Power grid equipment scheduling method and device based on graph neural network, and electronic device

Abstract

This invention provides a method, apparatus, electronic device, and storage medium for scheduling power grid equipment based on graph neural networks. The method includes: acquiring front-end power grid detection information; sending the power grid detection information to a back-end power grid operation intelligent agent; determining whether a tripping fault has occurred based on the power grid detection information and historical fault information; responding to a tripping fault, analyzing the power grid detection information based on a back-end power grid cognitive intelligent agent to determine the cause of the tripping; and scheduling power grid equipment according to the cause of the tripping. This invention can send front-end detection information to a back-end intelligent agent, detect the occurrence of tripping faults through a back-end intelligent agent, and analyze the cause of the tripping through another intelligent agent. The analysis process is fully automated, improving the accuracy and efficiency of detection. Furthermore, by separating the judgment and analysis steps using different intelligent agents, this application distributes the training and computational burden of the intelligent agents, reducing costs.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and specifically to a scheduling method, apparatus, electronic device, and storage medium for power grid equipment based on graph neural networks. Background Technology

[0002] With the further increase in the proportion of new energy installed capacity and the scale of the power grid, the randomness and volatility of power grid operation have increased significantly, and the pressure on the safe operation of the power grid is increasing day by day. The safety and stability of power equipment has attracted widespread attention, and the importance of the operation and maintenance of main grid equipment is self-evident. Once power equipment fails, it will not only affect the normal power consumption of a large number of users, but may also cause huge property losses and casualties. The traditional equipment operation and maintenance and management model has gradually shown its limitations and is difficult to meet the needs of high efficiency and precision.

[0003] Existing methods for analyzing the causes of power outages mainly rely on human experience. However, this method is highly subjective, has a high error rate, and is inefficient, resulting in significant errors and low efficiency in the final dispatching methods for power grid equipment. Summary of the Invention

[0004] The problem addressed by this invention is that existing power grid equipment scheduling methods suffer from high error rates and low efficiency.

[0005] To address the above problems, this invention provides a scheduling method for power grid equipment based on graph neural networks, the method comprising: Obtain front-end power grid detection information; The power grid detection information is sent to the power grid operation intelligent agent in the background; The power grid operation intelligent agent determines whether a tripping fault has occurred based on the power grid detection information and historical fault information. In response to a tripping fault, the power grid cognitive intelligence agent in the background analyzes the power grid detection information to determine the cause of the tripping. The power grid equipment is dispatched according to the cause of the trip.

[0006] Optionally, the power grid fault information includes image information and voiceprint information.

[0007] Optionally, the voiceprint information is a real-time data stream.

[0008] Optionally, the step of determining whether a tripping fault has occurred based on the power grid detection information and historical fault information by the power grid operation intelligent agent includes: The voiceprint features of the voiceprint information in the power grid detection information are extracted by the power grid operation intelligent agent. The target voiceprint features are obtained by fusing the voiceprint features according to the time series. Obtain the target image features from the image information in the power grid detection information; The target voiceprint features and target image features are compared with the historical voiceprint features and historical image information corresponding to the historical fault information to determine whether a tripping fault has occurred.

[0009] Optionally, the image information is a real-time data stream.

[0010] Optionally, the background-based power grid cognitive agent analyzes the power grid detection information to determine the cause of the trip, including: The background-based power grid cognitive intelligent agent acquires the voiceprint feature sequence and image feature sequence of the power grid detection information; For each time point, the corresponding voiceprint feature in the voiceprint feature sequence is fused with the corresponding image feature in the image feature sequence to obtain a fused feature sequence; Analyze the fusion feature sequence to determine the cause of the trip.

[0011] Optionally, the tripping cause includes multiple candidate causes, and after the tripping fault occurs, the process of analyzing the power grid detection information based on the background power grid cognitive intelligent agent to determine the tripping cause includes: Retrieve historical trip logs; Based on the historical trip records in the historical trip log, the true cause is determined from the multiple candidate causes.

[0012] This application embodiment also provides a tripping cause determination device, including: The acquisition unit is used to acquire power grid detection information from the front end; The sending unit is used to send the power grid detection information to the power grid operation intelligent agent in the background; The judgment unit is used to determine whether a tripping fault has occurred based on the power grid detection information and historical fault information by the power grid operation intelligent agent; An analysis unit is used to analyze the power grid detection information based on the background power grid cognitive intelligent agent in response to a tripping fault to determine the cause of the tripping. The dispatching unit is used to dispatch power grid equipment based on the cause of the trip.

