Power grid data real-time topology reconstruction system and method

Abstract

The invention discloses a power grid data real-time topology reconstruction system and method, and relates to the technical field of power grids, and the system comprises a power frequency sensing module, a topology generation module, a field identification module, an information generation module, a data storage module, a data discovery module and a data forwarding module. According to the invention, information transmission and data processing are carried out by using the existing signal characteristics of the power grid, additional configuration or a complex initialization process is not needed, the technical threshold and time cost of system deployment are greatly reduced, and the limitation that traditional low-voltage general survey highly depends on manpower is changed; through real-time monitoring and dynamic topology updating, manual intervention is effectively reduced, the automation level of data acquisition and processing is improved, and human input is saved; by integrating data screening and optimal node selection functions, the timeliness and accuracy of the data are ensured, and an efficient means is provided for quickly discovering and solving the operation problem of the power distribution network.

Description

Technical Field

[0001] The present invention relates to the technical field of power grids, and in particular to a system and method for real-time topology reconstruction of power grid data. Background Art

[0002] As the core hub of electricity production and consumption, the power grid system consists of power plants, transmission and transformation lines, power distribution stations and user ends to form a complete power circulation network. Its main function is to convert primary energy in nature into electricity through power generation devices, and to deliver electricity to end users stably and efficiently through multiple links of transmission, transformation and distribution. In order to ensure the efficiency and safety of power grid operation, each link is equipped with corresponding information and control systems. These systems realize all-round management of the power production process, including real-time measurement, regulation and control of electricity, as well as fault protection, communication transmission and intelligent scheduling functions. In addition, with the popularization of smart grid technology and the application of Internet of Things technology in recent years, the automation, informationization and intelligence level of the power grid have been significantly improved, which enables the power grid to not only meet the daily electricity needs of residents and industries, but also better adapt to the access of new energy, diversified load distribution and complex regulation needs, providing technical support for building a green and intelligent energy system.

[0003] However, with the continuous development of urbanization in various provinces, the number of residential communities has been increasing, and the number of urban residents has also gradually increased, resulting in a surge in urban residents' demand for electricity. At the same time, some urban residents do not use electricity as required and privately connect lines. The emergence of these problems has increased the difficulty for power supply companies to determine the ownership of electricity meters and customer files. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to provide a real-time topology reconstruction system for power grid data to overcome the problems of the surge in electricity demand for urban residents and some users not using electricity as required or privately connecting lines.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a real-time topology reconstruction system for power grid data, which includes a power frequency perception module, a topology generation module, a field identification module, an information generation module, a data storage module, a data discovery module and a data forwarding module; the power frequency perception module is used to realize information transmission according to the position of the modulated signal; the topology generation module is used to monitor the operating status and topological changes of the nodes, scan the nodes and compare them; store, merge and distribute the topological data; support the updating and organization of the topological node archives; the field identification module is used to detect and topologically identify the user area information and generate a topological map; the information generation module is used to generate and load the substation and phase line signals; the data storage module is used to perceive data, match data and store data; the data discovery module is used to transmit the perceived data to the destination grid for storage; the data forwarding module is used to screen the data and select the best node.

[0008] As an optimal solution of the real-time topology reconstruction system for power grid data described in the present invention, wherein: constructing the power frequency sensing module means that when the power frequency voltage is THz, the current voltage and current waveform are distorted, the grid voltage and the grid fundamental wave are injected into the modulated voltage waveform, and slight distortions of the grid voltage and current waveforms are artificially generated to carry information. When no modulation is performed, the two adjacent waveforms are the same.

[0009] As a preferred solution of the real-time topology reconstruction system for power grid data described in the present invention, the topology generation module includes a topology identification slave terminal, a topology identification master terminal and a topology analysis handheld device; the topology identification master terminal sends topology information to the topology analysis handheld device for display, the data processing part mostly uses high-speed multi-channel A / D and DSP, and the data communication part mostly uses Bluetooth and USB data communication ports to directly connect to the background system or personal computer, and transmits the obtained text or data information to the system.

