Multi-source heterogeneous data fusion verification and diagnosis method, device and equipment for power distribution network

Abstract

The embodiment of the invention provides a power distribution network multi-source heterogeneous data fusion verification and diagnosis method, device and equipment, and the method comprises the steps: constructing a data fusion frame for fusing topological structure data based on a topological structure of a power distribution network; verifying topological structure data in a layered manner, and screening abnormal data; and performing hierarchical diagnosis on the verified topology structure data to obtain diagnosis information of a corresponding hierarchy. According to the technical scheme provided by the embodiment of the invention, data formats and storage modes of data from different positions in a power distribution network topology structure are unified, and the unified data is subjected to hierarchical verification and diagnosis according to a step-by-step hierarchical mode from a transformer substation to a user load; therefore, the problems of structural difference between data of different devices on the same level and incapability of cooperative processing caused by the structural difference are solved, and the efficiency of data verification and cooperative diagnosis of each link of the power distribution network is improved.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application provides the technical field of power distribution network data processing, and particularly relates to a power distribution network multi-source heterogeneous data fusion verification and diagnosis method, device and equipment. BACKGROUND

[0002] The high-voltage and medium-voltage power distribution network (hereinafter referred to as the power distribution network) is a core link connecting power sources and users of a power system, and mainly includes a power source end, a power distribution network line topology, a user load end and an energy storage end and the like functional links; in addition, it also includes a development department, a distribution network department, a dispatching department and the like supporting links, and the above-mentioned links all generate data in their respective working processes, thereby causing a great burden on the data management of the high-voltage and medium-voltage power distribution network, which is mainly because:

[0003] 1. Differences exist between multi-source data, and the data formats of different nodes are not the same, for example, device parameters are in Excel, topologies are in CAD, and time series are in text; and for cross-link data, the semantics at different links are very different, which will cause multi-dimensional data to be unable to be associated and analyzed, resulting in data fragmentation;

[0004] 2. For the data generated by each link, the verification method often adopts manual checking, lacks a multi-dimensional collaborative verification mechanism, and no closed-loop disposal method is formed for the abnormal data found, thereby affecting power supply decision-making;

[0005] 3. Since the data formats of different links of the high-voltage and medium-voltage power distribution network are not the same, it will be difficult to perform collaborative diagnosis when the power grid has a problem that needs to be diagnosed, thereby causing the problem disposal period to be lengthened.

[0006] Therefore, a multi-dimensional heterogeneous data fusion method for the power distribution network is needed to reduce the difficulty of data verification and collaborative diagnosis of each link of the power distribution network. SUMMARY

[0007] The power distribution network multi-source heterogeneous data fusion verification and diagnosis method, device and equipment provided by the embodiment of the present application improve the effect of collaborative processing of heterogeneous data by adopting a layered verification and diagnosis method after data fusion of all data of the power distribution network topology structure.

[0008] In a first aspect, the embodiment of the present application provides a power distribution network multi-source heterogeneous data fusion verification and diagnosis method, comprising:

[0009] Based on the topology structure of the power distribution network, a data fusion framework for fusing the topology structure data is constructed;

[0010] Layered verification of the topology structure data is performed to screen abnormal data;

[0011] The layered diagnostic verification of the topology structure data is performed to obtain diagnostic information corresponding to the layer.

[0012] In a second aspect, an embodiment of the present application provides a power distribution network multi-source heterogeneous data fusion verification device, which comprises:

[0013] A data fusion framework modeling module is configured to construct a data fusion framework for fusing topology structure data based on the topology structure of the power distribution network.

[0014] An abnormal data screening module is configured to perform layered verification of the topology structure data and screen abnormal data.

[0015] A diagnostic information generation module is configured to perform layered diagnostic verification of the topology structure data to obtain diagnostic information corresponding to the layer.

[0016] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method provided by the embodiment of the present application.

[0017] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and when the computer program is executed in a computer, the computer executes the method provided by the embodiment of the present application.