[0013] Optionally, the determining unit is further configured to: The voiceprint features of the voiceprint information in the power grid detection information are extracted by the power grid operation intelligent agent. The target voiceprint features are obtained by fusing the voiceprint features according to the time series. Obtain the target image features from the image information in the power grid detection information; The target voiceprint features and target image features are compared with the historical voiceprint features and historical image information corresponding to the historical fault information to determine whether a tripping fault has occurred.

[0014] Optionally, the analysis unit is further configured to: The background-based power grid cognitive intelligent agent acquires the voiceprint feature sequence and image feature sequence of the power grid detection information; For each time point, the corresponding voiceprint feature in the voiceprint feature sequence is fused with the corresponding image feature in the image feature sequence to obtain a fused feature sequence; Analyze the fusion feature sequence to determine the cause of the trip.

[0015] Optionally, the tripping cause includes multiple candidate causes, and the analysis unit is further used for: Retrieve historical trip logs; Based on the historical trip records in the historical trip log, the true cause is determined from the multiple candidate causes.

[0016] Optionally, the power grid fault information includes image information and voiceprint information.

[0017] Optionally, the voiceprint information is a real-time data stream.

[0018] Optionally, the image information is a real-time data stream.

[0019] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: The electronic device in this embodiment operates as the scheduling method of power grid equipment based on graph neural network of any embodiment of the present invention, and therefore has all the beneficial effects of the scheduling method of power grid equipment based on graph neural network of any embodiment of the present invention, which will not be repeated here.

[0020] In another aspect, embodiments of the present invention also provide an electronic device, which includes a memory and a processor; the memory stores a computer program, and the processor is used to run the computer program in the memory, wherein when the program or instructions are executed by the processor, the steps of the scheduling method for power grid equipment based on graph neural networks as described in any of the above embodiments are implemented.

[0021] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: The electronic device in this embodiment operates as the scheduling method of power grid equipment based on graph neural network of any embodiment of the present invention, and therefore has all the beneficial effects of the scheduling method of power grid equipment based on graph neural network of any embodiment of the present invention, which will not be repeated here.

[0022] In another aspect, embodiments of the present invention also provide a storage medium storing a program or instructions, which, when executed by a processor, implement the steps of the scheduling method for power grid equipment based on a graph neural network as described in any of the above embodiments.

[0023] Compared with the prior art, the technical effects achieved by adopting this technical solution are as follows: The readable storage medium in this embodiment is used to store the scheduling method of power grid equipment based on graph neural network as in any embodiment of the present invention, and therefore it has all the beneficial effects of the scheduling method of power grid equipment based on graph neural network as in any embodiment of the present invention, which will not be repeated here.

[0024] The grid equipment scheduling method based on graph neural networks provided in this application involves: acquiring front-end grid detection information; sending the grid detection information to a back-end grid operation intelligent agent; determining whether a tripping fault has occurred based on the grid detection information and historical fault information; responding to a tripping fault, analyzing the grid detection information based on the back-end grid cognitive intelligent agent to determine the cause of the tripping, and scheduling grid equipment according to the cause of the tripping. This application can send front-end detection information to the back-end, detect the occurrence of tripping faults through a back-end intelligent agent, and analyze the cause of the tripping through another intelligent agent. The analysis process is fully automated, improving the accuracy and efficiency of detection. Furthermore, by separating the judgment and analysis steps using different intelligent agents, this application distributes the training and computational burden of the intelligent agents, reducing costs. Attached Figure Description

[0025] Figure 1 A flowchart illustrating the scheduling method for power grid equipment based on graph neural networks provided in this application embodiment; Figure 2 Another flowchart illustrating the scheduling method for power grid equipment based on graph neural networks provided in this application embodiment; Figure 3 This is another flowchart illustrating the scheduling method for power grid equipment based on graph neural networks provided in this application embodiment; Figure 4 This is another flowchart illustrating the scheduling method for power grid equipment based on graph neural networks provided in this application embodiment; Figure 5 This is a schematic diagram of a trip cause determination device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] This application provides a scheduling method, apparatus, electronic device, and storage medium for power grid equipment based on graph neural networks. The query device can be integrated into a computer device, which can be a server. This server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0028] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0029] Please continue reading. Figure 1 , Figure 1 This is a flowchart illustrating a scheduling method for power grid equipment based on graph neural networks provided in an embodiment of this application. The electronic control unit 100 includes multiple hardware security modules, and the control method specifically includes the following steps: 110. Obtain front-end power grid detection information.

