Method, system and equipment for analyzing power failure event of feeder line of power distribution network and medium

Abstract

The invention provides a power distribution network feeder power failure event analysis method, system and device and a medium, and belongs to the field of power system monitoring and automation. The method comprises the following steps: acquiring historical line data, equipment archives and geographic information data of a power distribution network, and initializing a power grid topology model according to the line data, the equipment archives and the geographic information data; acquiring real-time operation state information of the transformer, and verifying and processing the real-time operation state information to determine abnormal data; correcting the abnormal data, and updating the power grid topology model based on the corrected data; and identifying a power failure area and a power recovery area based on the updated power grid topology model. Through integration of multi-source data, real-time monitoring, rapid positioning and intelligent processing of a power failure event of a power distribution network are realized, the fault response speed is significantly improved, power supply is rapidly recovered, the power failure time and the influence of power interruption are reduced, the fault position is accurately positioned through fusion of line topology, and reasons are analyzed.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system monitoring and automation, and in particular relates to a method, system, equipment and medium for analyzing power outage events in a distribution network feeder. Background Art

[0002] In power distribution network management, handling power outages is a critical task in ensuring power supply reliability and customer satisfaction. Traditional approaches suffer from information lag and slow response, making them particularly inefficient in locating faults and confirming the scope of outages. Operations and maintenance personnel struggle to obtain accurate location information in a timely manner, leading to processing delays. Furthermore, power restoration strategies often rely on empirical judgment, making it difficult to accurately assess fault severity and restoration priorities.

[0003] Currently, the distribution network's information sharing mechanism is weak, resulting in inefficient communication between departments and hindering the effectiveness of power outage management. In the absence of intelligent fault location and analysis methods, operations and maintenance personnel rely on manual inspections to locate the source of the fault, which prolongs recovery time and increases the complexity of the process.

[0004] Therefore, improving the automatic detection and location accuracy of power outage events and shortening the restoration time are key challenges to improving distribution network efficiency and user satisfaction. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a method, system, device and medium for analyzing power outage events in a distribution network feeder, which are used to fully or at least partially solve the technical problems of fault power outage location delay and low accuracy in the above-mentioned prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for analyzing a power distribution network feeder outage event, comprising: Acquire historical line data, equipment archives, and geographic information data of the distribution network, and initialize a power grid topology model based on the line data, equipment archives, and geographic information data, wherein the power grid topology model includes the connection relationship between each line and equipment in the distribution network and the status of the equipment; Collecting real-time operating status information of the transformer, verifying and processing the real-time operating status information, and determining abnormal data; Correcting the abnormal data and updating the power grid topology model based on the corrected data; Power outage areas and power restoration areas are identified based on the updated power grid topology model. The process of identifying power outage areas based on the updated power grid topology model includes analyzing the voltage amplitude and power distribution of each node, finding nodes where the voltage amplitude is lower than the normal range or where the power transmission is abnormally interrupted, and checking the status of each switch in the power grid topology model. If the switch in a certain area is in the disconnected state and there is no electrical connection between the area and other normal power supply areas, the area is characterized as a power outage area; the process of identifying power restoration areas based on the updated power grid topology model includes determining the power restoration area based on the restoration of electrical connectivity of abnormal equipment.

[0007] Optionally, collecting real-time operating status information of the transformer, verifying and processing the real-time operating status information, and determining abnormal data include: Compare and verify with the historical normal data of the transformer. If it is determined that the collected transformer status signal contains invalid data, data mutation, or inconsistent switching state timing, it is determined that abnormal data exists in the collected real-time transformer operating status information.

[0008] Optionally, correcting the abnormal data and updating the power grid topology model based on the corrected data includes: For invalid data, a spatial interpolation algorithm is used to fill missing values ​​based on the spatiotemporal correlation of adjacent nodes; For mutation data, multi-source data fusion verification is used to associate meteorological data with equipment status. Multi-source evidence is integrated through DS evidence theory to determine whether the mutation is a real fault. For inconsistent switch state timing data, a Petri net model of the switch action is established, and the switch action sequence is verified through the state transition matrix to correct the timing error; Based on the corrected invalid data, mutation data and inconsistent switch state timing data, spatiotemporal graph convolution is used to dynamically update the node features of the power grid topology model, and the graph attention mechanism is used to identify the voltage amplitude mutation area, and the disconnection location is corrected in combination with the equipment ledger parameters.

