Dynamic updating and fault processing method, device and system for distribution network contact diagram

Abstract

The invention relates to the field of distribution network management and control, and discloses a dynamic updating and fault processing method, device and system for a distribution network contact diagram. By implementing the method and the device, accurate identification and quick response to the target detection event in the target system are realized by efficiently integrating the multi-source heterogeneous data. Specifically, the topological structure of the distribution network contact diagram can be updated in real time according to the state change of the equipment, so that the problem of low updating speed of the distribution network contact diagram in the prior art is solved, and the data updating timeliness and accuracy after the distribution network contact diagram accesses the multi-source heterogeneous data are improved; and a multi-time-scale topological snapshot can be generated, and a basis is provided for subsequent data backtracking and information query positioning of power grid operation management. Meanwhile, when a fault event is detected, a fault area can be quickly positioned, a reasonable fault processing scheme can be generated, the fault processing time can be shortened, and the reliability and stability of a power grid can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network control, and in particular to a method, device and system for dynamically updating and troubleshooting a distribution network contact diagram. Background Art

[0002] In the power system, with the continuous development of information technology, systems such as SCADA (Supervisory Control and Data Acquisition), DMS (Distribution Management System), GIS (Geographic Information System), and AMI (Advanced Metering Infrastructure) have been widely used in grid operation and management. These systems each perform different functions. For example, SCADA is responsible for collecting real-time grid operation data, DMS is used for distribution automation management, GIS provides geospatial information, and AMI collects and analyzes user electricity usage information.

[0003] However, there's currently a lack of effective mechanisms for integrating and sharing data across these systems. Disparate data formats and storage methods exist across various systems, leading to data being scattered across different platforms and difficult to manage and analyze. This makes it difficult for grid operators to fully and accurately understand the grid's operating status and identify potential problems and risks in a timely manner.

[0004] At the same time, during power grid operation, equipment status changes and failures frequently occur. Existing power grid monitoring systems are limited to simple analysis of monitoring data, with low accuracy. Furthermore, after an event is discovered, decision-making relies on operators. This results in slow and inaccurate response times, making it difficult to implement effective measures to ensure safe and stable power grid operation.

[0005] For power grid monitoring, a distribution network diagram can be used to intuitively display the grid's topology and device status. However, when device status changes, due to the aforementioned difficulties in collecting heterogeneous data and inconsistent data formats, the distribution network diagram is ineffective and cannot accurately reflect the actual operating status of the grid. Summary of the Invention

[0006] The present invention provides a method, device and system for dynamically updating and handling faults of a distribution network contact diagram, which can improve the accuracy of collecting and processing heterogeneous data, as well as the timeliness and accuracy of updating the distribution network contact diagram, while improving the efficiency of handling distribution network faults.

[0007] In order to solve the above technical problems, the first aspect of the present invention discloses a method for dynamically updating and troubleshooting a distribution network contact diagram, the method comprising:

[0008] According to the preset data synchronization mechanism, the heterogeneous data corresponding to the target system is collected, and the distribution network connection diagram corresponding to the target system is obtained at the same time; the target system includes the SCADA system, DMS system, GIS system and AMI system; the heterogeneous data is converted into standardized data of the same format by the preset data conversion module;

[0009] performing an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data; and, when the event detection result indicates the presence of a target detection event, performing an event response operation on the distribution network contact diagram according to an event attribution class corresponding to the target detection event and a corresponding event processing requirement, to obtain an event response result for the distribution network contact diagram; the event attribution class includes a first attribution class matching the device state change event and / or a second attribution class matching a preset fault event;

[0010] Wherein, when the event attribution class corresponding to the target detection event includes the first attribution class, the event response operation includes a topology structure update operation, and the topology structure update operation includes updating the distribution network contact diagram based on a preset graph calculation algorithm, mapping the device status of the distribution network contact diagram, dynamic weight adjustment of the topological edges in the distribution network contact diagram, and generation of topology snapshots based on multiple time scales; the topology structure update operation is used to update the record information of the distribution network contact diagram;

[0011] When the event classification corresponding to the target detection event includes the second classification, the event response operation includes a fault handling operation for the distribution network contact map; the fault handling operation includes fault area location based on the distribution network contact map and fault handling solution generation.

[0012] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0013] In the process of performing the event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, when a visual interaction requirement for the distribution network contact diagram is detected, constructing a three-dimensional model corresponding to the distribution network contact diagram based on a three-dimensional engine;

[0014] performing a data rendering operation on the three-dimensional model according to the heterogeneous data to obtain a target three-dimensional model corresponding to the three-dimensional model; the data rendering operation includes a data filling operation and a spatial mapping operation based on the GIS data and the AMI data, and the spatial mapping operation includes mapping geographic information corresponding to the GIS data and mapping electrical data corresponding to the AMI data;

[0015] The event response result is connected to the target three-dimensional model to perform a real-time mapping operation on the event response result through the target three-dimensional model.

[0016] As an optional implementation, in the first aspect of the present invention, the heterogeneous data includes a plurality of sub-heterogeneous data; each of the sub-heterogeneous data has a corresponding event detection method; the event detection method corresponding to each of the sub-heterogeneous data is a first detection method based on a rule engine, or a second detection method based on a machine learning model;

[0017] The performing of an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data includes:

[0018] For each of the sub-heterogeneous data, when the event detection method corresponding to the sub-heterogeneous data is the first detection method, obtaining all event detection rules corresponding to the first detection method;

[0019] Matching each of the matter detection rules with the sub-heterogeneous data execution rules to obtain a comprehensive matching result corresponding to the sub-heterogeneous data and all the matter detection rules, wherein the comprehensive matching result corresponding to the sub-heterogeneous data includes a sub-matching result corresponding to the sub-heterogeneous data and each of the matter detection rules; and the sub-matching result corresponding to the sub-heterogeneous data and each of the matter detection rules is at least used to indicate whether the sub-heterogeneous data meets the rule triggering condition of the matter detection rule;

[0020] The comprehensive matching results corresponding to all the sub-heterogeneous data are added to the event detection results for the heterogeneous data.

[0021] As an optional implementation, in the first aspect of the present invention, performing an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data further includes:

[0022] For each of the sub-heterogeneous data, when the event detection mode corresponding to the sub-heterogeneous data is the second detection mode, determining a data record type of the sub-heterogeneous data and a corresponding event detection type; the data record type includes at least one of current, voltage, temperature, and switch state; and the event detection type includes any one of voltage anomaly, grid frequency anomaly, harmonic pollution, ground fault, protection malfunction / failure to operate, and communication failure.

[0023] Determining a target machine learning model adapted to the sub-heterogeneous data from a plurality of pre-built machine learning models according to the data record type of the sub-heterogeneous data and the corresponding event detection type;

[0024] Performing deep reasoning on the sub-heterogeneous data according to the target machine learning model to obtain a deep reasoning result corresponding to the sub-heterogeneous data;

[0025] The deep reasoning results corresponding to all the sub-heterogeneous data are added to the event detection results for the heterogeneous data.

[0026] As an optional embodiment, in the first aspect of the present invention, performing an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and obtaining an event response result for the distribution network contact diagram, includes:

[0027] When the event attribution class corresponding to the target detection event includes the first attribution class, determining a graph computing algorithm that matches the target detection event, the graph computing algorithm including an incremental graph update algorithm or a distributed graph processing algorithm;

[0028] Performing a graph update operation on the distribution network contact graph according to the graph calculation algorithm and the target detection event to obtain a graph update result corresponding to the distribution network contact graph;

[0029] Determine, based on the target detection event, all target devices whose device states have changed and device state change information corresponding to each target device; the device state change information corresponding to each target device includes at least one of the following information: closing / opening information of the target device, device failure / normal information, device load rate, and device failure probability;

[0030] Performing a device state mapping operation on the graph update result according to a preset device state mapping rule and the device state change information corresponding to each target device to obtain a device state mapping result corresponding to the graph update result;

[0031] According to a preset snapshot generation strategy, combined with the target detection event and the device status change information, a topology snapshot content for the distribution network contact diagram is generated; the topology snapshot content is used to record the topology information of the distribution network contact diagram according to a timestamp.