[0030] Power grid monitoring information can be acquired through various detection devices installed at the front end of the power grid. This information can include image and voiceprint data. For example, images can be captured by a camera, and sound can be collected by a recording system and processed to obtain voiceprint data. During operation, the voiceprint recognition model can be continuously optimized to improve its anti-interference capabilities and recognition accuracy, ensuring the reliability of alarm information.

[0031] In some embodiments, after acquiring sound and image information, the raw data is preprocessed and outliers are removed to ensure the accuracy of power grid detection information.

[0032] In some embodiments, maintenance records, technical documents, expert experience sharing, etc., are also obtained to ensure the comprehensiveness and timeliness of the data.

[0033] 120. Send the power grid monitoring information to the power grid operation intelligent agent in the background.

[0034] A secure and efficient transmission mechanism is used to send power grid monitoring information to the backend power grid operation intelligent agent, ensuring that the data is not lost or leaked during transmission and arrives in a timely manner.

[0035] 130. The power grid operation intelligent agent determines whether a tripping fault has occurred based on power grid detection information and historical fault information.

[0036] A power grid operation intelligent agent is used to determine whether a tripping fault has occurred based on power grid detection information, such as at least one of image information and voiceprint information. In some embodiments, the power grid operation intelligent agent can determine whether a tripping fault has occurred based on both image information and voiceprint information simultaneously to improve accuracy.

[0037] In some embodiments, a pre-defined agent can be trained to obtain a power grid operation agent. For example, multiple training data can be pre-acquired to form a highly integrated knowledge base. Through efficient cleaning, labeling, transformation, and structuring of various types of knowledge, vectorization is performed to form a graphical composite knowledge base. Then, the pre-defined agent can be trained using the training data in the knowledge base to obtain the power grid operation agent.

[0038] refer to Figure 2 In some embodiments, step 130 may include: 210. Extract the voiceprint features of voiceprint information from power grid detection information through the power grid operation intelligent agent.

[0039] 220. The target voiceprint features are obtained by fusing the voiceprint features according to the time series.

[0040] 230. Obtain the target image features from the image information in the power grid detection information.

[0041] 240. Compare the target voiceprint features and target image features with the historical voiceprint features and historical image information corresponding to the historical fault information to determine whether a tripping fault has occurred.

[0042] In this embodiment, the voiceprint information is a real-time data stream, meaning it can be a time series. The power grid operation intelligent agent can perform feature fusion on the voiceprint features of the voiceprint information according to the time series to obtain target voiceprint features containing time information.

[0043] After obtaining the target voiceprint and image features, the power grid operation intelligence agent can compare these features with historical voiceprint and image features corresponding to historical fault information, for example, by comparing their similarity. A higher similarity indicates a greater probability of a tripping fault. When the similarity reaches a preset threshold, a tripping fault can be determined. The thresholds for voiceprint feature comparison and image feature comparison can be different, and the threshold for determining a tripping fault can be adjusted according to actual circumstances.

[0044] 140. In response to a tripping fault, the power grid cognitive agent in the background analyzes the power grid detection information to determine the cause of the tripping.

[0045] When a tripping fault is detected, the cause of the tripping can be analyzed using a different intelligent agent than the power grid operation intelligent agent, namely, a power grid cognitive intelligent agent. In some embodiments, a pre-set intelligent agent can be trained to obtain a power grid cognitive intelligent agent. For example, multiple training data can be pre-acquired to form a highly integrated knowledge base. Through efficient cleaning, labeling, transformation, and structuring of various types of knowledge, vectorization is performed to form a graphical composite knowledge base. Then, the pre-set intelligent agent can be trained using the training data in the knowledge base to obtain the power grid cognitive intelligent agent.

[0046] refer to Figure 3 In some embodiments, step 140 may include: 310. The power grid cognitive agent based on the background acquires the voiceprint feature sequence and image feature sequence of power grid detection information.

[0047] 320. For each time point, the corresponding voiceprint feature in the voiceprint feature sequence is fused with the corresponding image feature in the image feature sequence to obtain the fused feature sequence.

[0048] 330. Analyze the fusion feature sequence to determine the cause of the trip.

[0049] In this embodiment, image information is also a real-time data stream. The trained power grid cognitive agent can extract voiceprint feature sequences and image feature sequences containing time information. Then, the voiceprint features and image features at each time point are fused to obtain a new fused feature sequence, which simultaneously contains voiceprint information and image information.

