Substation full-stop full-transfer load transfer method and system based on ai and contact graph

Abstract

The application discloses a substation full-stop full-transfer load transfer method and system based on AI and contact graph, comprising constructing a digital distribution line contact graph and an AI analysis model; obtaining real-time operation data of the substation, using the AI analysis model to determine whether a substation full-stop fault occurs, a fault type and a power loss range, generating a fault judgment result, and determining whether a substation full-stop fault occurs; if a substation full-stop fault occurs, triggering full-automatic load transfer, analyzing the digital distribution line contact graph, constructing an optimization target, and combining the analysis result, the fault type, the power loss range and the operation data to generate a full-stop full-transfer load transfer scheme and automatically execute it. The application realizes full-automatic, accurate and efficient load transfer in a full-stop scene, reduces the burden and improves the efficiency, improves the power supply reliability and avoids operation risks.

Description

Technical Field

[0001] This invention relates to the field of load transfer technology, and in particular to a method and system for load transfer in a substation with complete shutdown and transfer based on AI and interconnection diagrams. Background Technology

[0002] As the "last mile" of power supply, the reliability of the power distribution network directly affects people's livelihoods and economic development. Substations are the core hubs of the distribution network; a complete power outage (including a busbar outage) will cause multiple lines within their service area to lose power. In such emergencies, if load transfer is not timely or accurate, it can easily trigger widespread power outages, severely impacting social production and daily life.

[0003] Currently, in extreme scenarios where a substation experiences a complete outage, existing technologies mainly rely on semi-automatic or manual operation modes. The specific approach is as follows: the dispatcher uses a static distribution line connection diagram as a basic reference, manually analyzes the electrical connections between substations and lines in the power grid, manually judges the current load distribution, and formulates a specific operation plan for load transfer based on experience. Subsequently, the dispatcher needs to manually execute a series of switching operation commands on the distribution automation system to complete the load transfer.

[0004] Research has found that existing technologies have significant shortcomings. They rely heavily on the personal experience of dispatchers and involve cumbersome processes. They are inefficient at analyzing complex power distribution line connection diagrams, especially in scenarios with complex power grid topologies and multiple intersecting lines. Manual analysis is prone to misjudging connection relationships, leading to unreasonable power transfer plans, long processing times, and an inability to achieve rapid load restoration, making it difficult to meet the emergency response needs of complete power outages and transfers.

[0005] Meanwhile, existing technologies have not effectively integrated AI technology, making it impossible to intelligently analyze real-time power grid operation data and historical fault data, making it difficult to dynamically optimize power transfer schemes and achieve the dual goals of reducing burden and increasing efficiency and improving power supply reliability. Summary of the Invention

[0006] To address the aforementioned issues, this invention proposes a method and system for load transfer in substations under complete power outage and transfer scenarios based on AI and interconnection diagrams. This invention uses distribution line interconnection diagrams as a foundation and integrates AI intelligent analysis technology to achieve fully automated, precise, and efficient load transfer in complete power outage scenarios, thereby reducing the burden and increasing efficiency, improving power supply reliability, and mitigating operational risks.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for load transfer in a substation with complete shutdown and transfer based on AI and interconnection diagrams, comprising the following steps: Construct a digital distribution line interconnection map marked with transferable paths and load carrying capacity thresholds, and simultaneously build and calibrate an AI analysis model; The system acquires real-time operating data of the substation, uses an AI analysis model combined with preset undervoltage start-up conditions and interlocking conditions to determine whether a substation total shutdown fault has occurred, the fault type and the scope of power loss, generates fault judgment results, and determines whether a substation total shutdown fault has occurred. If a substation outage occurs, a fully automatic load transfer is triggered. The digital distribution line connection diagram is called and analyzed to obtain the analysis results. An optimization target is constructed, and a full outage and full transfer load transfer plan is generated and executed automatically, based on the analysis results, fault type, power outage range, and operating data.

[0008] As an alternative implementation, the digital power distribution line connection diagram includes basic information on all substations, power distribution lines, and switching equipment within the target area, as well as the connection relationships between each substation and each power distribution line; wherein, the basic information includes substation voltage level, line route, connection switch location, load distribution, and equipment parameters.

