Electricity stealing detection method and system based on cluster data of electric energy meter, equipment and medium

Abstract

The application discloses a kind of based on electric energy meter cluster data electricity larceny detection method and system, equipment, medium, the electricity larceny detection method of the present application first obtains the voltage variation data and current variation data of electric energy meter cluster under target station area, then using the voltage event attribution judgment of preset event detection window based on the voltage variation data and current variation data of electric energy meter cluster, can accurately identify the abnormal behavior that there is voltage mutation but no corresponding current variation, and generate unattributed electric energy meter sequence, then, based on unattributed electric energy meter sequence carries out statistical analysis, by the distribution characteristics of abnormal behavior is analyzed, if abnormal behavior distribution is normal, it is determined that target station area does not exist electricity larceny behavior, if abnormal behavior distribution is abnormal, it is determined that target station area exists electricity larceny behavior, can accurately detect bypass type electricity larceny behavior.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electricity stealing detection, in particular, to an electricity stealing detection method and system based on cluster data of electric energy meters, an electronic device and a computer readable storage medium. BACKGROUND

[0002] Under the background of the gradual popularization of smart grids, electricity stealing detection technology based on electric energy meter data has been widely researched and applied. The current mainstream electricity stealing detection method mainly relies on user electricity consumption behavior modeling, electricity quantity analysis, load prediction comparison, anomaly identification and other means. After discovering electricity consumption anomalies, manual verification is performed. This method has certain recognition ability for overt behaviors such as direct electricity stealing (such as short-circuiting meters and disconnecting neutral lines). However, as a more covert electricity stealing method, bypassing electric energy meter measurement channels and bypassing meter box incoming phase behaviors, the existing electricity stealing detection method is difficult to accurately identify and locate. Moreover, bypassing electricity stealing behaviors often affect multiple downstream users, showing the characteristics of "non-self abnormality and others fluctuation", further increasing the detection difficulty. SUMMARY

[0003] The present application provides an electricity stealing detection method and system based on cluster data of electric energy meters, an electronic device and a computer readable storage medium, which can accurately detect bypassing electricity stealing behaviors.

[0004] According to one aspect of the present application, an electricity stealing detection method based on cluster data of electric energy meters is provided, comprising the following contents:

[0005] Obtaining voltage change data and current change data of an electric energy meter cluster in a target substation;

[0006] Using a preset event detection window to perform attribution judgment of voltage events based on the voltage change data and the current change data of the electric energy meter cluster, and generating an unattributed electric energy meter sequence;

[0007] Performing statistical analysis based on the unattributed electric energy meter sequence, and determining whether there is electricity stealing behavior in the target substation according to the statistical analysis result.

[0008] Further, the process of using a preset event detection window to perform attribution judgment of voltage events based on the voltage change data and the current change data of the electric energy meter cluster, and generating an unattributed electric energy meter sequence comprises the following contents:

[0009] Generating an event sequence based on the voltage change data and the current change data of the electric energy meter cluster. The information contained in each event in the event sequence includes event type, phase, direction, change value, event occurrence time and electric energy meter address. The event type includes voltage events and current events;

[0010] Sliding on the event sequence with a preset event detection window, and making attribution judgment on all voltage events in the event detection window according to a preset rule, taking the electric energy meter with the highest voltage change value among all unattributed voltage events under the same phase as the unattributed electric energy meter;

[0011] After the traversal is completed, the sequence of unattributed electric energy meters is generated.

[0012] Further, the preset rule is:

[0013] If there is a current event in the current event detection window, the voltage event with the same phase and opposite direction of the current event is determined as attributed, and the remaining voltage events are determined as unattributed; if there is no current event in the current event detection window, all voltage events are determined as unattributed.

[0014] Further, in the process of generating the event sequence based on the voltage change data and the current change data of the electric energy meter cluster, the voltage change value and the current change value of each electric energy meter are compared with a preset voltage smooth fluctuation threshold and a current smooth fluctuation threshold respectively, and the voltage change data less than or equal to the voltage smooth fluctuation threshold and the current change data less than or equal to the current smooth fluctuation threshold are deleted.