[0018] The technical scheme provided by the embodiment of the present application constructs a data fusion framework for fusing topology structure data, and performs layered verification on the topology structure data, thereby screening abnormal data, and performs layered diagnosis on the topology structure data based on the foregoing layered manner, thereby obtaining diagnostic information corresponding to the layer. That is, the present application unifies the data format and storage manner of data from different positions in the topology structure of the power distribution network, and performs layered verification and diagnosis on the unified data in a manner of layering from the transformer substation to the user load, thereby overcoming the structural difference between data of different devices at the same layer and the problem of being unable to cooperatively dispose caused by the structural difference, and improving the efficiency of data verification and cooperative diagnosis of each link of the power distribution network. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 FIG. 1 is a flowchart of a power distribution network multi-source heterogeneous data fusion verification and diagnosis method provided by an embodiment of the present application;

[0020] Figure 2 FIG. 2 is a flowchart of fusing topology structure data in the power distribution network multi-source heterogeneous data fusion verification and diagnosis method provided by the embodiment of the present application;

[0021] Figure 3is a flow chart for missing value filling and correction to extend structure data in a power distribution network multi-source heterogeneous data fusion verification and diagnosis method provided by the embodiment of the present application.

[0022] Figure 4 is a flow chart for redundant data elimination to correct extended structure data in a power distribution network multi-source heterogeneous data fusion verification and diagnosis method provided by the embodiment of the present application.

[0023] Figure 5 is a flow chart for hierarchical verification to extend structure data in a power distribution network multi-source heterogeneous data fusion verification and diagnosis method provided by the embodiment of the present application.

[0024] Figure 6 is a structure block diagram of a power distribution network multi-source heterogeneous data fusion verification device provided by the embodiment of the present application.

[0025] Figure 7 is a structure schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application will be further described in detail by means of the accompanying drawings and specific embodiments.

[0027] Figure 1 is a flow chart of a power distribution network multi-source heterogeneous data fusion verification and diagnosis method provided by the embodiment of the present application, the method can be executed by a power distribution network multi-source heterogeneous data fusion verification and diagnosis device, the device can be realized by software and / or hardware, and the device can be configured in a computer or other electronic device.

[0028] As shown in Figures 1 to 5 , the technical scheme provided by the embodiment of the present application includes the following steps:

[0029] S10: based on the extension structure of the power distribution network, a data fusion framework for fusing the extension structure data is constructed; wherein the extension structure includes all structures of the power distribution network, such as all entity nodes of the power distribution network and the association relationship in the above entity nodes. For the fusion process of the extension structure data, including:

[0030] S11: Unify the data format of topology structure data; different data formats can be defined based on the data source and the characteristics of the data itself; for example, for equipment in the distribution network, which includes high-voltage substations (i.e., substations) at the power supply end, loads at the user end, and energy storage, since their respective data formats are not the same, the topology structure data of the above equipment can be uniformly defined as JSON format. Similarly, the topology structure data of departmental nodes adopts SVG format (or SVG+GIS coordinate format); for data involving time series, CSV format with timestamps is adopted, thereby establishing a cross-departmental data mapping dictionary, so as to unify the data format of data located in different topologies of the distribution network and eliminate semantic ambiguity.

[0031] S12: Correct the topology data through missing value imputation, outlier identification, and / or redundant data removal; Abnormal data may exist both during the process of using the same data format and during the initial data acquisition process, therefore, corrections are made for different situations, for example:

[0032] For missing value imputation, the specific methods include:

[0033] S121: Obtain time information for missing values;

[0034] S122: If the time information belongs to the first time interval, for example, the first time interval is less than or equal to 2 hours, then the topology data is filled by using linear interpolation to fill the adjacent data.

[0035] S123: If the time information belongs to the second time interval, for example, the second time interval is 2 hours to 24 hours, then similar historical data is obtained and the topology data is filled by fitting interpolation. The similar historical data mentioned here includes, but is not limited to, data of the same season, the same weather, and the same workday.

[0036] Furthermore, if the time information is greater than 24 hours, the topology data structure for that period is considered to be in a state of long-term missing data, requiring manual verification and manual supplementation in conjunction with equipment records. Since linear interpolation and data fitting interpolation are commonly used techniques in data analysis, they will not be elaborated upon here.

[0037] In addition, the 3σ principle can be used to identify outliers by setting a threshold for judging abnormal power grid operation. For example, the threshold can be set as "mean ± 3 standard deviations". When the data exceeds this threshold during normal operation, it is judged as abnormal. It should be added that under certain special operating conditions (such as equipment start-up and shutdown), the standard for judging the threshold can be relaxed according to the power grid threshold (such as voltage deviation and current), thereby excluding non-abnormal values.

[0038] In addition, the topology structure data is corrected by removing redundant data, specifically including:

[0039] S124: Obtain the device information and acquisition time information from the topology data; where “device information + acquisition time” is a part of the topology data, and the topology data of the corresponding device is added to the suffix;

[0040] S125: Based on the equipment information and the acquisition time information, retain the latest topology data acquired under the same equipment and at the latest acquisition time, and archive the retained data in the corresponding database.

