A power grid flow control method and system based on artificial intelligence neural network

Abstract

The present invention belongs to the fields of power grid operation and artificial intelligence technology, and discloses a power grid flow control method and system based on an artificial intelligence neural network. The method comprises: obtaining flow data of a target power grid; taking the amplitude and phase angle of the voltage at all nodes of the target power grid, the active and reactive power flows of the line, and a preset change in the active power flow of the line to be controlled as input; introducing the data into a pre-trained artificial intelligence neural network model of the line to be controlled for identification to obtain the voltage difference between the two ends of the line to be controlled; and controlling the voltage difference between the first and last nodes of the line to be controlled to be equal to the voltage difference between the two ends. The present invention associates the power adjustment value of the line with the voltage difference between the two ends of the line through the artificial intelligence neural network model. When the line flow control scheme is activated, the flow optimization on the line is achieved by controlling the node voltage.

Description

Technical Field

[0001] The present invention belongs to the field of power grid operation and artificial intelligence technology, and in particular relates to a power grid current control method and system based on artificial intelligence neural network. Background Art

[0002] With the access of a large number of uncontrollable power sources and loads to the power grid, the operation status of the power grid has become increasingly uncontrollable, posing a major challenge to the safe and stable operation of the entire power system. There is an urgent need to regulate the power flow of the lines to ensure the optimal system status. Summary of the Invention

[0003] The purpose of the present invention is to provide a power grid current control method and system based on artificial intelligence neural network, which can regulate the power flow of the line and ensure the optimal system state.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] In a first aspect, the present invention provides a power grid flow control method based on an artificial intelligence neural network, comprising:

[0006] Obtain the power flow data of the target power grid;

[0007] The voltage amplitude and phase angle of all nodes in the target power grid, the active and reactive power flows of the lines, and the preset change in the active power flow of the lines to be controlled are used as inputs. These are then fed into a pre-trained artificial intelligence neural network model of the lines to be controlled for identification, and the voltage difference between the two ends of the lines to be controlled is obtained.

[0008] The voltage difference between the first-end node and the end-end node of the circuit to be controlled is controlled to be equal to the voltage difference between the two ends.

[0009] A further improvement of the present invention is that the preset variation of the active power flow of the line to be controlled is within 5% of the rated value of the active power flow of the line to be controlled.

[0010] A further improvement of the present invention is that in the step of controlling the voltage difference between the head-end node and the end node of the circuit to be controlled to be equal to the voltage difference between the two ends, under the premise that the voltage of the head-end node remains unchanged, the voltage of the end node of the circuit to be controlled is controlled so that the voltage difference between the head-end node and the end node is equal to the voltage difference between the two ends.

[0011] A further improvement of the present invention is that the control means for the voltage at the end of the line to be controlled includes one or more of capacitor group switching, reactor group switching, SVG switching, SVC switching and generator adjustment.

[0012] A further improvement of the present invention is that the steps of establishing the pre-trained artificial intelligence neural network model of the circuit to be controlled include:

[0013] Collect historical data of the target power grid, including node voltage amplitude, phase angle, line active power and reactive power;

[0014] Under the current topology of the target power grid, the collected historical data is grouped into a primary group: for each line head end, the difference between the upper and lower limits of the head end node voltage is grouped into 10% levels, and multiple primary groups are obtained;

[0015] For each line, within each primary group, the line is grouped according to a power change of 5%. Within each primary group, multiple secondary groups are obtained.

[0016] Calculate the voltage difference between the line head node and the terminal node in the secondary group. The maximum distributed voltage difference in each secondary group data is taken as the voltage difference of the corresponding secondary group as the output;

[0017] Taking the amplitude and phase angle of the node voltage corresponding to each set of secondary grouping data, the active and reactive power on the line, and the flow on the line to be optimized as input, and the voltage difference between the two ends of the line to be optimized as output, the established artificial intelligence neural network model of the line to be optimized is trained to obtain the artificial intelligence neural network model of the line to be optimized.