[0009] As an optional implementation, the AI ​​analysis model includes a fault identification module, a tie-line diagram parsing module, a power transfer scheme generation module, and an effect optimization module. The fault identification module employs a convolutional neural network algorithm to generate fault judgment results; the tie-line diagram parsing module employs a graph neural network algorithm to parse the digital distribution line tie-line diagram; the power transfer scheme generation module employs a reinforcement learning algorithm to generate a full-shutdown / full-transfer load transfer scheme; and the effect optimization module employs an LSTM neural network algorithm to optimize the full-shutdown / full-transfer load transfer scheme.

[0010] As an optional implementation, the real-time operation data of the substation includes the bus voltage of each substation, the status of the main transformer switch, the outgoing switch undervoltage and undercurrent data, and the line load data; the undervoltage start conditions include the main transformer side switch tripping, the occurrence of a total fault signal, the bus three-phase voltage jump being lower than a preset threshold, the outgoing switch undervoltage and undercurrent jump being lower than a preset threshold, and the duration being not less than a set threshold; the blocking conditions include the substation going offline and the main transformer side switch being remotely tripped.

[0011] As an alternative implementation method, the digital distribution line connection diagram is called and analyzed to obtain the analysis results. Specifically, the following steps are taken: using a graph neural network algorithm, the power outage lines of the faulty substation, the adjacent substations that can be connected, and the power transfer line paths are extracted, and the load carrying capacity and switch status of each power transfer line path are obtained. Combined with real-time power flow data of the power grid, the power transfer paths that meet the conditions are selected to obtain the analysis results.

[0012] As an alternative implementation method, with the optimization goals of the fastest load recovery speed, the most balanced load distribution, the fewest operation steps, and the lowest safety risk, a full shutdown and full transfer load transfer scheme is generated by combining the analysis results, fault type, power outage range, and operation data. The full shutdown and full transfer load transfer scheme includes the transfer path, the sequence of switch operation, the transfer load distribution, and the operation time estimation.

[0013] Secondly, this invention provides a substation full shutdown and full transfer load transfer system based on AI and interconnection diagrams, comprising the following modules: The model building module is configured to: build a digital distribution line interconnection map labeled with transferable paths and load carrying capacity thresholds, and at the same time build and calibrate an AI analysis model; The fault diagnosis module is configured to: acquire real-time operating data of the substation, use an AI analysis model combined with preset undervoltage start conditions and interlocking conditions to determine whether a substation total shutdown fault has occurred, the fault type and the scope of power loss, generate fault diagnosis results, and determine whether a substation total shutdown fault has occurred. The load transfer scheme generation module is configured to: if a substation outage occurs, trigger a fully automatic load transfer, call the digital distribution line connection diagram and analyze it to obtain the analysis results, construct optimization targets, and combine the analysis results, fault type, power outage range and operation data to generate a full outage and full transfer load transfer scheme and execute it automatically.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention, through the collaborative work of power distribution line connection diagrams and AI analysis models, eliminates the need for manual analysis of connection relationships and formulation of transfer plans. It automatically completes fault identification, plan generation, and transfer execution throughout the entire process, effectively reducing the operational burden on dispatchers, avoiding human misjudgment and misoperation, and shortening the transfer execution time from several hours in the traditional manual mode to seconds or minutes, significantly improving transfer efficiency and achieving the core goal of reducing burden and increasing efficiency.

[0015] This invention generates a load transfer scheme for a complete power outage by analyzing the power distribution line connection diagram and combining it with real-time power grid operation data. It takes into account both the speed of load recovery and safety and stability. Especially for scenarios where the fault point is not clear, it adopts the logic of "fast power supply first, then analysis" to prioritize the restoration of loads while avoiding operational risks. This effectively improves the power supply reliability in the scenario of a complete power outage of the substation and reduces the impact of large-scale power outages.

