low-voltage users after fusion processing and the list of suspected low-voltage users after calling and testing. 2. The method for accurate identification of low-voltage users based on multi-source data fusion according to claim 1, wherein the multi-source data of low-voltage users is collected and integrated according to low-voltage judgment sources, comprising: (1) Collect 12398 or 95598 complaint information, classify and process the complaint information, set users who complained due to low voltage as suspected low voltage users, and conduct statistics on suspected low voltage users to generate suspected low voltage users list; (2) Collect the list of suspected low-voltage users checked out by the on-site operation and maintenance staff of the power supply bureau in their daily work; (3) Relying on the measurement automation system to set low voltage judgment conditions, the measurement automation measurement system analyzes and determines the user voltage data, obtains preliminary low voltage users, counts the preliminary low voltage users and generates a list of suspected low voltage users; (4) Analyze and process the user voltage data in the concentrator, determine low-voltage users, and generate a list of suspected low-voltage users. 3. The method for accurate identification of low-voltage users based on multi-source data fusion according to claim 2, characterized in that: expanding the function of the concentrator: adding in the concentrator to determine whether the recorded user voltage data is It is a low-voltage function. For users whose voltage data is low-voltage, the concentrator generates alarm information and reports the low-voltage user. The main station of the metering automation system generates a suspected low-voltage user according to the reported low-voltage user. List of Low Voltage Users. 4. The method for accurate identification of low-voltage users based on multi-source data fusion according to claim 3, wherein the function of expanding the concentrator is specifically set as: (1) The concentrator stores the meter load records of 384 points; (2) The concentrator selects the measurement point and selects the time period for the meter load record data collection through parameters; (3) The concentrator reports the time points and data corresponding to the high and low voltage of each measurement point in one day to the main station of the metering automation system; (4) According to the low voltage and high voltage thresholds, the concentrator judges the recorded voltage data to form an alarm and reports it to the main station of the metering automation system; the alarm is generated regularly according to the needs, that is, every day; The time points and number of high and low voltage thresholds.

Images