[0015] Further, the process of statistical analysis based on the sequence of unattributed electric energy meters includes the following contents:

[0016] The sequence of unattributed electric energy meters is counted according to the phase and the number of electric energy meters, the number sequence and the corresponding electric energy meter address sequence of each phase are obtained, and a statistical fitting method is used to make electricity stealing judgment based on the number sequence of each phase to determine whether there is electricity stealing behavior in the target area.

[0017] Further, after it is determined that there is electricity stealing behavior in the target area, the following contents are included:

[0018] The electricity stealing position is determined based on the number sequence of each phase and the corresponding electric energy meter address sequence.

[0019] Further, the process of determining the electricity stealing position based on the number sequence of each phase and the corresponding electric energy meter address sequence includes the following contents:

[0020] The maximum value in the number sequence of each phase is obtained first, and the electric energy meter address corresponding to the maximum value is found from the corresponding electric energy meter address sequence. Then, it is checked whether there is still an electric energy meter with the number of appearances greater than or equal to the maximum value multiplied by a preset coefficient in the number sequence. If not, the electric energy meter address corresponding to the maximum value is determined as the electricity stealing position. If yes, the electric energy meter address corresponding to the number is obtained. If the two electric energy meters are located in the same meter box or under the same branch, the meter box or branch is determined as the electricity stealing position. If the two electric energy meters are not located in the same meter box or under the same branch, both of the electric energy meters are determined as the electricity stealing positions.

[0021] In addition, the application further provides an electricity stealing detection system based on electric energy meter cluster data, comprising:

[0022] A data acquisition module is configured to acquire voltage change data and current change data of an electric energy meter cluster in a target area.

[0023] An attribution judgment module is configured to perform attribution judgment of a voltage event based on the voltage change data and the current change data of the electric energy meter cluster by using a preset event detection window, and generate an unattributed electric energy meter sequence of each phase.

[0024] An electricity stealing behavior detection module is configured to perform statistical analysis based on the unattributed electric energy meter sequence of each phase, and determine whether there is electricity stealing behavior in the target area according to the statistical analysis result.

[0025] In addition, the application further provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the method as described above by calling the computer program stored in the memory.

[0026] In addition, the application further provides a computer readable storage medium for storing a computer program for electricity stealing detection based on electric energy meter cluster data, wherein the computer program executes the steps of the method as described above when running on a computer.

[0027] The application has the following advantages:

[0028] The electricity stealing detection method based on the electric energy meter cluster data provided by the application obtains the voltage change data and the current change data of the electric energy meter cluster under the target transformer area, and then uses the preset event detection window to make the voltage event attribution judgment based on the voltage change data and the current change data of the electric energy meter cluster, so that the abnormal behavior of the voltage mutation without the corresponding current change can be accurately identified, and the unattributed electric energy meter sequence is generated. Then, the unattributed electric energy meter sequence is used for statistical analysis, the distribution characteristics of the abnormal behavior are analyzed, if the abnormal behavior distribution is normal, it is determined that the target transformer area does not exist electricity stealing behavior, if the abnormal behavior distribution is abnormal, it is determined that the target transformer area exists electricity stealing behavior, and the bypass type electricity stealing behavior can be accurately detected.

[0029] In addition, the electricity stealing detection system based on the electric energy meter cluster data provided by the application also has the above advantages.

[0030] In addition to the above described objects, features and advantages, the application has other objects, features and advantages. The application will be further described below with reference to the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0031] The accompanying drawings, which form a part of the present application, are included to provide a further understanding of the application, and are incorporated herein for explanation by reference. In the drawings:

[0032] Figure 1 is a flowchart of the electricity stealing detection method based on the electric energy meter cluster data of the preferred embodiment of the present application;

[0033] Figure 2 is a topological structure diagram of a certain transformer area in the preferred embodiment of the present application;

[0034] Figure 3 is Figure 2 is a schematic diagram of the electricity stealing behavior at the meter a and the meter box M1 in