[0016] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0017] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0018] Figure 1 This is a flowchart illustrating the substation full shutdown and full transfer load transfer method based on AI and interconnection diagrams according to the present invention. Figure 2 This is a digital power distribution line connection diagram of the present invention. Detailed Implementation

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0020] It should be noted that the following detailed description is exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0021] Example 1: Taking a complete power outage scenario at a 220kV A substation as an example, this example applies the AI-based load transfer method for a complete power outage and transfer of power to a substation, based on interconnection diagrams. Figure 1 As shown, the specific steps and technical solutions are as follows: S1: Construct a digital distribution line connection map labeled with transferable paths and load carrying capacity thresholds, and simultaneously build and calibrate an AI analysis model.

[0022] In step S1, basic information on the 220 kV A substation, adjacent substations, distribution lines, and switchgear, as well as the interconnections between substations and distribution lines, is collected. This basic information includes, but is not limited to, substation voltage levels, 10 kV busbar parameters, outgoing line routes, interconnection switch locations, load distribution on each line, and switchgear parameters, thus constructing a digital distribution line interconnection map. Simultaneously, the line interconnections between A substation and adjacent substations are defined, and transferable power paths and load carrying capacity thresholds for each interconnection path (such as the maximum load capacity of each interconnection line) are marked, forming an interconnection map database. Switchgear status and line load data are updated synchronously in real time.

[0023] In step S1, the constructed AI analysis model includes a fault identification module, a connection diagram parsing module, a supply transfer scheme generation module, and an effect optimization module; specifically as follows: The fault identification module is used to generate fault judgment results. It adopts the CNN convolutional neural network algorithm, and imports the substation full shutdown fault data, undervoltage data, and switch operation data of the past 3 years for training. The algorithm parameters are calibrated to ensure that the fault identification accuracy reaches more than 99%. The interconnection diagram parsing module is used to parse the digital power distribution line interconnection diagram. It uses the graph neural network (GNN) algorithm to parse the digital power distribution line interconnection diagram and extract key information such as the line interconnection relationship, transferable paths, and load distribution of each outgoing line of substation A. The load transfer scheme generation module is used to generate a full shutdown and full transfer load transfer scheme. It adopts a reinforcement learning algorithm with the goal of "completing the core line transfer and load distribution balance within 30 seconds". It combines the tie diagram analysis results, fault type, power outage range and operation data to generate a full shutdown and full transfer load transfer scheme. The performance optimization module is used to optimize the load transfer scheme for a complete shutdown and full transfer. It adopts the LSTM neural network algorithm and dynamically optimizes the transfer strategy based on historical transfer data and real-time transfer performance.

[0024] In this embodiment, after the AI ​​analysis model is constructed, it is trained and calibrated, including: importing historical substation outage fault data, load transfer data, and distribution line tie diagram data to train the AI ​​analysis model (gradually training the analytical thinking mode through a feeding method), adjusting algorithm parameters, and ensuring that the fault identification accuracy, tie diagram parsing accuracy, and the rationality of the transfer scheme meet the preset standards; at the same time, the AI ​​analysis model is connected to the distribution automation system and dispatch control platform to realize real-time data interaction and synchronous transmission of instructions.

[0025] S2: Obtain real-time operating data of the substation, use AI analysis models combined with preset undervoltage start conditions and interlocking conditions to determine whether a substation total shutdown fault has occurred, the fault type and the scope of power loss, generate fault judgment results, and determine whether a substation total shutdown fault has occurred.

[0026] In step S2, the power distribution automation system acquires real-time operating data of substation A. The real-time operating data includes, but is not limited to, bus voltage of each substation, status of main transformer switch, outgoing switch undervoltage and undercurrent data, and line load data, and transmits them synchronously to the fault identification module.

[0027] The fault identification module uses real-time operating data and preset undervoltage start conditions (tripping of the 10kV side switch of the main transformer, occurrence of a total fault signal, three-phase voltage jump of the 10kV bus below the preset threshold (0.5kV), undervoltage and current jump of the outgoing switch below the preset threshold (0.5kV, 0.5A), duration not less than the set threshold (30s)) and blocking conditions (substation offline, remote control tripping of the main transformer side switch, etc.) to determine whether a substation full shutdown fault has occurred, the fault type (bus full shutdown, main transformer fault causing full shutdown, etc.) and the scope of power loss, and generates fault identification results.

