Synchronous line loss intelligent diagnosis and analysis system and method based on electric power knowledge graph

Abstract

The invention relates to a synchronous line loss intelligent diagnosis and analysis system based on an electric power knowledge graph. The synchronous line loss intelligent diagnosis and analysis system comprises a data acquisition layer, a data access layer, a data storage layer, a data analysis layer and a visualization layer, the data acquisition layer is used for acquiring power grid node data; the data access layer is used for carrying out dynamic synchronization on power grid node data based on Apache Kafka; the data storage layer comprises a time sequence database and a graph database; the data analysis layer comprises a detection module and an inference engine; and the visualization layer is used for dynamically displaying a propagation path and node characteristics of an abnormal region based on a topological structure of the knowledge graph, and querying an abnormal reason of the node and the influence on the whole system by clicking the node of the device. According to the invention, intelligent detection and diagnosis of the line loss abnormal area are realized, and the problem root cause is rapidly identified.

Description

Technical Field

[0001] The present invention relates to the field of line loss analysis, and particularly to a synchronous line loss intelligent diagnosis and analysis system and method based on a power knowledge graph. Background Art

[0002] With the continuous expansion of the scale of the power system and the gradual improvement of the requirements for power supply reliability, the analysis and management of line loss in power grid operation have become one of the key concerns of power enterprises. As an important indicator to measure the power transmission and distribution efficiency, the level of synchronous line loss directly reflects the degree of energy loss in the power transmission and distribution process, and at the same time affects the economy of power grid operation and the fairness of user power consumption. However, due to the complex power grid structure, the complexity of multi-source data, and the diversity of line loss causes (such as equipment aging, line loss, illegal power consumption, etc.), traditional line loss detection and analysis methods often have the following deficiencies: The data comes from multiple heterogeneous systems (such as SCADA systems, GIS, metering systems, etc.), which cannot be efficiently integrated, lacking global semantic associations and background information; Behind the high line loss, there may be multiple complex factors such as equipment problems, unreasonable topological structures, or abnormal user behaviors, which require further intelligent analysis and evaluation; With the dynamic change of power grid load, traditional static analysis methods are difficult to capture anomalies and locate the source of problems in a timely manner. Summary of the Invention

[0003] In order to solve the above problems, the purpose of the present invention is to provide a synchronous line loss intelligent diagnosis and analysis system based on a power knowledge graph, which realizes intelligent detection and diagnosis of line loss abnormal areas and quickly identifies the root causes of problems.

[0004] To achieve the above purpose, the present invention adopts the following technical solutions: A synchronous line loss intelligent diagnosis and analysis system based on a power knowledge graph includes a data acquisition layer, a data access layer, a data storage layer, a data analysis layer, and a visualization layer; The data acquisition layer obtains power grid node data; The data access layer establishes a real-time streaming data analysis framework Apache Kafka to dynamically synchronize the power grid node data; The data storage layer includes a time series database and a graph database, stores the time series data in the time series database, and the graph database stores the topology and semantic relationships of the power grid based on the power network knowledge graph; The data analysis layer includes a detection module and an inference engine. The detection module extracts dynamic data from the time series database, identifies abnormal nodes and time periods, and extracts the topological structure from the graph database to analyze the propagation path of the anomaly; The inference engine combines the power network knowledge graph, constructs a causal chain based on the detection results, infers the root cause of the anomaly, and matches the anomaly pattern to identify possible fault types; Visualization layer, based on the topological structure of the knowledge graph, dynamically displays the propagation path of the abnormal area and the node characteristics. By clicking on the device node, the abnormal cause of the node and its impact on the entire system can be queried.

[0005] Furthermore, the power grid node data includes device sensor data, industrial protocol data, smart meter data, and power grid operation and maintenance historical data; the industrial protocol data is accessed through a protocol adapter, the device sensor data is accessed through a message middleware; the smart meter data is accessed through the AMI system; the power grid operation and maintenance historical data is batch imported through the Rest API or ETL tool.

