Power grid regulation and control integrated training auxiliary method, system, equipment and medium

Abstract

The invention relates to the technical field of power system training, in particular to a power grid regulation and control integrated training auxiliary method, system and device and a medium, and the method comprises the steps: obtaining first data under an extreme working condition, and constructing a basic database based on the first data; constructing a power grid regulation and control knowledge graph including substation positions, working condition types, risk levels, data monitoring and fault coping strategy entity nodes based on the basic database, and storing the power grid regulation and control knowledge graph in a graph database; and in response to an input target working condition type and a target substation, retrieving a matched target regulation and control strategy based on the power grid regulation and control knowledge graph, and visually displaying the target regulation and control strategy. Through knowledge graph driving, dynamic closed-loop optimization and multi-dimensional data fusion, the core problems of insufficient cross-function collaboration, poor real-time performance, knowledge updating lagging and the like in traditional power grid regulation and control training are solved, and an efficient and intelligent training and decision support tool is provided for safe operation of a power grid under extreme working conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of power system training, and in particular to an auxiliary method, system, equipment and medium for integrated training of power grid regulation. Background Art

[0002] With the rapid development of smart grids and the deepening implementation of integrated control models, power grid operations and management are gradually transforming towards an intensive and intelligent approach. Currently, the training system for controllers has transitioned from specialized training focused on a single function to comprehensive training encompassing multiple functions. Several technical approaches are being used to enhance controllers' professional capabilities. However, with the frequent occurrence of extreme operating conditions, the complexity of accidents faced by power grids has significantly increased, and traditional training methods are gradually exposing their limitations in addressing sudden, multi-factor coupled extreme scenarios.

[0003] Under extreme operating conditions, the existing training system has the following prominent problems: First, controllers lack cross-functional collaborative training, making it difficult to quickly integrate information from multiple links such as dispatching, monitoring, and operations and maintenance, resulting in inefficient decision-making. Second, traditional risk assessments and emergency response plans rely on static historical data, making it difficult to dynamically adapt to real-time changes in extreme operating conditions, resulting in insufficient accuracy and timeliness of operational recommendations. Third, the existing training system cannot effectively record and analyze controller operational feedback, resulting in delayed knowledge base updates and difficulty in forming a closed-loop optimization mechanism. These issues directly impact the reliability and safety of power grid control under extreme operating conditions. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] In a first aspect, the present invention provides a training assistance method for integrated power grid control, comprising obtaining first data under extreme working conditions and constructing a basic database based on the first data;

[0006] Based on the basic database, a power grid control knowledge graph is constructed, which includes entity nodes such as substation location, operating condition type, risk level, data monitoring, and fault response strategy, and the knowledge graph is stored in the graph database.

[0007] In response to the input target operating condition type and target substation, the matching target control strategy is retrieved based on the power grid control knowledge graph, and the target control strategy is visualized.

[0008] As a preferred solution of the integrated training auxiliary method for power grid control of the present invention, the method further comprises calculating a comprehensive satisfaction index based on satisfaction feedback on the target control strategy;

[0009] When the comprehensive satisfaction index is lower than the preset threshold, the basic database and power grid regulation knowledge graph are updated.

[0010] As a preferred solution of the power grid control integrated training auxiliary method of the present invention, wherein: constructing a basic database based on the first data includes:

[0011] Use digital processing technology to convert the first data under extreme working conditions into text files that are easy to retrieve;

[0012] A basic database is constructed based on text files and real-time collected operating status data of power grid equipment.

[0013] As a preferred solution of the integrated training auxiliary method for power grid control of the present invention, the calculation of the comprehensive satisfaction index includes:

[0014] Obtain the controller's subjective evaluation score;

[0015] Calculate the correctness of the operation, which is determined based on the number of deviations between the controller's operation and the grid control knowledge graph recommendations;

[0016] Calculate training effectiveness gains based on a comparison of the controller's actual operation time and the optimal time recommended by the grid control knowledge graph;

[0017] Generate a comprehensive satisfaction index based on qualitative indicators, operation accuracy and training effectiveness gain.

[0018] As a preferred solution of the integrated training auxiliary method for power grid control of the present invention, the target control strategy visualization includes:

[0019] Locate the geographical location of the target substation through the area selection interface;

[0020] Dynamically annotate the grid control knowledge graph with recommended operational suggestions through the substation SVG control diagram.

