A power grid data lineage management system

Abstract

The invention discloses a power grid data lineage management system, which relates to the technical field of data management. The invention comprises: a power grid data acquisition module, a power grid lineage data analysis module, a power grid lineage data processing module and a local database. The invention integrates the historical data of each substation equipment belonging to the power grid, analyzes the lineage abnormality correlation coefficient of each data of the substation equipment belonging to the power grid, and dynamically adjusts the abnormal weight factor value of each data accordingly, thereby improving the early warning accuracy of the substation equipment and reducing the failure rate of the substation equipment. By analyzing the lineage similarity between each outage substation equipment belonging to the power grid and each estimated fault substation equipment and each fault type, the predicted outage cause of each outage substation equipment belonging to the power grid and the estimated fault cause of each estimated fault substation equipment are quickly determined, thereby improving the maintenance efficiency of the substation equipment and improving the operation efficiency of the substation equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a power grid data lineage management system. Background Art

[0002] With the development of power grids, the number of substation equipment in power grids is increasing, which not only generates a huge amount of data, but also causes more and more damage to substation equipment. With limited human resources, it is often difficult to determine the fault type in a timely manner for a large number of faulty substation equipment, resulting in a decrease in operation and maintenance rate. Data lineage technology can better predict and identify faults through past data, thereby reducing the occurrence of faults. Therefore, it is necessary to manage the substation equipment of the power grid through data lineage technology.

[0003] Prior art, such as the invention patent application with announcement number: CN115658668A, discloses a centralized disciplinary inspection data management method and system for a power grid, the method comprising: this invention can collect and manage the data required for disciplinary inspection scattered in various systems, form a unified data format and standard, and establish a blood relationship between subsystem data and disciplinary inspection data for data and indicators of concern to disciplinary inspection, regularly clean the collected data, and uniformly perform data backup management to improve the management quality of disciplinary inspection data.

[0004] Prior art, such as the invention patent application with announcement number: CN106934538B, discloses a power grid data fusion method based on data lineage and gene comparison, which includes: the method constructs a lineage relationship between the business system data of each department, and genetically compares and associates the business units of different departments according to the data lineage relationship, thereby effectively solving the practical problems of lack of unified planning and management of the association relationship between multiple business system data of multiple power grids, inconsistent granularity of business data, difficulty in data governance, and difficulty in data fusion.

[0005] It can be seen from the above scheme that the current power grid data lineage management system lacks certain attention to the dynamic adjustment of the weight value of abnormal data based on the historical data of each substation belonging to the power grid. During the use of each substation belonging to the power grid, due to the environment, materials used and aging, the weight factors of the impact of different data on the substation will change. If the weight factor is not dynamically adjusted, it is easy for the substation to have signs of failure but no timely warning, thereby reducing the accuracy of the warning of the substation and increasing the failure rate of the substation. At the same time, there is a lack of attention to the fault diagnosis of the cause of the outage of the substation. Due to the large number of substations belonging to the power grid, when encountering a failure in the substation, the maintenance personnel need to first determine the type of failure and then prepare for the fault repair. In the case of insufficient human resources, it is easy to have a low operation and maintenance speed, thereby reducing the maintenance efficiency of the substation and reducing the operation efficiency of the substation. Summary of the invention

[0006] The purpose of the present invention is to provide a power grid data lineage management system that solves the problems existing in the background technology.

[0007] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a power grid data lineage management system, including: a power grid data acquisition module, which is used to obtain the operating status of each substation equipment belonging to the power grid and the characteristic values ​​of each data at the current monitoring time point.

[0008] The power grid lineage data analysis module is used to obtain the fault status and characteristic values ​​of each substation equipment in the power grid at each historical monitoring time point, analyze the lineage abnormality correlation coefficient of each data of the substation equipment in the power grid, and calculate the estimated fault coefficient of each substation equipment in the power grid at the current monitoring time point.