[0006] Furthermore, a real-time streaming data analysis framework Apache Kafka is established to dynamically synchronize the power grid node data, as follows: A distributed MQTT message broker is adopted to decode the real-time data into a standardized format; KafkaProducer is used to convert the data into message units in the Topic message queue for subsequent consumption; each type of data is mapped to a different Kafka Topic to achieve the separation and management of real-time data streams; multiple Topics are divided according to the data source and task requirements, topic-node-data is responsible for the real-time node data of the power grid, including voltage, current, and load fluctuations; topic-user-behavior is responsible for data related to abnormal user load and electricity consumption behavior; topic-ops-data is responsible for the historical records of power grid equipment operation and maintenance; and Kafka partitions are designed according to the data scale and load.

[0007] Furthermore, the graph database stores the topology and semantic relationships of the power grid based on the power network knowledge graph, as follows: The power network knowledge graph G=(V, E, A) includes entities V, relationships E, and semantic attributes A, as follows: Entities V include power grid equipment, regional division, and user nodes; Relationships E include physical connections between devices, regional ownership, and electricity consumption behavior; Semantic attribute A is a characteristic description of each entity or relationship; Entities and relationships: Device set V e ={v1, v2, …, v i , …, v n}; Region set V r ={r1, r2, …, r m}; Connection relationship set , indicating the physical connection between devices: E c ={(v i, v j ) | Device v i Connected to device v j There is a connection Attribute modeling: For any v i ∈ V e , define its attribute as A(v i ) = {a1, a2, …, a k}; Calculate the shortest connection path L(i, j) between device v i and device v j : ; where d(e) is the weight of edge e; P is a subset of the connection relation set E c in the graph, representing all possible connection paths between node i and node j; path represents the actual specific path; Upstream propagation impact simulation: For a certain device failure, determine its impact on the upstream node V upstream : ; where, means there is a path from node v i that can reach node f; Divide the load subnet according to the region and connection relationship , for partition analysis: ; where, means that node v is directly connected to the nodes in the set V e through the edge e in the graph; And associate the measurement data di(t) in the time series database with the node attributes A(vi) in the graph database.

[0008] Furthermore, the detection module extracts dynamic data from the time series database, identifies abnormal nodes and time periods, and extracts the topological structure from the graph database to analyze the propagation path of anomalies, specifically as follows: Extract dynamic data from the time series database and identify abnormal nodes and time periods; Extract the time series data of each power grid node from the time series database ; Apply threshold detection, sliding window statistics, and prediction error methods to determine whether each node is abnormal at each moment; Define the abnormal indication function :

[0009] Collect all the nodes that exist at any time t as : ; ; where is the value range of time t; For each collected node , according to the continuous time segments , determine the set of abnormal time periods : ; Obtain the marked abnormal nodes V abnormal and the abnormal time periods T abnormal ; According to the abnormal nodes and the power grid knowledge graph, calculate the shortest paths from the abnormal nodes to other nodes; analyze and obtain the upstream or downstream propagation influence ranges.

[0010] Furthermore, according to the abnormal nodes and the power grid knowledge graph, calculate the shortest paths from the abnormal nodes to other nodes; analyze and obtain the upstream or downstream propagation influence ranges, specifically as follows: Starting from the abnormal node v k ∈V abnormal , calculate the shortest path from the abnormal node to other nodes v j : ; If a certain abnormal node v f is set as the fault point, then all nodes v f that can be connected to v i through paths are regarded as being affected by the upstream of the fault point, and the upstream propagation range is obtained: ;Downstream propagation range: ; For the path from the abnormal node v f to any affected node v ∈ V affected , calculate the total cost of the propagation path C ( P f,v ):

[0011] where P f,v is the shortest path from v f to v.

