Method, device, equipment and medium for determining the weakness of power grid lines

Abstract

The present invention belongs to the field of electric power automation technology and discloses a method, device, equipment and medium for determining the weakness of power grid lines. The method comprises: obtaining the flow data of a target power grid; selecting a line in the target power grid, using the voltage phase angle and amplitude of all nodes in the target power grid in the flow data, as well as the flow and load rate on all lines except the selected line as input, inputting the voltage phase angle and amplitude of all nodes in the target power grid in the flow data, as well as the flow and load rate on all lines other than the selected line, and inputting the voltage into a pre-established deep graph convolutional neural network model for the selected line to obtain a weakness index of the selected line; traversing all lines in the target power grid to obtain line weakness indexes of all lines; and sorting the weakness indexes of all lines in the target power grid to complete the determination of the weakness of the power grid lines. On the one hand, the present invention binds the scenario to the line weakness, and on the other hand, takes into account the impact of intermittent new energy and random electric vehicle loads, and can well evaluate the operating status of the power grid.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power automation, and in particular relates to a method, device, equipment and medium for determining the weakness of a power grid line. Background Art

[0002] A grid's weak links are those components or groups of components that operate poorly, rapidly approach criticality after being disturbed, and have severe consequences if they fail. Factors influencing these weaknesses include grid structure, output level, load level, and power flow distribution. Therefore, identifying the vulnerability of actual grids and defining metrics for evaluating node and line weaknesses are crucial.

[0003] The short-circuit capacity, at unit voltage, is numerically equal to the system admittance, which is the reciprocal of the system's Thevenin equivalent impedance. The larger the short-circuit capacity, the smaller the system's Thevenin equivalent resistance. Switching on or off loads, shunt capacitors, or reactors will not cause significant changes in voltage amplitude, thus strengthening the system. The short-circuit ratio (SCR) represents the system's short-circuit capacity divided by the device's capacity. Therefore, a high SCR indicates that the device is connected to a strong system, indicating that switching the device will have a minimal impact on the system.

[0004] SCR can usually be obtained from the following equation:

[0005]

[0006] in,

[0007] S is the AC system three-phase symmetrical short-circuit level on the conversion or terminal AC bus at 1.0 pu, expressed in megavolt-amperes (MVA). AC terminal voltage;

[0008] P N It is the rated DC terminal power in megawatts (MW).

[0009] Based on this definition and typical inverter characteristics (such as the value of the converter or transformer reactance), the following SCR values ​​can be used to classify AC / DC systems:

[0010] High SCR AC / DC systems are classified as having an SCR value greater than 3.

[0011] Low SCR AC / DC systems are classified by SCR values ​​between 2 and 3.

[0012] Very low SCR AC / DC systems are classified as having an SCR value below 2

[0013] At the same time, for a typical inverter design, a critical short-circuit ratio of 2 is given for operation at maximum available power. The critical short-circuit ratio represents the boundary between the "stable" and "unstable" operating regions. For SCR values ​​below the critical short-circuit ratio, operation is in the "unstable" region of the AC voltage / DC power characteristic.

[0014] As can be seen from Publication (1), although the short-circuit ratio (SCR) can be used to determine the strength of the power system, due to the use of rated capacity, it cannot reflect the intermittent nature of large-scale renewable energy and the randomness of flexible loads such as a large number of electric vehicles. It is urgent to propose an indicator that can take into account the impact of renewable energy and electric vehicles on the power grid to define the weak strength of the power grid and conduct qualitative analysis.

[0015] With the influx of intermittent power sources, such as large-scale renewable energy, into the power system, as well as the influx of random loads, such as electric vehicles, the power system has been significantly impacted on both the power supply and load sides, posing greater challenges to grid operation. In the face of intermittent power sources and random loads in the grid, determining the strength of related lines has become a crucial issue. Summary of the Invention

[0016] The purpose of the present invention is to provide a method, device, equipment and medium for judging the weakness of power grid lines. By analyzing the impact of disconnecting power grid lines as samples, the voltage amplitude and phase angle of all nodes in the power grid, as well as the active power, reactive power and load rate of all lines are input, and an artificial neural network is used to judge the impact of disconnecting the lines, thereby realizing the judgment of the impact degree of the power grid.

