Medium voltage power failure event full life cycle data model construction method and system

Abstract

The invention discloses a medium-voltage power failure event full life cycle data model construction method and system. The method comprises the following steps: constructing a static object layer according to a power grid topology connection relationship based on IDs and attribute sets of equipment objects and environment objects; recording a real-time event through a pre-designed standardized power failure event mode; fusing the static object layer with a real-time event by using a graph database, and constructing a real-time relation graph layer; an intelligent analysis function is integrated in the real-time relation graph layer, and a dynamic knowledge graph model is constructed. According to the invention, complete and continuous data description of a power failure event in advance, in the event and after the event is realized; through the knowledge graph technology, the internal and external complex association of the power failure event is explicitly expressed and can be dynamically updated in real time, so that the power failure situation is visual, clear and comprehensive; the intelligent level of services such as fault positioning, first-aid repair command and power grid planning is remarkably improved, the power failure time is effectively shortened, and the power supply reliability and the customer satisfaction degree are improved.

Description

Technical Field

[0001] This invention relates to the field of power grid informatization and intelligentization technology, specifically to a method and system for constructing a full lifecycle data model of medium-voltage power outage events. Background Technology

[0002] Power supply reliability is a core indicator for measuring the operational level of a distribution network, and the medium-voltage distribution network is a key link affecting users' power outage experience. Currently, the management of medium-voltage power outages relies heavily on multiple independent information systems, such as Production Management Systems (PMS), Supervisory Control and Data Acquisition (SCADA) systems, electricity consumption information collection systems, and Geographic Information Systems (GIS). These systems each record only a portion of the outage-related data, forming "data silos."

[0003] The data models in existing technologies have significant flaws: Model flattening: It usually only records basic attributes of power outage events such as "line name, start time, end time, number of households at the time of power outage", and cannot describe the causal chain and dynamic evolution process of power outages.

[0004] Post-event recording type: The model is mainly used to meet the statistical reporting of reliability indicators (such as SAIDI, SAIFI). It is a passive recording method and lacks the ability to support pre-event warning and in-event command.

[0005] Weak correlation: There is a lack of explicit and dynamic correlation between power outage events and key entities such as power grid equipment, operating environment, and personnel handling the situation, making in-depth analysis difficult.

[0006] These limitations have resulted in the data value not being fully explored, failing to meet the needs of advanced applications such as proactive power grids, precise emergency repairs, and intelligent decision-making. Summary of the Invention

[0007] To address the issues of isolation, flatness, and static nature in existing medium-voltage power outage event data models, this invention proposes a method for constructing a full lifecycle data model for medium-voltage power outage events, including: A static object layer is constructed based on the IDs and attribute sets of device objects and environment objects, according to the power grid topology connection relationship. Real-time events are recorded using a pre-designed standardized power outage event pattern, wherein the standardized power outage event pattern is used to record all state changes throughout the entire power outage lifecycle; By leveraging graph databases, a real-time relationship graph layer is constructed by integrating static object layers with real-time events. Intelligent analysis functions are integrated into the real-time relationship graph layer to construct a dynamic knowledge graph model.

[0008] Preferably, the construction of the static object layer based on the IDs and attribute sets of device objects and environment objects, according to the power grid topology connection relationship, includes: Based on the IDs and attribute sets of device objects and environment objects, information technology and data analysis methods are used to model the relationships between various objects and construct the logical attributes and connection relationships of the objects. Based on the logical attributes and connection relationships of objects, a static object layer is constructed by deeply integrating the device objects with geospatial data using geographic information system technology.

[0009] Preferably, after constructing the static object layer based on the IDs and attribute sets of device objects and environment objects according to the power grid topology connection relationship, the method further includes: Data cleaning and verification mechanisms are used to clean and verify the data in the static object layer.

[0010] Preferably, the standardized power outage event pattern includes: an event and an event type; An event includes: event ID, type, timestamp, list of associated objects, geographic location, event source, and key metrics; Event types include: overload warning, fault trip, protection action, switch opening, fault patrol start, fault location, isolation operation execution, power transfer operation execution, repair completion, and power restoration.

[0011] Preferably, the integration of intelligent analysis functions into the real-time relationship graph layer to construct a dynamic knowledge graph model includes: Integrating the graph's association query and calculation capabilities into the real-time relationship graph layer enables rapid location of the root cause of a fault, generation of the optimal recovery strategy, and prediction of reliability risks for a line or region.

[0012] Furthermore, this application also provides a system for constructing a full lifecycle data model for medium-voltage power outage events, including: The topology building module is used to construct a static object layer based on the IDs and attribute sets of device objects and environment objects, according to the power grid topology connection relationships. The event logging module is used to record real-time events through a pre-designed standardized power outage event pattern, wherein the standardized power outage event pattern is used to record all state changes throughout the entire power outage lifecycle; The graph construction module is used to integrate static object layers with real-time events using graph databases to build a real-time relationship graph layer. The model building module is used to integrate intelligent analysis functions into the real-time relationship graph layer to build a dynamic knowledge graph model.

[0013] Preferably, the topology building module is specifically used for: Based on the IDs and attribute sets of device objects and environment objects, information technology and data analysis methods are used to model the relationships between various objects and construct the logical attributes and connection relationships of the objects. Based on the logical attributes and connection relationships of objects, a static object layer is constructed by deeply integrating the device objects with geospatial data using geographic information system technology.