[0035] Figure 4 is Figure 1 is a sub-flowchart of step S2 in

[0036] Figure 5 is another flowchart of the electricity stealing detection method based on the electric energy meter cluster data of the preferred embodiment of the present application;

[0037] Figure 6 is a module structure diagram of the electricity stealing detection system based on the electric energy meter cluster data of another embodiment of the present application. DETAILED DESCRIPTION

[0038] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0039] With reference to Figure 1 The preferred embodiments of the present application provide a power stealing detection method based on power meter cluster data, comprising the following contents:

[0040] Step S1: Obtain voltage change data and current change data of a power meter cluster under a target substation;

[0041] Step S2: Perform attribution judgment of voltage events based on the voltage change data and the current change data of the power meter cluster by using a preset event detection window, and generate a sequence of unattributed power meters;

[0042] Step S3: Perform statistical analysis based on the sequence of unattributed power meters, and determine whether there is power stealing behavior in the target substation according to the statistical analysis result.

[0043] It can be understood that the power stealing detection method based on power meter cluster data in the present embodiment first obtains voltage change data and current change data of a power meter cluster under a target substation, and then performs attribution judgment of voltage events based on the voltage change data and the current change data of the power meter cluster by using a preset event detection window, which can accurately identify abnormal behavior with voltage mutation but without corresponding current change, and generate a sequence of unattributed power meters. Then, statistical analysis is performed based on the sequence of unattributed power meters, and the distribution characteristics of abnormal behavior are analyzed. If the abnormal behavior is normally distributed, it is determined that there is no power stealing behavior in the target substation. If the abnormal behavior is abnormally distributed, it is determined that there is power stealing behavior in the target substation. The power stealing detection method can accurately detect bypass power stealing behavior.

[0044] In the step S1, the voltage data and the current data of the power meter cluster are obtained by high-frequency sampling, such as second-level sampling, of the power meter cluster under the target substation, so as to obtain the voltage change data and the current change data of the power meter cluster. The voltage change data includes voltage change direction, voltage change time and voltage change size, the current change data includes current change direction, current change time and current change size, and the change direction includes rising or falling. For example, if the voltage value at the next sampling time is greater than the voltage value at the previous sampling time, the voltage change direction is rising, which can be represented by a symbol +. If the voltage value at the next sampling time is less than the voltage value at the previous sampling time, the voltage change direction is falling, which can be represented by a symbol -. In addition, each voltage change or current change is a voltage event or a current event.

[0045] It can be understood that, as Figure 2As shown, a certain target area includes transformer S, branches B1 and B2, meter boxes M1 and M2, and end user meters a, b and c. Taking single-phase as an example, based on Ohm's law and Kirchhoff's voltage law, when the meter node a is connected to a high-power load, the s~a line current increases, which, together with the line impedance, causes the line voltage drop to increase. Since the transformer side voltage is only affected by the primary side, the change in voltage drop will directly affect the electrical data of the meter a on the line, resulting in a decrease in Ua. Correspondingly, when the load under the meter node a is disconnected, Ua rises. The voltage change of the meter node a can be represented as ΔUa. At the same time, the meter b under the same meter box, although its load has not changed, the voltage of the meter b also changes ΔUb due to the increase of the s~M1 current shared with the meter a, and |ΔUa|>|ΔUb|. The farther the electrical distance from the meter a, the smaller the voltage change value. The meter without a common line will not have a voltage change. Therefore, as shown in Figure 3 If the meter a position exists electricity stealing behavior, the electricity stealing position a' will cause the above voltage change to the normal meter b when connecting / disconnecting the load, and the closer the electrical distance from the electricity stealing point a', the greater the voltage change value. The voltage change value of the meter a is the largest, and the meter a will not have a corresponding current change. Similarly, if the meter box M1 position exists electricity stealing behavior, the electricity stealing position M1' will cause the above voltage change to the normal meters a and b when connecting / disconnecting the load, and the closer the electrical distance from the electricity stealing point M1', the greater the voltage change value.

