A method and system for detecting electricity consumption behavior

Abstract

The present invention discloses a method and system for detecting electricity usage behavior, and relates to the technical field of electricity usage behavior detection. The method comprises obtaining electrical data measured by an electric meter; the electrical data comprises user electricity consumption, area line loss and public transformer load; according to the electrical data, extracting electrical characteristic parameters for characterizing abnormal electricity consumption; the electrical characteristic parameters comprise electricity consumption coefficient, user dispersion coefficient, correlation coefficient between line loss and electricity consumption and the maximum load utilization day of the month; according to the electrical characteristic parameters and the time electricity consumption curves of different time periods, generating corresponding electrical characteristic criteria; according to the electrical characteristic criteria, screening users with high suspicion of electricity theft. The present invention can completely and accurately extract electrical characteristics that can characterize abnormal performance of users in electricity theft, and finally output accurate judgment results of users' electricity theft behavior, providing a reference for the power supply company's electricity theft investigation work.

Description

Technical Field

[0001] The present invention relates to the technical field of power usage behavior detection, and in particular to a power usage behavior detection method and system. Background Art

[0002] With the improvement of economic level, the electricity consumption of users is also increasing. Some lawless elements deliberately make the meter reading less or not count by means of destroying the meter, illegal wiring, etc., so that the measured electricity is less than the actual electricity consumption, so as to achieve the purpose of paying less electricity bills, which has a negative impact on the interests of power supply companies and the stable operation of power grids. For a long time, my country has remained in the primary stage in the construction of anti-electricity theft system, mainly relying on manual investigation and backward prevention and control measures, resulting in the increasing rampant electricity thieves and the increasingly serious electricity theft. With the increase in electricity consumption of special transformers and low-voltage users, the problem of electricity theft is more serious than before. It is mainly manifested in the high-tech means of electricity theft, the concealment of the electricity theft process, and the large amount of electricity theft, which has caused serious economic losses to the country. In addition, the indirect losses caused by accidents caused by electricity theft are even greater.

[0003] In recent years, my country's power grid has been continuously researching anti-electricity theft methods, mainly focusing on mechanical backstop and electromagnetic, and focusing on the development of anti-theft electric energy meters. With multiple measures, anti-electricity theft technology is also constantly improving and improving, and power supply companies have also increased their efforts in anti-electricity theft technology research. Therefore, it is necessary to explore new methods and new scientific and technological means in many aspects to more vigorously curb electricity theft. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for detecting electricity consumption behavior based on electrical characteristic criteria, analyze user statistical data based on a large amount of electricity data, and locate metering and electricity consumption anomalies.

[0005] To achieve the above object, an embodiment of the present invention provides a method for detecting power consumption behavior, comprising:

[0006] The electrical data measured by the electric meter is obtained; the electrical data includes the user's power consumption, the line loss in the substation area and the public transformer load; based on the electrical data, the electrical characteristic parameters used to characterize the abnormality of power consumption are extracted; the electrical characteristic parameters include the power consumption coefficient, the user dispersion coefficient, the correlation coefficient between the line loss and the power consumption and the maximum load utilization day of the month; based on the electrical characteristic parameters and the time power consumption curves of different time periods, the corresponding electrical characteristic criterion is generated; based on the electrical characteristic criterion, the users with high suspicion of power theft are screened.

[0007] Preferably, screening highly suspected electricity theft users according to the electrical characteristic criterion includes:

[0008] The satisfaction of the electricity usage characteristics of the user with high suspicion of electricity theft is calculated to obtain the user's suspicion of electricity theft.

[0009] Preferably, generating corresponding electrical characteristic criteria according to the electrical characteristic parameters and the time power consumption curves in different time periods includes:

[0010] A first criterion is generated according to the user's summer or winter electricity consumption curve and its electrical characteristic parameters; the first criterion is:

[0011]

[0012] Among them, χ is the electricity consumption coefficient, n is the number of users, is the user dispersion coefficient difference, and r is the Pearson correlation coefficient.

[0013] Preferably, generating corresponding electrical characteristic criteria according to the electrical characteristic parameters and the time power consumption curves in different time periods includes:

[0014] The second criterion is generated based on the user's 20-40 days electricity consumption curve and electrical characteristic parameters; the second criterion is:

[0015] The line loss rate of the dedicated transformer increases at night (line loss rate L>20%), and r>0.6;

[0016] Where r is the Pearson correlation coefficient.

