CN113919853B - Low-voltage user electricity stealing identification method based on edge-to-edge fusion - Google Patents
Low-voltage user electricity stealing identification method based on edge-to-edge fusion Download PDFInfo
- Publication number
- CN113919853B CN113919853B CN202111210041.XA CN202111210041A CN113919853B CN 113919853 B CN113919853 B CN 113919853B CN 202111210041 A CN202111210041 A CN 202111210041A CN 113919853 B CN113919853 B CN 113919853B
- Authority
- CN
- China
- Prior art keywords
- phase
- electricity stealing
- phase meter
- meter
- voltage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000004927 fusion Effects 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000013139 quantization Methods 0.000 claims abstract description 8
- 230000002159 abnormal effect Effects 0.000 claims description 42
- 230000005856 abnormality Effects 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 2
- 238000005303 weighing Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 abstract description 6
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 12
- 230000008901 benefit Effects 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 7
- 230000006399 behavior Effects 0.000 description 4
- 230000002265 prevention Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R11/00—Electromechanical arrangements for measuring time integral of electric power or current, e.g. of consumption
- G01R11/02—Constructional details
- G01R11/24—Arrangements for avoiding or indicating fraudulent use
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a low-voltage user electricity stealing identification method based on edge-to-edge fusion. The method comprises the steps that multivariate power consumption data of users are collected through cooperation of side-end equipment, and electricity stealing suspicion quantization parameters are obtained through processing based on uncapping event records, zero line current, live line current and voltage load curves aiming at single-phase users; aiming at a three-phase user, processing and obtaining suspected quantitative parameters of electricity stealing based on the record of the uncapping event, the voltage load curve and the active power load curve; establishing a single-phase meter and three-phase meter electricity stealing suspicion weight model, determining weight parameters in the electricity stealing suspicion weight model through an analytic hierarchy process, calculating the electricity stealing suspicion parameters and judging to obtain an electricity stealing identification result. The invention fully utilizes the characteristics of the multivariate power consumption data of the user, can effectively identify the power stealing behavior of the user, does not need to additionally install monitoring equipment, and avoids high investment, operation and maintenance cost; meanwhile, the influence of factors such as high data communication pressure and poor clock synchronism on the identification accuracy can be effectively relieved by utilizing the cooperation of the edge-end equipment on data acquisition.
Description
Technical Field
The invention relates to a power utilization detection method of an electric power internet of things information system, in particular to a low-voltage user electricity stealing identification method based on edge-side data fusion.
Background
With the more and more compact relationship between the social economic development and the electric power, part of lawless persons are driven by economic benefits to steal electricity by various means, and the electricity stealing phenomenon is often prohibited. The difficult problems which puzzles power supply enterprises for a long time not only seriously damage the benefits of the power supply enterprises and disturb the normal power utilization order, but also can cause the damage of power facilities to form a serious power utilization safety problem, and become an important topic. The power supply enterprises increase the work force of fighting against electricity stealing all the time, and simultaneously improve the technical means of electricity stealing prevention continuously. However, the current electricity stealing prevention technology still has great limitation, and the electricity stealing means are increasingly hidden, diversified, rapid and high-tech, and the difficulty of electricity stealing prevention is more and more great.
Disclosure of Invention
The invention aims to accurately position the information of low-voltage electricity stealing users, screen out users with electricity stealing behaviors, provide a user list for field workers and provide a quick and effective analysis means for the electricity stealing prevention work of power supply enterprises; promote the construction of the smart power grid, improve the economic operation level of the power grid, practically improve the economic benefit and the social benefit of a company,
as shown in fig. 1, the present invention adopts the following technical solutions:
step 1: acquiring multi-element electricity consumption data of user side equipment based on archive information of a target platform area, wherein the multi-element electricity consumption data comprises uncapping event records of a single-phase meter and a three-phase meter, zero line current and live line current of the single-phase meter, a voltage load curve of the single-phase meter, and a voltage load curve and a power load curve of the three-phase meter;
the electric meter is divided into a single-phase meter or a three-phase meter, the single-phase meter or the three-phase meter is adopted, a user installing the single-phase meter is a single-phase user, and a user installing the three-phase meter is a three-phase user.
In specific implementation, the record of the uncovering event of the electric meter is obtained through detection of an uncovering contact inside the electric meter.
Step 2: aiming at a single-phase user who installs a single-phase meter, processing and obtaining suspected quantitative parameters of electricity stealing of the single-phase meter based on the record of the uncapping event of the single-phase meter, the zero line current, the live line current and the voltage load curve data;
and step 3: aiming at a three-phase user installing a three-phase meter, processing and obtaining a suspected power stealing quantization parameter of the three-phase meter based on the record of the uncapping event of the three-phase meter and the data of the voltage load curve and the power load curve of the three-phase meter;
and 4, step 4: establishing an electricity stealing suspicion weight model of the single-phase meter and the three-phase meter, determining weight parameters in the electricity stealing suspicion weight model through an analytic hierarchy process, calculating the electricity stealing suspicion parameters of the single-phase user and the three-phase user, and judging to obtain an electricity stealing identification result.
