Data-driven power supply area and household relation identification method and system

Abstract

The invention relates to the technical field of power grid management, in particular to a data-driven power supply area and household relation identification method and system. The method comprises the following steps: acquiring current signals of each phase circuit on each pole tower and each access point in each monitoring period in a power supply area, transient current values of each phase circuit on each pole tower and installed capacity of each access point; calculating the harmonic influence degree of each phase circuit at each pole tower and each access point in each monitoring period; obtaining an evaluation score and an electricity stealing characterization value of each phase circuit on each tower in each monitoring period; and obtaining a discrimination coefficient of each to-be-detected line in the current monitoring period, carrying out electricity stealing detection on the to-be-detected lines, and identifying a platform user relationship of the power supply platform area. According to the invention, the electricity stealing behavior on each to-be-detected line in the power supply area can be accurately detected, and the identification accuracy of the intelligent area identification instrument on the user relationship is improved.

Description

Technical Field

[0001] This application relates to the technical field of power grid management, and particularly to a data-driven method and system for identifying the relationship between substations and households in a power supply area. Background Art

[0002] The relationship between substations and households in a power supply area is the basis for realizing efficient power supply management and accurate billing. With the continuous expansion of the power grid scale, greater challenges are posed to the management of the relationship between substations and households. Due to the uneven development of the power industry, in areas such as the urban-rural fringe and rural areas, there are problems such as intricate low-voltage power supply lines, overlapping adjacent power supply areas, and difficulty in dividing the scope of power supply areas.

[0003] However, hooking electricity theft can bypass the electricity meter and steal electricity directly from the transmission line, causing changes in the current path and electrical parameters, resulting in errors in electricity theft detection through the electricity meter. Existing technologies usually use intelligent substation identification devices based on power line carrier communication to transmit specific signals on the transmission line to identify the relationship between substations and households. Due to the low accuracy of electricity theft detection on the transmission line, the signals transmitted on the transmission line are inaccurate, which in turn interferes with the accurate identification of the relationship between substations and households by the intelligent substation identification device. Summary of the Invention

[0004] To solve the above technical problems, a data-driven method and system for identifying the relationship between substations and households in a power supply area are provided to solve the existing problems.

[0005] The solution of this application to solve the technical problems is to provide a data-driven method and system for identifying the relationship between substations and households in a power supply area, including the following steps:

[0006] In a first aspect, an embodiment of this application provides a data-driven method for identifying the relationship between substations and households in a power supply area, the method including the following steps:

[0007] Obtain the current signals and transient current values of each phase circuit on each pole under each monitoring period in the power supply area, and the current signals of each phase circuit at each access point and the installed capacity at each access point under each monitoring period when new energy is connected to the grid;

[0008] Calculate the harmonic influence degrees of each phase circuit at each pole and each access point under each monitoring period respectively through the proportion of harmonic components in the frequency domain of the current signals of each phase circuit at each pole and each access point under each monitoring period, and the deviation of the current signal waveform.

[0009] Analyze the changes in the harmonic influence of each phase circuit at all access points within the neighborhood of each tower in each monitoring period, the number of access points and the installed capacity, and combine the harmonic influence of each phase circuit on each tower to obtain the evaluation score of each phase circuit on each tower in each monitoring period through a multi-criteria decision algorithm;

[0010] The transmission line between two connected pole towers is recorded as the line to be tested; the power theft characterization value of each phase circuit in each line to be tested in each monitoring period is determined by combining the evaluation score with the fluctuation difference of the transient current value of each phase circuit between the pole towers at both ends of each line to be tested in each monitoring period;

[0011] Based on the differences in the electricity theft characterization values ​​of all phase circuits in each line to be tested in multiple monitoring cycles before the current monitoring cycle, and the differences in the current signals of all phase circuits, the discrimination coefficient of each line to be tested in the current monitoring cycle is obtained, and the electricity theft detection is performed on the line to be tested to identify the station-user relationship in the power supply area.

[0012] Preferably, each pole tower and each access point is recorded as each node, and the proportion is measured by calculating the total harmonic distortion, specifically:

[0013] Each monitoring cycle is divided into multiple time periods; the current signal of each phase circuit at each node in each time period is analyzed in the frequency domain to obtain a spectrum diagram;

[0014] The frequency component corresponding to 50 Hz in the spectrum diagram is recorded as the fundamental wave component; all other frequency components that are integer multiples of the fundamental wave component in the spectrum diagram are recorded as harmonic components;

[0015] The total harmonic distortion is calculated based on the amplitudes of all harmonic components and the amplitude of the fundamental component in the spectrum diagram.

[0016] Preferably, the calculation process of the harmonic influence degree is:

[0017] Obtaining a current signal when the transmission line is operating normally, and recording it as a standard current signal; calculating the difference between the current signal of each phase circuit at each node in each time period and the standard current signal, and recording it as the current distortion;

[0018] The harmonic influence degree is the average value of the product of the total harmonic distortion and the current distortion degree of each phase circuit at each node in all time periods within each monitoring cycle.