[0028] For example: if the three-phase voltage jump of the 10 kV busbar is detected to be lower than the preset threshold, the 10 kV switch on the main transformer side trips, and the outgoing switch loses current for 30 seconds, which meets the preset undervoltage start condition and does not trigger the blocking condition (the substation is online and the main transformer side switch is not remotely tripped), the CNN convolutional neural network algorithm will determine that the 10 kV busbar of substation A is completely shut down, and the power loss range is 9 outgoing lines.

[0029] If the fault is determined to be a complete substation outage, the AI ​​analysis model automatically triggers the fully automatic load transfer process, simultaneously pushing the fault information and power outage range to the dispatch control platform, triggering alarm prompts, and calling the digital power distribution line connection diagram to start the connection diagram parsing module.

[0030] S3: If a substation outage occurs, a fully automatic load transfer is triggered. The digital distribution line connection diagram is called and analyzed to obtain the analysis results. An optimization target is constructed, and a full outage and full transfer load transfer plan is generated and executed automatically, based on the analysis results, fault type, power outage range and operating data.

[0031] In step S3, the interconnection diagram parsing module uses a graph neural network (GNN) algorithm to parse the digital distribution line interconnection diagram, extract the power outage lines of the faulty substation, the adjacent substations that can be interconnected, and the power transfer line paths, and obtain the load carrying capacity and switch status of each power transfer line path. Combined with real-time power flow data of the power grid, the power transfer paths that meet the conditions are selected to obtain the parsing results.

[0032] The load transfer scheme generation module uses a reinforcement learning algorithm with the optimization goals of "fastest load recovery speed, most balanced load distribution, fewest operation steps, and lowest safety risk". Combining the analysis results, fault type, power outage range, and operating data (line load data), it automatically generates a full-stop and full-transfer load transfer scheme. The full-stop and full-transfer load transfer scheme includes the transfer path, switch operation sequence, transfer load distribution, operation time estimation, etc. At the same time, for scenarios where the fault point is not clear, a fast transfer scheme without reverse bus operation is generated first, and a reverse bus scheme is generated as needed to achieve "fast supply first, analysis later".

[0033] In this embodiment, the method also includes: performing a safety verification on the generated full-stop and full-switch load transfer scheme, including load carrying capacity verification, operation permission verification, time interval protection verification, and remote signaling quality code verification (corresponding to the interlocking conditions to prevent erroneous operation), to eliminate safety hazards such as erroneous transfer and overload transfer; if the scheme fails the verification, it automatically returns to adjustment and regenerates the optimal scheme until the safety requirements are met.

[0034] S4: Implement a full shutdown and full transfer load transfer plan to achieve full shutdown and full transfer load restoration while maintaining manual control.

[0035] In step S4, the AI ​​analysis model synchronously transmits the verified full-stop and full-transfer load transfer scheme to the distribution automation system, triggering a fully automatic execution command. Without manual intervention, the system automatically completes the remote control operation of the tie switch and outgoing switch according to the switch operation sequence in the full-stop and full-transfer load transfer scheme, thereby realizing the load transfer.

[0036] During the power transfer process, the AI ​​analysis model monitors the power transfer progress, line load changes, and switch operation status in real time. It updates the power transfer path status in real time through the power distribution line connection diagram. If abnormal situations such as switch remote control failure or line overload occur, the power transfer process is automatically suspended, an abnormality prompt is pushed to the dispatch control platform, and an emergency adjustment plan is generated for dispatchers to confirm and execute, achieving a two-way guarantee of "unmanned intervention" and "manual controllability".

[0037] Once all power outage loads have been transferred and the line loads have returned to normal, the AI ​​analysis model automatically terminates the transfer process, generates a transfer completion report, synchronously updates the equipment status and load data in the distribution line interconnection diagram, and pushes the transfer completion information to the dispatch control platform.