[0017] In order to achieve the above object, the present invention adopts the following technical solutions:

[0018] In a first aspect, the present invention provides a method for determining the weakness of a power grid line, characterized by comprising:

[0019] Obtain the power flow data of the target power grid;

[0020] A line in the target power grid is selected, and the voltage phase angles and amplitudes of all nodes in the target power grid, as well as the power flows and load rates on all lines except the selected line, are input into a pre-established deep graph convolutional neural network model for the selected line to obtain the vulnerability index of the selected line. All lines in the target power grid are traversed to obtain the line vulnerability index of all lines.

[0021] Sort the weakness indicators of all lines in the target power grid to determine the weakness of the power grid lines.

[0022] A further improvement of the present invention is that the flow data of the target power grid includes: the voltage phase angle and amplitude of all nodes of the target power grid, and the flow and load rate on all lines; the flow on the line specifically includes the active power and reactive power of the line.

[0023] A further improvement of the present invention is that the process of establishing the pre-established deep graph convolutional neural network model includes:

[0024] The selected lines in the target power grid are disconnected, and the short-circuit capacity of all new energy access and electric vehicle access points is calculated as the dividend. The real-time power of the collected new energy power stations and electric vehicles is used as the divisor. The ratio of the two is calculated to obtain the short-circuit ratio of the access point, and the short-circuit ratio is sorted, the minimum value is taken, and the normalized value is rounded off as the output quantity of the weakness judgment; the voltage amplitude and phase angle of all nodes in the target power grid, as well as the active power, reactive power and load rate of all lines outside the selected line are used as input, and the deep graph convolutional neural network model of the selected line is obtained through neural network training.

[0025] A further improvement of the present invention is that, in the determination of the degree of weakness:

[0026] If the discriminant value of the line weakness is 1, it means that the corresponding line cannot be disconnected under the target power grid;

[0027] If the discrimination value of the line weakness is 2, it means that under the target power grid, the power of renewable energy or electric vehicles on the corresponding line should be reduced;

[0028] If the discrimination value of the line weakness is 3, it means that the corresponding line can be disconnected under the target power grid.

[0029] In a second aspect, the present invention provides a device for determining the weakness of a power grid line, comprising:

[0030] An acquisition module is used to obtain the flow data of the target power grid;

[0031] The calculation module is used to select a line in the target power grid, take the voltage phase angle and amplitude of all nodes in the target power grid in the power flow data, as well as the power flow and load rate of all lines except the selected line as input, input them into the pre-established deep graph convolutional neural network model of the selected line, and obtain the line weakness index of the selected line; traverse all lines in the target power grid to obtain the line weakness index of all lines;

[0032] The sorting module is used to sort the weakness indicators of all lines of the target power grid and complete the judgment of the weakness of the power grid lines.

[0033] A further improvement of the present invention is that the flow data of the target power grid includes: the voltage phase angle and amplitude of all nodes of the target power grid, and the flow and load rate on all lines; the flow on the line specifically includes the active power and reactive power of the line.

[0034] A further improvement of the present invention is that the process of establishing the pre-established deep graph convolutional neural network model includes:

[0035] The selected lines in the target power grid are disconnected, and the short-circuit capacity of all new energy access and electric vehicle access points is calculated as the dividend. The real-time power of the collected new energy power stations and electric vehicles is used as the divisor. The ratio of the two is calculated to obtain the short-circuit ratio of the access point, and the short-circuit ratio is sorted, the minimum value is taken, and the normalized value is rounded off as the output quantity of the weakness judgment; the voltage amplitude and phase angle of all nodes in the target power grid, as well as the active power, reactive power and load rate of all lines outside the selected line are used as input, and the deep graph convolutional neural network model of the selected line is obtained through neural network training.

[0036] A further improvement of the present invention is that, in the determination of the degree of weakness:

[0037] If the discriminant value of the line weakness is 1, it means that the corresponding line cannot be disconnected under the target power grid;

[0038] If the discrimination value of the line weakness is 2, it means that under the target power grid, the power of renewable energy or electric vehicles on the corresponding line should be reduced;

[0039] If the discrimination value of the line weakness is 3, it means that the corresponding line can be disconnected under the target power grid.