[0019] Preferably, obtaining the evaluation score of each phase circuit on each tower in each monitoring period includes:

[0020] The area where multiple poles connected to any pole are located is recorded as the interconnection range;

[0021] Taking the average value of the harmonic influence of all access points of each phase circuit in each monitoring period within the interconnection range as the harmonic deterioration coefficient of each phase circuit on any tower in each monitoring period;

[0022] Counting the number of all access points within the interconnection range and the total value of the installed capacity of all access points;

[0023] The harmonic influence degree, the harmonic deterioration coefficient, the quantity, and the total value are combined into a characteristic vector;

[0024] A multi-criteria decision algorithm is used to comprehensively evaluate the characteristic vectors of all towers of each phase circuit in each monitoring period, and an evaluation score of each phase circuit on each tower in each monitoring period is obtained.

[0025] Preferably, the step of determining the power theft characterization value of each phase circuit in each circuit to be tested in each monitoring cycle includes:

[0026] The difference of the transient current value of the same phase circuit between the two towers at both ends of each line to be tested in each monitoring cycle is recorded as the transient current mutation amount;

[0027] Calculating the loss calibration amount according to the evaluation scores of the same phase circuits on the two towers at both ends of each line to be tested in each monitoring cycle;

[0028] Calculating the relative change rate between the transient current mutation amount and the loss calibration amount;

[0029] If the transient current mutation amount is less than the loss calibration amount, the electricity theft characterization value is the difference between the preset value and the relative change rate; otherwise, the electricity theft characterization value is the sum of the preset value and the relative change rate.

[0030] Preferably, the calculation process of the loss calibration amount is:

[0031] The average of the evaluation scores of the same phase circuit between the two towers at both ends of each line to be tested in each monitoring period is recorded as the current loss increment;

[0032] The adjustment magnification of the preset loss value is set according to the current loss increment, and the preset loss value is adjusted according to the adjustment magnification to obtain the loss calibration amount of each circuit in each circuit to be tested under each monitoring cycle.

[0033] Preferably, obtaining the discrimination coefficient of each line to be tested in the current monitoring period includes:

[0034] The average of the power theft characterization values ​​of all phase circuits of each line to be tested in multiple monitoring cycles before the current monitoring cycle is used as the three-phase power theft assessment value of each line to be tested in the current monitoring cycle;

[0035] Analyze the correlation change characteristics of the difference situation between the current signals of different-phase circuits on each line to be measured in multiple monitoring cycles before the current monitoring cycle and the difference situation of the electricity theft characterization value, and calculate the single-phase electricity theft evaluation value of each line to be measured in the current monitoring cycle;

[0036] Take the normalization result of the sum of the single-phase electricity theft evaluation value and the three-phase electricity theft evaluation value as the discrimination coefficient of each line to be measured in the current monitoring cycle.

[0037] Preferably, the calculation method of the single-phase electricity theft evaluation value is as follows:

[0038] Calculate the current imbalance degree of the current signals of the three-phase circuits in each line to be measured in each monitoring cycle;

[0039] Calculate the mean value of the difference between the maximum electricity theft characterization value and the other two electricity theft characterization values in all phase circuits of each line to be measured in each monitoring cycle, which is denoted as the relative difference amount;

[0040] Respectively, form an imbalance sequence and an electricity theft difference sequence with the current imbalance degree and the relative difference amount of each line to be measured in multiple monitoring cycles before the current monitoring cycle; calculate the correlation degree between the imbalance sequence and the electricity theft difference sequence;

[0041] The single-phase electricity theft evaluation value is the result of positive mapping of the correlation degree.

[0042] Preferably, the electricity theft detection for the line to be measured includes: if the discrimination coefficient is greater than the preset threshold, there is an electricity theft behavior on the corresponding line to be measured in the power supply substation area; otherwise, there is no electricity theft behavior on the corresponding line to be measured in the power supply substation area.

[0043] In a second aspect, an embodiment of the present application further provides a data-driven power supply substation area household relationship identification system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the above-mentioned data-driven power supply substation area household relationship identification method.

[0044] The present application has at least the following beneficial effects:

[0045] The present application calculates the harmonic influence of each phase circuit at each tower and each access point in each monitoring period by analyzing the harmonic components in the current signal of each phase circuit at each tower and each access point. The beneficial effect is that it takes into account the significant influence of harmonics in the current signal on the current, thereby reflecting the degree of current loss on the transmission line; the evaluation score of each phase circuit on each tower in each monitoring period is obtained, and the beneficial effect is that it takes into account the influence of each tower on the access point when the new energy is connected to the grid, so that the current loss of the line to be tested caused by harmonics can be considered in the subsequent calibration of the actual current loss in the line to be tested between the two towers, so as to dynamically obtain the loss calibration amount; secondly, by comparing the difference in transient current values ​​between the two towers at both ends of the line to be tested and the difference in loss calibration amount, the power theft characterization value of each phase circuit in each line to be tested in each monitoring period is determined, and the beneficial effect is that by comparing the difference in actual current loss on the line to be tested with the difference in current loss on the line to be tested, the power theft characterization value of each phase circuit in the line to be tested can be determined. The current loss on the corresponding line to be tested is caused by the phenomenon of electricity theft due to hooking or normal line loss; further, the discrimination coefficient of each line to be tested in the current monitoring period is obtained, the electricity theft detection is carried out on the line to be tested, and the station-household relationship in the power supply substation is identified. The beneficial effect is that by analyzing the average level of the electricity theft characterization values ​​between different phase circuits, the possibility of three-phase hooking electricity theft on the line to be tested is evaluated, and the possibility of single-phase hooking electricity theft on the line to be tested is evaluated through the imbalance of current signals between different phase circuits and the difference in the electricity theft characterization values. Through comprehensive evaluation, the discrimination coefficient is obtained to accurately judge whether the line to be tested has hooked electricity theft, and the electricity theft behavior of the line can be actively detected, thereby improving the accuracy of electricity theft detection on each line to be tested in the power supply substation, avoiding the interference of hooking electricity theft on the identification of the intelligent substation identification instrument, which is conducive to improving the accuracy of the intelligent substation identification instrument in identifying the station-household relationship and reducing the misjudgment and false alarm of the intelligent substation identification instrument in complex power supply substations. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The following is a further detailed description of a data-driven power supply area and user relationship identification method of the present application in conjunction with the accompanying drawings.

[0047] Figure 1 A flowchart of the steps of a data-driven method for identifying the relationship between power supply areas and users provided in an embodiment of the present application;

[0048] Figure 2 A flowchart of the steps of a method for obtaining the harmonic influence of each phase circuit on each tower in each monitoring period provided in an embodiment of the present application;

[0049] Figure 3 A flowchart of the steps of a method for obtaining the discrimination coefficient of each line to be tested in the current monitoring cycle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the following further details a data-driven method and system for identifying the relationship between substations and households in a power supply area in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0052] Please refer to Figure 1 , which shows a flowchart of the steps of a data-driven method for identifying the relationship between substations and households in a power supply area provided by an embodiment of the present application. The method includes the following steps:

[0053] Step 1, obtain the current signals and transient current values of each phase circuit on each pole under each monitoring period in the power supply area, as well as the current signals of each phase circuit at each access point and the installed capacity at each access point when new energy is connected to the grid under each monitoring period.

[0054] For the convenience of management, power grid users are managed by substation area. The identification of the relationship between substations and households is the basis for realizing marketing lean management, reducing power consumption and losses, and is also a prerequisite for detecting electricity theft. To ensure the accuracy of line loss calculation, the power department needs to regularly check the substation area information of users. Due to the modification of user wiring or line transformation for load balancing distribution, the recorded attribution relationship between the user's incoming line end and the concentrator is inaccurate, which seriously affects substation area management and line loss assessment. Therefore, it is very important to effectively identify the relationship between substations and households without power interruption. Currently, the main methods for identifying the relationship between substations and households are manual identification and using dedicated substation area identification devices. The identification of the relationship between substations and households usually needs to be achieved by analyzing electrical parameters such as current and voltage. If there is a hooking electricity theft behavior, it will cause abnormalities in data such as current and voltage, thus affecting the accuracy of the identification of the relationship between substations and households. Therefore, before using a dedicated substation area identification device, such as an intelligent substation area identifier, to identify the relationship between substations and households, it is necessary to detect the hooking electricity theft in the power supply area.

[0055] Deploy intelligent acquisition terminals on each pole in the power supply area to collect the current signals of the three-phase circuits on each pole;

[0056] It should be noted that the three-phase four-wire system mode is usually adopted in the distribution network. The three-phase circuits respectively refer to the A-phase circuit, the B-phase circuit, and the C-phase circuit. Therefore, the current signals of each phase circuit are obtained.

[0057] Secondly, due to the grid connection process of renewable energy sources such as solar energy and wind energy, the power supply penetration rate of new energy in the power supply substation area is continuously increasing, resulting in harmonics in the current of each phase circuit on each pole tower. Therefore, when new energy is grid-connected, intelligent acquisition terminals are deployed at each access point corresponding to the grid connection in the power supply substation area to obtain the current signals of each phase circuit at each access point.

[0058] In this embodiment, the acquisition frequency of the current signal is 12.8 kHz, and a 15-minute time period is used as a monitoring cycle. As other implementation methods, the implementer can set it according to the actual situation.

[0059] Therefore, the current signals of the three-phase circuits on each pole tower under each monitoring cycle, and the current signals of the three-phase circuits at each access point are obtained;

[0060] Furthermore, through the intelligent acquisition terminal, it is collected once every other monitoring cycle to obtain the transient current values of the three-phase circuits on each pole tower under each monitoring cycle;

[0061] In this embodiment, the transient current value refers to a specific current that appears at the moment of a fault, generally with a short duration and a very high oscillation frequency.

[0062] Secondly, the installed capacity of each access point is obtained;

[0063] It should be noted that the installed capacity refers to the maximum power that the new energy generator set can output under rated operating conditions, that is, the rated power, and the rated power can be queried through the production specifications of the generator set equipment.

[0064] So far, the current signals and transient current values of each phase circuit on each pole tower under each monitoring cycle, the current signals of each phase circuit at each access point, and the installed capacity at each access point are obtained.