[0018] In a second aspect, the present invention provides a power grid flow control device based on an artificial intelligence neural network, comprising:

[0019] An acquisition module is used to obtain the flow data of the target power grid;

[0020] The identification module is used to take the amplitude and phase angle of the voltage at all nodes of the target power grid, the active and reactive power flows of the line, and the preset change in the active power flow of the line to be controlled as input; it is introduced into a pre-trained artificial intelligence neural network model of the line to be controlled for identification, and the voltage difference between the two ends of the line to be controlled is obtained;

[0021] The control module is used to control the voltage difference between the head-end node and the end-end node of the circuit to be controlled to be equal to the voltage difference between the two ends.

[0022] A further improvement of the present invention is that: in the step of controlling the voltage difference between the head-end node and the end node of the line to be controlled to be equal to the voltage difference between the two ends, under the premise that the voltage of the head-end node remains unchanged, the voltage of the end node of the line to be controlled is controlled so that the voltage difference between the head-end node and the end node is equal to the voltage difference between the two ends; and the control means for the end voltage of the line to be controlled includes one or more of capacitor bank switching, reactor bank switching, SVG switching, SVC switching and generator adjustment.

[0023] A further improvement of the present invention is that the steps of establishing the pre-trained artificial intelligence neural network model of the circuit to be controlled include:

[0024] Collect historical data of the target power grid, including node voltage amplitude, phase angle, line active power and reactive power;

[0025] Under the current topology of the target power grid, the collected historical data is grouped into a primary group: for each line head end, the difference between the upper and lower limits of the head end node voltage is grouped into 10% levels, and multiple primary groups are obtained;

[0026] For each line, within each primary group, the line is grouped according to a power change of 5%. Within each primary group, multiple secondary groups are obtained.

[0027] Calculate the voltage difference between the line head node and the terminal node in the secondary group. The maximum distributed voltage difference in each secondary group data is taken as the voltage difference of the corresponding secondary group as the output;

[0028] Taking the amplitude and phase angle of the node voltage corresponding to each set of secondary grouping data, the active and reactive power on the line, and the flow on the line to be optimized as input, and the voltage difference between the two ends of the line to be optimized as output, the established artificial intelligence neural network model of the line to be optimized is trained to obtain the artificial intelligence neural network model of the line to be optimized.

[0029] 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 power grid flow control method based on an artificial intelligence neural network.

[0030] 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 power grid flow control method based on artificial intelligence neural network is implemented.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention provides a power grid flow control method and system based on an artificial intelligence neural network. An artificial intelligence neural network model of a line to be controlled is pre-trained under different voltage levels at the line headend nodes. The artificial intelligence neural network model takes the amplitude and phase angle of the voltage of all nodes in the target power grid, the active and reactive power flows of the line, and a preset change in the active power flow of the line to be controlled as input, and uses the voltage difference between the two ends of the line to be controlled as input. The present invention associates the power adjustment value of the line with the voltage difference between the two ends of the line through the artificial intelligence neural network model. When the line flow control scheme is started, the flow optimization on the line is achieved by controlling the node voltage.

[0033] Based on the analysis of the relationship between line flow and the voltage difference between its head and terminal, the present invention proposes a power grid flow control method based on artificial intelligence neural network. On the one hand, it can make full use of historical data and avoid time-consuming global optimization; on the other hand, it can quickly achieve control of the minimum equipment by controlling limited equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] 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:

[0035] Figure 1 A single-line diagram of the line voltage drop system for static voltage analysis;

[0036] Figure 2 Schematic diagram of the process of sample acquisition and model training;

[0037] Figure 3 It is a flowchart of a power grid power flow control method based on artificial intelligence neural network;

[0038] Figure 4 This is a structural block diagram of a power grid flow control device based on artificial intelligence neural network;

[0039] Figure 5 This is a structural block diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0040] 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.

[0041] 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.