[0014] Preferably, the model building module is specifically used for: Integrating the graph's association query and calculation capabilities into the real-time relationship graph layer enables rapid location of the root cause of a fault, generation of the optimal recovery strategy, and prediction of reliability risks for a line or region.

[0015] Furthermore, this application also provides a method for analyzing medium-voltage power outage events based on a full lifecycle data model, including: Obtain operational information for the predicted region or power grid; The operational information of the predicted area or power grid is input into a pre-built dynamic knowledge graph model to obtain one or more of the following: the cause of the fault in the predicted area or power grid, the optimal recovery strategy, and the reliability risk assessment value. The pre-built dynamic knowledge graph model is constructed using a method for constructing a full lifecycle data model of a medium-voltage power outage event as described above.

[0016] Preferably, the step of inputting the operational information of the predicted region or power grid into a pre-built dynamic knowledge graph model to obtain one or more of the following: fault causes, optimal recovery strategies, and reliability risk assessment values ​​for the predicted region or power grid, includes: When a power outage event is detected in the operational information of the predicted area or power grid, the root cause of the fault can be quickly located and the optimal recovery strategy can be generated through real-time topology analysis based on the power outage event and a pre-built dynamic knowledge graph model. When no power outage events are found in the operational information of the predicted area or power grid, the reliability risk value of the line or area is predicted based on the historical power outage events, equipment operating conditions, and environmental data associated in the pre-built dynamic knowledge graph model.

[0017] Preferably, when a power outage event occurs in the predicted area or power grid operation information, the root cause of the fault is quickly located and the optimal recovery strategy is generated through real-time topology analysis based on the power outage event and a pre-built dynamic knowledge graph model, including: Based on the power outage event and a pre-built dynamic knowledge graph model, calculate a list of grid equipment and users affected by the power outage; Based on the relationships between events and objects in a pre-built dynamic knowledge graph model, the root cause of the failure is located and the optimal recovery strategy is generated.

[0018] Furthermore, this application also provides a system for analyzing medium-voltage power outage events based on a full lifecycle data model, including: The information acquisition module is used to acquire operational information of the forecast area or power grid; The intelligent analysis module is used to input the operation information of the predicted area or power grid into a pre-built dynamic knowledge graph model to obtain one or more of the following: the cause of failure in the predicted area or power grid, the optimal recovery strategy, and the reliability risk assessment value. The pre-built dynamic knowledge graph model is constructed using a method for constructing a full lifecycle data model of a medium-voltage power outage event as described above.

[0019] Preferably, the intelligent analysis module includes: The event analysis submodule is used to quickly locate the root cause of the fault and generate the optimal recovery strategy when a power outage event is detected in the operation information of the predicted area or power grid, based on the power outage event and a pre-built dynamic knowledge graph model through real-time topology analysis. The risk assessment submodule is used to predict the reliability risk value of a line or area based on historical power outage events, equipment operating conditions, and environmental data associated with a pre-built dynamic knowledge graph model when no power outage events are found in the operational information of the predicted area or power grid.

[0020] Preferably, the event analysis submodule is specifically used for: Based on the power outage event and a pre-built dynamic knowledge graph model, calculate a list of grid equipment and users affected by the power outage; Based on the relationships between events and objects in a pre-built dynamic knowledge graph model, the root cause of the failure is located and the optimal recovery strategy is generated.

[0021] In another aspect, this application also provides an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, a method for constructing a full lifecycle data model of a medium-voltage power outage event, as described above, or a method for analyzing medium-voltage power outage events based on a full lifecycle data model, is implemented.

[0022] In another aspect, this application also provides a computer-readable storage medium having an executable program stored thereon, which, when executed, implements a method for constructing a full lifecycle data model of a medium-voltage power outage event or a method for analyzing a medium-voltage power outage event based on a full lifecycle data model, as described above.

[0023] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention provides a method for constructing a full lifecycle data model for medium-voltage power outage events, comprising: constructing a static object layer based on the IDs and attribute sets of equipment and environmental objects, according to the power grid topology; recording real-time events through a pre-designed standardized power outage event pattern, wherein the standardized power outage event pattern is used to record all state changes throughout the power outage lifecycle; integrating the static object layer with real-time events using a graph database to construct a real-time relationship graph layer; and integrating intelligent analysis functions into the real-time relationship graph layer to construct a dynamic knowledge graph model. This invention achieves a complete and continuous data characterization of power outage events from "pre-event to during-event to post-event"; through knowledge graph technology, it explicitly expresses the complex internal and external relationships of power outage events and can dynamically update them in real time, making the power outage situation intuitive, clear, and comprehensive; significantly improving the intelligence level of fault location, emergency repair command, and power grid planning, effectively shortening power outage time, and improving power supply reliability and customer satisfaction. Attached Figure Description

[0024] Figure 1 This is a flowchart of a method for constructing a full lifecycle data model for medium-voltage power outage events according to the present invention; Figure 2 This is a flowchart of the full lifecycle data model for medium-voltage power outage events based on dynamic knowledge graphs, as presented in this invention. Figure 3 This is a flowchart illustrating the construction process of the power grid physical topology layer of the present invention; Figure 4 This is an example diagram of the power outage dynamic event mode—event tracing framework of the present invention; Figure 5 This is a flowchart of the real-time relationship graph construction process of the present invention; Figure 6 This is a schematic diagram of the power outage event integrated feature enhancement and intelligent analysis module of the present invention; Figure 7 This is a schematic diagram of an electronic device structure according to the present invention. Detailed Implementation