[0012] Furthermore, in combination with the power grid knowledge graph, a causal chain is constructed based on the detection results to infer the root cause of the anomaly, match the anomaly pattern, and identify possible fault types, as follows: For each detected abnormal node v f , query the upstream related entities and relationships using the power grid knowledge graph, construct a candidate causal chain {P i} and calculate its weight W(P i ); determine the main causal chain by comparing the weights to infer the possible root cause; Form an abnormal subgraph G a with the abnormal node V a and the associated relationships E anomaly , G anomaly = (V a , E a ); Compare with the preset fault mode template M k , and calculate the matching degree S(M k , G anomaly ): ; When the matching degree S(M k , G anomaly ) exceeds the threshold θ m , it is considered that the anomaly highly matches the pattern M k , thus identifying the fault type; V k , E k are the abnormal nodes and the associated relationships of the pattern M k respectively; Based on the comprehensive causal chain analysis and pattern matching results, an anomaly diagnosis report is output, including the inference of the fault root cause, the fault type, and corresponding suggestions.

[0013] Furthermore, based on the topological structure of the knowledge graph, dynamically display the propagation path and node characteristics of the abnormal area, and query the cause of the anomaly of the node and its impact on the entire system by clicking on the device node, as follows: Extract the latest anomaly detection results, causal chains, and propagation paths from the time series database, graph database, and knowledge graph to form a graphical data structure; Use WebSocket to achieve real-time communication between the front end and the back end to ensure that the visualization interface reflects the state changes in a timely manner; Based on the graph database, use a graphical display engine to render the real-time topology graph and dynamically mark the abnormal area, propagation path, and node status; After the user clicks on a device node, the details of the device node are queried through the REST API and the detailed results are displayed in a pop-up window or sidebar.

[0014] Furthermore, a graphical display engine is used to render the real-time topology map, and the abnormal areas, propagation paths, and node states are dynamically marked as follows: Each device node shows its normal / abnormal state through different colors, sizes, or shapes. Abnormal devices are marked in red, and information about the abnormal time period or abnormal level is prompted on the node. Based on the data in the graph database, the connection relationships of each device are drawn, and the thickness or transparency of the edges reflects the edge weights and transmission costs. When an abnormal propagation path is detected, the connection line of the path is highlighted in a different color to indicate the abnormal propagation direction and path weight. Using the power knowledge graph data, the upstream and downstream causal chains related to the abnormality are embedded between the nodes, or the key relationships are displayed on the graph in the form of floating annotations to visually show the root cause of the fault and its propagation mechanism.

[0015] A synchronous line loss intelligent diagnosis and analysis method based on a power knowledge graph includes the following steps: S1: Obtain power grid node data, and perform dynamic synchronization on the power grid node data through the real-time streaming data analysis framework Apache Kafka; S2: Store the time series data in a dynamic database, and the graph database stores the topology and semantic relationships of the power grid based on the power network knowledge graph; S3: Extract dynamic data from the time series database, identify abnormal nodes and time periods, and extract the topology from the graph database to analyze the abnormal propagation path; S4: Construct a causal chain based on the detection results, infer the root cause of the abnormality, and match the abnormal pattern to identify possible fault types; S5: Based on the topology of the knowledge graph, dynamically display the propagation path and node characteristics of the abnormal area. By clicking on a device node, query the abnormal cause of the node and its impact on the entire system.

