Method for detecting electricity theft, smart circuit breaker and electricity meter
Through intelligent circuit breakers and electricity meters, power consumption and network correlation data are obtained and analyzed in the low-voltage distribution station area, and the vector network characteristics and spectrum characteristics are used to identify power stolen behavior, which solves the problem of low accuracy in power stolen detection in the prior art The problem has achieved more efficient detection of power theft.
Patent Information
- Application Number
- CN202110214528.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-02-25
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2041-02-25
AI Technical Summary
The existing power stolen detection technology is low in accuracy in low-voltage distribution station areas, making it difficult to effectively detect power stolen behavior, which may lead to safety risks and economic losses in the power grid operation.
Using intelligent circuit breakers and electricity meters, by obtaining data such as electricity consumption, line loss and network correlation, the vector network characteristics and spectrum characteristics of the distribution network are used to determine the line loss threshold and characteristic values, identify suspicious electricity meters, and improve the The accuracy of power theft detection.
It improves the accuracy and efficiency of power theft detection, can more effectively detect power theft behavior, and reduces grid operation risks and economic losses.
Smart Images

Figure CN113009221B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of electricity theft detection, and in particular to a method for detecting electricity theft, an intelligent circuit breaker and an electric meter. Background Art
[0002] Electricity theft is an illegal act that will lead to power loss, causing serious losses to the country and endangering the safe operation of the power grid. On the one hand, electricity theft by users may cause power supply lines to be interrupted, resulting in large-scale power outages; on the other hand, electricity theft may also cause power supply lines to short-circuit, causing fires and causing serious consequences. Therefore, it is urgent to find a feasible and efficient supervision method to promptly identify users who steal electricity in the substation area. However, the current electricity theft detection technology mainly analyzes user electricity consumption data and has low accuracy. Summary of the invention
[0003] The purpose of the embodiments of the present invention is to provide a method for detecting electricity theft, an intelligent circuit breaker and an electricity meter.
[0004] In order to achieve the above-mentioned object, the first aspect of the present invention provides a method for detecting electricity theft, which is applied to an intelligent circuit breaker in a low-voltage distribution station area, and the intelligent circuit breaker manages multiple electricity meters. The method includes:
[0005] Obtain the power consumption of the intelligent circuit breaker in the first period and the power consumption of each corresponding managed electric meter in the first period;
[0006] Determine the line loss amount of the intelligent circuit breaker in the first time period according to the power consumption of the intelligent circuit breaker in the first time period and the power consumption of each electric meter in the first time period;
[0007] Determine a line loss threshold value of the intelligent circuit breaker in the first time period according to the line loss amount of the intelligent circuit breaker in the first time period;
[0008] Sending the line loss threshold value of the first time period to each electric meter, and detecting whether any electric meter returns a corresponding network association;
[0009] In the case of detecting that an electric meter returns a corresponding network association, determining a characteristic value corresponding to the electric meter that sends the network association according to the received network association;
[0010] A preset number of electric meters with the largest characteristic values are determined as suspicious electric meters.
[0011] In the embodiment of the present invention, determining the line loss threshold value of the intelligent circuit breaker in the first time period according to the line loss amount in the first time period includes:
[0012] Obtain the line loss amount and line loss threshold value of the intelligent circuit breaker in the previous period;
[0013] The line loss threshold value of the intelligent circuit breaker in the first time period is determined according to the line loss amount of the intelligent circuit breaker in the first time period, the line loss amount of the intelligent circuit breaker in the previous time period, and the line loss threshold value of the intelligent circuit breaker in the previous time period.
[0014] In an embodiment of the present invention, determining the characteristic value corresponding to the electric meter that sends the network association according to the received network association includes:
[0015] Formula (1) is used to determine the characteristic value corresponding to the meter that sends the network association:
[0016]
[0017] Among them, C i represents the characteristic value corresponding to the meter i that sends the network association, j is the meter that has a communication relationship with the meter i, j∈Γ(i), Γ(i) represents the set of all meters that have a communication relationship with the meter i, Q represents the number of meters in Γ(i), k represents the first duration, L(l) represents the line loss of the intelligent circuit breaker at the lth moment, 0<l<k, It represents the network association degree between meter i and meter j at the lth moment.