[0025] This invention proposes a method for constructing a full lifecycle data model for medium-voltage power outage events, and proposes an "event-object-relationship" dynamic knowledge graph model, hereinafter referred to as the EOR-DKG model. This model treats a power outage event as a dynamic process composed of a series of sub-events, and deeply associates them with various static and dynamic objects through knowledge graph technology. Its purpose is to achieve full lifecycle data fusion and management of power outage events from "early warning, occurrence, evolution, handling to recovery"; to construct a knowledge graph model that can dynamically reflect the complex relationships between power outage events and power grid assets, operating environment, and handling activities; and to improve the model's intelligence level, providing a high-quality data foundation for advanced applications such as fault prediction, root cause analysis, and recovery strategy optimization.

[0026] To better understand the present invention, the following description, in conjunction with the accompanying drawings and embodiments, will further illustrate the content of the present invention.

[0027] Example 1: A method for constructing a full lifecycle data model for medium-voltage power outage events, such as Figure 1 As shown, it includes: Step 1: Based on the IDs and attribute sets of device objects and environment objects, construct a static object layer according to the power grid topology connection relationship; Step 2: Record real-time events using a pre-designed standardized power outage event pattern, wherein the standardized power outage event pattern is used to record all state changes throughout the entire power outage lifecycle; Step 3: Use a graph database to integrate the static object layer with real-time events to construct a real-time relationship graph layer; Step 4: Integrate intelligent analysis functions into the real-time relationship graph layer to build a dynamic knowledge graph model.

[0028] The invention will be further described below with reference to the accompanying drawings. A method for constructing a full lifecycle data model of medium-voltage power outage events based on dynamic knowledge graphs is described below. Figure 2 As shown, it includes the following steps: Step 1: Construct the static object layer (power grid physical topology layer), such as Figure 3 As shown.

[0029] A model of power grid assets is established, including equipment objects such as medium-voltage lines, switches, transformers, and towers, as well as environmental objects such as meteorological monitoring points and geographical areas. Each object has a unique ID and attribute set (such as equipment model, commissioning date, health index, geographical location, etc.), and a static relationship network is constructed according to the power grid topology.

[0030] The equipment includes important components such as medium-voltage lines, switches, transformers, and poles. Medium-voltage lines, as key channels for power transmission, play a vital role in connecting various nodes and transmitting electrical energy throughout the power grid system; switches control the on / off state of circuits, ensuring the safe and stable operation of the power grid; transformers are responsible for voltage conversion to meet the power needs of different users and equipment; and poles, as supporting structures, provide a stable foundation for the lines.

[0031] Environmental factors are equally important, including meteorological monitoring stations and geographical regions. Meteorological monitoring stations collect real-time meteorological data such as temperature, humidity, wind speed, and precipitation. These meteorological conditions have a significant impact on the operation of power grid equipment; for example, high temperatures can cause equipment overheating, and strong winds can damage poles and lines. The division of geographical regions helps in the rational planning and management of the power grid based on factors such as terrain, population density, and electricity demand in different areas.

[0032] Each object has a unique ID and a detailed set of attributes. The equipment's attribute set covers key information such as equipment model, commissioning date, health index, and geographical location. The equipment model determines the equipment's performance and applicable scope; the commissioning date helps determine the equipment's service life and degree of aging; the health index comprehensively reflects the equipment's operating status and reliability; and geographical location information is of great significance for equipment maintenance, emergency repair, and power grid planning and layout.

[0033] A static relationship network is constructed based on the power grid topology. Power grid topology refers to the electrical connections and spatial relationships between various equipment and environmental objects. Accurately understanding these relationships allows for a clear depiction of the entire power grid's structure and operational logic. When constructing the static relationship network, advanced information technology and data analysis methods are used to precisely model and visualize the relationships between various objects. This enables power grid managers to intuitively understand the power grid's operational status, promptly identify potential problems and faults, and provide strong support for the safe and stable operation of the power grid. GIS (Geographic Information System) technology is used to deeply integrate the power grid asset model with geospatial data. GIS technology has powerful spatial analysis and visualization capabilities, combining the geographical location information of power grid equipment and environmental objects with map data to achieve precise spatial positioning and visualization of equipment and environmental objects. Within the GIS system, the distribution of power grid equipment, line routes, and their relationship with the surrounding geographical environment can be intuitively seen. This not only helps power grid planners to make scientific and rational power grid layouts but also provides important information for emergency repair personnel to quickly locate fault points and formulate repair plans.

[0034] After constructing the static object layer based on the IDs and attribute sets of device objects and environment objects according to the power grid topology connection relationship, the present invention further includes: Data cleaning and verification mechanisms are used to clean and verify the data in the static object layer.

[0035] Specifically, the process involves utilizing data cleaning and verification mechanisms to ensure the integrity, accuracy, and consistency of data at the static object layer. Data cleaning refers to the screening, organization, and correction of collected raw data, removing duplicates, errors, and incomplete data. Data verification involves checking and validating the cleaned data by setting a series of rules and standards to ensure that the data meets requirements. In practice, automated data cleaning and verification tools will be used in conjunction with manual review to conduct comprehensive quality control of the static object layer data, ensuring high data quality and providing a reliable data foundation for the subsequent construction of dynamic knowledge graphs. This will enable effective management and analysis of the entire lifecycle of medium-voltage power outage events. Step 2: Define the dynamic event pattern (event sourcing framework).