[0017] Preferably, generating corresponding electrical characteristic criteria according to the electrical characteristic parameters and the time power consumption curves in different time periods includes:

[0018] A third criterion is generated based on the user's 50-100-day electricity consumption curve and electrical characteristic parameters; the third criterion is:

[0019] χ<0.3 or the line loss rate increases on weekends (line loss rate L>20%), and r>0.6;

[0020] Among them, χ is the electricity consumption coefficient and r is the Pearson correlation coefficient.

[0021] Preferably, generating corresponding electrical characteristic criteria according to the electrical characteristic parameters and the time power consumption curves in different time periods includes:

[0022] A fourth criterion is generated based on the user's electricity consumption curve for more than 300 days and its electrical characteristic parameters; the fourth criterion is:

[0023] The line loss rate increases significantly in the middle of the month, and the correlation coefficient with a certain user is relatively high (line loss rate L>20%), and r>0.6), and d<15;

[0024] Where, d is the maximum load utilization day of the month, and r is the Pearson correlation coefficient.

[0025] Preferably, generating corresponding electrical characteristic criteria according to the electrical characteristic parameters and the time power consumption curves in different time periods includes:

[0026] A fifth criterion is generated based on the user's electricity consumption curve for more than 600 days and its electrical characteristic parameters; the fifth criterion is:

[0027] Line loss rate L>20%, and r>0.6, and

[0028] Where r is the Pearson correlation coefficient, is the user dispersion coefficient difference.

[0029] The embodiment of the present invention further provides a power consumption behavior detection system, including:

[0030] A data acquisition module is used to acquire electrical data measured by an electric meter; the electrical data includes user power consumption, area line loss and public transformer load;

[0031] A feature extraction module is used to extract electrical characteristic parameters for characterizing abnormal power consumption according to the electrical data; the electrical characteristic parameters include power consumption coefficient, user dispersion coefficient, correlation coefficient between line loss and power consumption, and maximum load utilization day of the month;

[0032] A criterion classification module, used to generate corresponding electrical characteristic criteria according to the electrical characteristic parameters and time power consumption curves of different time periods;

[0033] The suspect screening module is used to screen users who are highly suspected of stealing electricity according to the electrical characteristic criteria.

[0034] An embodiment of the present invention further provides a computer terminal device, comprising one or more processors and a memory. The memory is coupled to the processor and is used to store one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the power consumption behavior detection method as described in any of the above embodiments.

[0035] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for detecting power usage behavior as described in any of the above embodiments is implemented.

[0036] The electricity usage behavior detection method provided by the present invention first collects various types of electrical data of users measured by smart meters; then organizes the experience in the actual investigation process; then converts the experience into electrical characteristic criteria that can be calculated; finally compares the electricity usage curves of different users with the corresponding electrical characteristics, so as to determine whether the user has electricity theft behavior. The electrical characteristics that can characterize the abnormal performance of the user's electricity theft can be completely and accurately extracted, and finally an accurate judgment result of the user's electricity theft behavior is output, which can provide a reference for the power supply company's electricity theft investigation work. Compared with the prior art, the present invention has the following beneficial effects: the present invention proposes electrical characteristic parameters that characterize abnormal electricity usage, and establishes electrical characteristic criteria based on actual investigation experience, which not only ensures the practicality of the method, but also ensures the theoretical nature of the method. The present invention adopts a more accurate suspicion calculation method, takes into account the suspicion of the combined criterion, and makes the user's suspicion calculation more reasonable and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the implementation mode will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 is a flow chart of a method for detecting power consumption behavior provided by a certain embodiment of the present invention;

[0039] Figure 2 is a flow chart of a method for detecting power consumption behavior provided by another embodiment of the present invention;

[0040] Figure 3 is a structural schematic diagram of a power consumption behavior detection system provided by an embodiment of the present invention;

[0041] Figure 4 It is a schematic diagram of the structure of a computer terminal device provided by a certain embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0044] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0045] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0046] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0047] With the promotion and application of smart meters and advanced measurement systems, the available electrical data has also increased significantly. In this context, first collect various types of electrical data of users measured by smart meters; then organize the experience in the actual investigation process; then convert the experience into electrical characteristic criteria that can be calculated; finally compare the power consumption curves of different users with the corresponding electrical characteristics to determine whether the user has electricity theft. The present invention can completely and accurately extract electrical characteristics that can characterize the abnormal performance of users' electricity theft, and finally output accurate judgment results of users' electricity theft behavior, which can provide a reference for the power supply company's electricity theft investigation work.

