A method, medium and terminal for analyzing abnormal power consumption based on LTU and multidimensional data

Abstract

The present invention is applicable to the field of power grid monitoring technology, and relates to a method, medium, and terminal for analyzing abnormal power consumption based on LTU and multidimensional data, including: establishing a power grid relationship model; connecting the electric meter and LTU equipment to the main station, collecting electric energy indication data and topology identification data for a specific time period; matching and comparing the topology identification data with the power grid relationship model, automatically correcting the relevant power grid hierarchical affiliation, placing the user electric meter for which the topological relationship cannot be identified into a pre-adjusted power grid relationship user electric meter pool, and placing the relevant monitoring points into a pre-adjusted power grid relationship monitoring point pool; calculating the loss rate data of each monitoring point; performing linear correlation analysis; aggregating to obtain the characteristic information matrix of each pre-adjusted power grid relationship monitoring point and pre-adjusted power grid relationship user electric meter; performing multidimensional data fusion analysis and correcting topology linkage iteration; and obtaining a list of abnormal power users. The present invention has a simple process and is easy to operate, and effectively improves the accuracy of abnormal power consumption analysis in the substation area.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid monitoring, and in particular relates to a method, medium and terminal for analyzing abnormal power consumption based on LTU and multi-dimensional data. Background Art

[0002] In traditional power AMI systems, grid supervision can often only reach the substation area. The grid between the substation and the user's meter is difficult to supervise due to its complex and diverse conditions. Especially in densely populated areas with complex environments, the grid structure is even more complex and diverse, and electricity safety is difficult to guarantee. The existing technology's method for judging abnormal user electricity consumption has a wide scope and low accuracy in abnormal electricity consumption analysis.

[0003] The patent with announcement number CN117039850B provides a method and system for analyzing abnormal power consumption based on spatiotemporal features. The method includes: implementing multi-level grid division for the monitoring area; collecting and organizing historical power consumption information of users in the power monitoring area, including user categories, user power consumption behavior characteristics, and historical weather information; constructing a power consumption data model for regional users based on regional spatiotemporal data and historical power consumption information to predict regional user power consumption data; setting thresholds for power consumption of different categories of users, power consumption of users in unused time periods, and power consumption in different weather conditions; and analyzing whether the predicted power consumption is within a reasonable range of the calibrated threshold based on the predicted power consumption. If so, it is not abnormal power consumption; otherwise, it is recorded as abnormal power consumption. This patent uses a spatial multi-level grid division model to calibrate different types of power users and set different threshold models to achieve abnormal power consumption detection. However, its management scope is still large, and its accuracy is difficult to guarantee. It has the same disadvantages as the existing technology.

[0004] Therefore, how to improve the accuracy of abnormal power consumption analysis in substations is an urgent problem to be solved by personnel in this technical field. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a method for analyzing abnormal power consumption based on LTU and multi-dimensional data fusion, so as to solve the problem of low accuracy of abnormal power consumption analysis in the existing technology; in addition, the present invention also provides a medium and terminal for analyzing abnormal power consumption based on LTU and multi-dimensional data fusion.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for analyzing abnormal power consumption based on LTU and multi-dimensional data fusion, comprising the following steps:

[0008] S10, establishing a power grid relationship model from the substation transformer to the user's electricity meter;

[0009] S20: Connect the electric meter and LTU (Line Terminal Unit or Low Voltage Distribution Monitoring Terminal Unit, intelligent monitoring terminal for low-voltage distribution lines) to the master station to fully collect the electric energy indication data of the electric meter and LTU for a specific time period, as well as the LTU device topology identification data.

[0010] S30, matching and comparing the topology identification data with the grid relationship model, automatically correcting the relevant grid hierarchical affiliation, and placing user meters for which the topological relationship cannot be identified into a pre-adjusted grid relationship user meter pool, and placing relevant monitoring points into a pre-adjusted grid relationship monitoring point pool;

[0011] S40, calculating the loss rate data of each monitoring point according to the electric energy indication value in the specific time period and the power grid relationship model;

[0012] S50, performing a linear correlation analysis between the user meters in the pre-adjusted power grid relationship user meter pool and the power supply nodes directly connected thereto;

[0013] S60, obtaining a characteristic information matrix of each of the pre-adjusted grid relationship monitoring points and pre-adjusted grid relationship user meters according to the grid relationship model attributes, loss rate, and linear correlation aggregation;

[0014] S70, performing multi-dimensional data fusion analysis and topology correction linkage iteration based on the characteristic information matrix to obtain a corrected power grid relationship model;

[0015] S80. Based on the corrected power grid relationship model, recalculate the loss rate data of the monitoring points, re-perform linear correlation analysis on the monitoring points with abnormal loss rates, and obtain a list of abnormal electricity users.