[0018] A second aspect of the present invention provides another method for detecting electricity theft, which is applied to electric meters in a low-voltage distribution station area, wherein in the low-voltage distribution station area, one intelligent circuit breaker manages multiple electric meters, and the method comprises:
[0019] Obtaining the data sequence correlation degree of the electric meter in the first time period, the power threshold value of the electric meter in the first time period, the network correlation degree of the electric meter in the first time period, and the power average value of the electric meter in the first time period;
[0020] A line loss threshold value of the smart circuit breaker in the first time period sent by the smart circuit breaker corresponding to the receiving electric meter;
[0021] Determine whether the data sequence correlation of the electric meter in the first time period is greater than the line loss threshold value of the intelligent circuit breaker in the first time period, and whether the power average of the electric meter in the first time period is less than the power threshold value of the electric meter in the first time period;
[0022] When it is determined that the data sequence correlation degree of the first time length is greater than the line loss threshold value of the intelligent circuit breaker in the first time length, and the average power of the electric meter in the first time length is less than the power threshold value of the electric meter in the first time length, the network correlation degree of the electric meter in the first time length is returned to the intelligent circuit breaker, so that the intelligent circuit breaker determines the suspicious electric meter according to the network correlation degree.
[0023] In an embodiment of the present invention, the method further includes:
[0024] When it is determined that the data sequence correlation degree of the first time length is less than or equal to the line loss threshold value of the intelligent circuit breaker in the first time length, or the power average of the electric meter in the first time length is greater than or equal to the power threshold value of the electric meter in the first time length, the network correlation degree of the electric meter in the first time length is returned to the intelligent circuit breaker with a preset probability.
[0025] In the embodiment of the present invention, obtaining the data sequence correlation of the electric meter in the first time period includes:
[0026] Obtaining a frequency spectrum feature sequence of the electric meter at a first time length;
[0027] Determine the correlation degree of the data sequence of the electric meter at the first time length according to the frequency spectrum feature sequence of the electric meter at the first time length.
[0028] In the embodiment of the present invention, obtaining the power threshold value of the electric meter for the first time period includes:
[0029] Get the average voltage value of the electric meter in the previous period;
[0030] The power threshold value of the electric meter in the first time period is determined according to the voltage average value of the electric meter in the previous time period.
[0031] In the embodiment of the present invention, obtaining the network association degree of the electric meter for the first time period includes:
[0032] Obtaining a time network characteristic sequence of the electric meter at a first time length;
[0033] The network association degree of the electric meter in the first time period is determined according to the time network characteristic sequence of the electric meter in the first time period.
[0034] A third aspect of the present invention provides an intelligent circuit breaker, which can execute any one of the methods for detecting electricity theft provided in the first aspect.
[0035] A fourth aspect of the present invention provides an electricity meter capable of executing any one of the methods for detecting electricity theft provided in the second aspect.
[0036] Through the above technical solution, the power consumption of the smart circuit breaker in the first time period and the power consumption of each corresponding electric meter in the first time period are obtained; the line loss of the smart circuit breaker in the first time period is determined according to the power consumption of the smart circuit breaker in the first time period and the power consumption of each electric meter in the first time period; the line loss threshold value of the smart circuit breaker in the first time period is determined according to the line loss of the smart circuit breaker in the first time period; the line loss threshold value of the first time period is sent to each electric meter, and it is detected whether there is an electric meter returning the corresponding network association; in the case of detecting that there is an electric meter returning the corresponding network association, the characteristic value corresponding to the electric meter sending the network association is determined according to the received network association; the electric meters with the largest characteristic values of a preset number are determined as suspicious electric meters. The embodiment of the present invention uses the vector network characteristics, spectrum characteristics and power consumption data of the distribution network to analyze whether there is power theft in the distribution network, so that the analysis result is more accurate.
[0037] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:
[0039] Figure 1 is a flow chart of a method for detecting electricity theft according to an embodiment of the present invention;
[0040] Figure 2 is a flow chart of a method for detecting electricity theft according to another embodiment of the present invention;
[0041] Figure 3 This is a schematic diagram of a power distribution network architecture according to an application embodiment of the present invention;
[0042] Figure 4 is a schematic diagram of an electric meter module according to an application embodiment of the present invention;
[0043] Figure 5 It is a schematic diagram of the electric meter processing flow of an application embodiment of the present invention;
[0044] Figure 6 It is a diagram of the internal structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0045] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.
