Power grid abnormal data acquisition method, system, equipment and medium

By preset division of power data and calculating abnormal data intervals, the abnormal data is quickly judged, which solves the shortcomings of manual annotation and machine learning methods in the prior art, and realizes efficient processing of large-scale data.

CN119088798APending Publication Date: 2024-12-06TAIAN POWER SUPPLY CO OF STATE GRID SHANDONG ELECTRIC POWER CO +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411007634.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing grid abnormal data acquisition scheme does not apply to large-scale data through manual annotation, and requires a large amount of computing resources and memory through machine learning methods.

Method used

By obtaining power data and based on its source and preset division requirements, we determine the storage data table, calculate the abnormal data interval, quickly judge the abnormal data, and avoid the participation of complex machine learning algorithms.

Benefits of technology

It realizes rapid judgment of large batches of data, reduces the consumption of computing resources and memory, and solves the shortcomings of manual annotation and machine learning methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088798A_ABST
    Figure CN119088798A_ABST
Patent Text Reader

Abstract

The invention discloses a power grid abnormal data acquisition method, system and device and a medium, mainly relates to the technical field of abnormal data acquisition, and is used for solving the problem that an existing manual annotation scheme is not suitable for large-batch data; in addition, an extraction scheme of a machine learning method needs to consume a large number of computing resources and internal memories. Comprising the following steps: after all power data are added to a corresponding storage data table, determining first power data corresponding to a first preset position of overall sorting of the storage data table, and determining second power data corresponding to a second preset position of overall sorting; calculating X and Y based on formulas: X = first power data-a (second power data-first power data), Y = second power data + a (second power data-first power data); wherein a is a preset constant; (-infinity, X) and [Y, + infinity) are determined as abnormal data intervals; and determining the power data falling into the abnormal data interval as abnormal data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of abnormal data acquisition, and in particular to a method, system, device and medium for acquiring abnormal data of a power grid. Background Art

[0002] Abnormal power grid data refers to data anomalies caused by various reasons during the operation of the power grid. These abnormal data may be manifested as abnormal changes in large sections of load data, or sudden increases or decreases in load data within a period of time.

[0003] The existing scheme for acquiring abnormal data in power grids is: in the process of abnormal data mining, abnormal data is labeled and diagnosed. Labeling and diagnosis mainly include: analyzing and judging abnormal data through manual labeling and the introduction of expert knowledge. In addition, various machine learning methods, such as neural networks, support vector machines, etc., can be used to detect and classify abnormalities in power grid data of power systems. For example, historical data and target data in the power system are obtained; the possibility that the target data is abnormal power load data is obtained based on the historical data and the target data; based on the possibility that the target data is abnormal power load data, the local reachable distance of the target data in the incremental window of the target data is obtained; the abnormal degree of abnormal power load data in the target data set within the incremental window of the target data is calculated; and the abnormal power load data is monitored based on the abnormal degree of abnormal power load data.

[0004] However, the above-mentioned scheme through manual annotation is not applicable to large quantities of data; in addition, the scheme extracted by machine learning methods requires a large amount of computing resources and memory. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the present application provides a method, system, device and medium for acquiring abnormal data of a power grid to solve the problem that the existing schemes through manual labeling are not suitable for large quantities of data; in addition, the extraction schemes through machine learning methods need to consume a large amount of computing resources and memory.

[0006] In a first aspect, the present application provides a method for acquiring abnormal data of a power grid, the method comprising: acquiring a number of power data, and determining a storage data table corresponding to each power data based on the source of the power data and a preset division requirement; adding the power data to the corresponding position of the storage data table in order from small to large, and after all the power data are added to the corresponding storage data table, determining the first power data corresponding to the first preset position of the overall sorting of the storage data table, and determining the second power data corresponding to the second preset position of the overall sorting; based on the formula: X=first power data-a(second power data-first power data), Y=second power data+a(second power data-first power data), calculate X and Y; wherein a is a preset constant; determine (-∞, X] and [Y, +∞) as abnormal data intervals; determine that the power data falling into the abnormal data interval is abnormal data.

[0007] Furthermore, the sources of electricity data include: electricity consumption type, electricity consumption equipment area and data generation time period; electricity consumption type includes: industrial electricity consumption, commercial electricity consumption and residential electricity consumption; the data generation time period is divided into: preset peak time period, preset normal time period and preset low time period; the preset division requirements include: storing electricity data of the same electricity consumption type, the same electricity consumption equipment area and the same data generation time period in a storage data table.

