Method for analyzing abnormal electricity utilization based on LTU and multi-dimensional data, medium and terminal

Abstract

The invention is suitable for the technical field of power grid monitoring, and relates to a method for analyzing abnormal power utilization based on LTU and multi-dimensional data, a medium and a terminal, and the method comprises the steps: building a power grid relation model; the method comprises the following steps: connecting an ammeter and LTU equipment into a master station, and collecting electric energy indicating value data and topology identification data in a specific time period; matching and comparing the topology identification data with the power grid relation model, automatically correcting a related power grid hierarchical membership relation, putting user electricity meters of which the topology relation cannot be identified into a preset power grid relation user electricity meter pool, and putting related monitoring points into a preset power grid relation monitoring point pool; accounting the loss rate data of each monitoring point; carrying out linear correlation analysis; aggregating to obtain a characteristic information matrix of each pre-dispatching power grid relation monitoring point and a pre-dispatching power grid relation user electric meter; carrying out multi-dimensional data fusion analysis and correction topology linkage iteration; and obtaining an abnormal electricity user roster. The method is simple in process and convenient to operate, and effectively improves the analysis accuracy of the abnormal power consumption of the transformer area.

Description

Technical Field

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

[0002] In the traditional power AMI system, power grid supervision can often only reach the substation area. For the power grid in the interval from the substation area to the user's electricity meter, it is difficult to supervise due to the complex and diverse situations. Especially in those densely populated and complex environments, the power grid structure is more complex and diverse, and the electricity consumption safety is difficult to guarantee. In the prior art, the scope targeted by the method for judging abnormal electricity consumption of users is relatively large, and the accuracy of abnormal electricity consumption analysis is relatively low.

[0003] The patent with the publication number CN117039850B provides a method and system for analyzing abnormal electricity consumption based on spatio-temporal and geographical features. The method includes: implementing multi-level grid division for the monitoring area; collecting and sorting out the historical electricity consumption information of users in the electricity consumption monitoring area, including user categories, user electricity consumption behavior characteristics, and historical weather information; constructing an electricity consumption data model for regional users based on regional spatio-temporal data and historical electricity consumption information to realize the prediction of regional user electricity consumption data; setting thresholds for electricity consumption of different categories of users, electricity consumption at different time periods, and electricity consumption under different weather conditions; and analyzing whether the predicted electricity consumption is within the reasonable range of the calibrated threshold. If it is, it is not abnormal electricity consumption, otherwise it is recorded as abnormal electricity consumption. In this patent, through the mode of multi-level spatial grid division and the calibration of different types of electricity consumption users, different threshold models are set to realize abnormal electricity consumption detection. However, the management scope is still relatively large, and the accuracy is difficult to guarantee, and it has the same drawbacks as the prior art.

[0004] Therefore, how to improve the accuracy of abnormal electricity consumption analysis in the substation area is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the purpose of the present invention is to provide a method for analyzing abnormal electricity consumption based on the fusion of LTU and multi-dimensional data to solve the problem of low accuracy of abnormal electricity consumption analysis in the substation area in the prior art; in addition, the present invention also provides a medium and a terminal for analyzing abnormal electricity consumption based on the fusion of LTU and multi-dimensional data.

[0006] To solve the above technical problems, the present invention adopts the following technical solutions:

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

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

[0009] S20. Connect the electricity meter and LTU (Line Terminal Unit or Low Voltage Distribution Monitoring Terminal Unit) devices to the master station, completely collect the electricity energy indication data of the electricity meter and LTU for a specific period, and completely collect the topology identification data of the LTU device;

[0010] S30. Match and compare the topology identification data with the power grid relationship model, automatically correct the relevant power grid hierarchical subordination relationships, put the user electricity meters for which the topology relationship cannot be identified into the pre-adjusted power grid relationship user electricity meter pool, and put the relevant monitoring points into the pre-adjusted power grid relationship monitoring point pool;

[0011] S40. Calculate the loss rate data of each monitoring point according to the electricity energy indication value for the specific period and the power grid relationship model;