The low voltage in the low voltage user according to the present invention refers to a voltage class. The voltage classes of the power grid comprise 500kV, 220kV, 110kV, 35kV, 10kV and 380V, wherein the power supply network of 380V and below is generally called a low-voltage power distribution network, and power supply users thereof are generally called low-voltage users.
The step 2 specifically comprises the following steps:
the suspected quantitative parameters of electricity stealing of the meter cover of the single-phase meter are determined according to the following formula:
in the formula, Sd1Opening a meter cover of the single-phase meter to obtain suspected parameters of electricity stealing; m is the uncapping event frequency of the single-phase meter; m0A frequency threshold value of the single-phase meter uncapping event abnormity is set;
processing and determining suspected quantization parameters of zero line current deviation electricity stealing of the single-phase meter according to the following formula:
in the formula, Sd2Quantizing parameters for suspicion of electricity stealing due to zero-live line current deviation of a single-phase meter;
respectively the live wire current and the zero line current at the time t of the single-phase meter; epsilonIA threshold value for judging the current deviation abnormity of the zero line and live line of the single-phase meter at the current moment; omegaTThe time set meeting the abnormal zero line and live line current deviation of the single-phase meter is set;
the current of the live wire and the current of the zero line at the h moment of the single-phase meter are respectively; I.C. A0A threshold value for judging the availability of the zero line current and the live line current of the single-phase meter at the current moment; omegaHA time set available for the zero live line current of the single-phase meter; num (omega)T)、num(ΩH) Respectively represent the set omegaT、ΩHThe number of elements of (a);
the integrity of the zero line and live line current of the single-phase meter is processed, the current threshold and the difference value of the current sequence with the current integrity are compared, then the suspect estimation is carried out according to the total time period number of the zero line and live line current comparison and the suspect time period number, and the suspect electricity stealing parameter of the single-phase user is obtained by calculating the proportion of the suspect electricity stealing time period in the total time period.
The suspected quantitative parameters of the abnormal voltage electricity stealing of the single-phase meter are determined according to the following formula:
in the formula, Sd3Quantifying parameters for suspicion of electricity stealing due to voltage abnormality of the single-phase meter;
voltage data of the single-phase meter at the time t; u shape0A threshold value for judging the voltage abnormality of the single-phase meter; t is1The total time period of the voltage load curve data of the single-phase meter is shown.
The step 3 specifically comprises the following steps:
and (3) judging whether one phase or two phases of voltage loss exists or not and the occurrence time is greater than the sampling time by detecting the three-phase voltage of a three-phase user according to the voltage and abnormal event recorded data of the three-phase electric meter, and further processing to obtain suspected quantitative parameters of the voltage phase loss abnormality. It should be noted that: for the judgment of the voltage abnormity of the three-phase meter, the voltage abnormity of the three-phase meter is judged as long as any phase voltage data of the three-phase meter is abnormal; and judging the active power abnormity of the three-phase meter only if the active power abnormity of any phase or two-phase active power data is required to be met.
Processing and determining suspected quantization parameters of electricity stealing of the open meter cover of the three-phase meter according to the following formula:
in the formula, Ss1Quantifying parameters for suspicion of electricity stealing when opening a meter cover of the single-phase meter; n is the opening event frequency of the three-phase meter; n is a radical of0A frequency threshold value of the three-phase meter uncovering event abnormity is set;
the suspected quantitative parameters of the abnormal voltage electricity stealing of the three-phase meter are determined according to the following formula:
in the formula, Ss2Quantifying parameters for suspicion of electricity stealing due to abnormal voltage of the three-phase meter;
for the time t of a three-phase watch
Phase voltage data; u shape0A threshold value for judging the voltage abnormity of the three-phase meter; t is a unit of2The total time period number of the voltage load curve data of the three-phase meter is shown; [ A, B, C ]]Is an ABC three-phase set;
the electricity stealing of the three-phase user is not only reflected on one-phase or two-phase loss, but also has abnormal power consumption of the user, and is assisted to the suspicion of electricity stealing of the user by combining three-phase abnormal data,
processing and determining the suspected quantitative parameters of active power abnormal electricity stealing of the three-phase meter according to the following formula:
in the formula, Ss3Quantifying parameters for active power abnormal electricity stealing suspicion of the three-phase meter;
for the time t of a three-phase watch
Phase active power data; p is0A threshold value for judging the active power abnormity of the three-phase meter; t is2And the total time period number of the active power load curve data of the three-phase meter.
