Information-driven intelligent construction system and method for power grid operation status knowledge graph

Abstract

This invention discloses an information-driven intelligent construction system and method for a power grid operation status knowledge graph. The method includes: fusing acquired real-time power grid information to determine multi-source power grid data; extracting pre-defined power grid knowledge from the multi-source data to construct a network-based knowledge base model; extracting knowledge based on the network-based knowledge base model to determine the entities, relationships, and attributes of the power grid, and fusing these entities, relationships, and attributes to determine entity-knowledge-attribute triples; constructing a data-to-entity mapping algorithm using a data-driven approach, and updating the existing large power grid operation status knowledge graph based on the entity-knowledge-attribute triples to determine the updated knowledge graph of the power grid.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and more specifically, to an information-driven intelligent construction system and method for a knowledge graph of power grid operation status. Background Technology

[0002] With the development of the energy internet and new power systems, interconnected power grids are exhibiting increasingly complex cyber-physical integration and dynamic operating characteristics, posing significant challenges to their safe and economical operation and dispatch control. Currently, to improve the online safe and economical operation of large power grids, the State Grid Corporation of China has established a fully functional intelligent dispatch support system. Big data and artificial intelligence technologies are being further applied in the field of large power grid regulation, and an information-driven intelligent panoramic proactive safety defense and control system for large power grids is gradually being established. The core of this system is to deeply mine the spatiotemporal dynamic operating characteristics and evolution laws of the power grid based on its state information at different time scales, different operating scenarios, and related stability issues. It provides refined quantitative assessment indicators of stability status and adaptive optimization control strategies, and presents key value information in a simple, intuitive, and visual manner.

[0003] From the perspective of graph theory and complex networks, power grids have typical network attributes and graph structures. For core issues such as the dynamic operation characteristics, stability analysis and optimization control of large power grids, it is urgent to use advanced complex network theory, big data and artificial intelligence technologies to extract the real-time operation status and control strategies of the power grid into more valuable knowledge, and to combine it with the spatial physical distribution map of the power grid for simple, intuitive and vivid visualization. This will efficiently support dispatching and operation personnel to quickly, accurately and proactively grasp the overall operation status and control strategies of the power grid, and improve the real-time intelligent panoramic proactive security defense level of the large power grid.

[0004] Meanwhile, the knowledge graph concept and graph model knowledge representation proposed by Google in recent years have similarities with the physical network attributes and core business scenarios of the power grid itself. Knowledge graphs have many advantages in the power grid field. Currently, many scholars have carried out exploratory research and engineering practice on the application of knowledge graphs in the fields of power system regulation digitalization, assessment and decision-making, fault handling, distribution network topology identification, and power equipment health management, promoting the deep integration and innovative application of knowledge graphs in power grid business scenarios.

[0005] In summary, due to the increasingly complex cyber-physical integration and dynamic operation characteristics of power grids, and the continuous expansion of various business scenarios, there is a wide variety of power grid stability assessment indicators and optimization control strategies, resulting in severe fragmentation. The extraction and display of core value knowledge are somewhat inadequate, making it difficult to effectively address the complex operational patterns of large power grids and the application needs of dispatching and operation personnel in terms of timeliness, precision, and practicality. Knowledge graphs have begun new research and meaningful exploration in many power grid business scenarios, but their practical application in production is still in its early stages. Especially in the field of intelligent defense for online security and stability of large power grids, establishing a complete functional architecture and core technical solutions for the knowledge graph of large power grid operation status is of great value and significance for the construction of an information-driven intelligent panoramic proactive security defense and control system for large power grids. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides an information-driven intelligent construction system and method for a knowledge graph of power grid operation status.

[0007] According to one aspect of the present invention, an information-driven intelligent construction method for a power grid operation status knowledge graph is provided, comprising:

[0008] The obtained real-time power grid information is fused to determine the multi-source data of the power grid;

[0009] Pre-defined power grid knowledge is extracted from multi-source power grid data to construct a network-based knowledge base model;

[0010] Knowledge extraction is performed based on a network-based knowledge base model to determine the entities, relationships, and attributes of the power grid. Knowledge fusion is then performed on the entities, relationships, and attributes of the power grid to determine the entity-knowledge-attribute triples of the power grid.