[0009] The power grid lineage data processing module is used to screen the outage substations and estimated fault substations belonging to the power grid, analyze the predicted outage reasons of each outage substation belonging to the power grid, and evaluate the estimated fault reasons of each estimated fault substation belonging to the power grid, and send the predicted outage reasons of each outage substation belonging to the power grid and the estimated fault reasons of each estimated fault substation to the person in charge of the power grid.

[0010] The beneficial effects of the present invention are as follows: (1) The power grid data acquisition module of the present invention acquires data of each substation equipment belonging to the power grid, thereby facilitating subsequent analysis.

[0011] (2) The power grid lineage data analysis module of the present invention integrates the historical data of each substation belonging to the power grid, analyzes the lineage anomaly correlation coefficient of each data of the substation belonging to the power grid, and dynamically adjusts the abnormal weight factor value of each data accordingly, thereby reducing the occurrence rate of the problem that the substation has signs of failure but no timely warning is given, thereby improving the warning accuracy of the substation equipment and reducing the failure rate of the substation equipment.

[0012] (3) The power grid lineage data processing module of the present invention can quickly determine the predicted outage causes of each outage substation belonging to the power grid and the predicted fault causes of each predicted fault substation by analyzing the lineage similarity between each outage substation belonging to the power grid and each predicted fault substation and each fault type, thereby facilitating maintenance personnel to make initial preparations and reducing the time spent on determining the fault type, thereby improving the maintenance efficiency of the substation equipment and enhancing the operating efficiency of the substation equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0014] Figure 1 It is a schematic diagram of the system module of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Reference Figure 1 As shown, the present invention provides a power grid data lineage management system, including: a power grid data acquisition module, a power grid lineage data analysis module, a power grid lineage data processing module and a local database.

[0017] It should be noted that the power grid data acquisition module is connected to the power grid lineage data analysis module, the power grid lineage data analysis module is connected to the power grid lineage data processing module, and the local database is connected to the power grid lineage data analysis module and the power grid lineage data processing module.

[0018] It should also be noted that the local database is used to store the fault status of each substation belonging to the power grid at each historical monitoring time point and the characteristic value of each data, the appropriate characteristic value of each data, the abnormal fluctuation coefficient threshold, the initial abnormal weight factor value of each data, the abnormal weight factor adjustment value corresponding to each occupied percentage deviation coefficient interval, the estimated fault coefficient threshold, and the fault type of each faulty substation belonging to the power grid at each historical monitoring time point.

[0019] The power grid data acquisition module is used to acquire the operating status of each substation equipment belonging to the power grid and the characteristic values ​​of each data at the current monitoring time point.

[0020] In a specific embodiment, the operating status of each substation belonging to the power grid and the characteristic value of each data are obtained by a specific method: the operating status of each substation belonging to the power grid is obtained through a power grid terminal, and the characteristic value of each data of each substation belonging to the power grid is obtained through a data collection sensor.

[0021] It should be noted that the operating status includes: normal operating status and stopped operating status.

[0022] It should also be noted that if the operating status of a substation belonging to the power grid at the current monitoring time point is a stopped operating state, the characteristic values ​​of the data at the moment the substation stops operating will be used as the characteristic values ​​of the data of the substation belonging to the power grid at the current monitoring time point.

[0023] It should also be noted that the characteristic values ​​of each data include: the characteristic values ​​of each power data and the characteristic values ​​of each environmental data, wherein each power data includes: output end voltage peak-to-peak value, output end current peak-to-peak value and input end voltage peak-to-peak value and other power data, and each environmental data includes: temperature value, humidity value, air pressure value and other environmental data.

[0024] The power grid data acquisition module of the present invention acquires data of each substation equipment belonging to the power grid, thereby facilitating subsequent analysis.

[0025] The power grid lineage data analysis module is used to obtain the fault status of each substation belonging to the power grid and the characteristic value of each data at each historical monitoring time point, analyze the lineage abnormality correlation coefficient of each data of the substation belonging to the power grid, and calculate the estimated fault coefficient of each substation belonging to the power grid at the current monitoring time point.