[0008] Further, determining the first power data corresponding to the first preset position of the overall sorting of the storage data table, and determining the second power data corresponding to the second preset position of the overall sorting, specifically include: obtaining the first preset percentage and the second preset percentage; rounding the total number of the overall sorting sequence numbers * the first preset percentage, and obtaining the first power data corresponding to the sequence number after the rounding; rounding the total number of the overall sorting sequence numbers * the second preset percentage, and obtaining the second power data corresponding to the sequence number after the rounding.

[0009] Further, determining the first power data corresponding to the first preset position in the overall sorting of the storage data table, and determining the second power data corresponding to the second preset position in the overall sorting, specifically also includes: obtaining the maximum value A in the current storage data table; the minimum value B in the current storage data table; obtaining the median value C in the current storage data table; by formula: , calculate D, determine the position of the value closest to CD in the storage data table as the first preset position, and determine the first power data corresponding to the first preset position in the overall sorting of the storage data table; determine the position of the value closest to C+D in the storage data table as the second preset position, and determine the second power data corresponding to the second preset position in the overall sorting.

[0010] In a second aspect, the present application provides a power grid abnormal data acquisition system, the system comprising: a table determination module, used to acquire a number of power data, and determine the storage data table corresponding to each power data based on the source of the power data and the preset division requirements; an area determination module, used to add the power data to the corresponding position of the storage data table in order from small to large, and when all the power data are added to the corresponding storage data table, determine the first power data corresponding to the first preset position of the overall sorting of the storage data table, and determine the second power data corresponding to the second preset position of the overall sorting; based on the formula: X=first power data-a(second power data-first power data), Y=second power data+a(second power data-first power data), calculate X and Y; wherein a is a preset constant; determine (-∞, X] and [Y, +∞) as abnormal data intervals; an abnormality determination module, used to determine that the power data falling into the abnormal data interval is abnormal data.

[0011] Furthermore, the sources of power data include: power consumption type, power equipment area and data generation time period; power consumption type includes: industrial power consumption, commercial power consumption and residential power consumption; the data generation time period is divided into: preset power consumption peak time period, preset normal time period and preset valley time period; the table determination module includes a partitioning execution unit, which is used to store power data of the same power consumption type, the same power equipment area and the same data generation time period in a storage data table according to preset partitioning requirements.

[0012] Furthermore, the area determination module includes a first data determination unit, which is used to obtain a first preset percentage and a second preset percentage; rounding the total number of overall sorting sequence numbers * the first preset percentage to obtain the first power data corresponding to the rounded sequence number; rounding the total number of overall sorting sequence numbers * the second preset percentage to obtain the second power data corresponding to the rounded sequence number.

[0013] Furthermore, the region determination module includes a second data determination unit, which obtains a maximum value A in the current storage data table; a minimum value B in the current storage data table; and a median value C in the current storage data table.

[0014] By formula: , calculate D, determine the position of the value closest to CD in the storage data table as the first preset position, and determine the first power data corresponding to the first preset position in the overall sorting of the storage data table; determine the position of the value closest to C+D in the storage data table as the second preset position, and determine the second power data corresponding to the second preset position in the overall sorting.

[0015] In a third aspect, the present application provides a power grid abnormality data acquisition device, the device comprising: a processor; and a memory on which executable code is stored, and when the executable code is executed, the processor executes a power grid abnormality data acquisition method such as any one of the above items.

[0016] In a fourth aspect, the present application provides a non-volatile computer storage medium having computer instructions stored thereon, which, when executed, implement a method for acquiring abnormal power grid data as described in any one of the above items.

[0017] Those skilled in the art can understand that the present application has at least the following beneficial effects: The present application proposes a method, system, device and medium for acquiring abnormal data of a power grid. By preset division requirements, power data of the same type are placed in a storage data table. Since the same type of power data has the characteristic that data falls into a concentrated range, the minimum value X of the concentrated interval and the maximum value Y of the concentrated interval are calculated, and then (-∞, X] and [Y, +∞) are determined as abnormal data intervals. Through the abnormal data intervals, rapid judgment of data is achieved, which solves the problem that the existing scheme through manual labeling is not suitable for large quantities of data; in addition, there is no need for the participation of complex machine learning algorithms, which solves the problem that the extraction scheme through machine learning methods needs to consume a large amount of computing resources and memory. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Some embodiments of the present disclosure are described below with reference to the accompanying drawings, in which: Figure 1 It is a flow chart of a method for acquiring abnormal power grid data provided in an embodiment of the present application.

