Method and device for determining low-voltage user with abnormal line loss in transformer area

Abstract

The invention discloses a method and a device for determining a low-voltage user with abnormal line loss in a transformer area. The method comprises the following steps: acquiring line loss data of a to-be-identified transformer area; determining an abnormal degree value of the to-be-identified transformer area according to the line loss data; determining a target transformer area in the to-be-identified transformer areas according to the abnormal degree value; acquiring line loss related data of subordinate users of each target station area; according to the line loss related data, determining a first time sequence of the power loss of each target transformer area in unit time and a second time sequence of the power consumption of each subordinate user in unit time; according to the first time sequence and the second time sequence, determining a correlation coefficient between the power consumption of the subordinate user and the power loss of the target transformer area; and determining line loss abnormal users in each target transformer area according to the correlation coefficient. According to the method and the device, the technical problem that various abnormities cannot be comprehensively covered and abnormal users cannot be accurately identified due to the fact that a unified and representative transformer area line loss checking method does not exist in related technologies is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of line loss investigation in a transformer area, and in particular to a method and device for determining low-voltage users with abnormal line loss in a transformer area. Background Art

[0002] The existing methods for troubleshooting users with abnormal line losses in substations are mainly divided into three categories. The first category is the traditional manual one-by-one troubleshooting method: based on the power loss in each substation and the power consumption of its subordinate users, basic files, meter reading and collection, load cutting, business changes, production operations and other issues are eliminated one by one to determine the abnormal users of line losses in the substation and correct the line loss rate. The second category is the power trend, current voltage and load power consumption analysis method, which can identify significant anomalies such as low-voltage user meter codes, file errors, power loss and voltage loss. The third category is a new statistical method for hidden anomalies such as power theft, such as the correlation coefficient method, the K value method and the linear regression method. When the user's load pattern (i.e., power consumption) changes suddenly and is roughly consistent with the fluctuation trend of the line loss in the substation (i.e., the correlation coefficient, K value or regression coefficient is high), there is a suspicion of power theft or metering failure.

[0003] The first method mentioned above is a manual one-by-one troubleshooting mode. For the substations with abnormal line loss reports, the archives, meter reading data, metering management and production operations in the metering automation and marketing systems are checked one by one, and the cause of the abnormal line loss is found before the response is completed. Although this method can check the specific cause of the abnormality in detail, its disadvantage is that it requires switching between multiple platforms and functional modules, which is cumbersome and time-consuming, resulting in low efficiency in line loss analysis. In addition, due to the limited number of substation managers, it is difficult to effectively manage and troubleshoot a large number of line loss substations and users.

[0004] The second method mentioned above, namely, the power trend analysis method, the current and voltage analysis method, and the overload power analysis method, can detect significant anomalies such as the meter code of the substation and the low-voltage user, file errors, power loss and voltage loss by observing the fluctuation of the power supply and output and the current and voltage of the substation, but in most cases, only obvious anomalies can be analyzed, and it is difficult to accurately detect hidden anomalies such as power theft. The third method mentioned above, namely, the correlation coefficient method, the K value method and the linear regression method.

[0005] The above three methods are currently the more representative and important methods for identifying electricity theft problems and troubleshooting abnormal low-voltage users. By selecting the daily power consumption of users and the daily power loss of the substation on a certain date, calculating the correlation coefficient and K value, or establishing a linear regression model, low-voltage users that are highly correlated with the daily power loss of the substation can be finally identified.

[0006] However, in actual application, it was found that these methods may result in missed or wrong judgments, and may miss the identification of real problem low-voltage users, or mistakenly identify low-voltage users with high correlation coefficients, K values ​​or regression coefficients but who are actually not abnormal, resulting in insufficient troubleshooting accuracy.

[0007] Therefore, there is currently no unified and representative method for troubleshooting line losses in substations. There are problems such as being unable to fully cover various abnormalities and accurately identify abnormal users, and the process is cumbersome, time-consuming, and lacks accuracy.

[0008] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0009] The embodiments of the present invention provide a method and device for determining low-voltage users with abnormal line loss in a substation, so as to at least solve the technical problems in the related art that there is no unified and representative method for troubleshooting line loss in substations, and that it is impossible to comprehensively cover various abnormalities and accurately identify abnormal users.

[0010] According to one aspect of an embodiment of the present invention, a method for determining low-voltage users with abnormal line loss in a substation is provided, comprising: obtaining line loss data of a substation to be identified, wherein the substation to be identified is a substation that needs to be checked for abnormal line loss, wherein the line loss data at least includes the following data of the substation to be identified: power supply, power supply, power loss, line loss rate, data integrity rate, and number of users; determining an abnormality level value of the substation to be identified based on the line loss data; determining a target substation in the substation to be identified based on the abnormality level value, wherein the target substation is the abnormal substation in the substation to be identified Substations whose degree values ​​are greater than the abnormal degree threshold; obtaining line loss related data of subordinate users of each of the target substations, wherein the subordinate users are electricity users within the power supply range of each of the target substations; determining a first time series of power loss of each of the target substations per unit time and a second time series of power consumption of each of the subordinate users per unit time according to the line loss related data; determining a correlation coefficient between the power consumption of the subordinate users and the power loss of the target substation according to the first time series and the second time series; determining users with abnormal line losses in each of the target substations according to the correlation coefficient.

[0011] Optionally, acquiring the line loss data of the to-be-identified substation includes: determining the to-be-identified substation within a predetermined range; and downloading the line loss data of each to-be-identified substation within the unit time through a line loss data downloading program.

[0012] Optionally, determining the abnormality degree value of the substation to be identified based on the line loss data includes: obtaining evaluation information of each substation abnormality evaluation index in the line loss data; comparing the numerical values ​​of each substation abnormality evaluation index in the line loss data with the evaluation intervals in the evaluation information to obtain evaluation scores of each substation abnormality evaluation index; and determining the abnormality degree value of the substation to be identified based on the evaluation scores.

[0013] Optionally, determining a target substation in the to-be-identified substation according to the abnormality degree value comprises: comparing each of the abnormality degree values ​​with the abnormality degree threshold value to obtain a first comparison result; and determining the substation corresponding to the abnormality degree value greater than the abnormality degree threshold value among the abnormality degree values ​​in the first comparison result as the target substation.

[0014] Optionally, determining the correlation coefficient between the power consumption of the subordinate user and the power loss of the target area according to the first time series and the second time series includes: determining the correlation coefficient between the power consumption of the subordinate user and the power loss of the target area according to the first time series and the second time series by a predetermined formula, wherein the predetermined formula is: r represents the correlation coefficient, n represents the number of days for which the line loss related data is statistically analyzed, and X i represents the power consumption of the subordinate user on the i-th day, represents the average power consumption of the subordinate users within the statistical days, S X represents the standard deviation of the power consumption of the subordinate users within the statistical days, Y i represents the power loss of the target area on the i-th day, represents the average value of the target area's power loss within the statistical days, S Y It represents the standard deviation of the power loss in the target area within the statistical days.

[0015] Optionally, determining the abnormal line loss users in each of the target substations according to the correlation coefficients includes: performing hypothesis tests on each of the correlation coefficients to obtain significance values ​​of each of the correlation coefficients; determining the risk value of each of the subordinate users in each of the target substations according to each of the significance values, each of the correlation coefficients and the standard deviation of the power consumption of each of the subordinate users within the unit time; and determining the abnormal line loss users in each of the target substations according to the risk value.

[0016] Optionally, the risk value of each subordinate user in each target substation is determined according to each significance value, each correlation coefficient and the standard deviation of electricity consumption of each subordinate user within the unit time, including: determining the evaluation information of each significance value, each correlation coefficient and each standard deviation of electricity consumption; comparing each significance value, each correlation coefficient and each standard deviation of electricity consumption with the evaluation interval in the evaluation information, respectively, to obtain the evaluation score of each subordinate user under the significance value, the correlation coefficient and the standard deviation of electricity consumption; and determining the risk value of each subordinate user according to the evaluation score.