[0038] S5: Review and optimize to continuously improve the efficiency and accuracy of supply transfer.

[0039] In step S5, the performance optimization module acquires all data from the current power transfer process, including fault information, power transfer plan, execution time, load recovery status, and anomaly handling. Combining this with historical power transfer data, it uses an LSTM neural network algorithm for post-mortem analysis to identify areas for optimization in the power transfer plan. Based on the post-mortem analysis results, it automatically adjusts the AI ​​analysis model algorithm parameters and the power transfer plan generation logic, optimizes the parsing accuracy of the distribution line connection diagram, improves the undervoltage start-up conditions and interlocking conditions, and enhances the efficiency and accuracy of subsequent full-shutdown and full-transfer load transfers, continuously optimizing the load reduction and efficiency improvement effects.

[0040] Meanwhile, dispatchers can view the transfer process, generated transfer plans, fault information, and transfer effects in real time through the dispatch control platform. For complex fault scenarios or abnormal situations in the AI ​​analysis model, they can manually intervene to terminate the automatic transfer process and adjust the transfer plan to ensure the safety and reliability of the transfer operation. After the transfer is completed, the dispatcher will manually verify the transfer effect. After confirming that the load has returned to normal and there are no safety hazards, the full shutdown and full transfer load transfer process is completed.

[0041] Example 2: This example provides a substation full shutdown and full transfer load transfer system based on AI and interconnection diagrams, including the following modules: The model building module is configured to: build a digital distribution line interconnection map labeled with transferable paths and load carrying capacity thresholds, and at the same time build and calibrate an AI analysis model; The fault diagnosis module is configured to: acquire real-time operating data of the substation, use an AI analysis model combined with preset undervoltage start conditions and interlocking conditions to determine whether a substation total shutdown fault has occurred, the fault type and the scope of power loss, generate fault diagnosis results, and determine whether a substation total shutdown fault has occurred. The load transfer scheme generation module is configured to: if a substation outage occurs, trigger a fully automatic load transfer, call the digital distribution line connection diagram and analyze it to obtain the analysis results, construct optimization targets, and combine the analysis results, fault type, power outage range and operation data to generate a full outage and full transfer load transfer scheme and execute it automatically.

[0042] It should be noted that the above modules correspond to the steps in Embodiment 1, and the examples and application scenarios implemented by the above modules and their corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should also be noted that the above modules can be executed in a computer system as part of the system.

[0043] In further embodiments, the following is also provided: An electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the method described in Embodiment 1. For brevity, further details are omitted here.

[0044] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0045] A computer-readable storage medium for storing computer instructions that, when executed by a processor, perform the method of Embodiment 1.

[0046] The method in Example 1 can be directly executed by a hardware processor, or it can be executed by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0047] A computer program product includes a computer program that, when executed by a processor, implements the method in Embodiment 1.

[0048] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which execute in a device on a target real or virtual processor to perform the processes / methods described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided among program modules as needed. The machine-executable instructions for the program modules can execute within a local or distributed device. In a distributed device, the program modules can reside in both local and remote storage media.

[0049] The computer program code used to implement the methods of the present invention may be written in one or more programming languages. This computer program code may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the computer or other programmable data processing device, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0050] In the context of this invention, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals may include electrical, optical, radio, sound, or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0051] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A substation full shutdown and load transfer method based on AI and interconnection diagrams, characterized in that, Includes the following steps: Construct a digital distribution line interconnection map marked with transferable paths and load carrying capacity thresholds, and simultaneously build and calibrate an AI analysis model; The system acquires real-time operating data of the substation, uses an AI analysis model combined with preset undervoltage start-up conditions and interlocking conditions to determine whether a substation total shutdown fault has occurred, the fault type and the scope of power loss, generates fault judgment results, and determines whether a substation total shutdown fault has occurred. If a substation outage occurs, a fully automatic load transfer is triggered. The digital distribution line connection diagram is called and analyzed to obtain the analysis results. An optimization target is constructed, and a full outage and full transfer load transfer plan is generated and executed automatically, based on the analysis results, fault type, power outage range, and operating data.