[0009] Optionally, identifying power outage areas based on the updated grid topology model includes: The corrected real-time operating status information of the transformer and the status information of related equipment are sorted according to chronological order and equipment identification, and the geographic information data is integrated to determine the location relationship of each device in geographic space; The sorted real-time operating status information of transformers, status information of related equipment, and location relationships are input into the updated power grid topology model. The node features are updated through spatiotemporal graph convolution to determine the current operating status of the power grid. Use the Newton-Raphson power flow algorithm to calculate power flow on the power grid, analyze the voltage amplitude and power distribution at each node, and compare the voltage and power ranges during normal operation to identify nodes where the voltage amplitude is below the normal range or where power transmission is abnormally interrupted. Check the status of each switch in the power grid topology model. If the switch in a certain area is disconnected and there is no electrical connection between the area and other normally powered areas, the area is marked as a power outage area. The grid topology model is analyzed through the graph attention mechanism to identify voltage amplitude mutation areas. The currently identified voltage amplitude mutation areas are matched with the fault history data to determine similar fault modes and fault occurrence areas. Based on the fault point and the grid topology structure, the scope of the affected power outage area is determined. By analyzing the status of adjacent nodes and judging the electrical connection relationship, all equipment and lines in the power outage area are identified.

[0010] Optionally, the method for analyzing a power distribution network feeder outage event further includes: After determining the power outage area, the relationship between the power outage area and user access points obtained through topological analysis is combined with the load information of the power grid to determine the number of affected users and identify sensitive users.

[0011] Optionally, identifying the power restoration area based on the updated grid topology model includes: For devices whose status has changed, the electrical connectivity between them and other normally powered devices is analyzed. If an electrical connection is established between a device and the normal power supply area, and the voltage and power of the device return to normal, the area where the device is located is identified as the power restoration area. The area is gradually expanded with the device as the center to identify all devices and lines within the power restoration area.

[0012] Optionally, the method for analyzing a power distribution network feeder outage event further includes: Organize the identified power outage and restoration areas and present them in the form of a device list or geographic graph, where for each area, the device name, number, and geographic location information are listed; Combined with the geographic information system, the power outage areas and power restoration areas are visualized on the map, and the power outage areas and power restoration areas are distinguished by different colors and icons.

[0013] In a second aspect, an embodiment of the present application further provides a system for analyzing power outage events in a distribution network feeder, comprising: an acquisition unit, configured to acquire historical line data, equipment archives, and geographic information data of the power distribution network, and initialize a power grid topology model based on the line data, equipment archives, and geographic information data, wherein the power grid topology model includes connection relationships between various lines and equipment in the distribution network and the status of the equipment; A determination unit, configured to collect real-time operating status information of the transformer, verify and process the real-time operating status information, and determine abnormal data; an updating unit, configured to correct the abnormal data and update the power grid topology model based on the corrected data; An identification unit is used to identify power outage areas and power restoration areas based on an updated power grid topology model, wherein the process of identifying power outage areas based on the updated power grid topology model includes analyzing the voltage amplitude and power distribution of each node, finding out the nodes where the voltage amplitude is lower than the normal range or the power transmission is abnormally interrupted, and checking the status of each switch in the power grid topology model. If the switch in a certain area is in the disconnected state and there is no electrical connection between the area and other normal power supply areas, the area is characterized as a power outage area; the process of identifying power restoration areas based on the updated power grid topology model includes determining the power restoration area based on the restoration of electrical connectivity of abnormal equipment.

[0014] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the steps of the above-mentioned method for analyzing power outage events in a distribution network feeder are implemented.

[0015] In a fourth aspect, an embodiment of the present application further provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for analyzing power outage events of feeder lines in a distribution network.

[0016] It can be seen from the above technical solutions that the present invention has the following advantages: The present application provides an analysis method, system, device and medium for power outage events in a distribution network feeder. By integrating multi-source data, real-time monitoring, rapid positioning and intelligent processing of power outage events in the distribution network can be achieved, which significantly improves the fault response speed, quickly restores power supply, reduces the power outage time and the impact of power interruptions, and integrates line topology to accurately locate the fault location and analyze the cause. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A flow chart of a method for analyzing a power outage event in a distribution network feeder provided by an embodiment of the present invention; Figure 2 A flowchart of updating a power grid topology model based on corrected data provided by an embodiment of the present invention; Figure 3 A flowchart of identifying a power outage area based on an updated power grid topology model provided by an embodiment of the present invention; Figure 4 A detailed implementation flow chart of a method for analyzing a power distribution network feeder outage event provided by an embodiment of the present invention; Figure 5 A schematic structural diagram of a system for analyzing power outage events in a distribution network feeder provided by an embodiment of the present invention; Figure 6 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In the detailed description below, various embodiments of the present disclosure will be described more fully. The present disclosure can have various embodiments, and adjustments and changes can be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather that the present disclosure should be understood to encompass all adjustments, equivalents, and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0020] Hereinafter, the terms "include" or "may include" used in various embodiments of the present disclosure indicate the presence of the disclosed functions or operations and do not limit the addition of one or more functions or operations. In addition, as used in various embodiments of the present disclosure, the terms "include", "have" and their cognates are intended only to indicate specific features, numbers, steps, operations or combinations of the foregoing items, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations or combinations of the foregoing items.