[0017] According to another aspect of an embodiment of the present invention, a device for determining low-voltage users with abnormal line loss in a substation is also provided, comprising: a first acquisition module, used to acquire line loss data of a substation to be identified, wherein the substation to be identified is a substation that needs to be checked for abnormal line loss, wherein the line loss data at least includes the following data of the substation to be identified: power supply, power supply, power loss, line loss rate, data integrity rate and number of users; a first determination module, used to determine the abnormality degree value of the substation to be identified based on the line loss data; a second determination module, used to determine a target substation in the substation to be identified based on the abnormality degree value, wherein the target substation is a substation with a large abnormality degree value in the substation to be identified a substation that is below the abnormality level threshold; a second acquisition module, used to acquire line loss related data of subordinate users of each of the target substations, wherein the subordinate users are electricity users within the power supply range of each of the target substations; a third determination module, used to determine a first time series of power loss of each of the target substations per unit time and a second time series of power consumption of each of the subordinate users per unit time according to the line loss related data; a fourth determination module, used to determine a correlation coefficient between the power consumption of the subordinate users and the power loss of the target substation according to the first time series and the second time series; a fifth determination module, used to determine users with abnormal line losses in each of the target substations according to the correlation coefficient.

[0018] Optionally, the first acquisition module includes: a first determination unit, used to determine the to-be-identified substations within a predetermined range; and a downloading unit, used to download the line loss data of each to-be-identified substation within the unit time through a line loss data downloading program.

[0019] Optionally, the first determination module includes: a first acquisition unit, used to obtain evaluation information of each substation abnormality evaluation index in the line loss data; a first comparison unit, used to compare the numerical values ​​of the various substation abnormality evaluation indicators in the line loss data with the evaluation intervals in the evaluation information to obtain evaluation scores of the various substation abnormality evaluation indicators; and a second determination unit, used to determine the abnormality degree value of the substation to be identified based on the evaluation scores.

[0020] Optionally, the second determination module includes: a second comparison unit, used to compare each of the abnormality degree values ​​with the abnormality degree threshold to obtain a first comparison result; a third determination unit, used to determine the station area corresponding to the abnormality degree value greater than the abnormality degree threshold among each of the abnormality degree values ​​in the first comparison result as the target station area.

[0021] Optionally, the fourth determination module includes: a fourth determination unit, configured to determine the correlation coefficient between the power consumption of the subordinate user and the power loss of the target station area according to the first time series and the second time series through a predetermined formula, wherein the predetermined formula is: r represents the correlation coefficient, n represents the number of days for which the line loss related data is statistically analyzed, and X i represents the power consumption of the subordinate user on the i-th day, represents the average power consumption of the subordinate users within the statistical days, S X represents the standard deviation of the power consumption of the subordinate users within the statistical days, Y i represents the power loss of the target area on the i-th day, represents the average value of the target area's power loss within the statistical days, S Y It represents the standard deviation of the power loss in the target area within the statistical days.

[0022] Optionally, the fifth determination module includes: a hypothesis testing unit, used to perform hypothesis testing on each of the correlation coefficients to obtain a significance value of each of the correlation coefficients; a fifth determination unit, used to determine the risk value of each of the subordinate users in each of the target substations based on each of the significance values, each of the correlation coefficients and the standard deviation of the power consumption of each of the subordinate users per unit time; and a sixth determination unit, used to determine the abnormal line loss users in each of the target substations based on the risk value.

[0023] Optionally, the fifth determination unit includes: a first determination subunit, used to determine the evaluation information of each of the significance values, each of the correlation coefficients and each of the standard deviations of electricity consumption; a first comparison subunit, used to compare each of the significance values, each of the correlation coefficients and each of the standard deviations of electricity consumption with the evaluation intervals in the evaluation information, to obtain the evaluation scores of each of the subordinate users under the significance value, the correlation coefficient and the standard deviation of electricity consumption; and a second determination subunit, used to determine the risk value of each of the subordinate users based on the evaluation scores.

[0024] According to another aspect of the embodiments of the present invention, there is also provided a computer program product, including computer instructions, which, when executed by a processor, perform any one of the above-mentioned methods for determining low-voltage users with abnormal line loss in a transformer area.

[0025] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium comprising a stored program, wherein the program executes any one of the above-mentioned methods for determining low-voltage users with abnormal line loss in a substation area.

[0026] According to another aspect of the embodiments of the present invention, a processor is provided, the processor being used to run a program, wherein when the program is run, any one of the above-mentioned methods for determining low-voltage users with abnormal line loss in a transformer area is executed.

[0027] In an embodiment of the present invention, line loss data of a to-be-identified substation is obtained, wherein the to-be-identified substation is a substation that needs to be checked for abnormal line loss, wherein the line loss data includes at least the following data of the to-be-identified substation: power supply, power supply, power loss, line loss rate, data integrity rate and number of users; the abnormality level value of the to-be-identified substation is determined according to the line loss data; the target substation in the to-be-identified substation is determined according to the abnormality level value, wherein the target substation is a substation in the to-be-identified substation whose abnormality level value is greater than the abnormality level threshold value; line loss related data of subordinate users of each target substation is obtained, wherein the subordinate users are power users within the power supply range of each target substation; a first time series of power loss of each target substation per unit time and a second time series of power consumption of each subordinate user per unit time are determined according to the line loss related data; a correlation coefficient between the power consumption of the subordinate users and the power loss of the target substation is determined according to the first time series and the second time series; and users with abnormal line loss in each target substation are determined according to the correlation coefficient. Through the technical solution provided by the present invention, the purpose of more accurately identifying abnormal line loss users in the substation area and improving the efficiency of abnormal line loss analysis in the substation area is achieved by optimizing the correlation analysis method, constructing an assignment weighted model to evaluate multi-dimensional line loss indicators, and designing a corresponding intelligent diagnosis Python program. It can effectively reduce line losses, improve the operation efficiency of the power grid, save labor costs, and achieve the technical effect of improving the accuracy and efficiency of identifying abnormal line loss users in the substation area, thereby solving the technical problem that there is no unified and representative substation line loss troubleshooting method in the related technology, and there is an inability to comprehensively cover various abnormalities and accurately identify abnormal users. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0029] Figure 1 It is a hardware structure block diagram of a mobile terminal of a method for determining low-voltage users in a transformer area with abnormal line loss according to an embodiment of the present invention;

[0030] Figure 2 is a flow chart of a method for determining low-voltage users with abnormal line loss in a transformer area according to an embodiment of the present invention;

[0031] Figure 3 is a flow chart of an optional method for determining low-voltage users with abnormal line loss in a transformer area according to an embodiment of the present invention;

[0032] Figure 4 2 is a schematic diagram of a device for determining low-voltage users with abnormal line loss in a transformer area according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] As introduced in the background technology, there is no unified and representative method for checking line loss in the relevant technology, and there is a technical problem that it cannot fully cover various abnormalities and accurately identify abnormal users. In view of the above defects, a method and device for determining low-voltage users with abnormal line loss in the area, a computer-readable storage medium, a processor, and a computer program product are provided in the embodiments of the present invention.

[0036] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0037] The method embodiments provided in the embodiments of the present invention can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a method for determining low-voltage users in a transformer area with abnormal line loss according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0038] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for determining users of abnormally low-voltage line loss in the substation area in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] According to an embodiment of the present invention, a method embodiment of a method for determining low-voltage users with abnormal line loss in a substation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] Figure 2 FIG. 4 is a flow chart of a method for determining low-voltage users with abnormal line loss in a transformer area according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0041] Step S202, obtaining line loss data of the to-be-identified substation, wherein the to-be-identified substation is a substation that needs to be checked for abnormal line loss, wherein the line loss data at least includes the following data of the to-be-identified substation: power supply, power supply, power loss, line loss rate, data integrity rate, and number of users.

