Energy internet voltage control method and system based on intelligent agent power demand

Abstract

This invention belongs to the field of power grid operation technology, and discloses a voltage control method and system for an energy internet based on intelligent agent power demand. The method includes: obtaining the power demand of a preset category of equipment in the power grid portion of the target energy internet at a certain moment; accumulating the power demand of each category of equipment at a certain moment, inputting it into a corresponding trained graph convolutional artificial neural network to obtain a preset number of reactive power configuration schemes; and concatenating the preset number of reactive power configuration schemes to obtain the reactive power configuration scheme corresponding to the entire power grid portion. This invention can fully utilize existing historical data and find matching reactive power configuration schemes by analyzing the power of relevant power grid equipment. It can quickly match historical data and effectively achieve reasonable voltage control for the energy internet.

Description

Technical Field

[0001] This invention belongs to the field of power grid operation technology, and specifically relates to a voltage control method and system for the energy internet based on intelligent agent power demand. Background Technology

[0002] The Energy Internet can be understood as a network that comprehensively utilizes advanced power electronics, information technology, and intelligent management technology to interconnect a large number of energy nodes, such as power networks, oil networks, and natural gas networks, consisting of distributed energy harvesting devices, distributed energy storage devices, and various types of loads, to achieve bidirectional energy flow, peer-to-peer energy exchange, and sharing. It can be seen that the key to the Energy Internet is interconnecting energy systems through power networks, with the power network acting as a "medium" for interaction with other energy forms. Therefore, meeting power demand and related voltage control are crucial to its stable operation.

[0003] In typical energy internet systems, the introduction of numerous distributed energy sources, such as photovoltaics, can lead to issues. The randomness and uncertainty of these distributed energy sources' output, as well as their mismatch with loads, all impact system voltage. The randomness of their installation locations can alter power flow, thus affecting the stable operation of the grid within the energy internet. Currently, a common approach is to comprehensively consider available reactive power sources within the system and optimize node voltage adjustments by setting objective functions, equality constraints, and inequality constraints. However, with the increasing complexity and diversification of energy internet equipment and its operational modes, optimization schemes may become trapped in local optima or even fail to achieve optimal results. Summary of the Invention

[0004] The purpose of this invention is to provide a voltage control method and system for the energy internet based on intelligent agent power demand, which can quickly match historical data and effectively achieve reasonable voltage control for the energy internet.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a voltage control method for an energy internet based on intelligent agent power demand, comprising:

[0007] Obtain the power demand of a preset category of equipment in the power grid section of the target energy internet at a certain moment;

[0008] The power demand of each type of equipment at a certain moment is accumulated and input into the corresponding trained graph convolutional artificial neural network to obtain the reactive power configuration schemes corresponding to the preset categories.

[0009] By concatenating the corresponding reactive power configuration schemes of the preset categories, the reactive power configuration schemes corresponding to the entire power grid are obtained.

[0010] A further improvement of the present invention is that it also includes verifying the configuration scheme, and if it is reasonable, outputting the reactive power configuration scheme corresponding to the entire power grid section.

[0011] A further improvement of the present invention is that the preset category of equipment includes four categories, namely power generation equipment, load equipment, power transmission equipment, and equipment that interacts with other types of energy.

[0012] A further improvement of the present invention is that the device for power interaction with other types of energy is an electrothermal coupling device or a geothermal device.

[0013] A further improvement of this invention is that the trained graph convolutional artificial neural network is obtained through the following steps:

[0014] Historical data of selected grid segments in the target energy internet is obtained, and devices are classified into preset categories in the form of intelligent agents; the power of devices in preset categories and the corresponding reactive power configuration schemes of the grid are extracted from the historical data.

[0015] At the same time, the power data corresponding to the intelligent agents representing different types of devices are accumulated, and the corresponding reactive power configuration schemes of the power grid are also accumulated to obtain the reactive power configuration scheme of the power grid after the preset categories are accumulated.