[0036] Design a standardized power outage event model to record all state changes throughout the entire power outage lifecycle. Each event includes attributes such as event ID, type, timestamp, list of associated objects, geographical location, event source, and key indicators. Event types include, but are not limited to: overload warning, fault trip, protection action, switch opening, fault patrol start, fault location, isolation operation execution, power transfer operation execution, repair completion, and power restoration.

[0037] This model allows for detailed tracking of every critical step in a power outage event, from its occurrence to its recovery. For example, in an overload warning event, it records the load value at the time, the warning time, and potentially affected related objects; in a fault trip event, it identifies the specific time of the trip, the associated lines or equipment, and geographical location information. These detailed event records facilitate comprehensive analysis of subsequent power outage events, including determining the cause of the fault, assessing the scope of impact, and calculating the outage duration, providing strong data support for power grid operation and maintenance management and decision-making.

[0038] Step 3: Construct a real-time relationship graph layer (dynamic fusion and computation), such as Figure 5 As shown.

[0039] Using a graph database, the static object layer from step 1 is merged with the real-time event stream flowing in from step 2. When a power outage event occurs, the system automatically executes the following process: Impact range calculation in seconds: Based on events such as switch tripping and protection actions, the system uses real-time topology analysis to accurately calculate the list of power grid equipment and users affected by the power outage.

[0040] Dynamic coloring of the map: Visualize the power outage status in the map, for example, use red to mark faulty equipment, gray to mark the power outage area, blue to mark the area that has been transferred to power, and orange to mark the isolated equipment.

[0041] Dynamic relationship establishment: Establish relationships between events and objects in real time, such as fault event-impact-user, emergency repair instruction-assignment-repair team, power transfer scheme-restoration-load.

[0042] Step 4: Integrate the feature enhancement and intelligent analysis module (data integration and analysis prediction).

[0043] Based on the real-time relationship graph layer, an intelligent analysis module is integrated, such as... Figure 6 As shown, by utilizing the association query and calculation capabilities of the graph, the following can be achieved: Root cause analysis: By tracing back the event sequence and historical data associated with the faulty equipment, the root cause of the fault can be quickly located; Recovery strategy recommendation: Based on the real-time graph status, the optimal recovery strategy can be generated by comprehensively considering the transfer path, capacity constraints, and operational efficiency; Reliability prediction: By associating historical power outage events, equipment operating conditions, and environmental data, the reliability risk of the line or area can be predicted.

[0044] Based on the model, an intelligent analysis module is integrated to fully leverage the powerful association query and computation capabilities of the graph, constructing the following key functionalities: Root cause analysis: When a power grid fault occurs, the intelligent analysis module quickly traces back the sequence of events associated with the faulty equipment. For example... Figure 4 As shown in the diagram, E003 is the event code. This includes not only recent real-time events such as switch tripping and protection actions, but also in-depth historical data analysis, covering past equipment fault records, maintenance status, and trends in operating parameters. Through meticulous analysis and precise reasoning of large amounts of complex data, the root cause of a fault can be quickly and accurately located in a short time. For example, if a line trips, the system will thoroughly investigate the related protection actions, the operating status of surrounding equipment, and whether similar faults and their handling methods exist in the past, thereby identifying the true root cause of the trip.

[0045] Recommended Recovery Strategy: Based on the real-time power grid status presented in the graph, the intelligent analysis module generates the optimal recovery strategy by integrating multiple factors. On one hand, it comprehensively considers the feasibility and stability of power transfer paths, assessing the carrying capacity, electrical distance, and connectivity with other parts of the power grid of different transfer lines. On the other hand, it strictly considers capacity constraints to ensure that overload issues do not occur during the power transfer process, guaranteeing the safe and stable operation of the power grid. Simultaneously, it also considers operational efficiency, prioritizing recovery schemes that are simple to operate and have short processing times. For example, after a power outage occurs in a certain area, the system analyzes multiple possible power transfer paths based on real-time graph information, then conducts a detailed evaluation of the capacity and operational difficulty of each path, ultimately determining the optimal recovery strategy that can quickly restore power while ensuring power grid safety.

[0046] Reliability Prediction: The intelligent analysis module integrates multi-dimensional information, including historical power outage events, equipment operating conditions, and environmental data, to scientifically predict reliability risks for power lines or regions. For historical power outage events, it analyzes their timing, frequency, causes, and impact range, summarizing potential patterns and risk factors. Regarding equipment operating conditions, it monitors various operating parameters in real time, such as temperature, voltage, and current, to assess the equipment's health status. Environmental data includes meteorological conditions and geographical information, as severe weather conditions (such as heavy rain, strong winds, and high temperatures) and unique geographical environments can all affect power grid reliability. Through comprehensive analysis and in-depth mining of this information, potential reliability risks for power lines or regions can be predicted in advance, providing strong decision support for power grid operation and management.