[0012] S50. Conduct a linear correlation analysis between the user electricity meters in the pre-adjusted power grid relationship user electricity meter pool and their directly connected power supply nodes;

[0013] S60. Aggregate to obtain the characteristic information matrix of each of the pre-adjusted power grid relationship monitoring points and pre-adjusted power grid relationship user electricity meters according to the power grid relationship model attributes, loss rate, and linear correlation;

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

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

[0016] Further, in step S10, the power grid relationship model sinks the minimum management unit of the distribution network to the electrical box, and the specific content is as follows:

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

[0018] Electricity users: user electricity meters;

[0019] Relationships: the upstream and downstream hierarchical topology relationships of power grid nodes, and the relationships between user electricity meters and directly associated power grid nodes.

[0020] Further, in step S20, the electricity energy indication data for the specific period is the 15-minute electricity energy indication data, and the data integrity rate is not less than 95%; the topology identification data is identified by means of micro-current signals, and the data integrity rate is not less than 90%.

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

[0022] Loss rate = (power input - power output) / power input.

[0023] Further, in the step S50, the linear correlation analysis uses the Pearson correlation coefficient algorithm to locate and eliminate the abnormal phenomenon of the power supply node loss rate caused by the incorrect grid relationship.

[0024] Further, in the step S60, the characteristic information of the pre-adjusted grid relationship monitoring point includes the monitoring point, loss power, 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 un-identified user meters; the characteristic information of the pre-adjusted grid relationship user meter includes the suspected user meter, the power of the user meter, the affiliated monitoring point, the affiliated neighbor monitoring point, and whether it is linearly correlated.

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

[0026] S701. Select all monitoring points with abnormal loss rates from the pre-adjusted grid relationship monitoring points, and at the same time select the pre-adjusted user meters related to the monitoring points;

[0027] S702. According to the loss power, the number of un-identified user meters, and the difference in the number of user meters of the monitoring point, find one or more combinations of user meter powers that satisfy the relative approximation standard with the loss power of the monitoring point from the pre-adjusted grid relationship user meter pool through the combined traversal algorithm. In the combined traversal algorithm, only select the user meters that are linearly correlated with the target monitoring point of the current loss power to be compared for combination. The combination scheme preferably selects the scheme with the smallest number of adjusted user meters. When selecting the adjusted user meters from the neighbor monitoring points, preferably select the neighbor user meters without linear correlation until the relative approximation value is found. When all combination schemes do not meet the conditions, then select other combination schemes and continue to traverse in the same way.

[0028] Furthermore, the system automatically calculates and adjusts the loss rates of the monitoring points and related monitoring points, as well as the linear correlation analysis of all non-linear related user electric meters after adjustment. When the loss rate of the monitoring point is normal and the user electric meters are all linearly related, it indicates that a topological correction scheme for the monitoring point has been found, and this monitoring point and all user electric meters below it are removed from the pre-adjusted power grid relationship monitoring point pool and the pre-adjusted power grid relationship user electric meter pool. Otherwise, only the adjusted monitoring point is removed from the pre-adjusted power grid relationship monitoring point pool, indicating that no topological correction scheme can be found for this monitoring point. After iterative cycling until all pre-adjusted power grid relationship monitoring points have been processed, the system obtains a complete topological correction scheme. After this scheme is sent to the system user for approval, the system will automatically complete the topological relationship correction to obtain a corrected power grid relationship model. For monitoring points with abnormal loss rates, the linear correlation between the user electric meter power consumption and the monitoring point power supply is recalculated, and user electric meters without linear correlation are marked as suspected abnormal power consumption.

[0029] In a second aspect, the present invention also provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the method as described above.

[0030] In a third aspect, the present invention also provides an electronic terminal, including: 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 as described above.