[0019] Figure 2 It is a schematic diagram of the internal structure of a power grid abnormality data acquisition system provided in an embodiment of the present application.

[0020] Figure 3 It is a schematic diagram of the internal structure of a power grid abnormality data acquisition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] It should be understood by those skilled in the art that the embodiments described below are only preferred embodiments of the present disclosure, and do not mean that the present disclosure can only be implemented through the preferred embodiments. The preferred embodiments are only used to explain the technical principles of the present disclosure, and are not used to limit the protection scope of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work should still fall within the protection scope of the present disclosure.

[0022] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0023] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0024] The present application embodiment provides a method for acquiring abnormal data of a power grid, such as Figure 1 As shown, the method provided in the embodiment of the present application mainly includes the following steps: Step 110: Acquire a number of power data, and determine a storage data table corresponding to each power data based on the source of the power data and preset division requirements.

[0025] It should be noted that the sources of electricity data include: electricity consumption type, electricity consumption equipment area and data generation time period; electricity consumption types include: industrial electricity consumption, commercial electricity consumption and residential electricity consumption; the data generation time period is divided into: preset peak electricity consumption time period, preset normal time period and preset low electricity consumption time period.

[0026] As an example, the preset division requirement may be: storing power data of the same power consumption type, the same power consumption equipment area, and the same data generation time period in one storage data table.

[0027] Step 120: Add the power data to the corresponding positions of the storage data table in ascending order. After all the power data are added to the corresponding storage data table, determine the first power data corresponding to the first preset position of the overall sorting of the storage data table, and determine the second power data corresponding to the second preset position of the overall sorting; calculate X and Y based on the formula: X=first power data-a(second power data-first power data), Y=second power data+a(second power data-first power data); determine (-∞, X] and [Y, +∞) as abnormal data intervals.

[0028] It should be noted that a is a preset constant, which is generally 1.6.

[0029] Since the storage data table has the characteristic of data aggregation of the same type, the present application can obtain the first power data and the second power data through a ratio-limited solution. The first power data and the second power data can also be calculated through a rectangular graph division solution.

[0030] The scheme for obtaining the first power data and the second power data by proportional limitation may specifically be as follows: Obtain the first preset percentage and the second preset percentage; round the total number of overall sorting sequence numbers * the first preset percentage to obtain the first power data corresponding to the rounded sequence numbers; round the total number of overall sorting sequence numbers * the second preset percentage to obtain the second power data corresponding to the rounded sequence numbers.

[0031] It should be noted that, due to the relatively concentrated phenomenon of data values, the value range of the first preset percentage is (0.1, 0.2), and the value range of the second preset percentage is (0.8, 0.9).

[0032] The scheme for calculating the first power data and the second power data by dividing the rectangular graph may be specifically as follows: Get the maximum value A in the current storage data table; get the minimum value B in the current storage data table; get the median value C in the current storage data table.

[0033] By formula: , calculate D, determine the position of the value closest to CD in the storage data table as the first preset position, and determine the first power data corresponding to the first preset position in the overall sorting of the storage data table; determine the position of the value closest to C+D in the storage data table as the second preset position, and determine the second power data corresponding to the second preset position in the overall sorting.

[0034] Step 130: Determine that the power data falling into the abnormal data interval is abnormal data.

[0035] besides, Figure 2 A power grid abnormality data acquisition system is provided in an embodiment of the present application. Figure 2 As shown, the system provided in the embodiment of the present application mainly includes: The table determination module 210 is used to obtain a number of power data and determine the storage data table corresponding to each power data based on the source of the power data and the preset division requirements.

[0036] It should be noted that the sources of electricity data include: electricity consumption type, electricity consumption equipment area and data generation time period; electricity consumption types include: industrial electricity consumption, commercial electricity consumption and residential electricity consumption; the data generation time period is divided into: preset peak electricity consumption time period, preset normal time period and preset low electricity consumption time period.

[0037] The table determination module 210 includes a partition execution unit for storing power data of the same power consumption type, the same power consumption equipment area and the same data generation time period into a storage data table according to preset partition requirements.