[0042] It should be noted that the above-mentioned substation to be identified refers to the area in the power system where the electrical equipment to be confirmed is located, that is, the substation where line loss abnormality needs to be checked; the above-mentioned line loss data refers to the data on power loss caused by resistance, inductance, capacitance and other factors when power lines, transformers and other equipment in the power system transmit power.

[0043] Optionally, the line loss data at least includes: power supply, power supply, power loss, line loss rate, data integrity rate and number of users. In addition, it may also include: line length, line loss cost and line loss distribution data.

[0044] It should be noted that the above-mentioned power loss is the power loss in addition to the normal loss of lines, transformers and metering devices.

[0045] Optionally, the main sources of the above-mentioned power loss may include: power theft, metering failure, leakage, equipment overload, low voltage, three-phase imbalance, missing meter reading, etc.

[0046] In the embodiment of the present invention, the power loss of the substation = the power supply - the power supply - the inherent loss of the metering equipment - the power transmission loss, and the substation line loss rate = the power loss of the substation / the power supply of the substation * 100%.

[0047] In this embodiment, the line loss data of the substation that needs to be checked for abnormal line loss can be obtained, which can help analyze the power loss situation of the substation, understand the power consumption and line operation status of the substation, and evaluate the operation status of the power grid equipment.

[0048] Step S204: determining the abnormality level value of the to-be-identified substation according to the line loss data.

[0049] It should be noted that the above-mentioned abnormality degree value is an indicator calculated based on the line loss data, which is used to measure whether the power grid operation in the substation is normal. The higher the abnormality degree value, the more serious the line loss situation in the substation and the more unstable the power grid operation.

[0050] In this embodiment, whether the power usage of the substation is normal can be determined by comparing the line loss rate with the historical data of the substation. That is, whether the power usage of the substation to be identified is normal can be determined based on the line loss data.

[0051] Step S206, determining a target area among the areas to be identified according to the abnormality level value, wherein the target area is an area among the areas to be identified whose abnormality level value is greater than an abnormality level threshold.

[0052] In this embodiment, the areas to be identified whose abnormality values ​​are greater than the abnormality threshold can be determined according to the abnormality values, which can help identify and locate the abnormal areas so that timely measures can be taken for repair and maintenance.

[0053] Step S208, obtaining line loss related data of subordinate users of each target substation, wherein the subordinate users are electricity users within the power supply range of each target substation.

[0054] Optionally, the above-mentioned subordinate users may include various types of electricity users such as residents, enterprises, factories, etc.

[0055] Optionally, the above-mentioned line loss related data may include: power consumption, line length, line loss rate, power factor and other information.

[0056] In this embodiment, line loss related data of power users within the power supply range of each target substation can be obtained, the line loss situation of each substation can be understood, and corresponding measures can be taken to reduce the line loss rate and improve power supply quality and efficiency.

[0057] Step S210, determining a first time series of power loss of each target substation within a unit time and a second time series of power consumption of each subordinate user within a unit time according to line loss related data.

[0058] It should be noted that the above-mentioned unit time can be a specific day, month or continuous time period, and the unit time of the substation and the subordinate users must be consistent. When the unit time of the substation's power loss time series is a certain day, the unit time of the subordinate user's power consumption time series should also be the same day; the above-mentioned first time series can calculate the power loss of each target substation based on the power supply and line loss rate within the unit time; the above-mentioned second time series is the power consumption of each subordinate user within the unit time, which can be obtained through real-time monitoring of meter data or smart meter system. According to the power consumption of each subordinate user, the second time series of the power consumption of each subordinate user within the unit time can be determined.

[0059] In this embodiment, the first time series of power loss in each target substation within a unit time and the second time series of power consumption of each subordinate user within a unit time can be determined. By analyzing the time series data of power loss and user power consumption, the grid dispatch and power supply plan can be optimized.

[0060] Step S212, determining the correlation coefficient between the power consumption of subordinate users and the power loss of the target substation according to the first time series and the second time series.

[0061] It should be noted that the above correlation coefficient is a statistic used to measure the strength of the linear relationship between two variables, and its value range is between -1 and 1. A correlation coefficient of 1 indicates a completely positive correlation, a correlation coefficient of -1 indicates a completely negative correlation, and a correlation coefficient of 0 indicates no linear relationship. The correlation coefficient of the target substation's lost electricity can measure the strength of the linear relationship between the lost electricity and other variables (such as weather, grid load, etc.). If the correlation coefficient is close to 1 or -1, it means that there is a strong linear relationship between the lost electricity and other variables, which can be used to help predict the lost electricity. If the correlation coefficient is close to 0, it means that there is almost no linear relationship between the lost electricity and other variables.

[0062] In this embodiment, by calculating the correlation coefficient between the power consumption of subordinate users and the power loss of the target substation, it is possible to determine whether there is a linear relationship between the two, as well as the strength and direction of the linear relationship.

[0063] Step S214, determining users with abnormal line loss in each target station area according to the correlation coefficient.

[0064] Optionally, abnormal line loss users and meters are users and meters that have a significant impact on the line loss rate of the area due to reasons such as reading and collection, change of household relations, production operation, and metering management in the abnormal line loss area.

[0065] In this embodiment, by analyzing the correlation between each user's electricity usage data and the line loss rate, users with abnormal electricity usage behavior or potential illegal electricity usage behavior can be identified, which can help power companies to promptly discover and solve line loss problems and improve the operating efficiency and stability of the power grid.

[0066] As can be seen from the above, in an embodiment of the present invention, line loss data of the to-be-identified substation is obtained, wherein the to-be-identified substation is the substation that needs to be checked for line loss anomalies, wherein the line loss data at least includes the following data of the to-be-identified substation: power supply, power supply, power loss, line loss rate, data integrity rate and number of users; the abnormality level value of the to-be-identified substation is determined according to the line loss data; the target substation in the to-be-identified substation is determined according to the abnormality level value, wherein the target substation is the substation whose abnormality level value in the to-be-identified substation is greater than the abnormality level threshold value; the line loss related data of the subordinate users of each target substation is obtained, wherein the subordinate users are the power users within the power supply range of each target substation; the number of each target substation per unit time is determined according to the line loss related data The first time series of the loss of electricity in the target substation and the second time series of the electricity consumption of each subordinate user in unit time; determine the correlation coefficient between the electricity consumption of the subordinate users and the loss of electricity in the target substation according to the first time series and the second time series; determine the abnormal line loss users in each target substation according to the correlation coefficient, and achieve the purpose of more accurately identifying abnormal line loss users in the substation and improving the efficiency of abnormal line loss analysis in the substation by optimizing the correlation analysis method, constructing an assignment weighted model for multi-dimensional line loss index evaluation, and designing corresponding intelligent diagnosis Python programs. It can effectively reduce line losses, improve the efficiency of power grid operation, save labor costs, and achieve the technical effect of improving the accuracy and efficiency of identifying abnormal line loss users in the substation.

[0067] The above-mentioned technical solution provided by the embodiment of the present invention solves the technical problems in the related art that there is no unified and representative method for troubleshooting line loss in substations, and that it is impossible to comprehensively cover various abnormalities and accurately identify abnormal users.

[0068] According to the above embodiment of the present invention, obtaining the line loss data of the to-be-identified substation includes: determining the to-be-identified substation within a predetermined range; and downloading the line loss data of each to-be-identified substation in a unit time through a line loss data downloading program.