[0032] As an optional implementation, in the first aspect of the present invention, performing a graph update operation on the distribution network contact graph according to the graph calculation algorithm and the target detection event to obtain a graph update result corresponding to the distribution network contact graph includes:

[0033] When the graph calculation algorithm is the incremental graph update algorithm, identifying, based on the target detection event, a target subgraph in the distribution network connection graph whose state has changed, the target subgraph including a first subgraph corresponding to the target detection event and a second subgraph associated with the first subgraph; determining, based on the target detection event, change information for the target subgraph, and performing a subgraph update on the target subgraph based on the change information, to obtain a subgraph update result for the target subgraph as a graph update result corresponding to the distribution network connection graph;

[0034] When the graph calculation algorithm is the distributed graph processing algorithm, all divided subgraphs corresponding to the distribution network contact graph are obtained, and all the divided subgraphs are obtained by dividing the distribution network contact graph into subgraphs according to preset regional management requirements; and the target divided subgraph corresponding to the target detection event is determined from all the divided subgraphs, and at the same time, the weight impact information of the target detection event on the remaining other divided subgraphs is calculated in parallel based on the target divided subgraph; and the weight of the subgraph boundary in each of the divided subgraphs is updated according to the target detection event and the weight impact information, to obtain the weight update results for all the divided subgraphs as the graph update results corresponding to the distribution network contact graph.

[0035] As an optional embodiment, in the first aspect of the present invention, performing an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and obtaining an event response result for the distribution network contact diagram, further includes:

[0036] When the event classification corresponding to the target detection event includes the second classification, performing fault location and location result verification on the target detection event according to a pre-trained fault processing model to obtain a fault area location result for the distribution network contact map;

[0037] According to the fault handling model, a policy generation operation is performed on the fault area locating result to obtain a fault handling policy responsive to the fault area locating result as an event response result for the distribution network contact diagram; the policy generation operation includes a multi-policy generation operation and a multi-policy evaluation operation based on the fault area locating result.

[0038] A second aspect of the present invention discloses a device for dynamically updating and troubleshooting a distribution network contact diagram, the device comprising:

[0039] The data acquisition module is used to collect heterogeneous data corresponding to the target system according to the preset data synchronization mechanism;

[0040] An acquisition module is used to acquire a distribution network connection diagram corresponding to the target system; the target system includes a SCADA system, a DMS system, a GIS system, and an AMI system; the heterogeneous data is standardized data converted into the same format by a preset data conversion module;

[0041] An event detection module, configured to perform an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data;

[0042] An event response module is configured to, when the event detection result indicates the presence of a target detection event, perform an event response operation on the distribution network contact diagram according to the event attribution class corresponding to the target detection event and the corresponding event processing requirements, thereby obtaining an event response result for the distribution network contact diagram; the event attribution class includes a first attribution class matching the device state change event and / or a second attribution class matching a preset fault event;

[0043] Wherein, when the event attribution class corresponding to the target detection event includes the first attribution class, the event response operation includes a topology structure update operation, and the topology structure update operation includes updating the distribution network contact diagram based on a preset graph calculation algorithm, mapping the device status of the distribution network contact diagram, dynamic weight adjustment of the topological edges in the distribution network contact diagram, and generation of topology snapshots based on multiple time scales; the topology structure update operation is used to update the record information of the distribution network contact diagram;

[0044] When the event classification corresponding to the target detection event includes the second classification, the event response operation includes a fault handling operation for the distribution network contact map; the fault handling operation includes fault area location based on the distribution network contact map and fault handling solution generation.

[0045] As an optional embodiment, in the second aspect of the present invention, the device further includes:

[0046] a model construction module configured to construct, in the process of performing an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, a three-dimensional model corresponding to the distribution network contact diagram based on a three-dimensional engine when a visual interaction requirement for the distribution network contact diagram is detected;

[0047] a data rendering module, configured to perform a data rendering operation on the three-dimensional model according to the heterogeneous data to obtain a target three-dimensional model corresponding to the three-dimensional model; the data rendering operation includes a data filling operation and a spatial mapping operation based on the GIS data and the AMI data, and the spatial mapping operation includes a geographic information mapping corresponding to the GIS data and an electrical data mapping corresponding to the AMI data;

[0048] A data mapping module is used to connect the event response result to the target three-dimensional model to perform a real-time mapping operation on the event response result through the target three-dimensional model.

[0049] As an optional implementation, in the second aspect of the present invention, the heterogeneous data includes a plurality of sub-heterogeneous data; each of the sub-heterogeneous data has a corresponding event detection method; the event detection method corresponding to each of the sub-heterogeneous data is a first detection method based on a rule engine, or a second detection method based on a machine learning model;

[0050] The event detection module performs event detection operations on the heterogeneous data to obtain event detection results for the heterogeneous data, specifically including:

[0051] For each of the sub-heterogeneous data, when the event detection method corresponding to the sub-heterogeneous data is the first detection method, obtaining all event detection rules corresponding to the first detection method;

[0052] Matching each of the matter detection rules with the sub-heterogeneous data execution rules to obtain a comprehensive matching result corresponding to the sub-heterogeneous data and all the matter detection rules, wherein the comprehensive matching result corresponding to the sub-heterogeneous data includes a sub-matching result corresponding to the sub-heterogeneous data and each of the matter detection rules; and the sub-matching result corresponding to the sub-heterogeneous data and each of the matter detection rules is at least used to indicate whether the sub-heterogeneous data meets the rule triggering condition of the matter detection rule;

[0053] The comprehensive matching results corresponding to all the sub-heterogeneous data are added to the event detection results for the heterogeneous data.

[0054] As an optional implementation, in the second aspect of the present invention, the matter detection module performs a matter detection operation on the heterogeneous data, and a method for obtaining a matter detection result for the heterogeneous data specifically includes:

[0055] For each of the sub-heterogeneous data, when the event detection mode corresponding to the sub-heterogeneous data is the second detection mode, determining a data record type of the sub-heterogeneous data and a corresponding event detection type; the data record type includes at least one of current, voltage, temperature, and switch state; and the event detection type includes any one of voltage anomaly, grid frequency anomaly, harmonic pollution, ground fault, protection malfunction / failure to operate, and communication failure.

[0056] Determining a target machine learning model adapted to the sub-heterogeneous data from a plurality of pre-built machine learning models according to the data record type of the sub-heterogeneous data and the corresponding event detection type;

[0057] Performing deep reasoning on the sub-heterogeneous data according to the target machine learning model to obtain a deep reasoning result corresponding to the sub-heterogeneous data;

[0058] The deep reasoning results corresponding to all the sub-heterogeneous data are added to the event detection results for the heterogeneous data.

[0059] As an optional embodiment, in the second aspect of the present invention, the event response module performs an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and obtains the event response result for the distribution network contact diagram in a manner specifically including:

[0060] When the event attribution class corresponding to the target detection event includes the first attribution class, determining a graph computing algorithm that matches the target detection event, the graph computing algorithm including an incremental graph update algorithm or a distributed graph processing algorithm;

[0061] Performing a graph update operation on the distribution network contact graph according to the graph calculation algorithm and the target detection event to obtain a graph update result corresponding to the distribution network contact graph;

[0062] Determine, based on the target detection event, all target devices whose device states have changed and device state change information corresponding to each target device; the device state change information corresponding to each target device includes at least one of the following information: closing / opening information of the target device, device failure / normal information, device load rate, and device failure probability;

[0063] Performing a device state mapping operation on the graph update result according to a preset device state mapping rule and the device state change information corresponding to each target device to obtain a device state mapping result corresponding to the graph update result;

[0064] According to a preset snapshot generation strategy, combined with the target detection event and the device status change information, a topology snapshot content for the distribution network contact diagram is generated; the topology snapshot content is used to record the topology information of the distribution network contact diagram according to a timestamp.