[0011] A data-driven approach is used to construct a data-to-entity mapping algorithm. Based on the entity-knowledge-attribute triple, the existing knowledge graph of the power grid operation status is updated to determine the updated knowledge graph of the power grid.

[0012] Optionally, the multi-source data of the power grid includes: real-time measurement information of the power grid, power grid simulation information, and external environmental information, among which...

[0013] The real-time measurement information of the power grid includes status data of equipment at all levels, operating status indicators, control decision information, abnormal event alarms and historical sections collected by SCADA / PMU;

[0014] The power grid simulation information consists of static and transient scenario data obtained from BPA / PSASP simulations;

[0015] The external environmental information refers to the meteorological information outside the power grid.

[0016] Optionally, the operation of extracting pre-defined power grid knowledge from multi-source power grid data and constructing a network-based knowledge base model includes:

[0017] Pre-defined power grid knowledge is extracted from multi-source power grid data. Through intelligent analysis and feature association of the power grid knowledge, the core knowledge elements of the network-type knowledge base model are obtained. The core knowledge elements include equivalent models, evaluation indicators, stability domains, weak links, critical paths, prevention and control strategies, correlation relationships, and behavioral events.

[0018] By abstracting the core knowledge elements and mapping them to an entity-relationship-attribute organizational structure, a network-type knowledge base model is constructed.

[0019] Optionally, knowledge extraction based on a network-based knowledge base model is performed to determine the entities, relationships, and attributes of the power grid, including:

[0020] Based on the network-based knowledge base model, real physical entities and virtual digital entities are extracted to determine the entities of the power grid. Real physical entities include various basic physical facilities, while virtual digital entities include various equivalent virtual parameters, disturbance propagation models, and spatiotemporal correlation characteristics.

[0021] Based on a network-based knowledge base model, the topological connections and spatiotemporal relationships of the power grid are extracted to determine the relationships within the power grid.

[0022] Stability indicators and control strategies are extracted based on a network-based knowledge base model to determine the attributes of the power grid.

[0023] Optionally, knowledge fusion is performed on the entities, relationships, and attributes of the power grid to determine the operations of the entity-knowledge-attribute triple of the power grid, including:

[0024] By eliminating coreference and disambiguating entities, redundancy and ambiguity among entities, relations and attributes of the power grid are removed, and entity-knowledge-attribute triples are determined.

[0025] Optionally, after performing knowledge fusion on the entities, relationships, and attributes of the power grid to determine the entity-knowledge-attribute triple of the power grid, the operation includes:

[0026] Perform knowledge reasoning, quality assessment, and ontology extraction on the knowledge in the entity-knowledge-attribute triples to remove knowledge errors and conflicts in the entity-knowledge-attribute triples.

[0027] Optionally, it also includes:

[0028] Build a visual map engine to update the knowledge graph;

[0029] Based on the visualization map engine and various operating states of the power grid, a 3D scenario of the core business of the power grid is built.

[0030] According to another aspect of the present invention, an information-driven intelligent construction system for a power grid operation status knowledge graph is provided, comprising:

[0031] The first determining module is used to fuse the obtained real-time power grid information to determine the multi-source data of the power grid;

[0032] The first construction module is used to extract preset power grid knowledge from multi-source power grid data and construct a network-type knowledge base model.

[0033] The second determination module is used to extract knowledge based on the network-type knowledge base model, determine the entities, relationships and attributes of the power grid, and perform knowledge fusion on the entities, relationships and attributes of the power grid to determine the entity-knowledge-attribute triple of the power grid.

[0034] The third determination module is used to construct a data-to-entity mapping algorithm in a data-driven manner, update the existing large power grid operation status knowledge graph based on the entity-knowledge-attribute triple, and determine the updated knowledge graph of the power grid.

[0035] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the methods described in any of the above aspects of the present invention.

[0036] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the preceding aspects of the present invention.

