Method and system for detecting and positioning electricity stealing user, medium and terminal
Through the collection, cleaning and fluctuation coefficient calculation of power data, combined with outlier and clustering algorithms to calculate the suspicion of power theft, the problem of insufficient discovery of power theft characteristics in the existing technology is solved, and efficient positioning of power theft users is achieved. Diagnosis improves work efficiency.
Patent Information
- Application Number
- CN202411199609.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-12
AI Technical Summary
The existing anti-power stolen methods cannot effectively utilize massive historical data on electricity consumption, resulting in insufficient discovery of power stolen characteristics and poor diagnosis and positioning effects, which increases the on-site inspection workload and waste of resources.
Through the calculation of the suspicion of power theft by collecting power quantity data, data cleaning, fluctuation coefficient calculation and outlier and clustering algorithms, the suspected data of power theft is determined and the user of power theft is finally located.
It improves the diagnosis and positioning effect of power theft, reduces on-site inspection work, reduces resource waste, and improves work efficiency.
Smart Images

Figure CN118940190A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of user electricity consumption monitoring, and in particular to a detection and positioning method, system, medium and terminal for electricity theft users. Background Art
[0002] The existing device-based anti-electricity theft methods can improve the accuracy of metering devices, but cannot effectively utilize massive electricity consumption history data and discover the characteristics of electricity theft. Therefore, it is urgent to develop an electricity theft detection and positioning solution based on data mining technology, so as to further improve the diagnosis and positioning effects of electricity theft, reduce the workload of front-line employees in on-site inspections, reduce resource waste and improve work efficiency. Summary of the invention
[0003] In view of the technical problems pointed out in the background technology, the purpose of the present invention is to provide a method, system, medium and terminal for detecting and locating electricity theft users.
[0004] To achieve the purpose of the present invention, the technical solution provided by the present invention is specifically as follows:
[0005] First aspect
[0006] The present invention provides a method for detecting and locating electricity theft users, comprising the following steps:
[0007] Step 1: Collect electricity consumption data of power users;
[0008] Step 2: Cleaning the power data according to the cleaning strategy;
[0009] Step 3: Calculate the fluctuation coefficient based on the cleaned electricity data, calculate the electricity theft suspicion degree by using the outlier algorithm and clustering algorithm in combination with the fluctuation coefficient, and determine the electricity theft suspicion data according to the electricity theft suspicion degree;
[0010] Step 4: Locate the electricity theft user based on the suspected electricity theft data.
[0011] Second aspect
[0012] Corresponding to the above method, the present invention also provides a detection and positioning system for electricity theft users, including an electricity data acquisition unit, a data cleaning unit, an electricity theft suspicion data determination unit, and an electricity theft user positioning unit;
[0013] The power data collection unit is used to collect power data of power users;
[0014] The data cleaning unit is used to clean the power data according to a cleaning strategy;
[0015] The electricity theft suspicion data determination unit is used to calculate the fluctuation coefficient based on the cleaned electricity data.
[0016] In combination with the fluctuation coefficient, outlier algorithm and clustering algorithm are used to calculate the suspicion of electricity theft, and the suspected electricity theft data is determined according to the suspicion of electricity theft;
[0017] The electricity theft user locating unit is used to locate the electricity theft user according to the electricity theft suspicion data.
[0018] The third aspect
[0019] The present invention also provides a storage medium, in which at least one instruction, at least one program, code set or instruction set is stored. The at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the method for detecting and locating electricity theft users.
[0020] The fourth aspect
[0021] The present invention also provides an electronic terminal, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the method for detecting and locating electricity theft users.
[0022] Compared with the prior art, the present invention has the following beneficial effects:
[0023] The solution provided by the present invention collects and cleans the electricity data, then calculates the fluctuation coefficient based on the cleaned electricity data, combines the fluctuation coefficient, uses the outlier algorithm and the clustering algorithm to calculate the suspicion of electricity theft, and determines the suspected electricity theft data according to the suspected electricity theft degree; finally, locates the electricity theft user according to the suspected electricity theft data. The solution improves the diagnosis and positioning effects of electricity theft, reduces the workload of on-site inspections by front-line employees, reduces resource waste and improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 A schematic diagram of the method flow provided in an embodiment of the present application. DETAILED DESCRIPTION
[0025] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0026] Example 1
[0027] like Figure 1As shown, this embodiment provides a method for detecting and locating electricity theft users, including the following steps:
[0028] Step 1: Collect electricity consumption data of power users;
[0029] It should be noted that the electricity consumption data refers to the electricity consumption data for three months in the same quarter.