[0041] S13: Divide the topology into nodes and the associated networks connecting the nodes. Nodes include substations, medium-voltage lines, user loads, and distributed power sources; the associated networks include business associations and responsibility associations.

[0042] The nodes include equipment nodes and departmental nodes. Equipment nodes include substations, medium-voltage lines, distributed power sources, and user loads. Classified by both the "source-grid-load-storage" business dimension and the cross-departmental dimension, the topology data includes node data and cross-departmental data. Node data includes substation data, medium-voltage line data, load forecasting data, and distributed power source storage data. Cross-departmental data includes planning data, operation and maintenance data, and scheduling data. Specifically:

[0043] Substation data includes substation ID, voltage level, capacity, commissioning year, and health status; medium-voltage line data includes medium-voltage line ID, conductor signal information, length, laying method, and load rate; distributed power storage data includes power type (photovoltaic / wind power), installed capacity, connection point, and real-time output; and load forecasting data includes load user ID, load type, power supply area, and real-time electricity consumption.

[0044] The departmental nodes include the Development Department, Distribution Network Department, and Dispatch Department. This part corresponds to the following in the topology data: planning data, namely the Development Department's scope of responsibility, data access information, and verification timeliness requirements; operation and maintenance data, namely the Distribution Network Department's operation and maintenance area information, equipment management information, and corresponding handling timeliness information; and dispatch data, namely the Dispatch Department's monitoring scope information, real-time data access information, and abnormal warning threshold information.

[0045] Furthermore, the aforementioned association management includes business associations and responsibility associations. Business associations refer to the business relationships between nodes, such as "220kV substation - power supply - 110kV substation", "220kV substation - connection - 500kV power supply point", and "medium voltage line A - ownership - substation 1", etc. Responsibility associations refer to the corresponding responsibilities of nodes, such as "verification responsibility" (e.g., "distribution network department - verification responsibility - medium voltage line load rate"), "diagnosis responsibility" (e.g., "development department - diagnosis responsibility - substation capacity ratio"), and "handling association" (e.g., "distribution network department - handling association - medium voltage line three-phase imbalance").

[0046] In general, the establishment of the above-mentioned topology structure includes each node and the associated network formed by each node. The corresponding data fusion framework performs semantic fusion on the topology structure data generated by each node.

[0047] It's worth noting that once the topology structure is established and the topology data is integrated, a hybrid database structure can be used to store the data in different formats. For example, the topology data of the equipment can be stored using a relational database like MySQL, while time-series data can be stored using a time-series database like InfluxDB. This facilitates subsequent queries and analysis. Furthermore, a differentiated storage approach is adopted for the above data to improve the rationality of data storage. For example, real-time data is retained for 1 year, historical time-series data is retained for 5 years, and static data (such as equipment ledgers) is permanently archived. A dual-active disaster recovery architecture with primary and backup databases is adopted, with a primary-backup data synchronization latency of ≤50ms, to avoid data loss due to hardware failures or natural disasters and ensure business continuity.

[0048] Next, step S20 is executed: hierarchical verification of the topology data and filtering of abnormal data; wherein, hierarchical verification specifically includes:

[0049] S21: Based on equipment information, the topology is divided into high-voltage side and medium-voltage side;

[0050] S22: Verify the topological structure data of the high-voltage side, the topological structure data of the medium-voltage side, and the topological structure data under the coordinated state of the high-voltage side and the medium-voltage side, respectively.

[0051] The high-voltage side mainly focuses on the verification of substations in the "source-grid-load-storage" system, such as capacity-to-load ratio threshold verification, power flow balance verification, and tie-line quantity verification. For capacity-to-load ratio threshold verification, based on past experience, the capacity-to-load ratio should be ≥1.6 during normal operation and ≥1.4 under heavy load conditions (such as summer peak). Capacity-to-load ratio = substation rated capacity / maximum load. For power flow balance verification, the deviation between the substation's injected power (power received from the upstream grid) and output power (power transmitted to the downstream grid) should be ≤5%. If the deviation exceeds 5%, the accuracy of the line loss calculation should be checked. For tie-line quantity verification, the number of tie lines for 220kV substations should be ≥2 to meet the "N-1" safety criterion and ensure that the load can be transferred in the event of a single line failure.