[0046] Before introducing the solutions of the embodiments of the present invention, the following terms are introduced.
[0047] The characteristics of vector networks mainly include reflection characteristics and transmission characteristics. Among them, the reflection characteristics include: S parameters ( S 11 , S22 ), voltage standing wave ratio (VSWR), reflection coefficient, return loss; transmission characteristics include: S parameters ( S 21 ,S 12 ), transmission coefficient, insertion loss, gain, group delay, and phase.
[0048] The most basic term for reflecting characteristics is reflection coefficient. The reflection coefficient is the ratio of the voltage level of the reflected signal to the voltage level of the incident signal. For example, when the load impedance is equal to the characteristic impedance, the transmission line of the characteristic impedance transmits all the energy to the load, so the reflection coefficient amplitude μ is 0. When the load impedance is not equal to the characteristic impedance, part of the energy is reflected, and μ is greater than 0. When the load impedance is short-circuited or open-circuited, all the energy is reflected, and μ is 1. Therefore, μ is between 0 and 1.
[0049] Return loss is another way to express the reflection coefficient in logarithmic terms. Return loss is the number of dB that the reflected signal is lower than the incident signal. It is a positive number that varies between infinity and 0.
[0050] Another common term used to describe reflection is the voltage standing wave ratio (VSRW), which is defined as the ratio of the maximum value of the RF envelope to the minimum value of the RF envelope. VSWR values range from 1 (no reflection) to infinity (full reflection).
[0051] The most basic term for transmission characteristics is the transmission coefficient, which is defined as the transmitted voltage divided by the incident voltage. If the absolute value of the transmitted voltage is greater than the absolute value of the incident voltage, the device or system under test is considered to have gain. If the absolute value of the transmitted voltage is less than the absolute value of the incident voltage, the system under test is considered to have insertion loss.
[0052] Another useful measure of transmission characteristics is group delay, which is a measure of the variation of the signal's transit time through the DUT with frequency. Mean delay represents the average transit time of the signal through the DUT.
[0053] In addition, in the simple two-port network, S 11 Equivalent to the input complex reflection coefficient or impedance of the device under test, S 22 Equivalent to the output complex reflection coefficient or impedance of the device under test, used to represent the reflection characteristics. S 21 is the forward complex transmission coefficient, S 12 is the inverse complex transmission coefficient, which is used to represent the transmission characteristics.
[0054] The embodiment of the present invention provides a method for detecting electricity theft, which is applied to an intelligent circuit breaker in a low-voltage distribution station area. The intelligent circuit breaker manages multiple electricity meters, such as Figure 1 As shown, the method includes:
[0055] Step 101: Obtain the power consumption of the intelligent circuit breaker in the first period and the power consumption of each corresponding managed electric meter in the first period;
[0056] Step 102: determining the line loss of the intelligent circuit breaker in the first time period according to the power consumption of the intelligent circuit breaker in the first time period and the power consumption of each electric meter in the first time period;
[0057] Step 103: determining a line loss threshold value of the intelligent circuit breaker in the first time period according to the line loss amount of the intelligent circuit breaker in the first time period;
[0058] Step 104: Send the line loss threshold value of the first time length to each electric meter, and detect whether any electric meter returns a corresponding network association degree;
[0059] Step 105: when it is detected that an electric meter returns a corresponding network association, determining a characteristic value corresponding to the electric meter that sends the network association according to the received network association;
[0060] Step 106: Determine the electric meters with the largest preset number of characteristic values as suspicious electric meters. Specifically, the largest preset number of characteristic values (i.e., the minimum value among the selected characteristic values is greater than the maximum value among the unselected characteristic values) may be selected from the determined characteristic values (set), and the electric meters corresponding to the selected characteristic values may be determined as suspicious electric meters. In one example, the determined characteristic values may be sorted (e.g., from large to small), and the electric meters corresponding to the preset number of characteristic values may be determined as suspicious electric meters.
[0061] Specifically, the electric meter in this embodiment may be a smart electric meter. The smart circuit breaker may communicate with the electric meter via carrier communication technology.
[0062] In actual application, the first duration can be set based on judgment needs.