[0021] As a preferred solution of the integrated training auxiliary method for power grid control of the present invention, wherein: the operating condition types include extreme weather, natural disasters and emergencies;

[0022] Risk levels include low, medium, and high and are associated with action recommendations;

[0023] Data monitoring includes real-time monitoring of current, voltage and frequency parameters;

[0024] Fault response strategies include corresponding strategies for fault type and location, dispatch coordination strategies, and grid configuration adjustment strategies.

[0025] As a preferred solution of the integrated training auxiliary method for power grid control of the present invention, the comprehensive satisfaction index is obtained by weighting the qualitative index, the operation accuracy and the training effectiveness gain.

[0026] In a second aspect, the present invention provides an integrated training assistance system for power grid control, comprising: a first construction module for acquiring first data under extreme working conditions and constructing a basic database based on the first data;

[0027] The second construction module is used to build a power grid control knowledge graph containing entity nodes such as substation location, operating condition type, risk level, data monitoring, and fault response strategy based on the basic database, and store the power grid control knowledge graph in the graph database;

[0028] The matching display module is used to respond to the input target operating condition type and target substation, retrieve the matching target control strategy based on the power grid control knowledge graph, and visualize the target control strategy.

[0029] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0030] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when the computer program is executed by a processor.

[0031] Compared with the existing technology, the beneficial effects of the present invention are: constructing a basic database containing normative data and operating data, integrating the standard operating procedures, power dispatching procedures and real-time operating status data of power grid operation, providing comprehensive, accurate and dynamically updated data support for training, and ensuring that the training content is closely aligned with actual operating needs; and by constructing a power grid control knowledge graph, presenting various complex knowledge of power grid operation in a structured form, realizing systematic integration and efficient retrieval of knowledge, especially when facing specific (extreme) working conditions, it can quickly and accurately retrieve matching control strategies, and intuitively present them to controllers through visual display, effectively improving the pertinence and practicality of training, and improving the decision-making efficiency and accuracy of controllers under complex working conditions; further, by introducing a satisfaction feedback mechanism, it can ensure that the training system is continuously optimized and improved according to actual usage, so that the training content always meets the ever-changing operating requirements and extreme working conditions under the integrated power grid control mode. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1A schematic diagram of the process of an integrated training auxiliary method for power grid control Figure 1 .

[0034] Figure 2 A schematic diagram of the process of an integrated training auxiliary method for power grid control Figure 2 .

[0035] Figure 3 Schematic diagram of the framework structure of the power grid control knowledge graph.

[0036] Figure 4 Schematic diagram of the knowledge graph of power grid regulation under extreme working conditions.

[0037] Figure 5 It is the location of the computer interface area.

[0038] Figure 6 It is the substation location in a certain area of ​​the computer interface.

[0039] Figure 7 This is the SVG control diagram of a substation. DETAILED DESCRIPTION

[0040] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0041] Example 1, with reference to Figure 1 , which is the first embodiment of the present invention, provides a power grid control integrated training auxiliary method, comprising:

[0042] S100: Acquire first data under extreme working conditions, and build a basic database based on the first data;

[0043] S200: Build a power grid control knowledge graph based on the basic database, including entity nodes of substation location, operating condition type, risk level, data monitoring, and fault response strategy, and store the power grid control knowledge graph in the graph database;

[0044] S300: In response to the input target operating condition type and target substation, a matching target regulation strategy is retrieved based on the power grid regulation knowledge graph, and the target regulation strategy is visualized and displayed.

[0045] It should be noted that the integrated power grid control model faces complex and ever-changing operating conditions, especially under extreme conditions, which places extremely high demands on controllers' decision-making capabilities and response speed. Traditional training methods struggle to provide comprehensive and real-time decision-making support, resulting in suboptimal training results and a failure to meet actual work needs.

[0046] Therefore, to address the current problem of suboptimal training for controllers and their inability to meet actual work needs, a basic database is constructed through steps S100-S300 based on first-hand data under extreme operating conditions, ensuring that the training content is both compliant with standards and reflects reality. A knowledge graph for power grid control is further constructed, integrating scattered data into a structured knowledge system, which is stored in a graph database for efficient retrieval. Once specific operating conditions and substation information are input, the system can quickly match and display corresponding control strategies based on the power grid control knowledge graph, providing controllers with precise decision-making assistance, improving the practicality and pertinence of training, and enhancing their ability to cope with complex power grid conditions.

[0047] Example 2, reference Figures 2 to 7 , which is an embodiment of the present invention, provides an integrated training assistance method for power grid control based on the above embodiment.