[0046] Therefore, the present application monitors the consistency of voltage and current changes at each meter, and in order to avoid interference caused by voltage changes due to load changes of other meters in the same phase, all meters need to be monitored synchronously. If there is any current change in the t±Δt time period, the voltage change of the meter in the same phase is considered to match the change reason, which is recorded as attribution. Otherwise, if there is no current change in the same phase in this period, the voltage change of the meter is considered to be unable to match the change reason, which is recorded as non-attribution. The meter with the largest voltage change value under the same phase and non-attribution is the electricity stealing position.

[0047] Therefore, in the step S2, the present application presets an event detection window, and then uses the preset event detection window to make attribution judgment of voltage events based on the voltage change data and current change data of the meter cluster, identifies abnormal behaviors with voltage mutation but without corresponding current change, and generates a sequence of non-attribution meters.

[0048] As shown in Figure 4As shown, the process of using the preset event detection window to make the attribution judgment of the voltage event based on the voltage change data and the current change data of the power meter cluster and generating the unattributed power meter sequence includes the following contents:

[0049] Step S21: generating an event sequence based on the voltage change data and the current change data of the power meter cluster, the information contained in each event in the event sequence including event type, phase, direction, change value, event occurrence time and power meter address, wherein the event type includes voltage event and current event;

[0050] Step S22: using the preset event detection window to continuously slide on the event sequence, and making attribution judgment on all voltage events in the event detection window according to the preset rule, taking the power meter with the highest voltage change value among all unattributed voltage events under the same phase as the unattributed power meter;

[0051] Step S23: generating the unattributed power meter sequence after the traversal is completed.

[0052] Specifically, an event sequence is first generated based on the voltage change data and the current change data of the power meter cluster, which can be represented as: There are n events in total, and the information contained in each event includes event type, phase, direction, change value, event occurrence time and power meter address, which can be represented as: Wherein, represents the phase of the power meter, represents the change direction, represents the change value, represents the event type, i.e. voltage event or current event, represents the event occurrence time, represents the power meter address, wherein the event sequence is arranged in ascending order of time.

[0053] Optionally, in order to avoid the influence of random fluctuations of the voltage / current of the transformer area on the voltage / current change data and ensure that the voltage / current change is caused by user load, in the process of generating the event sequence based on the voltage change data and the current change data of the power meter cluster, the voltage change value and the current change value of each power meter are compared with the preset voltage smooth fluctuation threshold value and the current smooth fluctuation threshold value respectively, wherein the two threshold values are set according to the daily electricity consumption of the users in the transformer area, the voltage change data less than or equal to the voltage smooth fluctuation threshold value and the current change data less than or equal to the current smooth fluctuation threshold value are deleted, only the voltage change data and the current change data greater than the preset threshold value are retained, it is determined that the voltage / current change is a change event caused by user load change, the interference of random fluctuations of the voltage / current of the transformer area is excluded, not only the data processing amount in the subsequent process can be reduced, but also the accuracy of the subsequent attribution judgment is improved.

[0054] Then, an event detection window with a fixed time length is set, considering the time asynchronization between different electric energy meters, so the length of the event detection window is set to 6-10 seconds, and the event detection window is continuously slid on the event sequence. Starting from the first event, the current event detection window is , and all voltage events in the window are judged according to a preset rule, wherein the preset rule is: if there is a current event in the current event detection window, the voltage event with the same phase and opposite direction as the current event is judged as having been attributed, and the remaining voltage events are judged as not having been attributed; if there is no current event in the current event detection window, all voltage events are judged as not having been attributed. The attribution judgment results of all voltage events can be obtained, then the electric energy meter with the highest voltage change value among all voltage events in the same phase is taken as the unattributed electric energy meter, and the address of the unattributed electric energy meter is recorded.

[0055] Finally, after the event sequence is traversed, the three-phase unattributed electric energy meter sequence sorted by time can be obtained, that is, the unattributed electric energy meter sequence includes electric energy meters in three phases. The address and phase of each electric energy meter in the three-phase unattributed electric energy meter sequence are included.