[0052] Medium-voltage side mainly refers to the verification of the remaining parts of the "source-grid-load-storage" system. The verification content includes load rate limit verification and three-phase imbalance verification. Among them, the load rate limit verification is ≤80% under normal operating conditions and ≤90% under temporary power supply during faults (such as when a line is under maintenance and the load is transferred to other lines). The three-phase imbalance verification is ≤2% under normal operating conditions and ≤4% during load fluctuation periods (such as the morning peak from 7:00 to 9:00). The imbalance is calculated by the difference in three-phase current. In addition, medium-voltage side verification also includes a correlation verification, which matches user load data with the power supply lines of the transformer area to avoid incorrect load attribution.

[0053] Collaborative verification mainly targets geographical boundary matching verification and power transfer conservation verification, primarily involving collaborative work between the high-voltage and medium-voltage sides. For example, in geographical boundary matching verification, the geographical deviation between the planned power supply area of ​​the substation and the actual coverage area of ​​the medium-voltage line is ≤500 meters, determined by GIS coordinate comparison. In power transfer conservation verification, the substation outgoing power = the total input power of the corresponding medium-voltage line × (1 - line loss rate), with a deviation of ≤3%, ensuring that there are no omissions or duplicates in the high and medium voltage power transfer statistics.

[0054] Then, step S30 is executed: the topology data after hierarchical diagnostic verification is verified to obtain the diagnostic information of the corresponding level. Since the aforementioned hierarchical verification is used, hierarchical diagnosis is preferred for the subsequent diagnostic methods, including high-pressure side diagnosis, medium-pressure side diagnosis, and high-medium-pressure combined diagnosis;

[0055] The diagnostic information for the high-voltage side includes abnormal load ratio, power supply connection defects, and equipment association anomalies. Abnormal load ratio is based on the aforementioned load ratio threshold verification. For example, an actual load ratio < 1.4 indicates a risk of overload, or > 2.0 indicates capacity redundancy. Power supply connection defects refer to insufficient connection to meet the "N-1" safety criterion (i.e., when any line, transformer, or switch in the distribution network is out of service, the remaining parts can still meet the power supply needs of all users and the grid operating parameters are within a safe range) or a load rate > 85%. Equipment association anomalies refer to equipment health scores < 70 points and operating parameters close to the threshold. In such cases, appropriate measures need to be taken by the development department, distribution network department, and dispatch department at the departmental nodes. For example, when the load ratio is < 1.4, priority is given to load transfer; if transfer is not possible, capacity expansion is carried out. When the load ratio is > 2.0, load allocation is optimized or the capacity expansion plan is adjusted. For connection defects, new / modified lines are built. Equipment problems are addressed through simultaneous maintenance and temporary power supply.

[0056] The diagnostic information for the medium-voltage side includes: feeder load rate overload, excessive three-phase imbalance, and abnormal line loss. Abnormal feeder load rate includes a load rate of >80% for ≥1 hour under normal operating conditions or >90% for ≥30 minutes under fault conditions, with a continuous ≥70% load rate for 7 consecutive days triggering a heavy load warning. Excessive three-phase imbalance is determined based on the aforementioned three-phase imbalance verification conditions. If the imbalance exceeds the threshold and persists for ≥2 hours, the source of imbalance is identified as a single-phase high-power user. Abnormal line loss is determined for example, a loss rate >5% at different voltages (e.g., 10kV >3%) or >3% at 35kV. This determination also needs to consider equipment errors, topology, and conductor type.

[0057] When the above-mentioned abnormalities occur, corresponding measures shall be taken to deal with them, namely, load cut-off or conductor capacity increase for overload / early warning; adjustment of user phase or installation of compensation device for imbalance; and optimization of path or replacement of large diameter conductor for abnormal loss.

[0058] High and medium voltage coordinated diagnostic information includes: power transmission imbalance, mismatch between power supply range and line coverage, and asynchrony between planning and operation and maintenance. Power transmission imbalance can be identified as a substation experiencing a medium voltage line input power deviation >5%; a mismatch between power supply range and line coverage can be identified as a medium voltage line deviation >500 meters or a load point not being connected to the corresponding line; and asynchrony between planning and operation and maintenance can be identified as a substation being in operation for more than 3 months without feeders being operational, resulting in a lightly loaded substation and overloaded existing lines.

[0059] When the above-mentioned abnormalities occur, corresponding measures shall be taken to deal with them, namely, checking the load statistics or line affiliation for power imbalance; adjusting the routing of medium voltage lines or the power supply range for coverage mismatch; and establishing a coordination mechanism for commissioning time for asynchronous operation, and temporarily transferring the load in case of emergency.