[0048] In the embodiment of the present application, building a basic database based on the first data in step S100 includes the following steps A1-A2:

[0049] A1: Use digital processing technology to convert the first data under extreme working conditions into a text file that is easy to search. The first data includes regulatory data, including but not limited to the "State Grid Corporation of China Electric Power Safety Work Regulations (Substation Section)", "DL / T 741-2019 Overhead Transmission Line Operation Regulations", and "State Grid Corporation of China Rain, Snow and Ice Disaster Emergency Plan";

[0050] A2: A basic database is constructed based on the text file and the operating status data of the power grid equipment collected in real time, wherein the operating status data of the power grid equipment includes data such as voltage, current or frequency.

[0051] In an optional embodiment, the first data may be converted into a text file that is easy for computer retrieval by using scanning combined with OCR recognition technology;

[0052] In another optional embodiment, the first data may be manually input word for word into a computer to generate a text file that is easy to retrieve.

[0053] It should be noted that the operating status data of power grid equipment under extreme working conditions collected in real time are dynamically updated to the basic database.

[0054] In the embodiment of the present application, in step S200, a power grid control knowledge graph including entity nodes of substation location, operating condition type, risk level, data monitoring, and fault response strategy is constructed based on the basic database. The substation location refers to the location of the target substation that the controller needs to control when facing extreme operating conditions.

[0055] It should be noted that when a fault occurs, the color of the line in the substation SVG control diagram will turn red, so that the substation location can be determined.

[0056] In an optional embodiment, the construction of the power grid control knowledge graph can be carried out by pre-processing the data in the basic database using automated scripts to ensure the consistency and accuracy of the data. Then, natural language processing (NLP) technology is applied to automatically identify entities in the text, such as substation location, operating condition type, risk level, etc., and these entities are mapped to nodes of the knowledge graph. Then, a machine learning model is used to extract the relationships between entities from the text, and these relationships are represented in the form of edges in the knowledge graph. Furthermore, a knowledge graph construction tool (such as Neo4j, Apache Jena, etc.) is used to automatically construct a knowledge graph based on the extracted entities and relationships.

[0057] In another optional embodiment, the power grid regulation knowledge graph can also be constructed by inviting experts to manually input entity nodes and relationships based on their knowledge and experience, and manually constructing the graph using knowledge graph software, and finally presenting the integrated data in a graphical manner.

[0058] Furthermore, the types of working conditions include extreme weather, natural disasters and emergencies;

[0059] It is understandable that extreme weather includes blizzards, thunderstorms, strong winds, etc., natural disasters include earthquakes, mudslides, typhoons, etc., and emergencies include line damage, equipment damage, overload operation, etc.

[0060] Furthermore, the risk level includes three levels: low, medium, and high and is associated with action recommendations;

[0061] It should be noted that the risk level is divided according to the duration of the fault. Specifically, low level: short-term controllable, the fault can be automatically recovered within 30 minutes; medium level: continuous deterioration, no recovery for more than 1 hour, and manual intervention is required; high level: irreversible loss; permanent damage to the equipment or system instability time exceeds 2 hours.

[0062] It should be further explained that the operational suggestions are derived from the operational suggestions included in the basic database. Further operational suggestions include four parts: coordinated scheduling, adjustment of grid configuration, power restriction sequence and fault elimination plan.

[0063] For example, first, assuming it is windy and snowy weather, first: the severity level is low (short-term controllable), the controller monitors real-time data: line ice thickness (<10mm), main transformer load rate (<95%), equipment temperature is within the limit, weather forecast: wind and snow intensity weakens and stops within 30 minutes.

[0064] Specific operation steps: 1. Automatic ice melting (initiate DC ice melting for 35kV lines, set the current to 1.1 times the rated value, and last for 15 minutes); 2. Load optimization (transfer the overloaded load of a substation to the standby main transformer through the bus tie switch); 3. Equipment maintenance (remotely activate the electric heating of the circuit breaker mechanism box); 4. Operation and maintenance personnel are on standby but not physically present, and only monitor through video surveillance and online device inspections.