[0065] As an optional implementation, in the second aspect of the present invention, the event response module performs a graph update operation on the distribution network contact graph according to the graph calculation algorithm and the target detection event, and obtains a graph update result corresponding to the distribution network contact graph in a manner specifically including:

[0066] When the graph calculation algorithm is the incremental graph update algorithm, identifying, based on the target detection event, a target subgraph in the distribution network connection graph whose state has changed, the target subgraph including a first subgraph corresponding to the target detection event and a second subgraph associated with the first subgraph; determining, based on the target detection event, change information for the target subgraph, and performing a subgraph update on the target subgraph based on the change information, to obtain a subgraph update result for the target subgraph as a graph update result corresponding to the distribution network connection graph;

[0067] When the graph calculation algorithm is the distributed graph processing algorithm, all divided subgraphs corresponding to the distribution network contact graph are obtained, and all the divided subgraphs are obtained by dividing the distribution network contact graph into subgraphs according to preset regional management requirements; and the target divided subgraph corresponding to the target detection event is determined from all the divided subgraphs, and at the same time, the weight impact information of the target detection event on the remaining other divided subgraphs is calculated in parallel based on the target divided subgraph; and the weight of the subgraph boundary in each of the divided subgraphs is updated according to the target detection event and the weight impact information, to obtain the weight update results for all the divided subgraphs as the graph update results corresponding to the distribution network contact graph.

[0068] As an optional implementation, in the second aspect of the present invention, the event response module performs an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and the method of obtaining the event response result for the distribution network contact diagram specifically includes:

[0069] When the event classification corresponding to the target detection event includes the second classification, performing fault location and location result verification on the target detection event according to a pre-trained fault processing model to obtain a fault area location result for the distribution network contact map;

[0070] According to the fault handling model, a policy generation operation is performed on the fault area locating result to obtain a fault handling policy responsive to the fault area locating result as an event response result for the distribution network contact diagram; the policy generation operation includes a multi-policy generation operation and a multi-policy evaluation operation based on the fault area locating result.

[0071] A third aspect of the present invention discloses another device for dynamically updating and troubleshooting a distribution network contact diagram, the device comprising:

[0072] a memory storing executable program code;

[0073] a processor coupled to the memory;

[0074] The processor calls the executable program code stored in the memory to execute the dynamic update and fault handling method of the distribution network connection diagram disclosed in the first aspect of the present invention.

[0075] A fourth aspect of the present invention discloses a computer storage medium storing computer instructions. When the computer instructions are called, they are used to execute the dynamic update and fault handling method of the distribution network connection diagram disclosed in the first aspect of the present invention.

[0076] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0077] In an embodiment of the present invention, a method for dynamically updating and troubleshooting a distribution network contact diagram is provided, the method comprising: collecting heterogeneous data corresponding to a target system according to a preset data synchronization mechanism, and simultaneously obtaining a distribution network contact diagram corresponding to the target system; the target system comprises a SCADA system, a DMS system, a GIS system, and an AMI system; the heterogeneous data is standardized data converted into the same format by a preset data conversion module; an event detection operation is performed on the heterogeneous data to obtain an event detection result for the heterogeneous data; and, when the event detection result indicates the existence of a target detection event, an event response operation is performed on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, to obtain an event response result for the distribution network contact diagram; the event classification It includes a first attribution class that matches the device state change event and / or a second attribution class that matches the preset fault event; wherein, when the event attribution class corresponding to the target detection event includes the first attribution class, the event response operation includes a topology structure update operation, and the topology structure update operation includes updating the distribution network contact map based on a preset graph calculation algorithm, mapping the device state of the distribution network contact map, adjusting the dynamic weight of the topology edge in the distribution network contact map, and generating a topology snapshot based on multiple time scales; the topology structure update operation is used to update the record information of the distribution network contact map; when the event attribution class corresponding to the target detection event includes the second attribution class, the event response operation includes a fault handling operation for the distribution network contact map; the fault handling operation includes locating the fault area based on the distribution network contact map and generating a fault handling solution. It can be seen that the implementation of the present invention realizes accurate identification and rapid response to target detection events in the target system by efficiently integrating multi-source heterogeneous data. Specifically, the topology of the distribution network connection diagram can be updated in real time based on changes in device status, resolving the existing issue of slow update speeds. This improves the timeliness and accuracy of data updates after integrating heterogeneous data from multiple sources. It can also generate topological snapshots at multiple time scales, providing a foundation for subsequent data backtracking and information query and location in grid operation management. Furthermore, when a fault is detected, it can quickly locate the fault area and generate a reasonable fault handling plan, shortening fault handling time and improving grid reliability and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0079] Figure 1 This is a flow chart of a method for dynamically updating a distribution network contact diagram and handling faults disclosed in an embodiment of the present invention;

[0080] Figure 2 This is a flow chart of another method for dynamically updating and troubleshooting a distribution network contact diagram disclosed in an embodiment of the present invention;

[0081] Figure 3 This is a structural diagram of a device for dynamically updating and troubleshooting a distribution network contact diagram disclosed in an embodiment of the present invention;

[0082] Figure 4 It is a structural diagram of another device for dynamically updating and troubleshooting a distribution network contact diagram disclosed in an embodiment of the present invention;

[0083] Figure 5 The present invention discloses a structural diagram of a system for dynamically updating and troubleshooting a distribution network contact diagram. DETAILED DESCRIPTION

[0084] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0085] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or end comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed therein, or may optionally include other steps or elements inherent to such process, method, product, or end.

[0086] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0087] The present invention discloses a method, device and system for dynamic updating and fault handling of a distribution network contact diagram. By efficiently integrating multi-source heterogeneous data, it achieves accurate identification and rapid response to target detection events in the target system. Specifically, it can update the topological structure of the distribution network contact diagram in real time according to changes in equipment status, solving the problem of slow update speed of the distribution network contact diagram in the prior art, and improving the timeliness and accuracy of data updates after the distribution network contact diagram is connected to multi-source heterogeneous data; it can also generate topological snapshots of multiple time scales, providing a basis for subsequent data backtracking and information query positioning for power grid operation management. At the same time, when a fault event is detected, it can quickly locate the fault area and generate a reasonable fault handling plan, which is conducive to shortening the fault handling time and improving the reliability and stability of the power grid. The following are detailed descriptions.

[0088] Example 1

[0089] See also Figure 1 , Figure 1 This is a flow chart of a method for dynamically updating and troubleshooting a distribution network contact diagram disclosed in an embodiment of the present invention. Figure 1 The described method for dynamically updating and troubleshooting a distribution network contact diagram can be applied to a dynamic updating and troubleshooting device for a distribution network contact diagram, and the embodiment of the present invention does not limit this. Figure 1 As shown, the method for dynamically updating and troubleshooting the distribution network contact diagram may include the following operations:

[0090] 101. According to the preset data synchronization mechanism, the heterogeneous data corresponding to the target system is collected, and the distribution network connection diagram corresponding to the target system is obtained at the same time.

[0091] In the embodiment of the present invention, the target system includes a SCADA system, a DMS system, a GIS system, and an AMI system; the heterogeneous data is standardized data converted into the same format by a preset data conversion module.

[0092] In an embodiment of the present invention, heterogeneous data corresponding to the target system can be collected based on a pre-built data platform; and after collecting the heterogeneous data, the heterogeneous data corresponding to different systems can be converted into a data format with the same standard; and then the heterogeneous data corresponding to different systems can be synchronously transmitted according to a preset data synchronization period / frequency.

[0093] In an embodiment of the present invention, when converting heterogeneous data corresponding to different systems into the same standard data format, a data fusion algorithm can be introduced to clean, deduplicate, correlate and fuse the heterogeneous data, thereby generating high-quality consistent data.

[0094] In this embodiment of the present invention, this data is converted into standardized data in a uniform format via a pre-defined data conversion module, effectively resolving incompatibilities between data formats across different systems and enabling efficient integration of multi-source data. This makes subsequent data analysis and processing more convenient and accurate, providing a comprehensive and reliable data foundation for dynamic updates of distribution network diagrams and troubleshooting.

[0095] 102. Perform an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data.

[0096] 103. When the event detection result indicates that there is a target detection event, an event response operation is performed on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and an event response result for the distribution network contact diagram is obtained.

[0097] In the embodiment of the present invention, the event attribution class includes a first attribution class that matches a device state change event and / or a second attribution class that matches a preset fault event.

[0098] In an embodiment of the present invention, further, when the event attribution class corresponding to the target detection event includes the first attribution class, the event response operation includes a topology structure update operation, and the topology structure update operation includes updating the distribution network contact diagram based on a preset graph calculation algorithm, device status mapping for the distribution network contact diagram, dynamic weight adjustment of the topological edges in the distribution network contact diagram, and topology snapshot generation based on multiple time scales; the topology structure update operation is used to update the record information of the distribution network contact diagram.