[0069] In this embodiment, the substations to be identified within a predetermined range can be determined, and the line loss data of each substation to be identified per unit time can be downloaded through the line loss data download program. For example, the Python line loss data download program can be used to automatically and batch download the line loss data of the actual substations per unit time of the metering automation system, that is, to collect and pre-process the substation data to provide an accurate data basis for subsequent processing work.

[0070] Optionally, the above-mentioned line loss data may include: supply in, supply out, power loss and line loss rate, data integrity rate, number of users, etc.

[0071] It should be noted that the substation adopts a full-scale processing method, mainly because this method can ensure that all data in the entire area are processed to avoid missing any data. The full-scale processing method can ensure the integrity and accuracy of the data, avoid data inconsistencies or errors, and can ensure the integrity, accuracy and consistency of the data, improve processing efficiency and ensure data quality.

[0072] According to the above embodiment of the present invention, the abnormality degree value of the substation to be identified is determined based on the line loss data, including: obtaining evaluation information of each substation abnormality evaluation index in the line loss data; comparing the numerical value of each substation abnormality evaluation index in the line loss data with the evaluation interval in the evaluation information to obtain the evaluation score of each substation abnormality evaluation index; determining the abnormality degree value of the substation to be identified based on the evaluation score.

[0073] In this embodiment, a weighted model for assigning abnormal degree of substations can be constructed to conduct a comprehensive assessment of the line loss situation in the substations. That is, the line loss data is imported into the database, and the python substation abnormal level diagnosis program is used to establish an assignment weighted evaluation model based on factors such as the power supply of the substation, line loss rate, data integrity rate and number of users. A variety of algorithms are used to calculate the weight of each factor, and the weight value is determined based on the actual situation. According to the risk value calculated by the evaluation model, the corresponding evaluation standard is formulated, the abnormal degree of the substation is graded, the substation is graded according to the size of the risk value, and the corresponding abnormal substation diagnosis conclusion is formed.

[0074] Table 1 is a comprehensive evaluation table of power substations, which shows the abnormal evaluation indicators and abnormal degree values ​​of the substations:

[0075] Table 1

[0076]

[0077] The embodiment is explained below in conjunction with Table 1. First, the values ​​of various substation abnormality evaluation indicators in the line loss data are collected, and then the evaluation information of each indicator is found. The evaluation level of each indicator is determined based on the comparison between the values ​​of each indicator in the line loss data and the evaluation interval in the evaluation information. The evaluation score of each indicator is obtained based on the evaluation level, and finally the abnormality degree value of the substation to be identified is comprehensively calculated, so as to objectively evaluate the abnormality degree of the substation to be identified.

[0078] According to the above embodiment of the present invention, the target substation in the to-be-identified substation is determined according to the abnormality degree value, including: comparing each abnormality degree value with the abnormality degree threshold value to obtain a first comparison result; and determining the substation corresponding to the abnormality degree value greater than the abnormality degree threshold value among the abnormality degree values ​​in the first comparison result as the target substation.

[0079] In this embodiment, each abnormality degree value can be compared with the abnormality degree threshold to obtain a first comparison result, that is, the collected abnormality degree values ​​are sorted to find the substation with the highest abnormality degree value. The higher the abnormality degree value, the more serious the abnormal situation in the substation; the substation corresponding to the abnormality degree value greater than the abnormality degree threshold in each abnormality degree value in the first comparison result is determined as the target substation, that is, the substation with the highest abnormality degree value is determined as the target substation among the substations to be identified. This substation may have serious problems or faults and needs to be identified and processed as soon as possible.

[0080] As shown in Table 1, the higher the total score, the higher the abnormality level value, and the more serious the abnormal situation in the substation. The abnormality level value is determined by comparing the evaluation score with the abnormality level threshold in the total score.

[0081] According to the above embodiment of the present invention, determining the correlation coefficient between the power consumption of the subordinate user and the power loss of the target area according to the first time series and the second time series includes: determining the correlation coefficient between the power consumption of the subordinate user and the power loss of the target area according to the first time series and the second time series through a predetermined formula, wherein the predetermined formula is: r represents the correlation coefficient, n represents the number of days for which line loss related data are statistically analyzed, and X i represents the power consumption of subordinate users on the i-th day, Indicates the average power consumption of subordinate users within the statistical days, S X Indicates the standard deviation of the electricity consumption of subordinate users within the statistical days, Y i represents the power loss of the target area on the i-th day, It represents the average power loss of the target area within the statistical days, S Y It indicates the standard deviation of the power loss in the target substation within the statistical days.

[0082] Figure 3 FIG. 1 is a flow chart of an optional method for determining low-voltage users with abnormal line loss in a transformer area according to an embodiment of the present invention. Figure 3 As shown, determine the substation where abnormal users need to be identified, use the python line loss data download program to download the line loss related data of users under each substation, check the table code, multiplier information and power consumption of each user per unit time, and calculate the standard deviation of power consumption of each user per unit time, and perform data collection and preprocessing operations on users under the substation.

[0083] It should be noted that the above-mentioned first time series is the time series Y={Y1,Y2,…Yn} of the power loss in the substation per unit time, and the above-mentioned second time series is the time series X={X1,X2,…,Xn} of the power consumption of each subordinate user in the substation per unit time, wherein n is the number of elements in the world sequence, and i=1, 2,…,N.

[0084] In this embodiment, the first time series and the second time series can be used to calculate the time series X of the power consumption of each subordinate user in the substation area within a unit time. i Correlation analysis is performed with Y as the independent variable and the time series Y of power loss in the substation per unit time as the dependent variable, and the correlation coefficient r between the power consumption of each subordinate user and the power loss in the substation is calculated.

[0085] It should be noted that when the absolute value of the correlation coefficient is above 0.7, it is a strong correlation; between 0.3 and 0.7, it is a weak correlation; and below 0.3, there is no correlation. The larger the correlation coefficient, the higher the correlation between the user's electricity consumption and the electricity loss in the substation, that is, the higher the suspicion of user abnormality.

[0086] According to the above embodiment of the present invention, the abnormal line loss users in each target substation are determined based on the correlation coefficient, including: performing hypothesis tests on each correlation coefficient to obtain the significance value of each correlation coefficient; determining the risk value of each subordinate user in each target substation according to each significance value, each correlation coefficient and the standard deviation of the power consumption of each subordinate user per unit time; and determining the abnormal line loss users in each target substation according to the risk value.

[0087] In this embodiment, the key dimensions of user line loss can be determined, a user assignment weighted model can be constructed, and abnormal users can be identified. That is, the significance of the correlation coefficient is judged by the significance value (p-value) obtained by the hypothesis test. In statistical software such as SPSS, the p-value of the correlation coefficient is usually automatically calculated. If the p-value is less than the significance level (generally 0.05), the correlation coefficient is considered to be statistically significant, indicating that there is a significant linear relationship between the two variables. Combining the correlation coefficient, the significance value (p-value) and the standard deviation of the electricity consumption of each user per unit time, an assignment weighted model is constructed. This model will calculate the risk value of each user according to the preset evaluation criteria, thereby realizing the identification of abnormal users.

[0088] It should be noted that the above hypothesis test is a statistical method used to determine whether a hypothesis about a population parameter is valid. In order to ensure that the calculated correlation coefficient is statistically significant, a hypothesis test is required.

[0089] In the above embodiment of the present invention, the risk value of each subordinate user in each target substation is determined according to each significance value, each correlation coefficient and the standard deviation of electricity consumption of each subordinate user per unit time, including: determining the evaluation information of each significance value, each correlation coefficient and each standard deviation of electricity consumption; comparing each significance value, each correlation coefficient and each standard deviation of electricity consumption with the evaluation interval in the evaluation information respectively, to obtain the evaluation score of each subordinate user under the significance value, correlation coefficient and standard deviation of electricity consumption respectively; determining the risk value of each subordinate user according to the evaluation score.