[0065] 2. The severity level is medium (continuously worsening). The controller monitors real-time data: line ice thickness (>15mm), main transformer load factor (>100%), and high equipment temperature. The weather forecast shows that the wind and snow intensity continues to increase, and the radar shows that the snow clouds are stagnant. Specific operation steps: 1. Manual ice melting (Operation and maintenance personnel carry mechanical de-icing tools to the site to knock on the wires. Simultaneously activate multiple line ice melting devices) 2. Emergency load shedding (cut off 30% of non-critical loads according to the plan, giving priority to ensuring power supply to hospitals and communication base stations) 3. Equipment isolation (emergency power outage of 220kV lines that are severely iced and continuously discharged, dedicated to load) 4. Emergency preparation (activate mobile emergency power supply and coordinate with fire and transportation departments to clear snow on roads outside the station to ensure unobstructed repair channels).

[0066] Furthermore, data monitoring includes real-time monitoring of current, voltage and frequency parameters;

[0067] It is understandable that data monitoring is used to reflect the real-time current, voltage, frequency and other parameters of the substation and its subordinate areas, and to evaluate the system operation status.

[0068] It is understandable that when data monitoring detects an abnormality in the substation, the line on the substation SVG will turn red. When the fault is resolved, the red line on the SVG diagram will return to its original color.

[0069] Furthermore, the fault response strategy includes corresponding strategies for fault type and location, dispatch coordination strategies, and grid configuration adjustment strategies.

[0070] It is understandable that the purpose of applying the dispatching coordination strategy is to collaborate with upstream and downstream dispatching centers and related power stations, inform the situation and coordinate response measures, and dispatch other power stations or equipment to compensate for the power supply in the affected areas according to dispatching instructions; the grid configuration adjustment strategy refers to adjusting the power supply path by switching the distribution network switches according to specific circumstances to ensure stable power supply to users. When necessary, the substation can be segmented to reduce the scope of impact.

[0071] It should be noted that the strategies for coordinated dispatch and adjustment of grid configuration under extreme working conditions all come from the basic database.

[0072] In the embodiment of the present application, in step S300, in response to the input target operating condition type and target substation, a matching target control strategy is retrieved based on the power grid control knowledge graph, and the target control strategy is visually displayed, including the following steps B1-B2:

[0073] B1: Locate the geographical location of the target substation through the area selection interface;

[0074] In an optional embodiment, the geographic location of the substation can be integrated with the map service by creating an interactive map interface. The user can select or search for a specific area through the map interface, and the system automatically locates and highlights the substations in the area.

[0075] In another optional embodiment, a drop-down menu or list box containing a list of all substations can be created. The user can select the target substation from the drop-down menu, or browse and select through the list box. After selection, the system processes and locates the geographical location of the selected substation in the background.

[0076] B2: Dynamically annotate the grid control knowledge graph with recommended operational suggestions through the substation SVG control diagram.

[0077] In an optional embodiment, a control diagram of a substation is created by using scalable vector graphics technology, and corresponding operation suggestions are dynamically marked on the SVG diagram according to the operation steps recommended by the knowledge graph.

[0078] In another optional embodiment, the physical model of the substation can be combined with virtual operation suggestions by utilizing augmented reality technology. The user views the substation model through an AR device (such as AR glasses or a smartphone), and the system annotates and displays the operation suggestions on the model in real time.

[0079] In the implementation manner of the present application, step S400 is also included: based on the satisfaction feedback on the target control strategy, a comprehensive satisfaction index is calculated; when the comprehensive satisfaction index is lower than a preset threshold, the basic database and the power grid control knowledge graph are updated.

[0080] Regarding the calculation of the comprehensive satisfaction index in step S400, the following steps C1-C4 are included:

[0081] C1: Obtain the controller's subjective evaluation score;

[0082] It is understandable that the subjective evaluation score S subThe evaluation is divided into five levels, with corresponding scores as follows: very satisfied (5 points), satisfied (4 points), average (3 points), dissatisfied (2 points), and very dissatisfied (1 point). The controller determines the subjective evaluation score based on their own actual situation.

[0083] C2: Calculate the operation accuracy rate, which is determined based on the number of deviations between the controller's operation and the grid control knowledge graph's recommendations. The operation accuracy rate is used to indicate whether the recommendations given by the knowledge graph in response to the nth operating condition are detailed and easy for the controller to understand.

[0084] The specific operation accuracy (A n ) is calculated as follows:

[0085]

[0086] Where: E n is the number of deviations between the actual operation and the recommended operation of the controller under the nth working condition; R n The total number of recommended operations in the knowledge graph under n working conditions.