[0037] Therefore, this application determines multi-source power grid data by fusing real-time power grid information, constructs a network-based knowledge base model using this multi-source data, extracts power grid entities, relationships, and attributes, and finally uses a data-driven approach to construct a data-to-entity mapping algorithm. Based on the entity-knowledge-attribute triples, it updates the existing large power grid operation status knowledge graph, thus determining the updated power grid knowledge graph. Addressing the problem of severe fragmentation of various types of power grid information, the system design provided by this invention enables efficient management and display of massive amounts of fragmented power grid data, improves the efficiency of mining and utilizing core power grid knowledge, and helps dispatching and operation personnel efficiently understand the power grid's operational status. Attached Figure Description

[0038] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures:

[0039] Figure 1This is a flowchart illustrating an exemplary embodiment of the present invention for a method of intelligently constructing an information-driven knowledge graph of power grid operation status.

[0040] Figure 2 This is a schematic diagram of an information-driven intelligent construction system for a knowledge graph of power grid operation status provided in an exemplary embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of an information-driven intelligent construction architecture for a knowledge graph of power grid operation status provided in an exemplary embodiment of the present invention;

[0042] Figure 4 This is a schematic diagram of the organizational structure of an information-driven knowledge graph of the operation status of a large power grid, provided in an exemplary embodiment of the present invention.

[0043] Figure 5 This is a schematic diagram of the structure of an information-driven intelligent construction system for a knowledge graph of power grid operation status provided in an exemplary embodiment of the present invention;

[0044] Figure 6 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. Detailed Implementation

[0045] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0046] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention.

[0047] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of the present invention are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0048] It should also be understood that in the embodiments of the present invention, "multiple" can refer to two or more, and "at least one" can refer to one, two or more.

[0049] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more unless explicitly defined or given contrary instructions in the context.

[0050] Furthermore, the term "and / or" in this invention is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this invention generally indicates that the preceding and following related objects have an "or" relationship.

[0051] It should also be understood that the description of the various embodiments in this invention emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0052] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0053] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0054] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0055] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0056] The embodiments of this invention can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Well-known examples of terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0057] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0058] Exemplary methods

[0059] Figure 1 This is a flowchart illustrating an exemplary embodiment of the present invention regarding an information-driven intelligent construction method for a power grid operation status knowledge graph. This embodiment can be applied to electronic devices, such as… Figure 1 As shown, the information-driven intelligent construction method 100 for power grid operation status knowledge graph includes the following steps:

[0060] Step 101: The obtained real-time power grid information is fused to determine the multi-source data of the power grid;

[0061] Step 102: Extract pre-defined power grid knowledge from multi-source power grid data and construct a network-based knowledge base model;

[0062] Step 103: Extract knowledge based on the network knowledge base model, determine the entities, relationships and attributes of the power grid, and perform knowledge fusion on the entities, relationships and attributes of the power grid to determine the entity-knowledge-attribute triple of the power grid.

[0063] Step 104: A data-driven approach is used to construct a data-to-entity mapping algorithm. Based on the entity-knowledge-attribute triple, the existing large power grid operation status knowledge graph is updated to determine the updated knowledge graph of the power grid.

[0064] Optionally, the multi-source data of the power grid includes: real-time measurement information of the power grid, power grid simulation information, and external environmental information, among which...

[0065] The real-time measurement information of the power grid includes status data of equipment at all levels, operating status indicators, control decision information, abnormal event alarms and historical sections collected by SCADA / PMU;

[0066] The power grid simulation information consists of static and transient scenario data obtained from BPA / PSASP simulations;

[0067] The external environmental information refers to the meteorological information outside the power grid.

[0068] Optionally, the operation of extracting pre-defined power grid knowledge from multi-source power grid data and constructing a network-based knowledge base model includes:

[0069] Pre-defined power grid knowledge is extracted from multi-source power grid data. Through intelligent analysis and feature association of the power grid knowledge, the core knowledge elements of the network-type knowledge base model are obtained. The core knowledge elements include equivalent models, evaluation indicators, stability domains, weak links, critical paths, prevention and control strategies, correlation relationships, and behavioral events.

[0070] By abstracting the core knowledge elements and mapping them to an entity-relationship-attribute organizational structure, a network-type knowledge base model is constructed.

[0071] Optionally, knowledge extraction based on a network-based knowledge base model is performed to determine the entities, relationships, and attributes of the power grid, including:

[0072] Based on the network-based knowledge base model, real physical entities and virtual digital entities are extracted to determine the entities of the power grid. Real physical entities include various basic physical facilities, while virtual digital entities include various equivalent virtual parameters, disturbance propagation models, and spatiotemporal correlation characteristics.