[0060] It should be added here that the diagnostic information obtained from high-voltage side diagnosis, medium-voltage side diagnosis, and high-medium-voltage coordinated diagnosis is fed back to the relevant departments (development department, distribution network department, and dispatch department, etc.) for joint handling. During the feedback process, the handling can be classified according to the urgency, such as emergency (handled within 24 hours), important (handled within 72 hours), and general (handled within 1 week), and the effect can be automatically verified according to the handling progress.

[0061] As an alternative verification method, this application can also adopt a cross-departmental verification method to filter out abnormal data; that is, cross-departmental verification of topology structure data and filtering out abnormal data to replace the original step S20.

[0062] Cross-departmental verification includes: confirming verification permissions, visualizing abnormal data, and tracing the source of abnormal data. Since the diagnostic phase requires collaborative handling by multiple departments within a single department node, it is necessary to confirm the permissions of each department during the verification and diagnostic process. For example, permissions can be defined according to a four-dimensional framework of "department-data type-operation permission-data range." For instance, the distribution network department can only modify the operation and maintenance data of medium-voltage lines within its jurisdiction, and cannot modify planning data; modifications to planning data by the development department must be reviewed by the dispatch department; change records are retained when permissions are dynamically adjusted, and unauthorized operations are intercepted and warned in real time.

[0063] In a preferred embodiment, for the screening of abnormal data, a heat map can be used at the macro level to display regional data deviations, with red markings for equipment / lines with load rates exceeding the upper limit and capacity ratios abnormal, and yellow markings for areas approaching the threshold; a topology map can be used at the meso level to display the data correlation deviations between substations and lines, with dashed lines marking lines with mismatched power supply ranges; and a comparison table can be used at the micro level to display the differences before and after correction of a single data entry, including data ID, correction field, original data value, new data value, and correction basis.

[0064] Furthermore, an automatic source tracing mechanism is adopted for the abnormal data obtained from the screening, that is, by tracing the data source system - acquisition equipment - data entry personnel - review personnel - historical modification records, a source tracing report is generated; if the abnormality is caused by the failure of the acquisition equipment (such as the accuracy deviation of the current transformer), a maintenance work order is automatically pushed to the distribution network department; if it is caused by manual entry error, a rectification notice is pushed to the data entry personnel and the person in charge.

[0065] The technical solution provided in this application constructs a data fusion framework for integrating topology data and performs hierarchical verification on the aforementioned topology data to filter out abnormal data. Based on the aforementioned hierarchical method, the topology data is then diagnosed hierarchically to obtain diagnostic information at the corresponding level. In other words, this application unifies the data format and storage method of data from different locations in the distribution network topology, and performs hierarchical verification and diagnosis on the unified data according to the hierarchical method from substation to user load. This overcomes the structural differences between data from different devices at the same level and the resulting inability to coordinate processing, thereby improving the efficiency of data verification and collaborative diagnosis of various links in the distribution network.

[0066] Figure 6 This application provides a multi-source heterogeneous data fusion and verification device for power distribution networks, such as... Figure 6 As shown, the device includes:

[0067] Data fusion framework construction module 01 is used to build a data fusion framework for fusing topology data based on the topology structure of the power distribution network.

[0068] Abnormal data filtering module 02 is used for hierarchical verification of topology structure data and filtering of abnormal data;

[0069] The diagnostic information generation module 03 is used to obtain the corresponding level of diagnostic information from the topological structure data after hierarchical diagnostic verification.

[0070] In one optional implementation, the fusion of topology data specifically includes:

[0071] Unify the data format of topological structure data;

[0072] Topology data is corrected by filling in missing values, identifying outliers, and / or removing redundant data.

[0073] The topology is divided into nodes and the associated networks connecting the nodes. Nodes include substations, medium-voltage lines, user loads, and distributed power sources; the associated networks include business associations and responsibility associations.

[0074] In one alternative implementation, the node further includes departmental role nodes, including the development department, distribution network department, and scheduling department.

[0075] In one alternative implementation, the topology structure data is corrected by filling in missing values, specifically including:

[0076] Obtain the time information of missing values;

[0077] If the time information belongs to the first time interval, the topology structure data is filled by linear interpolation of adjacent data.

[0078] If the time information belongs to the second time interval, similar historical data is obtained and the topology structure data is filled by fitting and interpolation.