[0047] Load Forecasting: Combining historical load data, meteorological information, and the impact of real-time events, the intelligent analysis module accurately predicts future load trends in the power grid. Historical load data includes electricity consumption patterns across different time periods, seasons, weekdays, and weekends. Analysis and modeling of this data reveals user electricity consumption habits and load variation characteristics. Meteorological information is also a crucial factor influencing load; for example, high temperatures lead to a significant increase in electricity consumption for cooling equipment such as air conditioners, while cold weather increases the use of heating equipment. Real-time event impacts include major events and adjustments to industrial production plans. The intelligent analysis module comprehensively considers these factors, employing advanced data analysis and prediction algorithms to accurately predict power grid load changes over a future period, providing a scientific basis for power grid dispatching and planning.

[0048] Risk Assessment: The intelligent analysis module comprehensively and thoroughly assesses the operational risks of each link in the power grid by considering multiple dimensions, including equipment health status, operating environment, and real-time events. Regarding equipment health status, it monitors and analyzes various performance indicators and operating parameters to determine if there are potential faults. The operating environment includes both natural and social factors. Natural disasters such as earthquakes and floods can damage power grid facilities, while social factors such as nearby construction and human-caused damage can affect the safe operation of the power grid. Real-time events cover various emergencies, such as fault tripping and protection actions. Through a comprehensive assessment of these factors, the risk level faced by each link in the power grid can be accurately identified, providing detailed and reliable information for operation and maintenance decisions, enabling targeted measures to mitigate risks.

[0049] Resource optimization and allocation: Based on real-time network data and prediction results, the intelligent analysis module rationally allocates repair resources and backup equipment to improve resource utilization efficiency and reduce power outage losses. The real-time network data clearly displays the fault location, affected area, and equipment damage status, thus determining the type and quantity of repair resources required. Prediction results include estimates of outage duration and load recovery status. Based on this information, the system scientifically dispatches repair teams, rationally arranging their routes and travel times to the fault site to ensure rapid arrival and commencement of repair work. Simultaneously, backup equipment is optimized, and appropriate backup equipment is promptly allocated and replaced according to the type and specifications of the faulty equipment, minimizing outage time and ensuring the grid's rapid restoration of power supply. For example, after a large-scale power grid fault occurs, the system, based on real-time data and prediction results, quickly dispatches multiple repair teams to different fault locations and allocates corresponding backup transformers, cables, and other equipment to efficiently complete the repair task and minimize power outage losses. Example 2 Furthermore, this application also provides a system for constructing a full lifecycle data model for medium-voltage power outage events, including: The topology building module is used to construct a static object layer based on the IDs and attribute sets of device objects and environment objects, according to the power grid topology connection relationships. The event logging module is used to record real-time events through a pre-designed standardized power outage event pattern, wherein the standardized power outage event pattern is used to record all state changes throughout the entire power outage lifecycle; The graph construction module is used to integrate static object layers with real-time events using graph databases to build a real-time relationship graph layer. The model building module is used to integrate intelligent analysis functions into the real-time relationship graph layer to build a dynamic knowledge graph model.

[0050] Preferably, the topology building module is specifically used for: Based on the IDs and attribute sets of device objects and environment objects, information technology and data analysis methods are used to model the relationships between various objects and construct the logical attributes and connection relationships of the objects. Based on the logical attributes and connection relationships of objects, a static object layer is constructed by deeply integrating the device objects with geospatial data using geographic information system technology.

[0051] Preferably, the model building module is specifically used for: Integrating the graph's association query and calculation capabilities into the real-time relationship graph layer enables rapid location of the root cause of a fault, generation of the optimal recovery strategy, and prediction of reliability risks for a line or region.

[0052] Example 3 Furthermore, this application also provides a method for analyzing medium-voltage power outage events based on a full lifecycle data model, including: Obtain operational information for the predicted region or power grid; The operational information of the predicted area or power grid is input into a pre-built dynamic knowledge graph model to obtain one or more of the following: the cause of the fault in the predicted area or power grid, the optimal recovery strategy, and the reliability risk assessment value. The pre-built dynamic knowledge graph model is constructed using a method for constructing a full lifecycle data model of a medium-voltage power outage event as described above.

[0053] Preferably, the step of inputting the operational information of the predicted region or power grid into a pre-built dynamic knowledge graph model to obtain one or more of the following: fault causes, optimal recovery strategies, and reliability risk assessment values ​​for the predicted region or power grid, includes: When a power outage event is detected in the operational information of the predicted area or power grid, the root cause of the fault can be quickly located and the optimal recovery strategy can be generated through real-time topology analysis based on the power outage event and a pre-built dynamic knowledge graph model. When no power outage events are found in the operational information of the predicted area or power grid, the reliability risk value of the line or area is predicted based on the historical power outage events, equipment operating conditions, and environmental data associated in the pre-built dynamic knowledge graph model.

[0054] Preferably, when a power outage event occurs in the predicted area or power grid operation information, the root cause of the fault is quickly located and the optimal recovery strategy is generated through real-time topology analysis based on the power outage event and a pre-built dynamic knowledge graph model, including: Based on the power outage event and a pre-built dynamic knowledge graph model, calculate a list of grid equipment and users affected by the power outage; Based on the relationships between events and objects in a pre-built dynamic knowledge graph model, the root cause of the failure is located and the optimal recovery strategy is generated.

[0055] The specific content includes: model application and output (report output).

[0056] The constructed EOR-DKG model will provide services to upper-level application systems through API interfaces or visualization platforms, and the output content includes: accurate power outage impact range, visualized panoramic view of the handling process, structured analysis reports, and intelligent decision-making suggestions.