[0016] Based on the per-unit voltage value, the range from 0.97 to 1.07 is divided into 10 intervals at 10% increments: [0.97-0.98], (0.98-0.99]...(1.06-1.07].

[0017] Select a voltage range from 10 ranges. If at a certain moment the voltage of more than 80% of the devices handled by the intelligent agent is within the selected voltage range, the cumulative reactive power configuration scheme of the power grid at the corresponding moment is taken as a typical scheme.

[0018] Determine whether the typical schemes for all agents in all intervals have been selected. If they have, for each agent, input the reactive power configuration scheme corresponding to the typical scheme and the cumulative power data of each device into the graph convolutional artificial neural network for training, and obtain the graph convolutional artificial neural network trained for the corresponding agent.

[0019] Secondly, the present invention provides an energy internet voltage control system based on intelligent agent power demand, comprising:

[0020] The acquisition module is used to acquire the power demand of a preset category of equipment in the power grid section of the target energy internet at a certain moment;

[0021] The calculation module is used to accumulate the power demand of each type of equipment at a certain moment, input it into the corresponding trained graph convolutional artificial neural network, and obtain the reactive power configuration schemes corresponding to the preset categories.

[0022] The output module is used to concatenate the corresponding reactive power configuration schemes of the preset categories to obtain the reactive power configuration schemes corresponding to the entire power grid.

[0023] A further improvement of the present invention is that the output module is also used to verify the configuration scheme, and if it is reasonable, output the reactive power configuration scheme corresponding to the entire power grid.

[0024] A further improvement of the present invention is that the preset category of equipment includes four categories, namely power generation equipment, load equipment, power transmission equipment, and equipment that interacts with other types of energy.

[0025] A further improvement of the present invention is that the device for power interaction with other types of energy is an electrothermal coupling device or a geothermal device.

[0026] A further improvement of this invention is that the trained graph convolutional artificial neural network is obtained through the following steps:

[0027] Historical data of selected grid segments in the target energy internet is obtained, and devices are classified into preset categories in the form of intelligent agents; the power of devices in preset categories and the corresponding reactive power configuration schemes of the grid are extracted from the historical data.

[0028] At the same time, the power data corresponding to the intelligent agents representing different types of devices are accumulated, and the corresponding reactive power configuration schemes of the power grid are also accumulated to obtain the reactive power configuration scheme of the power grid after the preset categories are accumulated.

[0029] Based on the per-unit voltage value, the range from 0.97 to 1.07 is divided into 10 intervals at 10% increments: [0.97-0.98], (0.98-0.99]...(1.06-1.07].

[0030] Select a voltage range from 10 ranges. If at a certain moment the voltage of more than 80% of the devices handled by the intelligent agent is within the selected voltage range, the cumulative reactive power configuration scheme of the power grid at the corresponding moment is taken as a typical scheme.

[0031] Determine whether the typical schemes for all agents in all intervals have been selected. If they have, for each agent, input the reactive power configuration scheme corresponding to the typical scheme and the cumulative power data of each device into the graph convolutional artificial neural network for training, and obtain the graph convolutional artificial neural network trained for the corresponding agent.

[0032] Thirdly, the present invention provides an electronic device including a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the aforementioned energy internet voltage control method based on intelligent agent power demand.

[0033] Fourthly, the present invention provides a computer-readable storage medium storing at least one instruction that, when executed by a processor, implements the energy internet voltage control method based on intelligent agent power demand.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] This invention provides a voltage control method and system for the energy internet based on intelligent proxy power demand. It can fully utilize existing historical data and find matching reactive power configuration schemes by analyzing the power of relevant power grid equipment. It can quickly match data using historical data, effectively achieving reasonable voltage control for the energy internet.