[0063] In addition, the line loss in this embodiment refers to the difference between the power supply and the power sales, which generally includes two parts: technical line loss and management line loss. The line loss caused by power theft belongs to management line loss.
[0064] In one embodiment, determining the characteristic value corresponding to the electric meter sending the network association according to the received network association includes:
[0065] Formula (1) is used to determine the characteristic value corresponding to the meter that sends the network association:
[0066]
[0067] Among them, C i represents the characteristic value corresponding to the meter i that sends the network association, j is the meter that has a communication relationship with the meter i, j∈Γ(i), Γ(i) represents the set of all meters that have a communication relationship with the meter i, Q represents the number of meters in Γ(i), k represents the first duration, L(l) represents the line loss of the intelligent circuit breaker at the lth moment, 0<l<k, It represents the network association degree between meter i and meter j at the lth moment.
[0068] Specifically, the line loss of the intelligent circuit breaker in the first time period can be determined using formula (2):
[0069]
[0070] Where L(k) represents the line loss of the intelligent circuit breaker in the first time period, e 0 (k) represents the power consumption of the smart circuit breaker in the first period, C represents the number of meters managed by the smart circuit breaker, and e i (k) represents the power consumption of meter i in the first period, 0<i<C.
[0071] In one embodiment, determining the line loss threshold value of the intelligent circuit breaker in the first time period according to the line loss amount in the first time period includes:
[0072] Obtain the line loss amount and line loss threshold value of the intelligent circuit breaker in the previous period;
[0073] The line loss threshold value of the intelligent circuit breaker in the first time period is determined according to the line loss amount of the intelligent circuit breaker in the first time period, the line loss amount of the intelligent circuit breaker in the previous time period, and the line loss threshold value of the intelligent circuit breaker in the previous time period.
[0074] Specifically, the line loss threshold value of the intelligent circuit breaker in the first time period can be determined using formula (3):
[0075] V 2 (k) = V 2 (k-1)+u×L(k-1) Formula (3)
[0076] Among them, V 2 (k) represents the line loss threshold value of the intelligent circuit breaker in the first time period, V 2 (k-1) represents the line loss threshold value of the intelligent circuit breaker in the previous period, u represents a constant, 0<u<1, and L(k-1) represents the line loss amount of the intelligent circuit breaker in the previous period.
[0077] In addition, an embodiment of the present invention further provides a method for detecting electricity theft, which is applied to electric meters in a low-voltage distribution station area, wherein in the low-voltage distribution station area, one intelligent circuit breaker manages multiple electric meters, such as Figure 2 As shown, the method includes:
[0078] Step 201: obtaining a data sequence correlation degree of the electric meter in the first time period, a power threshold value of the electric meter in the first time period, a network correlation degree of the electric meter in the first time period, and a power average value of the electric meter in the first time period;
[0079] Step 202: receiving a line loss threshold value of the smart circuit breaker in the first time period sent by the smart circuit breaker corresponding to the electric meter;
[0080] Step 203: determine whether the data sequence correlation of the electric meter in the first time period is greater than the line loss threshold value of the intelligent circuit breaker in the first time period, and whether the power average of the electric meter in the first time period is less than the power threshold value of the electric meter in the first time period;
[0081] Step 204: When it is determined that the data sequence correlation of the first time length is greater than the line loss threshold value of the intelligent circuit breaker in the first time length, and the average power of the meter in the first time length is less than the power threshold value of the meter in the first time length, the network correlation of the meter in the first time length is returned to the intelligent circuit breaker, so that the intelligent circuit breaker determines the suspicious meter according to the network correlation.
[0082] Specifically, the electric meter in this embodiment may be a smart electric meter. The smart circuit breaker may communicate with the electric meter via carrier communication technology.
[0083] In actual application, the first duration can be set based on judgment needs.
[0084] In addition, the line loss in this embodiment refers to the difference between the power supply and the power sales, which generally includes two parts: technical line loss and management line loss. The line loss caused by power theft belongs to management line loss.
[0085] In one embodiment, the method further comprises:
[0086] When it is determined that the data sequence correlation degree of the first time length is less than or equal to the line loss threshold value of the intelligent circuit breaker in the first time length, or the power average of the electric meter in the first time length is greater than or equal to the power threshold value of the electric meter in the first time length, the network correlation degree of the electric meter in the first time length is returned to the intelligent circuit breaker with a preset probability.