[0065] Step 2: Calculate the harmonic influence degrees of each phase circuit on each pole tower and each access point under each monitoring cycle respectively through the proportion of the harmonic components in the frequency domain and the deviation of the current signal waveform of each phase circuit on each pole tower and each access point under each monitoring cycle.

[0066] According to Kirchhoff's current law, the sum of the injected currents of each pole tower in the power supply substation area is equal to the sum of the outflow currents. When power theft by hooking occurs in the transmission line between two pole towers, it is equivalent to adding an additional branch between the two pole towers. The appearance of the new branch will have a significant impact on the current distribution in the original transmission line, causing the current path to change, resulting in the shunting of the current flowing through the original transmission line, and causing a significant difference in the transient current values between the two pole towers.

[0067] Secondly, in the power grid, due to factors such as reactance and resistance in the transmission line, there will be a certain power loss. In the prior art, the preset loss value is directly used as the current loss value of the transmission line. However, the operating state of the power grid in the actual power supply substation area is dynamically changing, with a large number of nonlinear loads and new energy power sources. The preset loss value does not consider the influence of current harmonics on the transmission line loss, making it unable to adapt to the dynamic changes of the power grid and easily resulting in misdetection and missed detection when detecting electricity theft behavior; moreover, during the process of electric energy transmission in the transmission line, when the alternating current flows through the transmission line, the high-frequency components of the harmonics in the current will cause a large skin effect in the transmission conductor, thereby increasing the resistance of the transmission line and resulting in an increase in the actual current loss value of the transmission line.

[0068] Based on the above analysis, by analyzing the harmonic components in the current signals of each phase circuit at each tower and each access point in each monitoring period, the harmonic influence degree is calculated.

[0069] Furthermore, the step flowchart of the method for obtaining the harmonic influence degree of each phase circuit on each tower in each monitoring period provided by the embodiment of the present application is as Figure 2 shown.

[0070] First, analyze the harmonic content of the current signal, specifically:

[0071] Divide each monitoring period into multiple time periods;

[0072] In this embodiment, each monitoring period is divided into 30 time periods, that is, the time length of each monitoring period is 15 min, and the current signal with a time length of 30 s is recorded as one time period.

[0073] Perform frequency-domain analysis on the current signals of each phase circuit on each tower in each time period to obtain a spectrogram;

[0074] In this embodiment, fast Fourier transform is used for frequency-domain analysis to obtain a spectrogram. Among them, fast Fourier transform is a well-known technology and will not be elaborated here.

[0075] Record the frequency component corresponding to 50 Hz in the spectrogram as the fundamental wave component;

[0076] It should be noted that in the working frequency of the domestic power grid, the fundamental wave frequency is 50 Hz. Therefore, the frequency component corresponding to 50 Hz in the spectrogram is the fundamental wave component.

[0077] Record all the remaining frequency components that are integer multiples of the fundamental wave component in the spectrogram as each harmonic component;

[0078] Based on the amplitudes of all harmonic components and the amplitude of the fundamental wave component in the spectrogram, calculate the total harmonic distortion;

[0079] It should be noted that the calculation of total harmonic distortion (THD) is a well-known technology and will not be elaborated here. Secondly, the larger the total harmonic distortion, the greater the content of high-frequency harmonic components in the current of each phase circuit on each tower at each time period, indicating a relatively large actual current loss value of the phase circuit on the tower.

[0080] Secondly, the harmonics of each phase circuit on each tower will cause waveform distortion of the current in the time domain. The greater the degree of waveform distortion, the greater the harm to the power grid caused by the harmonics. Therefore, the analysis of the waveform change of the current signal is specifically as follows:

[0081] Obtain the current signal during the normal operation of the transmission line, denoted as the standard current signal;

[0082] Calculate the difference between the current signal of each phase circuit on each tower at each time period and the standard current signal, denoted as the current distortion degree;

[0083] In this embodiment, calculate the DTW distance between the current signal of each phase circuit on each tower at each time period and the standard current signal, denoted as the current distortion degree. As other implementation manners, implementers can adopt other methods, such as Euclidean distance, Mahalanobis distance, etc. to measure the difference. This embodiment does not make special restrictions on this.

[0084] Take the mean value of the product of the total harmonic distortion and the current distortion degree of each phase circuit on each tower during all time periods in each monitoring cycle as the harmonic influence degree of each phase circuit on each tower in each monitoring cycle;

[0085] For the current signal of each phase circuit at each access point in each monitoring cycle, adopt the same method as the harmonic influence degree of each phase circuit on each tower in each monitoring cycle to calculate the harmonic influence degree of each phase circuit at each access point in each monitoring cycle.

[0086] It should be noted that the larger the current distortion degree, the greater the difference between the waveform of the current and the standard current, the greater the obtained harmonic influence degree, indicating that the influence of the harmonics on the current is more significant and can cause a greater actual current loss of the transmission line.

[0087] So far, the harmonic influence degrees of each phase circuit of each tower and each access point in each monitoring cycle are obtained.