2. The substation full shutdown and load transfer method based on AI and interconnection diagrams as described in claim 1, characterized in that, The digital power distribution line connection diagram contains basic information on all substations, power distribution lines, and switching equipment within the target area, as well as the connection relationships between each substation and power distribution line. The basic information includes substation voltage level, line route, location of connection switches, load distribution, and equipment parameters.

3. The substation full shutdown and load transfer method based on AI and interconnection diagrams as described in claim 1, characterized in that, The AI ​​analysis model includes a fault identification module, a tie-line diagram parsing module, a power transfer scheme generation module, and an effect optimization module. The fault identification module uses a convolutional neural network algorithm to generate fault judgment results; the tie-line diagram parsing module uses a graph neural network algorithm to parse the digital distribution line tie-line diagram; the power transfer scheme generation module uses a reinforcement learning algorithm to generate a full-shutdown / full-transfer load transfer scheme; and the effect optimization module uses an LSTM neural network algorithm to optimize the full-shutdown / full-transfer load transfer scheme.

4. The substation full shutdown and load transfer method based on AI and interconnection diagram as described in claim 1, characterized in that, The real-time operation data of the substation includes the bus voltage of each substation, the status of the main transformer switch, the outgoing switch undervoltage and undercurrent data, and the line load data; the undervoltage start conditions include the main transformer side switch tripping, the occurrence of a total fault signal, the bus three-phase voltage jump below a preset threshold, the outgoing switch undervoltage and undercurrent jump below a preset threshold, and the duration not less than a set threshold; the blocking conditions include the substation going offline and the main transformer side switch being remotely tripped.

5. The substation full shutdown and load transfer method based on AI and interconnection diagrams as described in claim 1, characterized in that, The analysis results are obtained by calling and parsing the digital distribution line connection diagram. Specifically, the graph neural network algorithm is used to extract the power outage lines of the faulty substation, the adjacent substations that can be connected, and the line paths that can be transferred to power supply. The load carrying capacity and switch status of each line path that can be transferred to power supply are obtained. Combined with real-time power flow data of the power grid, the line paths that meet the conditions are selected to obtain the analysis results.

6. The substation full shutdown and load transfer method based on AI and interconnection diagram as described in claim 1, characterized in that, With the optimization goals of the fastest load recovery speed, the most balanced load distribution, the fewest operation steps, and the lowest safety risk, a full shutdown and full transfer load transfer scheme is generated by combining the analysis results, fault types, power outage range, and operating data. The full shutdown and full transfer load transfer scheme includes the transfer path, switch operation sequence, transfer load allocation, and operation time estimation.

7. A substation full shutdown and full transfer load transfer system based on AI and interconnection diagrams, characterized in that, include: The model building module is configured to: build a digital distribution line interconnection map labeled with transferable paths and load carrying capacity thresholds, and at the same time build and calibrate an AI analysis model; The fault diagnosis module is configured to: acquire real-time operating data of the substation, use an AI analysis model combined with preset undervoltage start conditions and interlocking conditions to determine whether a substation total shutdown fault has occurred, the fault type and the scope of power loss, generate fault diagnosis results, and determine whether a substation total shutdown fault has occurred. The load transfer scheme generation module is configured to: if a substation outage occurs, trigger a fully automatic load transfer, call the digital distribution line connection diagram and analyze it to obtain the analysis results, construct optimization targets, and combine the analysis results, fault type, power outage range and operation data to generate a full outage and full transfer load transfer scheme and execute it automatically.

8. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When the processor executes the computer instructions, it performs the substation full shutdown and full transfer load transfer method based on AI and interconnection diagrams as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, complete the substation full shutdown and full transfer load transfer method based on AI and interconnection diagrams as described in any one of claims 1-6.

10. A computer program product, characterized in that, The method includes a computer program that, when executed by a processor, implements the substation full shutdown and full transfer load transfer method based on AI and interconnection diagrams as described in any one of claims 1-6.

Images