[0036] This invention uses multiple intelligent agents to replace different types of equipment. It uses historical data to analyze typical reactive power configuration schemes and power relationships in multiple intelligent agents, and obtains an analysis model through convolutional artificial neural networks. Given the power demand of the energy internet power grid, it can quickly obtain relevant reactive power configuration schemes. Attached Figure Description

[0037] The accompanying drawings, which form part of this specification, 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 undue limitation of the invention. In the drawings:

[0038] Figure 1 This is a schematic diagram illustrating the training steps of a graph-based convolutional artificial neural network.

[0039] Figure 2 This is a schematic diagram of the recognition steps of a graph convolutional artificial neural network.

[0040] Figure 3 This is a flowchart illustrating a voltage control method for an energy internet based on intelligent agent power demand according to the present invention.

[0041] Figure 4 This is a structural block diagram of an energy internet voltage control device based on intelligent agent power demand according to the present invention.

[0042] Figure 5 This is a structural block diagram of an electronic device according to the present invention. Detailed Implementation

[0043] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0044] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this invention is for describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0045] In the energy internet, the power grid is a crucial link, serving as the "medium" and pipeline for various energy interactions. The integration of renewable energy generation, DC transmission, and electric vehicles into this grid has led to increasingly sophisticated power electronics, making the system's operation more complex. This places higher demands on voltage and power flow control, both in terms of accuracy and timeliness. This invention proposes an energy internet voltage control method based on intelligent agent power demand. It represents relevant power generation, consumption, and transmission processes as intelligent agents, categorized by type. Historical data is used to obtain the correspondence between the power demands (generation, consumption, or losses) of these representative energy internet devices and the reactive power configuration schemes in the power grid. A corresponding analytical model is established using a graph convolutional artificial neural network. Thus, for the current energy internet, by using real-time data collected from various devices and load demands as input, the corresponding reactive power configuration scheme can be obtained, achieving reactive power control objectives quickly and efficiently without complex and time-consuming calculations.

[0046] Example 1

[0047] This invention proposes a voltage control method for the energy internet based on intelligent agent power demand. It studies the grid voltage configuration scheme in the energy internet, and uses an intelligent agent to reflect the power demand (power generation, power consumption, or loss) of similar equipment. By utilizing the corresponding reactive power configuration scheme in historical data, a corresponding analysis model is established through graph convolutional artificial neural network to achieve the purpose of identifying reactive power configuration scheme through real-time data collection.

[0048] The present invention provides a voltage control method for the energy internet based on intelligent agent power demand, which mainly consists of two parts. The first part is to construct sufficient samples using historical data and establish a graph convolutional artificial neural network analysis model. The second part is to use the collected data to input into the established graph convolutional artificial neural network analysis model to identify the state of the system and obtain the required reactive power configuration and voltage control scheme.

[0049] The first part, and its key focus, is the construction of samples using historical data. The proposed construction method and artificial intelligence training framework are as follows: Figure 1 As shown. The specific steps include:

[0050] S101. For the target energy internet, select the power grid portion.

[0051] S102. Construct intelligent agent agents. For the selected types of equipment in the power grid, the equipment is divided into four categories in the form of intelligent agent agents: power generation, load, power transmission, and equipment that interacts with other types of energy. In a specific implementation, the equipment that interacts with other types of energy can be electrothermal coupling, geothermal, etc. For each of the four types of equipment, an intelligent agent is constructed, and finally four intelligent agents are constructed.

[0052] S103. Obtain historical data of the selected power grid portion in the target energy internet, extract the corresponding power generation, load, transmission, and power interaction with other types of energy from the historical data, as well as the corresponding reactive power configuration scheme of the power grid.

[0053] S104. At the same time, the power data corresponding to the intelligent agents representing different types of devices are accumulated (power generation, load, transmission and interaction with other types of energy), and the corresponding reactive power configuration schemes of the power grid are also accumulated to obtain four types of accumulated reactive power configuration schemes of the power grid.