[0057] In this way, upper-level application systems can obtain real-time information on the current status of the power grid and detailed information on fault handling. Precise outage impact range helps dispatchers quickly understand the affected areas and users, improving emergency response efficiency; a visualized panoramic view of the handling process intuitively displays the entire process from fault occurrence to resolution, facilitating monitoring and command; structured analysis reports provide detailed data support and root cause analysis, assisting in the development of long-term improvement strategies; and intelligent decision-making suggestions, based on real-time data and historical experience, provide optimal operational guidance for maintenance personnel, reducing the risk of human error.

[0058] Compared with the prior art, the present invention has the following significant advantages: Full lifecycle management: It enables a complete and continuous data characterization of power outage events from "before the event to during the event to after the event", changing the traditional model's fragmented recording mode that only focuses on "during the event to after the event".

[0059] Deep correlation and dynamic perception: Through knowledge graph technology, the complex internal and external relationships of power outage events are explicitly expressed and can be dynamically updated in real time, making the power outage situation intuitive, clear and comprehensive.

[0060] Support for intelligent applications: Provides a high-quality, highly correlated data foundation for AI algorithms, significantly improving the intelligence level of services such as fault location, emergency repair command, and power grid planning.

[0061] Improve operational efficiency: Through precise power outage impact analysis and optimized recovery strategies, power outage time can be effectively shortened, power supply reliability and customer satisfaction can be improved.

[0062] In the process of realizing the fusion and management of data throughout the entire lifecycle of power outage events, the EOR-DKG model of this invention will play a core role. This model is not merely a simple collection of static objects, but rather dynamically captures the evolution of power outage events, realizing the complex relationships between power outage events and grid assets, operating environment, and response activities through knowledge graph technology.

[0063] When a power outage occurs, the EOR-DKG model can respond quickly, updating the grid status based on real-time data. It dynamically adjusts the grid model based on historical data, real-time monitoring information, and external data sources such as weather forecasts to predict potential power outage risks and provide decision support for grid dispatch and emergency response. For example, if the model predicts line overload due to extreme weather conditions, it can promptly adjust grid operation strategies to transfer loads to other stable lines, thereby avoiding or mitigating power outages.

[0064] When a power outage inevitably occurs, the EOR-DKG model records every detail of the event, including the scope of the outage, affected equipment, and affected user groups. This information is added to the knowledge graph in real time, providing rich data support for root cause analysis. Root cause analysis is a crucial step in understanding the nature of power outage events. Through in-depth analysis of event details, the root causes of power outages can be revealed, providing a scientific basis for future preventative measures and system improvements.

[0065] Optimizing recovery strategies is another important application of the EOR-DKG model. During the outage response phase, the model proposes optimal recovery strategies based on the current grid state and historical recovery cases. These strategies may include prioritizing the restoration of power to critical infrastructure, rationally dispatching backup power sources and mobile generation equipment, and developing scientific user electricity consumption guidance strategies. By optimizing recovery strategies, the impact of power outages on socio-economic activities can be minimized, and the grid can be restored to normal operation more quickly.

[0066] In summary, the EOR-DKG model proposed in this invention is an important tool for realizing intelligent power grid management. By constructing a comprehensive, dynamic, and intelligent data model, it not only improves the efficiency and effectiveness of the power grid in responding to power outages but also provides strong data support for the long-term planning and development of the power grid. In the future, with continuous technological advancements and increased data accumulation, the EOR-DKG model will be further improved, injecting new vitality into the development of smart grids.

[0067] Example 4 Furthermore, this application also provides a system for analyzing medium-voltage power outage events based on a full lifecycle data model, including: The information acquisition module is used to acquire operational information of the forecast area or power grid; The intelligent analysis module is used to input the operation information of the predicted area or power grid into a pre-built dynamic knowledge graph model to obtain one or more of the following: the cause of failure in the predicted area or power grid, the optimal recovery strategy, and the reliability risk assessment value. The pre-built dynamic knowledge graph model is constructed using a method for constructing a full lifecycle data model of a medium-voltage power outage event as described above.

[0068] Preferably, the intelligent analysis module includes: The event analysis submodule is used to quickly locate the root cause of the fault and generate the optimal recovery strategy when a power outage event is detected in the operation information of the predicted area or power grid, based on the power outage event and a pre-built dynamic knowledge graph model through real-time topology analysis. The risk assessment submodule is used to predict the reliability risk value of a line or area based on historical power outage events, equipment operating conditions, and environmental data associated with a pre-built dynamic knowledge graph model when no power outage events are found in the operational information of the predicted area or power grid.

[0069] Preferably, the event analysis submodule is specifically used for: Based on the power outage event and a pre-built dynamic knowledge graph model, calculate a list of grid equipment and users affected by the power outage; Based on the relationships between events and objects in a pre-built dynamic knowledge graph model, the root cause of the failure is located and the optimal recovery strategy is generated.

[0070] Example 5 The application of this model is illustrated by taking the entire process of a transient fault developing into a permanent fault on a 10kV line as an example.

[0071] Initial state: A complete digital twin model of the line has been established in the static object layer, including all switches, towers, transformers and users supplied by it.

[0072] The incident occurred: At time t1: The SCADA system generates an "XX line overload warning" event, and the model records the event and associates it with the "XX line" device.

[0073] At time t2: The "XX line protection action (reclosing)" event and the "switch tripping" event are generated. The model immediately starts topology analysis, calculates the list of affected users within seconds, and marks the relevant areas in gray (power outage) on the graph.