[0021] In various embodiments of the present disclosure, the expression "or" or "at least one of A or / and B" includes any or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0023] See Figure 1 FIG. 1 is a flow chart of a method for analyzing a power outage event of a feeder in a distribution network according to a specific embodiment, including the following steps: Step 100: Acquire historical line data, equipment archives, and geographic information data of the power distribution network, and initialize a power grid topology model based on the line data, equipment archives, and geographic information data.

[0024] The power grid topology model includes the connection relationship between various lines and devices in the distribution network and the status of the devices.

[0025] For example, the system imports distribution network line data, equipment profiles, and related geographic information through interfaces with homologous system services. This data includes line topology, equipment location information (such as the spatial coordinates of transformers, switches, and other equipment), and equipment attributes (such as rated power and fault protection level). This step provides basic data support for the subsequent establishment of the grid topology model, including equipment status, such as the closed or open state of switches and the operating status of transformers.

[0026] For example, Java multithreading technology is used to concurrently collect data such as current, voltage, power, and switch status. Sensors and monitoring devices provide real-time system status information. This collected data is then efficiently and reliably transmitted to the data processing center via message-based middleware. Within the data processing center, the Hadoop Distributed File System (HDFS) is used to store big data, ensuring efficient operation despite high concurrency and large data volumes. Apache Spark is then used for real-time computing and analysis, rapidly processing the data and identifying potential issues or faults.

[0027] To improve accuracy, GIS technology and grid topology information are combined to precisely locate the location of power outages. The GIS platform visualizes the geographic distribution of power facilities, helping the system determine the type of outage (e.g., mainline, branch, or substation outage) and providing real-time updates on the outage area and impact. Once an outage is identified, JavaMail and WebSocket technologies are used to promptly notify operations and maintenance personnel. JavaMail sends email notifications and triggers responses.

[0028] Through the integration of the above technologies, accurate monitoring and rapid response to distribution network faults are achieved, the accuracy and timeliness of fault diagnosis are improved, and support is provided for the stable operation of the power system.

[0029] Step 101: Collect real-time operating status information of the transformer, verify and process the real-time operating status information, and determine abnormal data.

[0030] Specifically, a comparison is performed with the historical normal data of the transformer. If it is determined that the collected transformer status signal contains invalid data, data mutation, or inconsistent switching state timing, it is determined that abnormal data exists in the collected real-time transformer operating status information.

[0031] For example, real-time information such as transformer outage and restoration signals, current data, and the opening and closing status of digital switches can be obtained from the same source system and the SCADA system. This data reflects the operating status of the distribution network and can promptly reflect the instantaneous state of the fault. For example, whether the transformer was in a power outage state or whether certain switches were disconnected when the fault occurred. This real-time data is essential for fault location.

[0032] Step 102: Correct the abnormal data and update the power grid topology model based on the corrected data.

[0033] For details, see Figure 2 As shown, when executing step 102, the following steps may be specifically performed: S1020: For invalid data, a spatial interpolation algorithm is used to fill in missing values ​​based on the spatiotemporal correlation of adjacent nodes.

[0034] Specifically, data collection and organization: Collect spatiotemporal datasets containing invalid data (missing values), ensuring that the datasets contain the node's spatial location information (such as latitude and longitude coordinates), timestamp information, and corresponding observations (which may be missing). Traverse the dataset and accurately identify all invalid data, or missing values, using predefined rules (such as specific null value markers and outlier ranges). For each node with a missing value, calculate the spatial distance between it and all other nodes in the dataset. In addition to spatial distance, temporal correlation also needs to be considered. For time series data, determine an appropriate time window, for example, centered around the time point where the missing value occurs and within a certain time range before and after it. Select adjacent nodes within this time window. Based on spatial distance and temporal correlation, select a certain number of adjacent nodes with the closest distance and high temporal correlation as the node set for interpolation. Using inverse distance weighted interpolation, weights are assigned to adjacent nodes based on the inverse of distance, with closer nodes receiving larger weights. The observed values ​​of adjacent nodes are weighted summed with the corresponding weights to obtain an estimate of the point to be interpolated (the location of the missing value), thereby filling in the missing value. The formula for inverse distance weighted interpolation is as follows:

[0035] Where, is the estimated value of the interpolation point (x0, y0), z(xi,yi) is the observed value of the adjacent node (xi,yi), d(xi,yi) is the distance from the adjacent node (xi,yi) to the interpolation point (x0,y0), and p is the power parameter.