[0031] The method, medium, and terminal for analyzing abnormal power consumption based on LTU and multi-dimensional data provided by the present invention have at least the following beneficial effects compared with the prior art:

[0032] In the prior art, the situation is complex and diverse, making it difficult to supervise, and the safety of power consumption is difficult to guarantee. The method for judging abnormal power consumption by users targets a relatively large range, and the accuracy of abnormal power consumption analysis is relatively low. The process of the present invention is simple and convenient to operate. It sinks the management of the power grid to the smallest unit and integrates the LTU substation area identification technology and the automatic topological correction technology based on multi-loss and linear correlation and other multi-dimensional feature data analysis and iterative matching, more accurately locating the scope of abnormal power consumption, thereby greatly improving the hit rate of abnormal power consumption users and ensuring the accuracy of abnormal power consumption analysis in the substation area. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the solution of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

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

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

[0036] Figure 3 Generation process diagram of the pre-adjusted grid relationship monitoring point and the user electricity meter in a method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data provided by an embodiment of the present invention;

[0037] Figure 4 Loss rate diagram in a method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data provided by an embodiment of the present invention;

[0038] Figure 5 Combined scenario diagram of user electricity meters at the PH297 abnormal monitoring point in a method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data provided by an embodiment of the present invention;

[0039] Figure 6 Strategy diagram for preferentially selecting and traversing user electricity meters at the PH297 in a method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data provided by an embodiment of the present invention. Detailed implementation manners

[0040] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. The preferred embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the understanding of the disclosure of the present invention more thorough and comprehensive.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the description of the present invention herein 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 electricity consumption based on LTU and multi-dimensional data, which is applied to the analysis process of abnormal electricity consumption in the grid from the substation to the user electricity meter in the power AMI system. The method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data fusion includes the following steps:

[0043] S10. Establish a power grid relationship model from the substation transformer to the user electricity meter; S20. Connect the electricity meter and the LTU device to the master station, completely collect the electricity energy indication data of the electricity meter and the LTU during a specific time period, and completely collect the topology identification data of the LTU device; S30. Match and compare the topology identification data with the power grid relationship model, automatically correct the relevant power grid hierarchical subordination relationship, and put the user electricity meters for which the topology relationship cannot be identified into the pre-adjusted power grid relationship user electricity meter pool, and put the relevant monitoring points into the pre-adjusted power grid relationship monitoring point pool; S40. Calculate the loss rate data of each monitoring point according to the electricity energy indication value during a specific time period and the power grid relationship model; S50. Conduct a linear correlation analysis on the user electricity meters in the pre-adjusted power grid relationship user electricity meter pool and their directly connected power supply nodes; S60. Aggregate the characteristic information matrices of each pre-adjusted power grid relationship monitoring point and pre-adjusted power grid relationship user electricity meter according to the power grid relationship model attributes, loss rate, and linear correlation; S70. Based on the characteristic information matrix, conduct multi-dimensional data fusion analysis and corrective topology linkage iteration to obtain a corrected power grid relationship model; S80. Based on the corrected power grid relationship model, recalculate the loss rate data of the monitoring points, and conduct a linear correlation analysis on the monitoring points with abnormal loss rates again to obtain a list of abnormal electricity users.

[0044] The process of the present invention is simple and convenient to operate, effectively improving the accuracy of abnormal electricity consumption analysis in the substation area.

[0045] In order to enable those skilled in the art of this technology to better understand the solution 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 electricity consumption based on LTU and multi-dimensional data, which is applied to the process of analyzing abnormal electricity consumption in the power grid from the substation area to the user electricity meter in the power AMI system, and combines Figures 1 to 6 In this embodiment, the method for analyzing abnormal electricity 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 electricity meter, and this model sinks the minimum management unit of the distribution network to the electrical box.

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

[0049] Power grid nodes: substation transformer (TR), main switchboard (QGBT), distribution box (CD), feeder (FEEDER), head box (PH), electrical box (CCL), LTU;

[0050] Electricity users: user electricity meters;

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

[0052] S20. Automatically collect data, connect electricity meters and LTU devices to the master station, and achieve complete collection of 15-minute power indication data of electricity meters and LTUs (requiring a data integrity rate of over 95%). Completely collect the topology identification data of LTU devices (Note: LTUs use micro-current signal methods and can identify the relationship between monitoring points and downstream electricity meters. LTU001 can identify the relationship between PH1367 and downstream installed electricity meters), and require a data integrity rate of over 90%.