[0042] The power flow analysis of the power grid is a dynamic problem that must take into account the dynamic characteristics of the power system components. It can usually be explained using the static power flow calculation method.

[0043] See also Figure 1 The figure shows a single-line diagram of the line voltage drop system used for static voltage analysis, which is used to analyze the relationship between the power flow and voltage on the line.

[0044] In the figure, Z=R+jX is the impedance of the equivalent line, which represents the line between endpoints 1 and 2. Endpoint 1 is the starting end and endpoint 2 is the end end. S' is the power injected into endpoint 1, which is the starting end, and S" is the power injected into endpoint 2, which is the end end. LD is the output power of endpoint 2, which is equal to S' due to no other power injection; is the voltage at endpoint 1, i.e. the first end, is the voltage at terminal 2, i.e. the end, is the current on the line.

[0045] The voltage difference between the two ends can be expressed as:

[0046]

[0047] Therefore, it can be seen that the power on the line is strongly correlated with the line impedance and the node voltage. By considering the voltage difference between the two ends of the line, the power on the line can be adjusted, thereby optimizing or controlling the power flow on the line.

[0048] Example 1

[0049] The present invention proposes a power grid flow control method based on an artificial intelligence neural network. Based on a given voltage level, for each line, the voltage amplitude and project of all nodes in the power grid, the active and reactive power on the line, and the power on the line that needs to be adjusted are input. The artificial intelligence neural network is used as an analysis model to output the voltage difference that needs to be adjusted at both ends of the line, and then the node voltage adjustment method is activated to achieve power adjustment on the line.

[0050] The sample acquisition scheme and training of the present invention are as follows Figure 2 shown.

[0051] S101, collecting historical data of the target power grid, wherein the historical data includes: node voltage amplitude, phase angle, line active power, and reactive power;

[0052] S102. Under the current topology of the target power grid, the collected historical data is grouped into primary groups: for each line head end, the difference between the upper and lower limits of the node voltage is grouped into 10% levels to obtain multiple primary groups;

[0053] In a specific embodiment, the per-unit value range of the upper and lower limits of the node voltage is 0.97-1.07; the per-unit value X of the difference between the upper and lower limits of the node voltage is divided into groups of 10% at intervals of 0.01, i.e., 0.97≤X<0.98, 0.98≤X<0.99, ..., 0.96≤X≤1.07, for a total of ten groups;

[0054] S103. Check whether the analysis of the head-end nodes of all lines has been completed. If not, go to step S102. If the analysis is completed, perform secondary grouping: for each line, within the first grouping of the interval of 10% difference between the upper and lower limits of each node voltage, group according to the power change of 5% at a level. In each first grouping, obtain multiple secondary groups.

[0055] S104: Check whether all lines have been classified. If not, proceed to step S103. If analysis is complete, proceed to the next step, sorting the grouped data to obtain multiple secondary grouped data with line head node voltages within the 10% interval and line power within the 5% interval. Calculate the voltage difference between the line head node and the line end node in the secondary groupings, and then find the maximum distribution in this secondary grouping data. The value corresponding to this maximum distribution is taken as the voltage difference of the corresponding secondary grouping as the output. The maximum distribution is the data in a group of data where most of the data is located. This data is selected, and this data is called the maximum distribution.

[0056] S105. Taking the amplitude and phase angle of the node voltage corresponding to each set of secondary grouped data, the active and reactive power on the line, and the flow on the line to be optimized as input, and the voltage difference between the two ends of the line to be optimized as output, an artificial intelligence neural network model of each line of the target power grid is established through artificial intelligence neural networks such as convolution.

[0057] S106. Complete the training of the artificial intelligence neural network model for each line of the target power grid.