[0036] S1021: For mutation data, multi-source data fusion verification is used to associate meteorological data with equipment status, and multi-source evidence is integrated through DS evidence theory to determine whether the mutation is a real fault.

[0037] For example, the above basic probability distribution is integrated using the combination rule of DS evidence theory. The combination rule formula is:

[0038] Among them, m(A) is the basic probability distribution after fusion, mi(Ai) is the basic probability distribution of each evidence, and A is a subset of the recognition framework Θ.

[0039] S1022: For inconsistent switch state timing data, a Petri net model of the switch action is established, the switch action sequence is verified through the state transition matrix, and the timing error is corrected.

[0040] For example, in a simple power distribution system, there are three switches, S1, S2, and S3, with a certain logical control relationship between them. The normal operating process is: first close switch S1, then close switch S2, and finally close switch S3 to complete the power supply to a certain area. At the same time, when disconnecting, the order is reversed, that is, first disconnect S3, then disconnect S2, and finally disconnect S1. Build a Petri net model: Define the library: P1: Represents the open state of switch S1. P2: Represents the closed state of switch S1. P3: Represents the open state of switch S2. P4: Represents the closed state of switch S2. P5: Represents the open state of switch S3. P6: Represents the closed state of switch S3. P7: Represents the initial state of the system (all switches open). P8: Represents the normal power supply state of the system (all switches closed).

[0041] Define transitions: T1: represents the action of closing switch S1. T2: represents the action of closing switch S2. T3: represents the action of closing switch S3. T4: represents the action of opening switch S3. T5: represents the action of opening switch S2. T6: represents the action of opening switch S1. Determine the connection relationship: There is a directed arc from P7 to T1, a directed arc from T1 to P1, and a directed arc from T1 to P2 (indicating that after T1 is triggered, S1 changes from open to closed). There is a directed arc from P2 to T2, a directed arc from T2 to P3, and a directed arc from T2 to P4 (indicating that after T2 is triggered, S2 changes from open to closed). There is a directed arc from P4 to T3, a directed arc from T3 to P5, and a directed arc from T3 to P6 (indicating that after T3 is triggered, S3 changes from open to closed). There is a directed arc from P6 to T4, and a directed arc from T4 to P5 (indicating that after T4 is triggered, S3 changes from closed to open). There is a directed arc from P4 to T5, and a directed arc from T5 to P3 (indicating that after T5 is triggered, S2 changes from closed to open). There is a directed arc from P2 to T6, and a directed arc from T6 to P1 (indicating that after T6 is triggered, S1 changes from closed to open). There is a directed arc from P8 to T4 (indicating that S3 is disconnected from the normal power supply state). There is an initial token from P7, representing the initial state of the system. Constructing a state transition matrix: The state transition matrix M is used to describe the changes in the state of a place before and after a transition is triggered in a Petri net. Assume that the state of a place is represented by a vector, with the presence of a token represented by 1 and the absence of a token represented by 0. According to the connection relationship and transition triggering rules of the Petri net, it can be obtained that each row in the state transition matrix M corresponds to a transition, and each column corresponds to a library place. The row vectors corresponding to all transitions are calculated in sequence to obtain the complete state transition matrix M.

[0042] Verifying the switch operation sequence and correcting timing errors: Obtaining actual switch state data: Assume that the actual monitored switch operation sequence is: first close S2, then close S1, and finally close S3. This does not conform to the normal operating process. Converting to a Petri net state vector sequence: Convert the actual operation sequence into a sequence of place state vectors in the Petri net. Verifying using the state transition matrix: Starting with the initial state vector M0, based on the actual state vector sequence, check whether the next state vector can be triggered by the transitions in the state transition matrix M. If this cannot be achieved, a timing error exists. For the initial state M0 = [1, 0, 0, 0, 0, 0, 0], according to the normal process, T1 should be triggered first to obtain M1 = [0, 1, 0, 0, 0, 0, 0]. However, S2 is actually closed first, and it is impossible to directly obtain [0, 0, 0, 1, 0, 0, 0, 0] from M0 through the transitions in M, indicating a timing error. Correcting Timing Errors: Based on the Petri Net model and the state transition matrix, the correct action sequence is to trigger T1 first, then T2, and finally T3. Therefore, the actual action sequence was corrected to: first close S1, then S2, and finally S3, to conform to the normal operating process specified by the Petri Net model.