[0073] Based on a network-based knowledge base model, the topological connections and spatiotemporal relationships of the power grid are extracted to determine the relationships within the power grid.

[0074] Stability indicators and control strategies are extracted based on a network-based knowledge base model to determine the attributes of the power grid.

[0075] Optionally, knowledge fusion is performed on the entities, relationships, and attributes of the power grid to determine the operations of the entity-knowledge-attribute triple of the power grid, including:

[0076] By eliminating coreference and disambiguating entities, redundancy and ambiguity among entities, relations and attributes of the power grid are removed, and entity-knowledge-attribute triples are determined.

[0077] Optionally, after performing knowledge fusion on the entities, relationships, and attributes of the power grid to determine the entity-knowledge-attribute triple of the power grid, the operation includes:

[0078] Perform knowledge reasoning, quality assessment, and ontology extraction on the knowledge in the entity-knowledge-attribute triples to remove knowledge errors and conflicts in the entity-knowledge-attribute triples.

[0079] Optionally, it also includes:

[0080] Build a visual map engine to update the knowledge graph;

[0081] Based on the visualization map engine and various operating states of the power grid, a 3D scenario of the core business of the power grid is built.

[0082] Specifically, this invention provides an information-driven intelligent construction method for a knowledge graph of the operation status of a large power grid, the system functional architecture of which is as follows: Figure 2 As shown in the figure, this architecture is designed for intelligent scheduling scenarios. It relies on six functional modules: multi-source information fusion, spatiotemporal big data platform, situational graph engine, knowledge association reasoning, graph business application, and user-friendly human-computer interaction. It overlays business flow and information flow to achieve deep integration of "physical network + information system + knowledge graph", thereby realizing "one graph to know the whole situation" and "one graph to understand the whole state", and improving the real-time intelligent defense level of the power grid.

[0083] The information-driven intelligent construction system for the knowledge graph of the operation status of large power grids mainly includes 7 steps (such as...). Figure 3 As shown):

[0084] Step (1) Multi-source information fusion. Real-time power grid measurement information, simulation information, and external environmental information are obtained from the power grid dispatch automation system and various simulation tools. The real-time measurement information mainly includes the status data of equipment at all levels, operating status indicators, control decision information, abnormal event alarms, and historical sections collected by SCADA / PMU. The power grid simulation information mainly refers to the static and transient scene data obtained by simulations such as BPA / PSASP. The external environmental information mainly refers to meteorological information. The above multi-source information is fused by adaptive correction, gap filling, correlation, alignment, etc., and stored and managed according to structured data, semi-structured data, and unstructured data to provide a unified standard of basic data support for system construction.

[0085] Step (2) Knowledge Modeling. Extract the power grid knowledge required for model construction from the multi-source information formed in Step 1. Use intelligent analysis and feature association techniques to obtain the core knowledge elements for model construction, including: equivalent model, evaluation index, stability domain, weak link, critical path, prevention and control strategy, correlation, behavioral events, etc. Combined with the requirements of physical equipment entities, power grid control business and knowledge application attributes, the core knowledge elements are abstracted and mapped to the entity-relationship-attribute organizational structure to establish a network-type knowledge base model in the field of power grid control. Combined with the primary physical topology connection relationship of the power grid, graph database technology is used for unified storage and management to improve the analysis, calculation and query performance of the knowledge model.

[0086] Step (3) Knowledge Extraction. This mainly includes entity extraction, relation extraction, and attribute extraction of the power grid operation status knowledge graph. Entity extraction mainly involves the extraction of real physical entities and virtual digital entities. Physical entities include various basic physical facilities, such as generators and buses, while digital entities include various equivalent virtual parameters, disturbance propagation models, and spatiotemporal correlation characteristics. Relationship extraction is mainly based on measurement data to extract the topological connection relationship of the power grid, identify the main grid structure, and extract the interaction relationship between power grid equipment based on spatiotemporal correlation to support the wide-area optimization control, disturbance propagation prediction, and isolation of the grid. Attribute extraction, by integrating the results of various static / transient analysis and control algorithms, can obtain the stability status indicators and control strategies of equipment and the power grid, thereby enabling the value of equipment entities. When a fault occurs in the power grid, the transient stability can be quickly estimated based on the fault location, network structure, state trajectory, and other information, and then corresponding measures can be taken.