[0026] In a specific embodiment, the fault status of each substation equipment belonging to the power grid and the characteristic value of each data at each historical monitoring time point are obtained, and the specific acquisition method is: obtaining the fault status of each substation equipment belonging to the power grid and the characteristic value of each data at each historical monitoring time point from the local database.

[0027] It should be noted that the fault state includes a faulty state and a non-faulty state.

[0028] In a specific embodiment of the present invention, the bloodline abnormality correlation coefficient of each data of the substation equipment belonging to the power grid is analyzed, and its specific analysis method is: based on the fault status of each substation equipment belonging to the power grid at each historical monitoring time point, each faulty substation equipment and each normal substation equipment belonging to the power grid at each historical monitoring time point is screened.

[0029] According to the characteristic values ​​of each data of each substation belonging to the power grid at each historical monitoring time point, the characteristic values ​​of each data of each faulty substation belonging to the power grid and the characteristic values ​​of each data of each normal substation belonging to the power grid at each historical monitoring time point are extracted, and the abnormal fluctuation coefficient of each data of each faulty substation belonging to the power grid at each historical monitoring time point is calculated. , where x represents the number of each historical monitoring time point, , y is a positive integer greater than 2, n represents the number of each fault substation equipment, , m is a positive integer greater than 2, i represents the number of each data, , j is a positive integer greater than 2.

[0030] Evaluate the triggering frequency threat coefficient of each data of the fault substation of the power grid at each historical monitoring time point .

[0031] Analyze the abnormal correlation coefficient of each data of the substation equipment in the power grid , where y is the number of historical monitoring time points.

[0032] In a specific embodiment, the screening of each faulty substation and each normal substation belonging to the power grid at each historical monitoring time point, the specific screening method is: if the fault state of a substation belonging to the power grid at a certain historical monitoring time point is a faulty state, then the substation is marked as a faulty substation, otherwise, the substation is marked as a normal substation, thereby screening each faulty substation and each normal substation belonging to the power grid at each historical monitoring time point.

[0033] In a specific embodiment of the present invention, the abnormal fluctuation coefficient of each data of each fault substation belonging to the power grid at each historical monitoring time point is calculated by the specific calculation method as follows: based on the characteristic value of each data of each normal substation belonging to the power grid at each historical monitoring time point, the average characteristic value of each data of the normal substation belonging to the power grid at each historical monitoring time point is calculated. .

[0034] Obtain appropriate characteristic values ​​for each data from the local database, analyze the characteristic value set of each data of the normal substation equipment of the power grid at each historical monitoring time point based on the average characteristic value and appropriate characteristic value of each data of the normal substation equipment of the power grid at each historical monitoring time point .

[0035] Based on the characteristic values ​​of each data of each fault substation in the power grid at each historical monitoring time point , calculate the abnormal fluctuation coefficient of each data of each fault substation of the power grid at each historical monitoring time point .

[0036] In a specific embodiment, the analysis is performed on a set of characteristic values ​​of each data of a normal substation equipment belonging to a power grid at each historical monitoring time point, and the specific analysis method is as follows: if the average characteristic value of a certain data of a normal substation equipment belonging to a power grid at a certain historical monitoring time point is greater than a suitable characteristic value, then the average characteristic value of the data is used as the upper limit value of the interval of the characteristic value set, and the suitable characteristic value of the data is used as the lower limit value of the interval of the characteristic value set.

[0037] If the average eigenvalue of a certain data of a normal substation belonging to a power grid at a certain historical monitoring time point is less than the appropriate eigenvalue, the average eigenvalue of the data is used as the lower limit of the interval of the eigenvalue set, and the appropriate eigenvalue of the data is used as the upper limit of the interval of the eigenvalue set.