[0043] S1023: Based on the corrected invalid data, mutation data, and inconsistent switch state timing data, spatiotemporal graph convolution is used to dynamically update the node features of the power grid topology model, and the voltage amplitude mutation area is identified through the graph attention mechanism. The disconnection location is corrected in combination with the equipment ledger parameters.

[0044] Step 103: Identify power outage areas and power restoration areas based on the updated power grid topology model.

[0045] Among them, the process of identifying the power outage area based on the updated power grid topology model includes analyzing the voltage amplitude and power distribution of each node, finding the nodes where the voltage amplitude is lower than the normal range or the power transmission is abnormally interrupted, and checking the status of each switch in the power grid topology model. If the switch in a certain area is in the disconnected state and there is no electrical connection between the area and other normal power supply areas, the area is characterized as a power outage area; the process of identifying the power restoration area based on the updated power grid topology model includes determining the power restoration area based on the restoration of electrical connectivity of abnormal equipment.

[0046] For details, see Figure 3 As shown, in step 103, identifying the power outage area based on the updated grid topology model may specifically include the following steps: S1030: Arrange the corrected real-time operating status information of the transformer and the status information of related equipment in chronological order and by equipment identification, and integrate geographic information data to determine the positional relationship of each device in geographic space.

[0047] S1031: Input the sorted real-time operating status information of the transformer, the status information of related equipment, and the position relationship into the updated power grid topology model, and update the node features through spatiotemporal graph convolution to determine the current operating status of the power grid.

[0048] S1032: Use the Newton-Raphson power flow algorithm to calculate the power flow of the power grid, analyze the voltage amplitude and power distribution of each node, and compare the voltage and power range during normal operation to find nodes where the voltage amplitude is lower than the normal range or where power transmission is abnormally interrupted.

[0049] S1033: Checking the status of each switch in the power grid topology model. If the switch in a certain area is in the disconnected state and there is no electrical connection between the area and other areas with normal power supply, the area is marked as a power outage area. S1034: Analyze the grid topology model through the graph attention mechanism to identify the voltage amplitude mutation area, match the currently identified voltage amplitude mutation area with the fault history data, determine similar fault modes and fault occurrence areas, and use the fault point as the center to determine the scope of the affected power outage area based on the grid topology. By analyzing the status of adjacent nodes and judging the electrical connection relationship, determine all equipment and lines in the power outage area.

[0050] Specifically, the graph attention mechanism analyzes the power grid topology model and identifies areas of voltage amplitude mutation. This involves defining a graph G = (V, E) based on the power grid topology data, where V is the set of nodes and E is the set of edges. The feature vector of each node in G is initialized using the node's feature data. The attention mechanism is introduced based on the graph neural network, and a graph attention layer is constructed. This layer calculates the attention weight of each node on its neighboring nodes, thereby dynamically adjusting the information flow between nodes.

[0051] In some embodiments, the following steps are further performed: after determining the power outage area, the relationship between the power outage area and the user access point obtained through topological analysis is combined with the load information of the power grid to determine the number of affected users and identify sensitive users based on power consumption.

[0052] Exemplarily, sensitive users include hospitals, important communication facilities, public security systems, etc.

[0053] In some embodiments, the identification of the power restoration area based on the updated grid topology model in step 103 can be performed specifically by performing the following steps: for devices whose status has changed, the electrical connectivity between the device and other normally powered devices is analyzed; if an electrical connection is established between a device and the normal power supply area, and the voltage and power of the device are restored to normal, the area where the device is located is identified as the power restoration area, and the area is gradually extended with the device as the center to determine all devices and lines within the power restoration area.

[0054] In some embodiments, the method for analyzing power outage events on feeder lines of a distribution network further includes: organizing the identified power outage areas and power restoration areas and presenting them in the form of a device list or a geographic graph, wherein for each area, the device name, number, and geographic location information are listed; in combination with a geographic information system, the power outage areas and power restoration areas are visually displayed on a map, and the power outage areas and power restoration areas are distinguished by different colors and icons.