[0090] Table 2 is a table of power evaluation indicators, which shows the abnormal evaluation indicators of the substation area and the user identification conclusions:

[0091] Table 2

[0092]

[0093]

[0094] The embodiment is described below in conjunction with Table 2. According to the size of the significance value, it can be determined whether the data analysis results of each subordinate user are statistically significant. If the p value is less than 0.05, the correlation coefficient is considered to be statistically significant, indicating that there is a significant linear relationship between the two variables. The correlation coefficient can reflect the degree of association between the variables. According to the size of the correlation coefficient, the degree of association between the subordinate users can be evaluated. If the correlation coefficient is close to 1 or -1, it means that the variables are strongly associated with each other and the score is high. If the correlation coefficient is close to 0, it means that the variables are weakly associated with each other and the score is low. The standard deviation of electricity consumption can reflect the degree of fluctuation of electricity consumption. According to the size of the standard deviation, the stability of electricity consumption of each subordinate user can be evaluated. If the standard deviation is small, it means that the fluctuation of electricity consumption is small and the score is high.

[0095] Based on the above evaluation scores, the risk value of each subordinate user can be determined. The higher the risk value, the greater the risk, and corresponding risk management measures need to be taken. By evaluating the significance value, correlation coefficient and standard deviation of electricity consumption, we can have a more comprehensive understanding of the risk situation of each subordinate user and formulate risk management strategies in a targeted manner.

[0096] like Figure 3As shown, the public transformer in the substation collects data and transmits it to the distribution transformer terminal, such as the power supply in the substation and the power supply out of the substation; the distribution transformer terminal collects and pre-processes the data; a weighted model for assigning abnormal values ​​to the substation is constructed based on indicators such as power supply and output, line loss rate, data integrity rate, and number of users; the model is used to grade and evaluate the degree of abnormality in the substation; the public transformer in the substation provides power services to multiple subordinate users in the area, and there is loss during the power transmission process. The power meter measures the power consumption of the users; the substation where the abnormal users need to be identified is determined, and the power meter data of the subordinate users in the substation is collected from the public transformer in the substation; the power meter data of the subordinate users in the substation is obtained, including information such as power consumption and power consumption time; the power meter data is analyzed Collection and preprocessing, including data cleaning, removal of outliers and other operations; sorting out the data of users under the substation area for subsequent analysis; taking the time series of power consumption X of users under the substation area per unit time as the independent variable and the time series Y of power loss in the substation area per unit time as the dependent variable, conduct correlation analysis to determine the correlation between the two; construct an abnormal user assignment weighted model based on the correlation coefficient, significance value and standard deviation of power consumption of each user per unit time; according to the total score calculated by the model, users with a score less than 8 are users to be observed, and users with a score greater than or equal to 8 are abnormal users; conduct on-site verification of the identified abnormal situations to verify the accuracy of the analysis results.

[0097] Normally, when the power consumption of subordinate users in the substation is obviously missing or fluctuates, the trend of power loss in the substation should be coupled with the power consumption trend of subordinate users, showing an obvious correlation. Therefore, through correlation analysis of the time series of power loss in the substation and power consumption of subordinate users per unit time, supplemented by standard deviation analysis, the impact of power consumption of multiple subordinate users on power loss in the substation per unit time can be determined, thereby identifying subordinate users who are significantly correlated with the time series of power loss in the substation, and then the line loss staff conducts on-site analysis and inspection of suspected abnormal users. Compared with the manual investigation method, this method improves the efficiency and accuracy of identifying abnormal line loss users in the substation, reduces the inspection cost, and reduces the workload of line loss staff, thereby achieving more efficient and accurate line loss management.

[0098] It should be noted that the above correlation analysis is a conventional statistical analysis method, which can effectively analyze the correlation between the power loss in the substation and the power consumption of its subordinate users. It can be constructed using SPSS or calculated using Python program.

[0099] Here, the embodiment is described by taking the power loss time series Y of a certain area in July 2023 and the power consumption time series X1, X2...X18 of its 18 subordinate users as an example. A correlation analysis is performed on them by SPSS, and the following results are obtained: 1) The average and standard deviation of the power consumption of the 18 users within 31 days of the month are calculated. Table 3 is a user descriptive statistics table, as shown in Table 3:

[0100] Table 3

[0101]

[0102] The results show that users X2, X9, X10, X11, X12, X13, and X15 have obvious fluctuations in electricity consumption; 2) Calculate the Pearson correlation coefficient between the power loss time series Y of the substation on the 31st of the month and the power consumption time series X1, X2...X18 of the 18 subordinate users, and obtain the significance value p after hypothesis testing. Table 4 is a correlation table of user power loss, as shown in Table 4:

[0103] Table 4

[0104] Loss of power X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14 X15 X16 X17 X18 Pearson correlation Loss of power 1 0.04 -0.499 -0.182 -0.462 -0.279 -0.259 -0.388 -0.255 -0.607 -0.737 -0.135 -0.269 -0.493 -0.266 -0.405 . -0.358 -0.077 X1 0.04 1 0.356 0.213 0.055 -0.175 -0.127 -0.254 0.036 -0.097 -0.039 -0.111 0.434 -0.178 0.382 -0.018 . 0.515 0.186 X2 -0.499 0.356 1 0.099 0.042 0.035 0.122 0.034 0.139 0.023 0.136 -0.262 0.685 0.278 0.331 0.358 . 0.369 0.108 X3 -0.182 0.213 0.099 1 0.521 0.054 0.596 0.248 0.676 0.244 0.309 -0.227 -0.008 -0.072 0.615 -0.215 . 0.485 0.721 X4 -0.462 0.055 0.042 0.521 1 0.216 0.495 0.644 0.551 0.52 0.356 0.04 -0.207 0.227 0.454 0.062 . 0.493 0.396 X5 -0.279 -0.175 0.035 0.054 0.216 1 0.289 0.365 0.173 -0.131 -0.054 -0.271 -0.192 0.06 -0.174 -0.263 . -0.206 -0.101 X6 -0.259 -0.127 0.122 0.596 0.495 0.289 1 0.447 0.925 0.244 0.189 -0.283 -0.223 0.249 0.302 -0.264 . 0.192 0.769 X7 -0.388 -0.254 0.034 0.248 0.644 0.365 0.447 1 0.298 0.323 0.128 -0.11 -0.275 0.363 0.031 0.135 . 0.139 0.07 X8 -0.255 0.036 0.139 0.676 0.551 0.173 0.925 0.298 1 0.235 0.276 -0.296 -0.184 0.082 0.524 -0.197 . 0.414 0.852 X9 -0.607 -0.097 0.023 0.244 0.52 -0.131 0.244 0.323 0.235 1 0.791 0.429 0.154 0.68 0.127 0.21 . 0.221 0.288 X10 -0.737 -0.039 0.136 0.309 0.356 -0.054 0.189 0.128 0.276 0.791 1 0.334 0.197 0.431 0.376 0.337 . 0.365 0.302 X11 -0.135 -0.111 -0.262 -0.227 0.04 -0.271 -0.283 -0.11 -0.296 0.429 0.334 1 -0.056 0.259 -0.161 0.267 . -0.074 -0.117 X12 -0.269 0.434 0.685 -0.008 -0.207 -0.192 -0.223 -0.275 -0.184 0.154 0.197 -0.056 1 0.221 0.142 0.312 . 0.203 -0.013 X13 -0.493 -0.178 0.278 -0.072 0.227 0.06 0.249 0.363 0.082 0.68 0.431 0.259 0.221 1 -0.237 0.237 . -0.131 0.109 X14 -0.266 0.382 0.331 0.615 0.454 -0.174 0.302 0.031 0.524 0.127 0.376 -0.161 0.142 -0.237 1 0.222 . 0.854 0.582 X15 -0.405 -0.018 0.358 -0.215 0.062 -0.263 -0.264 0.135 -0.197 0.21 0.337 0.267 0.312 0.237 0.222 1 . 0.391 -0.289 X16 . . . . . . . . . . . . . . . . 1 . . X17 -0.358 0.515 0.369 0.485 0.493 -0.206 0.192 0.139 0.414 0.221 0.365 -0.074 0.203 -0.131 0.854 0.391 . 1 0.383 X18 -0.077 0.186 0.108 0.721 0.396 -0.101 0.769 0.07 0.852 0.288 0.302 -0.117 -0.013 0.109 0.582 -0.289 . 0.383 1 Sig.(one side) Loss of power . 0.415 0.002 0.164 0.004 0.064 0.08 0.015 0.083 0 0 0.234 0.072 0.002 0.074 0.012 0 0.024 0.341 X1 0.415 . 0.025 0.125 0.385 0.173 0.248 0.084 0.424 0.301 0.417 0.277 0.007 0.169 0.017 0.462 0 0.002 0.158 X2 0.002 0.025 . 0.298 0.411 0.426 0.257 0.427 0.229 0.451 0.234 0.077 0 0.065 0.035 0.024 0 0.021 0.281 X3 0.164 0.125 0.298 . 0.001 0.386 0 0.089 0 0.093 0.045 0.109 0.483 0.35 0 0.123 0 0.003 0 X4 0.004 0.385 0.411 0.001 . 0.122 0.002 0 0.001 0.001 0.025 0.414 0.132 0.109 0.005 0.37 0 0.002 0.014 X5 0.064 0.173 0.426 0.386 0.122 . 0.057 0.022 0.176 0.242 0.386 0.07 0.151 0.375 0.175 0.076 0 0.133 0.294 X6 0.08 0.248 0.257 0 0.002 0.057 . 0.006 0 0.093 0.154 0.061 0.114 0.089 0.05 0.076 0 0.151 0 X7 0.015 0.084 0.427 0.089 0 0.022 0.006 . 0.052 0.038 0.247 0.278 0.067 0.022 0.434 0.235 0 0.228 0.354 X8 0.083 0.424 0.229 0 0.001 0.176 0 0.052 . 0.101 0.067 0.053 0.161 0.331 0.001 0.144 0 0.01 0 X9 0 0.301 0.451 0.093 0.001 0.242 0.093 0.038 0.101 . 0 0.008 0.204 0 0.248 0.128 0 0.116 0.058 X10 0 0.417 0.234 0.045 0.025 0.386 0.154 0.247 0.067 0 . 0.033 0.144 0.008 0.019 0.032 0 0.022 0.049 X11 0.234 0.277 0.077 0.109 0.414 0.07 0.061 0.278 0.053 0.008 0.033 . 0.382 0.079 0.194 0.073 0 0.347 0.266 X12 0.072 0.007 0 0.483 0.132 0.151 0.114 0.067 0.161 0.204 0.144 0.382 . 0.116 0.224 0.044 0 0.137 0.473 X13 0.002 0.169 0.065 0.35 0.109 0.375 0.089 0.022 0.331 0 0.008 0.079 0.116 . 0.099 0.1 0 0.241 0.28 X14 0.074 0.017 0.035 0 0.005 0.175 0.05 0.434 0.001 0.248 0.019 0.194 0.224 0.099 . 0.115 0 0 0 X15 0.012 0.462 0.024 0.123 0.37 0.076 0.076 0.235 0.144 0.128 0.032 0.073 0.044 0.1 0.115 . 0 0.015 0.057 X16 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 . 0 0 X17 0.024 0.002 0.021 0.003 0.002 0.133 0.151 0.228 0.01 0.116 0.022 0.347 0.137 0.241 0 0.015 0 . 0.017 X18 0.341 0.158 0.281 0 0.014 0.294 0 0.354 0 0.058 0.049 0.266 0.473 0.28 0 0.057 0 0.017 .

[0105] The results show that the absolute values ​​of the correlation coefficients of users X9 and X10 are relatively large; the significance values ​​of X9, X10, and X16 meet the standards, and the correlation coefficients are statistically significant; 3) According to the evaluation criteria, a value-assigned weighted model is built to calculate the correlation coefficient, significance value, and standard deviation score, and finally the total score and recognition conclusion are obtained. Table 5 is the correlation analysis result table, as shown in Table 5:

[0106] Table 5

[0107]

[0108]

[0109] The model shows that users X9 and X10 are suspected of abnormal power consumption and line loss and must be investigated; 4) After on-site analysis, the substation had unqualified power loss and line loss rates on 7 days of that month. Users X9 and X10 had obvious abnormal power consumption during the same period. The average daily power consumption of users X9 and X10 was fitted according to their power consumption habits, and it was found that it was consistent with the power loss in the substation. Users X9 and X10 were determined to be users with abnormal line losses in the substation.

[0110] As can be seen from the above, in the embodiment of the present invention, the correlation coefficient method, K value method and linear regression method are combined to focus on the correlation characteristics between the power loss in the substation and the power consumption of users; by analyzing the influencing factors of the substation line loss, the final score is calculated after weighting, and the abnormality of the substation and the user is evaluated; through correlation analysis, the evaluation model is constructed based on the correlation coefficient and significance value of the power loss in the substation per unit time and the power consumption of the subordinate users, and the abnormal line loss users in the substation are identified; a database and Python program are built to complete the automatic download and intelligent diagnosis of the substation line loss data. It comprehensively considers various factors such as the efficiency of line loss analysis, missed judgment and misjudgment of abnormal users, avoids the shortcomings of the insufficient accuracy of the substation line loss investigation method in the traditional method, can more comprehensively evaluate the correlation characteristics of the power loss in the substation and the power consumption of users, effectively identify substations and users with higher abnormalities, and improve the accuracy and efficiency of line loss analysis.

[0111] Among them, the above K value method is based on the correlation coefficient method, selects the lines with large line loss rate fluctuations in the metering system, selects one or more inflection points, respectively queries the suspected user's daily power consumption and line loss power consumption, and calculates the K value. The larger the K value, the greater the suspicion. Here, K value = (inflection point user power consumption / inflection point line loss power consumption) × 100%.

[0112] The above-mentioned assignment weighted evaluation method is to sort the selection indicators according to their importance, assign natural numbers from large to small (that is, assign values ​​in the opposite order of sorting), and finally calculate the total score of the assignment to give a specific evaluation conclusion.

[0113] Therefore, the above technical solution provided by the embodiment of the present invention effectively solves the following problems: 1) The correlation coefficient method and K value method in the original line loss analysis only consider the absolute value of the correlation coefficient. However, the correlation coefficient only indicates the direction and strength of the linear relationship between two variables, but cannot determine whether this relationship is statistically significant; 2) In general, the abnormal classification of the substation is performed according to the size of the line loss rate, and the evaluation dimension is too single; 3) The linear regression model has obvious omissions when identifying abnormal users. This is mainly because the linear regression model usually only contains those independent variables that are considered to have a significant impact on the dependent variable. If the power consumption of some users is considered to have little impact on the power loss in the substation in the model analysis, they may be excluded from the model. In addition, nonlinear relationships or complex interactions between independent variables may also have an adverse effect on the recognition effect of the model; 4) The correlation coefficient method has only a single evaluation criterion, that is, observing whether the correlation coefficient meets the standard, while the linear regression rule builds a significant model and observes the regression coefficient and significance value at the same time.