[0016] The present invention has the following beneficial effects: 1. The present invention effectively solves the problem of synchronous line loss diagnosis in large-scale power grids, and effectively improves the power operation efficiency and economic benefits; 2. The present invention obtains the data of each node of the power grid in real time through the data acquisition layer, and uses Apache Kafka to achieve real-time streaming synchronization of data in the data access layer, ensuring that the system can timely capture the operation status and abnormal dynamics of the power grid, and based on the collaborative work of the time series database and the graph database, it can not only record the historical data of the equipment, but also reflect the real-time topology and semantic relationship of the power grid, thereby providing comprehensive data support for subsequent analysis; 3. The detection module of the present invention can accurately identify abnormal nodes and abnormal time periods from the time series data. At the same time, combined with the power grid topology information in the graph database, it deeply analyzes the propagation path of abnormal events in the network, helps the operation and maintenance personnel to timely discover potential risks, and uses the power network knowledge graph to construct a causal chain, and infers the root cause of the abnormality based on the abnormal detection results, which not only improves the accuracy of fault diagnosis, but also provides a basis for subsequent decision-making and processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is the system architecture diagram of the present invention; Figure 2 is the method flow chart in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following further describes the present invention in detail with reference to the drawings and specific embodiments: Refer to Figure 1 , in this embodiment, a synchronous line loss intelligent diagnosis and analysis system based on a power knowledge graph is provided, including a data acquisition layer, a data access layer, a data storage layer, a data analysis layer, and a visualization layer; The data acquisition layer obtains the power grid node data; The data access layer establishes a real-time streaming data analysis framework Apache Kafka to dynamically synchronize the power grid node data; The data storage layer includes a time series database and a graph database, stores the time series data in the time series database, and the graph database stores the topology and semantic relationship of the power grid based on the power network knowledge graph; The data analysis layer includes a detection module and an inference engine. The detection module extracts dynamic data from the time series database, identifies abnormal nodes and time periods, and extracts the topology from the graph database to analyze the propagation path of the abnormality; the inference engine combines the power network knowledge graph, constructs a causal chain based on the detection results, infers the root cause of the abnormality, and matches the abnormal pattern to identify possible fault types; The visualization layer, based on the topology of the knowledge graph, dynamically displays the propagation path and node characteristics of the abnormal area, and queries the abnormal cause of the node and its impact on the entire system by clicking on the device node.

[0019] In this embodiment, the power grid node data includes device sensor data (such as high-frequency current and voltage fluctuations), industrial protocol data, smart meter data, and power grid operation and maintenance historical data; the industrial protocol data (such as IEC 104, Modbus) is accessed through a protocol adapter, and the device sensor data (such as MQTT) is accessed through a message middleware; the smart meter data is accessed through an AMI (Advanced Metering Infrastructure) system; the power grid operation and maintenance historical data is batch imported through a Rest API or an ETL tool.

[0020] In this embodiment, a real-time streaming data analysis framework Apache Kafka is established to perform dynamic synchronization on the power grid node data, as follows: A distributed MQTT message broker is adopted to decode real-time data into a standardized format; KafkaProducer is used to convert the data into message units in a Topic message queue for subsequent consumption; each type of data (such as current, voltage, user behavior data, operation and maintenance historical data, etc.) is mapped to a different Kafka Topic to achieve the separation and management of real-time data streams; multiple Topics are divided according to data sources and task requirements. topic-node-data is responsible for power grid real-time node data, including voltage, current, and load fluctuations; topic-user-behavior is responsible for data related to user load and abnormal power consumption behavior; topic-ops-data is responsible for the power grid equipment operation and maintenance historical records; and Kafka partitions are designed according to the data scale and load. For example, topic-node-data is partitioned by substation ID or transformer ID to support high-concurrency processing.

[0021] In this embodiment, the graph database stores the topology and semantic relationships of the power grid based on a power network knowledge graph, as follows: The power network knowledge graph G=(V, E, A) includes entities V, relationships E, and semantic attributes A, as follows: Entities V include power grid equipment (such as transformers, meters, and lines), regional divisions, and user nodes; Relationships E include physical connections between devices, regional affiliations, and power consumption behaviors; Semantic attribute A is a characteristic description of each entity or relationship (such as device capacity, topology type, operation and maintenance records, etc.); Entities and relationships: Device set V e ={v1, v2, …, v i , …, v n}, such as transformers and switches; regional set V r ={r1, r2, …, r m}, such as substation areas, regional divisions; set of connection relationships , representing the physical connections between devices: E c ={(v i ,v j ) | device v i is connected to device v j}, Attribute modeling: For any v i ∈V e , define its attribute as A(v i )={a1,a2,…,a k}, such as device number, power capacity, status; Calculate the shortest connection path L(i,j) between device v i and device v j :