[0087] In actual application, the preset probability can be set based on needs. For example, when the preset probability is 30%, the data of the first time length is obtained for 10 times. If the data of the first time length each time in the 10 times satisfies that the data sequence correlation of the first time length is less than or equal to the line loss threshold value of the intelligent circuit breaker in the first time length, or the power average of the meter in the first time length is greater than or equal to the power threshold value of the meter in the first time length, then the data of the first time length for 10 times is randomly reported with the data of the first time length for 3 times.
[0088] In one embodiment, obtaining the correlation degree of the data sequence of the electric meter at the first time length includes:
[0089] Obtaining a frequency spectrum feature sequence of the electric meter at a first time length;
[0090] Determine the correlation degree of the data sequence of the electric meter at the first time length according to the frequency spectrum feature sequence of the electric meter at the first time length.
[0091] Specifically, the correlation degree of the data sequence of the electric meter in the first time period can be determined using formula (4):
[0092]
[0093] in, represents the data sequence correlation of meter i in the first time period, k represents the first time period, M is the total number of measured frequency points, 0<h<M, represents the spectrum characteristic value of the hth frequency point in the spectrum characteristic sequence of the first duration of meter i, It represents the spectrum characteristic value of the hth frequency point in the spectrum characteristic sequence of the electric meter i in the previous time period.
[0094] In one embodiment, obtaining the power threshold value of the electric meter for the first time period includes:
[0095] Get the average voltage value of the electric meter in the previous period;
[0096] The power threshold value of the electric meter in the first time period is determined according to the voltage average value of the electric meter in the previous time period.
[0097] Specifically, the power threshold value of the electric meter in the first time period can be determined using formula (5):
[0098]
[0099] Among them, V 1 (k) represents the power threshold value of meter i in the first time period, U i (k-1) represents the average voltage of meter i in the previous period, α represents a constant, 0<α<1.
[0100] In one embodiment, obtaining the network association of the electric meter in the first time period includes:
[0101] Obtaining a time network characteristic sequence of the electric meter at a first time length;
[0102] The network association degree of the electric meter in the first time period is determined according to the time network characteristic sequence of the electric meter in the first time period.
[0103] Specifically, the network association degree of the electric meter in the first time period can be determined using formula (6):
[0104]
[0105] in, represents the network association between meter i and meter j in the first time period, j is the meter that has a communication relationship with meter i, j∈Γ(i), Γ(i) represents the set of all meters that have a communication relationship with meter i, M is the total number of measured frequency points, is a complex number, which represents the vector transmission characteristic of the hth frequency point in the time network characteristic sequence of the first duration between the electric meter i and the electric meter j. is a complex number, representing the vector transmission characteristic of the hth frequency point in the time network characteristic sequence of the electric meter i and the electric meter j in the previous time length, k represents the first time length, and 0<h<M.
[0106] Through the above technical solution, the power consumption of the smart circuit breaker in the first time period and the power consumption of each corresponding electric meter in the first time period are obtained; the line loss of the smart circuit breaker in the first time period is determined according to the power consumption of the smart circuit breaker in the first time period and the power consumption of each electric meter in the first time period; the line loss threshold value of the smart circuit breaker in the first time period is determined according to the line loss of the smart circuit breaker in the first time period; the line loss threshold value of the first time period is sent to each electric meter, and it is detected whether there is an electric meter returning the corresponding network association; in the case of detecting that there is an electric meter returning the corresponding network association, the characteristic value corresponding to the electric meter sending the network association is determined according to the received network association; the electric meters with the largest characteristic values of a preset number are determined as suspicious electric meters. The embodiment of the present invention uses the vector network characteristics, spectrum characteristics and power consumption data of the distribution network to analyze whether there is power theft in the distribution network, so that the analysis result is more accurate.
[0107] The present invention is further described in detail below in conjunction with application examples.
[0108] This application embodiment proposes a low-voltage area electricity theft detection system based on vector network characteristic analysis, spectrum characteristic analysis and electricity consumption data analysis. Figure 3 As shown, the whole system consists of two parts: smart circuit breaker and smart meter. One smart circuit breaker is responsible for a certain number of smart meters.