[0114] At the same time, it has the following beneficial effects: 1) Optimize the correlation coefficient method, introduce the significance value (p-value) to enhance the reliability of the correlation coefficient method, take the significance value (p-value) in the correlation analysis into consideration, optimize the original correlation coefficient method, and by incorporating the significance value (p-value), provide a quantitative measurement standard for the significance of the correlation coefficient, effectively reduce the impact of random factors and sample capacity on the analysis results, and thus reduce the risk of misinterpretation of data; 2) Use the assignment weighted model to evaluate multi-dimensional line loss indicators to achieve more refined abnormal classification of substations and identification of abnormal users, expand the evaluation dimension, and take user power consumption, line loss rate, data integrity rate and number of users into consideration at the same time, set the corresponding assignment weighted standard, which will help to prioritize the substations with large power consumption and obvious line loss abnormalities. Similarly, abnormal user identification assigns correlation coefficients, significance values ​​and standard deviations. Weighting improves the accuracy and comprehensiveness of identification; 3) Reduces missed identification of abnormal users. By adopting a flexible correlation analysis model to reduce missed identification of abnormal users, a more flexible method, namely correlation analysis, is adopted, focusing on the correlation between the power consumption of each subordinate user and the power loss in the substation area to reduce the noise between the independent variables, and expands the initial screening range of abnormal users to reduce missed identification; 4) Reduces the misidentification of normal users as abnormal. The traditional correlation coefficient method and linear regression method are improved to improve the accuracy of abnormal user identification. The correlation coefficient and significance value (p value) are comprehensively considered to ensure that the correlation coefficient is not only numerically significant but also statistically significant. This method improves the standard of abnormal identification and effectively excludes those users with large absolute values ​​of correlation coefficients but no substantial linear relationship with the power loss in the substation area.

[0115] In addition, the concept of "consistency between user load patterns and line loss fluctuation trends in the substation area" was incorporated to reduce interference with the analysis by excluding users with small fluctuations in power consumption or who basically do not use electricity. The standard deviation measurement was introduced into the value-assigned weighted model, thereby optimizing the original correlation coefficient method, reducing the risk of misjudgment, and improving the accuracy of the analysis.

[0116] That is, the technical solution provided by the embodiment of the present invention comprehensively considers various factors, adopts a suitable data processing method, an advanced correlation coefficient method and an assignment weighted model, and can help the power sector to better manage and optimize the power system.

[0117] In addition, it should be noted that since the metering automation system lacks data on the amount of electricity supplied by subordinate users, in general, the identification of abnormal users has to rely on predictive methods to observe the synchronous changes in the trend of power loss in the substation and the power consumption of subordinate users. The embodiment of the present invention can choose to analyze the correlation between the power loss in the substation and the daily power consumption of subordinate users. If a new user power monitoring device can be developed to accurately obtain the power supply and power consumption data of each user under the substation, the identification of abnormal users will be transformed into a simple numerical calculation problem. By comparing the power supply and power supply of the substation, the abnormal degree of the line loss in the substation can be evaluated. At the same time, by calculating the difference and ratio between the power supply and output of the substation, the power supply of the user and the power consumption of the user, abnormal users can be effectively identified.

[0118] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0119] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0120] According to an embodiment of the present invention, there is also provided a device for determining users with abnormally low voltage in a transformer area using abnormally low voltage line loss, which is used to implement the above-mentioned method for determining users with abnormally low voltage line loss in a transformer area. Figure 4 is a schematic diagram of a device for determining low-voltage users with abnormal line loss in a transformer area according to an embodiment of the present invention. Figure 4 As shown, the device includes: a first acquisition module 401, a first determination module 403, a second determination module 405, a second acquisition module 407, a third determination module 409, a fourth determination module 411 and a fifth determination module 413. The device for determining low-voltage users with abnormal line loss in the substation area is described below.

[0121] The first acquisition module 401 is used to obtain line loss data of the substation to be identified, wherein the substation to be identified is the substation that needs to be checked for line loss anomalies, wherein the line loss data at least includes the following data of the substation to be identified: power supply, power supply, power loss, line loss rate, data integrity rate and number of users.

[0122] The first determination module 403 is used to determine the abnormality level value of the to-be-identified substation according to the line loss data.

[0123] The second determination module 405 is used to determine a target area among the areas to be identified according to the abnormality level value, wherein the target area is an area among the areas to be identified whose abnormality level value is greater than an abnormality level threshold.

[0124] The second acquisition module 407 is used to acquire line loss related data of subordinate users of each target substation, wherein the subordinate users are electricity users within the power supply range of each target substation.

[0125] The third determination module 409 is used to determine the first time series of power loss of each target substation within a unit time and the second time series of power consumption of each subordinate user within a unit time according to the line loss related data.

[0126] The fourth determination module 411 is used to determine the correlation coefficient between the power consumption of subordinate users and the power loss of the target substation according to the first time series and the second time series.

[0127] The fifth determination module 413 is used to determine the abnormal line loss users in each target station area according to the correlation coefficient.

[0128] It should be noted here that the above-mentioned first acquisition module 401, first determination module 403, second determination module 405, second acquisition module 407, third determination module 409, fourth determination module 411 and fifth determination module 413 correspond to steps S202 to S214 in the above-mentioned embodiments, and the seven modules are the same as the instances and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0129] As can be seen from the above, in the scheme recorded in the above-mentioned embodiment of the present invention, firstly, the first acquisition module can be used to acquire the line loss data of the to-be-identified substation, wherein the to-be-identified substation is the substation that needs to be checked for line loss anomalies, wherein the line loss data at least includes the following data of the to-be-identified substation: power supply, power supply, power loss, line loss rate, data integrity rate and number of users; then, the first determination module can be used to determine the abnormality degree value of the to-be-identified substation according to the line loss data; then, the second determination module can be used to determine the target substation in the to-be-identified substation according to the abnormality degree value, wherein the target substation is the substation whose abnormality degree value in the to-be-identified substation is greater than the abnormality degree threshold; secondly, the second acquisition module can be used to acquire the line loss related data of the subordinate users of each target substation, wherein the subordinate users are the electricity users within the power supply range of each target substation; and the third determination module can also be used to determine the abnormality degree value of the to-be-identified substation according to the abnormality degree value. The determination module determines the first time series of the power loss of each target substation per unit time and the second time series of the power consumption of each subordinate user per unit time according to the line loss related data; in addition, the fourth determination module can be used to determine the correlation coefficient between the power consumption of the subordinate users and the power loss of the target substation according to the first time series and the second time series; finally, the fifth determination module can be used to determine the abnormal line loss users in each target substation according to the correlation coefficient, thereby achieving the purpose of more accurately identifying abnormal line loss users in the substation and improving the efficiency of abnormal line loss analysis in the substation by optimizing the correlation analysis method, constructing an assignment weighted model for multi-dimensional line loss index evaluation, and designing corresponding intelligent diagnosis Python programs, which can effectively reduce line losses, improve the operation efficiency of the power grid, save labor costs, and achieve the technical effect of improving the accuracy and efficiency of identifying abnormal line loss users in the substation.

[0130] The above-mentioned technical solution provided by the embodiment of the present invention solves the technical problems in the related art that there is no unified and representative method for troubleshooting line loss in substations, and that it is impossible to comprehensively cover various abnormalities and accurately identify abnormal users.

[0131] In an optional embodiment, the first acquisition module includes: a first determination unit, used to determine the to-be-identified substation within a predetermined range; a downloading unit, used to download the line loss data of each to-be-identified substation in a unit time through a line loss data downloading program.

[0132] In an optional embodiment, the first determination module includes: a first acquisition unit, used to obtain evaluation information of each substation abnormality evaluation index in the line loss data; a first comparison unit, used to compare the numerical value of each substation abnormality evaluation index in the line loss data with the evaluation interval in the evaluation information to obtain the evaluation score of each substation abnormality evaluation index; a second determination unit, used to determine the abnormality degree value of the substation to be identified according to the evaluation score.

[0133] In an optional embodiment, the second determination module includes: a second comparison unit, which is used to compare each abnormality degree value with the abnormality degree threshold to obtain a first comparison result; and a third determination unit, which is used to determine the station area corresponding to the abnormality degree value greater than the abnormality degree threshold in each abnormality degree value in the first comparison result as the target station area.