[0055] In some implementations, a comprehensive intelligent feeder outage analysis and processing system was deployed within a city's power distribution network, achieving significant results. For example, during high-temperature weather, a distribution line automatically tripped due to overload. The system rapidly detected the trip by monitoring multiple data sources in real time (such as SCADA switch status, current, and transformer power). By comparing historical and real-time data, it accurately and in real time determined the fault location, the scope of the outage, and whether sensitive users were affected, allowing for the timely generation of a power transfer plan. Upon receiving the system alert, operations and maintenance personnel quickly assessed the impact of the outage using a visual interface and, based on intelligent recommendations, developed a load transfer plan. The system's power restoration simulation function helped verify the feasibility of the transfer plan. During implementation, the system collaborated with dispatch, customer service, and emergency repair departments to share fault information in real time, improving response efficiency. Emergency repair personnel quickly arrived at the scene to repair the fault and optimize load distribution, ensuring rapid power restoration. Through intelligent analysis and rapid response, event processing time was significantly shortened, power restoration was significantly accelerated, and the impact on users during high-temperature periods was minimized. This provided an effective emergency plan for future high-temperature weather events, enhanced the reliability and resilience of the power supply network, and significantly improved user satisfaction.

[0056] In this embodiment, by integrating multi-source data, real-time monitoring, rapid positioning and processing of power outage events in the distribution network are achieved, which significantly improves the fault response speed, quickly restores power supply, reduces the power outage time and the impact of power interruptions, and integrates the line topology to accurately locate the fault location and analyze the cause.

[0057] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0058] See Figure 4 The figure shows a detailed implementation flow chart of a method for analyzing power outage events on distribution network feeders provided by an embodiment of the present invention, including: importing distribution network line data and equipment archives from the same source system, initializing the power grid topology model, acquiring real-time data, identifying and correcting anomalies in the above data, dynamically updating the power grid topology model, inferring power outage and restoration areas through topological analysis, identifying the current power outage area, determining whether the topological calculation results are logically consistent with transformer status data and real-time power flow data, and if so, calculating the affected user data and sensitive users, saving and analyzing historical power outage event data, and identifying recurring issues and patterns. If not, the power grid topology model is dynamically updated and subsequent steps are executed.

[0059] like Figure 5 As shown, the following is an embodiment of the analysis system for distribution network feeder power outage events provided by the embodiment of the present disclosure, which belongs to the same inventive concept as the analysis method for distribution network feeder power outage events in the above-mentioned embodiments. For details not fully described in the embodiment of the analysis system for distribution network feeder power outage events, please refer to the embodiment of the analysis method for distribution network feeder power outage events mentioned above.

[0060] an acquisition unit, configured to acquire historical line data, equipment archives, and geographic information data of the power distribution network, and initialize a power grid topology model based on the line data, equipment archives, and geographic information data, wherein the power grid topology model includes connection relationships between various lines and equipment in the distribution network and the status of the equipment; A determination unit, configured to collect real-time operating status information of the transformer, verify and process the real-time operating status information, and determine abnormal data; an updating unit, configured to correct the abnormal data and update the power grid topology model based on the corrected data; An identification unit is used to identify power outage areas and power restoration areas based on an updated power grid topology model, wherein the process of identifying power outage areas based on the updated power grid topology model includes analyzing the voltage amplitude and power distribution of each node, finding out the nodes where the voltage amplitude is lower than the normal range or the power transmission is abnormally interrupted, and checking the status of each switch in the power grid topology model. If the switch in a certain area is in the disconnected state and there is no electrical connection between the area and other normal power supply areas, the area is characterized as a power outage area; the process of identifying power restoration areas based on the updated power grid topology model includes determining the power restoration area based on the restoration of electrical connectivity of abnormal equipment.

[0061] In some embodiments, the architecture of a system for analyzing power distribution network feeder outage events includes: The data collection layer integrates data from multiple sources, focusing on collecting core power parameters such as current, voltage, power, and switch status, and acquiring device status information from the SCADA system. Simultaneously, it collects line topology data from the same source system and transformer power-on and power-off information to accurately track the status of power equipment. Furthermore, the data collection layer integrates map data from GIS (Geographic Information System) to display the spatial distribution of distribution lines, substations, and transformers, assisting in fault location and analysis.

[0062] The data processing layer is responsible for receiving and processing various types of real-time data from the data acquisition layer. This layer establishes a complete distribution network operation database by cleaning, organizing, and storing data to ensure efficient data management and utilization. In terms of data processing, the system uses advanced data analysis algorithms to process and analyze the collected data in real time. First, through real-time monitoring and analysis, it determines whether a power outage has occurred and further identifies the type of event (such as main line power outage, branch power outage, or substation power outage) and the severity of the event. Secondly, the system combines historical data with real-time data to conduct intelligent analysis and judgment of power outage events. It can predict key factors such as the scope of the power outage, the number of affected users, and the timeliness of restoration, providing decision support for power dispatchers.