[0109] Also, see Figure 4, the smart meter in this embodiment includes a controller A1, a power line carrier communication module A2, a network characteristic measurement output A3, a network characteristic measurement input A4, a spectrum detection input A5, a coupling circuit A6, and a power consumption detection A7. The power line carrier communication module A2 is used for carrier communication with the smart circuit breaker; the network characteristic measurement output A3 and the network characteristic measurement input A4 are used to obtain the network characteristic data in the distribution network using the coupling circuit A6 and transmit it to the controller A1; the spectrum detection input A5 is used to obtain the spectrum data in the distribution network using the coupling circuit A6 and transmit it to the controller A1; the power consumption detection A7 is used to obtain the power consumption data (such as voltage, current, power) of the user in the distribution network using the coupling circuit A6 and transmit it to the controller A1; the controller A1 performs processing based on the obtained information. The spectrum detection input A5 in this embodiment can be understood as a spectrum detection module, and the network characteristic measurement output A3 and the network characteristic measurement input A4 can be understood as a vector network characteristic analysis module.
[0110] It should also be explained that the coupling circuit A6 is connected to a power line, which is a low-voltage power line, usually with a voltage of 220V or 380V.
[0111] Specifically, the electricity theft detection method of this embodiment includes the following steps:
[0112] Step 1: The spectrum detection module A5 collects the power supply voltage data of the voltage port of the meter and obtains the voltage According to voltage Get the spectrum feature sequence of M frequency points Where m is the total number of measured frequency points, i is the meter number, and k is a period of time.
[0113] Step 2: The vector network characteristic analysis module A4 obtains the vector network frequency characteristics between the meters and obtains the vector transmission characteristics from meter i to meter j. The network characteristic sequence of meter i and meter j at time k is: j∈Γ(i), where m is the total number of measured frequency points, i and j are meter numbers, k is a period of time, and Γ(i) represents the set of meters whose distance to meter i is less than the threshold.
[0114] Step 3: The power measurement module A7 measures the voltage and power of the meter to obtain the voltage average value U i (k), power mean P i (k) and electricity consumption e i (k), where i is the meter number and k is a period of time.
[0115] Step 4: The intelligent circuit breaker uses the above formula (2) to calculate the line loss at time k.
[0116] Step 5: The intelligent circuit breaker calculates the line loss threshold value according to the line loss amount in step 4 using the above formula (3) and sends it to each electricity meter.
[0117] Step 6: Each meter is based on the voltage average value U in step 3 i (k) Calculate the power threshold value using the above formula (5).
[0118] Step 7: Electric meter i calculates the data sequence correlation degree at the kth time using the above formula (4) according to the frequency spectrum feature sequence obtained in step 1.
[0119] Step 8: Meter i calculates the network association degree between meter i and meter j at time k using the above formula (6) according to the time network characteristic sequence obtained in step 2.
[0120] Step 9: When the meter detects the correlation of the data sequence Greater than V 2 (k), and the average power P i (k) is less than V 1 (k), report the data; otherwise, report the data with probability ρ (a constant greater than 0 and less than 1).
[0121] Step 10: The smart circuit breaker obtains the meter's data from the data reported in step 9. The eigenvalue is calculated using the above formula (1).
[0122] Step 11: Sort the nodes by their characteristic values from large to small, and mark the top several (for example, a preset number) of meter nodes as suspicious nodes.
[0123] For practical application, see Figure 5 , the processing of the electric meter is as follows:
[0124] Step 501: Start; then execute step 502;
[0125] Step 502: Get the sequence L(k); then execute step 503;
[0126] Step 503: Calculate the threshold value V 2 (k) = V 2 (k-1)+u×L(k-1); then execute step 504;
[0127] Step 504: Calculate the correlation between the measurement data sequence Ai(k) of meter i in time period k and the previous time Ai(k-1) Then execute step 505;
[0128] Step 505: Calculate the correlation between the vector network characteristic sequence Dij(k) formed by the electric meter i and the electric meter j and its previous moment Dij(k-1) Then execute step 506;
[0129] Step 506: Setting the threshold value Then execute step 507;
[0130] Step 507: Determine whether And P i (k) <V 1 (k);
[0131] in the case of And P i (k) <V 1 (k), then execute step 508, if not, then execute step 509;
[0132] Step 508: reporting data; then executing step 510;
[0133] Step 509: reporting data with probability p; then executing step 510;
[0134] Step 510: End.