[0058] See also Figure 3 As shown, a power grid flow control method based on artificial intelligence neural network includes the following steps:

[0059] S1. Obtain the power flow data of the target power grid;

[0060] S2. Take the amplitude and phase angle of all node voltages, the active and reactive power flows of the line, and the required change in the active power flow of the line to be controlled (with an accuracy of 5% of the rated capacity) as input; bring them into the established artificial intelligence neural network model of the line to be controlled for identification, and obtain the voltage difference between the two ends of the line to be controlled.

[0061] S3. Based on the voltage difference between the two ends of the line to be controlled, and considering that the voltage of the first-end node of the line to be controlled remains unchanged, the voltage of the end node of the line to be controlled is controlled, and the voltage difference between the first-end node and the end node is equal to the voltage difference between the two ends calculated in step S3, so as to realize the control of the power flow on the line.

[0062] In a specific embodiment, the control means for the voltage at the end of the line to be controlled includes switching of a capacitor bank, switching of a reactor bank, switching of an SVG, switching of an SVC, or adjusting of a generator.

[0063] S4. Check the control means. If the control result is not achieved (the voltage difference between the head node and the end node is equal to the voltage difference between the two ends calculated in step S3), go to step S3 to continue control. If it is achieved, the control of the flow of the control line is completed.

[0064] Example 2

[0065] This embodiment provides a power grid power flow control method based on an artificial intelligence neural network, comprising the following steps:

[0066] Obtain the power flow data of the target power grid;

[0067] The voltage amplitude and phase angle of all nodes in the target power grid, the active and reactive power flows of the lines, and the preset change in the active power flow of the lines to be controlled are used as inputs. These are then fed into a pre-trained artificial intelligence neural network model of the lines to be controlled for identification, and the voltage difference between the two ends of the lines to be controlled is obtained.

[0068] The voltage difference between the first-end node and the end-end node of the circuit to be controlled is controlled to be equal to the voltage difference between the two ends.

[0069] In a specific implementation manner, the preset variation of the active power flow of the line to be controlled is within 5% of the rated value of the active power flow of the line to be controlled.

[0070] In a specific embodiment, in the step of controlling the voltage difference between the head node and the end node of the circuit to be controlled to be equal to the voltage difference between the two ends, under the premise that the voltage of the head node remains unchanged, the voltage of the end node of the circuit to be controlled is controlled so that the voltage difference between the head node and the end node is equal to the voltage difference between the two ends.

[0071] In a specific embodiment, the control means for the voltage at the end of the line to be controlled includes one or more of capacitor bank switching, reactor bank switching, SVG switching, SVC switching and generator adjustment.

[0072] In a specific embodiment, the steps of establishing the pre-trained artificial intelligence neural network model of the circuit to be controlled include:

[0073] Collect historical data of the target power grid, including node voltage amplitude, phase angle, line active power and reactive power;

[0074] Under the current topology of the target power grid, the collected historical data is grouped into a primary group: for each line head end, the difference between the upper and lower limits of the head end node voltage is grouped into 10% levels, and multiple primary groups are obtained;

[0075] For each line, within each primary group, the line is grouped according to a power change of 5%. Within each primary group, multiple secondary groups are obtained.

[0076] Calculate the voltage difference between the line head node and the terminal node in the secondary group. The maximum distributed voltage difference in each secondary group data is taken as the voltage difference of the corresponding secondary group as the output;

[0077] Taking the amplitude and phase angle of the node voltage corresponding to each set of secondary grouping data, the active and reactive power on the line, and the flow on the line to be optimized as input, and the voltage difference between the two ends of the line to be optimized as output, the established artificial intelligence neural network model of the line to be optimized is trained to obtain the artificial intelligence neural network model of the line to be optimized.

[0078] Example 3

[0079] See also Figure 4 As shown, the present invention provides a power grid flow control device based on artificial intelligence neural network, comprising:

[0080] An acquisition module is used to obtain the flow data of the target power grid;

[0081] The identification module is used to take the amplitude and phase angle of the voltage at all nodes of the target power grid, the active and reactive power flows of the line, and the preset change in the active power flow of the line to be controlled as input; it is introduced into a pre-trained artificial intelligence neural network model of the line to be controlled for identification, and the voltage difference between the two ends of the line to be controlled is obtained;

[0082] The control module is used to control the voltage difference between the head-end node and the end-end node of the circuit to be controlled to be equal to the voltage difference between the two ends.