[0088] Step 3: Analyze the changes in the harmonic influence of each phase circuit at all access points within the neighborhood of each tower in each monitoring period, the number of access points and the installed capacity, and combine the harmonic influence of each phase circuit on each tower to obtain the evaluation score of each phase circuit on each tower in each monitoring period through a multi-criteria decision algorithm; determine the power theft characterization value of each phase circuit in each line to be tested in each monitoring period through the fluctuation difference of the transient current value of each phase circuit between the towers at both ends of each line to be tested in each monitoring period and the evaluation score.

[0089] Furthermore, when new energy is connected to the grid, harmonics will be superimposed, which will deteriorate the power quality of the grid. Moreover, the larger the installed capacity of new energy connected to the grid, the more severe the impact on the grid. Therefore, based on the harmonic impact of each phase circuit at each access point in each monitoring cycle, as well as the number of access points and installed capacity, the current loss increment is obtained, which is:

[0090] Taking any pole tower as the center, the area where multiple pole towers connected to it are located is recorded as the interconnection range;

[0091] Taking the average value of the harmonic influence of all access points of each phase circuit in each monitoring period within the interconnection range as the harmonic deterioration coefficient of each phase circuit on any tower in each monitoring period;

[0092] In this embodiment, the area where the three pole towers connected to any of the pole towers are located is recorded as the interconnection range. As other implementation methods, the implementer can set it according to the actual situation.

[0093] Counting the number of all access points within the interconnection range and the total value of the installed capacity of all access points;

[0094] The harmonic influence degree, the harmonic deterioration coefficient, the quantity and the total value of each phase circuit on any tower in each monitoring period are combined into a characteristic vector;

[0095] A multi-criteria decision algorithm is used to comprehensively evaluate the characteristic vectors of all towers of each phase circuit in each monitoring period to obtain an evaluation score of each phase circuit on each tower in each monitoring period;

[0096] In this embodiment, the Topsis algorithm is used for comprehensive evaluation, wherein the Topsis algorithm is a well-known technology and will not be described in detail here. As other implementation methods, implementers can adopt other methods of the existing technology, such as the AHP hierarchical analysis method, etc. This embodiment does not impose any special restrictions on this.

[0097] The transmission line between two adjacent transmission towers is denoted as the line to be measured; the mean value of the evaluation scores of the same-phase circuit on the two transmission towers at both ends of each line to be measured in each monitoring period is used as the current loss increment of each phase circuit in each line to be measured in each monitoring period.

[0098] It should be noted that the larger the evaluation score, the greater the impact of the harmonic component in the corresponding-phase circuit on the power quality of the tower, resulting in a greater loss of current on the transmission line of the power grid. Therefore, the current loss increment can reflect the current loss of each phase circuit on the line to be measured in the power grid.

[0099] Furthermore, based on the current loss increment, the current loss of each line to be measured is calibrated, specifically as follows:

[0100] Set the adjustment ratio of the preset loss value according to the current loss increment, and adjust the preset loss value according to the adjustment ratio to obtain the loss calibration amount of each circuit in each line to be measured in each monitoring period.

[0101] In this embodiment, the calculation method of the loss calibration amount of each phase circuit in each line to be measured in each monitoring period is as follows:

[0102] P n,m,k =(1 + θ n,m,k )×P0

[0103] Wherein, P n,m,k is the loss calibration amount of the k-phase circuit in the nth line to be measured in the mth monitoring period, θ n,m,k is the current loss increment of the k-phase circuit in the nth line to be measured in the mth monitoring period, and P0 is the preset loss value.

[0104] In this embodiment, the preset loss value is 10A. As other implementation manners, the implementer can set it according to the line loss value set by the power supply enterprise for each transmission line.

[0105] It should be noted that the greater the current loss increment caused by current harmonics in the power grid, the more serious the actual current loss of the line to be measured.

[0106] The difference in the transient current values of the same-phase circuit between the two transmission towers at both ends of each line to be measured in each monitoring period is denoted as the transient current mutation amount.

[0107] In this embodiment, the absolute value of the difference in the transient current values of the same-phase circuit between the two transmission towers at both ends of each line to be measured in each monitoring period is denoted as the transient current mutation amount.

[0108] Calculate the relative change rate between the transient current mutation amount and the loss calibration amount.

[0109] It should be noted that the calculation of the relative change rate is a well-known technology and will not be elaborated here. In this embodiment, the calculation formula of the relative change rate is as follows: where, Δδ n,m,k is the relative change rate of the k-phase circuit in the nth line to be measured in the mth monitoring period, P n,m,k is the loss calibration amount of the k-phase circuit in the nth line to be measured in the mth monitoring period, and ΔI n,m,k is the sudden change amount of the transient current of the k-phase circuit in the nth line to be measured in the mth monitoring period.

[0110] If the sudden change amount of the transient current is less than the loss calibration amount, the electricity theft characterization value is the difference between the preset value and the relative change rate; otherwise, the electricity theft characterization value is the sum of the preset value and the relative change rate.

[0111] In this embodiment, the value of the preset value is 1. As other implementation manners, the implementer can set it according to the actual situation.