[0048] See also Figure 1 , Figure 1 1 is a flow chart of a method for detecting power usage behavior provided by an embodiment of the present invention. The method for detecting power usage behavior of this embodiment includes the following steps:

[0049] S110, obtaining electrical data measured by an electric meter, including user power consumption, area line loss, and public transformer load.

[0050] S120, extracting electrical characteristic parameters for characterizing power consumption abnormality according to the electrical data. The electrical characteristic parameters include power consumption coefficient, user dispersion coefficient, correlation coefficient between line loss and power consumption, and maximum load utilization day of the month.

[0051] S130, generating corresponding electrical characteristic criteria according to the electrical characteristic parameters and the time power consumption curves of different time periods, wherein the criteria are mainly established based on the historical data of electricity theft investigation.

[0052] S140, screening users with high suspicion of electricity theft according to the electrical characteristic criterion. Furthermore, the satisfaction of the electricity usage characteristics of users with high suspicion of electricity theft can be calculated according to the electrical characteristic criterion and electrical characteristic parameters to obtain more detailed information on the suspicion of electricity theft of users.

[0053] In the above step S110, the electrical data measured by the electric meter is obtained. The electrical data includes the user's power consumption, the line loss of the substation area, and the public transformer load. It is necessary to determine the electrical data, including key data types such as the user's power consumption, the line loss of the substation area, and the public transformer load. The collection integrity of the actual power consumption data should be high to ensure the accuracy of subsequent calculation and detection.

[0054] In one embodiment, the formula calculation method of each electrical characteristic parameter includes:

[0055] The electrical parameters used to characterize the abnormality of the user's power consumption characteristics are calculated using the collected user power consumption data, substation line loss rate and other data, as well as user account number, substation number and other label information. The number of users is n, the length of data collection is t, S is the transformer capacity, E is the user's daily power consumption, and L is the line loss rate.

[0056] The calculation formula of the power consumption coefficient (the ratio of the total power consumption of the user during this period to the capacity of the public or special transformer) χ is:

[0057]

[0058] User dispersion coefficient difference The calculation formula is:

[0059]

[0060]

[0061] The calculation formula of the Pearson correlation coefficient r between the line loss rate of the substation area and the user's power consumption is:

[0062] r j =R(L,E j );

[0063] The calculation formula for the monthly maximum load utilization day d is:

[0064]

[0065] See also Figure 2 , Figure 2 It is a flow chart of a method for detecting electricity consumption provided by another embodiment of the present invention. The method for detecting electricity consumption provided by this embodiment needs to sort out the electrical characteristic criteria represented by electrical characteristic parameters based on actual experience, and generate five electrical characteristic criteria based on daily, weekly, monthly, seasonal and annual electricity consumption curves according to the time length required for judgment.

[0066] First, according to the electrical characteristic parameters and the time power consumption curves of different time periods, the corresponding electrical characteristic criteria are generated, including:

[0067] The first criterion is generated based on the user's summer or winter electricity consumption curve and its electrical characteristic parameters. The first criterion: "low electricity consumption in hot or cold weather"

[0068] 1) Data scale: electricity consumption data in summer and July / winter for users in the same industry or in the same area;

[0069] 2) Troubleshooting method: Compare with other users in the same industry or in the same area. If the monthly average electricity consumption is significantly lower than that of other users, there is suspicion of electricity theft.

[0070] 3) In summary, the first criterion is:

[0071]

[0072] Among them, χ is the electricity consumption coefficient, n is the number of users, is the user dispersion coefficient difference, and r is the Pearson correlation coefficient.

[0073] Secondly, according to the electrical characteristic parameters and the time power consumption curves of different time periods, the corresponding electrical characteristic criteria are generated, including:

[0074] The second criterion is generated based on the user's 20-40 day electricity consumption curve and its electrical characteristic parameters. The second criterion: "There is a peak in the afternoon in the daily curve, but no peak in the evening"

[0075] 1) Data scale: Daily power consumption curve of users for one month

[0076] 2) Troubleshooting method: Focus on comparing the 11:00-13:00 and 19:00-24:00 sections in the daily electricity consumption curve, and continue to observe for one month. If the electricity consumption at noon is much greater than the electricity consumption at night for at least 24 days in a month or for a period of one week, there is a suspicion of electricity theft;

[0077] 3) In summary, the second criterion is:

[0078] The line loss rate of the dedicated transformer increases at night (L>20%), and r>0.6; where L represents the line loss rate.