[0022] where d(e) is the weight of edge e (such as transmission distance); P is a subset of the set of connection relationships E c in the graph, representing all possible connection paths between node i and node j; path represents the actual specific path; Upstream propagation impact simulation: For a certain device failure, determine its impact on the upstream nodes V upstream : ; where, represents that there is a path from node v i to reach node f; Divide the load subnet according to the region and connection relationship , for partition analysis: ; where, represents that node v is directly connected to the nodes in the set V e through the edge e in the graph; And associate the measurement data di(t) in the time series database with the node attribute A(vi) in the graph database.

[0023] In this embodiment, the detection module extracts dynamic data from the time series database, identifies abnormal nodes and time periods, and extracts the topological structure from the graph database to analyze the propagation path of the abnormality, specifically as follows: Extract dynamic data from the time series database and identify abnormal nodes and time periods; Extract the time series data of each power grid node from the time series database ; Apply threshold detection, sliding window statistics, and prediction error methods to determine whether each node is abnormal at each moment; Define an anomaly indication function :

[0024] Collect all nodes that exist at any moment t as : : ; where is the value range of moment t; For each collected node , determine the set of abnormal time periods according to the continuous time segments : ; Obtain the marked abnormal nodes V abnormal and the abnormal time periods T abnormal ; According to the abnormal nodes, calculate the shortest paths from the abnormal nodes to other nodes based on the power grid knowledge graph; analyze and obtain the upstream or downstream propagation influence ranges.

[0025] In this embodiment, according to the abnormal nodes, calculate the shortest paths from the abnormal nodes to other nodes based on the power grid knowledge graph; analyze and obtain the upstream or downstream propagation influence ranges, specifically as follows: Starting from the abnormal node v k ∈V abnormal , calculate the shortest path from the abnormal node to other nodes v j : ; If a certain abnormal node v f is set as the fault point, then all nodes v f that can be connected to v i through paths are regarded as being affected by the upstream of the fault point, and the upstream propagation range is obtained: ; Downstream propagation range: ; For the path from the abnormal node v f to any affected node v∈V affected , calculate the total cost of the propagation path C (P f,v ):

[0026] Among them, P f,v is the shortest path from v f to v.

[0027] In this embodiment, combined with the power network knowledge graph, a causal chain is constructed based on the detection results, the root cause of the anomaly is inferred, and the anomaly pattern is matched to identify possible fault types, as follows: For each detected abnormal node v f , use the power network knowledge graph to query upstream related entities and relationships, construct a candidate causal chain {P i} and calculate its weight W(P i ); determine the main causal chain by comparing the weights and infer the possible root cause; Combine the abnormal node V a and the abnormal node association relationship E a to form an abnormal subgraph G anomaly , G anomaly =(V a , E a ); Compare with the preset fault mode template M k , and calculate the matching degree S(M k , G anomaly ): ; When the matching degree S(M k , G anomaly ) exceeds the threshold θ m , it is considered that the anomaly highly matches the pattern M k , thus identifying the fault type; V k , E k are the abnormal nodes and abnormal node association relationships of the pattern M k respectively; Integrate the causal chain analysis and pattern matching results, and output an anomaly diagnosis report, including the inference of the fault root cause (based on the causal chain), the fault type (based on pattern matching), and corresponding suggestions.