[0099] In an embodiment of the present invention, optionally, when the event attribution class corresponding to the target detection event includes the second attribution class, the event response operation includes a fault handling operation for the distribution network contact diagram; the fault handling operation includes fault area positioning based on the distribution network contact diagram and fault handling solution generation.

[0100] In the embodiment of the present invention, by clarifying the event classification, including a first classification matching the device state change event and a second classification matching the preset fault event, it is helpful to improve the recognition accuracy for different types of events.

[0101] In this embodiment of the present invention, the distribution network interconnection diagram update, based on a preset graph calculation algorithm, can adjust the topology of the distribution network interconnection diagram in real time based on device status changes, ensuring the accuracy and real-time nature of the diagram. The device status mapping for the distribution network interconnection diagram can intuitively reflect the actual status of the devices on the interconnection diagram, making it easier for operators to understand the operation of the power grid.

[0102] In this embodiment of the present invention, the dynamic weight adjustment of topological edges can be performed based on the actual operating parameters of the power grid, such as line load and voltage, to more accurately reflect the operating status and importance of the power grid. This multi-timescale topological snapshot generation can record the state of the distribution network connection diagram at different points in time, providing rich data support for historical data analysis, fault tracing, and operational optimization of the power grid.

[0103] It can be seen that implementation Figure 1 The described method for dynamically updating and troubleshooting distribution network contact diagrams achieves accurate identification and rapid response to target detection events in the target system through the efficient integration of multi-source heterogeneous data. Specifically, it can update the topology of the distribution network contact diagram in real time based on changes in device status, resolving the issue of slow distribution network contact diagram updates in existing technologies and improving the timeliness and accuracy of data updates after integrating multi-source heterogeneous data into the distribution network contact diagram. It can also generate topological snapshots at multiple time scales, providing a foundation for subsequent data backtracking and information query and location in power grid operation management. Furthermore, when a fault event is detected, it can quickly locate the fault area and generate a reasonable fault handling plan, which helps shorten fault handling time and improve the reliability and stability of the power grid.

[0104] In an optional embodiment, the heterogeneous data includes a plurality of sub-heterogeneous data; each sub-heterogeneous data has a corresponding event detection method; the event detection method corresponding to each sub-heterogeneous data is a first detection method based on a rule engine, or a second detection method based on a machine learning model;

[0105] The above step 102 performs an event detection operation on the heterogeneous data, and the method of obtaining the event detection result for the heterogeneous data specifically includes:

[0106] For each sub-heterogeneous data, when the event detection method corresponding to the sub-heterogeneous data is the first detection method, obtain all event detection rules corresponding to the first detection method;

[0107] Matching each event detection rule with the execution rule of the sub-heterogeneous data to obtain a comprehensive matching result corresponding to the sub-heterogeneous data and all event detection rules, wherein the comprehensive matching result corresponding to the sub-heterogeneous data includes a sub-matching result corresponding to the sub-heterogeneous data and each event detection rule; and the sub-matching result corresponding to the sub-heterogeneous data and each event detection rule is used to at least indicate whether the sub-heterogeneous data meets the rule triggering condition of the event detection rule;

[0108] The comprehensive matching results corresponding to all sub-heterogeneous data are added to the event detection results for heterogeneous data.

[0109] In this optional embodiment, the all-event detection rules can be a series of anomaly detection rules defined based on grid operation experience and standards. For example: Current mutation rule: If the current of a certain line changes by more than a threshold value (such as jumping from 100A to 500A) within a specified time window (such as 1 second), an "overload event" is triggered. Switch state rule: If the switch state switches multiple times within a short period of time (such as within 5 seconds), a "switch abnormality event" is triggered. And, after defining a series of anomaly detection rules, all rules are stored in a configuration file or database (such as JSON format) for dynamic loading and updating.

[0110] In this optional embodiment, the first detection method may be implemented by relying on an open source rule engine, such as Drools, or by using a custom rule script.

[0111] It can be seen that in this optional embodiment, by setting a variety of event detection methods for each sub-heterogeneous data in the heterogeneous data, including a first detection method based on a rule engine and a second detection method based on a machine learning model, the flexibility and accuracy of event detection are improved. Among them, when adopting the first detection method based on the rule engine, by obtaining all event detection rules and performing rule matching, a comprehensive matching result for each sub-heterogeneous data is obtained, thereby ensuring the accuracy of the detection. At the same time, the detection method based on the rule engine is efficient and maintainable, and can well cope with and adapt to the detection needs of events with low complexity, which is conducive to improving detection efficiency and reducing system maintenance costs.

[0112] In another optional embodiment, the above step 102 performs an event detection operation on the heterogeneous data, and the method of obtaining the event detection result for the heterogeneous data specifically further includes:

[0113] For each sub-heterogeneous data, when the event detection mode corresponding to the sub-heterogeneous data is the second detection mode, determine the data record type of the sub-heterogeneous data and its corresponding event detection type; the data record type includes at least one of current, voltage, temperature, and switch status; the event detection type includes any one of voltage anomaly, grid frequency anomaly, harmonic pollution, ground fault, protection malfunction / failure, and communication failure;

[0114] Determining a target machine learning model adapted to the sub-heterogeneous data from a plurality of pre-built machine learning models according to the data record type of the sub-heterogeneous data and the corresponding event detection type;

[0115] Perform deep reasoning on the sub-heterogeneous data according to the target machine learning model to obtain a deep reasoning result corresponding to the sub-heterogeneous data;

[0116] The deep reasoning results corresponding to all sub-heterogeneous data are added to the event detection results for heterogeneous data.

[0117] In this optional embodiment, when the matter detection method for processing all sub-heterogeneous data includes the first detection method and the second detection method, that is, when the comprehensive matching results corresponding to the sub-heterogeneous data and the deep reasoning results corresponding to the sub-heterogeneous data are obtained at the same time, the two data can be merged / integrated / fused.

[0118] In this optional embodiment, the second detection method can first determine the data record type and event detection type. This clear classification method can accurately match the characteristics of the sub-heterogeneous data with possible abnormal events. For example, when the sub-heterogeneous data is voltage-related, the corresponding event detection type may focus on voltage anomalies. By clarifying this correspondence, it provides an accurate basis for the subsequent selection of an appropriate machine learning model, making the detection process more targeted and thus improving detection accuracy.

[0119] It can be seen that in this optional embodiment, by accurately determining the data record type and event detection type of the sub-heterogeneous data using the second detection method, and selecting a suitable target machine learning model for deep reasoning, the potential abnormal information in the data is effectively mined. Among them, the deep reasoning results of all sub-heterogeneous data are integrated into the event detection results, which realizes a comprehensive and in-depth analysis of heterogeneous data, which is conducive to improving the accuracy and completeness of event detection. At the same time, the detection method based on the machine learning model improves the intelligence and automation level of detection. Compared with the first detection method mentioned above, this detection method can better adapt to the power system's needs for highly complex event detection and ensure the safe and stable operation of the power grid.

[0120] Example 2

[0121] See also Figure 2 , Figure 2 This is a flow chart of another method for dynamically updating and troubleshooting a distribution network contact diagram disclosed in an embodiment of the present invention. Figure 2 The described method for dynamically updating and troubleshooting a distribution network contact diagram can be applied to a dynamic updating and troubleshooting device for a distribution network contact diagram, and the embodiment of the present invention does not limit this. Figure 2 As shown, the method for dynamically updating and troubleshooting the distribution network contact diagram may include the following operations:

[0122] 201. According to the preset data synchronization mechanism, the heterogeneous data corresponding to the target system is collected, and the distribution network connection diagram corresponding to the target system is obtained at the same time.

[0123] 202. Perform an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data.

[0124] 203. When the event detection result indicates that there is a target detection event, an event response operation is performed on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and an event response result for the distribution network contact diagram is obtained.

[0125] In the embodiment of the present invention, for other descriptions of steps 201 to 203, please refer to other specific descriptions of steps 101 to 103 in the first embodiment, which will not be repeated in the embodiment of the present invention.

[0126] 204. In the process of performing event response operations on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, when a visual interaction requirement for the distribution network contact diagram is detected, a three-dimensional model corresponding to the distribution network contact diagram is constructed based on the three-dimensional engine.