[0056] It can be understood that, by constructing an event sequence and setting an event detection window to slide on the event sequence to perform attribution judgment, the present application can accurately identify abnormal behaviors with voltage mutations but without corresponding current changes, and the event detection can be repeated without missing detection, which is beneficial to improve the accuracy of electricity stealing detection.

[0057] In addition, in the step S3, statistical analysis is performed on the unattributed electric energy meter sequence, and according to the statistical analysis result, it can be determined whether the target area exists electricity stealing behavior. If the target area does not exist electricity stealing behavior, the number of unattributed voltage events is low as a whole, there is no obvious frequency center, and the three phases are uniformly and randomly distributed; if electricity stealing behavior occurs at the position of a single-phase electric energy meter, the frequency of unattributed voltage events in the phase where the electric energy meter is located will be significantly increased, and in the same phase, the closer the electrical distance, the higher the frequency, and the electric energy meters in other phases are normal; if electricity stealing occurs at the single-phase position in front of a meter box, multiple same-phase electric energy meters under the meter box will have high-frequency unattributed voltage events, the frequency of unattributed voltage events of same-phase electric energy meters under other meter boxes will also decrease with the increase of the electrical distance from the electricity stealing meter box, and the electric energy meters in other phases are normal.

[0058] The process of statistical analysis based on the unattributed electric energy meter sequence includes the following contents:

[0059] The unattributed electric energy meter sequence is counted according to phases and electric energy meter occurrence times to obtain a time sequence and a corresponding electric energy meter address sequence of each phase, and a statistical fitting method is used to determine whether the target transformer area has electricity stealing behavior based on the time sequence of each phase.

[0060] Specifically, the three-phase unattributed electric energy meter sequence is counted according to phases and electric energy meter occurrence times to obtain a time sequence CntList and a corresponding electric energy meter address sequence AddrList under each phase. Then, a statistical fitting method is used to determine whether the target transformer area has electricity stealing behavior based on the time sequence of each phase.

[0061] Wherein, since strict distribution fitting requires a large sample number, when the number of electric energy meters under a phase of the target transformer area is less than a threshold (for example, 30), a simple Poisson distribution is used for fitting, the mean and variance of the time sequence CntList are calculated, and the variance mean ratio is calculated, which can be expressed as: D = s / λ, wherein D represents the variance mean ratio, s represents the variance, and λ represents the mean. If D ∈ [0.9, 1.1], it means that the data of the time sequence conforms to the Poisson distribution, and can be regarded as normal, otherwise, it is regarded as data anomaly, that is, it is determined that the target transformer area has electricity stealing behavior.

[0062] When the number of electric energy meters under a phase (A / B / C) of the target transformer area is greater than or equal to the threshold (for example, 30), a specific fitting distribution method is used for judgment, which is more accurate. For example, Poisson distribution fitting is first performed, and goodness of fit is used for testing, which can be expressed as: , represents the maximum value in the time sequence, represents the sample number (i.e., the observed frequency) of the actual occurrence times, k represents the theoretical predicted frequency, represents the sample mean, , n represents the total number of samples, represents the probability mass function of the Poisson distribution, represents the sample mean, and the goodness of fit and the degree of freedom are obtained by looking up the table p value: wherein Z represents the number of non-zero categories, m represents the number of model estimation parameters, and the Poisson distribution is 1, represents the chi-square statistic calculated according to the actual observed value and the theoretical expected value , represents the right tail probability of the chi-square distribution, p represents the probability. If , it is determined that it is not significantly different from the Poisson distribution, and it can be considered as a normal state, i.e., it is determined that the target transformer area does not exist electricity stealing behavior, and if , it is determined that it is significantly deviated from the Poisson distribution, which indicates that there is abnormal aggregation, i.e., it is determined that the target transformer area is suspected to exist electricity stealing behavior. Then, if it is determined that the target transformer area is suspected to exist electricity stealing behavior, the power-law distribution and the exponential distribution are used for fitting, and the power-law distribution coefficient and the exponential distribution coefficient are calculated, and if there is or , it is determined that the number sequence is abnormal, i.e., it is determined that the target transformer area exists electricity stealing behavior. The fitting calculation process of the power-law distribution and the exponential distribution belongs to the prior art, and will not be described here.