[0030] Step 2: Cleaning the power data according to the cleaning strategy;
[0031] Among them, in step 2, the cleaning strategy includes cleaning the fields that are missing any data; cleaning the meter reading data collected by the terminal meter; cleaning the data with unclear labels; and cleaning a small number of extreme data and negative data in the sample.
[0032] Step 3: Calculate the fluctuation coefficient based on the cleaned electricity data, calculate the electricity theft suspicion degree by using the outlier algorithm and clustering algorithm in combination with the fluctuation coefficient, and determine the electricity theft suspicion data according to the electricity theft suspicion degree;
[0033] It should be noted that the method for calculating the volatility coefficient is as follows:
[0034]
[0035] In the formula, CV is the coefficient of variation, d i represents the i-th sample point, Represents the sample mean, and N represents the number of sample points. The larger the CV, the greater the degree to which the sample deviates from the "center of mass".
[0036] It should be noted that the suspicion of electricity theft is a quantitative description of the user's suspicion of electricity theft based on the algorithm's abnormal data identification, and consists of two factor coefficients: the suspicion coefficient of electricity theft and the warning time coefficient defined by the algorithm itself.
[0037] For the outlier algorithm, p is the algorithm parameter, f 1 It is the electricity theft warning time coefficient of the outlier algorithm.
[0038]
[0039] In the formula, x is the number of warning days. As x increases, the abnormal power consumption of the user continues for a longer period of time, and therefore the possibility of power theft is greater.
[0040] Suspicion of electricity theft S under outlier algorithm d1 for:
[0041] S d1 =p×f 1
[0042] For the clustering algorithm, j is the ratio coefficient of the suspected class to the total number of samples, and f2 is the electricity theft warning coefficient of the clustering algorithm.
[0043]
[0044] Suspicion degree S of electricity theft based on clustering algorithm d2 for:
[0045] S d2 =j×f 2 .
[0046] It should be noted that more electricity consumption data of users are collected during the time period when there is suspicion of electricity theft, and the obtained electricity theft suspicion level S is adjusted according to the analysis status of electricity theft behavior. d (including S d1 and / or S d2 ), is the first suspected degree of electricity theft Q 0 ;
[0047]
[0048] In the formula, m 1 、m 2 is the adjustment coefficient of the suspected degree of electricity theft, which is set according to actual needs; according to the analysis status of the electricity theft behavior, if it matches, u=1, otherwise u=0;
[0049] If the corresponding metering abnormality such as reverse running of the energy meter, stoppage of the energy meter, voltage phase failure, current loss, power differential abnormality, etc. that leads to electricity theft occurs, adjust the suspicion level to the second electricity theft suspicion level Q according to the metering status of the energy meter (v = 0 means no metering abnormality occurs, v = 1, 2, 3, 4, 5 means one of the above metering abnormalities occurs) 1 (n v is the adjustment coefficient of the suspected degree of electricity theft, which is set according to actual needs).
[0050]
[0051] Analyze whether the PQUI corresponding to the power data is normal or the deviation is within a reasonable range, and adjust the power theft suspicion level to the third power theft suspicion level Q according to the normal power data (normal if w=1, otherwise w=0). 2 (l 1 , l 2 is the power theft suspicion coefficient, set according to actual needs)
[0052]
[0053] Determine whether it is an intermittent power usage sample. If it is an intermittent power usage sample, r = 0, otherwise r = 1, and adjust the suspected power theft degree to Q 3 (s 1 、s2 It is the adjustment coefficient of the suspected degree of electricity theft, which should be set according to actual needs)
[0054]
[0055] The third electricity theft suspicion degree Q 3 (The following content is represented by S d ) to classify the data and determine the suspected electricity theft data as needed.
[0056] Step 4: Locate the electricity theft user based on the suspected electricity theft data.
[0057] It should be noted that the location of the electricity theft user is output based on the electricity theft suspicion data, the electricity theft knowledge base and the historical data.