[0016] Furthermore, in step S10, the power grid relationship model sinks the minimum management unit of the distribution network to the power box, and the specific contents are as follows:

[0017] Grid nodes include substation transformers, main switchboards, distribution boxes, branch lines, terminal boxes, electrical boxes, and LTUs;

[0018] Electricity user: user's electricity meter;

[0019] Relationship: topological relationship between upstream and downstream grid nodes, and relationship between user meters and directly associated grid nodes.

[0020] Furthermore, in step S20, the electric energy indication data for a specific time period is 15 minutes of electric energy indication data, and the data integrity rate is not less than 95%; the topology identification data is identified by microcurrent signal, and the data integrity rate is not less than 90%.

[0021] Furthermore, in step S40, the loss rate calculation formula is as follows:

[0022] Loss rate = (power supply in - power supply out) / power supply in.

[0023] Furthermore, in step S50, the linear correlation analysis uses a Pearson correlation coefficient algorithm to locate and eliminate abnormal power supply node loss rates caused by grid relationship errors.

[0024] Furthermore, in step S60, the characteristic information of the monitoring point related to the pre-adjusted power grid includes the monitoring point, power loss, loss rate, whether the loss rate is abnormal, the number of user meters, the number of identified user meters, the difference in the number of user meters, and the number of unidentified user meters; the characteristic information of the user meters related to the pre-adjusted power grid includes the suspected user meter, the power of the user meter, the monitoring point to which it belongs, the neighboring monitoring point to which it belongs, and whether it is linearly correlated.

[0025] Furthermore, in step S70, the specific process of multi-dimensional data fusion analysis and topology correction linkage iteration is as follows:

[0026] S701. Select all monitoring points with abnormal loss rates from the pre-adjustment grid-related monitoring points, and simultaneously select the pre-adjustment user electricity meters associated with the monitoring points;

[0027] S702. Based on the power loss at the monitoring point, the number of unidentified user meters, and the difference in the number of user meters, a combination traversal algorithm is used to find one or more user meter power combinations from the pre-adjusted power grid relationship user meter pool that meet the relative approximation standard for the power loss at the monitoring point. In the combination traversal algorithm, only user meters that are linearly correlated with the target monitoring point to be compared with the power loss are selected for combination. The combination scheme gives priority to the scheme with the smallest number of adjusted user meters. When selecting user meters to be adjusted from neighboring monitoring points, neighboring user meters that are not linearly correlated are given priority until a relative approximation is found. When none of the combination schemes meet the conditions, other combination schemes are selected to continue traversing using the same method.

[0028] Furthermore, the system automatically calculates the loss rate of the adjusted monitoring point and related monitoring points, as well as the linear correlation analysis of all non-linearly related user meters after adjustment. When the loss rate of the monitoring point is normal and the user meters are linearly correlated, it means that the topology correction plan for the monitoring point is found, and this monitoring point and all user meters under it are removed from the pre-adjustment grid relationship monitoring point pool and the pre-adjustment grid relationship user meter pool. Otherwise, only the adjusted monitoring point is removed from the pre-adjustment grid relationship monitoring point pool, indicating that no topology correction plan can be found for this monitoring point. After iterative cycles, until all pre-adjustment grid relationship monitoring points are processed, the system obtains a complete topology correction plan. After this plan is sent to the system user for review and approval, the system will automatically complete the topology relationship correction and obtain the corrected grid relationship model. For monitoring points with abnormal loss rates, the linear correlation between the user meter power and the power supply of the monitoring point is recalculated, and non-linearly related user meters are marked as suspected abnormal power consumption.

[0029] In a second aspect, the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0030] In a third aspect, the present invention further provides an electronic terminal, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the method described above.