[0040] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the method for determining the degree of weakness of a power grid line.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for determining the weakness of a power grid line is implemented.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention provides a method, device, equipment and medium for determining the weakness of power grid lines. The method takes the voltage and current of the target power grid as input and the normalized short-circuit ratio of the corresponding nodes of the electric vehicles with intermittent new energy and random loads under the disconnected lines as output, thereby realizing the classification of the strength of the lines in a given scenario. On the one hand, the present invention binds the scenario with the weakness of the line, and on the other hand, takes into account the influence of intermittent new energy and random electric vehicle loads, and can well evaluate the operating status of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which constitute part of the present invention, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 Schematic diagram of the training process of the deep graph convolutional neural network model;

[0046] Figure 2 A schematic flow chart of a method for determining the weakness of a power grid line according to the present invention;

[0047] Figure 3 This is a schematic structural diagram of a device for determining the weakness of a power grid line according to the present invention;

[0048] Figure 4 This is a structural block diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0049] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other.

[0050] The following detailed description is an exemplary description and is intended to provide further detailed description of the present invention. Unless otherwise indicated, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0051] Example 1

[0052] The present invention proposes a method for determining the degree of weakness of power grid lines. The method takes the voltage amplitude and phase angle of all nodes in the power grid, as well as the active power, reactive power and load rate of all lines as input, and takes the impact of line interruption on the power grid defined by the short-circuit ratio as output. The method utilizes an artificial neural network to determine the degree of weakness of the power grid lines.

[0053] The present invention is divided into two steps: the first step is training, which involves disconnecting the studied line and calculating the short-circuit capacity of the new energy access and electric vehicle access points as the dividend. The real-time power of the collected new energy power station and electric vehicle is used as the divisor, and the ratio of the two is calculated to obtain the short-circuit ratio of these access points. The short-circuit ratio is then sorted, the minimum value is taken, and the whole value is normalized and rounded as the output of the weak degree discriminant. The voltage amplitude and phase angle of all nodes in the power grid at this time, as well as the active power, reactive power, and load rate of all lines are then used as inputs. The neural network is trained to obtain a deep graph convolutional neural network model. The second step is identification. The voltage amplitude and phase angle of all nodes in the power grid, as well as the active power, reactive power, and load rate of all lines are used as inputs. The input deep graph convolutional neural network model can output the corresponding weak degree of this line under the current model.

[0054] See also Figure 1 As shown in FIG, the training method of the deep graph convolutional neural network model for target power grid line weakness discrimination includes:

[0055] S11, selecting a target power grid, selecting a line in the target power grid, and disconnecting the selected line;

[0056] S12. Under the target grid topology, calculate the short-circuit capacity of all nodes connected to renewable energy sources and electric vehicles;

[0057] S13, selecting a power flow section and collecting renewable energy power and electric vehicle power at each node;

[0058] S14, using the short-circuit capacity as the dividend and the renewable energy power or electric vehicle power at each node as the divisor, to calculate the actual output short-circuit ratio of the renewable energy or electric vehicle at each node;

[0059] S15. Sort all obtained short-circuit ratios, take the minimum value, and normalize (defined as 3 if greater than 3, 2 if between 2 and 3, and 1 if less than 2). This represents the vulnerability of this line to the current power flow under the topology under consideration. A value of 1 indicates very weak; a value of 2 indicates weak; and a value of 3 indicates strong. A strong value indicates that disconnecting the line will have little impact on the grid; a weak value indicates the need to reduce the power of renewable energy or electric vehicles; and a very weak value indicates system instability and that the line cannot be disconnected under this topology.

[0060] S16. Check whether the flow sample is sufficient under the disconnected line. If not, go to S12. If sufficient, go to the next step.

[0061] S17, check whether all circuits are disconnected. If not, go to S11. After all circuits are disconnected, go to the next step.

[0062] S18. For each line, the voltage phase angle and amplitude of all nodes in the power grid, as well as the flow and load rate on all lines except this line are used as input, and the normalized short-circuit ratio is calculated as output. The deep graph convolutional neural network is used for training to obtain a deep graph convolutional neural network model for each line; the training of the model is completed.

[0063] In a specific embodiment, the neural network may be a convolutional neural network or a BP neural network.