[0053] S30. Modify the power grid relationship model, match and compare the topology identification data collected in step S20 with the power grid relationship model in step S10, and automatically correct the relevant power grid hierarchical subordination relationships; after the automatic correction is completed, put the user electricity meters for which the topology relationship cannot be identified into the pre-adjusted power grid relationship user electricity meter pool, and put the relevant monitoring points into the pre-adjusted power grid relationship monitoring point pool.

[0054] S40. Calculate the power loss of monitoring points, and automatically calculate the power loss rate data of each monitoring point according to 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 collected by LTU001, and the output power of PH1367 is equal to the sum of the electricity consumption of all downstream users.

[0056] S50. Linear correlation analysis: For the power supply nodes near the user side of the distribution network, their power supply and user electricity consumption are usually linearly correlated under normal electricity consumption conditions. Perform linear correlation analysis on the user electricity meters in the pre-adjusted power grid relationship user electricity meter pool and their directly connected power supply nodes (linear correlation uses the Pearson Correlation Coefficient algorithm) to quickly locate and eliminate abnormal power loss rates of power supply nodes caused by incorrect power grid relationships.

[0057] S60. Aggregate to form a multi-dimensional feature matrix, and aggregate the feature information matrices of each pre-adjusted power grid relationship monitoring point and pre-adjusted power grid relationship user electricity meter according to multi-dimensional data such as the power grid file model attributes, loss rate, and linear correlation.

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

[0059] Table 1

[0060]

[0061] Pre-adjust the characteristic information of user electricity meters as shown in Table 2 below:

[0062] Table 2

[0063]

[0064] Note: The neighbor monitoring points refer to the power grid nodes of the co-parent monitoring points in the power grid relationship, and the user electricity meters among the neighbor monitoring points are mutually neighbor user electricity meters.

[0065] S70. Multi-dimensional data fusion analysis and corrective topology linkage iteration. Based on the feature matrix in step S60, perform logical iteration according to the following steps:

[0066] S701. Select all the monitoring points with abnormal loss rates from the pre-adjusted power grid relationship monitoring points, such as PH298, PH11352, PH297, and at the same time select the related pre-adjusted user electricity meters of these monitoring points, such as: C15, C19, C20, C24, C26, C25, C30, C31;

[0067] S702. Based on the loss power consumption of the monitoring point, the number of user electricity meters not recognized, and the difference in the number of user electricity meters, find one or more combinations of user electricity meter powers (the number of user electricity meter combinations <= the number of unrecognized user electricity meters) from the pre-adjusted power grid-related user electricity meter pool through a combination traversal algorithm to meet the relative approximation standard with the loss power consumption of the monitoring point; in the combination traversal algorithm, only select the user electricity meters linearly related to the target monitoring point whose loss power consumption is currently to be compared for combination, and the combination scheme preferentially selects the scheme with the smallest number of adjusted user electricity meters; the abnormal monitoring point combination scheme for PH297 is "C30 + C31 + adjusted user electricity meter", and when selecting the adjusted user electricity meter from the neighboring monitoring points, preferentially select the neighboring user electricity meters without linear correlation until a relative approximation value is found. When none of these combination schemes meet the conditions, then select other combination schemes and continue to traverse in the same way; for example, if the loss power consumption of the PH297 abnormal monitoring point is 12.03 and the user electricity of C30 + C31 + C26 is 12.01, and the threshold change rate interval of the preset relative approximation value number of the system is (0.03, -0.03), then (12.03 - 12.01) / 12.03 = 0.001 meets the conditions). The system will automatically calculate and adjust the loss rates of the monitoring point (such as PH297) and related monitoring points (such as PH11352), as well as perform a linear correlation analysis of all non-linearly related user electricity meters after adjustment (such as the electricity of the C26 user electricity meter and the power supply of PH297, the electricity of the C25 user electricity meter and the power supply of PH11352). When the loss rate of the monitoring point is normal and all user electricity meters are linearly related, it indicates that the topology correction scheme of the monitoring point is found, and this monitoring point and all its subordinate user electricity meters are removed from the pre-adjusted power grid-related monitoring point pool and the pre-adjusted power grid-related user electricity meter pool. Otherwise, only the adjusted monitoring point is removed from the pre-adjusted power grid-related monitoring point pool, indicating that the topology correction scheme cannot 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 at the same time, C24, C26, C25, C30, and C31 will be removed. According to the above algorithm, iterate until all pre-adjusted power grid-related monitoring points are processed. The system will obtain a complete topology correction scheme. After this scheme is sent to the system user for review and approval, the system will automatically complete the topology relationship correction to obtain a more accurate power grid relationship model.