[0054] S105. Divide the voltage per-unit value into 10 intervals from 0.97 to 1.07, with each interval representing 10%: [0.97-0.98], (0.98-0.99]...(1.06-1.07].

[0055] S106. Select a voltage range from the 10 ranges. If at a certain moment the voltage of more than 80% of the devices handled by the intelligent agent is within the selected voltage range, the cumulative reactive power configuration scheme of the power grid at the corresponding moment is a typical scheme.

[0056] S107. Determine whether the typical solutions for all agents in all intervals have been selected. If not, return to S106; if not, proceed to the next step. For each voltage interval, obtain several typical solutions corresponding to 4 agents to obtain training samples.

[0057] S108. For each agent, the reactive power configuration scheme corresponding to the typical solution and the accumulated power data of each device are input into the graph convolutional artificial neural network for training, resulting in the graph convolutional artificial neural network trained for the corresponding agent. Finally, four graph convolutional artificial neural networks trained for different agents are obtained.

[0058] Part Two: Steps for determining reactive power configuration schemes through model building, as follows Figure 2 As shown.

[0059] S201. For the target energy internet, select the power grid section; obtain the power demand of four types of equipment (power generation, load, transmission, and power interaction with other types of energy) in the power grid section at a certain moment;

[0060] S202. Accumulate the power demand of each type of equipment at a certain moment, input it into the graph convolutional artificial neural network trained by the corresponding agent, and obtain the reactive power configuration schemes for the four types of equipment.

[0061] S203. Concatenate the reactive power configuration schemes corresponding to the four types of equipment to obtain the reactive power configuration scheme corresponding to the entire power grid; check whether the configuration scheme is reasonable. If it is not reasonable, exclude the current scheme; if it is reasonable, output the reactive power configuration scheme corresponding to the entire power grid to complete the identification.

[0062] Example 2

[0063] Please see Figure 3 As shown, this invention provides a voltage control method for an energy internet based on intelligent agent power demand, comprising:

[0064] S1. Obtain the power demand of a preset category of equipment in the power grid section of the target energy internet at a certain moment;

[0065] S2. Accumulate the power demand of each type of equipment at a certain moment, input it into the corresponding trained graph convolutional artificial neural network, and obtain the reactive power configuration schemes corresponding to the preset categories.

[0066] S3. Combine the preset categories and corresponding reactive power configuration schemes to obtain the reactive power configuration schemes for the entire power grid.

[0067] In one specific implementation, the configuration scheme is checked, and if it is reasonable, the reactive power configuration scheme corresponding to the entire power grid is output.

[0068] In one specific embodiment, the preset category of equipment includes four categories: power generation equipment, load equipment, power transmission equipment, and equipment that interacts with other types of energy.

[0069] In one specific embodiment, the device that interacts with other types of energy is an electrothermal coupling device or a geothermal device.

[0070] In one specific implementation, the trained graph convolutional artificial neural network is obtained through the following steps:

[0071] Historical data of selected grid segments in the target energy internet is obtained, and devices are classified into preset categories in the form of intelligent agents; the power of devices in preset categories and the corresponding reactive power configuration schemes of the grid are extracted from the historical data.

[0072] At the same time, the power data corresponding to the intelligent agents representing different types of devices are accumulated, and the corresponding reactive power configuration schemes of the power grid are also accumulated to obtain the reactive power configuration scheme of the power grid after the preset categories are accumulated.

[0073] Based on the per-unit voltage value, the range from 0.97 to 1.07 is divided into 10 intervals at 10% increments: [0.97-0.98], (0.98-0.99]...(1.06-1.07].

[0074] Select a voltage range from 10 ranges. If at a certain moment the voltage of more than 80% of the devices handled by the intelligent agent is within the selected voltage range, the cumulative reactive power configuration scheme of the power grid at the corresponding moment is taken as a typical scheme.

