Intelligent power grid simulation system based on remote visual control

Abstract

The invention discloses an intelligent power grid simulation system based on remote visual control, and the system comprises an intelligent power grid simulation system which comprises a power monitoring module, an intelligent research calculation module, an acquisition calling module, a power grid model module, and a display modification module. The monitoring system is a power monitoring system based on the Beidou + wireless ad hoc network technology, provides communication support service for real-time monitoring of the state of a power transmission line tower, power inspection and maintenance and emergency repair, provides spatio-temporal data for overall operation of a power transmission line, and optimizes an emergency rescue disposal process and an external damage prevention early warning means in a key area; the system is simple in structure and easy to use by setting the acquisition and calling module and the power grid model module, building a target power model, autonomously matching similar values, carrying out fault simulation on the target power model and carrying out power model visualization display in real time according to a corresponding maintenance database.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grid simulation systems, and particularly to a smart grid simulation system based on remote visual control. Background Art

[0002] As an indispensable and important link in the power system, a substation undertakes the heavy tasks of electric energy conversion and redistribution of electric energy, and plays a crucial role in the safe and economic operation of the power grid.

[0003] The smart grid simulation system has a powerful data processing center, which can efficiently process and analyze a large amount of power information data, improve the accuracy of information transmission. Since the smart grid mainly relies on computer control, manual intervention is reduced, and the error rate of information transmission is significantly reduced. The smart grid reduces labor costs and improves the economic benefits of power enterprises. The smart grid transmits information through unique frequencies and bands, effectively enhancing the confidentiality of the information transmission process. The smart grid has functions of alarm, detection, prediction and protection, can quickly respond to abnormal situations, and ensure the stable and reliable operation of the power system. The smart grid can optimize energy allocation, reduce carbon dioxide emissions, achieve green environmental protection, realize efficient energy conservation by analyzing the energy curve through real-time monitoring of electricity load information, adopt distributed management, and can be flexibly configured and scheduled according to different regions and specific needs. Users can understand the electricity consumption situation in real time through devices such as smart meters, and adjust their electricity consumption behavior according to their needs to optimize the user experience. The construction investment of the smart grid is relatively low, and it has an efficient energy-saving function, reducing the energy consumption cost.

[0004] However, the traditional smart grid simulation system has the following disadvantages:

[0005] With the improvement of people's living standards, the demand for electricity gradually increases, and the requirement for the stability of the power grid gradually improves. The traditional smart grid simulation system cannot meet people's current needs. Summary of the Invention

[0006] The purpose of the present invention is to provide a smart grid simulation system based on remote visual control to solve the problem that with the improvement of people's living standards, the demand for electricity gradually increases, the requirement for the stability of the power grid gradually improves, and the traditional smart grid simulation system cannot meet people's current needs as mentioned in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solution: A smart grid simulation system based on remote visual control, including a smart grid simulation system, and the smart grid simulation system includes a power monitoring module, an intelligent research and calculation module, a collection and call module, a power grid model module, and a display and modification module;

[0008] The power monitoring module adopts the Beidou high-precision automatic monitoring method to collect the settlement and tilt displacement change data of power poles in real time; the intelligent research and calculation module endows the AI system with a deeper understanding and reasoning ability of the power environment by simulating the dynamic changes of the power environment, and the acquisition and call module collects all the power grid construction data and transmits it to the power grid construction to facilitate the construction of the corresponding power grid model. The power grid model module receives the selected model and modified data transmitted, and modifies the selected model according to the modified data to obtain the final selected model. The display and modification module displays the operation state of the power grid and provides modification operations.

[0009] As a preferred technical solution of the present invention, the power monitoring module includes a wireless communication sub-module and a Beidou monitoring sub-module;

[0010] The wireless communication sub-module uses the hardware architecture of FPGA+CPU+AD9361 to integrally construct two networking methods from the physical layer, including two wireless transmission channels: a narrowband transmission channel and a broadband service transmission channel. The narrowband transmission channel is used to transmit intercom voices and position data; the broadband service transmission channel is used to transmit videos, Beidou raw data, and sensing data. The Beidou monitoring sub-module observes the overall small deformation amount, constructs a statistical analysis model, and predicts the long-term change trend of the deformed body to provide a basis for subsequent analysis and decision-making. After receiving the satellite raw data, the Beidou receiving terminal encapsulates the data through a protocol and transmits it to the backend solution engine based on the self-organizing network. The solution engine parses and processes the encapsulated data.

[0011] As a preferred technical solution of the present invention, the Beidou monitoring sub-module includes a solution server, a data transmission and access device, a data collector, a first data transmitter, a data processor, a second data transmitter, and a data analyzer. The solution server, data collector, first data transmitter, data processor, second data transmitter, and data analyzer are all connected to the data transmission and access device. The data collector is connected to the first data transmitter, the first data transmitter is connected to the data processor, the data processor is connected to the second data transmitter, and the second data transmitter is connected to the data analyzer;

[0012] The solution server uses the Kalman filter to solve the double-difference equation to obtain the real solution of the relative positioning result. For the double-difference equation of the Kalman filter, the calculation formula of the system state prediction equation is as follows:

[0013] x k =A k x k-1 +w k-1 p(w)-N(0,Q),

[0014] where A k is the state transition matrix at time, w k-1is the system noise, Q is the covariance matrix of the system noise, and the calculation formula of the system measurement equation is as follows:

[0015] Z k = H k x k + v k p(v) - N(0, R),

[0016] where H k is the measured system state transition matrix, v k is the measurement noise, R is the covariance matrix of the measurement noise. The data transmission accessor performs data transmission and data access. The data collector conducts auxiliary data collection and GNSS data collection, deduces and establishes a functional model for multi-frequency GNSS kinematic relative positioning, and uses a large amount of measured data to analyze and compare the double-difference relative positioning models under different conditions to obtain the optimal reference star selection strategy. The first data transmitter receives and stores the original observation data, and the calculation formula for establishing the functional model of multi-frequency GNSS kinematic relative positioning is as follows:

[0017] Number of GNSS equations = (number of satellites * (1 + 1) + (number of ground station position parameters * 1) + (number of Earth geometric parameters * 1),

[0018] where the number of satellites refers to the number of satellite signals received by the receiver. The ground station position parameters include longitude, latitude, and altitude. The Earth geometric parameters include the Earth radius and the Earth equatorial radius. The data processor conducts original data quality checking and various corrections, carrier phase ambiguity fixing, sidereal day multipath filtering, solution quality assessment, and auxiliary data analysis. The second data transmitter transmits data for coordinate transformation. The data analyzer conducts single-point analysis, chart output, profile analysis, report output, trend prediction, and warning and pre-alarm in sequence.

[0019] As a preferred technical solution of the present invention, the intelligent research and calculation module includes a supervised learning calculation sub-module, an AlphaTensor calculation sub-module, and a modal exploration calculation sub-module;

[0020] The supervised learning calculation sub-module trains a neural network model to approximate the calculation results of the finite element method, thereby greatly improving the power environment calculation efficiency while ensuring a certain accuracy. The displacement quantity in finite element calculation is usually represented by a vector, which has magnitude and direction. The displacement vector represents the displacement of an object, the distance and direction of movement. In finite element calculation, the displacement quantity is usually represented by u, expressed as a vector u = (u1, u2, u3), where u1, u2, and u3 respectively represent the displacement quantities in the x, Y, and z directions. The magnitude of the displacement quantity is obtained by calculating the modulus of the displacement vector, and the calculation formula is as follows:

[0021]

[0022] The AlphaTensor computing sub-module optimizes the calculation process of matrix multiplication through deep learning algorithms, finds new tensor product calculation modes, changes the original calculation path, and significantly improves the calculation efficiency. The modal exploration computing sub-module extracts information from a large number of scientific literatures and experimental data, discovers new laws and knowledge, and at the same time explores the power model by combining the hierarchical coding alignment technology of native multi-modalities.

[0023] As a preferred technical solution of the present invention, the acquisition and call module includes a data collection sub-module, a database sub-module, and a data call sub-module. The data collection sub-module is connected to the database sub-module, and the database sub-module is connected to the data call sub-module;

[0024] The data collection sub-module collects all power grid construction data and their corresponding power receiving ranges and distribution levels. The power receiving range is the power supply area corresponding to the power grid construction data. The database sub-module receives the power grid construction data transmitted by the data collection unit and stores it in real time. The data call sub-module is used to transmit the primary selected model data to the power grid construction for building the corresponding power grid model.

[0025] As a preferred technical solution of the present invention, the power grid model module includes a fault simulation sub-module, a simulation monitoring sub-module, a maintenance database sub-module, and a power grid construction sub-module. The maintenance database sub-module is connected to the simulation monitoring sub-module, and both the simulation monitoring sub-module and the fault simulation sub-module are connected to the power grid construction sub-module;

[0026] The fault simulation sub-module detects the monitoring signal generated by the power grid construction module and conducts fault simulation. The simulation monitoring sub-module transmits the selected value K to the data induction. The maintenance database sub-module stores the maintenance time of each individual running fault. The power grid construction sub-module generates a monitoring signal when generating the final selected model.

[0027] As a preferred technical solution of the present invention, the display and modification module includes a visual display sub-module and a visual modification sub-module;

[0028] The visual display sub-module visually displays the power grid simulation system, and the visual modification sub-module modifies the displayed power grid parameters.

[0029] As a preferred technical solution of the present invention, the visual display sub-module includes a data source unit, a data processing unit, a visual display unit, and a user interaction unit. The data source unit is connected to the data processing unit, the data processing unit is connected to the visual display unit, and the visual display unit is connected to the user interaction unit;

[0030] The data source unit collects power grid data through databases, API interfaces, and sensors. The data processing unit cleans, transforms, and aggregates the raw data. The visualization display unit presents the processed data to users in the form of charts. The user interaction unit interacts with the visualization system through JavaScript, Vue, and React.

[0031] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0032] 1. By setting up a wireless communication sub-module, based on wireless ad-hoc network communication technology for audio and video data transmission, it ensures real-time video transmission, saves the cost of Internet of Things traffic, has simple daily system maintenance, and strong disaster tolerance of the transmission system; in specific scenarios such as large-scale power outages and emergency repairs, it ensures real-time video transmission.

[0033] 2. By setting up a Beidou monitoring sub-module, the monitoring system is a power monitoring system based on Beidou + wireless ad-hoc network technology, providing communication support services for real-time monitoring of the status of transmission line towers, power inspection and repair, and emergency repairs, providing spatio-temporal data for the overall operation of transmission lines, and optimizing the emergency rescue and disposal process and the early warning means for preventing external damage in key areas.

[0034] 3. By setting up an acquisition and call module and a power grid model module, a target power model is built, similar values are autonomously matched, fault simulation is carried out on it, and according to the corresponding maintenance database, real-time visualization display of the power model is carried out. The system structure is simple and easy to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the architecture of the intelligent power grid simulation system of the present invention;

[0036] Figure 2 It is a schematic diagram of the architecture of the power monitoring module of the present invention;

[0037] Figure 3 It is a schematic diagram of the architecture of the Beidou monitoring sub-module of the present invention;

[0038] Figure 4 It is a schematic diagram of the architecture of the intelligent research and calculation module of the present invention;

[0039] Figure 5 It is a schematic diagram of the architecture of the acquisition and call module of the present invention;

[0040] Figure 6 It is a schematic diagram of the architecture of the power grid model module of the present invention;

[0041] Figure 7 It is a schematic diagram of the architecture of the display and modification module of the present invention;

[0042] Figure 8This is a schematic diagram of the architecture of the visualization display sub-module of the present invention. Specific embodiments

[0043] Next, in combination with the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] Please refer to Figure 1-8 , the present invention provides an intelligent power grid simulation system based on remote visualization control, including an intelligent power grid simulation system, which includes a power monitoring module, an intelligent research calculation module, a data acquisition and call module, a power grid model module, and a display and modification module;

[0045] The power monitoring module adopts the Beidou high-precision automatic monitoring method to collect the settlement and tilt displacement change data of power poles in real time; the intelligent research calculation module endows the AI system with a deeper understanding and reasoning ability of the power environment by simulating the dynamic changes of the power environment. The data acquisition and call module collects all the power grid construction data and transmits it to the power grid construction for building the corresponding power grid model. The power grid model module receives the selected model and modification data transmitted, and modifies the selected model according to the modification data to obtain the final selected model. The display and modification module displays the operation status of the power grid and provides modification operations.

[0046] The power monitoring module includes a wireless communication sub-module and a Beidou monitoring sub-module;

[0047] The wireless communication sub-module uses the hardware architecture of FPGA + CPU + AD9361 to integrate and construct two networking methods from the physical layer, including two wireless transmission channels: a narrowband transmission channel and a broadband service transmission channel. The narrowband transmission channel is used to transmit intercom voice and position data; the broadband service transmission channel is used to transmit video, Beidou raw data, and sensing data. The Beidou monitoring sub-module observes the overall small deformation amount, constructs a statistical analysis model, and predicts the long-term change trend of the deformed body to provide a basis for subsequent analysis and decision-making. After receiving the satellite raw data, the Beidou receiving terminal encapsulates the data through a protocol and transmits it to the backend solution engine based on a self-organizing network. The solution engine parses and processes the encapsulated data.

[0048] The Beidou monitoring sub-module includes a solution server, a data transmission and access device, a data collector, a first data transmitter, a data processor, a second data transmitter, and a data analyzer. The solution server, the data collector, the first data transmitter, the data processor, the second data transmitter, and the data analyzer are all connected to the data transmission and access device. The data collector is connected to the first data transmitter, the first data transmitter is connected to the data processor, the data processor is connected to the second data transmitter, and the second data transmitter is connected to the data analyzer;

[0049] The solution server uses Kalman filtering to solve the double-difference equation and obtains the real solution of the relative positioning result. For the double-difference equation and the system state prediction equation in Kalman filtering, the calculation formulas are as follows:

[0050] x k =A k x k-1 +w k-1 p(w)-N(0,Q),

[0051] where A k is the state transition matrix at that time, w k-1 is the system noise, Q is the covariance matrix of the system noise. The calculation formula of the system measurement equation is as follows:

[0052] Z k =H k x k +v k p(v)-N(0,R),

[0053] where H k is the measured system state transition matrix, v k is the measurement noise, R is the covariance matrix of the measurement noise. The data transmission and access device performs data transmission and data access. The data collector derives and establishes a function model for multi-frequency GNSS dynamic relative positioning through auxiliary data collection and GNSS data collection, and uses a large number of measured data to analyze and compare double-difference relative positioning models under different conditions to obtain the best reference star selection strategy. The first data transmitter receives and stores the original observation data. The calculation formula for establishing the function model of multi-frequency GNSS dynamic relative positioning is as follows:

[0054] Number of GNSS equations = (number of satellites * (1 + 1) + (number of ground station position parameters * 1) + (number of earth geometric parameters * 1),

[0055] Among them, the number of satellites refers to the number of satellite signals received by the receiver. The ground station position parameters include longitude, latitude, and altitude. The earth geometric parameters include the earth radius and the earth equatorial radius. The data processor conducts original data quality verification and various corrections, carrier phase ambiguity fixing, sidereal day multipath filtering, solution quality assessment, and auxiliary data analysis. The second data transmitter transmits data for coordinate transformation. The data analyzer sequentially conducts single-point analysis, chart output, profile analysis, report output, trend prediction, and alarm warning.

[0056] The intelligent research and calculation module includes a supervised learning calculation sub-module, an AlphaTensor calculation sub-module, and a modal exploration calculation sub-module;

[0057] The supervised learning calculation sub-module trains a neural network model to approximate the calculation results of the finite element method, thereby significantly improving the power environment calculation efficiency while ensuring a certain accuracy. The displacement quantity in the finite element calculation is usually represented by a vector, which has magnitude and direction. The displacement vector represents the displacement of an object, the distance and direction of movement. In the finite element calculation, the displacement quantity is usually represented by u, expressed as a vector u = (u1, u2, u3), where u1, u2, and u3 respectively represent the displacement quantities in the x, Y, and z directions. The magnitude of the displacement quantity is obtained by calculating the modulus of the displacement vector, and the calculation formula is as follows:

[0058]

[0059] The AlphaTensor calculation sub-module optimizes the calculation process of matrix multiplication through deep learning algorithms and finds a new tensor product calculation mode, changing the original calculation path and significantly improving the calculation efficiency. The modal exploration calculation sub-module extracts information from a large number of scientific literature and experimental data to discover new laws and knowledge, and at the same time explores the power model by combining the hierarchical coding alignment technology of native multi-modalities.

[0060] The acquisition and call module includes a data collection sub-module, a database sub-module, and a data call sub-module. The data collection sub-module is connected to the database sub-module, and the database sub-module is connected to the data call sub-module;

[0061] The data collection sub-module collects all the power grid construction data and its corresponding power receiving range and distribution magnitude. The power receiving range is the power supply area corresponding to the power grid construction data. The database sub-module receives the power grid construction data transmitted by the data collection unit and stores it in real time. The data call sub-module is used to transmit the primary selected model data to the power grid construction to facilitate the construction of the corresponding power grid model.

[0062] The power grid model module includes a fault simulation sub-module, a simulation monitoring sub-module, a maintenance database sub-module, and a power grid construction sub-module. The maintenance database sub-module is connected to the simulation monitoring sub-module, and both the simulation monitoring sub-module and the fault simulation sub-module are connected to the power grid construction sub-module;

[0063] The fault simulation sub-module detects the monitoring signal generated by the power grid construction module and conducts fault simulation. The simulation monitoring sub-module transmits the selected value K to data induction. The maintenance database sub-module stores the maintenance time of each individual running fault, and the power grid construction sub-module generates a monitoring signal when generating the final selected model.

[0064] The display modification module includes a visual display sub-module and a visual modification sub-module;

[0065] The visual display sub-module visually displays the power grid simulation system, and the visual modification sub-module modifies the displayed power grid parameters.

[0066] The visual display sub-module includes a data source unit, a data processing unit, a visual display unit, and a user interaction unit. The data source unit is connected to the data processing unit, the data processing unit is connected to the visual display unit, and the visual display unit is connected to the user interaction unit;

[0067] The data source unit collects power grid data through databases, API interfaces, and sensors. The data processing unit performs cleaning, conversion, and aggregation operations on the raw data. The visual display unit presents the processed data to the user in the form of charts, and the user interaction unit interacts with the visual system through JavaScript, Vue, and React.

[0068] In the present invention, the wireless communication sub-module adopts a hardware architecture of FPGA + CPU + AD9361 to integrally construct two networking modes from the physical layer, including two wireless transmission channels: a narrowband transmission channel and a broadband service transmission channel. The narrowband transmission channel is used to transmit intercom voice and position data; the broadband service transmission channel is used to transmit video, Beidou raw data, and sensing data. The Beidou monitoring sub-module observes the overall micro deformation amount, constructs a statistical analysis model, and predicts the long-term change trend of the deformed body to provide a basis for subsequent analysis and decision-making. After receiving the satellite raw data, the Beidou receiving terminal encapsulates the data through a protocol and transmits it to the backend decoding engine based on the self-organizing network. The decoding engine parses and processes the encapsulated data. The supervised learning calculation sub-module trains a neural network model to approximate the calculation results of the finite element method, thereby significantly improving the calculation efficiency of the power environment under the premise of ensuring a certain accuracy. The displacement amount in the finite element calculation is usually represented by a vector, which has a magnitude and a direction. The displacement vector represents the displacement of an object, the distance and direction of movement. In the finite element calculation, the displacement amount is usually represented by u, expressed as a vector u = (u1, u2, u3), where u1, u2, and u3 respectively represent the displacement amounts in the x, Y, and z directions. The magnitude of the displacement amount is obtained by calculating the modulus of the displacement vector, and the calculation formula is as follows:

[0069]

[0070] The AlphaTensor calculation sub-module optimizes the calculation process of matrix multiplication through deep learning algorithms, finds a new calculation mode for tensor products, changes the original calculation path, and significantly improves the calculation efficiency. The mode exploration calculation sub-module extracts information from a large number of scientific literature and experimental data, discovers new laws and knowledge, and at the same time explores the power model in combination with the hierarchical coding alignment technology of native multi-modalities. The data collection sub-module collects all the power grid construction data and their corresponding power receiving ranges and distribution levels. The power receiving range is the power supply area corresponding to the power grid construction data. The database sub-module receives the power grid construction data transmitted by the data collection unit and stores it in real time. The data call sub-module is used to transmit the preliminary selected model data to the power grid construction to facilitate the construction of the corresponding power grid model. The fault simulation sub-module detects the monitoring signal generated by the power grid construction module and conducts fault simulation. The simulation monitoring sub-module transmits the selected value K to the data induction. The maintenance database sub-module stores the maintenance time of each separate running fault. The power grid construction sub-module generates a monitoring signal when generating the final selected model. The visualization display sub-module visually displays the power grid simulation system. The visualization modification sub-module modifies the displayed power grid parameters.

[0071] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent power grid simulation system based on remote visual control, including an intelligent power grid simulation system, characterized in that: The intelligent power grid simulation system includes a power monitoring module, an intelligent research and calculation module, a data acquisition and call module, a power grid model module, and a display and modification module; The power monitoring module adopts the Beidou high-precision automatic monitoring method to collect the settlement and tilt displacement change data of power poles in real time; the intelligent research and calculation module endows the AI system with a deeper understanding and reasoning ability of the power environment by simulating the dynamic changes of the power environment. The data acquisition and call module collects all the power grid construction data and transmits it to the power grid construction to facilitate the construction of the corresponding power grid model. The power grid model module receives the selected model and modification data transmitted, and modifies the selected model according to the modification data to obtain the final selected model. The display and modification module displays the power grid operation status and provides modification operations.

2. The intelligent power grid simulation system based on remote visual control according to claim 1, wherein: The power monitoring module includes a wireless communication sub-module and a Beidou monitoring sub-module; The wireless communication sub-module integrates and constructs two networking methods with the hardware architecture of FPGA+CPU+AD9361, including two wireless transmission channels: a narrowband transmission channel and a broadband service transmission channel. The narrowband transmission channel is used to transmit intercom voice and position data; the broadband service transmission channel is used to transmit video, Beidou raw data, and sensing data. The Beidou monitoring sub-module constructs a statistical analysis model by observing the overall minute deformation amount to predict the long-term change trend of the deformed body and provide a basis for subsequent analysis and decision-making. After receiving the satellite raw data, the Beidou receiving terminal encapsulates the data through a protocol and transmits it to the backend solution engine based on the self-organizing network. The solution engine parses and processes the encapsulated data.

3. An intelligent power grid simulation system based on remote visual control according to claim 2, characterized in that: The Beidou monitoring sub-module includes a solution server, a data transmission and storage device, a data collector, a first data transmitter, a data processor, a second data transmitter, and a data analyzer. The solution server, data collector, first data transmitter, data processor, second data transmitter, and data analyzer are all connected to the data transmission and storage device. The data collector is connected to the first data transmitter, the first data transmitter is connected to the data processor, the data processor is connected to the second data transmitter, and the second data transmitter is connected to the data analyzer; The solution server uses the Kalman filter to solve the double-difference equation to obtain the real solution of the relative positioning result. The Kalman filter for the double-difference equation, the calculation formula of the system state prediction equation is as follows: x k = A k x k-1 + w k-1 p(w) - N(0, Q), Among them, A k is the state transition matrix at time, w k-1 is the system noise, Q is the covariance matrix of the system noise, and the calculation formula of the system measurement equation is as follows: Z k = H k x k + v k p(v)-N(0,R), Among them, H k is the measured system state transition matrix, v k is the measurement noise, R is the covariance matrix of the measurement noise. The data transmission accessor conducts data transmission and data access. The data collector derives and establishes a functional model for multi-frequency GNSS kinematic relative positioning through auxiliary data collection and GNSS data collection, and uses a large amount of measured data to analyze and compare the double-difference relative positioning models under different conditions to obtain the best reference star selection strategy. The first data transmitter receives and stores the original observation data. The calculation formula for establishing the functional model of multi-frequency GNSS kinematic relative positioning is as follows: GNSS equation number = (number of satellites * (1 + 1) + (number of ground station position parameters * 1) + (number of earth geometric parameters * 1)), where the number of satellites refers to the number of satellite signals received by the receiver. The ground station position parameters include longitude, latitude, and altitude. The earth geometric parameters include the earth radius and the earth's equatorial radius. The data processor performs quality check and various corrections on the raw data, fixes the carrier phase ambiguity, filters the sidereal day multipath, evaluates the solution quality, and analyzes the auxiliary data. The second data transmitter transmits the data for coordinate transformation. The data analyzer performs single-point analysis, chart output, profile analysis, report output, trend prediction, and alarm warning in sequence.

4. An intelligent power grid simulation system based on remote visual control according to claim 1, characterized in that: The intelligent research computing module includes a supervised learning computing sub-module, an AlphaTensor computing sub-module, and a modal exploration computing sub-module; The supervised learning computing sub-module trains a neural network model to approximate the calculation results of the finite element method, thereby greatly improving the power environment calculation efficiency while ensuring a certain accuracy. The displacement quantity in finite element calculation is usually represented by a vector, which has magnitude and direction. The displacement vector represents the displacement of an object, the distance and direction of movement. In finite element calculation, the displacement quantity is usually represented by u, expressed as a vector u = (u1, u2, u3), where u1, u2, and u3 respectively represent the displacement quantities in the x, Y, and z directions. The magnitude of the displacement quantity is obtained by calculating the modulus of the displacement vector, and the calculation formula is as follows: The AlphaTensor computing sub-module optimizes the calculation process of matrix multiplication through deep learning algorithms and finds a new tensor product calculation mode, changing the original calculation path and significantly improving the calculation efficiency. The modal exploration computing sub-module extracts information from a large number of scientific literature and experimental data, discovers new laws and knowledge, and at the same time explores the power model by combining the hierarchical coding alignment technology of native multi-modalities.

5. An intelligent power grid simulation system based on remote visual control according to claim 1, characterized in that: The acquisition and call module includes a data collection sub-module, a database sub-module, and a data call sub-module. The data collection sub-module is connected to the database sub-module, and the database sub-module is connected to the data call sub-module; The data collection sub-module collects all power grid construction data and their corresponding power receiving ranges and distribution levels. The power receiving range is the power supply area corresponding to the power grid construction data. The database sub-module receives the power grid construction data transmitted by the data collection unit and stores it in real time. The data call sub-module is used to transmit the primary selected model data to the power grid construction to facilitate the construction of the corresponding power grid model.

6. An intelligent power grid simulation system based on remote visualization control according to claim 1, characterized in that: The power grid model module includes a fault simulation sub-module, a simulation monitoring sub-module, a maintenance database sub-module, and a power grid construction sub-module. The maintenance database sub-module is connected to the simulation monitoring sub-module, and both the simulation monitoring sub-module and the fault simulation sub-module are connected to the power grid construction sub-module; The fault simulation sub-module detects the monitoring signal generated by the power grid construction module and conducts fault simulation. The simulation monitoring sub-module transmits the selected value K to the data induction. The maintenance database sub-module stores the maintenance time of each separate operation fault. The power grid construction sub-module generates a monitoring signal when generating the final selected model.

7. An intelligent power grid simulation system based on remote visualization control according to claim 1, characterized in that: The display and modification module includes a visualization display sub-module and a visualization modification sub-module; The visualization display sub-module visually displays the power grid simulation system, and the visualization modification sub-module modifies the displayed power grid parameters.

8. An intelligent power grid simulation system based on remote visualization control according to claim 7, characterized in that: The visualization display sub-module includes a data source unit, a data processing unit, a visualization display unit, and a user interaction unit. The data source unit is connected to the data processing unit, the data processing unit is connected to the visualization display unit, and the visualization display unit is connected to the user interaction unit; The data source unit collects power grid data through databases, API interfaces, and sensors. The data processing unit performs cleaning, transformation, and aggregation operations on the raw data. The visualization display unit presents the processed data to users in the form of charts. The user interaction unit interacts with the visualization system through JavaScript, Vue, and React.

Images