[0058] Example 2
[0059] This embodiment provides a detection and positioning system for electricity theft users, including an electricity data collection unit, a data cleaning unit, an electricity theft suspicion data determination unit, and an electricity theft user positioning unit;
[0060] The power data collection unit is used to collect power data of power users;
[0061] The data cleaning unit is used to clean the power data according to a cleaning strategy;
[0062] The electricity theft suspicion data determination unit is used to calculate the fluctuation coefficient based on the cleaned electricity data, calculate the electricity theft suspicion degree by using the outlier algorithm and the clustering algorithm in combination with the fluctuation coefficient, and determine the electricity theft suspicion data according to the electricity theft suspicion degree;
[0063] The electricity theft user locating unit is used to locate the electricity theft user according to the electricity theft suspicion data.
[0064] The electricity consumption data refers to the electricity consumption data for three months in the same quarter.
[0065] The cleaning strategy includes cleaning fields that are missing any data; cleaning meter reading data collected by terminal meters; cleaning unclearly labeled data; and cleaning a small number of extreme data and negative data in samples.
[0066] The method for calculating the fluctuation coefficient is as follows:
[0067]
[0068] In the formula, CV is the coefficient of variation, d i represents the i-th sample point, represents the sample mean, and N represents the number of sample points.
[0069] Example 3
[0070] In addition, the present invention provides a storage medium, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the method for detecting and locating electricity theft users.
[0071] Example 4
[0072] In addition, the present invention provides an electronic terminal, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the method for detecting and locating electricity theft users.
[0073] The optional implementation modes of the embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above implementation modes. Within the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical scheme of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.
Claims
1. A method for detecting and locating electricity theft users, characterized in that: The steps include: Step 1: Collect electricity consumption data of power users; Step 2: Cleaning the power data according to the cleaning strategy; Step 3: Calculate the fluctuation coefficient based on the cleaned electricity data, calculate the electricity theft suspicion degree by using the outlier algorithm and clustering algorithm in combination with the fluctuation coefficient, and determine the electricity theft suspicion data according to the electricity theft suspicion degree; Step 4: Locate the electricity theft user based on the suspected electricity theft data.
2. A method for detecting and locating electricity theft users according to claim 1, characterized in that: In step 1, the electricity data is the electricity data for three months in the same quarter.
3. A method for detecting and locating electricity theft users according to claim 1, characterized in that: In step 2, the cleaning strategy includes cleaning fields that are missing any data; cleaning meter reading data collected by terminal meters; cleaning unclearly labeled data; and cleaning a small number of extreme data and negative data in the sample.
4. A method for detecting and locating electricity theft users according to claim 1, characterized in that: In step 3, the volatility coefficient is calculated as follows: In the formula, CV is the coefficient of variation, d i represents the i-th sample point, represents the sample mean, and N represents the number of sample points.
5. A detection and positioning system for electricity theft users, characterized in that: It includes an electricity data collection unit, a data cleaning unit, a suspected electricity theft data determination unit, and an electricity theft user positioning unit; The power data collection unit is used to collect power data of power users; The data cleaning unit is used to clean the power data according to a cleaning strategy; The electricity theft suspicion data determination unit is used to calculate the fluctuation coefficient based on the cleaned electricity data, calculate the electricity theft suspicion degree by using the outlier algorithm and the clustering algorithm in combination with the fluctuation coefficient, and determine the electricity theft suspicion data according to the electricity theft suspicion degree; The electricity theft user locating unit is used to locate the electricity theft user according to the electricity theft suspicion data.
6. A detection and positioning system for electricity theft users according to claim 5, characterized in that: The electricity data are therefore electricity data for three months in the same quarter.
7. A detection and positioning system for electricity theft users according to claim 5, characterized in that: The cleaning strategy includes cleaning fields that are missing any data; cleaning meter reading data collected by terminal electric meters; cleaning data with unclear labels; and cleaning a small number of extreme data and negative data in samples.
8. A detection and positioning system for electricity theft users according to claim 5, characterized in that: The method for calculating the coefficient of fluctuation is as follows: In the formula, CV is the coefficient of variation, d i represents the i-th sample point, represents the sample mean, and N represents the number of sample points.
9. A storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the method for detecting and locating electricity theft users according to any one of claims 1 to 4.
10. An electronic terminal, characterized in that: The electronic terminal includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the method for detecting and locating electricity theft users according to any one of claims 1 to 4.