[0028] In this embodiment, based on the topological structure of the knowledge graph, the propagation path and node characteristics of the abnormal area are dynamically displayed. By clicking on the device node, the cause of the anomaly of the node and its impact on the entire system can be queried, as follows: Extract the latest anomaly detection results, causal chains, and propagation paths from the time series database, graph database, and knowledge graph to form a graphical data structure; Use WebSocket to achieve real-time communication between the front end and the back end, ensuring that the visualization interface promptly reflects state changes; Based on the graph database, use a graphical display engine (such as D3.js, Cytoscape.js, or Sigma.js) to render the real-time topology graph, and dynamically mark the abnormal areas, propagation paths, and node states; After the user clicks on a device node, query the device node details (including the cause of the anomaly, the abnormal time period, the causal chain information, and the propagation impact) through the REST API and display the detailed results in a pop-up window or sidebar.

[0029] In this embodiment, a graphical display engine is used to render the real-time topology graph, and the abnormal areas, propagation paths, and node states are dynamically marked, as follows: Each device node shows its normal / abnormal state through different colors, sizes, or shapes. Abnormal devices are marked in red, and the abnormal time period or abnormal level information is prompted on the node; Draw the connection relationships of each device according to the graph database data. The thickness or transparency of the edges reflects the edge weight and transmission cost; When an abnormal propagation path is detected, the connection line of the path is highlighted in a different color to indicate the abnormal propagation direction and path weight; Utilize the power knowledge graph data to embed the upstream and downstream causal chains related to the anomaly between the nodes, or display the key relationships on the graph in the form of floating annotations, intuitively showing the root cause of the fault and its propagation mechanism.

[0030] Refer to Figure 2 In this embodiment, a method for intelligent diagnosis and analysis of synchronous line losses based on a power knowledge graph is provided, including the following steps: S1: Obtain power grid node data and perform dynamic synchronization on the power grid node data through the real-time streaming data analysis framework Apache Kafka; S2: Store the time-series data in a dynamic database. The graph database stores the topology and semantic relationships of the power grid based on the power network knowledge graph; S3: Extract dynamic data from the time-series database, identify abnormal nodes and time periods, and extract the topology structure from the graph database to analyze the abnormal propagation path; S4: Construct a causal chain based on the detection results, infer the root cause of the anomaly, and match the abnormal pattern to identify possible fault types; S5: Based on the topology structure of the knowledge graph, dynamically display the propagation path and node characteristics of the abnormal area. By clicking on a device node, query the cause of the anomaly of the node and its impact on the entire system.

[0031] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0032] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0033] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0034] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0035] As mentioned above, it is only the preferred embodiments of the present invention, and the present invention is not limited to other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A synchronous line loss intelligent diagnosis and analysis system based on a power knowledge graph, characterized in that, It includes a data acquisition layer, a data access layer, a data storage layer, a data analysis layer, and a visualization layer; The data acquisition layer acquires power grid node data; The data access layer establishes a real-time streaming data analysis framework Apache Kafka to dynamically synchronize the power grid node data; The data storage layer includes a time series database and a graph database. The time series data is stored in the time series database, and the graph database stores the topology and semantic relationships of the power grid based on the power network knowledge graph; The data analysis layer includes a detection module and an inference engine. The detection module extracts dynamic data from the time series database, identifies abnormal nodes and time periods, and extracts the topology from the graph database to analyze the propagation path of the anomaly. The inference engine combines the power network knowledge graph, constructs a causal chain based on the detection results, infers the root cause of the anomaly, and matches the anomaly pattern to identify possible fault types; The visualization layer dynamically displays the propagation path and node characteristics of the abnormal area based on the topology of the knowledge graph. By clicking on the device node, the abnormal cause of the node and its impact on the entire system can be queried.

2. The intelligent diagnosis and analysis system for synchronous line loss based on the power knowledge graph according to claim 1, wherein The power grid node data includes device sensor data, industrial protocol data, smart meter data, and power grid operation and maintenance historical data; the industrial protocol data is accessed through a protocol adapter, and the device sensor data is accessed through a message middleware; the smart meter data is accessed through an AMI system; the power grid operation and maintenance historical data is batch imported through a Rest API or an ETL tool.