[0038] If the average eigenvalue of a certain data of a normal substation belonging to a power grid at a certain historical monitoring time point is equal to the appropriate eigenvalue, the average eigenvalue of the data is taken as the only value in the eigenvalue set.

[0039] A set of characteristic values ​​of various data of normal substation equipment belonging to the power grid at each historical monitoring time point is summarized.

[0040] In a specific embodiment of the present invention, the triggering number threat coefficient of each data of a faulty substation belonging to a power grid at each historical monitoring time point is evaluated, and its specific evaluation method is: obtaining an abnormal fluctuation coefficient threshold from a local database, if the abnormal fluctuation coefficient of a certain data of a certain faulty substation belonging to a power grid at a certain historical monitoring time point is greater than the abnormal fluctuation coefficient threshold, then marking the data as abnormal data, thereby screening each abnormal data of each faulty substation belonging to the power grid at each historical monitoring time point, and mapping to obtain the number of faulty substations with each abnormal data in the power grid at each historical monitoring time point , where p represents the number of abnormal data. , q is a positive integer greater than 2.

[0041] According to the substation equipment of the power grid at each historical monitoring time point, the number of substation equipment of the power grid at each historical monitoring time point is counted , calculate the triggering frequency threat coefficient of each abnormal data of the fault substation equipment of the power grid at each historical monitoring time point , where e is represented by a natural constant.

[0042] If the abnormal fluctuation coefficients of a certain data of each faulty substation belonging to the power grid at a certain historical monitoring time point are all less than or equal to the abnormal fluctuation coefficient threshold, the triggering number threat coefficient of the data of the faulty substation belonging to the power grid at that historical monitoring time point is recorded as 0.

[0043] Summarize the triggering frequency threat coefficient of each data of the faulty substation equipment belonging to the power grid at each historical monitoring time point.

[0044] In a specific embodiment of the present invention, the estimated fault coefficient of each substation belonging to the power grid at the current monitoring time point is calculated by: evaluating the target abnormal weight factor value of each data of the substation belonging to the power grid according to the abnormal correlation coefficient of each data of the substation belonging to the power grid .

[0045] According to the characteristic values ​​of each data of each substation equipment in the power grid , where r represents the number of each substation equipment, , s is a positive integer greater than 2, and according to the appropriate eigenvalue of each data , calculate the estimated failure coefficient of each substation equipment in the power grid at the current monitoring time point , where j represents the number of data.

[0046] In a specific embodiment of the present invention, the target abnormal weight factor value of each data of the substation equipment belonging to the power grid is evaluated, and the specific evaluation method is: based on the blood relationship abnormality correlation coefficient of each data of the substation equipment belonging to the power grid , calculate the percentage of abnormal correlation coefficient of each data of the substation equipment in the power grid .

[0047] Get the initial abnormal weight factor value of each data from the local database , calculate the percentage of initial abnormal weight factors of each data of the substation equipment in the power grid .

[0048] Calculate the percentage deviation coefficient of each data of the substation equipment belonging to the power grid .

[0049] Obtain the abnormal weight factor adjustment parameter value corresponding to each percentage deviation coefficient interval from the local database, and map it to obtain the abnormal weight factor adjustment parameter value of each data of the substation equipment belonging to the power grid .

[0050] It should be noted that the larger the occupancy percentage deviation coefficient is, the larger the abnormal weight factor adjustment parameter value is, and the abnormal weight factor adjustment parameter value can be either positive or negative.

[0051] Calculate the target abnormal weight factor value of each data of the substation equipment belonging to the power grid .

[0052] The power grid lineage data analysis module of the present invention integrates the historical data of each substation belonging to the power grid, analyzes the lineage abnormality correlation coefficient of each data of the substation belonging to the power grid, and dynamically adjusts the abnormal weight factor value of each data accordingly, thereby reducing the occurrence rate of the problem that the substation has signs of failure but no timely warning is given, thereby improving the warning accuracy of the substation equipment and reducing the failure rate of the substation equipment.