[0087] For example, suppose that in a certain power grid control training, for the nth working condition (assuming that "a sudden thunderstorm occurs in area A, and a substation has an overload risk"), the knowledge graph gives the total number of recommended operations R n = 5 items, including checking the status of substation equipment, adjusting regional power supply load distribution, starting backup lines, notifying operation and maintenance personnel for on-site inspection, and modifying subsequent power supply plans. After the actual operation, the controller compared it with the recommended operation and found that there were E n =1 deviation (e.g. failure to modify the subsequent power supply plan in a timely manner).

[0088] Calculated according to the formula:

[0089] This means that when dealing with the nth operating condition, the recommended operations given by the knowledge graph are relatively detailed, and the controllers understand and execute most of the key operations. However, there is still room for improvement. Failure to modify the power supply plan may affect the subsequent stable recovery of the power grid. By calculating the accuracy of this operation, the practicality of the knowledge graph suggestions and the accuracy of the controllers' operations can be clarified, providing a basis for the subsequent optimization of training content and knowledge graphs.

[0090] C3: Calculates training effectiveness gain based on a comparison of the controller's actual operation time with the optimal time recommended by the grid control knowledge graph. Training effectiveness gain measures the improvement in the results achieved by the dispatcher based on personal experience or innovative methods compared to the preset results in the knowledge graph.

[0091] The specific calculation formula is as follows:

[0092]

[0093] Where r is the operation success identifier, which is used to indicate whether the final result is correct or not.

[0094]

[0095] Where: T2 is the time taken by the controller to operate based on his own experience, T1 is the optimal operation time under the nth working condition in the knowledge graph; Teg n is the training efficiency gain under the nth working condition. If the controller's final result is wrong, the training efficiency gain is 0. On the premise that the final operation result is correct, the shorter the time the controller takes to operate based on his own experience, the greater the training efficiency gain, indicating that the operation suggestion recommended by the knowledge graph under this working condition is not optimal.

[0096] For example, assume that under a certain power grid operating condition (such as "a sudden failure of a substation in a certain area requires urgent adjustment of the power supply path"):

[0097] The optimal operation time T1 preset in the knowledge graph is 10 minutes;

[0098] The time T2 taken by the controller to complete the operation based on personal experience is 8 minutes;

[0099] Finally, the final operation result is correct, so the operation success identifier r=1.

[0100] Calculated according to the formula:

[0101] This shows that the controller spent 20% less time than the optimal time recommended by the knowledge graph while ensuring correct operation, indicating that his personal experience or method is more efficient under this working condition, which reflects that the operation suggestions recommended by the knowledge graph for this working condition may not be optimal and there is room for further optimization.

[0102] C4: Based on qualitative indicators, operation accuracy and training efficiency gain, a comprehensive satisfaction index is generated, where the comprehensive satisfaction index is a comprehensive satisfaction score. This technical solution does not limit the preset range. In an optional implementation, the preset threshold is 0.6.

[0103] Furthermore, the comprehensive satisfaction index is obtained by weighting the qualitative indicators, operation accuracy and training effectiveness gain.

[0104] The specific calculation formula is as follows:

[0105] S com =αS sub +βA n -γTeg n

[0106] Where: α, β, γ are weight coefficients, and α+β+γ=1.

[0107] In an optional embodiment, α=0.2, β=0.4, and γ=0.4.

[0108] Furthermore, regarding the updating of the basic database and the power grid control knowledge graph in step S400.

[0109] In an optional embodiment, updating the basic database and the power grid control knowledge graph can be automatically updated based on event triggering;

[0110] In another optional implementation, the basic database and the power grid control knowledge graph may also be updated manually based on user feedback.

[0111] In summary, the present invention integrates the standard operating procedures, power dispatching procedures and real-time operating status data of power grid operation by constructing a basic database containing normative data and operating data, providing comprehensive, accurate and dynamically updated data support for training, ensuring that the training content is closely aligned with actual operating needs; and by constructing a power grid control knowledge graph to present various complex knowledge of power grid operation in a structured form, it realizes the systematic integration and efficient retrieval of knowledge, especially when facing specific (extreme) working conditions, it can quickly and accurately retrieve matching control strategies and intuitively present them to controllers through visual display, effectively improving the pertinence and practicality of training, and improving the decision-making efficiency and accuracy of controllers under complex working conditions; further, by introducing a satisfaction feedback mechanism, it can ensure that the training system is continuously optimized and improved according to actual usage, so that the training content always meets the ever-changing operating requirements and extreme working conditions under the integrated power grid control mode.