[0031] Compared with the prior art, the method, medium, and terminal for analyzing abnormal power consumption based on LTUs and multidimensional data provided by the present invention have at least the following beneficial effects:

[0032] The existing technology is complex and diverse, making supervision difficult. Electricity safety is difficult to ensure, and methods for identifying abnormal electricity usage by users cover a wide range, resulting in low accuracy in abnormal electricity usage analysis. The present invention has a simple process and convenient operation, bringing grid management down to the smallest unit. It also integrates LTU area identification technology and automatic topology correction technology based on iterative matching of multi-dimensional feature data analysis such as multi-loss and linear correlation, allowing for more accurate positioning of abnormal electricity usage. This significantly improves the hit rate for abnormal electricity users and ensures the accuracy of abnormal electricity usage analysis within the area. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the scheme of the present invention, a brief introduction is given below to the figures required for use in the description of the embodiments. Obviously, the figures described below are some embodiments of the present invention. For ordinary technicians in this field, other figures can be obtained based on these figures without paying any creative work.

[0034] Figure 1A flowchart of a method for analyzing abnormal power consumption based on LTU and multi-dimensional data provided by an embodiment of the present invention;

[0035] Figure 2 A power grid relationship diagram between the transformer and the meter in the method for analyzing abnormal power consumption based on LTU and multi-dimensional data provided by an embodiment of the present invention;

[0036] Figure 3 A diagram showing the generation process of pre-adjusting the relationship between the monitoring points of the power grid and the user's electricity meter in a method for analyzing abnormal power consumption based on LTU and multi-dimensional data provided by an embodiment of the present invention;

[0037] Figure 4 A loss rate graph in a method for analyzing abnormal power consumption based on LTUs and multidimensional data provided by an embodiment of the present invention;

[0038] Figure 5 A diagram of the combined scenario of user meters at the PH297 abnormal monitoring point in a method for analyzing abnormal electricity consumption based on LTUs and multidimensional data provided by an embodiment of the present invention;

[0039] Figure 6 In a method for analyzing abnormal power consumption based on LTU and multi-dimensional data provided by an embodiment of the present invention, PH297 preferentially selects a strategy diagram for traversing user electricity meters. DETAILED DESCRIPTION

[0040] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the accompanying drawings. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present disclosure.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0042] The present invention provides a method for analyzing abnormal power consumption based on LTU and multidimensional data, which is applied to the abnormal power consumption analysis process of the power grid between the substation and the user's meter in the power AMI system. The method for analyzing abnormal power consumption based on LTU and multidimensional data fusion includes the following steps:

[0043] S10, establish the power grid relationship model from the transformer in the substation to the user's meter; S20, connect the meter and LTU equipment to the main station, and fully collect the data of the meter and LTU. The specific time period electric energy indication data and the complete collection of LTU equipment topology identification data; S30, matching and comparing the topology identification data with the power grid relationship model, automatically correcting the relevant power grid hierarchical affiliation, and placing the user meters for which the topological relationship cannot be identified into the pre-adjustment power grid relationship user meter pool, and the relevant monitoring points into the pre-adjustment power grid relationship monitoring point pool; S40, calculating the loss rate data of each monitoring point according to the electric energy indication in the specific time period and the power grid relationship model; S50, performing a linear correlation analysis on the user meters in the pre-adjustment power grid relationship user meter pool and the power supply nodes directly connected thereto; S60, obtaining the characteristic information matrix of each pre-adjustment power grid relationship monitoring point and pre-adjustment power grid relationship user meter according to the attributes, loss rate and linear correlation of the power grid relationship model; S70, performing multi-dimensional data fusion analysis and correction topology linkage iteration based on the characteristic information matrix to obtain the corrected power grid relationship model; S80, recalculating the loss rate data of the monitoring point based on the corrected power grid relationship model, and re-performing a linear correlation analysis on the monitoring points with abnormal loss rates to obtain a list of abnormal electricity users.

[0044] The present invention has a simple process and is easy to operate, and effectively improves the accuracy of abnormal power consumption analysis in substations.

[0045] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0046] The present invention provides a method for analyzing abnormal power consumption based on LTU and multi-dimensional data, which is applied to the abnormal power consumption analysis process of the power grid between the substation and the user's meter in the power AMI system. Figures 1 to 6 In this embodiment, the method for analyzing abnormal power consumption based on LTU and multi-dimensional data includes the following steps:

[0047] S10. Modeling: Establish a power grid relationship model from the substation transformer to the user's electricity meter. This model sinks the minimum management unit of the distribution network to the power box.