[0134] In an optional embodiment, the fourth determination module includes: a fourth determination unit, which is used to determine the correlation coefficient between the power consumption of the subordinate user and the power loss of the target station area according to the first time series and the second time series through a predetermined formula, wherein the predetermined formula is: r represents the correlation coefficient, n represents the number of days for which line loss related data are statistically analyzed, and X i represents the power consumption of subordinate users on the i-th day, Indicates the average power consumption of subordinate users within the statistical days, S X Indicates the standard deviation of the electricity consumption of subordinate users within the statistical days, Y i represents the power loss of the target area on the i-th day, It represents the average power loss of the target area within the statistical days, S Y It indicates the standard deviation of the power loss in the target substation within the statistical days.

[0135] In an optional embodiment, the fifth determination module includes: a hypothesis testing unit, used to perform hypothesis testing on each correlation coefficient to obtain a significance value of each correlation coefficient; a fifth determination unit, used to determine the risk value of each subordinate user in each target substation according to each significance value, each correlation coefficient and the standard deviation of electricity consumption of each subordinate user per unit time; and a sixth determination unit, used to determine the users with abnormal line losses in each target substation according to the risk value.

[0136] In an optional embodiment, the fifth determination unit includes: a first determination subunit, used to determine the evaluation information of each significance value, each correlation coefficient and each standard deviation of electricity consumption; a first comparison subunit, used to compare each significance value, each correlation coefficient and each standard deviation of electricity consumption with the evaluation interval in the evaluation information, to obtain the evaluation score of each subordinate user under the significance value, correlation coefficient and standard deviation of electricity consumption; a second determination subunit, used to determine the risk value of each subordinate user based on the evaluation score.

[0137] According to another aspect of an embodiment of the present invention, a processor is provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned methods for determining low-voltage users with abnormal line loss in a transformer area is executed.

[0138] According to another aspect of an embodiment of the present invention, there is also provided a computer program product, including computer instructions, which, when executed by a processor, perform any one of the above methods for determining low-voltage users with abnormal line loss in a transformer area.

[0139] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium comprising a stored program, wherein the program executes any one of the above-mentioned methods for determining low-voltage users in a substation with abnormal line loss.

[0140] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0141] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining low-voltage users with abnormal line loss in a transformer area, characterized in that: include: Acquire line loss data of the to-be-identified substation, wherein the to-be-identified substation is a substation that needs to be checked for abnormal line loss, wherein the line loss data at least includes the following data of the to-be-identified substation: power supply, power supply, power loss, line loss rate, data integrity rate, and number of users; Determine the abnormality level value of the to-be-identified substation according to the line loss data; Determine a target area among the areas to be identified according to the abnormality level value, wherein the target area is an area among the areas to be identified whose abnormality level value is greater than an abnormality level threshold; Acquire line loss related data of subordinate users of each target substation, wherein the subordinate users are electricity users within the power supply range of each target substation; Determine, according to the line loss related data, a first time series of power loss of each target substation within a unit time and a second time series of power consumption of each subordinate user within the unit time; Determine the correlation coefficient between the power consumption of the subordinate user and the power loss of the target station area according to the first time series and the second time series; The users with abnormal line loss in each of the target stations are determined according to the correlation coefficient.

2. The method for determining low-voltage users with abnormal line loss in an area according to claim 1, characterized in that: Obtain the line loss data of the area to be identified, including: Determining the to-be-identified station area within a predetermined range; The line loss data of each of the to-be-identified stations within the unit time is downloaded through a line loss data downloading program.

3. The method for determining low-voltage users with abnormal line loss in an area according to claim 1, characterized in that: Determining the abnormality level value of the to-be-identified substation according to the line loss data includes: Obtaining evaluation information of various abnormal evaluation indicators of the substation in the line loss data; Comparing the values ​​of the various substation abnormality evaluation indicators in the line loss data with the evaluation intervals in the evaluation information to obtain evaluation scores for the various substation abnormality evaluation indicators; The abnormality degree value of the station area to be identified is determined according to the evaluation score.

4. The method for determining low-voltage users with abnormal line loss in a transformer area according to claim 1, characterized in that: Determining a target area among the areas to be identified according to the abnormality level value includes: Comparing each of the abnormality level values ​​with the abnormality level threshold value to obtain a first comparison result; The station area corresponding to the abnormality level value greater than the abnormality level threshold value among the abnormality level values ​​in the first comparison result is determined as the target station area.

5. The method for determining low-voltage users with abnormal line loss in an area according to claim 1, characterized in that: Determining the correlation coefficient between the power consumption of the subordinate user and the power loss of the target area according to the first time series and the second time series includes: The correlation coefficient between the power consumption of the subordinate user and the power loss of the target area is determined according to the first time series and the second time series by a predetermined formula, wherein the predetermined formula is: r represents the correlation coefficient, n represents the number of days for which the line loss related data is statistically analyzed, and X i represents the power consumption of the subordinate user on the i-th day, represents the average power consumption of the subordinate users within the statistical days, S X represents the standard deviation of the power consumption of the subordinate users within the statistical days, Y i represents the power loss of the target area on the i-th day, represents the average value of the target area's power loss within the statistical days, S Y It represents the standard deviation of the power loss in the target area within the statistical days.

6. The method for determining low-voltage users with abnormal line loss in an area according to claim 1, characterized in that: Determining users with abnormal line loss in each of the target areas according to the correlation coefficients includes: Conduct hypothesis testing on each of the correlation coefficients to obtain a significance value of each of the correlation coefficients; Determine the risk value of each subordinate user in each target area according to each significance value, each correlation coefficient and the standard deviation of power consumption of each subordinate user within the unit time; The abnormal line loss users in each of the target stations are determined according to the risk value.

7. The method for determining low-voltage users with abnormal line loss in an area according to claim 6, characterized in that: Determining the risk value of each subordinate user in each target area according to each significance value, each correlation coefficient and the standard deviation of power consumption of each subordinate user within the unit time includes: Determining evaluation information of each of the significance values, each of the correlation coefficients, and each of the standard deviations of the power consumption; According to each of the significance values, each of the correlation coefficients, and each of the standard deviations of power consumption, respectively, the evaluation intervals in the evaluation information are compared to obtain the evaluation scores of each of the subordinate users under the significance value, the correlation coefficient, and the standard deviation of power consumption; The risk value of each of the subordinate users is determined according to the evaluation score.

8. A device for determining low-voltage users with abnormal line loss in a transformer area, characterized in that: include: A first acquisition module is used to acquire line loss data of a to-be-identified substation, wherein the to-be-identified substation is a substation that needs to be checked for abnormal line loss, wherein the line loss data at least includes the following data of the to-be-identified substation: power supply, power supply, power loss, line loss rate, data integrity rate, and number of users; A first determination module, used to determine the abnormality level value of the to-be-identified substation according to the line loss data; A second determination module is used to determine a target area among the areas to be identified according to the abnormality level value, wherein the target area is an area among the areas to be identified whose abnormality level value is greater than an abnormality level threshold; A second acquisition module is used to acquire line loss related data of subordinate users of each target substation, wherein the subordinate users are electricity users within the power supply range of each target substation; A third determination module is used to determine a first time series of power loss of each target substation within a unit time and a second time series of power consumption of each subordinate user within a unit time according to the line loss related data; A fourth determination module, configured to determine a correlation coefficient between the power consumption of the subordinate user and the power loss of the target substation according to the first time series and the second time series; The fifth determining module is used to determine the abnormal line loss users in each of the target stations according to the correlation coefficient.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method for determining low-voltage users with abnormal line loss in a substation area as described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the method for determining low-voltage users with abnormal line loss in a substation area as described in any one of claims 1 to 7 is performed.

Images