[0079] Where r is the Pearson correlation coefficient.

[0080] Thirdly, according to the electrical characteristic parameters and the time power consumption curves in different time periods, the corresponding electrical characteristic criteria are generated, including:

[0081] The third criterion is generated based on the user's 50-100-day electricity consumption curve and its electrical characteristic parameters. The third criterion: "Low electricity consumption on weekends or during the week within the weekly curve"

[0082] 1) Data scale: Collect 2-3 months of user daily power consumption curves

[0083] 2) Investigation method: For low-voltage users, focus on observing the electricity consumption data on the weekends of each week, and continue the observation for 2-3 months. If the electricity consumption remains low on weekends every week, there is suspicion of electricity theft; conversely, for special transformer users with weekday characteristics, focus on observing their electricity consumption data from Monday to Friday. If the average electricity consumption is basically the same as that on the weekends, there is suspicion of electricity theft.

[0084] 3) In summary, the third criterion is:

[0085] χ<0.3 or the line loss rate L increases on weekends (L>20%), and r>0.6;

[0086] Among them, χ is the electricity consumption coefficient and r is the Pearson correlation coefficient.

[0087] Fourthly, according to the electrical characteristic parameters and the time power consumption curves in different time periods, the corresponding electrical characteristic criteria are generated, including:

[0088] The fourth criterion is generated based on the user's electricity consumption curve for more than 300 days and its electrical characteristic parameters. The fourth criterion is: "Long-term zero electricity during the non-meter reading period in the monthly curve"

[0089] 1) Data scale: Collecting daily power consumption curves of users for a whole year

[0090] 2) Troubleshooting method: Observe the difference in electricity consumption data between the middle and the beginning and end of each month. If there are more than 8 months in a year, the average value in the middle of the month and the electricity consumption on the 1st of the month or the 1st of the next month will be very different.

[0091] 3) In summary, the fourth criterion is:

[0092] The line loss rate increases significantly in the middle of the month, and the correlation coefficient with a certain user is relatively high ((L>20%), and r>0.6), and d<15;

[0093] Where, d is the maximum load utilization day of the month, and r is the Pearson correlation coefficient.

[0094] In the fifth aspect, according to the electrical characteristic parameters and the time power consumption curves in different time periods, the corresponding electrical characteristic criteria are generated, including:

[0095] The fifth criterion is generated based on the user's electricity consumption curve for more than 600 days and its electrical characteristic parameters. The fifth criterion is: "Annual electricity consumption curve is abnormal compared with historical data for the same period"

[0096] 1) Data scale: Collect 2-3 years of user annual electricity consumption curve

[0097] 2) Troubleshooting method: Take daily electricity consumption as the unit (average value for special transformers), calculate the monthly electricity consumption correlation coefficients for two years, and take the smallest ones among the 12 correlation coefficients as the suspected months of electricity theft. If the electricity consumption correlation coefficients of other users in these months are also very low, it may be caused by other factors; but if only a few users have very low electricity consumption, the line loss rate is very large in these suspected months, and the correlation coefficients with these users are relatively high, then there may be electricity theft.

[0098] 3) In summary, the fifth criterion is:

[0099] ((L>20%), and r>0.6), and

[0100] Where r is the Pearson correlation coefficient, is the user dispersion coefficient difference.

[0101] In a certain embodiment, step S140 needs to set the corresponding electricity theft suspicion for each electrical characteristic criterion, take into account the situation of combined electricity theft, for users who meet multiple criteria, calculate their combined criterion suspicion, and output the final user suspicion, thereby providing a reference for the grid company's screening order.

[0102] Combined with the first aspect above, the first criterion is: "low power consumption in hot or cold weather". The electrical characteristic criteria are set to case_a, case_b, and case_c in sequence; considering that the original criterion is not sufficient to describe the severity of the user's power theft, it is modified on the basis of the original criterion to:

[0103]

[0104]

[0105] case_c1:r>0.8

[0106] According to expert experience, the suspicion of each case is set as follows: b = (case_a: 0.6, case_b: 0.6, case_c: 0.7, case_a1: 0.8, case_b1: 0.8, case_c1: 0.9);

[0107] Considering that a user may satisfy different cases at the same time, the suspicion calculation method for the combined case is:

[0108]

[0109] Combined with the second aspect above, the second criterion is: "There is a noon peak in the daily curve, but no evening peak." This criterion has only one case, and its suspicion is set to b_=0.7; on the original basis, if (L>25%) is satisfied and r>0.8, the suspicion is b_=0.9.