[0068] S80. Sort out the roster of abnormal electricity users, recalculate the power loss of the monitoring point based on the power grid relationship model corrected in step S70, for the monitoring points with abnormal loss rates, recalculate the linear correlation between the electricity of the user electricity meter and the power supply of the monitoring point, and mark the non-linearly related user electricity meters as suspected abnormal electricity users. Thus, the range of abnormal electricity users is relatively accurately locked. If targeted abnormal electricity analysis is carried out on these users, the hit rate will be greatly improved.

[0069] The method, medium and terminal for analyzing abnormal power consumption based on LTU and multi-dimensional data in the above-described embodiments, compared with the prior art, are complex and diverse in the prior art and difficult to supervise, and the power consumption safety is difficult to be guaranteed. The scope targeted by the method for judging abnormal power consumption of users is relatively large, and the accuracy of abnormal power consumption analysis is relatively low. The process of the present invention is simple and the operation is convenient. The management of the power grid is sunk to the smallest unit, and the LTU substation area identification technology and the automatic topology correction technology based on the analysis and iterative matching of multi-dimensional feature data such as multi-loss and linear correlation are integrated, so as to more accurately locate the abnormal power consumption range, thereby greatly improving the hit rate of abnormal power consumption users and ensuring the accuracy of abnormal power consumption analysis in the substation area.

[0070] Obviously, the above-described embodiments are only the preferred embodiments of the present invention, rather than all embodiments. The preferred embodiments of the present invention are given in the drawings, but 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 disclosed content of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing specific embodiments, or perform equivalent replacements on some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present invention in other related technical fields shall be similarly within the scope of the patent protection of the present invention.

Claims

1. A method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data, characterized in that, It includes the following steps: S10. Establish a power grid relationship model from the substation transformer to the user electricity meter; S20. Connect the electricity meter and LTU device to the master station, completely collect the electricity energy indication data of the electricity meter and LTU during a specific time period, and completely collect the topology identification data of the LTU device; S30. Match and compare the topology identification data with the power grid relationship model, automatically correct the relevant power grid hierarchical subordination relationships, put the user electricity meters for which the topology relationship cannot be identified into the pre-adjusted power grid relationship user electricity meter pool, and put the relevant monitoring points into the pre-adjusted power grid relationship monitoring point pool; S40. Calculate the loss rate data of each monitoring point according to the electricity energy indication during the specific time period and the power grid relationship model; S50. Conduct a linear correlation analysis on the user electricity meters in the pre-adjusted power grid relationship user electricity meter pool and their directly connected power supply nodes; S60. Aggregate to obtain the characteristic information matrix of each of the pre-adjusted power grid relationship monitoring points and pre-adjusted power grid relationship user electricity meters according to the power grid relationship model attributes, loss rate, and linear correlation; S70. Based on the characteristic information matrix, conduct multi-dimensional data fusion analysis and corrective topology linkage iteration to obtain a corrected power grid relationship model; S80. Based on the corrected power grid relationship model, recalculate the loss rate data of the monitoring points, and for the monitoring points with abnormal loss rates, conduct a linear correlation analysis again to obtain a list of abnormal electricity users.