[0038] The area determination module 220 is used to add the power data to the corresponding positions of the storage data table in ascending order. After all the power data are added to the corresponding storage data table, determine the first power data corresponding to the first preset position of the overall sorting of the storage data table, and determine the second power data corresponding to the second preset position of the overall sorting; based on the formula: X=first power data-a(second power data-first power data), Y=second power data+a(second power data-first power data), calculate X and Y; where a is a preset constant; determine (-∞, X] and [Y, +∞) as abnormal data intervals.

[0039] Since the storage data table has the characteristic of data aggregation of the same type, the present application can obtain the first power data and the second power data through a ratio-limited solution. The first power data and the second power data can also be calculated through a rectangular graph division solution.

[0040] The scheme for obtaining the first power data and the second power data by proportional limitation may specifically be as follows: The first data determination unit in the area determination module 220 obtains the first preset percentage and the second preset percentage; rounds the total number of overall sorting sequence numbers * the first preset percentage to obtain the first power data corresponding to the rounded sequence number; rounds the total number of overall sorting sequence numbers * the second preset percentage to obtain the second power data corresponding to the rounded sequence number.

[0041] The scheme for calculating the first power data and the second power data by dividing the rectangular graph may be specifically as follows: The second data determination unit in the region determination module 220 obtains the maximum value A in the current storage data table; the minimum value B in the current storage data table; and the median value C in the current storage data table.

[0042] By formula: , calculate D, determine the position of the value closest to CD in the storage data table as the first preset position, and determine the first power data corresponding to the first preset position in the overall sorting of the storage data table; determine the position of the value closest to C+D in the storage data table as the second preset position, and determine the second power data corresponding to the second preset position in the overall sorting.

[0043] The abnormality determination module 230 is used to determine that the power data falling into the abnormal data interval is abnormal data.

[0044] The above is a method embodiment of the present application. Based on the same inventive concept, the present application embodiment also provides a power grid abnormality data acquisition device. Figure 3As shown, the device includes: a processor; and a memory, on which executable codes are stored. When the executable codes are executed, the processor executes a method for acquiring abnormal power grid data as described in the above embodiment.

[0045] Specifically, the server obtains a number of power data, determines the storage data table corresponding to each power data based on the source of the power data and the preset division requirements; adds the power data to the corresponding position of the storage data table in order from small to large, and when all the power data are added to the corresponding storage data table, determines the first power data corresponding to the first preset position of the overall sorting of the storage data table, and determines the second power data corresponding to the second preset position of the overall sorting; calculates X and Y based on the formula: X=first power data-a(second power data-first power data), Y=second power data+a(second power data-first power data); wherein a is a preset constant; determines (-∞, X] and [Y, +∞) as abnormal data intervals; determines that the power data falling into the abnormal data interval is abnormal data.

[0046] In addition, an embodiment of the present application further provides a non-volatile computer storage medium on which executable instructions are stored. When the executable instructions are executed, a method for acquiring abnormal power grid data as described above is implemented.

[0047] So far, the technical solutions of the present disclosure have been described in combination with the above multiple embodiments, but it is easy for those skilled in the art to understand that the protection scope of the present disclosure is not limited to these specific embodiments. Without departing from the technical principles of the present disclosure, those skilled in the art can split and combine the technical solutions in the above-mentioned various embodiments, and can also make equivalent changes or replacements to the relevant technical features. Any changes, equivalent replacements, improvements, etc. made within the technical concept and / or technical principle of the present disclosure will fall within the protection scope of the present disclosure.

Claims

1. A method for acquiring abnormal data of power grid, It is characterized in that The method comprises: Acquire a number of power data, and determine a storage data table corresponding to each power data based on the source of the power data and preset division requirements; Add the power data to the corresponding position of the storage data table in ascending order. When all the power data are added to the corresponding storage data table, determine the first power data corresponding to the first preset position of the overall sorting of the storage data table, and determine the second power data corresponding to the second preset position of the overall sorting; calculate X and Y based on the formula: X=first power data-a(second power data-first power data), Y=second power data+a(second power data-first power data); where a is a preset constant; determine (-∞, X] and [Y, +∞) as abnormal data intervals; The power data falling into the abnormal data interval is determined as abnormal data.

2. The method for acquiring abnormal power grid data according to claim 1, It is characterized in that The sources of power data include: power consumption type, power consumption equipment area and data generation time period; power consumption type includes: industrial power consumption, commercial power consumption and residential power consumption; data generation time period is divided into: preset power consumption peak time period, preset average time period and preset low power consumption time period; The preset division requirements include: storing power data of the same power consumption type, the same power consumption equipment area and the same data generation time period in one storage data table.