[0112] In this embodiment, the calculation formula of the electricity theft characterization value of each phase circuit in each line to be measured in each monitoring period is as follows:

[0113]

[0114] where, R n,m,k is the electricity theft characterization value of the k-phase circuit in the nth line to be measured in the mth monitoring period, and Δδ n,m,k is the relative change rate of the k-phase circuit in the nth line to be measured in the mth monitoring period, and P n,m,k is the loss calibration amount of the k-phase circuit in the nth line to be measured in the mth monitoring period, and ΔI n,m,k is the sudden change amount of the transient current of the k-phase circuit in the nth line to be measured in the mth monitoring period.

[0115] It should be noted that if the sudden change amount of the transient current is larger than the loss calibration amount, according to Kirchhoff's current law, it indicates that there is a higher possibility of hooking electricity theft in the line to be measured, and the electricity theft characterization value is larger; otherwise, it indicates that the sudden change amount of the transient current is caused by normal line loss, and the possibility of hooking electricity theft in the line to be measured is lower, and the electricity theft characterization value is smaller.

[0116] Thus, the electricity theft characterization values of each phase circuit in each line to be measured in each monitoring period are obtained.

[0117] Step 4: Based on the difference situation of the electricity theft characterization values of all phase circuits in each line to be measured in multiple monitoring periods before the current monitoring period, and the difference situation of the current signals of all phase circuits, obtain the discrimination coefficient of each line to be measured in the current monitoring period, perform electricity theft detection on the lines to be measured, and identify the relationship between the stations and households in the power supply substation area.

[0118] Further, the flowchart of the method for obtaining the discrimination coefficient of each line to be measured in the current monitoring period provided by the embodiments of the present application is as Figure 3 shown.

[0119] Hook electricity theft can be divided into three-phase hook electricity theft and single-phase hook electricity theft. Three-phase hook electricity theft refers to the electricity thief illegally connecting wires from a three-phase power supply circuit and using the three-phase power supply to supply power to power equipment or electrical appliances with a relatively large power; single-phase hook electricity theft refers to the electricity thief illegally connecting a live wire and a neutral wire from the power supply line. The electricity theft load of three-phase hook electricity theft is relatively large, and the electricity theft behavior can be detected through the electricity theft characterization value. However, the electricity theft load of single-phase hook electricity theft is relatively small, and the electricity theft characterization value has a low accuracy in identifying single-phase hook electricity theft with a small-scale load.

[0120] Based on the above analysis, based on the electricity theft characterization value, calculate the three-phase electricity theft evaluation value, specifically:

[0121] Take the average value of the electricity theft characterization values of all phase circuits of each line to be measured in multiple monitoring periods before the current monitoring period as the three-phase electricity theft evaluation value of each line to be measured in the current monitoring period;

[0122] In this embodiment, take the average value of the electricity theft characterization values of all phase circuits of each line to be measured in all monitoring periods within 24 hours before the current monitoring period as the three-phase electricity theft evaluation value of each line to be measured in the current monitoring period; that is, the number of all monitoring periods within 24 hours is 96. As other implementation manners, the implementer can set it by himself according to the actual situation.

[0123] It should be noted that the larger the three-phase electricity theft evaluation value is, the greater the possibility that the line to be measured has three-phase hook electricity theft, and the more accurately the three-phase hook electricity theft phenomenon can be identified.

[0124] Secondly, single-phase hook electricity theft means that the electricity thief only illegally connects a single phase line from the power supply line, which is more likely to cause the current imbalance of the power supply line, and the electricity theft characterization value of the phase circuit corresponding to the hook electricity theft is larger than that of other normal phase circuits. Therefore, calculate the single-phase electricity theft evaluation value, specifically:

[0125] Calculate the current imbalance degree of the current signals of the three-phase circuits in each line to be measured in each monitoring period;

[0126] It should be noted that the calculation method of current unbalance degree is a well-known technology and will not be elaborated here. In this embodiment, the average current method is adopted to calculate the current unbalance degree, specifically: calculate the average value of the current signals of each phase circuit in each line to be measured under each monitoring period, which is denoted as the current value; the average value of the current values of all phase circuits in each line to be measured under each monitoring period is denoted as the average current, and the absolute value of the difference between the current value of each phase circuit in each line to be measured under each monitoring period and the average current is selected. The ratio of the maximum value of the absolute value among all phase circuits in each line to be measured under each monitoring period to the average current is used as the current unbalance degree of each line to be measured under each monitoring period.

[0127] Calculate the average value of the difference between the maximum power theft characterization value and the other two power theft characterization values among all phase circuits of each line to be measured under each monitoring period, which is denoted as the relative difference amount;

[0128] In this example, calculate the average value of the absolute value of the difference between the maximum power theft characterization value and the other two power theft characterization values among all phase circuits of each line to be measured under each monitoring period, which is denoted as the relative difference amount.

[0129] It should be noted that for the convenience of understanding, the power theft characterization values of the A-phase, B-phase, and C-phase circuits of the nth line to be measured under the mth monitoring period are respectively R n,m,A 、R n,m,B 、R n,m,C . Select the maximum value among R n,m,A 、R n,m,B 、R n,m,C . Assume that the R n,m,A of the A-phase circuit is the largest, then the relative difference amount is

[0130] Respectively, the current unbalance degrees and the relative difference amounts of each line to be measured under multiple monitoring periods before the current monitoring period are formed into an unbalance sequence and a power theft difference sequence;

[0131] In this embodiment, the current unbalance degrees and the relative difference amounts of each line to be measured under all monitoring periods within 24 hours before the current monitoring period are respectively formed into an unbalance sequence and a power theft difference sequence.