[0112] Example 3. The above is a schematic scheme of a method for assisting integrated training in power grid regulation. It should be noted that the technical scheme of this integrated training assistance system for power grid regulation and control is based on the same concept as the technical scheme of the aforementioned method for assisting integrated training in power grid regulation and control. For details not described in detail in the technical scheme of the integrated training assistance system for power grid regulation and control in this embodiment, please refer to the description of the technical scheme of the aforementioned method for assisting integrated training in power grid regulation and control.

[0113] This embodiment also provides a power grid control integrated training auxiliary system, including:

[0114] A first building module is used to obtain first data under extreme working conditions and build a basic database based on the first data;

[0115] The second construction module is used to build a power grid control knowledge graph containing entity nodes such as substation location, operating condition type, risk level, data monitoring, and fault response strategy based on the basic database, and store the power grid control knowledge graph in the graph database;

[0116] The matching display module is used to respond to the input target operating condition type and target substation, retrieve the matching target control strategy based on the power grid control knowledge graph, and visualize the target control strategy.

[0117] This embodiment also provides an electronic device suitable for integrated training assistance for power grid regulation, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the integrated training assistance method for power grid regulation proposed in the above embodiment.

[0118] This embodiment further provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the power grid control integrated training auxiliary method proposed in the above embodiment.

[0119] The storage medium proposed in this embodiment and the auxiliary method for realizing integrated training of power grid regulation proposed in the above embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0120] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general hardware, and of course can also be implemented by hardware. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0121] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A training assistance method for integrated power grid control, characterized by: include, Acquiring first data under extreme working conditions, and building a basic database based on the first data; Building a power grid control knowledge graph based on the basic database, including entity nodes of substation location, operating condition type, risk level, data monitoring, and fault response strategy, and storing the power grid control knowledge graph in a graph database; In response to the input target operating condition type and target substation, a matching target regulation strategy is retrieved based on the power grid regulation knowledge graph, and the target regulation strategy is visualized and displayed.

2. The power grid control integrated training auxiliary method according to claim 1, characterized in that: The method further includes calculating a comprehensive satisfaction index based on satisfaction feedback on the target regulation strategy; When the comprehensive satisfaction index is lower than a preset threshold, the basic database and the power grid regulation knowledge graph are updated.

3. The power grid control integrated training auxiliary method according to claim 2, characterized in that: The constructing of a basic database based on the first data includes: Use digital processing technology to convert the first data under extreme working conditions into text files that are easy to retrieve; The basic database is constructed based on the text file and the operating status data of the power grid equipment collected in real time.

4. The power grid control integrated training auxiliary method according to claim 3, characterized in that: The calculation of the comprehensive satisfaction index includes: Obtain the controller's subjective evaluation score; Calculate the correctness of the operation, which is determined based on the number of deviations between the controller's operation and the grid control knowledge graph recommendations; Calculate training effectiveness gains based on a comparison of the controller's actual operation time and the optimal time recommended by the grid control knowledge graph; A comprehensive satisfaction index is generated based on the qualitative indicators, the operation accuracy rate and the training effectiveness gain.

5. The power grid control integrated training auxiliary method according to claim 4, characterized in that: The target regulation strategy visualization display includes: Locate the geographical location of the target substation through the area selection interface; Dynamically annotate the grid control knowledge graph with recommended operational suggestions through the substation SVG control diagram.

6. The power grid control integrated training auxiliary method according to claim 5, characterized in that: The types of working conditions include extreme weather, natural disasters and emergencies; The risk levels include low, medium and high and are associated with action recommendations; The data monitoring includes real-time monitoring of current, voltage and frequency parameters; The fault response strategy includes corresponding strategies for fault type and location, scheduling coordination strategies and power grid configuration adjustment strategies.

7. The power grid control integrated training auxiliary method according to claim 6, characterized in that: The comprehensive satisfaction index is obtained by weighting the qualitative index, the operation accuracy and the training effectiveness gain.

8. A power grid control integrated training auxiliary system, applying the method according to any one of claims 1 to 7, characterized in that: include: A first building module is used to obtain first data under extreme working conditions and build a basic database based on the first data; A second construction module is configured to construct a power grid control knowledge graph including entity nodes of substation location, operating condition type, risk level, data monitoring, and fault response strategy based on the basic database, and store the power grid control knowledge graph in a graph database; The matching display module is used to respond to the input target operating condition type and target substation, retrieve the matching target control strategy based on the power grid control knowledge graph, and visualize the target control strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images