[0010] As a preferred solution of the real-time topology reconstruction system for power grid data described in the present invention, the field identification module includes a master terminal and a slave terminal; the master terminal is a master terminal arranged in the substation distribution transformer, the slave terminal is a slave terminal arranged on the cable branch box and the meter box side, the detection terminal is a topology identification slave terminal, and the topology identification master terminal is placed in a relatively central position in the substation to obtain the best communication success rate.

[0011] As a preferred solution of the real-time topology reconstruction system for power grid data described in the present invention, the information generating module is an important device installed on the transformer side; the information generating module is used to realize the generation and loading of substation and phase line signals, form a topology map and display it according to the topology information fed back by the topology terminal, or transmit the topology information to the topology analysis handheld device for display via Bluetooth; the information generating module is composed of transmission communication, data processing, power management, touch display control, information storage and data communication.

[0012] As a preferred solution of the real-time topology reconstruction system for power grid data of the present invention, the data storage module is composed of a sensor module, a computing module and a storage module; the sensor module is used to collect data at multiple levels, the storage module is used to sense data, and the computing module is used to match data; the data discovery module is used to send the sensed data to the destination grid for storage, and the data forwarding module is used to screen the data and select the best node.

[0013] As a preferred solution of the real-time topology reconstruction system for power grid data of the present invention, the establishment process of the topology generation module includes the following steps: realizing data reconstruction through confrontation and competition; using the generation network to update the weight bias and noise error of the production network; after the production network is balanced, the GAN converges, and the generator and discriminator in the GAN will have two corresponding objective functions; the specific formula of the objective function of the discriminator is as follows:

[0014]

[0015] Among them, LD is the objective function of the discriminator; E x is the average value of the samples; D(·) is the discriminator function; X g is the fake data generated by the network; X1 is the real data sample; x m is the intermediate sampling point between the real data and the generated data.

[0016] In the second aspect, in order to further solve the safety problems existing in the power grid, the present invention provides a method for real-time topology reconstruction of power grid data in an embodiment, which includes: obtaining power grid power frequency voltage data; establishing a topology generation module including a topology identification slave terminal, a topology identification master terminal and a topology analysis handheld device; arranging the topology identification master terminal at the distribution transformer location in the substation, and arranging the topology identification slave terminal at the cable branch box and the meter box side location; installing an information generation module on the transformer side; sending a topology identification signal through the topology identification master terminal to obtain feedback information; constructing a data storage module, including a sensor unit, a computing unit and a storage unit, to collect multi-level data; sending the data collected by the sensor unit to the destination grid storage unit through the computing unit; iteratively updating the weight bias and noise error of the generated network, and generating a topology map based on the discriminator objective function.

[0017] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the real-time topology reconstruction system for power grid data as described in the first aspect of the present invention is implemented.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the real-time topology reconstruction system for power grid data as described in the first aspect of the present invention is implemented.

[0019] Beneficial effects of the invention: The invention proposes a real-time topology reconstruction system for power grid data, which utilizes the existing signal characteristics of the power grid to transmit information and process data, without the need for additional configuration or complex initialization processes, greatly reducing the technical threshold and time cost of system deployment, and changing the limitation of traditional low-voltage census that is highly dependent on manual labor; through real-time monitoring and dynamic topology updates, it effectively reduces manual intervention, improves the automation level of data collection and processing, and significantly saves manpower investment; through the integration of data screening and optimal node selection functions, it ensures the timeliness and accuracy of the data, providing an efficient means for quickly discovering and solving distribution network operation problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0021] Figure 1 This is a flowchart for constructing a real-time topology reconstruction system for power grid data in Example 1.

[0022] Figure 2 This is a schematic diagram of the structure of the computer device in Example 3. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0024] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0025] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0026] Example 1

[0027] Reference Figure 1 , which is the first embodiment of the present invention, and provides a real-time topology reconstruction system for power grid data, including:

[0028] The power frequency sensing module, the topology generation module, the field identification module, the information generation module, the data storage module, the data discovery module and the data forwarding module are provided. Figure 1 The figure shows a flow chart for constructing a real-time topology reconstruction system for power grid data.