[0075] Determine whether the typical schemes for all agents in all intervals have been selected. If they have, for each agent, input the reactive power configuration scheme corresponding to the typical scheme and the cumulative power data of each device into the graph convolutional artificial neural network for training, and obtain the graph convolutional artificial neural network trained for the corresponding agent.

[0076] Example 3

[0077] Please see Figure 4 As shown, the present invention provides an energy internet voltage control system based on intelligent agent power demand, comprising:

[0078] The acquisition module is used to acquire the power demand of a preset category of equipment in the power grid section of the target energy internet at a certain moment;

[0079] The calculation module is used to accumulate the power demand of each type of equipment at a certain moment, input it into the corresponding trained graph convolutional artificial neural network, and obtain the reactive power configuration schemes corresponding to the preset categories.

[0080] The output module is used to concatenate the corresponding reactive power configuration schemes of the preset categories to obtain the reactive power configuration schemes corresponding to the entire power grid.

[0081] In one specific implementation, the configuration scheme is checked, and if it is reasonable, the reactive power configuration scheme corresponding to the entire power grid is output.

[0082] In one specific embodiment, the preset category of equipment includes four categories: power generation equipment, load equipment, power transmission equipment, and equipment that interacts with other types of energy.

[0083] In one specific embodiment, the device that interacts with other types of energy is an electrothermal coupling device or a geothermal device.

[0084] In one specific implementation, the trained graph convolutional artificial neural network is obtained through the following steps:

[0085] Historical data of selected grid segments in the target energy internet is obtained, and devices are classified into preset categories in the form of intelligent agents; the power of devices in preset categories and the corresponding reactive power configuration schemes of the grid are extracted from the historical data.

[0086] At the same time, the power data corresponding to the intelligent agents representing different types of devices are accumulated, and the corresponding reactive power configuration schemes of the power grid are also accumulated to obtain the reactive power configuration scheme of the power grid after the preset categories are accumulated.

[0087] Based on the per-unit voltage value, the range from 0.97 to 1.07 is divided into 10 intervals at 10% increments: [0.97-0.98], (0.98-0.99]...(1.06-1.07].

[0088] Select a voltage range from 10 ranges. If at a certain moment the voltage of more than 80% of the devices handled by the intelligent agent is within the selected voltage range, the cumulative reactive power configuration scheme of the power grid at the corresponding moment is taken as a typical scheme.

[0089] Determine whether the typical schemes for all agents in all intervals have been selected. If they have, for each agent, input the reactive power configuration scheme corresponding to the typical scheme and the cumulative power data of each device into the graph convolutional artificial neural network for training, and obtain the graph convolutional artificial neural network trained for the corresponding agent.

[0090] Example 4

[0091] Please see Figure 5 As shown, the present invention also provides an electronic device 100 for implementing a voltage control method for an energy internet based on intelligent agent power demand; 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 energy internet voltage control method based on intelligent agent power demand as described in Embodiment 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 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, 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 (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. The processor 102 may be a microprocessor or any conventional processor. The processor 102 is the control center of the electronic device 100, connecting various parts of the electronic device 100 via various interfaces and lines.

[0094] The memory 101 in the electronic device 100 stores multiple instructions to implement an energy internet voltage control method based on intelligent agent power demand, and the processor 102 can execute the multiple instructions to achieve:

[0095] Obtain the power demand of a preset category of equipment in the power grid section of the target energy internet at a certain moment;

[0096] The power demand of each type of equipment at a certain moment is accumulated and input into the corresponding trained graph convolutional artificial neural network to obtain the reactive power configuration schemes corresponding to the preset categories.

[0097] By concatenating the corresponding reactive power configuration schemes of the preset categories, the reactive power configuration schemes corresponding to the entire power grid are obtained.