[0063] Optionally, as shown in Figure 5 , the electricity stealing detection based on the electric energy meter cluster data further includes the following content after it is determined that the target transformer area exists electricity stealing behavior:

[0064] Step S4: determining the electricity stealing position based on the number sequence of each phase and the corresponding electric energy meter address sequence.

[0065] Specifically, the maximum value in the number sequence of each phase is obtained, and the electric energy meter address corresponding to the maximum value is found from the corresponding electric energy meter address sequence. Then, it is determined whether there is an electric energy meter whose number of appearances is greater than or equal to the maximum value multiplied by a preset coefficient (for example, 0.9) in the number sequence. If not, it is determined that the electric energy meter address corresponding to the maximum value is the electricity stealing position. If yes, the electric energy meter address corresponding to the number of appearances is obtained. If the two electric energy meters are located in the same meter box or the same branch, it is determined that the meter box or the branch is the electricity stealing position. If the two electric energy meters are not located in the same meter box or the same branch, it is determined that both of the electric energy meters are the electricity stealing positions.

[0066] For example, it is assumed that there are tables 1 to 15 in a certain transformer area, and the number sequence of the A phase is [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 10], which belongs to a typical non-Poisson distribution. The maximum value Cnt max=10 and its corresponding electric energy meter 15, then, it is found that there is no number greater than or equal to 10x0.9 in the number sequence, and it is determined that the electric energy meter 15 is the electric energy meter at which the electricity stealing behavior occurs. If the number sequence of the A-phase of the electric energy meter 15 is [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 9, 10], the electric energy meter corresponding to the number 9 is the electric energy meter 14. At this time, if only the electric energy meter 15 is the electric energy meter at which the electricity stealing behavior occurs, based on the principle that the frequency of the position far away from the electricity stealing position is lower, even if the electric energy meter 14 is adjacent to the electric energy meter 15, the frequency of the electric energy meter 14 will not exceed the frequency of the electric energy meter 15 multiplied by the preset coefficient, that is, the frequency of the electric energy meter 14 will not exceed 10x0.9=9, that is, the frequency of 9 times of the electric energy meter 14 is not caused by the electricity stealing behavior of the electric energy meter 15. Once the frequency of the electric energy meter 14 exceeds 9 times, it means that the electric energy meter 14 is also the electric energy meter at which the electricity stealing behavior occurs, or the frequency of the electric energy meter 14 and the electric energy meter 15 is simultaneously abnormally high due to the electricity stealing behavior at the upper aggregation position (meter box or branch) of the electric energy meter 14 and the electric energy meter 15. At this time, it is necessary to analyze the topological structure again. If the electric energy meter 14 and the electric energy meter 15 are located in the same meter box or the same branch, it is determined that the A-phase of the meter box or the branch is the electricity stealing position. If the electric energy meter 14 and the electric energy meter 15 are not located in the same meter box or the same branch, it is determined that the electric energy meter 14 and the electric energy meter 15 are both the electricity stealing positions. In addition, the preset coefficient can also be 0.8, 0.85, 0.95, etc., and can be flexibly set according to the detection accuracy. In addition, the electricity stealing position detection principle of the other phases is the same as that of the A-phase, and will not be described here.

[0067] It can be understood that, by analyzing the number sequence of each phase and the corresponding electric energy meter address sequence, based on the principle that the frequency of the electricity stealing position is the highest and the frequency of the position far away from the electricity stealing position is lower, the electricity stealing position can be accurately detected.

[0068] In addition, as shown in FIG. 1, Figure 6 Another embodiment of the present application also provides an electricity stealing detection system based on electric energy meter cluster data, which preferably adopts the electricity stealing detection method based on electric energy meter cluster data as described above, and comprises:

[0069] A data acquisition module is configured to acquire voltage change data and current change data of an electric energy meter cluster in a target area;

[0070] An attribution judgment module is configured to perform attribution judgment of a voltage event based on the voltage change data and the current change data of the electric energy meter cluster by using a preset event detection window, and generate an unattributed electric energy meter sequence of each phase;

[0071] An electricity stealing behavior detection module is configured to perform statistical analysis based on the unattributed electric energy meter sequence of each phase, and determine whether the target area has electricity stealing behavior according to the statistical analysis result.