[0048] Specifically, in this embodiment, the grid relationship model content is as follows:

[0049] Grid nodes: transformer (TR), main switchboard (QGBT), distribution box (CD), feeder (FEEDER), line terminal box (PH), distribution box (CCL), LTU;

[0050] Electricity user: user's electricity meter;

[0051] Relationships: The topological relationships between upstream and downstream grid nodes, the relationships between user meters and directly associated grid nodes. The number of user meters under a grid node is known business information, and the grid relationships between various electrical devices.

[0052] S20: Automatically collect data by connecting the electricity meter and LTU equipment to the main station to fully collect the 15-minute electricity energy indication data of the electricity meter and LTU (the data completeness rate must be above 95%), and fully collect the topology identification data of the LTU equipment (Note: LTU uses microcurrent signals to identify the relationship between the monitoring point and the downstream electricity meter. LTU001 can identify the relationship between PH1367 and the electricity meter installed downstream). The data completeness rate must be above 90%.

[0053] S30, correct the grid relationship model, match and compare the topology identification data collected in step S20 with the grid relationship model in step S10, and automatically correct the relevant grid hierarchical affiliation; after the automatic correction is completed, the user meters whose topological relationships cannot be identified are placed in the pre-adjusted grid relationship user meter pool, and the relevant monitoring points are placed in the pre-adjusted grid relationship monitoring point pool.

[0054] S40, calculating the power loss of the monitoring point, and automatically calculating the power loss rate data of each monitoring point based on the 15-minute power indication and the power grid relationship model.

[0055] Specifically, in this embodiment, the loss rate calculation formula is loss rate = (input power - output power) / input power. For example, the input power of PH1367 is calculated based on the power indication value collected by LTU001, and the output power of PH1367 is equal to the sum of the power of all downstream users.

[0056] S50. Linear correlation analysis: For power supply nodes close to the user side of the distribution network, the power supply and the user's power consumption are usually linearly correlated in the absence of abnormal power consumption. A linear correlation analysis is performed between the user meters in the pre-adjusted grid relationship user meter pool and the power supply nodes directly connected to them (the linear correlation uses the Pearson Correlation Coefficient algorithm) to quickly locate and eliminate abnormal power supply node loss rates caused by grid relationship errors.

[0057] S60, aggregating to form a multi-dimensional feature matrix, aggregating the data in multiple dimensions according to the attributes of the power grid archive model, the loss rate, and the linear correlation to obtain the feature information matrix of each pre-adjustment power grid relationship monitoring point and the pre-adjustment power grid relationship user meter.

[0058] Specifically, in this embodiment, the characteristic information of the monitoring points of the pre-adjusted power grid relationship is as shown in Table 1 below:

[0059] Table 1

[0060]

[0061] Pre-adjust the user's electricity meter characteristic information, as shown in Table 2 below:

[0062] Table 2

[0063]

[0064] Note: Neighbor monitoring points refer to grid nodes with a common parent monitoring point in the grid relationship. User electricity meters in neighbor monitoring points are also neighbor user electricity meters.

[0065] S70, multi-dimensional data fusion analysis and topology correction linkage iteration, based on the feature matrix of step S60, logically iterate according to the following steps:

[0066] S701. Take all monitoring points with abnormal loss rates from the pre-adjustment grid related monitoring points, such as PH298, PH11352, and PH297, and simultaneously take out the pre-adjustment user meters related to these monitoring points, such as C15, C19, C20, C24, C26, C25, C30, and C31;