[0063] The application layer integrates multi-source data to provide real-time monitoring, rapid location, and intelligent processing capabilities for power feeder faults. It combines information from diverse data sources to comprehensively understand power network operations and rapidly diagnose and locate faults. To enhance operational convenience for operations personnel, an intuitive visualization interface has been designed to display relevant information about power outages, including the location of the outage area, a list of events, severe overload conditions, and information on key users (such as hospitals). This allows operations personnel to clearly understand the distribution and impact of power outages, facilitating rapid response.

[0064] Figure 6 It is a schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0065] The analysis method for power distribution network feeder power outage events provided in the embodiments of the present application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In the embodiments of the present invention, the electronic device includes but is not limited to laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0066] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, a button, a camera, a display, and a SIM card interface, etc.

[0067] It is understood that the structures illustrated in the embodiments of the present application do not constitute specific limitations on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown, or combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0068] A processor may include one or more processing units, such as a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0069] The processor can be the nerve center and command center of the electronic device. The controller can generate operation control signals based on the instruction opcode and timing signal to complete the control of instruction fetching and execution.

[0070] The processor may also include a memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or is reusing. If the processor needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0071] The external memory interface can be used to connect an external memory card, such as a MicroSD card, to expand the storage capacity of an electronic device. The external memory card communicates with the processor through the external memory interface, enabling data storage. For example, files such as music and videos can be stored on the external memory card.

[0072] Internal memory can be used to store computer-executable program code, which includes instructions. The processor executes the instructions stored in the internal memory to perform various functional applications and data processing of the electronic device. The internal memory can include a program storage area and a data storage area. The internal memory can include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0073] The wireless communication function of electronic devices can be realized through antennas, wireless communication modules, modem processors, and baseband processors.

[0074] Wireless communication modules can provide wireless communication solutions for electronic devices, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.

[0075] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0076] Electronic devices can achieve shooting functions through ISP, camera, video codec, GPU, display and application processor.

[0077] Electronic devices can achieve display functions through GPU, display screen and application processor.

[0078] A GPU is a microprocessor for image processing that connects the display screen to the application processor. The GPU performs mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0079] The display screen is used to display images, videos, etc. The display screen includes a display panel.

[0080] The storage medium provided in the present application stores a program product that can implement an analysis method for power distribution network feeder outage events.

[0081] The analysis method of the power distribution network feeder power outage event includes: obtaining historical line data, equipment archives and geographic information data of the distribution network, and initializing the power grid topology model based on the line data, equipment archives and geographic information data, wherein the power grid topology model includes the connection relationship between each line and equipment of the distribution network and the status of the equipment; collecting the real-time operating status information of the transformer, and verifying and processing the real-time operating status information to determine abnormal data; correcting the abnormal data, and updating the power grid topology model based on the corrected data; and identifying the power outage area and the power restoration area based on the updated power grid topology model.

[0082] In some possible embodiments, the subject matter of the present disclosure, namely, a method and system for analyzing power outage events in a distribution network feeder, can be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure.

[0083] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0084] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for analyzing a power outage event in a distribution network feeder, characterized in that: include: Acquire historical line data, equipment archives, and geographic information data of the distribution network, and initialize a power grid topology model based on the line data, equipment archives, and geographic information data, wherein the power grid topology model includes the connection relationship between each line and equipment in the distribution network and the status of the equipment; Collecting real-time operating status information of the transformer, verifying and processing the real-time operating status information, and determining abnormal data; Correcting the abnormal data and updating the power grid topology model based on the corrected data; Power outage areas and power restoration areas are identified based on the updated power grid topology model. The process of identifying power outage areas based on the updated power grid topology model includes analyzing the voltage amplitude and power distribution of each node, finding nodes where the voltage amplitude is lower than the normal range or where the power transmission is abnormally interrupted, and checking the status of each switch in the power grid topology model. If the switch in a certain area is in the disconnected state and there is no electrical connection between the area and other normal power supply areas, the area is characterized as a power outage area; the process of identifying power restoration areas based on the updated power grid topology model includes determining the power restoration area based on the restoration of electrical connectivity of abnormal equipment.

2. The method for analyzing a power outage event in a distribution network feeder according to claim 1, characterized in that: Collecting real-time operating status information of the transformer, verifying and processing the real-time operating status information, and determining abnormal data, including: Compare and verify with the historical normal data of the transformer. If it is determined that the collected transformer status signal contains invalid data, data mutation, or inconsistent switching state timing, it is determined that abnormal data exists in the collected real-time transformer operating status information.