[0074] At time t3: Reclosing fails, generating a "Protection Action (Permanent Fault)" event. The model updates the event status.

[0075] Incident handling: At time t4: The dispatcher issues a "fault patrol" command, and the model records the command event and associates it with the specific patrol team assigned to it.

[0076] At time t5: The patrol personnel report the "#15 tower insulator breakdown" event via mobile terminal. The model associates this event with the "#15 tower" object and marks its status as red (fault).

[0077] At time t6: Based on automatic analysis of the spectrum, the model recommends the optimal power transfer scheme: "Transfer the non-faulty section load to the adjacent 'XX line' via tie switch L1". The dispatcher executes the "Operate switch L1" event.

[0078] At time t7: Operation complete. The model updates the power grid topology, marking the areas that have been transferred to power supply in blue and narrowing the gray outage area.

[0079] At time t8: Repair is completed, generating "Repair Complete" and "Power Restoration" events. The model updates the status of all relevant objects to normal.

[0080] Post-outage analysis: Based on data from the entire process, the model can generate an analysis report with one click, including the cause of the power outage, the number of households affected, the assessment of handling efficiency, etc., and provide predictions and early warnings for similar subsequent failures.

[0081] The data model constructed by the method described in this invention covers the entire process of a power outage event, enabling data-driven accurate perception, intelligent decision-making, and efficient handling, and significantly improving the level of power supply reliability management.

[0082] In step 1, a digital twin foundation for power grid assets and the environment is constructed, transforming physical entities into digital objects with rich attributes and topological relationships, serving as the static basis for the data model.

[0083] In step 2, an event sourcing design pattern was adopted, which defined a standardized power outage event pattern and recorded all important state change sequences in the power outage lifecycle, rather than just the final result.

[0084] In step 3, an innovative method for constructing a dynamic knowledge graph of "event-object-relationship" is proposed. By integrating static objects and dynamic events in real time, it enables second-level accurate calculation of the impact range of power outages and dynamic topology coloring visualization.

[0085] In step 4, a feature enhancement and intelligent analysis module is integrated on the basis of the data model. By utilizing the correlation of the graph data, advanced functions such as root cause analysis, recovery strategy recommendation and reliability prediction are realized.

[0086] A system for constructing a full lifecycle data model of a medium-voltage power outage event is protected. The system includes a static object management module, an event stream processing engine, a graph construction and calculation engine, and an intelligent analysis module for implementing the above methods.

[0087] Example 6 like Figure 7As shown, the present invention also provides an electronic device, which may be a computer device, a microcontroller device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, processor, and transceiver component are connected via a bus; the memory can be used to store executable programs, and an exemplary executable program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, which can be accessed and / or modified when instructions are executed.

[0088] The processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and it is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the storage medium to realize the corresponding method flow or corresponding function, so as to realize the steps of the method for constructing a full life cycle data model of a medium-voltage power outage event or a method for analyzing a medium-voltage power outage event based on a full life cycle data model in the above embodiments.

[0089] Example 7 Based on the same inventive concept, this invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory). This readable storage medium is a memory device within an electronic device used to store programs and data. It is understood that the storage medium here can include both built-in storage media within the electronic device and extended storage media supported by the electronic device. The storage medium provides storage space, which stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more executable programs (including program code). It should be noted that the storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. Loading and executing one or more instructions stored in the storage medium by the processor can implement the steps of the method for constructing a full lifecycle data model of a medium-voltage power outage event or a method for analyzing medium-voltage power outage events based on a full lifecycle data model, as described in the above embodiments.

[0090] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. 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. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0092] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0093] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0094] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of the claims of the present invention pending approval.

Claims

1. A method for constructing a full lifecycle data model for medium-voltage power outage events, characterized in that, include: A static object layer is constructed based on the IDs and attribute sets of device objects and environment objects, according to the power grid topology connection relationship. Real-time events are recorded using a pre-designed standardized power outage event pattern, wherein the standardized power outage event pattern is used to record all state changes throughout the entire power outage lifecycle; By leveraging graph databases, a real-time relationship graph layer is constructed by integrating static object layers with real-time events. Intelligent analysis functions are integrated into the real-time relationship graph layer to construct a dynamic knowledge graph model.

2. The method as described in claim 1, characterized in that, The static object layer, constructed based on the IDs and attribute sets of device objects and environment objects according to the power grid topology connection relationship, includes: Based on the IDs and attribute sets of device objects and environment objects, information technology and data analysis methods are used to model the relationships between various objects and construct the logical attributes and connection relationships of the objects. Based on the logical attributes and connection relationships of objects, a static object layer is constructed by deeply integrating the device objects with geospatial data using geographic information system technology.

3. The method as described in claim 1, characterized in that, After constructing the static object layer based on the IDs and attribute sets of device objects and environment objects according to the power grid topology connection relationship, the following is also included: Data cleaning and verification mechanisms are used to clean and verify the data in the static object layer.

4. The method as described in claim 1, characterized in that, The standardized power outage event model includes: events and event types; An event includes: event ID, type, timestamp, list of associated objects, geographic location, event source, and key metrics; Event types include: overload warning, fault trip, protection action, switch opening, fault patrol start, fault location, isolation operation execution, power transfer operation execution, repair completion, and power restoration.