[0067] S702. Based on the power loss at the monitoring point, the number of unidentified user meters, and the difference in the number of user meters, a combination traversal algorithm is used to find one or more user meter power combinations (the number of user meter combinations <= the number of unidentified user meters) from the pre-adjusted power grid relationship user meter pool that meet the relative approximation standard for the power loss at the monitoring point. In the combination traversal algorithm, only user meters that are linearly correlated with the target monitoring point for power loss comparison are selected for combination, and the combination scheme with the smallest number of adjusted user meters is prioritized. The combination scheme for the abnormal monitoring point PH297 is "C30+C31+adjusted user meters". When selecting adjusted user meters from neighboring monitoring points, neighboring user meters without linear correlation are prioritized until a relative approximation is found. If no such combination scheme meets the conditions, other combination schemes are selected and the traversal is continued using the same method. For example, if the power loss at the abnormal monitoring point PH297 is 12.03, C30+C31+C26 The user's power consumption is 12.01, and the system preset threshold change rate interval of the relative approximate value is (0.03, -0.03), then (12.03-12.01) / 12.03=0.001 meets the condition). The system will automatically calculate the loss rate of the adjusted monitoring point (such as PH297) and related monitoring points (such as PH11352), as well as the linear correlation analysis of all non-linearly related user meters after adjustment (such as the power of C26 user meter and the power supplied by PH297, and the power of C25 user meter and the power supplied by PH11352). When the loss rate of the monitoring point is normal and the user meters are all linearly correlated, it means that the topology correction plan for the monitoring point has been found, and this monitoring point and all user meters under it will be removed from the pre-adjustment grid relationship monitoring point pool and the pre-adjustment grid relationship user meter pool. Otherwise, only the adjusted monitoring point will be removed from the pre-adjustment grid relationship monitoring point pool, indicating that no topology correction plan can be found for this monitoring point; for example, when the adjustment of the PH297 monitoring point is completed, PH297 and PH11352 will be removed, and C24, C26, C25, C30, and C31 will also be removed. According to the above algorithm, the system will iterate until all the pre-adjustment grid relationship monitoring points are processed. The system will obtain a complete topology correction plan. After this plan is sent to the system user for review and approval, the system will automatically complete the topology relationship correction and obtain a more accurate grid relationship model.

[0068] S80. Arrange the list of abnormal electricity users, recalculate the power loss of the monitoring points based on the grid relationship model corrected in step S70, and recalculate the linear correlation between the power consumption of the user's meter and the power supply of the monitoring point for the monitoring points with abnormal loss rates. The user's meter without linear correlation is marked as suspected abnormal power consumption. In this way, the scope of abnormal electricity users is locked more accurately. If the abnormal power consumption analysis is carried out on these users in a targeted manner, the hit rate will be greatly improved.

[0069] The methods, media, and terminals for analyzing abnormal power consumption based on LTU and multi-dimensional data described in the above embodiments are compared with the existing technologies, in which the situations are complex and diverse and difficult to supervise, the safety of power consumption is difficult to ensure, the scope of users' abnormal power consumption judgment methods is large, and the accuracy of abnormal power consumption analysis is low. The present invention has a simple process and convenient operation, sinks the management of the power grid to the smallest unit, and integrates LTU substation identification technology and automatic topology correction technology based on iterative matching of multi-dimensional feature data analysis such as multi-loss and linear correlation, so as to more accurately locate the scope of abnormal power consumption, thereby significantly improving the hit rate of abnormal power users and ensuring the accuracy of abnormal power consumption analysis in the substation.

[0070] Obviously, the embodiments described above are only preferred embodiments of the present invention, rather than all embodiments. The preferred embodiments of the present invention are given in the accompanying drawings, but they do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present invention specification and drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present invention.