[0083] In a specific embodiment, in the step of controlling the voltage difference between the head-end node and the end node of the line to be controlled to be equal to the voltage difference between the two ends, under the premise that the voltage of the head-end node remains unchanged, the voltage of the end node of the line to be controlled is controlled so that the voltage difference between the head-end node and the end node is equal to the voltage difference between the two ends; the means for controlling the end voltage of the line to be controlled includes one or more of capacitor bank switching, reactor bank switching, SVG switching, SVC switching, and generator adjustment.

[0084] In a specific embodiment, the steps of establishing the pre-trained artificial intelligence neural network model of the circuit to be controlled include:

[0085] Collect historical data of the target power grid, including node voltage amplitude, phase angle, line active power and reactive power;

[0086] Under the current topology of the target power grid, the collected historical data is grouped into a primary group: for each line head end, the difference between the upper and lower limits of the head end node voltage is grouped into 10% levels, and multiple primary groups are obtained;

[0087] For each line, within each primary group, the line is grouped according to a power change of 5%. Within each primary group, multiple secondary groups are obtained.

[0088] Calculate the voltage difference between the line head node and the terminal node in the secondary group. The maximum distributed voltage difference in each secondary group data is taken as the voltage difference of the corresponding secondary group as the output;

[0089] Taking the amplitude and phase angle of the node voltage corresponding to each set of secondary grouping data, the active and reactive power on the line, and the flow on the line to be optimized as input, and the voltage difference between the two ends of the line to be optimized as output, the established artificial intelligence neural network model of the line to be optimized is trained to obtain the artificial intelligence neural network model of the line to be optimized.

[0090] Example 4

[0091] See also Figure 5 As shown, the present invention also provides an electronic device 100 for implementing a power grid flow control method based on an artificial intelligence neural network; 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.

[0092] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the power grid power flow control method based on artificial intelligence neural network described in Example 1 or 2 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data (such as audio data) created according to the use of the electronic device 100. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0093] 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.

[0094] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a power grid flow control based on an artificial intelligence neural network, and the processor 102 can execute the plurality of instructions to implement:

[0095] Obtain the power flow data of the target power grid;

[0096] The voltage amplitude and phase angle of all nodes in the target power grid, the active and reactive power flows of the lines, and the preset change in the active power flow of the lines to be controlled are used as inputs. These are then fed into a pre-trained artificial intelligence neural network model of the lines to be controlled for identification, and the voltage difference between the two ends of the lines to be controlled is obtained.

[0097] The voltage difference between the first-end node and the end-end node of the circuit to be controlled is controlled to be equal to the voltage difference between the two ends.

[0098] Example 5

[0099] 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).

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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 The steps for the function specified in one or more boxes.

[0104] 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 power grid power flow control method based on artificial intelligence neural network, characterized in that: include: Obtain the power flow data of the target power grid; The inputs are the voltage amplitude and phase angle of all nodes in the target power grid, the active and reactive power flows of the lines, and the preset change in the active power flow of the lines to be controlled; Bring it into the pre-trained artificial intelligence neural network model of the circuit to be controlled for identification, and obtain the voltage difference between the two ends of the circuit to be controlled; Controlling the voltage difference between the first-end node and the end-end node of the circuit to be controlled to be equal to the voltage difference between the two ends; The steps of establishing the pre-trained artificial intelligence neural network model of the circuit to be controlled include: Collect historical data of the target power grid, including node voltage amplitude, phase angle, line active power and reactive power; Under the current topology of the target power grid, the collected historical data is grouped into a primary group: at the head end of each line, the difference between the upper and lower limits of the head end node voltage is grouped into 10% levels, and multiple primary groups are obtained; For each line, within each primary group, the lines are grouped according to a power change level of 5%. Within each primary group, multiple secondary groups are obtained. Calculate the voltage difference between the line head node and the terminal node in the secondary group. The maximum distributed voltage difference in each secondary group data is taken as the voltage difference of the corresponding secondary group as the output; Taking the amplitude and phase angle of the node voltage corresponding to each set of secondary grouping data, the active and reactive power on the line, and the flow on the line to be optimized as input, and the voltage difference between the two ends of the line to be optimized as output, the established artificial intelligence neural network model of the line to be optimized is trained to obtain the artificial intelligence neural network model of the line to be optimized.