[0029] Preferably, the power frequency sensing module is used to realize information transmission according to the position of the modulated signal.

[0030] Specifically, building an industrial frequency sensing module means that when the industrial frequency voltage is 50Hz, the grid voltage and the grid fundamental wave are injected into the modulated voltage waveform through the current voltage and current waveform distortion, and slight distortion of the grid voltage and current waveform is artificially generated to carry information. When no modulation is performed, the two adjacent waveforms are the same.

[0031] It should be noted that the power frequency sensing module carries information by artificially generating slight distortions in the grid voltage and current waveforms near the zero-crossing point of the 50Hz power frequency voltage, and completes data transmission in the grid by modulating the voltage waveform. When the grid voltage reaches the trough, a modulated voltage waveform with the same period as the grid fundamental wave is injected into it, and only one modulated voltage waveform is injected into two adjacent voltage waveforms; when no modulation is performed, the two adjacent waveforms are the same, and the injected modulation signal obviously changes the grid voltage waveform. The power frequency sensing module can realize information transmission according to the position of the modulation signal.

[0032] Preferably, the present invention carries information by artificially generating tiny waveform distortions, which is different from traditional independent communication equipment, realizes invisible transmission of power grid data, effectively reduces equipment costs, breaks through the traditional method's reliance on additional communication channels, and integrates data transmission into the existing power grid waveform, which saves resources and does not interfere with power supply.

[0033] Preferably, the topology generation module is used to monitor the operation status of nodes and topology changes, scan nodes and compare them; store, merge and distribute topology data; and support the updating and organization of topology node archives.

[0034] Specifically, the topology generation module includes a topology identification slave terminal, a topology identification master terminal and a topology analysis handset.

[0035] Furthermore, the topology identification main terminal sends the topology information to the topology analysis handheld device for display. The data processing part mostly uses high-speed multi-channel A / D and DSP, which can effectively complete the data collection and processing on the power line; the data communication part mostly uses Bluetooth and USB data communication ports to directly connect to the background system or personal computer, and transmit the obtained text or data information to the system.

[0036] It should be noted that the specific functions of the topology generation module include: being able to dynamically monitor the operating status and topology changes of each node of the low-voltage distribution network in real time, being able to dynamically scan each node of the low-voltage distribution network in real time and complete the comparison with the original information.

[0037] It can realize the storage, integration and distribution of low-voltage distribution network topology data.

[0038] Able to support the updating and organization of low voltage distribution network topology node files.

[0039] Furthermore, the establishment process of the topology generation module includes the following steps: data reconstruction is achieved through confrontation and competition.

[0040] The generator network is used to update the weight bias and noise error of the production network.

[0041] After the production network is balanced, GAN converges, and the generator and discriminator in GAN will have two corresponding objective functions.

[0042] Specifically, the specific formula of the discriminator's objective function is as follows:

[0043]

[0044] Among them, LD is the objective function of the discriminator; E x is the average value of the samples; D(·) is the discriminator function; X g is the fake data generated by the network; X1 is the real data sample; x m is the intermediate sampling point between the real data and the generated data.

[0045] Preferably, the present invention utilizes the collaborative working mechanism of topology identification master-slave terminals and handheld devices to achieve multi-level power grid topology identification, overcomes the problem of lag in traditional low-voltage distribution network node identification through real-time monitoring and dynamic scanning functions, and constructs topology by generating adversarial networks (GANs), thereby improving the accuracy of topology data generation.

[0046] Preferably, the site identification module is used to detect and identify the topology of the user area information and generate a topology map.

[0047] Specifically, the field identification module includes a master terminal and a slave terminal.

[0048] Furthermore, the master terminal is a master terminal arranged in the distribution transformer of the substation, the slave terminal is a slave terminal arranged on the cable branch box and the meter box side, the detection terminal is a topology identification slave terminal, and the topology identification master terminal is placed in a relatively central location in the substation to obtain the best communication success rate.

[0049] It should be noted that the present invention mainly includes three parts: a topology identification slave terminal, a topology identification master terminal and a topology analysis handset.

[0050] Preferably, the information generation module is used to generate and load substation and phase line signals.