[0098] Example 5

[0099] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0100] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0103] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of 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, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for power grid voltage control based on intelligent agent power demand, characterized in that, include: Obtain the power demand of a preset category of equipment in the power grid section of the target energy internet at a certain moment; The power demand of each type of equipment at a certain moment is accumulated and input into the corresponding trained graph convolutional artificial neural network to obtain the reactive power configuration schemes corresponding to the preset categories. By splicing together the corresponding reactive power configuration schemes of the preset categories, the reactive power configuration schemes corresponding to the entire power grid are obtained. The preset equipment categories include four types: power generation equipment, load equipment, power transmission equipment, and equipment that interacts with other types of energy; the equipment that interacts with other types of energy is either an electrothermal coupling device or a geothermal device. The trained graph convolutional artificial neural network is obtained through the following steps: Historical data of selected grid segments in the target energy internet is obtained, and devices are classified into preset categories in the form of intelligent agents; the power of devices in preset categories and the corresponding reactive power configuration schemes of the grid are extracted from the historical data. At the same time, the power data corresponding to the intelligent agents representing different types of devices are accumulated, and the corresponding reactive power configuration schemes of the power grid are also accumulated to obtain the reactive power configuration scheme of the power grid after the preset categories are accumulated. Based on the per-unit voltage value, the range from 0.97 to 1.07 is divided into 10 intervals at 10% increments: [0.97-0.98], (0.98-0.99]...(1.06-1.07]; Select a voltage range from 10 ranges. If at a certain moment the voltage of more than 80% of the devices handled by the intelligent agent is within the selected voltage range, the cumulative reactive power configuration scheme of the power grid at the corresponding moment is taken as a typical scheme. Determine whether the typical schemes for all agents in all intervals have been selected. If they have, for each agent, input the reactive power configuration scheme corresponding to the typical scheme and the cumulative power data of each device into the graph convolutional artificial neural network for training, and obtain the graph convolutional artificial neural network trained for the corresponding agent.

2. A voltage control system for an energy internet based on intelligent proxy power demand, characterized in that, include: The acquisition module is used to acquire the power demand of a preset category of equipment in the power grid section of the target energy internet at a certain moment; The calculation module is used to accumulate the power demand of each type of equipment at a certain moment, input it into the corresponding trained graph convolutional artificial neural network, and obtain the corresponding reactive power configuration schemes for the preset categories. The output module is used to splice together the corresponding reactive power configuration schemes of the preset categories to obtain the reactive power configuration schemes corresponding to the entire power grid. The preset equipment categories include four types: power generation equipment, load equipment, power transmission equipment, and equipment that interacts with other types of energy; the equipment that interacts with other types of energy is either an electrothermal coupling device or a geothermal device. The trained graph convolutional artificial neural network is obtained through the following steps: Historical data of selected grid segments in the target energy internet is obtained, and devices are classified into preset categories in the form of intelligent agents; the power of devices in preset categories and the corresponding reactive power configuration schemes of the grid are extracted from the historical data. At the same time, the power data corresponding to the intelligent agents representing different types of devices are accumulated, and the corresponding reactive power configuration schemes of the power grid are also accumulated to obtain the reactive power configuration scheme of the power grid after the preset categories are accumulated. Based on the per-unit voltage value, the range from 0.97 to 1.07 is divided into 10 intervals at 10% increments: [0.97-0.98], (0.98-0.99]...(1.06-1.07]; Select a voltage range from 10 ranges. If at a certain moment the voltage of more than 80% of the devices handled by the intelligent agent is within the selected voltage range, the cumulative reactive power configuration scheme of the power grid at the corresponding moment is taken as a typical scheme. Determine whether the typical schemes for all agents in all intervals have been selected. If they have, for each agent, input the reactive power configuration scheme corresponding to the typical scheme and the cumulative power data of each device into the graph convolutional artificial neural network for training, and obtain the graph convolutional artificial neural network trained for the corresponding agent.

3. An electronic device, comprising: It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the energy internet voltage control method based on intelligent agent power demand as described in claim 1.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the energy internet voltage control method based on intelligent agent power demand as described in claim 1.

Images