[0050] Then, the power grid cognitive agent can analyze the fused feature sequence to determine the cause of the trip. For example, different trip causes can be pre-matched with their corresponding feature sequences, and then the fused feature sequence can be compared with the feature sequences during analysis. The trip cause corresponding to the feature sequence with high similarity can be taken as the cause of the current trip.

[0051] In some embodiments, multiple feature sequences may have a high similarity to the fused feature sequence, in which case the reference... Figure 4 Step 140 may include: 410. Obtain historical trip logs.

[0052] 420. Based on historical trip records in historical trip logs, determine the true cause from multiple candidate causes.

[0053] Historical trip logs can contain multiple trip records entered by maintenance personnel. These records can include trip time, cause, and other details. Through these historical trip records, the power grid cognitive agent can identify the most frequently occurring target candidate cause from multiple candidate causes and use it as the actual cause.

[0054] 150. Dispatch power grid equipment according to the cause of the trip.

[0055] Based on the type of tripping cause, such as line overload, equipment insulation damage, short circuit fault, and abnormal voltage fluctuations, a graph neural network model is used to perform real-time simulations of the power grid topology, operating parameters of various equipment, and load distribution. Priority is given to disconnecting the electrical connection between the faulty and non-faulty areas to prevent the fault from spreading. Simultaneously, backup power equipment is deployed, the load distribution ratio in non-faulty areas is adjusted, and the power transmission path of transmission lines is optimized to restore normal power supply to the core areas of the power grid. For equipment hazards corresponding to the tripping cause, intelligent maintenance terminals are simultaneously dispatched to the fault location for investigation and repair. After the hazards are eliminated, power supply to the faulty area is gradually restored, ensuring the overall stability, safety, and reliability of the power grid operation, and minimizing the impact of tripping faults on the power grid supply.

[0056] To facilitate better implementation of the power grid equipment scheduling method based on graph neural networks provided in this application, a power grid equipment scheduling device based on graph neural networks is also provided in one embodiment. The meanings of the terms used are the same as in the aforementioned power grid equipment scheduling method based on graph neural networks, and specific implementation details can be found in the description of the method embodiments.

[0057] This scheduling device can be integrated into computer equipment, such as... Figure 5 As shown, the scheduling device may include: an acquisition unit 501, a sending unit 502, a judgment unit 503, an analysis unit 504, and a scheduling unit 505, as detailed below: Acquisition unit 501 is used to acquire front-end power grid detection information; The sending unit 502 is used to send the power grid detection information to the power grid operation intelligent agent in the background; The judgment unit 503 is used to determine whether a tripping fault has occurred based on the power grid detection information and historical fault information by the power grid operation intelligent agent; Analysis unit 504 is used to analyze the power grid detection information based on the background power grid cognitive intelligent agent to determine the cause of the trip in response to the occurrence of a tripping fault. The dispatching unit 505 is used to dispatch power grid equipment based on the cause of the trip.

[0058] This application also provides an electronic device, which may be a server, such as... Figure 6 As shown, it illustrates a schematic diagram of the server structure involved in an embodiment of this application. Specifically: The server may include components such as a processor 1001 with one or more processing cores, a memory 1002 with one or more computer-readable storage media, a power supply 1003, and an input unit 1004. Those skilled in the art will understand that... Figure 5 The server architecture shown does not constitute a limitation on the server and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. Wherein: The processor 1001 is the control center of the server, connecting various parts of the server through various interfaces and lines. It performs various server functions and processes data by running or executing software programs and / or modules stored in the memory 1002, and by calling data stored in the memory 1002, thereby providing overall monitoring of the server. Optionally, the processor 1001 may include one or more processing cores; preferably, the processor 1001 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and computer programs, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1001.

[0059] The memory 1002 can be used to store software programs and modules. The processor 1001 executes various functional applications and data processing by running the software programs and modules stored in the memory 1002. The memory 1002 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, computer programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the server, etc. In addition, the memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 1002 may also include a memory controller to provide the processor 1001 with access to the memory 1002.

[0060] The server also includes a power supply 1003 that supplies power to the various components. Preferably, the power supply 1003 can be logically connected to the processor 1001 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 1003 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0061] The server may also include an input unit 1004, which can be used to receive input numeric or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0062] Although not shown, the server may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 1001 in the server loads the executable files corresponding to the processes of one or more computer programs into the memory 1002 according to the following instructions, and the processor 1001 runs the computer programs stored in the memory 1002 to realize various functions, as follows: Obtain front-end power grid detection information; The power grid detection information is sent to the power grid operation intelligent agent in the background; The power grid operation intelligent agent determines whether a tripping fault has occurred based on the power grid detection information and historical fault information. In response to a tripping fault, the power grid cognitive intelligence agent in the background analyzes the power grid detection information to determine the cause of the tripping. The power grid equipment is dispatched according to the cause of the trip.