In the step 4, establishing a suspicion of electricity stealing weight model of the single-phase meter and the three-phase meter to obtain suspicion of electricity stealing parameters of the single-phase user and the three-phase user:
Sd＝wd1Sd1+wd2Sd2+wd2Sd2
Ss＝ws1Ss1+ws2Ss2+ws2Ss2
in the formula, Sd、SsSuspicion of electricity stealing, w, for single and three phase users respectivelyd1、wd2、wd3Respectively opening a meter cover for a single-phase user, weighing parameters of abnormal zero-live line deviation and suspicion of electricity stealing due to abnormal voltage, ws1、ws2、ws3Respectively opening a meter cover for a three-phase user, and weighting parameters of voltage abnormity and active power abnormity electricity stealing suspicion;
and then comparing the electricity stealing suspicion parameters of the single-phase user and the three-phase user with a preset electricity stealing suspicion reference threshold value: if the electricity stealing suspicion parameter is larger than the electricity stealing suspicion reference threshold, the existence of electricity stealing is determined; otherwise there is no electricity stealing.
Specifically, iterative optimization processing is carried out on each weight parameter in the electricity stealing suspicion weight model by using an analytic hierarchy process, and each optimal weight parameter is obtained.
Each weight parameter in the suspected electricity stealing weight model is decomposed into 4 factors including uncapping record, zero line current, voltage and active power according to the influence electricity stealing identification, and the weight parameters are calculated for the 4 influence factors by utilizing an analytic hierarchy process.
The complex system evaluation systematization and modeling can be realized by adopting an analytic hierarchy process, and the used data is less.
The data quality is analyzed to obtain each weight parameter, which weight parameters are important can be seen, and the data quality has important influence on the quality of the algorithm identification result, so that the data quality of the station area in each day can be further analyzed to evaluate the reliability of the identification result.
The step 1 specifically comprises the following steps:
acquiring zero line current, live line current and voltage load curve data of a single-phase meter by adopting end-side equipment (namely an ammeter), and locally judging zero line current deviation abnormity and voltage abnormity; collecting voltage and active power load curves of the three-phase meter and locally judging the voltage and active power abnormity; the side equipment acquires uncovering event records of the single-phase meter and the three-phase meter, time data corresponding to the abnormal zero-live line current deviation and the abnormal voltage of the single-phase meter, and time data corresponding to the abnormal voltage and the abnormal active power of the three-phase meter; through the data acquisition mode of edge-end fusion, the communication pressure of mass data uplink can be effectively relieved, and the influence of data synchronism on analysis and judgment is avoided.
The purpose of this is to: generally, one platform area is provided with one side device and a plurality of end side electric meters, and the side device is responsible for gathering data of all the end side electric meters and uploading the data to a remote main station. The zero-live line current, the voltage load curve and the active power load curve of the end-side ammeter are data with large sample size, and normal sample data do not need to be sent to side equipment, so that communication pressure is avoided; meanwhile, some data (such as zero live wire current) have high real-time requirements, and if the data are uploaded and then abnormal analysis is performed in the side equipment, the influence of data synchronism may exist, so that analysis is locally performed in the side equipment, and then an analysis result is reported to the side equipment for comprehensive analysis. Based on the above, a data acquisition and analysis method of edge-end fusion is provided.
The invention makes full use of the multivariate electricity consumption data of the electric meter to carry out the analysis of the abnormal electricity consumption of the user. The electric meter multivariate data acquisition and analysis framework based on edge-end fusion is provided, an electric larceny suspicion parameter calculation model is established around meter cover opening behaviors, zero-live line current deviation, voltage and active power data of users, an electric larceny user list is finally screened out, and low-voltage user electric larceny identification based on edge-end fusion is achieved. Compared with other methods, the method has the advantages that electricity stealing users in low-voltage users can be accurately identified and positioned through electricity stealing suspicion quantitative calculation on the premise that target low-voltage archive information and electricity consumption data such as station electric meter zero-live line current, voltage and active power are known and other terminal equipment is not newly added, and the method is low in cost and high in engineering application value.
The invention has the beneficial effects that:
(1) the method can realize the identification of electricity stealing in the low-voltage distribution room, realize the treatment of electricity stealing, greatly reduce the data analysis work of suspected electricity stealing users, and has stronger adaptability;
(2) terminal equipment does not need to be additionally arranged in a low-voltage distribution room, and the method has the advantages of low cost, high engineering practical value and the like;
(3) by adopting the electric meter multi-data acquisition and analysis framework with edge-end fusion, the communication pressure of mass electric data can be effectively relieved, the influence of clock synchronism on the identification accuracy rate is reduced, and the electric meter multi-data acquisition and analysis framework has good engineering practical value.
The method provided by the invention is based on the existing low-voltage centralized meter reading frame, the characteristics of the multi-element electricity consumption data of the user are fully utilized, the electricity stealing behavior of the user can be effectively identified, the additional installation of monitoring equipment is not needed, the high investment operation and maintenance cost is avoided, meanwhile, the influence of factors such as high data communication pressure, poor clock synchronism and the like on the identification accuracy can be effectively relieved through the advantage complementation of the intelligent ammeter at the side and the end side, and the method has engineering practical value.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a plot of a neutral current profile for a single-phase electric meter in an example of implementation;
FIG. 3 is a live current profile for a single-phase electric meter in an exemplary embodiment;
FIG. 4 is a graph of the active power distribution of the A phase of a three-phase electric meter in an example of implementation;
FIG. 5 is a B-phase active power distribution plot for a three-phase electric meter in an example implementation;
FIG. 6 is a C-phase active power distribution plot for a three-phase electric meter in an example implementation;
table 1 is a table of uncapping records of each smart meter.