[0051] Specifically, the information generating module is an important device installed on the transformer side.

[0052] Furthermore, the information generation module is used to realize the generation and loading of substation and phase line signals. The detection terminal is mounted at the branch switch. The topology identification main terminal initiates topology identification through carrier or wireless communication, and forms a topology map and displays it based on the topology information fed back by the topology terminal, or transmits the topology information via Bluetooth to the topology analysis handheld device for display, so as to facilitate on-site viewing and analysis.

[0053] Furthermore, the information generation module is composed of transmission communication, data processing, power management, touch display control, information storage and data communication.

[0054] It should be noted that the field identification module and the information generation module are the two main devices that constitute the real-time topology reconstruction system of power grid data; the detection personnel detect the user area information, and the information generation module is responsible for the generation and loading of the substation and phase line signals. It is an important device installed on the transformer side; the modulation control circuit of the industrial frequency load transmission communication part can effectively transmit the load signal on the power line, and the data processing part mostly uses high-speed multi-channel A / D and DSP, which can effectively complete the data collection and processing on the power line; the power management adopts a high-anti-interference switching power supply, which does not affect the communication performance while maintaining voltage stability, reducing the power consumption and weight of the equipment, and the data communication part mostly uses Bluetooth and USB data communication ports to directly connect to the background system or personal computer, and transmit the obtained text or data information to the system.

[0055] Preferably, the present invention optimizes the flexibility of substation and phase line signal loading by adopting carrier or wireless communication combined with Bluetooth transmission, realizes stable loading and transmission of signals in a complex power grid environment, and improves the anti-interference ability of the information identification module.

[0056] Preferably, the data storage module is used to sense data, match data and store data.

[0057] Preferably, the data discovery module is used to transmit the sensed data to a destination grid for storage.

[0058] Preferably, the data forwarding module is used to screen the data and select the best node.

[0059] Specifically, the data storage module is composed of a sensor module, a computing module and a storage module.

[0060] Specifically, the sensor module is used to collect data at multiple levels, the storage module is used to perceive data, and the computing module is used to match data.

[0061] Furthermore, the perception node is used to collect and forward data, the sensor module can be integrated or connected to the computing IED node of the same grid, the main function of the storage module is to receive the perception data forwarded from the computing IED node and store this data for a period of time, the computing module is used to receive the perception data sent by the sensor nodes in this grid, calculate the purpose of the perception data storage grid and forward it, and receive data that matches the storage type of this grid.

[0062] Furthermore, the data discovery module is used to send the sensed data to the destination grid for storage, and the data forwarding module is used to filter the data and select the best node.

[0063] Specifically, when the sensor module senses the data, it generates a message and sends the message to the self-computing IED node in the grid, and then the data is sent to the destination grid for storage through the computing IED node; in order to reduce the computing and communication overhead of the sensor node and ensure the integrity of the sensor network, it is necessary to prioritize the nodes within its communication radius before selecting the best next-hop node; in order to realize the real-time reading and query functions of data, improve the availability and storage capacity of the system, and make the intelligent control of the power grid faster and more accurate, a hierarchical expansion storage mechanism can be implemented, and the extended hash coding method is used to dynamically expand the storage nodes outward. At the same time, the inner nodes can perform data backup and other tasks, increase the storage capacity of the system, and improve the operation efficiency of the system. Then, a multi-threshold level storage method is used to evenly store data on multiple storage nodes in the same layer, avoiding excessive energy consumption of some nodes caused by excessive concentration of storage and query. Large-scale smart grids can comprehensively monitor the status of all nodes, lines and equipment in the power grid and conduct comprehensive management, analysis and fault diagnosis for them, improve system performance and data query efficiency, and store data evenly on multiple nodes, and dynamically expand storage nodes to improve system availability.

[0064] Preferably, the present invention balances the storage load by adopting a hierarchical extended storage mechanism and a multi-threshold level storage method, avoids the single-point bottleneck caused by traditional centralized storage, and improves the storage capacity and query efficiency of large-scale smart grids; by preferentially screening nodes within the communication radius and dynamically adjusting the forwarding path, the communication overhead of sensor nodes is reduced, the service life of the sensor network is extended, and the integrity and efficiency of real-time data transmission are ensured.

[0065] In summary, the present invention proposes a real-time topology reconstruction system for power grid data, which uses the existing signal characteristics of the power grid to transmit information and process data without additional configuration or complicated initialization processes, greatly reducing the technical threshold and time cost of system deployment, and changing the limitation of traditional low-voltage census that is highly dependent on manual work; through real-time monitoring and dynamic topology updates, it effectively reduces manual intervention, improves the automation level of data collection and processing, and significantly saves manpower investment; through the integration of data screening and optimal node selection functions, it ensures the timeliness and accuracy of the data, providing an efficient means for quickly discovering and solving distribution network operation problems.

[0066] Embodiment 2 is an embodiment of the present invention, which provides a real-time topology reconstruction method for power grid data, including: obtaining power grid power frequency voltage data; establishing a topology generation module including a topology identification slave terminal, a topology identification master terminal and a topology analysis handheld device; arranging the topology identification master terminal at the distribution transformer location in the substation, and arranging the topology identification slave terminal at the cable branch box and the meter box side location; installing an information generation module on the transformer side; sending a topology identification signal through the topology identification master terminal to obtain feedback information; constructing a data storage module, including a sensor unit, a computing unit and a storage unit, to collect multi-level data; sending the data collected by the sensor unit to the destination grid storage unit through the computing unit; iteratively updating the weight bias and noise error of the generated network, and generating a topology map based on the discriminator objective function.

[0067] Embodiment 3 is an embodiment of the present invention, which is different from the previous embodiment in that:

[0068] like Figure 2 As shown, if the function 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 technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0069] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0070] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0071] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0072] Embodiment 4 is an embodiment of the present invention, which provides a real-time topology reconstruction system for power grid data. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0073] This example simulates the low-voltage distribution network environment of an industrial park. The experimental area includes 4 substations and 25 nodes, and the topological structure of each substation includes 1 main transformer, several branch boxes and branch cables. First, under the 50Hz power frequency voltage, the modulation signal is injected through the distortion of the current and voltage waveforms to form the grid voltage waveform distortion information, and the modulation signal at the trough position is monitored in real time through the main terminal to ensure the integrity and effectiveness of signal transmission. Secondly, the topology generation module is used to scan each node of the low-voltage distribution network, and the topological data is stored in the system background to ensure that the topological changes can be fed back in time. In addition, through the collaborative work of the master and slave terminals of the field identification module, the user area information is integrated into the topology generation module to form a real-time topological map, and the dynamic changes of the topological structure are output through the handheld display. Finally, the information generation module is used to load the substation and phase line signals to the main terminal, and the data is transmitted to the background system through Bluetooth to complete the signal analysis and debugging. Table 1 shows the dynamic scanning experimental data of the grid topology nodes.

[0074] Table 1. Power grid topology node dynamic scanning experimental data table

[0075] Parameter name Node A Node B Node C Node voltage (V) 220.1 219.8 221.0 Current distortion rate (%) 0.3 0.4 0.2 Modulation signal strength (dB) 45 48 46 Communication success rate (%) 98.5 97.8 99.2 Data delay (ms) 20 22 19

[0076] It can be seen from the above table that the modulation signal strength is maintained between 45 and 48 dB, and the communication success rate is in the range of 97.8% to 99.2%, showing a high signal transmission stability. This shows that compared with the signal interference problem in the traditional system, the present invention carries information through tiny distortion, which effectively reduces the bit error rate in the data transmission process; the node voltage and current distortion rate data in this example remain stable during the scanning process, and the data delay is controlled within 20ms, indicating that the present invention can provide real-time feedback on the dynamic changes of the low-voltage distribution network and meet the needs of online topology updates.

[0077] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A real-time topology reconstruction system for power grid data, characterized by: include: Power frequency sensing module, topology generation module, site identification module, information generation module, data storage module, data discovery module and data forwarding module; The power frequency sensing module is used to realize information transmission according to the position of the modulated signal; The topology generation module is used to monitor the operation status and topology changes of nodes, scan nodes and compare them; store, merge and distribute topology data; support the updating and organization of topology node archives; The site identification module is used to detect user zone information and perform topology identification to generate a topology map; The information generation module is used to generate and load the substation and phase line signals; The data storage module is used to sense data, match data and store data; The data discovery module is used to transmit the sensed data to the destination grid for storage; The data forwarding module is used to screen the data and select the best node.

2. The real-time topology reconstruction system for power grid data according to claim 1, characterized in that: Constructing the power frequency sensing module means that when the THz power frequency voltage is used, the current voltage and current waveform are distorted, the grid voltage and the grid fundamental wave are injected into the modulated voltage waveform, and slight distortions of the grid voltage and current waveforms are artificially generated to carry information. When no modulation is performed, the two adjacent waveforms are the same.

3. The real-time topology reconstruction system for power grid data according to claim 2, characterized in that: The topology generation module includes a topology identification slave terminal, a topology identification master terminal and a topology analysis handset; The topology identification main terminal sends topology information to the topology analysis handheld device for display. The data processing part mostly uses high-speed multi-channel A / D and DSP, and the data communication part mostly uses Bluetooth and USB data communication ports to directly connect to the background system or personal computer to transmit the obtained text or data information to the system.

4. The real-time topology reconstruction system for power grid data according to claim 3, characterized in that: The site identification module includes a master terminal and a slave terminal; The master terminal is a master terminal arranged in the distribution transformer of the substation, the slave terminal is a slave terminal arranged on the cable branch box and the meter box side, the detection terminal is a topology identification slave terminal, and the topology identification master terminal is placed in a relatively central location in the substation to obtain the best communication success rate.

5. The real-time topology reconstruction system for power grid data according to claim 4, characterized in that: The information generation module is an important device installed on the transformer side; The information generation module is used to realize the generation and loading of the substation and phase line signals, form a topology map and display it according to the topology information fed back by the topology terminal, or transmit the topology information to the topology analysis handheld device via Bluetooth for display; The information generation module is composed of transmission communication, data processing, power management, touch display control, information storage and data communication.

6. The real-time topology reconstruction system for power grid data according to claim 5, characterized in that: The data storage module is composed of a sensor module, a computing module and a storage module; The sensor module is used to collect data at multiple levels, the storage module is used to sense data, and the calculation module is used to match data; The data discovery module is used to send the sensed data to the destination grid for storage, and the data forwarding module is used to screen the data and select the best node.

7. The real-time topology reconstruction system for power grid data according to claim 6, characterized in that: The establishment process of the topology generation module includes the following steps: Data reconstruction through confrontation and competition; Use the generated network to update the weight bias and noise error of the production network; After the production network is balanced, GAN converges, and the generator and discriminator in GAN will have two corresponding objective functions; The specific formula of the objective function of the discriminator is as follows: Among them, LD is the objective function of the discriminator; E x is the average value of the samples; D(·) is the discriminator function; X g is the fake data generated by the network; X1 is the real data sample; x m is the intermediate sampling point between the real data and the generated data.

8. A method for real-time topology reconstruction of power grid data, based on the real-time topology reconstruction system of power grid data according to any one of claims 1 to 7, characterized in that: include, Obtain power grid power frequency voltage data; Establishing a topology generation module including a topology identification slave terminal, a topology identification master terminal and a topology analysis handset; Arrange the topology identification master terminal at the distribution transformer location in the substation area, and arrange the topology identification slave terminal at the cable branch box and meter box side location; Install the information generation module on the transformer side; Send a topology identification signal through the topology identification main terminal to obtain feedback information; Construct a data storage module, including a sensor unit, a computing unit, and a storage unit, to collect multi-level data; The data collected by the sensor unit is sent to the destination grid storage unit through the computing unit; The weight bias and noise error of the generated network are iteratively updated, and a topological map is generated based on the discriminator objective function.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the real-time topology reconstruction system for power grid data according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the real-time topology reconstruction system for power grid data according to any one of claims 1 to 7 are implemented.

Images