[0087] Step (4) Knowledge Fusion. To address the numerous differences in time, space, name, and attributes among multi-source data of the power grid, redundancy and ambiguity in the three core elements of the knowledge graph—entities, relations, and attributes—are removed through common reference resolution and entity disambiguation. This yields high-quality "entity-relationship-entity" core element triples, providing high-quality knowledge units for the power grid operation status knowledge graph.

[0088] Step (5) Knowledge Processing. To address erroneous knowledge generated during the knowledge extraction or fusion stage, knowledge reasoning, quality assessment, and ontology extraction are added before adding new knowledge to eliminate knowledge errors or conflicts. Quality assessment can be conducted through expert evaluation or by flexibly defining a quality assessment function based on business needs. By discarding knowledge with low credibility, the quality of the knowledge base is ensured.

[0089] Step (6) Knowledge Update. This mainly includes concept layer updates and data layer updates. A data-driven approach is used to construct a data-to-entity mapping algorithm, automatically updating the relationships between nodes and edges in the knowledge graph, as well as the associations between the power grid physical topology and the corresponding knowledge graph. Simultaneously, when a node changes, the relationships between it and other connected nodes will also change accordingly. Therefore, consistency issues need to be considered when updating knowledge.

[0090] Step (7) System Visualization. First, using visualization technologies such as geographic information technology, a knowledge graph visualization map engine is constructed. Then, for various operating states of the power grid, a three-dimensional scene of the core business of the power grid is built. At the same time, through high-dimensional data visualization methods, key information such as real-time evaluation of the power grid operating status, anomaly analysis, risk warning, control strategy, and historical traceability are mapped and displayed in layers. In order to improve the efficiency of real-time graphic update and rendering, multi-threaded computing and streaming rendering technology can be used to construct a knowledge graph visualization engine to comprehensively display the knowledge graph of the power grid operating status.

[0091] To more clearly illustrate the practical solution of the present invention, a detailed case description is provided using a regional power grid as an example:

[0092] (1) The system uses Hadoop core components to build a big data environment. The cluster is mainly divided into two categories of roles: management server (Master) and storage server (Salve). The table below shows the main configuration of the experimental platform server.

[0093]

[0094] (2) At the physical level, the power grid in this region includes 188 major substations (220kV and above), 688 key lines, and 158 important loads. Based on real-time steady-state information from the intelligent dispatch system, wide-area dynamic measurement information, and simulation results, the system, through the intelligent construction system design of the power grid operation status knowledge graph proposed in this invention, integrates, calculates, and analyzes various types of power grid knowledge. This yields the results of stability status assessment, optimized control decisions, and comprehensive status characterization of the power grid under different scenarios, which are then visualized.

[0095] (3) The system adopts information-driven and dynamic coloring technology to intuitively display important information such as key equipment, indicators, paths and strategies in the primary wiring diagram. The top of the interface provides comprehensive evaluation indicators that reflect the overall operation status of the power grid, which can intuitively express the current stability status and margin of the power grid. The left and right sides of the interface provide core value information of the current operation status of the power grid, such as power grid stability indicator curves, stability domains, optimization strategy tables, and equivalent parameter identification, according to the actual operating conditions of the power grid.

[0096] (4) When a power grid fault occurs, the information extraction module extracts key information such as the fault occurrence time, fault type, and fault location. This information is then matched against a standard word description library in the knowledge fusion module to generate standardized descriptive terms. Finally, the fault information is associated with measurement and topology information via the device ID to achieve knowledge fusion. Knowledge reasoning technology is then used to determine the correctness of the basic logic of the fused knowledge graph. For example... Figure 4As shown, in this scenario, the knowledge graph can be used to determine that a three-phase short circuit occurred on a certain day in January 2022, with the fault lasting for 0.3 seconds. The calculated evaluation index is 0.72. The relevant information is pushed to the graph display module and stored using graph database technology to help the dispatcher quickly understand the impact of the fault.