[0064] See also Figure 2 As shown, the method for determining the line weakness in the target power grid includes the following steps:

[0065] S21. Select the target power grid and import the scenario to be identified, mainly the power flow data, including the voltage phase angle and amplitude of all nodes in the power grid, as well as the power flow and load rate of all lines, as input;

[0066] S22. Select a route and determine the corresponding trained deep graph convolutional neural network model based on the route;

[0067] S23. The voltage phase angle and amplitude of all nodes in the power grid, as well as the flow and load rate information on all lines except this line are used as input. The corresponding weakness index is obtained through the deep graph convolutional neural network model. Among them, very weak is 1, indicating that the corresponding line is very important and cannot be disconnected in the current scenario; weak is 2, indicating that the line is relatively important and the power of the connected new energy or electric vehicles needs to be reduced in the current scenario; strong is 3, indicating that the line is not very important and can be disconnected in the current scenario.

[0068] S24, check whether all lines have been identified. If not, go to S22. If identification is completed, go to the next step.

[0069] S25. Sort the weakness of all lines to complete the identification.

[0070] The present invention proposes an artificial neural network method for distinguishing the weakness of power grid lines. The method takes the flow data of nodes and lines in the power grid scenario as input, and uses the real-time short-circuit ratio (normalized) of intermittent new energy and random electric vehicle loads after the line is disconnected as output. The method realizes the distinction through identification by artificial neural network.

[0071] Example 2

[0072] See also Figure 3 As shown, the present invention provides a device for determining the weakness of a power grid line, comprising:

[0073] An acquisition module is used to obtain the flow data of the target power grid;

[0074] The calculation module is used to select a line in the target power grid, take the voltage phase angle and amplitude of all nodes in the target power grid in the power flow data, as well as the power flow and load rate of all lines except the selected line as input, input them into the pre-established deep graph convolutional neural network model of the selected line, and obtain the line weakness index of the selected line; traverse all lines in the target power grid to obtain the line weakness index of all lines;

[0075] The sorting module is used to sort the weakness indicators of all lines of the target power grid and complete the judgment of the weakness of the power grid lines.

[0076] In a specific embodiment, the target power grid flow data obtained includes: voltage phase angles and amplitudes of all nodes in the target power grid, and flow and load rates on all lines; the flow on the line specifically includes active power and reactive power of the line.

[0077] In a specific embodiment, the process of establishing the pre-established deep graph convolutional neural network model includes:

[0078] The selected lines in the target power grid are disconnected, and the short-circuit capacity of all new energy access and electric vehicle access points is calculated as the dividend. The real-time power of the collected new energy power stations and electric vehicles is used as the divisor. The ratio of the two is calculated to obtain the short-circuit ratio of the access point, and the short-circuit ratio is sorted, the minimum value is taken, and the normalized value is rounded off as the output quantity of the weakness judgment; the voltage amplitude and phase angle of all nodes in the target power grid, as well as the active power, reactive power and load rate of all lines outside the selected line are used as input, and the deep graph convolutional neural network model of the selected line is obtained through neural network training.

[0079] In a specific embodiment, the weakness level determination metric is:

[0080] If the discriminant value of the line weakness is 1, it means that the corresponding line cannot be disconnected under the target power grid;

[0081] If the discrimination value of the line weakness is 2, it means that under the target power grid, the power of renewable energy or electric vehicles on the corresponding line should be reduced;

[0082] If the discrimination value of the line weakness is 3, it means that the corresponding line can be disconnected under the target power grid.

[0083] Example 3

[0084] See also Figure 4As shown, this embodiment provides an electronic device 100; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0085] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the method for determining the weakness of a power grid line described in Example 1 by running or executing the computer program stored in the memory 101 and accessing the data stored in the memory 101. The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data (such as audio data) generated based on the use of the electronic device 100. In addition, the memory 101 may include non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0086] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 using various interfaces and lines.

[0087] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for determining the degree of weakness of a power grid line. The processor 102 may execute the plurality of instructions to implement:

[0088] Obtain the power flow data of the target power grid;

[0089] A line in the target power grid is selected, and the voltage phase angles and amplitudes of all nodes in the target power grid, as well as the power flows and load rates on all lines except the selected line, are input into a pre-established deep graph convolutional neural network model for the selected line to obtain the vulnerability index of the selected line. All lines in the target power grid are traversed to obtain the line vulnerability index of all lines.