[0072] It can be understood that the electricity stealing detection system based on the cluster data of the electric energy meter in the embodiment can acquire the voltage change data and the current change data of the cluster of electric energy meters under the target transformer area, and then perform the attribution judgment of the voltage event based on the voltage change data and the current change data of the cluster of electric energy meters by using the preset event detection window, so as to accurately identify the abnormal behavior of the existence of voltage mutation without corresponding current change, and generate the unattributed electric energy meter sequence. Then, the unattributed electric energy meter sequence is subjected to statistical analysis, the distribution characteristics of the abnormal behavior are analyzed, if the abnormal behavior is normally distributed, it is determined that the target transformer area does not exist electricity stealing behavior, if the abnormal behavior is abnormally distributed, it is determined that the target transformer area exists electricity stealing behavior, and the bypass electricity stealing behavior can be accurately detected.

[0073] In addition, the electricity stealing detection system based on the cluster data of the electric energy meter further comprises:

[0074] The electricity stealing position detection module is configured to determine the electricity stealing position based on the number sequence of each phase and the corresponding electric energy meter address sequence.

[0075] It can be understood that each module of the system embodiment corresponds to each step of the method embodiment, and therefore the specific working principle of each module will not be described here again, and the corresponding reference to each step of the method embodiment can be made.

[0076] In addition, another embodiment of the present application further provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the method by calling the computer program stored in the memory.

[0077] In addition, another embodiment of the present application further provides a computer readable storage medium for storing a computer program for detecting electricity stealing based on the cluster data of the electric energy meter, wherein the computer program performs the steps of the method when running on a computer.

[0078] The computer readable storage medium can be a machine-readable storage medium, including but not limited to diskette, floppy disk, hard disk, global positioning system, read-only memory, random access memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, flash memory, compact disc read-only memory, tape, cassette, cassette tape, magnetic tape, punch cards, paper tape, any other physical medium with patterns of holes, any other medium that can be used to store information suitable for use with a computer, or any suitable combination of the foregoing. The computer program product can also be a transmission medium that carries or communicates program code in the form of instructions or data arranged to be transferred, used, or processed by a machine, such as a computer, a processor, or an embedded processor, for example. The transmission medium can be any medium that can be used to provide propagation of information, including but not limited to electronic, electromagnetic, optical, or any other suitable propagation medium. The transmission medium can take the form of a propagating signal, such as a digital or an analog communication signal, or any other suitable type of signal. The transmission medium can also take the form of a computer readable medium, such as a compact disc, a tape, a cassette, a cassette tape, a magnetic tape, punch cards, paper tape, any other physical medium with patterns of holes, any other medium that can be used to store information suitable for use with a computer, or any suitable combination of the foregoing.

[0079] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, apparatus, or computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage devices, etc.) embodying computer readable program code. Embodiments of the present application are also directed to computer program products comprising computer readable program code embodied on one or more computer readable storage media.

[0080] The present application is described in reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 The means for performing the function specified by one or more of the flowchart or block diagram blocks. Figure 1 The means for performing the function specified by one or more of the flowchart or block diagram blocks.

[0081] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0082] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0083] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0084] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0085] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A power stealing detection method based on cluster data of electric energy meters, characterized in that, Includes the following: Acquire voltage and current change data of the electricity meter cluster under the target distribution area; Using a preset event detection window, the attribution of voltage events is determined based on voltage and current change data of the energy meter cluster, and a sequence of unattributed energy meters is generated. Statistical analysis was performed based on unattributed electricity meter sequences, and the results of the statistical analysis were used to determine whether there was electricity theft in the target area. The process of statistical analysis based on unattributed energy meter sequences includes the following: The unattributed electricity meter sequence is statistically analyzed according to phase and the number of times the electricity meter appears, to obtain the frequency sequence of each phase and the corresponding electricity meter address sequence. Then, a statistical fitting method is used to judge electricity theft based on the frequency sequence of each phase to determine whether there is electricity theft in the target area.