[0053] The power grid lineage data processing module is used to screen the outage substations and estimated fault substations belonging to the power grid, analyze the predicted outage reasons of the outage substations belonging to the power grid, and evaluate the estimated fault reasons of the estimated fault substations belonging to the power grid, and send the predicted outage reasons of the outage substations and the estimated fault reasons of the estimated fault substations belonging to the power grid to the person in charge of the power grid.

[0054] In a specific embodiment of the present invention, the specific screening method for screening each outage substation and each estimated fault substation belonging to the power grid is as follows: if the operating status of a substation belonging to the power grid at the current monitoring time point is a stopped operating status, then the substation is marked as an outage substation; otherwise, an estimated fault coefficient threshold is obtained from a local database; if the estimated fault coefficient of the substation belonging to the power grid at the current monitoring time point is greater than the estimated fault coefficient threshold, then the substation is marked as an estimated fault substation, thereby screening each outage substation and each estimated fault substation belonging to the power grid at the current monitoring time point.

[0055] In a specific embodiment of the present invention, the predicted outage reasons of each outage substation belonging to the power grid are analyzed, and the specific analysis method is: obtaining the fault type of each faulty substation belonging to the power grid at each historical monitoring time point from the local database, and mapping each faulty substation of each fault type belonging to the power grid at each historical monitoring time point.

[0056] Calculate the blood relationship characteristic value of each data of each fault type of the substation equipment belonging to the power grid , where u represents each fault type, , w is a positive integer greater than 2.

[0057] According to the characteristic values ​​of each data of each substation belonging to the power grid, the characteristic values ​​of each data of each outage substation belonging to the power grid are extracted. , where D represents the serial number of each out-of-service substation equipment, , E is a positive integer greater than 2, and the blood relationship similarity coefficient between each outage substation equipment in the power grid and each fault type is calculated .

[0058] The fault type with the largest similarity coefficient between the power grid and each outage substation is selected, and is used as the predicted outage cause of each outage substation in the power grid.

[0059] In a specific embodiment of the present invention, the blood relationship characteristic value of each data of each fault type of the substation equipment belonging to the power grid is calculated by mapping the characteristic value of each data of each fault substation equipment belonging to each fault type of the power grid at each historical monitoring time point according to the abnormal fluctuation coefficient of each data of each fault substation equipment belonging to the power grid at each historical monitoring time point. .

[0060] Calculate the blood relationship characteristic value of each data of each fault type of the substation equipment belonging to the power grid .

[0061] In a specific embodiment of the present invention, the estimated fault cause of each estimated fault substation belonging to the power grid is evaluated by a specific evaluation method: based on the method of analyzing the predicted outage cause of each outage substation belonging to the power grid, the estimated fault cause of each estimated fault substation belonging to the power grid is evaluated by the same method.

[0062] The power grid lineage data processing module of the present invention analyzes the lineage similarity between each outage substation equipment and each predicted fault substation equipment and each fault type, and quickly determines the predicted outage cause of each outage substation equipment belonging to the power grid and the predicted fault cause of each predicted fault substation equipment, thereby facilitating maintenance personnel to make initial preparations and reducing the time spent on determining the fault type, thereby improving the maintenance efficiency of the substation equipment and enhancing the operating efficiency of the substation equipment.