Claims

1. A method for analyzing abnormal power consumption based on LTU and multi-dimensional data, characterized in that: The following steps are involved: S10, establishing a power grid relationship model from the substation transformer to the user's electricity meter; S20: Connect the electric meter and LTU device to the master station, and completely collect the electric energy indication data of the electric meter and LTU in a specific time period, as well as the complete topology identification data of the LTU device; S30, matching and comparing the topology identification data with the grid relationship model, automatically correcting the relevant grid hierarchical affiliation, and placing user meters for which the topological relationship cannot be identified into a pre-adjusted grid relationship user meter pool, and placing relevant monitoring points into a pre-adjusted grid relationship monitoring point pool; S40, calculating the loss rate data of each monitoring point according to the electric energy indication value in the specific time period and the power grid relationship model; S50, performing a linear correlation analysis between the user meters in the pre-adjusted power grid relationship user meter pool and the power supply nodes directly connected thereto; S60, obtaining a characteristic information matrix of each of the pre-adjusted grid relationship monitoring points and pre-adjusted grid relationship user meters according to the grid relationship model attributes, loss rate, and linear correlation aggregation; In step S60, the characteristic information of the monitoring point related to the pre-adjusted power grid includes the monitoring point, power loss, loss rate, whether the loss rate is abnormal, the number of user meters, the number of identified user meters, the difference in the number of user meters, and the number of unidentified user meters; the characteristic information of the user meters related to the pre-adjusted power grid includes the suspected user meter, the power of the user meter, the monitoring point to which it belongs, the neighboring monitoring point to which it belongs, and whether it is linearly correlated; S70, performing multi-dimensional data fusion analysis and topology correction linkage iteration based on the characteristic information matrix to obtain a corrected power grid relationship model; In step S70, the specific process of multi-dimensional data fusion analysis and topology correction linkage iteration is as follows: S701. Select all monitoring points with abnormal loss rates from the pre-adjustment grid-related monitoring points, and simultaneously select the pre-adjustment user electricity meters associated with the monitoring points; S702. Based on the power loss at the monitoring point, the number of unidentified user meters, and the difference in the number of user meters, a combination traversal algorithm is used to search for one or more user meter power combinations from the pre-adjusted power grid-related user meter pool that meet a relative approximation criterion for the power loss at the monitoring point. In the combination traversal algorithm, only user meters that are linearly correlated with the target monitoring point for power loss comparison are selected for combination. The combination scheme that minimizes the number of adjusted user meters is prioritized. When selecting user meters to be adjusted from neighboring monitoring points, neighboring user meters that are not linearly correlated are prioritized until a relative approximation is found. If no combination scheme meets the criteria, other combination schemes are selected and the traversal is continued using the same method. S80. Based on the corrected power grid relationship model, recalculate the loss rate data of the monitoring points, re-perform linear correlation analysis on the monitoring points with abnormal loss rates, and obtain a list of abnormal electricity users.

2. The method for analyzing abnormal power consumption based on LTU and multi-dimensional data according to claim 1, characterized in that: In step S10, the power grid relationship model sinks the minimum management unit of the distribution network to the power box, and the specific contents are as follows: Grid nodes include substation transformers, main switchboards, distribution boxes, branch lines, terminal boxes, electrical boxes, and LTUs; Electricity user: user's electricity meter; Relationship: topological relationship between upstream and downstream grid nodes, and relationship between user meters and directly associated grid nodes.

3. The method for analyzing abnormal power consumption based on LTU and multi-dimensional data according to claim 1, characterized in that: In step S20, the electric energy indication data for a specific time period is 15 minutes of electric energy indication data, and the data integrity rate is not less than 95%; the topology identification data is identified by microcurrent signals, and the data integrity rate is not less than 90%.

4. The method for analyzing abnormal power consumption based on LTU and multi-dimensional data according to claim 1, characterized in that: In step S40, the loss rate calculation formula is as follows: Loss rate = (power supply in - power supply out) / power supply in.

5. The method for analyzing abnormal power consumption based on LTU and multi-dimensional data according to claim 1, characterized in that: In step S50, the linear correlation analysis uses the Pearson correlation coefficient algorithm to locate and eliminate abnormal power supply node loss rate caused by grid relationship errors.

6. The method for analyzing abnormal power consumption based on LTU and multi-dimensional data according to claim 1, characterized in that: The system automatically calculates the loss rate of the adjusted monitoring point and related monitoring points, as well as the linear correlation analysis of all non-linearly related user meters after adjustment. When the loss rate of the monitoring point is normal and the user meters are linearly correlated, it means that the topology correction plan for the monitoring point is found, and this monitoring point and all user meters under it are removed from the pre-adjustment grid relationship monitoring point pool and the pre-adjustment grid relationship user meter pool. Otherwise, only the adjusted monitoring point is removed from the pre-adjustment grid relationship monitoring point, indicating that no topology correction plan can be found for this monitoring point. After iterative cycles, until all pre-adjustment grid relationship monitoring points are processed, the system obtains a complete topology correction plan. After this plan is sent to the system user for review and approval, the system will automatically complete the topology relationship correction and obtain the corrected grid relationship model. For monitoring points with abnormal loss rates, the linear correlation between the user meter power and the power supply of the monitoring point is recalculated, and the non-linearly related user meters are marked as suspected abnormal power consumption.

7. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

8. An electronic terminal, characterized in that: include: processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal performs the method according to any one of claims 1 to 6.

Images