Detailed Description
The following description of the embodiments of the present invention is provided in connection with the accompanying drawings and examples.
Fig. 1 shows an implementation process provided in the embodiment of the present invention, which specifically includes the following steps:
step 1: acquiring multiple electricity consumption data of a user ammeter based on the archive information of a target area, wherein the multiple electricity consumption data comprises uncapping event records of a single-phase meter and a three-phase meter, zero line current and live line current of the single-phase meter, a voltage load curve of the single-phase meter, and a voltage load curve and a power load curve of the three-phase meter;
specifically, end-side equipment (namely an electric meter) is adopted to collect curve data of zero line current, live line current and voltage load of a single-phase meter, and zero line current deviation abnormity and voltage abnormity are judged locally; collecting voltage and active power load curves of the three-phase meter and locally judging the voltage and active power abnormity; the side equipment acquires uncovering event records of the single-phase meter and the three-phase meter, time data corresponding to the abnormal zero-live line current deviation and the abnormal voltage of the single-phase meter, and time data corresponding to the abnormal voltage and the abnormal active power of the three-phase meter; through the data acquisition mode of edge-end fusion, the uplink communication pressure of mass data can be effectively relieved, and the influence of data synchronism on analysis and judgment is avoided.
Step 2: aiming at a single-phase user who installs a single-phase meter, processing and obtaining suspected quantitative parameters of electricity stealing of the single-phase meter based on the record of the uncapping event of the single-phase meter, the zero line current, the live line current and the voltage load curve data;
the suspected quantitative parameters of electricity stealing of the meter cover of the single-phase meter are determined according to the following formula:
in the formula, Sd1Quantifying parameters for suspicion of electricity stealing when opening a meter cover of the single-phase meter; m is the uncapping event frequency of the single-phase meter; m0A frequency threshold value of single-phase meter uncapping event abnormity is set; in the embodiment, the threshold value M of the abnormal times of the single-phase meter cover opening event is set based on engineering experience0Is 10.
The suspected quantitative parameters of electricity stealing of zero live wire current deviation of the single-phase meter are determined according to the following formula:
in the formula, Sd2The parameters are suspected quantization parameters of zero-live line current deviation electricity stealing of the single-phase meter;
live line current and zero line current of the single-phase meter at the time t are respectively; I.C. AεA current threshold value for judging the current deviation abnormity of the zero line and live line of the single-phase meter at the current moment; omegaTThe time set meeting the abnormal zero line and live line current deviation of the single-phase meter is set;
the current of a live wire and the current of a zero line at the moment h of the single-phase meter are respectively; I.C. A0A threshold value for judging the availability of the zero line current and the live line current of the single-phase meter at the current moment; omegaHA time set available for the zero live line current of the single-phase meter; num (omega)T)、num(ΩH) Respectively represent the set omegaT、ΩHThe number of elements of (a); in the embodiment, the threshold epsilon of the single-phase meter zero-live line current deviation abnormity is set based on engineering experience I10 percent; threshold value I available for zero live wire current of single-phase meter at current moment0Was 0.01A.
Processing and determining suspected quantization parameters of abnormal voltage electricity stealing of the single-phase meter according to the following formula:
in the formula, Sd3Quantifying parameters for suspicion of electricity stealing due to voltage abnormality of the single-phase meter;
voltage data of the single-phase meter at the time t; u shape0A threshold value for judging the voltage abnormality of the single-phase meter; t is1The total time period number of the voltage load curve data of the single-phase meter is shown. In the embodiment, the threshold U of the voltage abnormality of the single-phase meter is set based on engineering experience0Is 176V.
And step 3: aiming at a three-phase user installing a three-phase meter, processing and obtaining suspected quantitative parameters of electricity stealing of the three-phase meter based on the record of the uncapping event of the three-phase meter and the data of the voltage load curve and the power load curve of the three-phase meter;
and (3) judging whether one phase or two phases of voltage loss exists or not and the occurrence time is greater than the sampling time by detecting the three-phase voltage of a three-phase user according to the voltage and abnormal event recorded data of the three-phase electric meter, and further processing to obtain suspected quantitative parameters of the voltage phase loss abnormality.
And (3) processing and determining suspected quantization parameters of the voltage open-phase abnormality of the three-phase meter according to the following formula:
in the formula, Ss1Opening a meter cover of the single-phase meter to obtain suspected parameters of electricity stealing; n is the opening event frequency of the three-phase meter; n is a radical of0A frequency threshold value of the three-phase meter uncovering event abnormity is set; in the embodiment, the number threshold N of the abnormal cover opening events of the three-phase meter is set based on engineering experience0Is 10.