5. The method as described in claim 1, characterized in that, The integration of intelligent analysis functions into the real-time relationship graph layer to construct a dynamic knowledge graph model includes: Integrating the graph's association query and calculation capabilities into the real-time relationship graph layer enables rapid location of the root cause of a fault, generation of the optimal recovery strategy, and prediction of reliability risks for a line or region.

6. A system for constructing a full lifecycle data model for medium-voltage power outage events, characterized in that, include: The topology building module is used to construct a static object layer based on the IDs and attribute sets of device objects and environment objects, according to the power grid topology connection relationships. The event logging module is used to record real-time events through a pre-designed standardized power outage event pattern, wherein the standardized power outage event pattern is used to record all state changes throughout the entire power outage lifecycle; The graph construction module is used to integrate static object layers with real-time events using graph databases to build a real-time relationship graph layer. The model building module is used to integrate intelligent analysis functions into the real-time relationship graph layer to build a dynamic knowledge graph model.

7. The system as described in claim 6, characterized in that, The topology construction module is specifically used for: Based on the IDs and attribute sets of device objects and environment objects, information technology and data analysis methods are used to model the relationships between various objects and construct the logical attributes and connection relationships of the objects. Based on the logical attributes and connection relationships of objects, a static object layer is constructed by deeply integrating the device objects with geospatial data using geographic information system technology.

8. The system as described in claim 6, characterized in that, The model building module is specifically used for: Integrating the graph's association query and calculation capabilities into the real-time relationship graph layer enables rapid location of the root cause of a fault, generation of the optimal recovery strategy, and prediction of reliability risks for a line or region.

9. A method for analyzing medium-voltage power outage events based on a full lifecycle data model, characterized in that, include: Obtain operational information for the predicted region or power grid; The operational information of the predicted area or power grid is input into a pre-built dynamic knowledge graph model to obtain one or more of the following: the cause of the fault in the predicted area or power grid, the optimal recovery strategy, and the reliability risk assessment value. The pre-built dynamic knowledge graph model is constructed using a method for constructing a full lifecycle data model of a medium-voltage power outage event as described in any one of claims 1-5.

10. The method as described in claim 9, characterized in that, The step of inputting the operational information of the predicted region or power grid into a pre-built dynamic knowledge graph model to obtain one or more of the following: fault causes, optimal recovery strategies, and reliability risk assessment values ​​for the predicted region or power grid, includes: When a power outage event is detected in the operational information of the predicted area or power grid, the root cause of the fault can be quickly located and the optimal recovery strategy can be generated through real-time topology analysis based on the power outage event and a pre-built dynamic knowledge graph model. When no power outage events are found in the operational information of the predicted area or power grid, the reliability risk value of the line or area is predicted based on the historical power outage events, equipment operating conditions, and environmental data associated in the pre-built dynamic knowledge graph model.

11. The method as described in claim 10, characterized in that, When a power outage event is detected in the predicted area or power grid operation information, the system quickly locates the root cause of the fault and generates the optimal recovery strategy through real-time topology analysis based on the power outage event and a pre-built dynamic knowledge graph model, including: Based on the power outage event and a pre-built dynamic knowledge graph model, calculate a list of grid equipment and users affected by the power outage; Based on the relationships between events and objects in a pre-built dynamic knowledge graph model, the root cause of the failure is located and the optimal recovery strategy is generated.

12. A system for analyzing medium-voltage power outage events based on a full lifecycle data model, characterized in that, include: The information acquisition module is used to acquire operational information of the forecast area or power grid; The intelligent analysis module is used to input the operation information of the predicted area or power grid into a pre-built dynamic knowledge graph model to obtain one or more of the following: the cause of the fault in the predicted area or power grid, the optimal recovery strategy, and the reliability risk assessment value. The pre-built dynamic knowledge graph model is constructed using a method for constructing a full lifecycle data model of a medium-voltage power outage event as described in any one of claims 1-5.

13. The system as described in claim 12, characterized in that, The intelligent analysis module includes: The event analysis submodule is used to quickly locate the root cause of the fault and generate the optimal recovery strategy when a power outage event is detected in the operation information of the predicted area or power grid, based on the power outage event and a pre-built dynamic knowledge graph model through real-time topology analysis. The risk assessment submodule is used to predict the reliability risk value of a line or area based on historical power outage events, equipment operating conditions, and environmental data associated with a pre-built dynamic knowledge graph model when no power outage events are found in the operational information of the predicted area or power grid.

14. The system as described in claim 13, characterized in that, The event analysis submodule is specifically used for: Based on the power outage event and a pre-built dynamic knowledge graph model, calculate a list of grid equipment and users affected by the power outage; Based on the relationships between events and objects in a pre-built dynamic knowledge graph model, the root cause of the failure is located and the optimal recovery strategy is generated.

15. An electronic device, characterized in that, include: At least one processor and memory; The memory and processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, a method for constructing a full lifecycle data model of a medium-voltage power outage event as described in any one of claims 1 to 5 is implemented, or a method for analyzing a medium-voltage power outage event based on a full lifecycle data model as described in any one of claims 9 to 11 is implemented.

16. A readable storage medium, characterized in that, It contains an execution program, which, when executed, implements a method for constructing a full lifecycle data model of a medium-voltage power outage event as described in any one of claims 1 to 5, or a method for analyzing a medium-voltage power outage event based on a full lifecycle data model as described in any one of claims 9 to 11.

Images