3. The intelligent diagnosis and analysis system for synchronous line loss based on the power knowledge graph according to claim 2, characterized in that, The establishment of the real-time streaming data analysis framework Apache Kafka to dynamically synchronize the power grid node data is as follows: A distributed MQTT message broker is used to decode the real-time data into a standardized format; Kafka Producer is used to convert the data into message units in the Topic message queue for subsequent consumption; each type of data is mapped to a different Kafka Topic to achieve the separation and management of real-time data streams; multiple Topics are divided according to the data source and task requirements. topic-node-data is responsible for the real-time node data of the power grid, including voltage, current, and load fluctuations; topic-user-behavior is responsible for data related to abnormal user load and electricity consumption behavior; topic-ops-data is responsible for the historical records of power grid equipment operation and maintenance; and Kafka partitions are designed according to the data scale and load.

4. The intelligent diagnosis and analysis system for synchronous line loss based on the power knowledge graph according to claim 1, wherein The graph database stores the topology and semantic relationships of the power grid based on the power network knowledge graph as follows: The power network knowledge graph G=(V, E, A) includes entities V, relationships E, and semantic attributes A, as follows: Entities V include power grid equipment, regional divisions, and user nodes; Relationships E include physical connections between devices, regional affiliations, and electricity consumption behaviors; Semantic attribute A is a characteristic description of each entity or relationship; Entities and relationships: Device set V e = {v1, v2, …, v i , …, v n}; Region set V r = {r1, r2, …, r m}; Connection relation set , representing the physical connections between devices: E c ={(v i ,v j ) | The device v i is connected to the device v j has a connection} Attribute modeling: For any v i ∈ V e , define its attribute as A(v i ) = {a1, a2, …, a k}; Computing device v i and device v j The shortest connection path L(i, j) between: ； where d(e) is the weight of edge e; P is a subset of the set of connection relationships E in the graph, representing all possible connection paths between node i and node j; path represents the actual specific path; c and Upstream propagation impact simulation: For a certain equipment failure, determine its impact on the upstream node V upstream : ； Among them, indicates that there is a path from node v i to node f; Divide the load subnet according to the region and connection relationship , for partition analysis: ； Among them, indicates that the node v is directly connected to the nodes in the set V e through the edge e in the graph; And the measurement data di(t) in the time series database is associated with the node attribute A(vi) in the graph database.

5. The intelligent diagnosis and analysis system for synchronous line loss based on the power knowledge graph according to claim 4, characterized in that, The detection module extracts dynamic data from the time series database, identifies abnormal nodes and time periods, and extracts the topological structure from the graph database to analyze the propagation path of the abnormality, as follows: Extract dynamic data from the time series database and identify abnormal nodes and time periods; Extract the time series data of each power grid node from the time series database ; Apply threshold detection, sliding window statistics, and prediction error methods to determine whether each node is abnormal at each moment; Define the exception indication function :[[]]END]] All nodes existing at any given time t are collected as : ； Among them, is the value range of time t; For each node collected ,according to consecutive time segments ,determine the set of abnormal time periods : ； Obtain the marked abnormal node V abnormal and the abnormal time period T abnormal ; Based on the abnormal nodes and the power network knowledge graph, calculate the shortest paths from the abnormal nodes to other nodes; analyze and obtain the propagation influence range upstream or downstream.