[0097] (5) After receiving a fault warning, the system can automatically switch scenes and use visualization technologies such as a GIS engine to intuitively display core knowledge graph elements such as disturbance events, locations, attributes, evaluation indicators, control strategies, and critical paths. From the fault information overview, it can be seen intuitively that a three-phase short-circuit fault has occurred at a power grid substation. Combined with the power grid time-series measurement data, the degree of disturbance to the power grid equipment is analyzed, and the scope of the fault impact is intuitively displayed in the form of a shock wave, helping dispatchers to quickly understand the fault situation and take timely control strategies.

[0098] In summary, this application mainly includes the following points: (1) The system construction scheme provided by this invention mainly achieves "one map to know the whole situation" and "one map to know the whole state" in three aspects: power grid stability assessment, optimized control decision and comprehensive situation representation. It provides simple, intuitive, effective and reliable reference information for power grid dispatching and operation personnel and intelligent dispatching system, and supports the construction of a smart panoramic active security defense system for large power grids. (2) The construction scheme provided by this invention mainly includes seven key steps: multi-source information fusion, knowledge modeling, knowledge extraction, knowledge fusion, knowledge processing, knowledge updating and visualization. The steps are closely linked to each other and jointly realize the construction of the power grid operation status knowledge graph. (3) The system interface provided by this invention adopts the concept of intelligent dispatching cockpit. The power grid analysis mode analysis adopts "trajectory + event" driven to realize real-time intelligent monitoring and safety early warning of the power grid. It also utilizes the concise, efficient and intuitive "graph language" characteristics of knowledge graphs, combined with visualization technology, to intuitively display the core knowledge elements, so that dispatchers can grasp the dynamic operation characteristics of the power grid in real time and intuitively understand the power grid security and stability status and spatiotemporal distribution characteristics.

[0099] The technical effects of this application are as follows: (1) This invention addresses the core business issues of online security defense and intelligent dispatching of large power grids by introducing knowledge graph technology. From the perspective of deep integration of "physical system + information system + knowledge graph", it proposes and establishes a knowledge graph of the operation status of large power grids under the information-driven mode to guide the operation of power grid regulation. (2) This invention is aimed at dispatching and operating personnel. In response to the problem of severe fragmentation of various types of information in the power grid, the system design scheme provided by this invention can realize the efficient management and display of massive fragmented data of the power grid, improve the efficiency of mining and utilizing core knowledge of the power grid, and help dispatching and operating personnel to efficiently understand the operation status of the power grid. (3) The scheme design proposed in this invention can map the core value information of the power grid to the primary physical network system in parallel at the three levels of power grid stability assessment, optimized control decision-making and comprehensive situation representation, so as to realize "one map to know the whole situation" and "one map to know the whole state", providing simple, intuitive, effective and reliable reference information for power grid dispatching and operating personnel and intelligent dispatching systems, and supporting the construction of a smart panoramic active security defense system for large power grids.

[0100] Exemplary device

[0101] Figure 5 This is a schematic diagram of the structure of an information-driven intelligent construction system for a knowledge graph of power grid operation status provided in an exemplary embodiment of the present invention. Figure 5 As shown, the device 500 includes:

[0102] The first determining module 510 is used to fuse the obtained real-time power grid information to determine the multi-source data of the power grid;

[0103] The first construction module 520 is used to extract preset power grid knowledge from multi-source power grid data and construct a network-type knowledge base model.

[0104] The second determination module 530 is used to extract knowledge based on the network-type knowledge base model, determine the entities, relationships and attributes of the power grid, and perform knowledge fusion on the entities, relationships and attributes of the power grid to determine the entity-knowledge-attribute triple of the power grid.

[0105] The third determination module 540 is used to construct a data-to-entity mapping algorithm in a data-driven manner, update the existing large power grid operation status knowledge graph based on the entity-knowledge-attribute triple, and determine the updated knowledge graph of the power grid.

[0106] Optionally, the multi-source data of the power grid includes: real-time measurement information of the power grid, power grid simulation information, and external environmental information, among which...

[0107] The real-time measurement information of the power grid includes status data of equipment at all levels, operating status indicators, control decision information, abnormal event alarms and historical sections collected by SCADA / PMU;

[0108] The power grid simulation information consists of static and transient scenario data obtained from BPA / PSASP simulations;

[0109] The external environmental information refers to the meteorological information outside the power grid.