The suspected quantitative parameters of the abnormal voltage electricity stealing of the three-phase meter are determined according to the following formula:
in the formula, Ss2Quantifying parameters for suspicion of electricity stealing due to abnormal voltage of the three-phase meter;
for the time t of a three-phase watch
Phase voltage data; u shape0A threshold value for judging the voltage abnormity of the three-phase meter; t is a unit of2The total time period number of the voltage load curve data of the three-phase meter is shown; [ A, B, C ]]Is an ABC three-phase set; in the embodiment, the threshold U of the three-phase meter voltage abnormity is set based on engineering experience0Is 176V.
Processing and determining the suspected quantitative parameters of active power abnormal electricity stealing of the three-phase meter according to the following formula:
in the formula, Ss3Quantifying parameters for active power abnormal electricity stealing suspicion of the three-phase meter;
for the time t of a three-phase watch
Phase active power data; p is0A threshold value for judging the active power abnormity of the three-phase meter; t is2And the total time period of the active power load curve data of the three-phase meter. In the embodiment, the threshold value P of active power abnormity of the three-phase meter is set based on engineering experience0Is 0.002 kW.
And 4, step 4: establishing an electricity stealing suspicion weight model of the following single-phase and three-phase meters to obtain electricity stealing suspicion parameters of the single-phase and three-phase users:
Sd＝wd1Sd1+wd2Sd2+wd2Sd2
Ss＝ws1Ss1+ws2Ss2+ws2Ss2
in the formula, Sd、SsSuspicion of electricity stealing, w, for single and three phase users respectivelyd1、wd2、wd3Respectively opening a meter cover for a single-phase user, abnormal deviation of zero line and live line, and suspicion of electricity stealing due to abnormal voltage, ws1、ws2、ws3Respectively opening a meter cover for a three-phase user, and weighting parameters of voltage abnormity and active power abnormity electricity stealing suspicion;
and then comparing the electricity stealing suspicion parameters of the single-phase user and the three-phase user with a preset electricity stealing suspicion reference threshold: if the electricity stealing suspicion parameter is larger than the electricity stealing suspicion reference threshold value, electricity stealing is considered to exist; otherwise there is no electricity stealing.
Wherein, the three-scale-based analytic hierarchy process is adopted to calculate each weight coefficient in the single-phase and three-phase user electricity stealing suspicion weight model.
Firstly, a comparison matrix is established by adopting a three-scale method: adopting three scales (0, 1 and 2), and establishing a comparison matrix according to the correlation importance comparison among the layers, wherein the specific steps are as follows:
when the single-phase meter electricity stealing suspicion model is analyzed, the criterion of the meter cover opening event is set to be the most important, the criterion of the voltage abnormality is the second order, the criterion of the zero line current deviation is the lowest, and a comparison matrix is obtained as follows:
secondly, calculating the ranking index of each index according to the following formula:
it can be calculated that: r ═ 423;
then, the judgment matrix C is calculated using the following formula:
it can be calculated that:
further, a geometric mean b is obtainedi：
It can be calculated that:
bi＝[0.3333 3 1]T
further, the weight and the characteristic value are calculated and consistency check is carried out
B is to beiAfter normalization, the weight W 'corresponding to the maximum eigenvalue is obtained as (W'1,w′2,...,w′n)。
It can be calculated that:
w′i＝[0.0769 0.6923 0.2308]T
then calculating the maximum eigenvalue lambda of the judgment matrixmax；
It can be calculated that:
λmax＝3
and finally, carrying out consistency check:
it can be calculated that:
CR＝0
RI is called the average random consistency indicator and is related only to the matrix order n:
RI＝[0 0 0.52 0.89 1.12 1.36 1.41 1.46 1.49 1.52 1.54 1.56 1.58 1.59]
here, if the matrix order n is 3, RI is 0.52.
And if CR <0.1 is obtained by calculation, the consistency requirement is met, and the weight value calculated in the prior art can be used.
Based on the above method, the weight can be calculated:
W＝[0.0769 0.6923 0.2308]T
calculated maximum eigenvalue lambdamaxCR is 3 and 0. And each single-factor index weight distribution is available to show the data quality.
Similarly, the three-phase table suspect weight model obtains the weight as:
W＝[0.0769 0.2308 0.6923]T
the following is an example of the method of the present invention, assuming that the target area has three outgoing lines, each of which contains three ABC phases, for a total of 200 consumer smart meters. Table 1 shows statistical records of decapping events of the smart meters (some of the repeated data are omitted in table 1); as shown in fig. 2 to 3, the current distribution diagrams of the zero line and the live line of the single-phase electric meter are respectively shown; fig. 4 to 6 show current distribution diagrams of the a-phase, the B-phase and the C-phase of the three-phase electric meter, respectively.