[0063] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A power grid data lineage management system, characterized in that: include: The power grid data acquisition module is used to obtain the operating status of each substation equipment in the power grid and the characteristic values ​​of each data at the current monitoring time point; The power grid lineage data analysis module is used to obtain the fault status of each substation equipment in the power grid and the characteristic value of each data at each historical monitoring time point, analyze the lineage abnormality correlation coefficient of each data of the substation equipment in the power grid, and calculate the estimated fault coefficient of each substation equipment in the power grid at the current monitoring time point; The power grid lineage data processing module is used to screen the outage substation equipment and the estimated fault substation equipment belonging to the power grid, analyze the predicted outage reasons of the outage substation equipment belonging to the power grid, evaluate the estimated fault reasons of the estimated fault substation equipment belonging to the power grid, and send the predicted outage reasons of the outage substation equipment and the estimated fault reasons of the estimated fault substation equipment to the person in charge of the power grid; The specific analysis method of analyzing the abnormal correlation coefficient of blood relationship of each data of the substation equipment belonging to the power grid is as follows: According to the fault status of each substation equipment belonging to the power grid at each historical monitoring time point, each faulty substation equipment and each normal substation equipment belonging to the power grid at each historical monitoring time point are screened; According to the characteristic values ​​of each data of each substation belonging to the power grid at each historical monitoring time point, the characteristic values ​​of each data of each faulty substation belonging to the power grid and the characteristic values ​​of each data of each normal substation belonging to the power grid at each historical monitoring time point are extracted, and the abnormal fluctuation coefficient of each data of each faulty substation belonging to the power grid at each historical monitoring time point is calculated. , where x represents the number of each historical monitoring time point, , y is a positive integer greater than 2, n represents the number of each fault substation equipment, , m is a positive integer greater than 2, i represents the number of each data, j is a positive integer greater than 2; Evaluate the triggering frequency threat coefficient of each data of the fault substation of the power grid at each historical monitoring time point ; Analyze the abnormal correlation coefficient of each data of the substation equipment in the power grid , where y is the number of historical monitoring time points.

2. A power grid data lineage management system according to claim 1, characterized in that: The specific calculation method of calculating the abnormal fluctuation coefficient of each data of each fault substation of the power grid at each historical monitoring time point is as follows: According to the characteristic values ​​of each data of each normal substation equipment in the power grid at each historical monitoring time point, the average characteristic value of each data of the normal substation equipment in the power grid at each historical monitoring time point is calculated. ; Obtain appropriate characteristic values ​​for each data from the local database, analyze the characteristic value set of each data of the normal substation equipment of the power grid at each historical monitoring time point based on the average characteristic value and appropriate characteristic value of each data of the normal substation equipment of the power grid at each historical monitoring time point ; Based on the characteristic values ​​of each data of each fault substation in the power grid at each historical monitoring time point , calculate the abnormal fluctuation coefficient of each data of each fault substation of the power grid at each historical monitoring time point .

3. A power grid data lineage management system according to claim 2, characterized in that: The specific evaluation method of evaluating the triggering number threat coefficient of each data of the fault substation of the power grid at each historical monitoring time point is as follows: The abnormal fluctuation coefficient threshold is obtained from the local database. If the abnormal fluctuation coefficient of a certain data of a certain faulty substation belonging to the power grid at a certain historical monitoring time point is greater than the abnormal fluctuation coefficient threshold, the data is marked as abnormal data, thereby filtering the abnormal data of each faulty substation belonging to the power grid at each historical monitoring time point, and mapping the number of faulty substations with each abnormal data in the power grid at each historical monitoring time point. , where p represents the number of abnormal data. q is a positive integer greater than 2; According to the substation equipment of the power grid at each historical monitoring time point, the number of substation equipment of the power grid at each historical monitoring time point is counted , calculate the triggering frequency threat coefficient of each abnormal data of the fault substation equipment of the power grid at each historical monitoring time point , where e is represented as a natural constant; If the abnormal fluctuation coefficients of a certain data of each fault substation of the power grid at a certain historical monitoring time point are all less than or equal to the abnormal fluctuation coefficient threshold, the triggering number threat coefficient of the data of the fault substation of the power grid at the historical monitoring time point is recorded as 0; Summarize the triggering frequency threat coefficient of each data of the faulty substation equipment belonging to the power grid at each historical monitoring time point.