[0110] Optionally, the first building module 520 includes:

[0111] The acquisition submodule is used to extract preset power grid knowledge from multi-source power grid data, and to obtain the core knowledge elements of the network knowledge base model through intelligent analysis and feature association of the power grid knowledge. The core knowledge elements include equivalent model, evaluation index, stability domain, weak link, critical path, prevention and control strategy, correlation relationship, and behavioral event.

[0112] The sub-modules are used to abstract the core knowledge elements into an entity-relationship-attribute organizational structure to build a network-type knowledge base model.

[0113] Optionally, the second determining module 530 includes:

[0114] The first determination submodule is used to extract real physical entities and virtual digital entities based on the network-type knowledge base model to determine the entities of the power grid. The real physical entities include various basic physical facilities, and the virtual digital entities include various equivalent virtual parameters, disturbance propagation models, and spatiotemporal correlation characteristics.

[0115] The second determination submodule is used to extract the power grid topology connection relationship and spatiotemporal correlation relationship based on the network-type knowledge base model, and determine the relationship of the power grid.

[0116] The third determination submodule is used to extract stability indicators and control strategies based on the network-based knowledge base model to determine the attributes of the power grid.

[0117] Optionally, the second determining module 530 includes:

[0118] The fourth determination submodule is used to remove redundancy and ambiguity between entities, relations and attributes of the power grid through coreference resolution and entity disambiguation, and to determine entity-knowledge-attribute triples.

[0119] Optionally, after performing knowledge fusion on the entities, relationships, and attributes of the power grid to determine the entity-knowledge-attribute triple of the power grid, the device 500 includes:

[0120] The removal module is used to perform knowledge reasoning, quality assessment, and ontology extraction on the knowledge in the entity-knowledge-attribute triples, and to remove knowledge errors and conflicts in the entity-knowledge-attribute triples.

[0121] Optionally, the device 500 also includes:

[0122] The second building module is used to build a visual map engine for updating the knowledge graph;

[0123] The module is used to build 3D scenes of the power grid's core business based on the visualization map engine and various operating states of the power grid.

[0124] Exemplary electronic devices

[0125] Figure 6 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. For example... Figure 6 As shown, the electronic device 60 includes one or more processors 61 and a memory 62.

[0126] The processor 61 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0127] The memory 62 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 61 may execute the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above, and / or other desired functions. In one example, the electronic device may also include an input device 63 and an output device 64, these components being interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0128] In addition, the input device 63 may also include, for example, a keyboard, a mouse, etc.

[0129] The output device 64 can output various information to the outside. The output device 64 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0130] Of course, for the sake of simplicity, Figure 6 Only some of the components of the electronic device relevant to the present invention are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0131] Exemplary computer program products and computer-readable storage media

[0132] In addition to the methods and apparatus described above, embodiments of the present invention may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0133] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0134] Furthermore, embodiments of the present invention may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the methods for information mining of historical change records according to various embodiments of the present invention as described in the "Exemplary Methods" section above.

[0135] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0136] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0137] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0138] The block diagrams of devices, systems, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, systems, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0139] The methods and systems of the present invention may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of the present invention are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present invention may also be implemented as a program recorded on a recording medium, the program comprising machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers recording media storing programs for performing the methods according to the present invention.

[0140] It should also be noted that in the systems, apparatus, and methods of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered equivalents of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0141] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. An information-driven power grid operation situation knowledge graph intelligent construction method, characterized in that, The method comprises the following steps: fusing obtained real-time power grid information to determine power grid multi-source data; extracting preset power grid knowledge from the power grid multi-source data to construct a network-type knowledge base model; performing knowledge extraction according to the network-type knowledge base model to determine entities, relationships and attributes of the power grid, and performing knowledge fusion on the entities, relationships and attributes of the power grid to determine entity-knowledge-attribute triples of the power grid; constructing a data-to-entity mapping algorithm in a data-driven manner, updating an existing large power grid operation situation knowledge graph according to the entity-knowledge-attribute triples to determine an updated knowledge graph of the power grid; the operation of extracting preset power grid knowledge from the power grid multi-source data to construct a network-type knowledge base model comprises: extracting preset power grid knowledge from the power grid multi-source data, and obtaining core knowledge elements of the network-type knowledge base model through intelligent analysis and feature association of the power grid knowledge, wherein the core knowledge elements include equivalent models, evaluation indexes, stable domains, weak links, critical paths, control strategies, correlation relationships and behavior events; abstracting the core knowledge elements into an organization structure of entities-relationships-attributes to construct the network-type knowledge base model.