[0127] In the embodiment of the present invention, a basic three-dimensional model corresponding to the distribution network connection diagram can be constructed using three-dimensional graphics; the basic three-dimensional model at least includes the main elements of the distribution network connection diagram, such as substations, transmission lines, distribution equipment, etc.

[0128] The basic three-dimensional model is parameterized to update the basic three-dimensional model to obtain a three-dimensional model; the parameterized setting is at least used to set properties such as material, texture, and lighting corresponding to the basic three-dimensional model.

[0129] In the embodiments of the present invention, traditional two-dimensional distribution network diagrams have certain limitations when displaying complex grid structures and operating status. Three-dimensional models, however, provide more intuitive and realistic visuals. For example, the three-dimensional model clearly displays the spatial location, topological relationships, and operating status of grid equipment, enabling operators to more intuitively understand the actual grid situation and enhance their understanding and grasp of grid operation information.

[0130] 205. Perform a data rendering operation on the three-dimensional model according to the heterogeneous data to obtain a target three-dimensional model corresponding to the three-dimensional model; the data rendering operation includes a data filling operation and a spatial mapping operation based on GIS data and AMI data.

[0131] In the embodiment of the present invention, the spatial mapping operation includes geographic information mapping corresponding to GIS data and electrical data mapping corresponding to AMI data.

[0132] In this embodiment of the present invention, geographic information mapping corresponding to GIS data can integrate power grid equipment with their actual geographic location, giving the rendered 3D model a realistic geographic context and facilitating location-related analysis and decision-making for operators. Electrical data mapping corresponding to AMI data can accurately map the equipment's electrical parameters (such as voltage, current, and power) into the 3D model, ensuring that the model not only contains spatial information but also rich electrical operating information, providing operators with more comprehensive power grid operation data support.

[0133] 206. Connect the event response result to the target three-dimensional model to perform a real-time mapping operation on the event response result through the target three-dimensional model.

[0134] In this embodiment of the present invention, when a target detection event occurs in the power grid, the event response results (such as topology updates and fault handling solutions) are promptly reflected in the 3D model. Operators can use the 3D model to visually visualize changes in the grid status after the event is handled, such as adjustments to equipment operating status and isolation of faulty areas. This real-time mapping allows operators to more quickly understand the effectiveness of event handling and make timely decisions, improving the efficiency and accuracy of grid fault handling.

[0135] It can be seen that implementation Figure 2 The described method for dynamically updating and troubleshooting distribution network interconnection diagrams incorporates 3D visualization interaction into the distribution network interconnection diagram event response process. This method builds a 3D model based on a 3D engine and accurately renders heterogeneous data, mapping event response results to the 3D model in real time. This 3D model enhances the intuitiveness and comprehensibility of power grid information. Furthermore, the real-time mapping of event response results improves decision-making efficiency, thereby enhancing the operational safety and stability of the power grid.

[0136] In an optional embodiment, the above step 203 performs an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and obtains the event response result for the distribution network contact diagram in a manner specifically including:

[0137] When the event attribution class corresponding to the target detection event includes the first attribution class, determining a graph computing algorithm that matches the target detection event, the graph computing algorithm including an incremental graph update algorithm or a distributed graph processing algorithm;

[0138] According to the graph calculation algorithm and the target detection event, a graph update operation is performed on the distribution network contact graph to obtain a graph update result corresponding to the distribution network contact graph;

[0139] According to the target detection event, all target devices whose device status has changed and the device status change information corresponding to each target device are determined; the device status change information corresponding to each target device includes at least one of the following information: closing / opening information of the target device, device failure / normal information, device load rate, and device failure probability;

[0140] According to the preset device state mapping rules and the device state change information corresponding to each target device, a device state mapping operation is performed on the graph update result to obtain a device state mapping result corresponding to the graph update result;

[0141] According to the preset snapshot generation strategy, combined with the target detection event and the device status change information, the topology snapshot content for the distribution network contact diagram is generated; the topology snapshot content is used to record the topology information of the distribution network contact diagram according to the timestamp.

[0142] In this optional embodiment, different graph computation algorithms are suitable for different scenarios and data scales. The incremental graph update algorithm is suitable for local device status changes, enabling rapid updates to the affected portion of the graph and reducing computational effort. The distributed graph processing algorithm is suitable for large-scale power grid data, leveraging parallel processing across multiple computers to improve computational efficiency. By precisely selecting the appropriate graph computation algorithm, graph updates can be efficiently performed on the distribution network contact graph based on the characteristics of the target detection event, resulting in accurate graph update results and ensuring that the distribution network contact graph promptly reflects changes in device status.

[0143] In this optional embodiment, pre-set device status mapping rules specify how different device states are represented in the diagram. For example, different colors are used to represent device closed and open states, and different shapes and values ​​(0 / 1) are used to represent device failure and normal states. This rule-based mapping operation makes the distribution network connection diagram more intuitive, allowing operators to quickly and accurately understand the operating status of devices, improving the readability and practicality of the diagram.

[0144] In this optional embodiment, when a power grid failure occurs, the topology snapshots at different time points can be viewed to analyze the topology changes before and after the failure, and the cause and scope of the failure can be found. During the power grid operation optimization process, historical topology snapshots can also be referenced to evaluate the impact of different operation strategies on the power grid topology.

[0145] In this optional embodiment, the generated topology snapshot content may include static topology information, dynamic status information, timestamp and version identification corresponding to the distribution network connection diagram; wherein, the static topology information may include basic attribute information of nodes (such as substations, feeders) and edges (such as lines, switches) in the distribution network connection diagram; the dynamic status information may include real-time status of equipment (such as switch position, load rate), flow distribution and other information; the timestamp and version identification can be used to record the generation time and version of the snapshot, for subsequent data backtracking or comparison analysis with historical data.

[0146] It can be seen that in this optional embodiment, for device status change events, the distribution network contact diagram can be efficiently updated by accurately selecting the graph calculation algorithm, thereby improving the efficiency and accuracy of the distribution network contact diagram update. It can also fully obtain device status change information and accurately map it based on rules, while generating topology snapshots to record historical information, thereby enhancing the precision and reliability of the graph.

[0147] In another optional embodiment, the above-mentioned method of performing a graph update operation on the distribution network contact graph according to the graph calculation algorithm and the target detection event to obtain a graph update result corresponding to the distribution network contact graph specifically includes:

[0148] When the graph calculation algorithm is an incremental graph update algorithm, a target subgraph in a distribution network connection graph whose state has changed is identified based on a target detection event, the target subgraph including a first subgraph corresponding to the target detection event and a second subgraph associated with the first subgraph; change information for the target subgraph is determined based on the target detection event, and a subgraph update is performed on the target subgraph based on the change information, thereby obtaining a subgraph update result for the target subgraph as a graph update result corresponding to the distribution network connection graph;

[0149] When the graph calculation algorithm is a distributed graph processing algorithm, all divided subgraphs corresponding to the distribution network contact graph are obtained, and all divided subgraphs are obtained by dividing the distribution network contact graph into subgraphs according to preset regional management requirements; and the target divided subgraph corresponding to the target detection event is determined from all divided subgraphs, and at the same time, the weight impact information of the target detection event on the remaining other divided subgraphs is calculated in parallel based on the target divided subgraph; and the weight impact information of the target detection event is updated on the subgraph boundary in each divided subgraph according to the weight impact information of the target detection event, and the weight update result for all divided subgraphs is obtained as the graph update result corresponding to the distribution network contact graph.

[0150] In this optional embodiment, the second subgraph associated with the first subgraph may be a peripheral subgraph of the first subgraph; and after the first subgraph is changed, it may have a direct or indirect impact on the second subgraph, for example, a power outage in the first subgraph may cause a power outage in the second subgraph.

[0151] In this optional embodiment, the target subgraph includes not only the first subgraph directly corresponding to the target detection event, but also the associated second subgraphs. This comprehensive identification approach ensures that all graph regions affected by the event are accurately located, avoiding missing critical information and providing an accurate foundation for subsequent subgraph updates.

[0152] In this optional embodiment, an incremental graph update algorithm is used, which can update only the part where the status change occurs, rather than recalculating the entire distribution network connection graph, which greatly reduces the amount of calculation and is conducive to improving update efficiency and update accuracy.