[0079] The first time interval is less than or equal to 2 hours, and the second time interval is from 2 hours to 24 hours.

[0080] In one optional implementation, correcting the topology structure data through outlier identification further includes:

[0081] By adjusting the judgment threshold, non-abnormal information in outliers can be excluded.

[0082] In one optional implementation, the topology structure data is corrected by eliminating redundant data, specifically including:

[0083] Obtain device information and acquisition time information from the topology data;

[0084] Based on the equipment information and the acquisition time information, retain the latest topology data acquired from the same equipment at the same acquisition time.

[0085] In one optional implementation, the hierarchical verification of the topology data specifically includes:

[0086] Based on the equipment information, the topology structure is divided into a high-voltage side and a medium-voltage side;

[0087] The topological structure data of the high-voltage side, the topological structure data of the medium-voltage side, and the topological structure data of the high-voltage side and the medium-voltage side in a coordinated state are verified respectively.

[0088] like Figure 7 As shown in the figure, this application provides an electronic device, including a processor 711, a communication interface 712, a memory 713, and a communication bus 714, wherein the processor 711, the communication interface 712, and the memory 713 communicate with each other through the communication bus 714.

[0089] Memory 713 is used to store computer programs;

[0090] In one embodiment of this application, when the processor 711 executes a program stored in the memory 713, it implements the method provided in any of the foregoing method embodiments, including:

[0091] Based on the topology of the power distribution network, a data fusion framework is constructed for integrating topology data.

[0092] Validate topology data in layers and filter out abnormal data;

[0093] The topological structure data after hierarchical diagnostic verification yields diagnostic information for the corresponding level.

[0094] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method provided in any of the foregoing method embodiments.

[0095] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0097] The above embodiments are merely illustrative examples and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations. However, obvious variations or modifications derived therefrom are still within the scope of protection of this application.

Claims

1. A power distribution network multi-source heterogeneous data fusion verification and diagnosis method, characterized in that, The method comprises the following steps: Based on the topology structure of the power distribution network, a data fusion framework for fusing topology structure data is constructed; Layered verification of the topology structure data is performed to screen abnormal data; Layered diagnosis of the verified topology structure data is performed to obtain diagnosis information corresponding to the level.

2. The method of claim 1, wherein, The fused topology structure data specifically comprises: Unifying the data format of the topology structure data; The topology structure data is corrected by missing value filling, abnormal value identification and / or redundant data elimination; The topology structure is divided into nodes and associated networks connecting the nodes, the nodes including substations, medium voltage lines, user loads and distributed power sources; the associated networks including business association and responsibility association.

3. The method of claim 2, wherein, The nodes also include department role nodes, and the department nodes include development departments, distribution network departments and dispatching departments.

4. The method of claim 2, wherein, The topology structure data is corrected by missing value filling, specifically comprising: Obtaining time information of the missing value; If the time information belongs to a first time interval, the topology structure data is filled by linear interpolation of adjacent data; If the time information belongs to a second time interval, similar historical data is obtained to fill the topology structure data by fitting interpolation; Wherein the first time interval is less than or equal to 2 hours, and the second time interval is 2 hours to 24 hours.

5. The method of claim 2, wherein, The topology structure data is corrected by abnormal value identification, comprising: By adjusting the judgment threshold, non-abnormal information in the abnormal value is excluded.

6. The method of claim 2, wherein, The topology structure data is corrected by redundant data elimination, specifically comprising: Obtaining equipment information and collection time information in the topology structure data; According to the equipment information and the collection time information, the topology structure data with the latest collection time under the same equipment is retained.

7. The method of claim 6, wherein, The topology structure data is verified layer by layer, specifically comprising: According to the equipment information, the topology structure is divided into high voltage side and medium voltage side; The topology structure data of the high voltage side, the topology structure data of the medium voltage side and the topology structure data under the cooperative state of the high voltage side and the medium voltage side are verified respectively.

8. A power distribution network multi-source heterogeneous data fusion verification device, characterized in that, The method comprises the following steps: A data fusion framework construction module is used to construct a data fusion framework for fusing topology structure data based on the topology structure of the power distribution network; An abnormal data screening module is used to verify the topology structure data layer by layer to screen abnormal data; A diagnosis information generation module is used to diagnose the verified topology structure data layer by layer to obtain diagnosis information corresponding to the level.

9. An electronic device, comprising: A computer program is stored in the memory, and the processor executes the computer program to realize the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer, and when the computer program is executed in the computer, the computer executes the method of any one of claims 1-7.

Images