6. The intelligent diagnosis and analysis system for synchronous line loss based on the power knowledge graph according to claim 4, wherein The step of calculating the shortest paths from the abnormal nodes to other nodes based on the power network knowledge graph and analyzing and obtaining the propagation influence range upstream or downstream is as follows: Starting from the abnormal node v k ∈V abnormal compute the shortest path from the abnormal node to other nodes v j : ； If an abnormal node v is set f as the fault point, then all nodes v that can be connected to v f through a path i are regarded as being affected by the upstream of the fault point, and the upstream propagation range is obtained: ； Downstream propagation range: ； For an abnormal node v f to any affected node v ∈ V affected , calculate the total cost of the propagation path C ( P f,v ): ； Among them, P f,v is the shortest path from v f to v 7. The intelligent diagnosis and analysis system for synchronous line loss based on the power knowledge graph according to claim 6, wherein Combine the power network knowledge graph, construct a causal chain based on the detection results, infer the root cause of the abnormality, and match the abnormal pattern to identify possible fault types, as follows: For each detected abnormal node v f , query the upstream related entities and relationships using the power grid knowledge graph, construct the candidate causal chain {P i} and calculate its weight W(P i ); determine the main causal chain by comparing the weights and infer the possible root cause; The abnormal node V a and the abnormal node association relationship E a constitute an abnormal subgraph G anomaly , G anomaly =(V a ,E a ); Compare with the preset fault mode template M k , calculate the matching degree S(M k , G anomaly ): ； When the matching degree S(M k , G anomaly ) exceeds the threshold θ m , it is considered that the anomaly highly matches the pattern M k , thereby identifying the fault type; V k , E k are respectively the abnormal nodes and the associated relationships of the abnormal nodes of the pattern M k . Based on the comprehensive causal chain analysis and pattern matching results, output an abnormal diagnosis report, including the inferred root cause of the fault, the fault type, and corresponding suggestions.

8. The intelligent diagnosis and analysis system for synchronous line loss based on the power knowledge graph according to claim 1, wherein Based on the topological structure of the knowledge graph, dynamically display the propagation path and node characteristics of the abnormal area. By clicking on the device node, query the cause of the abnormality of the node and its impact on the entire system, as follows: Extract the latest abnormal detection results, causal chains, and propagation paths from the time series database, graph database, and knowledge graph to form a graphical data structure; Use WebSocket to achieve real-time communication between the front end and the back end to ensure that the visualization interface reflects the state changes in a timely manner; Based on the graph database, use a graphical display engine to render the real-time topology graph, and dynamically mark the abnormal area, propagation path, and node status; After the user clicks on the device node, query the device node details through the REST API and display the detailed results in a pop-up window or sidebar.

9. The intelligent diagnosis and analysis system for synchronous line loss based on the power knowledge graph according to claim 8, wherein, The step of using a graphical display engine to render the real-time topology graph and dynamically mark the abnormal area, propagation path, and node status is as follows: Each device node shows its normal / abnormal status through different colors, sizes, or shapes. Abnormal devices are marked in red, and the abnormal time period or abnormal level information is prompted on the node; Draw the connection relationships of each device according to the graph database data. The thickness or transparency of the edges reflects the edge weight and transmission cost; When an abnormal propagation path is detected, the connection line of the path is highlighted in a different color to indicate the abnormal propagation direction and path weight; Utilize the power knowledge graph data to embed the upstream and downstream causal chains related to the abnormality between the nodes, or display the key relationships on the graph in the form of floating annotations to intuitively display the root cause of the fault and its propagation mechanism.

10. A synchronous line loss intelligent diagnosis and analysis method based on an electric power knowledge graph, characterized in that, It includes the following steps: S1: Obtain power grid node data, and perform dynamic synchronization on the power grid node data through the real-time streaming data analysis framework Apache Kafka; S2: Store the time series data in a dynamic database, and the graph database stores the topology and semantic relationships of the power grid based on the power network knowledge graph; S3: Extract dynamic data from the time series database, identify abnormal nodes and time periods, and extract the topological structure from the graph database to analyze the propagation path of the abnormality; S4: Build a causal chain based on the detection results, infer the root cause of the anomaly, match the anomaly pattern, and identify possible fault types; S5: Based on the topological structure of the knowledge graph, dynamically display the propagation path and node characteristics of the abnormal area. By clicking on the device node, query the cause of the anomaly of this node and its impact on the entire system.

Images