[0153] In this optional embodiment, a distributed graph processing algorithm is used to partition the distribution network connection graph into subgraphs according to pre-set regional management requirements, generating all subgraphs. This partitioning approach facilitates decentralized processing of large-scale graph data, improving computational efficiency. When determining the target subgraph corresponding to a target detection event, the core area affected by the event can be quickly and accurately located, providing a clear starting point for subsequent parallel computation.

[0154] As can be seen, in this optional embodiment, by adopting an incremental graph update algorithm and a distributed graph processing algorithm, efficient and accurate updates are performed for both local and large-scale distribution network contact graph state changes. Specifically, the incremental graph update algorithm accurately identifies the target subgraph and performs local updates, reducing the amount of computation. The distributed graph processing algorithm rationally partitions the graph data, parallelizes the calculation of weight influence information, and comprehensively updates weights, improving computational efficiency. In other words, the dual-layer graph processing algorithm configuration can adapt to different distribution network management requirements, improving the real-time and accuracy of distribution network contact graph updates.

[0155] In another optional embodiment, the above-mentioned method of performing an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and obtaining the event response result for the distribution network contact diagram specifically includes:

[0156] When the event classification corresponding to the target detection event includes the second classification, the fault location and location result verification are performed on the target detection event according to the pre-trained fault processing model to obtain the fault area location result for the distribution network contact diagram;

[0157] According to the fault handling model, a policy generation operation is performed on the fault area location result to obtain a fault handling policy that responds to the fault area location result as an event response result for the distribution network contact diagram; the policy generation operation includes a multi-policy generation operation and a multi-policy evaluation operation based on the fault area location result.

[0158] As can be seen, in this optional embodiment, a pre-trained fault handling model can be used to accurately locate faults and generate and evaluate multiple fault handling strategies for each fault event. Accurate fault location improves fault handling efficiency, and the generation and evaluation of multiple strategies provides diverse solutions and ensures optimal strategy performance. This effectively improves the efficiency, accuracy, and reliability of distribution network fault handling.

[0159] Example 3

[0160] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a dynamic update and fault handling device for a distribution network contact diagram disclosed in an embodiment of the present invention. The dynamic update and fault handling device for the distribution network contact diagram can be a dynamic update and fault handling terminal, device, system or server for the distribution network contact diagram. The server can be a local server, a remote server, or a cloud server (also known as a cloud server). When the server is a non-cloud server, the non-cloud server can communicate with the cloud server, which is not limited in the embodiment of the present invention. Figure 3 As shown, the dynamic update and fault handling device for the distribution network contact diagram may include a data acquisition module 301, an acquisition module 302, an event detection module 303, and an event response module 304, wherein:

[0161] The data collection module 301 is used to collect heterogeneous data corresponding to the target system according to a preset data synchronization mechanism.

[0162] The acquisition module 302 is used to obtain the distribution network connection diagram corresponding to the target system; the target system includes the SCADA system, DMS system, GIS system and AMI system; the heterogeneous data is converted into standardized data of the same format by a preset data conversion module.

[0163] The event detection module 303 is used to perform event detection operations on heterogeneous data and obtain event detection results for the heterogeneous data.

[0164] The event response module 304 is configured to, when the event detection result indicates the presence of a target detection event, perform an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, thereby obtaining an event response result for the distribution network contact diagram; the event classification includes a first classification matching a device state change event and / or a second classification matching a preset fault event;

[0165] Among them, when the event attribution class corresponding to the target detection event includes the first attribution class, the event response operation includes a topology structure update operation, and the topology structure update operation includes updating the distribution network contact map based on a preset graph calculation algorithm, mapping the device status of the distribution network contact map, dynamic weight adjustment of the topological edges in the distribution network contact map, and generation of topology snapshots based on multiple time scales; the topology structure update operation is used to update the record information of the distribution network contact map;

[0166] When the event attribution class corresponding to the target detection event includes the second attribution class, the event response operation includes a fault handling operation for the distribution network contact map; the fault handling operation includes fault area location based on the distribution network contact map and fault handling solution generation.

[0167] It can be seen that implementation Figure 3 The described dynamic update and fault handling device for the distribution network contact diagram achieves accurate identification and rapid response to target detection events in the target system through the efficient integration of multi-source heterogeneous data. Specifically, it can update the topological structure of the distribution network contact diagram in real time based on changes in device status, solving the problem of slow distribution network contact diagram updates in the prior art and improving the timeliness and accuracy of data updates after the distribution network contact diagram is connected to multi-source heterogeneous data. It can also generate topological snapshots at multiple time scales, providing a basis for subsequent data backtracking and information query positioning for power grid operation management. At the same time, when a fault event is detected, it can quickly locate the fault area and generate a reasonable fault handling plan, which helps to shorten fault handling time and improve the reliability and stability of the power grid.

[0168] In an alternative embodiment, see Figure 4 , Figure 4 This is a schematic diagram of the structure of another dynamic update and fault handling device for a distribution network contact diagram disclosed in an embodiment of the present invention. Figure 4 As shown, the device further includes a model building module 305, a data rendering module 306 and a data mapping module 307, wherein:

[0169] The model construction module 305 is configured to construct a three-dimensional model corresponding to the distribution network contact diagram based on a three-dimensional engine when a visual interaction requirement for the distribution network contact diagram is detected during the process of executing an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements.

[0170] The data rendering module 306 is configured to perform a data rendering operation on the 3D model based on the heterogeneous data to obtain a target 3D model corresponding to the 3D model; the data rendering operation includes a data filling operation and a spatial mapping operation based on the GIS data and the AMI data, and the spatial mapping operation includes a geographic information mapping corresponding to the GIS data and an electrical data mapping corresponding to the AMI data;

[0171] The data mapping module 307 is configured to connect the event response result to the target three-dimensional model, so as to perform a real-time mapping operation on the event response result through the target three-dimensional model.

[0172] As can be seen, in this optional embodiment, by introducing 3D visualization interaction into the distribution network contact diagram event response process, building a 3D model based on a 3D engine, and utilizing heterogeneous data for precise rendering, event response results are mapped to the 3D model in real time. This 3D model construction enhances the intuitiveness and comprehensibility of power grid information. Furthermore, this real-time mapping of event response results helps improve decision-making efficiency, thereby enhancing the operational safety and stability of the power grid.

[0173] In another optional embodiment, the heterogeneous data includes a plurality of sub-heterogeneous data; each sub-heterogeneous data has a corresponding event detection method; the event detection method corresponding to each sub-heterogeneous data is a first detection method based on a rule engine, or a second detection method based on a machine learning model;

[0174] The event detection module 303 performs event detection operations on heterogeneous data, and obtains event detection results for the heterogeneous data in the following manner:

[0175] For each sub-heterogeneous data, when the event detection method corresponding to the sub-heterogeneous data is the first detection method, obtain all event detection rules corresponding to the first detection method;

[0176] Matching each event detection rule with the execution rule of the sub-heterogeneous data to obtain a comprehensive matching result corresponding to the sub-heterogeneous data and all event detection rules, wherein the comprehensive matching result corresponding to the sub-heterogeneous data includes a sub-matching result corresponding to the sub-heterogeneous data and each event detection rule; and the sub-matching result corresponding to the sub-heterogeneous data and each event detection rule is used to at least indicate whether the sub-heterogeneous data meets the rule triggering condition of the event detection rule;

[0177] The comprehensive matching results corresponding to all sub-heterogeneous data are added to the event detection results for heterogeneous data.

[0178] It can be seen that in this optional embodiment, by setting a variety of event detection methods for each sub-heterogeneous data in the heterogeneous data, including a first detection method based on a rule engine and a second detection method based on a machine learning model, the flexibility and accuracy of event detection are improved. Among them, when adopting the first detection method based on the rule engine, by obtaining all event detection rules and performing rule matching, a comprehensive matching result for each sub-heterogeneous data is obtained, thereby ensuring the accuracy of the detection. At the same time, the detection method based on the rule engine is efficient and maintainable, and can well cope with and adapt to the detection needs of events with low complexity, which is conducive to improving detection efficiency and reducing system maintenance costs.