[0132] Calculate the correlation degree between the unbalance sequence and the power theft difference sequence;

[0133] In this embodiment, the correlation degree is measured by calculating the Pearson correlation coefficient between the unbalance sequence and the power theft difference sequence. As other implementation manners, implementers can adopt other methods of the prior art, such as the Spearman correlation coefficient, etc. This embodiment does not make special restrictions on this.

[0134] The result of positive mapping of the correlation degree is used as the single-phase electricity theft evaluation value of each line to be measured in the current monitoring period;

[0135] In this embodiment, the process of positive mapping is: the sum of the correlation degree and the value 1 is used as the single-phase electricity theft evaluation value of each line to be measured in the current monitoring period;

[0136] In this embodiment, since the value range of the correlation degree is [-1, 1], by adding the value 1, the value range of the single-phase electricity theft evaluation value is in [0, 2]. The larger the obtained single-phase electricity theft evaluation value, the more likely the current imbalance is caused by single-phase hooking electricity theft, and the more accurately the single-phase hooking electricity theft phenomenon can be identified.

[0137] Furthermore, based on the single-phase electricity theft evaluation value and the three-phase electricity theft evaluation value, a discrimination coefficient is calculated to evaluate the hooking electricity theft of the line to be measured. Specifically:

[0138] The normalized result of the sum of the single-phase electricity theft evaluation value and the three-phase electricity theft evaluation value is used as the discrimination coefficient of each line to be measured in the current monitoring period;

[0139] In this embodiment, the sigmoid function is used for normalization processing. The sigmoid function is a well-known technology and will not be elaborated here. As other implementation manners, implementers can adopt other methods of the existing technology, such as the tanh function, etc. This embodiment does not make special restrictions on this.

[0140] If the discrimination coefficient is greater than the preset threshold, there is an electricity theft behavior on the corresponding line to be measured in the power supply substation area. On the contrary, there is no electricity theft behavior on the corresponding line to be measured in the power supply substation area.

[0141] In this embodiment, the preset threshold value is taken as 0.8. As other implementation manners, implementers can set it by themselves according to the actual situation.

[0142] Arrange grid staff to carry detection tools to check the lines with electricity theft behaviors. After all the lines with electricity theft behaviors have been checked, start the intelligent substation area identifier to obtain the relationship between the substation area and the households, improve the accuracy of the intelligent substation area identifier in identifying the relationship between the substation area and the households, so as to avoid the interference of hooking electricity theft on the intelligent substation area identifier.

[0143] Based on the same inventive concept as the above method, the embodiment of the present application also provides a data-driven power supply substation area and household relationship identification system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above methods for a data-driven power supply substation area and household relationship identification method.

[0144] It should be understood that although Figure 1 each step in the flowchart of Figure 1 is shown in sequence according to the indication of the arrow, these steps are not necessarily executed in sequence according to the order indicated by the arrow. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover,

[0145] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0146] The above-described embodiments merely represent several implementation manners of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation to the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can still be made. Therefore, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application all belong to the protection scope of the technical solution of the present application.

Claims

1. A data-driven method for identifying the relationship between power supply stations and users, characterized in that: The method comprises the following steps: Obtain the current signal and transient current value of each phase circuit on each tower in each monitoring period within the power supply area, as well as the current signal of each phase circuit at each access point and the installed capacity at each access point in each monitoring period when new energy is connected to the grid; Calculate the harmonic influence of each phase circuit at each tower and each access point in each monitoring period respectively by the proportion of harmonic components of the current signal of each phase circuit at each tower and each access point in the frequency domain and the deviation of the current signal waveform in each monitoring period; Analyze the changes in the harmonic influence of each phase circuit at all access points within the neighborhood of each tower in each monitoring period, the number of access points and the installed capacity, and combine the harmonic influence of each phase circuit on each tower to obtain the evaluation score of each phase circuit on each tower in each monitoring period through a multi-criteria decision algorithm; The transmission line between two connected pole towers is recorded as the line to be tested; the power theft characterization value of each phase circuit in each line to be tested in each monitoring period is determined by combining the evaluation score with the fluctuation difference of the transient current value of each phase circuit between the pole towers at both ends of each line to be tested in each monitoring period; Based on the differences in the electricity theft characterization values ​​of all phase circuits in each line to be tested in multiple monitoring cycles before the current monitoring cycle, and the differences in the current signals of all phase circuits, the discrimination coefficient of each line to be tested in the current monitoring cycle is obtained, and the electricity theft detection is performed on the line to be tested to identify the station-user relationship in the power supply area.