3. The method for analyzing a power outage event in a distribution network feeder according to claim 2, characterized in that: Correcting the abnormal data and updating the power grid topology model based on the corrected data includes: For invalid data, a spatial interpolation algorithm is used to fill missing values ​​based on the spatiotemporal correlation of adjacent nodes; For mutation data, multi-source data fusion verification is used to associate meteorological data with equipment status. Multi-source evidence is integrated through DS evidence theory to determine whether the mutation is a real fault. For inconsistent switch state timing data, a Petri net model of the switch action is established, and the switch action sequence is verified through the state transition matrix to correct the timing error; Based on the corrected invalid data, mutation data and inconsistent switch state timing data, spatiotemporal graph convolution is used to dynamically update the node features of the power grid topology model, and the voltage amplitude mutation area is identified through the graph attention mechanism. The disconnection location is corrected in combination with the equipment ledger parameters.

4. The method for analyzing a power outage event in a distribution network feeder according to claim 1, characterized in that: Identify power outage areas based on the updated grid topology model, including: The corrected real-time operating status information of the transformer and the status information of related equipment are sorted according to chronological order and equipment identification, and the geographic information data is integrated to determine the location relationship of each device in geographic space; The sorted real-time operating status information of transformers, status information of related equipment, and location relationships are input into the updated power grid topology model. The node features are updated through spatiotemporal graph convolution to determine the current operating status of the power grid. Use the Newton-Raphson power flow algorithm to calculate the power flow of the power grid, analyze the voltage amplitude and power distribution of each node, and compare the voltage and power range during normal operation to find nodes where the voltage amplitude is lower than the normal range or where power transmission is abnormally interrupted; Check the status of each switch in the power grid topology model. If the switch in a certain area is disconnected and there is no electrical connection between the area and other normally powered areas, the area is marked as a power outage area. The grid topology model is analyzed through the graph attention mechanism to identify voltage amplitude mutation areas. The currently identified voltage amplitude mutation areas are matched with the fault history data to determine similar fault modes and fault occurrence areas. Based on the fault point and the grid topology structure, the scope of the affected power outage area is determined. By analyzing the status of adjacent nodes and judging the electrical connection relationship, all equipment and lines in the power outage area are identified.

5. The method for analyzing a power outage event in a distribution network feeder according to claim 1, characterized in that: The method for analyzing a power distribution network feeder outage event further includes: After determining the power outage area, the relationship between the power outage area and user access points obtained through topological analysis is combined with the load information of the power grid to determine the number of affected users and identify sensitive users based on their power consumption.

6. The method for analyzing a power outage event in a distribution network feeder according to claim 1, characterized in that: Identify power restoration areas based on the updated grid topology model, including: For devices whose status has changed, the electrical connectivity between them and other normally powered devices is analyzed. If an electrical connection is established between a device and the normal power supply area, and the voltage and power of the device return to normal, the area where the device is located is identified as the power restoration area. The area is then gradually extended with the device as the center to identify all devices and lines within the power restoration area.

7. The method for analyzing a power outage event in a distribution network feeder according to claim 1, characterized in that: The method for analyzing a power distribution network feeder outage event further includes: Organize the identified power outage and restoration areas and present them in the form of a device list or geographic graph, where for each area, the device name, number, and geographic location information are listed; Combined with the geographic information system, the power outage areas and power restoration areas are visualized on the map, and the power outage areas and power restoration areas are distinguished by different colors and icons.

8. A system for analyzing power outage events in a distribution network feeder, characterized in that: include: an acquisition unit, configured to acquire historical line data, equipment archives, and geographic information data of the power distribution network, and initialize a power grid topology model based on the line data, equipment archives, and geographic information data, wherein the power grid topology model includes connection relationships between various lines and equipment in the distribution network and the status of the equipment; A determination unit, configured to collect real-time operating status information of the transformer, verify and process the real-time operating status information, and determine abnormal data; an updating unit, configured to correct the abnormal data and update the power grid topology model based on the corrected data; An identification unit is used to identify power outage areas and power restoration areas based on an updated power grid topology model, wherein the process of identifying power outage areas based on the updated power grid topology model includes analyzing the voltage amplitude and power distribution of each node, finding out the nodes where the voltage amplitude is lower than the normal range or the power transmission is abnormally interrupted, and checking the status of each switch in the power grid topology model. If the switch in a certain area is in the disconnected state and there is no electrical connection between the area and other normal power supply areas, the area is characterized as a power outage area; the process of identifying power restoration areas based on the updated power grid topology model includes determining the power restoration area based on the restoration of electrical connectivity of abnormal equipment.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for analyzing a power distribution network feeder outage event according to any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for analyzing a power distribution network feeder outage event according to any one of claims 1 to 7 are implemented.

Images