2. The power theft detection method based on cluster data of electric energy meters according to claim 1, characterized in that, The process of using a preset event detection window to determine the cause of voltage events based on voltage and current change data of the electricity meter cluster, and generating an unattributed electricity meter sequence, includes the following: Event sequences are generated based on voltage and current change data from the electricity meter cluster. Each event in the event sequence contains information including event type, phase, direction, change value, event occurrence time, and electricity meter address. The event types include voltage events and current events. The system continuously slides the preset event detection window across the event sequence and performs attribution judgment on all voltage events within the event detection window according to preset rules. The energy meter with the highest voltage change value among all unattributed voltage events under the same phase is identified as the unattributed energy meter. After the traversal is complete, a sequence of unattributed energy meters is generated. 3.The electricity stealing detection method based on the cluster data of electric energy meters according to claim 2, characterized in that, The preset rule is as follows: If a current event exists in the current event detection window, voltage events that are in the same phase but opposite in direction to the current event are determined to be attributed, and the remaining voltage events are determined to be unattributed; if no current event exists in the current event detection window, all voltage events are determined to be unattributed.

4. The electricity theft detection method based on electricity meter cluster data as described in claim 2, characterized in that, In the process of generating event sequences based on voltage and current change data from a cluster of electricity meters, the voltage and current change values ​​of each electricity meter are first compared with preset voltage smoothing fluctuation thresholds and current smoothing fluctuation thresholds, respectively. Voltage change data that is less than or equal to the voltage smoothing fluctuation threshold and current change data that is less than or equal to the current smoothing fluctuation threshold are then deleted.

5. The electricity theft detection method based on electricity meter cluster data as described in claim 1, characterized in that, After confirming that electricity theft has occurred in the target transformer area, the following content is also included: The location of electricity theft is determined based on the sequence of times for each phase and the corresponding electricity meter address sequence.

6. The electricity theft detection method based on electricity meter cluster data as described in claim 5, characterized in that, The process of determining the location of electricity theft based on the frequency sequence of each phase and the corresponding electricity meter address sequence includes the following: First, obtain the maximum value in the count sequence for each phase, and find the electricity meter address corresponding to the maximum value from the corresponding electricity meter address sequence. Then, check if there is another electricity meter in the count sequence whose count value is greater than or equal to the maximum value multiplied by a preset coefficient. If not, determine that the electricity meter address corresponding to the maximum value is the electricity theft location. If it exists, obtain the electricity meter address corresponding to the count value. If the two electricity meters are located in the same meter box or under the same branch, determine that the meter box or branch is the electricity theft location. If the two electricity meters are not located in the same meter box or under the same branch, determine that both electricity meter locations are electricity theft locations.

7. A system for detecting electricity theft based on electricity meter cluster data, characterized in that, include: The data acquisition module is used to acquire voltage and current change data of the electricity meter cluster under the target distribution area; The attribution judgment module is used to perform attribution judgment on voltage events based on voltage change data and current change data of the energy meter cluster using a preset event detection window, and generate an unattributed energy meter sequence for each phase. The electricity theft detection module is used to perform statistical analysis based on the unattributed energy meter sequence for each phase, and to determine whether there is electricity theft in the target area based on the statistical analysis results. The process of statistical analysis based on unattributed energy meter sequences is as follows: The unattributed electricity meter sequence is statistically analyzed according to phase and the number of times the electricity meter appears, to obtain the frequency sequence of each phase and the corresponding electricity meter address sequence. Then, a statistical fitting method is used to judge electricity theft based on the frequency sequence of each phase to determine whether there is electricity theft in the target area.

8. An electronic device, characterized in that, The method includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

9. A computer-readable storage medium for storing a computer program for detecting electricity theft based on electricity meter cluster data, characterized in that, The computer program, when run on a computer, performs the steps of the method as described in any one of claims 1 to 6.

Images