2. The method for analyzing abnormal electricity 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 electrical box, and the specific content is as follows: Power grid nodes include substation transformers, main switchboards, distribution boxes, branch lines, terminal boxes, electrical boxes, and LTUs; Electricity users: user electricity meters; Relationships: upstream and downstream hierarchical topology relationships of power grid nodes, relationships between user electricity meters and directly associated power grid nodes.

3. The method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data according to claim 1, characterized in that, In step S20, the electricity energy indication data during the specific time period is 15-minute electricity energy indication data, and the data integrity rate is not less than 95%; the topology identification data is identified by micro-current signal, and the data integrity rate is not less than 90%.

4. A method for analyzing abnormal electricity 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 = (input power - output power) / input power.

5. A method for analyzing abnormal electricity 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 the abnormal phenomenon of the power supply node loss rate caused by incorrect power grid relationships.

6. The method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data according to claim 1, wherein In step S60, the characteristic information of the pre-adjusted power grid relationship monitoring points includes monitoring points, loss electricity, loss rate, whether the loss rate is abnormal, the number of user electricity meters, the number of identified user electricity meters, the difference in the number of user electricity meters, and the number of un-identified user electricity meters; the characteristic information of the pre-adjusted power grid relationship user electricity meters includes suspected user electricity meters, user electricity meter electricity, the affiliated monitoring point, the affiliated neighbor monitoring point, and whether it is linearly correlated.

7. A method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data according to claim 6, characterized in that, In step S70, the specific process of multi-dimensional data fusion analysis and corrective topology linkage iteration is as follows: S701. Select all the monitoring points with abnormal loss rates from the pre-adjusted power grid relationship monitoring points, and at the same time select the relevant pre-adjusted user electricity meters of the monitoring points; S702. According to the power loss, the number of unrecognized user electric meters, and the difference in the number of user electric meters at the monitoring point, find one or more combinations of user electric meter power that satisfy the relative approximation standard with the power loss at the monitoring point from the pre-adjusted power grid relationship user electric meter pool through a combination traversal algorithm. In the combination traversal algorithm, only select the user electric meters that are linearly related to the target monitoring point of the currently proposed power loss to be compared for combination. The combination scheme preferentially selects the scheme with the smallest number of adjusted user electric meters. When selecting adjusted user electric meters from neighboring monitoring points, preferentially select the neighboring user electric meters that are not linearly related until a relative approximation value is found. When none of the combination schemes meet the conditions, then select other combination schemes and continue to traverse in the same way.

8. A method for analyzing abnormal electricity consumption based on LTU and multi-dimensional data according to claim 7, characterized in that, The system automatically calculates and adjusts the loss rate of the monitoring point and related monitoring points, as well as the linear correlation analysis of all non-linearly related user electric meters after adjustment. When the loss rate of the monitoring point is normal and all user electric meters are linearly related, it indicates that a topology correction scheme for the monitoring point has been found, and this monitoring point and all its subordinate user electric meters are removed from the pre-adjusted power grid relationship monitoring point pool and the pre-adjusted power grid relationship user electric meter pool. Otherwise, only the adjusted monitoring point is removed from the pre-adjusted power grid relationship monitoring points, indicating that no topology correction scheme can be found for this monitoring point. After iterative cycling until all pre-adjusted power grid relationship monitoring points have been processed, the system obtains a complete topology correction scheme. After this scheme is sent to the system user for approval, the system will automatically complete the topology relationship correction to obtain the corrected power grid relationship model. For the monitoring points with abnormal loss rates, recalculate the linear correlation between the user electric meter power and the power supply of the monitoring point, and mark the non-linearly related user electric meters as suspected abnormal electricity consumption.

9. 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, it implements the method according to any one of claims 1 to 8.

10. An electronic terminal, characterized in that, 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 according to any one of claims 1 to 8.

Images