[0135] This application embodiment takes the spectrum of electrical appliances and the vector network characteristics between meters into consideration in the electricity theft analysis by setting up voltage spectrum detection and vector network characteristic analysis modules, so as to more accurately detect the user's electricity theft behavior. At the same time, this application embodiment uses multimodal association to analyze the measurement data between meters, and obtains the multimodal association between electricity consumption / electricity theft behavior and two meters through secondary association analysis; constructs the network communication relationship between meters, and then uses the centrality analysis method in the field of social network research to obtain the ranking of electricity theft users of the meters, and reports the suspicious nodes. That is, this embodiment detects the possibility of electricity theft by users by detecting the changes in the vector network characteristics of the distribution network after the user's electrical appliances are used, and can provide corresponding information for power supply companies to prevent electricity theft and line loss management.
[0136] The embodiment of the present invention further provides an intelligent circuit breaker, which can execute the method in the above embodiment.
[0137] An embodiment of the present invention further provides an electric meter, which can execute the method in the above embodiment.
[0138] An embodiment of the present invention further provides a storage medium on which instructions are stored, and the instructions are used to enable a machine to execute the method of any one of the above embodiments.
[0139] An embodiment of the present invention further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method of any one of the above embodiments is implemented.
[0140] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, a method for detecting electricity theft is implemented. The display screen A04 of the computer device can be a liquid crystal display or an electronic ink display, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.
[0141] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0142] An embodiment of the present invention provides a device, including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the method for detecting electricity theft is implemented.
[0143] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0144] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0145] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0147] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0148] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0149] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0150] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0151] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.
Claims
1. A method for detecting electricity theft, It is characterized in that An intelligent circuit breaker applied to a low-voltage distribution station area, the intelligent circuit breaker correspondingly manages multiple electric meters, and the method includes: Obtaining the power consumption of the intelligent circuit breaker in the first period and the power consumption of each corresponding managed electric meter in the first period; Determine the line loss of the intelligent circuit breaker in the first time period according to the power consumption of the intelligent circuit breaker in the first time period and the power consumption of each electric meter in the first time period; Determine a line loss threshold value of the intelligent circuit breaker in the first time period according to the line loss amount of the intelligent circuit breaker in the first time period; Sending the line loss threshold value of the first time length to each electric meter, and detecting whether any electric meter returns a corresponding network association; In the case of detecting that an electric meter returns a corresponding network association, determining a characteristic value corresponding to the electric meter that sends the network association according to the received network association; Determine a preset number of electric meters with the largest characteristic values as suspicious electric meters; Wherein, determining the network association degree of the electric meter in the first time period according to the time network characteristic sequence of the electric meter in the first time period includes: determining the network association degree of the electric meter in the first time period by using the following formula: in, represents the network association between meter i and meter j in the first time period, j is the meter that has a communication relationship with meter i, j∈Γ(i), Γ(i) represents the set of all meters that have a communication relationship with meter i, M is the total number of measured frequency points, is a complex number, which represents the vector transmission characteristic of the hth frequency point in the time network characteristic sequence of the first duration between the electric meter i and the electric meter j. is a complex number, representing the vector transmission characteristic of the hth frequency point in the time network characteristic sequence of the last time length between the electric meter i and the electric meter j, k represents the first time length, 0<h<M; The determining, according to the received network association, the characteristic value corresponding to the electric meter that sends the network association comprises: determining the characteristic value corresponding to the electric meter using the following formula: Among them, C i represents the characteristic value corresponding to the meter i that sends the network association, j is the meter that has a communication relationship with the meter i, j∈Γ(i), Γ(i) represents the set of all meters that have a communication relationship with the meter i, Q represents the number of meters in Γ(i), k represents the first duration, L(l) represents the line loss of the intelligent circuit breaker at the lth moment, 0<l<k, It represents the network association degree between meter i and meter j at the lth moment.
2. The method for detecting electricity theft according to claim 1, It is characterized in that Determining the line loss threshold value of the intelligent circuit breaker in the first time period according to the line loss amount of the first time period includes: Obtaining the line loss amount of the intelligent circuit breaker in the previous period and the line loss threshold value in the previous period; The line loss threshold value of the intelligent circuit breaker in the first time length is determined according to the line loss amount of the intelligent circuit breaker in the first time length, the line loss amount of the intelligent circuit breaker in the previous time length, and the line loss threshold value of the intelligent circuit breaker in the previous time length.