3. The method for acquiring abnormal power grid data according to claim 1, It is characterized in that Determining the first power data corresponding to the first preset position in the overall sorting of the storage data table, and determining the second power data corresponding to the second preset position in the overall sorting specifically includes: Obtaining a first preset percentage and a second preset percentage; Rounding the total number of the overall sorting sequence numbers*the first preset percentage to obtain the first power data corresponding to the sequence numbers after the rounding; The total number of the overall sorting sequence numbers*the second preset percentage is rounded to obtain the second power data corresponding to the sequence numbers after the rounding.

4. The method for acquiring abnormal power grid data according to claim 1, It is characterized in that Determining the first power data corresponding to the first preset position in the overall sorting of the storage data table, and determining the second power data corresponding to the second preset position in the overall sorting, specifically also includes: Get the maximum value A in the current storage data table; get the minimum value B in the current storage data table; Get the median value C in the current storage data table; By formula: , calculate D, determine the position of the value closest to CD in the storage data table as the first preset position, and determine the first power data corresponding to the first preset position in the overall sorting of the storage data table; The position of the value closest to C+D in the storage data table is determined as the second preset position, and the second power data corresponding to the second preset position in the overall sorting is determined.

5. A power grid abnormal data acquisition system, It is characterized in that The system comprises: A table determination module, used to obtain a number of power data, and determine a storage data table corresponding to each power data based on the source of the power data and preset division requirements; The area determination module is used to add the power data to the corresponding position of the storage data table in the order from small to large. After all the power data are added to the corresponding storage data table, determine the first power data corresponding to the first preset position of the overall sorting of the storage data table, and determine the second power data corresponding to the second preset position of the overall sorting; calculate X and Y based on the formula: X=first power data-a(second power data-first power data), Y=second power data+a(second power data-first power data); wherein a is a preset constant; determine (-∞, X] and [Y, +∞) as abnormal data intervals; The abnormality determination module is used to determine that the power data falling into the abnormal data interval is abnormal data.

6. The power grid abnormality data acquisition system according to claim 5, It is characterized in that The sources of power data include: power consumption type, power consumption equipment area and data generation time period; power consumption type includes: industrial power consumption, commercial power consumption and residential power consumption; data generation time period is divided into: preset power consumption peak time period, preset average time period and preset low power consumption time period; The table determination module includes a partition execution unit, It is used to store the power data of the same power consumption type, the same power consumption equipment area and the same data generation time period into a storage data table according to preset division requirements.

7. The power grid abnormality data acquisition system according to claim 5, It is characterized in that The region determination module includes a first data determination unit, Used to obtain a first preset percentage and a second preset percentage; Rounding the total number of the overall sorting sequence numbers*the first preset percentage to obtain the first power data corresponding to the sequence numbers after the rounding; The total number of the overall sorting sequence numbers*the second preset percentage is rounded to obtain the second power data corresponding to the sequence numbers after the rounding.

8. The power grid abnormality data acquisition system according to claim 5, It is characterized in that The area determination module includes a second data determination unit, Get the maximum value A in the current storage data table; get the minimum value B in the current storage data table; Get the median value C in the current storage data table; By formula: , calculate D, determine the position of the value closest to CD in the storage data table as the first preset position, and determine the first power data corresponding to the first preset position in the overall sorting of the storage data table; The position of the value closest to C+D in the storage data table is determined as the second preset position, and the second power data corresponding to the second preset position in the overall sorting is determined.

9. A device for acquiring abnormal data of power grid, It is characterized in that The device comprises: processor; and a memory having executable codes stored thereon, which, when the executable codes are executed, enable the processor to execute a method for acquiring abnormal power grid data as described in any one of claims 1 to 4.

10. A non-volatile computer storage medium, It is characterized in that Computer instructions are stored thereon, and when the computer instructions are executed, a method for acquiring abnormal data of a power grid as described in any one of claims 1 to 4 is implemented.

Citation Information

Patent Citations

  • Method for detecting electricity stealing on basis of electricity utilization behavior patterns of electric energy users and application

    CN108593990A

  • Data anomaly discrimination method for electric power big data

    CN113987031A

  • Database construction method suitable for massive electric power carbon emission big data analysis

    CN115587218A

  • Regional power utilization enterprise data trend analysis system and method, and medium

    CN118014386A