[0110] Combined with the third aspect above, the third criterion is: "Low power on weekends or low power on weekdays within the weekly curve". This criterion has two cases, and the suspicions are b = (case_a: 0.6, case_b: 0.8); on the original basis, if χ < 0.15 or (L> 25%), and r> 0.8, the suspicions are b = (case_a1: 0.8, case_b1: 0.9).

[0111] The calculation method of suspicion of combined case is as follows:

[0112] case_(i,j):b_=max(b i ,b j )

[0113] i,j∈(case_a&b,case_a&b1,case_a1&b,case_a1&b1)

[0114] Combined with the fourth aspect above, the fourth criterion is: "Long-term zero electricity during the non-meter reading period in the monthly curve". This criterion has only one case, and its suspicion is set to b_=0.8; on the original basis, if ((L>20%), and r>0.8) and d<12 are satisfied, then the suspicion is b_=0.9.

[0115] Combined with the fifth aspect above, the fifth criterion is: "the annual electricity consumption curve is abnormal compared with the historical data of the same period". This criterion has only one case, and its suspicion is set to b_=0.8; on the original basis, if ((L>20%), and r>0.8) and Then the suspicion is b_=0.9.

[0116] Suspicion calculation method for combined criteria

[0117] According to the above method, the suspicion of electricity theft corresponding to the five electrical feature criteria is calculated respectively. If the user meets different feature criteria at the same time, the suspicion calculation method of the combined criteria is:

[0118] b_=min(0.99,max(b i )+0.1),i=(1,2,3,4,5).

[0119] See also Figure 3 , Figure 31 is a schematic diagram of the structure of a power consumption behavior detection system provided by an embodiment of the present invention. The same parts as those in the above embodiments are not repeated here. The power consumption behavior detection system of this embodiment includes:

[0120] The data acquisition module 210 is used to acquire the electrical data measured by the electric meter, including the user's electricity consumption, the line loss in the substation area and the load of the public transformer.

[0121] The feature extraction module 220 is used to extract electrical feature parameters for characterizing power consumption abnormality according to the electrical data. The electrical feature parameters include power consumption coefficient, user dispersion coefficient, correlation coefficient between line loss and power consumption, and the maximum load utilization day of the month.

[0122] The criterion classification module 230 is used to generate corresponding electrical characteristic criteria according to the electrical characteristic parameters and the time power consumption curves of different time periods.

[0123] The suspect screening module 240 is used to screen users who are highly suspected of electricity theft based on electrical characteristic criteria.

[0124] See also Figure 4 An embodiment of the present invention provides a computer terminal device, comprising one or more processors and a memory. The memory is coupled to the processor and is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the power consumption behavior detection method in any of the above embodiments.

[0125] The processor is used to control the overall operation of the computer terminal device to complete all or part of the steps of the above-mentioned power consumption behavior detection method. The memory is used to store various types of data to support the operation of the computer terminal device, and these data may include, for example, instructions for any application or method used to operate on the computer terminal device, as well as application-related data. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0126] In an exemplary embodiment, the computer terminal device can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, ASC), digital signal processors (Digital Signal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned power consumption behavior detection method and achieve the same technical effect as the above-mentioned method.

[0127] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the power usage behavior detection method in any of the above embodiments are implemented. For example, the computer-readable storage medium can be the above-mentioned memory including program instructions, and the above-mentioned program instructions can be executed by a processor of a computer terminal device to complete the above-mentioned power usage behavior detection method and achieve the same technical effect as the above-mentioned method.