[0179] In another optional embodiment, the event detection module 303 performs event detection operations on the heterogeneous data, and a method for obtaining event detection results for the heterogeneous data specifically includes:

[0180] For each sub-heterogeneous data, when the event detection mode corresponding to the sub-heterogeneous data is the second detection mode, determine the data record type of the sub-heterogeneous data and its corresponding event detection type; the data record type includes at least one of current, voltage, temperature, and switch status; the event detection type includes any one of voltage anomaly, grid frequency anomaly, harmonic pollution, ground fault, protection malfunction / failure, and communication failure;

[0181] Determining a target machine learning model adapted to the sub-heterogeneous data from a plurality of pre-built machine learning models according to the data record type of the sub-heterogeneous data and the corresponding event detection type;

[0182] Perform deep reasoning on the sub-heterogeneous data according to the target machine learning model to obtain a deep reasoning result corresponding to the sub-heterogeneous data;

[0183] The deep reasoning results corresponding to all sub-heterogeneous data are added to the event detection results for heterogeneous data.

[0184] It can be seen that in this optional embodiment, by accurately determining the data record type and event detection type of the sub-heterogeneous data using the second detection method, and selecting a suitable target machine learning model for deep reasoning, the potential abnormal information in the data is effectively mined. Among them, the deep reasoning results of all sub-heterogeneous data are integrated into the event detection results, which realizes a comprehensive and in-depth analysis of heterogeneous data, which is conducive to improving the accuracy and completeness of event detection. At the same time, the detection method based on the machine learning model improves the intelligence and automation level of detection. Compared with the first detection method mentioned above, this detection method can better adapt to the power system's needs for highly complex event detection and ensure the safe and stable operation of the power grid.

[0185] In another optional embodiment, the event response module 304 performs an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements. The manner of obtaining the event response result for the distribution network contact diagram specifically includes:

[0186] When the event attribution class corresponding to the target detection event includes the first attribution class, determining a graph computing algorithm that matches the target detection event, the graph computing algorithm including an incremental graph update algorithm or a distributed graph processing algorithm;

[0187] According to the graph calculation algorithm and the target detection event, a graph update operation is performed on the distribution network contact graph to obtain a graph update result corresponding to the distribution network contact graph;

[0188] According to the target detection event, all target devices whose device status has changed and the device status change information corresponding to each target device are determined; the device status change information corresponding to each target device includes at least one of the following information: closing / opening information of the target device, device failure / normal information, device load rate, and device failure probability;

[0189] According to the preset device state mapping rules and the device state change information corresponding to each target device, a device state mapping operation is performed on the graph update result to obtain a device state mapping result corresponding to the graph update result;

[0190] According to the preset snapshot generation strategy, combined with the target detection event and the device status change information, the topology snapshot content for the distribution network contact diagram is generated; the topology snapshot content is used to record the topology information of the distribution network contact diagram according to the timestamp.

[0191] It can be seen that in this optional embodiment, for device status change events, the distribution network contact diagram can be efficiently updated by accurately selecting the graph calculation algorithm, thereby improving the efficiency and accuracy of the distribution network contact diagram update. It can also fully obtain device status change information and accurately map it based on rules, while generating topology snapshots to record historical information, thereby enhancing the precision and reliability of the graph.

[0192] In another optional embodiment, the event response module 304 performs a graph update operation on the distribution network contact graph according to the graph calculation algorithm and the target detection event, and obtains a graph update result corresponding to the distribution network contact graph in a manner that specifically includes:

[0193] When the graph calculation algorithm is an incremental graph update algorithm, a target subgraph in a distribution network connection graph whose state has changed is identified based on a target detection event, the target subgraph including a first subgraph corresponding to the target detection event and a second subgraph associated with the first subgraph; change information for the target subgraph is determined based on the target detection event, and a subgraph update is performed on the target subgraph based on the change information, thereby obtaining a subgraph update result for the target subgraph as a graph update result corresponding to the distribution network connection graph;

[0194] When the graph calculation algorithm is a distributed graph processing algorithm, all divided subgraphs corresponding to the distribution network contact graph are obtained, and all divided subgraphs are obtained by dividing the distribution network contact graph into subgraphs according to preset regional management requirements; and the target divided subgraph corresponding to the target detection event is determined from all divided subgraphs, and at the same time, the weight impact information of the target detection event on the remaining other divided subgraphs is calculated in parallel based on the target divided subgraph; and the weight impact information of the target detection event is updated on the subgraph boundary in each divided subgraph according to the weight impact information of the target detection event, and the weight update result for all divided subgraphs is obtained as the graph update result corresponding to the distribution network contact graph.

[0195] As can be seen, in this optional embodiment, by adopting an incremental graph update algorithm and a distributed graph processing algorithm, efficient and accurate updates are performed for both local and large-scale distribution network contact graph state changes. Specifically, the incremental graph update algorithm accurately identifies the target subgraph and performs local updates, reducing the amount of computation. The distributed graph processing algorithm rationally partitions the graph data, parallelizes the calculation of weight influence information, and comprehensively updates weights, improving computational efficiency. In other words, the dual-layer graph processing algorithm configuration can adapt to different distribution network management requirements, improving the real-time and accuracy of distribution network contact graph updates.

[0196] In another optional embodiment, the event response module 304 performs an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, and obtains the event response result for the distribution network contact diagram in a manner that specifically includes:

[0197] When the event classification corresponding to the target detection event includes the second classification, the fault location and location result verification are performed on the target detection event according to the pre-trained fault processing model to obtain the fault area location result for the distribution network contact diagram;

[0198] According to the fault handling model, a policy generation operation is performed on the fault area location result to obtain a fault handling policy that responds to the fault area location result as an event response result for the distribution network contact diagram; the policy generation operation includes a multi-policy generation operation and a multi-policy evaluation operation based on the fault area location result.

[0199] As can be seen, in this optional embodiment, a pre-trained fault handling model can be used to accurately locate faults and generate and evaluate multiple fault handling strategies for each fault event. Accurate fault location improves fault handling efficiency, and the generation and evaluation of multiple strategies provides diverse solutions and ensures optimal strategy performance. This effectively improves the efficiency, accuracy, and reliability of distribution network fault handling.

[0200] Example 4

[0201] See also Figure 5 , Figure 5 This is a structural diagram of a dynamic update and fault handling system for a distribution network contact diagram disclosed in an embodiment of the present invention. Figure 5 As shown, the dynamic update and fault handling system of the distribution network contact diagram may include:

[0202] A memory 401 storing executable program code;

[0203] a processor 402 coupled to the memory 401;

[0204] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the method for dynamically updating and troubleshooting the distribution network connection diagram described in the first embodiment or the second embodiment of the present invention.

[0205] Example 5

[0206] An embodiment of the present invention discloses a computer storage medium storing computer instructions. When the computer instructions are called, they are used to execute the steps of the method for dynamically updating and troubleshooting a distribution network connection diagram described in the first embodiment or the second embodiment of the present invention.

[0207] Example 6

[0208] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the method for dynamically updating and troubleshooting a distribution network connection diagram described in Example 1 or Example 2.

[0209] The device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0210] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0211] Finally, it should be noted that the method, device, and system for dynamically updating and troubleshooting a distribution network contact diagram disclosed in the embodiments of the present invention are only preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for dynamically updating and troubleshooting a distribution network contact diagram, characterized in that: The method comprises: According to the preset data synchronization mechanism, the heterogeneous data corresponding to the target system is collected, and the distribution network connection diagram corresponding to the target system is obtained at the same time; the target system includes the SCADA system, DMS system, GIS system and AMI system; the heterogeneous data is converted into standardized data of the same format by the preset data conversion module; performing an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data; and, when the event detection result indicates the presence of a target detection event, performing an event response operation on the distribution network contact diagram according to an event attribution class corresponding to the target detection event and a corresponding event processing requirement, to obtain an event response result for the distribution network contact diagram; the event attribution class includes a first attribution class matching the device state change event and / or a second attribution class matching a preset fault event; Wherein, when the event attribution class corresponding to the target detection event includes the first attribution class, the event response operation includes a topology structure update operation, and the topology structure update operation includes updating the distribution network contact diagram based on a preset graph calculation algorithm, mapping the device status of the distribution network contact diagram, dynamic weight adjustment of the topological edges in the distribution network contact diagram, and generation of topology snapshots based on multiple time scales; the topology structure update operation is used to update the record information of the distribution network contact diagram; When the event classification corresponding to the target detection event includes the second classification, the event response operation includes a fault handling operation for the distribution network contact map; the fault handling operation includes fault area location based on the distribution network contact map and fault handling solution generation.