TABLE 1 cover opening recording table for each intelligent ammeter
The method comprises the steps of judging electricity stealing in a low-voltage transformer area by adopting MATLAB software, processing electricity stealing suspicion parameters of each user and a corresponding user intelligent electric meter by an identification method based on the embodiment, wherein the suspicion parameters of electricity stealing at the current measuring point by opening a cover are determined to be 0.4 by an analytic hierarchy process, the suspicion parameters of the single-phase electric meter abnormality of the suspicion user are 0.6, the suspicion parameters of the voltage phase loss abnormality of the current measuring point of the three-phase electric meter are 0.3, the suspicion parameters of the three-phase electricity using abnormality of the current measuring point of the three-phase electric meter are 0.3, and the preset electricity stealing suspicion reference threshold value set for the single-phase electric meter electricity stealing suspicion weight model and the three-phase electric meter electricity stealing suspicion weight model is 60. Through the weight scoring mode, suspected users with possible electricity stealing in the transformer area can be obtained, the suspected users with electricity stealing can be investigated on the spot, the electricity stealing behavior of the modified electricity meters can be found in the No. 6 single-phase electricity meter and the No. 2 three-phase electricity meter, the accuracy is high, and the effectiveness and the feasibility of the method provided by the invention are verified.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents of all embodiments and should be included in the scope of the present invention.
Claims (3)
1. A low-voltage user electricity stealing identification method based on edge-to-edge fusion is characterized by comprising the following steps:
step 1: acquiring multivariate power consumption data of user end-side equipment based on archive information of a target station area, wherein the multivariate power consumption data comprises uncapping event records of a single-phase meter and a three-phase meter, zero line current and live line current of the single-phase meter, a voltage load curve of the single-phase meter, and a voltage load curve and a power load curve of the three-phase meter;
step 2: aiming at a single-phase user who installs a single-phase meter, processing and obtaining suspected quantitative parameters of electricity stealing of the single-phase meter based on the record of the uncapping event of the single-phase meter, the zero line current, the live line current and the voltage load curve data;
and step 3: aiming at a three-phase user installing a three-phase meter, processing and obtaining suspected quantitative parameters of electricity stealing of the three-phase meter based on the record of the uncapping event of the three-phase meter and the data of the voltage load curve and the power load curve of the three-phase meter;
and 4, step 4: establishing an electricity stealing suspicion weight model of the single-phase meter and the three-phase meter, determining weight parameters in the electricity stealing suspicion weight model through an analytic hierarchy process, calculating electricity stealing suspicion parameters of a single-phase user and a three-phase user, and judging to obtain an electricity stealing identification result;
the step 1 specifically comprises the following steps:
acquiring zero line current, live line current and voltage load curve data of a single-phase meter by adopting end-side equipment, and locally judging zero line current deviation abnormality and voltage abnormality; collecting voltage and active power load curves of the three-phase meter, and locally judging the abnormity of the voltage and the active power; side equipment is adopted to collect uncapping event records of a single-phase meter and a three-phase meter, time data corresponding to zero-live line current deviation abnormity and voltage abnormity of the single-phase meter and time data corresponding to voltage and active power abnormity of the three-phase meter;
the step 2 specifically comprises the following steps:
the suspected quantitative parameters of electricity stealing of the meter cover of the single-phase meter are determined according to the following formula:
in the formula, Sd1Opening a meter cover of the single-phase meter to obtain suspected parameters of electricity stealing; m is the uncapping event frequency of the single-phase meter; m0A frequency threshold value of single-phase meter uncapping event abnormity is set;
the suspected quantitative parameters of electricity stealing of zero live wire current deviation of the single-phase meter are determined according to the following formula:
in the formula, Sd2Quantizing parameters for suspicion of electricity stealing due to zero-live line current deviation of a single-phase meter;
live line current and zero line current of the single-phase meter at the time t are respectively; epsilonIA threshold value for judging the current deviation abnormity of the zero line and live line of the single-phase meter at the current moment; omegaTThe time set meeting the abnormal zero line and live line current deviation of the single-phase meter is set;
the current of the live wire and the current of the zero line at the h moment of the single-phase meter are respectively; i is0Judging the available threshold value of the zero line current and the live line current of the single-phase meter at the current moment; omegaHA time set available for the zero live line current of the single-phase meter; num (omega)T)、num(ΩH) Respectively represent the set omegaT、ΩHThe number of elements of (a);
the suspected quantitative parameters of the abnormal voltage electricity stealing of the single-phase meter are determined according to the following formula:
in the formula, Sd3Quantifying parameters for the suspicion of electricity stealing due to abnormal voltage of the single-phase meter;
voltage data of the single-phase meter at the time t; u shape0A threshold value for judging the voltage abnormality of the single-phase meter; t is a unit of1The total time period number of voltage load curve data of the single-phase meter is obtained;
the step 3 specifically comprises the following steps:
the suspected quantitative parameters of electricity stealing by opening the meter cover of the three-phase meter are determined according to the following formula:
in the formula, Ss1The suspected quantitative parameters of electricity stealing are obtained by opening a meter cover of the three-phase meter; n is the opening event frequency of the three-phase meter; n is a radical of0A frequency threshold value of the three-phase meter uncovering event abnormity is set;
the suspected quantitative parameters of the abnormal voltage electricity stealing of the three-phase meter are determined according to the following formula:
in the formula, Ss2Quantifying parameters for suspicion of electricity stealing due to abnormal voltage of the three-phase meter;
for the time t of a three-phase watch
Phase voltage data; u shape0' is a threshold value for judging the voltage abnormality of the three-phase meter; t is a unit of2For three-phase electricity meteringThe total time period number of the pressure load curve data; [ A, B, C ]]Is an ABC three-phase set;
processing and determining the active power abnormal electricity stealing suspicion quantization parameter of the three-phase meter according to the following formula:
in the formula, Ss3Quantifying parameters for active power abnormal electricity stealing suspicion of the three-phase meter;
for the time t of a three-phase watch
Phase active power data; p0A threshold value for judging the active power abnormity of the three-phase meter; t is a unit of2' is the total time segment number of the active power load curve data of the three-phase meter.