2. The method of claim 1, wherein, The power grid multi-source data comprises power grid real-time measurement information, power grid simulation information and external environment information, wherein the power grid real-time measurement information is state data, operation state indexes, control decision information, abnormal event alarms and historical cross-sections collected by SCADA / PMU at all levels of equipment; the power grid simulation information is static and transient scenario data obtained by BPA / PSASP simulation; the external environment information is meteorological information of the external environment of the power grid.

3. The method of claim 1, wherein, The operation of performing knowledge extraction according to the network-type knowledge base model to determine entities, relationships and attributes of the power grid comprises: performing extraction of real physical entities and virtual digital entities according to the network-type knowledge base model to determine entities of the power grid, wherein the real physical entities include various types of basic physical facilities, and the virtual digital entities include various types of equivalent virtual parameters, disturbance propagation models and time-space correlation characteristics; performing extraction of power grid topology connection relationships and time-space correlation relationships according to the network-type knowledge base model to determine relationships of the power grid; performing extraction of stable situation indexes and control strategies according to the network-type knowledge base model to determine attributes of the power grid.

4. The method of claim 1, wherein, The operation of performing knowledge fusion on the entities, relationships and attributes of the power grid to determine entity-knowledge-attribute triples of the power grid comprises: removing redundancies and ambiguities among the entities, relationships and attributes of the power grid through co-reference resolution and entity disambiguation to determine the entity-knowledge-attribute triples.

5. The method of claim 1, wherein, After the operation of performing knowledge fusion on the entities, relationships and attributes of the power grid to determine entity-knowledge-attribute triples of the power grid, the following operation is performed: performing knowledge reasoning, quality evaluation and ontology extraction on the knowledge in the entity-knowledge-attribute triples to remove knowledge errors and conflicts in the entity-knowledge-attribute triples.

6. The method of claim 1, wherein, The method further comprises the following steps: constructing a visual map engine of the updated knowledge graph; According to the visual map engine and the various operating states of the power grid, a core business three-dimensional scene of the power grid is built.

7. An information-driven power grid operation situation knowledge graph intelligent construction system, characterized in that, Comprise: A first determination module for fusing obtained real-time power grid information to determine power grid multi-source data; A first construction module for extracting preset power grid knowledge from the power grid multi-source data to construct a network-type knowledge base model; A second determination module for knowledge extraction according to the network-type knowledge base model to determine the entities, relationships and attributes of the power grid, and to perform knowledge fusion on the entities, relationships and attributes of the power grid to determine the entity-knowledge-attribute triple of the power grid; A third determination module for constructing a data-to-entity mapping algorithm in a data-driven manner, updating an existing large power grid operation situation knowledge graph according to the entity-knowledge-attribute triple, and determining an updated knowledge graph of the power grid; The first construction module comprises: Extracting preset power grid knowledge from the power grid multi-source data, and obtaining core knowledge elements of the network-type knowledge base model by intelligently analyzing and feature correlating the power grid knowledge, wherein the core knowledge elements include equivalent models, evaluation indexes, stable domains, weak links, critical paths, control strategies, correlation relationships, and behavior events; According to the core knowledge elements, the corresponding organization structure of entity-relationship-attribute is abstracted to construct the network-type knowledge base model.

8. The system of claim 7, wherein, The power grid multi-source data includes power grid real-time measurement information, power grid simulation information, and external environment information, wherein The power grid real-time measurement information is state data, operating state indexes, control decision information, abnormal event alarms, and historical cross-sections collected by SCADA / PMU at all levels of equipment; The power grid simulation information is static and transient scenario data obtained from BPA / PSASP simulation; The external environment information is meteorological information outside the power grid.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which is used to execute the method of any one of claims 1-6.

10. An electronic device, comprising: The electronic device comprises: A processor; A memory for storing executable instructions of the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of any one of claims 1-6.

Images