2. The method for dynamically updating and troubleshooting a distribution network connection diagram according to claim 1, characterized in that: The method further comprises: In the process of performing the event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirements, when a visual interaction requirement for the distribution network contact diagram is detected, constructing a three-dimensional model corresponding to the distribution network contact diagram based on a three-dimensional engine; performing a data rendering operation on the three-dimensional model according to the heterogeneous data to obtain a target three-dimensional model corresponding to the three-dimensional model; the data rendering operation includes a data filling operation and a spatial mapping operation based on the GIS data and the AMI data, and the spatial mapping operation includes mapping geographic information corresponding to the GIS data and mapping electrical data corresponding to the AMI data; The event response result is connected to the target three-dimensional model to perform a real-time mapping operation on the event response result through the target three-dimensional model.

3. The method for dynamically updating and troubleshooting a distribution network connection diagram according to claim 1 or 2, characterized in that: The heterogeneous data includes a plurality of sub-heterogeneous data; each of the sub-heterogeneous data has a corresponding event detection method; the event detection method corresponding to each of the sub-heterogeneous data is a first detection method based on a rule engine, or a second detection method based on a machine learning model; The performing of an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data includes: For each of the sub-heterogeneous data, when the event detection method corresponding to the sub-heterogeneous data is the first detection method, obtaining all event detection rules corresponding to the first detection method; Matching each of the matter detection rules with the sub-heterogeneous data execution rules to obtain a comprehensive matching result corresponding to the sub-heterogeneous data and all the matter detection rules, wherein the comprehensive matching result corresponding to the sub-heterogeneous data includes a sub-matching result corresponding to the sub-heterogeneous data and each of the matter detection rules; and the sub-matching result corresponding to the sub-heterogeneous data and each of the matter detection rules is at least used to indicate whether the sub-heterogeneous data meets the rule triggering condition of the matter detection rule; The comprehensive matching results corresponding to all the sub-heterogeneous data are added to the event detection results for the heterogeneous data.

4. The method for dynamically updating and troubleshooting a distribution network connection diagram according to claim 3, characterized in that: The performing of the event detection operation on the heterogeneous data to obtain event detection results for the heterogeneous data further includes: For each of the sub-heterogeneous data, when the event detection mode corresponding to the sub-heterogeneous data is the second detection mode, determining a data record type of the sub-heterogeneous data and a corresponding event detection type; the data record type includes at least one of current, voltage, temperature, and switch state; and the event detection type includes any one of voltage anomaly, grid frequency anomaly, harmonic pollution, ground fault, protection malfunction / failure to operate, and communication failure. Determining a target machine learning model adapted to the sub-heterogeneous data from a plurality of pre-built machine learning models according to the data record type of the sub-heterogeneous data and the corresponding event detection type; Performing deep reasoning on the sub-heterogeneous data according to the target machine learning model to obtain a deep reasoning result corresponding to the sub-heterogeneous data; The deep reasoning results corresponding to all the sub-heterogeneous data are added to the event detection results for the heterogeneous data.

5. The method for dynamically updating and troubleshooting a distribution network connection diagram according to claim 1, 2 or 4, characterized in that: The performing of an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirement, and obtaining an event response result for the distribution network contact diagram, includes: When the event attribution class corresponding to the target detection event includes the first attribution class, determining a graph computing algorithm that matches the target detection event, the graph computing algorithm including an incremental graph update algorithm or a distributed graph processing algorithm; Performing a graph update operation on the distribution network contact graph according to the graph calculation algorithm and the target detection event to obtain a graph update result corresponding to the distribution network contact graph; Determine, based on the target detection event, all target devices whose device states have changed and device state change information corresponding to each target device; the device state change information corresponding to each target device includes at least one of the following information: closing / opening information of the target device, device failure / normal information, device load rate, and device failure probability; Performing a device state mapping operation on the graph update result according to a preset device state mapping rule and the device state change information corresponding to each target device to obtain a device state mapping result corresponding to the graph update result; According to a preset snapshot generation strategy, combined with the target detection event and the device status change information, a topology snapshot content for the distribution network contact diagram is generated; the topology snapshot content is used to record the topology information of the distribution network contact diagram according to a timestamp.

6. The method for dynamically updating and troubleshooting a distribution network connection diagram according to claim 5, characterized in that: The performing a graph update operation on the distribution network contact graph according to the graph calculation algorithm and the target detection event to obtain a graph update result corresponding to the distribution network contact graph includes: When the graph calculation algorithm is the incremental graph update algorithm, identifying, based on the target detection event, a target subgraph in the distribution network connection graph whose state has changed, the target subgraph including a first subgraph corresponding to the target detection event and a second subgraph associated with the first subgraph; determining, based on the target detection event, change information for the target subgraph, and performing a subgraph update on the target subgraph based on the change information, to obtain a subgraph update result for the target subgraph as a graph update result corresponding to the distribution network connection graph; When the graph calculation algorithm is the distributed graph processing algorithm, all divided subgraphs corresponding to the distribution network contact graph are obtained, and all the divided subgraphs are obtained by dividing the distribution network contact graph into subgraphs according to preset regional management requirements; and the target divided subgraph corresponding to the target detection event is determined from all the divided subgraphs, and at the same time, the weight impact information of the target detection event on the remaining other divided subgraphs is calculated in parallel based on the target divided subgraph; and the weight of the subgraph boundary in each of the divided subgraphs is updated according to the target detection event and the weight impact information, to obtain the weight update results for all the divided subgraphs as the graph update results corresponding to the distribution network contact graph.

7. The method for dynamically updating and troubleshooting a distribution network connection diagram according to claim 5 or 6, characterized in that: The performing of an event response operation on the distribution network contact diagram according to the event classification corresponding to the target detection event and the corresponding event processing requirement, and obtaining an event response result for the distribution network contact diagram, further includes: When the event classification corresponding to the target detection event includes the second classification, performing fault location and location result verification on the target detection event according to a pre-trained fault processing model to obtain a fault area location result for the distribution network contact map; According to the fault handling model, a policy generation operation is performed on the fault area locating result to obtain a fault handling policy responsive to the fault area locating result as an event response result for the distribution network contact diagram; the policy generation operation includes a multi-policy generation operation and a multi-policy evaluation operation based on the fault area locating result.

8. A dynamic update and fault handling device for a distribution network contact diagram, characterized in that: The device comprises: The data acquisition module is used to collect heterogeneous data corresponding to the target system according to the preset data synchronization mechanism; An acquisition module is used to acquire a distribution network connection diagram corresponding to the target system; the target system includes a SCADA system, a DMS system, a GIS system, and an AMI system; the heterogeneous data is standardized data converted into the same format by a preset data conversion module; An event detection module, configured to perform an event detection operation on the heterogeneous data to obtain an event detection result for the heterogeneous data; An event response module is configured to, when the event detection result indicates the presence of a target detection event, perform an event response operation on the distribution network contact diagram according to the event attribution class corresponding to the target detection event and the corresponding event processing requirements, thereby obtaining an event response result for the distribution network contact diagram; the event attribution class includes a first attribution class matching the device state change event and / or a second attribution class matching a preset fault event; Wherein, when the event attribution class corresponding to the target detection event includes the first attribution class, the event response operation includes a topology structure update operation, and the topology structure update operation includes updating the distribution network contact diagram based on a preset graph calculation algorithm, mapping the device status of the distribution network contact diagram, dynamic weight adjustment of the topological edges in the distribution network contact diagram, and generation of topology snapshots based on multiple time scales; the topology structure update operation is used to update the record information of the distribution network contact diagram; When the event classification corresponding to the target detection event includes the second classification, the event response operation includes a fault handling operation for the distribution network contact map; the fault handling operation includes fault area location based on the distribution network contact map and fault handling solution generation.

9. A dynamic update and fault handling system for a distribution network contact diagram, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for dynamically updating and troubleshooting a distribution network connection diagram according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the dynamic update and fault handling method of the distribution network connection diagram according to any one of claims 1 to 7.

Images