2. The low-voltage user electricity stealing identification method based on the edge-to-edge fusion as claimed in claim 1, characterized in that: in the step 4, establishing a suspicion of electricity stealing weight model of the single-phase meter and the three-phase meter to obtain suspicion of electricity stealing parameters of the single-phase user and the three-phase user:
Sd＝wd1Sd1+wd2Sd2+wd3Sd3
Ss＝ws1Ss1+ws2Ss2+ws3Ss3
in the formula, Sd、SsSuspicion of electricity stealing, w, for single and three phase users respectivelyd1、wd2、wd3Respectively opening a meter cover for a single-phase user, weighing parameters of abnormal zero-live line deviation and suspicion of electricity stealing due to abnormal voltage, ws1、ws2、ws3Respectively opening a meter cover for a three-phase user, and weighting parameters of voltage abnormity and active power abnormity electricity stealing suspicion;
and then comparing the electricity stealing suspicion parameters of the single-phase user and the three-phase user with a preset electricity stealing suspicion reference threshold: if the electricity stealing suspicion parameter is larger than the electricity stealing suspicion reference threshold, the existence of electricity stealing is determined; otherwise there is no electricity stealing.
3. The low-voltage user electricity stealing identification method based on edge-to-edge fusion as claimed in claim 2, characterized in that: and carrying out iterative optimization processing on each weight parameter in the electricity stealing suspicion weight model by using an analytic hierarchy process to obtain the optimal each weight parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111210041.XA CN113919853B (en) | 2021-10-18 | 2021-10-18 | Low-voltage user electricity stealing identification method based on edge-to-edge fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111210041.XA CN113919853B (en) | 2021-10-18 | 2021-10-18 | Low-voltage user electricity stealing identification method based on edge-to-edge fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113919853A CN113919853A (en) | 2022-01-11 |
| CN113919853B true CN113919853B (en) | 2022-07-15 |
Family
ID=79241289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111210041.XA Active CN113919853B (en) | 2021-10-18 | 2021-10-18 | Low-voltage user electricity stealing identification method based on edge-to-edge fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113919853B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2910903A1 (en) * | 2014-02-20 | 2015-08-26 | Siemens Aktiengesellschaft | Method for detecting electricity theft in a low voltage network |
| CN106373025A (en) * | 2016-08-22 | 2017-02-01 | 重庆邮电大学 | Outlier detection-based real-time anti-power-theft monitoring method for power utilization information acquisition system |
| CN107221927A (en) * | 2017-05-23 | 2017-09-29 | 国电南瑞三能电力仪表(南京)有限公司 | A kind of analysis method of opposing electricity-stealing based on quantitative appraisement model stealing suspicion parser |
| CN109101594A (en) * | 2018-07-27 | 2018-12-28 | 国家电网有限公司 | A kind of method, apparatus and terminal detecting stealing suspicion user |
| CN110082579A (en) * | 2019-05-21 | 2019-08-02 | 国网湖南省电力有限公司 | A kind of area's Intelligent power-stealing prevention monitoring method, system, equipment and medium |
| CN110417125A (en) * | 2019-08-01 | 2019-11-05 | 河南合众伟奇云智科技有限公司 | A kind of edge calculations based on ubiquitous electric power Internet of Things are opposed electricity-stealing method and device |
| CN110824270A (en) * | 2019-10-09 | 2020-02-21 | 中国电力科学研究院有限公司 | Electricity stealing user identification method and device combining transformer area line loss and abnormal events |
| CN113452145A (en) * | 2021-08-30 | 2021-09-28 | 广东电网有限责任公司中山供电局 | Method and system for monitoring power utilization condition of low-voltage transformer area user |
-
2021
- 2021-10-18 CN CN202111210041.XA patent/CN113919853B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2910903A1 (en) * | 2014-02-20 | 2015-08-26 | Siemens Aktiengesellschaft | Method for detecting electricity theft in a low voltage network |
| CN106373025A (en) * | 2016-08-22 | 2017-02-01 | 重庆邮电大学 | Outlier detection-based real-time anti-power-theft monitoring method for power utilization information acquisition system |
| CN107221927A (en) * | 2017-05-23 | 2017-09-29 | 国电南瑞三能电力仪表(南京)有限公司 | A kind of analysis method of opposing electricity-stealing based on quantitative appraisement model stealing suspicion parser |