2. The power grid power flow control method based on artificial intelligence neural network according to claim 1, characterized in that: The preset change in the active power flow of the line to be controlled is within 5% of the rated value of the active power flow of the line to be controlled.

3. The power grid power flow control method based on artificial intelligence neural network according to claim 1, characterized in that: In the step of controlling the voltage difference between the head node and the end node of the circuit to be controlled to be equal to the voltage difference between the two ends, under the premise that the voltage of the head node remains unchanged, the voltage of the end node of the circuit to be controlled is controlled so that the voltage difference between the head node and the end node is equal to the voltage difference between the two ends.

4. The power grid power flow control method based on artificial intelligence neural network according to claim 3 is characterized in that: The control means for the voltage at the end of the line to be controlled include one or more of capacitor group switching, reactor group switching, SVG switching, SVC switching and generator adjustment.

5. A power grid flow control device based on artificial intelligence neural network, characterized in that: include: An acquisition module is used to obtain the flow data of the target power grid; An identification module is used to take as input the amplitude and phase angle of the voltage at all nodes of the target power grid, the active and reactive power flows of the lines, and a preset change in the active power flow of the lines to be controlled; Bring it into the pre-trained artificial intelligence neural network model of the circuit to be controlled for identification, and obtain the voltage difference between the two ends of the circuit to be controlled; A control module, configured to control the voltage difference between the first-end node and the end-end node of the circuit to be controlled to be equal to the voltage difference between the two ends; The steps of establishing the pre-trained artificial intelligence neural network model of the circuit to be controlled include: Collect historical data of the target power grid, including node voltage amplitude, phase angle, line active power and reactive power; Under the current topology of the target power grid, the collected historical data is grouped into a primary group: at the head end of each line, the difference between the upper and lower limits of the head end node voltage is grouped into 10% levels, and multiple primary groups are obtained; For each line, within each primary group, the lines are grouped according to a power change level of 5%. Within each primary group, multiple secondary groups are obtained. Calculate the voltage difference between the line head node and the terminal node in the secondary group. The maximum distributed voltage difference in each secondary group data is taken as the voltage difference of the corresponding secondary group as the output; Taking the amplitude and phase angle of the node voltage corresponding to each set of secondary grouping data, the active and reactive power on the line, and the flow on the line to be optimized as input, and the voltage difference between the two ends of the line to be optimized as output, the established artificial intelligence neural network model of the line to be optimized is trained to obtain the artificial intelligence neural network model of the line to be optimized.

6. The power grid power flow control device based on artificial intelligence neural network according to claim 5, characterized in that: In the step of controlling the voltage difference between the first-end node and the end-end node of the circuit to be controlled to be equal to the voltage difference between the two ends, under the premise that the voltage of the first-end node remains unchanged, the voltage of the end-end node of the circuit to be controlled is controlled so that the voltage difference between the first-end node and the end-end node is equal to the voltage difference between the two ends; The control means for the voltage at the end of the line to be controlled include one or more of capacitor group switching, reactor group switching, SVG switching, SVC switching and generator adjustment.

7. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the power grid flow control method based on artificial intelligence neural network as described in any one of claims 1 to 4.

8. 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 the processor, the power grid power flow control method based on artificial intelligence neural network according to any one of claims 1 to 4 is implemented.

Images