[0090] Sort the weakness indicators of all lines in the target power grid to determine the weakness of the power grid lines.

[0091] Example 4

[0092] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0093] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0094] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for determining the weakness of a power grid line, characterized in that: include: Obtain the power flow data of the target power grid; A line in the target power grid is selected, and the voltage phase angles and amplitudes of all nodes in the target power grid, as well as the power flows and load rates of all lines except the selected line, are input into a pre-established deep graph convolutional neural network model for the selected line to obtain the vulnerability index of the selected line. Traverse all lines of the target power grid and obtain line weakness indicators of all lines; Sort the vulnerability indicators of all lines in the target power grid to determine the vulnerability of the power grid lines; The target power grid flow data obtained includes: voltage phase angles and amplitudes of all nodes in the target power grid, and flow and load rates on all lines; the flow on the line specifically includes active power and reactive power of the line; The process of establishing the pre-established deep graph convolutional neural network model includes: The selected lines in the target power grid are disconnected, and the short-circuit capacity of all new energy access and electric vehicle access points is calculated as the dividend. The real-time power of the collected new energy power stations and electric vehicles is used as the divisor. The ratio of the two is calculated to obtain the short-circuit ratio of the access point, and the short-circuit ratio is sorted, the minimum value is taken, and the normalized value is rounded off as the output quantity of the weakness judgment; the voltage amplitude and phase angle of all nodes in the target power grid, as well as the active power, reactive power and load rate of all lines outside the selected line are used as input, and the deep graph convolutional neural network model of the selected line is obtained through neural network training.

2. The method for determining the weakness of a power grid line according to claim 1, characterized in that: Among the criteria for determining the degree of weakness: If the discriminant value of the line weakness is 1, it means that the corresponding line cannot be disconnected under the target power grid; If the discrimination value of the line weakness is 2, it means that under the target power grid, the power of renewable energy or electric vehicles on the corresponding line should be reduced; If the discrimination value of the line weakness is 3, it means that the corresponding line can be disconnected under the target power grid.

3. A device for determining the weakness of a power grid line, characterized in that: include: An acquisition module is used to obtain the flow data of the target power grid; A calculation module is used to select a line in the target power grid, take the voltage phase angle and amplitude of all nodes in the target power grid in the power flow data, as well as the power flow and load rate of all lines except the selected line as input, input them into the pre-established deep graph convolutional neural network model of the selected line, and obtain the vulnerability index of the selected line; Traverse all lines of the target power grid and obtain line weakness indicators of all lines; The sorting module is used to sort the vulnerability indicators of all lines in the target power grid and determine the vulnerability of the power grid lines; The target power grid flow data obtained includes: voltage phase angles and amplitudes of all nodes in the target power grid, and flow and load rates on all lines; the flow on the line specifically includes active power and reactive power of the line; The process of establishing the pre-established deep graph convolutional neural network model includes: The selected lines in the target power grid are disconnected, and the short-circuit capacity of all new energy access and electric vehicle access points is calculated as the dividend. The real-time power of the collected new energy power stations and electric vehicles is used as the divisor. The ratio of the two is calculated to obtain the short-circuit ratio of the access point, and the short-circuit ratio is sorted, the minimum value is taken, and the normalized value is rounded off as the output quantity of the weakness judgment; the voltage amplitude and phase angle of all nodes in the target power grid, as well as the active power, reactive power and load rate of all lines outside the selected line are used as input, and the deep graph convolutional neural network model of the selected line is obtained through neural network training.

4. The device for determining the weakness of a power grid line according to claim 3, characterized in that: Among the criteria for determining the degree of weakness: If the discriminant value of the line weakness is 1, it means that the corresponding line cannot be disconnected under the target power grid; If the discrimination value of the line weakness is 2, it means that under the target power grid, the power of renewable energy or electric vehicles on the corresponding line should be reduced; If the discrimination value of the line weakness is 3, it means that the corresponding line can be disconnected under the target power grid.

5. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the method for determining the weakness of a power grid line as claimed in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for determining the weakness of a power grid line according to any one of claims 1 to 2 is implemented.

Images