[0063] Therefore, the grid equipment scheduling method based on graph neural networks provided in this application can send the detection information from the front end to the back end, detect the occurrence of tripping faults through the intelligent agent in the back end, analyze the cause of the tripping through another intelligent agent, and schedule the grid equipment according to the cause of the tripping. The analysis is fully automated, which improves the accuracy and efficiency of detection. Furthermore, by separating the judgment and analysis steps and using different intelligent agents, this application distributes the training and computing pressure of the intelligent agents and reduces costs.

[0064] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0065] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium (also referred to as a storage medium). A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations of the above embodiments.

[0066] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by a computer program, or by a computer program controlling related hardware. The computer program can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0067] Therefore, embodiments of this application provide a storage medium storing a computer program that can be loaded by a processor to execute steps in any of the graph neural network-based power grid equipment scheduling methods provided in embodiments of this application.

[0068] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0069] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0070] Since the computer program stored in the storage medium can execute the steps in any of the graph neural network-based power grid equipment scheduling methods provided in the embodiments of this application, the beneficial effects that any of the graph neural network-based power grid equipment scheduling methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0071] The foregoing has provided a detailed description of a scheduling method, apparatus, electronic device, and storage medium for power grid equipment based on graph neural networks, as provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A scheduling method for power grid equipment based on graph neural networks, characterized in that, The method includes: Obtain front-end power grid detection information; The power grid detection information is sent to the power grid operation intelligent agent in the background; The power grid operation intelligent agent determines whether a tripping fault has occurred based on the power grid detection information and historical fault information. In response to a tripping fault, the power grid cognitive intelligence agent in the background analyzes the power grid detection information to determine the cause of the tripping. The power grid equipment is dispatched according to the cause of the trip.

2. The method according to claim 1, characterized in that, The power grid fault information includes image information and voiceprint information.

3. The method according to claim 2, characterized in that, The voiceprint information is a real-time data stream.

4. The method according to claim 3, characterized in that, The step of determining whether a tripping fault has occurred based on the power grid detection information and historical fault information by the power grid operation intelligent agent includes: The voiceprint features of the voiceprint information in the power grid detection information are extracted by the power grid operation intelligent agent. The target voiceprint features are obtained by fusing the voiceprint features according to the time series. Obtain the target image features from the image information in the power grid detection information; The target voiceprint features and target image features are compared with the historical voiceprint features and historical image information corresponding to the historical fault information to determine whether a tripping fault has occurred.

5. The method according to claim 3, characterized in that, The image information is a real-time data stream.

6. The method according to claim 5, characterized in that, The background-based power grid cognitive agent analyzes the power grid detection information to determine the cause of the trip, including: The background-based power grid cognitive intelligent agent acquires the voiceprint feature sequence and image feature sequence of the power grid detection information; For each time point, the corresponding voiceprint feature in the voiceprint feature sequence is fused with the corresponding image feature in the image feature sequence to obtain a fused feature sequence; Analyze the fusion feature sequence to determine the cause of the trip.

7. The method according to claim 1, characterized in that, The tripping cause includes multiple candidate causes. In response to a tripping fault, after analyzing the power grid detection information based on the background power grid cognitive intelligent agent to determine the tripping cause, the process includes: Retrieve historical trip logs; Based on the historical trip records in the historical trip log, the true cause is determined from the multiple candidate causes.

8. A scheduling device for power grid equipment based on graph neural networks, characterized in that, include: The acquisition unit is used to acquire power grid detection information from the front end; The sending unit is used to send the power grid detection information to the power grid operation intelligent agent in the background; The judgment unit is used to determine whether a tripping fault has occurred based on the power grid detection information and historical fault information by the power grid operation intelligent agent; An analysis unit is used to analyze the power grid detection information based on the background power grid cognitive intelligent agent in response to a tripping fault to determine the cause of the tripping. The dispatching unit is used to dispatch power grid equipment based on the cause of the trip.

9. An electronic device, characterized in that, It includes a memory and a processor; the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the scheduling method for power grid equipment based on graph neural networks as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores multiple computer programs, which are adapted for loading by a processor to execute the scheduling method for power grid equipment based on graph neural networks as described in any one of claims 1 to 7.

Images