4. A power grid data lineage management system according to claim 2, characterized in that: The specific calculation method of calculating the estimated failure coefficient of each substation equipment in the power grid at the current monitoring time point is as follows: According to the blood relationship anomaly correlation coefficient of each data of the substation equipment belonging to the power grid, the target anomaly weight factor value of each data of the substation equipment belonging to the power grid is evaluated. ; According to the characteristic values ​​of each data of each substation equipment in the power grid , where r represents the number of each substation equipment, s is a positive integer greater than 2, and is calculated based on the appropriate eigenvalues ​​of each data. , calculate the estimated failure coefficient of each substation equipment in the power grid at the current monitoring time point , where j represents the number of data.

5. A power grid data lineage management system according to claim 4, characterized in that: The specific evaluation method of evaluating the target abnormal weight factor value of each data of the substation equipment belonging to the power grid is as follows: According to the abnormal correlation coefficient of each data of the substation equipment belonging to the power grid , calculate the percentage of abnormal correlation coefficient of each data of the substation equipment in the power grid ; Get the initial abnormal weight factor value of each data from the local database , calculate the percentage of initial abnormal weight factors of each data of the substation equipment in the power grid ; Calculate the percentage deviation coefficient of each data of the substation equipment belonging to the power grid ; Obtain the abnormal weight factor adjustment parameter value corresponding to each percentage deviation coefficient interval from the local database, and map it to obtain the abnormal weight factor adjustment parameter value of each data of the substation equipment belonging to the power grid ; Calculate the target abnormal weight factor value of each data of the substation equipment belonging to the power grid .

6. A power grid data lineage management system according to claim 1, characterized in that: The specific screening method of screening each out-of-service substation equipment and each estimated fault substation equipment belonging to the power grid is as follows: If the operating status of a substation belonging to the power grid at the current monitoring time point is a stopped operating state, the substation is marked as a stopped substation. Otherwise, the estimated fault coefficient threshold is obtained from the local database. If the estimated fault coefficient of the substation belonging to the power grid at the current monitoring time point is greater than the estimated fault coefficient threshold, the substation is marked as an estimated faulty substation, thereby screening out the stopped substations and estimated faulty substations belonging to the power grid at the current monitoring time point.

7. A power grid data lineage management system according to claim 1, characterized in that: The specific analysis method of analyzing the predicted outage reasons of each outage substation equipment in the power grid is as follows: Obtaining the fault type of each fault substation belonging to the power grid at each historical monitoring time point from the local database, and mapping to obtain each fault substation of each fault type belonging to the power grid at each historical monitoring time point; Calculate the blood relationship characteristic value of each data of each fault type of the substation equipment belonging to the power grid , where u represents each fault type, , w is a positive integer greater than 2; According to the characteristic values ​​of each data of each substation belonging to the power grid, the characteristic values ​​of each data of each outage substation belonging to the power grid are extracted. , where D represents the number of each out-of-service substation equipment, E is a positive integer greater than 2, and the blood relationship similarity coefficient between each outage substation equipment in the power grid and each fault type is calculated. ; The fault type with the largest blood relationship similarity coefficient between the power grid and each outage substation is selected, and is used as the predicted outage cause of each outage substation belonging to the power grid.

8. A power grid data lineage management system according to claim 7, characterized in that: The specific calculation method of calculating the blood relationship characteristic value of each data of each fault type of the substation equipment belonging to the power grid is as follows: According to the abnormal fluctuation coefficient of each data of each fault substation belonging to the power grid at each historical monitoring time point, the characteristic value of each data of each fault substation belonging to each fault type of the power grid at each historical monitoring time point is mapped. ; Calculate the blood relationship characteristic value of each data of each fault type of the substation equipment belonging to the power grid .

9. A power grid data lineage management system according to claim 7, characterized in that: The specific evaluation method of evaluating the estimated fault cause of each estimated fault substation equipment belonging to the power grid is as follows: Based on the method of analyzing the predicted outage causes of each outage substation belonging to the power grid, the predicted failure causes of each predicted failure substation belonging to the power grid are similarly evaluated.

Images