3. A method for detecting electricity theft, It is characterized in that Applied to an electric meter in a low-voltage distribution station area, wherein in the low-voltage distribution station area, one intelligent circuit breaker manages multiple electric meters, and the method comprises: Obtaining the data sequence correlation degree of the electric meter in the first time length, the power threshold value of the electric meter in the first time length, the network correlation degree of the electric meter in the first time length, and the power average value of the electric meter in the first time length; receiving a line loss threshold value of the intelligent circuit breaker for a first time period sent by the intelligent circuit breaker corresponding to the electric meter; Determine whether the data sequence correlation of the electric meter in the first time length is greater than the line loss threshold value of the intelligent circuit breaker in the first time length, and whether the power average of the electric meter in the first time length is less than the power threshold value of the electric meter in the first time length; When it is determined that the data sequence correlation of the first time length is greater than the line loss threshold value of the intelligent circuit breaker in the first time length, and the average power of the electric meter in the first time length is less than the power threshold value of the electric meter in the first time length, the network correlation of the electric meter in the first time length is returned to the intelligent circuit breaker, so that the intelligent circuit breaker determines the characteristic value corresponding to the electric meter according to the network correlation, and determines the electric meters with the largest characteristic values of a preset number as suspicious electric meters; Wherein, obtaining the network association degree of the electric meter in the first time period includes: Acquire a time network characteristic sequence of the electric meter for a first time period; Determining the network association of the electric meter for the first time period according to the time network characteristic sequence of the electric meter for the first time period includes: determining the network association of the electric meter for the first time period using the following formula: in, represents the network association between meter i and meter j in the first time period, j is the meter that has a communication relationship with meter i, j∈Γ(i), Γ(i) represents the set of all meters that have a communication relationship with meter i, M is the total number of measured frequency points, is a complex number, which represents the vector transmission characteristic of the hth frequency point in the time network characteristic sequence of the first duration between the electric meter i and the electric meter j. is a complex number, representing the vector transmission characteristic of the hth frequency point in the time network characteristic sequence of the last time length between the electric meter i and the electric meter j, k represents the first time length, 0<h<M; The intelligent circuit breaker determines the characteristic value corresponding to the electric meter according to the network association, including: determining the characteristic value corresponding to the electric meter using the following formula: Among them, C i represents the characteristic value corresponding to the meter i that sends the network association, j is the meter that has a communication relationship with the meter i, j∈Γ(i), Γ(i) represents the set of all meters that have a communication relationship with the meter i, Q represents the number of meters in Γ(i), k represents the first duration, L(l) represents the line loss of the intelligent circuit breaker at the lth moment, 0<l<k, It represents the network association degree between meter i and meter j at time l.
4. The method for detecting electricity theft according to claim 3, It is characterized in that The method further comprises: When it is determined that the data sequence correlation degree of the first time length is less than or equal to the line loss threshold value of the intelligent circuit breaker in the first time length, or the power average of the electric meter in the first time length is greater than or equal to the power threshold value of the electric meter in the first time length, the network correlation degree of the electric meter in the first time length is returned to the intelligent circuit breaker with a preset probability.
5. The method for detecting electricity theft according to claim 3, It is characterized in that The step of obtaining the data sequence correlation of the electric meter at the first time length comprises: Acquire a frequency spectrum feature sequence of the electric meter at a first time length; The correlation degree of the data sequence of the electric meter at the first time length is determined according to the frequency spectrum feature sequence of the electric meter at the first time length.
6. The method for detecting electricity theft according to claim 3, It is characterized in that The obtaining of the power threshold value of the electric meter for the first time period includes: Obtaining the voltage average value of the electric meter in the previous period; The power threshold value of the electric meter in the first time period is determined according to the voltage average value of the electric meter in the previous time period.
7. An intelligent circuit breaker, It is characterized in that The intelligent circuit breaker can execute the method for detecting electricity theft according to any one of claims 1 to 2.
8. An electric meter, It is characterized in that The electricity meter is capable of executing the method for detecting electricity theft according to any one of claims 3 to 6.