2. A data-driven method for identifying the relationship between power supply areas and users as claimed in claim 1, characterized in that: Each tower and each access point is recorded as a node, and the proportion is measured by calculating the total harmonic distortion, specifically: Each monitoring cycle is divided into multiple time periods; the current signal of each phase circuit at each node in each time period is analyzed in the frequency domain to obtain a spectrum diagram; The frequency component corresponding to 50 Hz in the spectrum diagram is recorded as the fundamental wave component; all other frequency components that are integer multiples of the fundamental wave component in the spectrum diagram are recorded as harmonic components; The total harmonic distortion is calculated based on the amplitudes of all harmonic components and the amplitude of the fundamental component in the spectrum diagram.

3. A data-driven method for identifying the relationship between power supply areas and users as claimed in claim 2, characterized in that: The calculation process of the harmonic influence is: Obtaining a current signal when the transmission line is operating normally, and recording it as a standard current signal; calculating the difference between the current signal of each phase circuit at each node in each time period and the standard current signal, and recording it as the current distortion; The harmonic influence degree is the average value of the product of the total harmonic distortion and the current distortion degree of each phase circuit at each node in all time periods within each monitoring cycle.

4. A data-driven method for identifying the relationship between power supply areas and users as claimed in claim 1, characterized in that: The evaluation score of each phase circuit on each tower in each monitoring period is obtained, including: The area where multiple poles connected to any pole are located is recorded as the interconnection range; Taking the average value of the harmonic influence of all access points of each phase circuit in each monitoring period within the interconnection range as the harmonic deterioration coefficient of each phase circuit on any tower in each monitoring period; Counting the number of all access points within the interconnection range and the total value of the installed capacity of all access points; The harmonic influence degree, the harmonic deterioration coefficient, the quantity, and the total value are combined into a characteristic vector; A multi-criteria decision algorithm is used to comprehensively evaluate the characteristic vectors of all towers of each phase circuit in each monitoring period, and an evaluation score of each phase circuit on each tower in each monitoring period is obtained.

5. A data-driven method for identifying the relationship between power supply areas and users as claimed in claim 1, characterized in that: The step of determining the power theft characterization value of each phase circuit in each circuit to be tested in each monitoring cycle includes: The difference of the transient current value of the same phase circuit between the two towers at both ends of each line to be tested in each monitoring cycle is recorded as the transient current mutation amount; Calculating the loss calibration amount according to the evaluation scores of the same phase circuits on the two towers at both ends of each line to be tested in each monitoring cycle; Calculating the relative change rate between the transient current mutation amount and the loss calibration amount; If the transient current mutation amount is less than the loss calibration amount, the electricity theft characterization value is the difference between the preset value and the relative change rate; otherwise, the electricity theft characterization value is the sum of the preset value and the relative change rate.

6. A data-driven method for identifying the relationship between power supply areas and users as claimed in claim 5, characterized in that: The calculation process of the loss calibration amount is: The average of the evaluation scores of the same phase circuit between the two towers at both ends of each line to be tested in each monitoring period is recorded as the current loss increment; The adjustment magnification of the preset loss value is set according to the current loss increment, and the preset loss value is adjusted according to the adjustment magnification to obtain the loss calibration amount of each circuit in each circuit to be tested under each monitoring cycle.

7. A data-driven method for identifying the relationship between power supply areas and users as claimed in claim 1, characterized in that: The step of obtaining the discrimination coefficient of each line to be tested in the current monitoring cycle includes: The average of the power theft characterization values ​​of all phase circuits of each line to be tested in multiple monitoring cycles before the current monitoring cycle is used as the three-phase power theft assessment value of each line to be tested in the current monitoring cycle; Analyze the relevant change characteristics of the difference between the current signals of different phase circuits on each line to be tested in multiple monitoring cycles before the current monitoring cycle and the difference between the power theft characterization values ​​thereof, and calculate the single-phase power theft assessment value of each line to be tested in the current monitoring cycle; A normalized result of the sum of the single-phase electricity theft evaluation value and the three-phase electricity theft evaluation value is used as a discrimination coefficient of each line to be tested in the current monitoring cycle.

8. A data-driven method for identifying the relationship between power supply areas and users as claimed in claim 7, characterized in that: The calculation method of the single-phase electricity theft assessment value is: Calculating the current imbalance of the current signal of the three-phase circuit in each circuit to be tested in each monitoring cycle; Calculate the average value of the difference between the maximum power theft characteristic value and the other two power theft characteristic values ​​in all phase circuits of each line to be tested in each monitoring cycle, and record it as the relative difference; The current unbalance degree and the relative difference of each line to be tested in multiple monitoring cycles before the current monitoring cycle are respectively combined into an unbalance sequence and a power theft difference sequence; and the correlation between the unbalance sequence and the power theft difference sequence is calculated; The single-phase electricity theft evaluation value is a result of positive mapping of the correlation degree.

9. A data-driven method for identifying the relationship between power supply areas and users as claimed in claim 1, characterized in that: The power theft detection on the line to be tested includes: if the discrimination coefficient is greater than a preset threshold, power theft exists on the corresponding line to be tested in the power supply area; otherwise, power theft does not exist on the corresponding line to be tested in the power supply area.

10. A data-driven power supply area and user relationship identification system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of a data-driven power supply area and user relationship identification method as described in any one of claims 1-9 are implemented.

Images