[0128] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for detecting electricity usage behavior, characterized in that: include: Acquire electrical data measured by an electric meter; the electrical data includes user power consumption, area line loss and public transformer load; Extracting electrical characteristic parameters for characterizing abnormal power consumption according to the electrical data; The electrical characteristic parameters include power consumption coefficient, user dispersion coefficient, correlation coefficient between line loss and power consumption, and the maximum load utilization day of the month; A first criterion is generated according to the user's summer or winter electricity consumption curve and the corresponding electrical characteristic parameters. The first criterion is: ； The second criterion is generated according to the user's 20-40 days electricity consumption curve and the corresponding electrical characteristic parameters. The second criterion is: The line loss rate of the dedicated transformer at night is L>20%, and r>0.6; According to the user's 50-100-day electricity consumption curve and the corresponding electrical characteristic parameters, a third criterion is generated, and the third criterion is: χ<0.3 and r>0.6; or, The line loss rate on weekends is L>20% and r>0.6; A fourth criterion is generated based on the user's electricity consumption curve for more than 300 days and the corresponding electrical characteristic parameters. The fourth criterion is: The line loss rate in the month is L>20%, and the correlation coefficient with a certain user is r>0.6 and d<15; According to the user's electricity consumption curve for more than 600 days and the corresponding electrical characteristic parameters, a fifth criterion is generated, and the fifth criterion is: Line loss rate L>20%, r>0.6 and ; In the formula, L is the line loss rate, r is the Pearson correlation coefficient between the line loss rate of the substation area and the user's power consumption, χ is the power consumption coefficient, which is the ratio of the user's total power consumption during this period to the capacity of the public or special transformer, n is the number of users, is the difference of user dispersion coefficient, d is the maximum load utilization day of the month; The calculation formula of the power consumption coefficient is: The calculation formula of the user dispersion coefficient difference is: In the formula, S is the transformer capacity, and t is the length of time for data collection; A corresponding electricity theft suspicion is set for each electrical feature criterion, and the electricity theft suspicion of the combined criterion of the electrical feature criterion satisfied by the user is calculated according to the electricity theft suspicion; the electricity theft suspicion of the combined criterion is used as the final user suspicion, and users with high electricity theft suspicion are screened according to the user suspicion; wherein the electricity theft suspicion of the combined criterion is calculated according to the following formula: In the formula, b_ represents the suspicion of electricity theft based on the combined criterion, represents the suspicion of electricity theft corresponding to the i-th electrical feature criterion, and i represents the i-th electrical feature criterion.

2. A power consumption behavior detection system, characterized in that: include: A data acquisition module is used to acquire electrical data measured by an electric meter; the electrical data includes user power consumption, area line loss and public transformer load; A feature extraction module is used to extract electrical feature parameters for characterizing abnormal power consumption according to the electrical data; The electrical characteristic parameters include power consumption coefficient, user dispersion coefficient, correlation coefficient between line loss and power consumption, and the maximum load utilization day of the month; The criterion classification module is used to generate a first criterion according to the user's summer or winter electricity consumption curve and the corresponding electrical characteristic parameters, wherein the first criterion is: ； The second criterion is generated according to the user's 20-40 days electricity consumption curve and the corresponding electrical characteristic parameters. The second criterion is: The line loss rate of the dedicated transformer at night is L>20%, and r>0.6; According to the user's 50-100-day electricity consumption curve and the corresponding electrical characteristic parameters, a third criterion is generated, and the third criterion is: χ<0.3 and r>0.6; or, The line loss rate on weekends is L>20% and r>0.6; A fourth criterion is generated based on the user's electricity consumption curve for more than 300 days and the corresponding electrical characteristic parameters. The fourth criterion is: The line loss rate in the month is L>20%, and the correlation coefficient with a certain user is r>0.6 and d<15; According to the user's electricity consumption curve for more than 600 days and the corresponding electrical characteristic parameters, a fifth criterion is generated, and the fifth criterion is: Line loss rate L>20%, r>0.6 and ; In the formula, L is the line loss rate, r is the Pearson correlation coefficient between the line loss rate of the substation area and the user's power consumption, χ is the power consumption coefficient, which is the ratio of the user's total power consumption during this period to the capacity of the public or special transformer, n is the number of users, is the difference of user dispersion coefficient, d is the maximum load utilization day of the month; The calculation formula of the power consumption coefficient is: The calculation formula of the user dispersion coefficient difference is: In the formula, S is the transformer capacity, and t is the length of time for data collection; The suspicion screening module is used to set a corresponding electricity theft suspicion for each electrical feature criterion, and calculate the electricity theft suspicion of the combined criterion of the electrical feature criterion satisfied by the user according to the electricity theft suspicion; use the electricity theft suspicion of the combined criterion as the final user suspicion, and screen users with high electricity theft suspicion according to the user suspicion; wherein the electricity theft suspicion of the combined criterion is calculated according to the following formula: In the formula, b_ represents the suspicion of electricity theft based on the combined criterion, represents the suspicion of electricity theft corresponding to the i-th electrical feature criterion, and i represents the i-th electrical feature criterion.

3. A computer terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the power usage behavior detection method as described in claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the power usage behavior detection method as claimed in claim 1 is implemented.

Images