| CN109101594A (en) * | 2018-07-27 | 2018-12-28 | 国家电网有限公司 | A kind of method, apparatus and terminal detecting stealing suspicion user |
| CN110082579A (en) * | 2019-05-21 | 2019-08-02 | 国网湖南省电力有限公司 | A kind of area's Intelligent power-stealing prevention monitoring method, system, equipment and medium |
| CN110417125A (en) * | 2019-08-01 | 2019-11-05 | 河南合众伟奇云智科技有限公司 | A kind of edge calculations based on ubiquitous electric power Internet of Things are opposed electricity-stealing method and device |
| CN110824270A (en) * | 2019-10-09 | 2020-02-21 | 中国电力科学研究院有限公司 | Electricity stealing user identification method and device combining transformer area line loss and abnormal events |
| CN113452145A (en) * | 2021-08-30 | 2021-09-28 | 广东电网有限责任公司中山供电局 | Method and system for monitoring power utilization condition of low-voltage transformer area user |
Non-Patent Citations (5)
| Title |
|---|
| Electricity Theft Detection Based on Stacked Autoencoder and the Undersampling and Resampling Based Random Forest Algorithm;Guoying Lin ey al.;《IEEE Access》;20210906;第9卷;第124044-124058页 * |
| SAI: A Suspicion Assessment-Based Inspection Algorithm to Detect Malicious Users in Smart Grid;Xiaofang Xia et al.;《IEEE Transactions on Information Forensics and Security》;20190605;第15卷;第361-371页 * |
| 基于用电信息采集大数据的防窃电方法研究;窦健 等;《电测与仪表》;20181130;第55卷(第21期);第43-49页 * |
| 基于配电物联网的反窃电预警***研究及应用;许小卉 等;《计算技术与自动化》;20200630;第39卷(第02期);第104-108页 * |
| 智能防窃电***方案设计及应用;刘晓巍;《中国优秀博硕士学位论文全文数据库(硕士) 工程科技辑(月刊)》;20200515(第05期);第1-80页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113919853A (en) | 2022-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111781463A (en) | Auxiliary diagnosis method for abnormal line loss of transformer area | |
| CN109633321B (en) | Transformer area household variable relation distinguishing system and method and transformer area high loss monitoring method | |
| CN107680368A (en) | A kind of metering device on-line monitoring and intelligent diagnosing method based on gathered data | |
| CN106199305A (en) | Underground coal mine electric power system dry-type transformer insulation health state evaluation method | |
| CN115018139A (en) | Current transformer error state online identification method and system based on interphase characteristics | |
| CN107886171B (en) | PMU data-based breaker state online diagnosis method and system | |
| CN110749784B (en) | Line electricity stealing detection method based on electric power data wavelet analysis | |
| CN115115282B (en) | Data analysis method for high-voltage transformer area power system | |
| CN115270974B (en) | Intelligent electricity larceny detection system based on big data analysis | |
| CN103617447A (en) | Evaluation system and method for intelligent substation | |
| CN110750760B (en) | Abnormal theoretical line loss detection method based on situation awareness and control diagram | |
| CN111209535B (en) | Power equipment successive fault risk identification method and system | |
| CN115759708A (en) | Line loss analysis method and system considering power space-time distribution characteristics | |
| CN116823226A (en) | Electric power district fault monitoring system based on big data | |
| CN116522746A (en) | Power distribution hosting method for high-energy-consumption enterprises | |
| CN109142830A (en) | Stealing detection method based on power information acquisition system big data | |
| CN113376553B (en) | Intelligent screening method and system for three-phase four-wire metering string current loop wiring | |
| CN111999695B (en) | State evaluation and abnormity diagnosis method for metering device of transformer substation | |
| CN113919853B (en) | Low-voltage user electricity stealing identification method based on edge-to-edge fusion | |
| Zhang et al. | Research on comprehensive diagnosis model of anti-stealing electricity based on big data technology | |
| CN105652157B (en) | Method for analyzing health state of power distribution network based on traveling wave electric quantity | |
| CN112036712A (en) | Power distribution terminal state evaluation index weight distribution method | |
| CN102882279A (en) | Real-time measurement and online analysis method for load of power grid | |
| CN115328965A (en) | Electricity consumption abnormity analysis method based on MK mutation detection | |
| CN115936482A (en) | Low-voltage distribution network power quality analysis method based on power consumption data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |