Intelligent power grid topology networking system and method based on SVG (Scalable Vector Graphics)

Abstract

The invention relates to the technical field of power supply systems, in particular to an SVG-based intelligent power grid topology networking system and method, and the system comprises a data collection module, a power grid SVG generation module, a power grid SVG visualization module, a power grid SVG reconstruction self-healing module, a power grid SVG multi-terminal operation module and a power grid SVG optimization module. Through cooperative work of data acquisition, power grid SVG generation, power grid SVG visualization, power grid SVG reconstruction self-healing, power grid SVG multi-terminal operation and a power grid SVG optimization module, the system outputs the smart power grid SVG, the comprehensiveness of the smart power grid SVG is enhanced, a power grid protection area is visually displayed through an SVG visualization area, and the power grid SVG protection effect is improved. The visuality and operability of the system SVG visualization area are improved, the intelligent power grid SVG is optimized through the conflict detection of the power grid change event and the multi-terminal cooperative operation, the accuracy and efficiency of the power grid topology are enhanced, and the intelligence and safety of the power grid SVG are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply systems, and in particular to an SVG-based smart grid topology networking system and method. Background Art

[0002] Currently, SVG-based smart grid topology construction cannot completely break away from real-time human control and cannot identify the optimal path for grid connection relationships, which restricts the real-time requirements of grid monitoring. Since traditional systems cannot intuitively display protection domains, the generated SVG diagrams cannot display visual operation areas, which limits the intuitiveness of operations and cannot achieve deep integration of visual management and real-time monitoring of operating status. Since the current SVG of smart grids is still immature in multi-terminal operation and has not been optimized enough, it cannot meet the industrial needs of grid dispatching and collaborative operations.

[0003] Chinese Patent Publication No.: CN116827800A discloses a method, device, equipment and medium for generating an SVG topology map of a power grid substation, which belongs to the technical field of power grid topology maps. The technical solution of the present invention is: the present invention discloses a method, device, equipment and medium for generating an SVG topology map of a power grid substation, which is used to solve the technical problem that the existing SVG topology map generation method is limited by the network speed and browser memory problem, and the download speed is too slow. The present invention includes: real-time monitoring of abnormal events in the ledger data of each substation; when an abnormal event is detected, the substation corresponding to the ledger data where the abnormal event occurs is marked as abnormal, and the abnormal substation is obtained; the SVG topology map generation operation of the abnormal substation is triggered on the PC side, and the underlying download authority of the PC side is enabled; the PC side establishes multiple download threads according to the underlying download authority; the PC side concurrently downloads the target ledger data of the abnormal substation through the download thread, and uses the target ledger data to generate the SVG topology map of the abnormal substation. This shows that this solution still lacks the real-time requirements for real-time monitoring of the power grid. The generated SVG diagram cannot display the visual operation area, which limits the intuitiveness of the operation and cannot achieve deep integration of visual management and real-time monitoring of operating status. In addition, SVG in smart grids is still immature in terms of multi-terminal operation, and the optimization of SVG in smart grids is insufficient to meet the industrial needs of power grid dispatching and collaborative operations. Summary of the Invention

[0004] To this end, the present invention provides a smart grid topology networking system and method based on SVG to overcome the lack of real-time requirements for real-time monitoring of the power grid in the existing technology. The generation of SVG diagrams cannot display the visual operation area, which limits the intuitiveness of the operation and cannot achieve deep integration of visual management and real-time monitoring of the operating status. In addition, SVG in smart grids is still immature in multi-terminal operation, and the optimization of SVG in smart grids is insufficient, which cannot meet the industrial needs of power grid scheduling and collaborative operations.

[0005] To achieve the above objectives, the present invention provides, on the one hand, a smart grid topology networking system based on SVG, comprising: Data acquisition module, used to collect electrical parameters and electrical measurement data; a power grid SVG generation module configured to output the standardized SVG model based on the electrical parameters using a standardized SVG model to obtain a standardized SVG model, analyze an optimal electrical path based on the electrical connection relationship and the electrical parameters using a graph theory algorithm to obtain an optimal electrical path, map the electrical measurement data using a mapping method to obtain an SVG visual attribute solution, optimize the layout of the SVG based on the electrical parameters to obtain an optimal layout solution, and output a smart grid SVG based on the standardized SVG model, the optimal electrical path, the SVG visual attribute solution, and the optimal layout solution to obtain a smart grid SVG; The power grid SVG visualization module is used to obtain the working status of the relay protection device based on electrical parameters and output the working content of the SVG visualization area based on the working status of the relay protection device; The grid SVG reconstruction self-healing module is used to obtain grid SVG change instructions based on grid change events; A power grid SVG multi-terminal operation module, configured to obtain conflict detection results according to the power grid SVG change instruction using a conflict detection model; The power grid SVG optimization module is used to correct the standardized SVG model, SVG visual attribute scheme and power grid SVG change instructions based on the conflict detection results, and is also used to correct the process of preset discrimination correction, and is also used to correct the process of preset visual discrimination correction, and is also used to update the SVG change instructions.

[0006] Furthermore, the power grid SVG generation module constructs the SVG model according to the SVG model construction method to obtain the SVG model, and compares the discrimination W in the electrical parameters with the preset discrimination W0, judges the standard state of the SVG model according to the comparison result, and outputs the standardized SVG model according to the judgment result. The power grid SVG generation module parses the electrical connection relationship according to the power grid equipment to obtain the electrical connection result, and constructs the electrical path model according to the graph theory algorithm to obtain the electrical path model, inputs the electrical connection result, line impedance and load capacity into the electrical path model, and outputs the optimal electrical path. The power grid SVG generation module maps the electrical measurement data through a mapping method to obtain an SVG visual attribute scheme. The power grid SVG generation module judges the structural characteristics according to the voltage value U in the electrical parameters, and outputs the optimal layout scheme according to the judgment result.

[0007] Furthermore, the power grid SVG generation module constructs the SVG generation model through the SVG generation model construction method to obtain the SVG generation model, and inputs the standardized SVG model, the optimal electrical path, the SVG visual attribute scheme and the optimal layout scheme into the SVG generation model to obtain the smart grid SVG output by the SVG generation model.

[0008] Furthermore, the grid SVG visualization module acquires the working status of the relay protection device according to the current value in the electrical appliance measurement data, obtains the working status of the relay protection device, and outputs the working content of the SVG visualization area according to the working status of the relay protection device, wherein: When the working state of the relay protection device is the protection state, the grid SVG visualization module outputs the SVG visualization area, and the working content is to automatically highlight the associated device group and dynamically render the SVG visualization area; When the working state of the relay protection device is the maintenance state, the grid SVG visualization module outputs the SVG visualization area, and the working content is to display the device isolation boundary and dynamically render the SVG visualization area.

[0009] Furthermore, the grid SVG reconstruction self-healing module adjusts the smart grid SVG according to the grid change event, verifies the load condition according to the adjustment process of the smart grid SVG, and obtains a grid SVG change instruction, wherein: When the grid change event is a device switching event, the smart grid SVG is adjusted to redraw the affected local topology; When the grid change event is a network reconstruction event, the smart grid SVG is adjusted, the optimal electrical path is recalculated, and the connection points are automatically magnetically attracted according to the recalculated optimal electrical path.

[0010] Furthermore, the power grid SVG multi-terminal operation module constructs a conflict detection model using a conflict detection model construction method to obtain a conflict detection model, inputs the power grid SVG change instruction into the conflict detection model, and obtains a conflict detection result output by the conflict detection model.

[0011] Furthermore, the power grid SVG optimization module corrects the standardized SVG model, the SVG visual attribute scheme, and the power grid SVG change instruction according to the conflict detection result, wherein: When the conflict detection result is inconsistent with the standardized SVG model, the power grid SVG optimization module corrects the preset discrimination, calculates the preset discrimination W01 according to the error rate Sm and the first weight coefficient α1, sets W01=α1×Sm, obtains the corrected preset discrimination W01, replaces the preset discrimination W0 with the adjusted preset discrimination W01, and re-compares the discrimination W with the adjusted preset discrimination W01; When the conflict detection result is inconsistent with the SVG visual attribute scheme, the power grid SVG optimization module corrects the preset visual discrimination, calculates the preset visual discrimination Y01 according to the error rate Sm and the second weight coefficient α2, sets Y01=α2×Sm, obtains the corrected preset visual discrimination Y01, replaces the preset visual discrimination Y0 with the corrected preset visual discrimination Y01, and re-compares the visual discrimination Y with the corrected preset visual discrimination Y01; When the conflict detection result is inconsistent with the grid SVG change instruction, the grid SVG optimization module corrects the adjustment process of the smart grid SVG to obtain a corrected grid SVG change instruction, pushes the corrected grid SVG change instruction to the administrator terminal, and issues an alarm to the terminal.

[0012] Furthermore, the power grid SVG optimization module compares the standardized SVG model inconsistency number P with a preset standardized SVG model inconsistency number p0, determines the inconsistency of the standardized SVG model based on the comparison result, and modifies the preset discrimination correction process based on the determination result, wherein: When P≤P0, the power grid SVG optimization module determines that the inconsistency of the standardized SVG model is normal and does not modify the preset discrimination correction process; When P>P0, the grid SVG optimization module determines that the inconsistency of the standardized SVG model is an abnormal situation, and corrects the process of the preset discrimination correction by using the coefficient g to correct the preset discrimination W01 and set , e is the base of the natural logarithm, and the corrected preset discrimination W02 is obtained. Set W02 = α1 / (0.47+g), replace the preset discrimination W0 with the corrected preset discrimination W02, and re-compare the discrimination W with the corrected preset discrimination W02.

[0013] The power grid SVG optimization module compares the number of SVG visual attribute scheme inconsistencies X with the preset number of SVG visual attribute scheme inconsistencies X0, determines the inconsistency of the SVG visual attribute scheme based on the comparison result, and modifies the preset visual discrimination correction process based on the judgment result, wherein: When X≤X0, the power grid SVG optimization module determines that the inconsistency of the SVG visual attribute scheme is normal and does not modify the preset visual discrimination correction process; When X>X0, the power grid SVG optimization module determines that the inconsistency of the SVG visual attribute scheme is an abnormal situation, and corrects the preset visual discrimination correction process, corrects the preset visual discrimination Y01 by the visual coefficient N, and sets , e is the base of the natural logarithm, and the corrected preset visual discrimination Y02 is obtained. Set Y02 = α2 / (0.47+g), replace the preset visual discrimination Y0 with the corrected preset visual discrimination Y02, and re-compare the visual discrimination Y with the corrected preset visual discrimination Y02; Furthermore, the power grid SVG optimization module compares the power grid SVG change instruction inconsistency number K with a preset SVG change instruction inconsistency number K0, determines the SVG change instruction inconsistency based on the comparison result, and updates the SVG change instruction based on the determination result, wherein: When K≤K0, the power grid SVG optimization module determines that the inconsistency of the SVG change instruction is normal and does not update the SVG change instruction; When K>K0, the power grid SVG optimization module determines that the inconsistency of the SVG change instruction is an abnormal situation, updates the SVG change instruction, and updates the inconsistent SVG change instruction as a new SVG change instruction.

[0014] In another aspect, the present invention further provides a method for constructing a smart grid topology system based on SVG, comprising: Step S1, collecting electrical parameters and electrical measurement data; Step S2: Outputting the standardized SVG model according to the electrical parameters using a standardized SVG model to obtain a standardized SVG model; analyzing an optimal electrical path according to the electrical connection relationship and the electrical parameters using a graph theory algorithm to obtain an optimal electrical path; mapping the electrical measurement data using a mapping method to obtain an SVG visual attribute solution; optimizing the layout of the SVG according to the electrical parameters to obtain an optimal layout solution; and outputting a smart grid SVG according to the standardized SVG model, the optimal electrical path, the SVG visual attribute solution, and the optimal layout solution to obtain a smart grid SVG; Step S3, acquiring the working state of the relay protection device according to the electrical parameters, and outputting the working content of the SVG visualization area according to the working state of the relay protection device; Step S4, obtaining a power grid SVG change instruction according to the power grid change event; Step S5, using a conflict detection model to obtain a conflict detection result according to the power grid SVG change instruction; Step S6: Correct the standardized SVG model, SVG visual attribute scheme and power grid SVG change instruction according to the conflict detection result, correct the preset discrimination correction process, correct the preset visual discrimination correction process, and update the SVG change instruction.

[0015] Compared with the prior art, the beneficial effect of the present invention is that the data acquisition module collects electrical parameters and electrical measurement data so as to subsequently generate a smart grid SVG, thereby optimizing the smart grid SVG and improving the efficiency of the system. The grid SVG generation module constructs the SVG model according to the SVG model construction method to obtain the SVG model, and compares the discrimination W in the electrical parameters with the preset discrimination W0, judges the standard state of the SVG model according to the comparison result, and outputs the standardized SVG model according to the judgment result, thereby improving the efficiency of electrical parameter analysis and the accuracy of outputting the standardized SVG model. The grid SVG generation module generates the electrical path model according to the graph theory algorithm. The electrical path model is constructed to obtain the electrical connection result, line impedance and load capacity. The electrical path model is input to the electrical path model, and the optimal electrical path is output. The load balancing pre-layout is realized through the optimal electrical path. The power grid SVG generation module maps the electrical measurement data through a mapping method to obtain an SVG visual attribute solution, thereby improving the deep integration of power grid visualization management and real-time monitoring of operation status. The power grid SVG generation module judges the structural characteristics according to the voltage value U in the electrical parameters, and outputs the optimal layout solution according to the judgment result, thereby improving the cognitive efficiency of the power grid structural characteristics and strengthening the timeliness of the optimal layout solution for different structural characteristics. The power grid SVG generation module standardizes the SVG model. , the optimal electrical path, the SVG visual attribute scheme and the optimal layout scheme are input into the SVG generation model to obtain the smart grid SVG output by the SVG generation model, thereby enhancing the comprehensiveness of the smart grid SVG and improving the intelligence of the grid SVG generation. The grid SVG visualization module obtains the working status of the relay protection device and outputs the working content of the SVG visualization area according to the working status of the relay protection device, thereby solving the problem that the traditional system cannot intuitively display the protection area and improving the intuitiveness and operability of the system SVG visualization area. The grid SVG reconstruction self-healing module adjusts the smart grid SVG according to the grid change event and verifies the load condition according to the adjustment process of the smart grid SVG to obtain the grid. SVG change instructions, realize closed-loop control of smart grid SVG adjustment and load balancing, improve system stability, the grid SVG multi-terminal operation module constructs a conflict detection model through a conflict detection model construction method to obtain a conflict detection model, inputs the grid SVG change instructions into the conflict detection model, obtains a conflict detection result output by the conflict detection model, improves grid dispatch coordination, the grid SVG optimization module corrects the standardized SVG model, SVG visual attribute scheme and grid SVG change instructions according to the conflict detection result, improves the accuracy and efficiency of the grid topology, and the grid SVG optimization module corrects the standardized SVG model correction process according to the number of inconsistencies in the standardized SVG model.The process of correcting the SVG visual attribute scheme is modified according to the number of inconsistencies in the SVG visual attribute scheme, and the SVG change instruction is updated according to the number of inconsistencies in the power grid SVG change instruction, thereby improving the security of the power grid system and strengthening the intelligence of the system's automatic optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a schematic diagram of the structure of the SVG-based smart grid topology networking system in this embodiment; Figure 2 Schematic diagram of the process of the SVG-based smart grid topology networking method in this embodiment. DETAILED DESCRIPTION

[0017] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0018] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0019] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0020] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0021] See also Figure 1 FIG. 1 is a schematic diagram of the structure of the SVG-based smart grid topology networking system according to this embodiment. The system includes: Data acquisition module, used to collect electrical parameters and electrical measurement data; a power grid SVG generation module configured to output the standardized SVG model based on the electrical parameters using a standardized SVG model to obtain a standardized SVG model, analyze the optimal electrical path based on the electrical parameters using a graph theory algorithm to obtain an optimal electrical path, map the electrical measurement data using a mapping method to obtain an SVG visual attribute solution, optimize the layout of the SVG based on the electrical parameters to obtain an optimal layout solution, and output a smart grid SVG based on the standardized SVG model, the optimal electrical path, the SVG visual attribute solution, and the optimal layout solution to obtain a smart grid SVG; the power grid SVG generation module being connected to the data acquisition module; A power grid SVG visualization module, configured to obtain the working status of the relay protection device based on electrical parameters and output the working content of the SVG visualization area based on the working status of the relay protection device. The power grid SVG visualization module is connected to the power grid SVG generation module. A power grid SVG reconstruction self-healing module, configured to obtain a power grid SVG change instruction according to a power grid change event, wherein the power grid SVG reconstruction self-healing module is connected to the power grid SVG visualization module; a power grid SVG multi-terminal operation module, configured to obtain conflict detection results according to the power grid SVG change instruction using a conflict detection model, wherein the power grid SVG multi-terminal operation module is connected to the power grid SVG reconstruction self-healing module; The power grid SVG optimization module is used to correct the standardized SVG model, the SVG visual attribute scheme and the power grid SVG change instruction according to the conflict detection results, and is also used to correct the process of correcting the standardized SVG model, the process of correcting the SVG visual attribute scheme, and the update of the SVG change instruction. The power grid SVG optimization module is connected to the power grid SVG multi-terminal operation module.

[0022] Specifically, the SVG-based smart grid topology networking system is applied to the smart grid topology networking. By real-time monitoring of electrical parameters and electrical measurement data, the smart grid SVG is obtained and optimized. The data acquisition module collects electrical parameters and electrical measurement data to subsequently generate the smart grid SVG, thereby optimizing the smart grid SVG and improving the efficiency of the system. The grid SVG generation module constructs the SVG model according to the SVG model construction method to obtain the SVG model, and compares the discrimination W in the electrical parameters with the preset discrimination W0. The standard state of the SVG model is judged according to the comparison result, and the standardized SVG model is output according to the judgment result, thereby improving the efficiency of the system. The efficiency of electrical parameter analysis is improved, and the accuracy of outputting the standardized SVG model is improved. The power grid SVG generation module constructs the electrical path model according to the graph theory algorithm to obtain the electrical path model, inputs the electrical connection results, line impedance and load capacity into the electrical path model, and outputs the optimal electrical path. The load balancing pre-layout is achieved through the optimal electrical path. The power grid SVG generation module maps the electrical measurement data through a mapping method to obtain an SVG visual attribute solution, thereby improving the deep integration of power grid visualization management and real-time monitoring of operating status. The power grid SVG generation module judges the structural characteristics according to the voltage value U in the electrical parameters, and outputs the optimal layout solution based on the judgment result. Improve the efficiency of cognition of grid structure characteristics and strengthen the timeliness of optimal layout solutions for different structural characteristics. The grid SVG generation module inputs the standardized SVG model, optimal electrical path, SVG visual attribute solution and optimal layout solution into the SVG generation model to obtain the smart grid SVG output by the SVG generation model, enhance the comprehensiveness of the smart grid SVG and improve the intelligence of grid SVG generation. The grid SVG visualization module obtains the working status of the relay protection device and outputs the working content of the SVG visualization area according to the working status of the relay protection device, solving the problem that the traditional system cannot intuitively display the protection area, improving the intuitiveness and operability of the system SVG visualization area, and the grid SV The G reconstruction self-healing module adjusts the smart grid SVG according to the grid change event, verifies the load situation according to the adjustment process of the smart grid SVG, obtains the grid SVG change instruction, realizes the closed-loop control of the adjustment and load balancing of the smart grid SVG, and improves the system stability. The grid SVG multi-terminal operation module constructs a conflict detection model through the conflict detection model construction method to obtain a conflict detection model, inputs the grid SVG change instruction into the conflict detection model, obtains the conflict detection result output by the conflict detection model, and improves the grid dispatch coordination. The grid SVG optimization module corrects the standardized SVG model, SVG visual attribute scheme and grid SVG change instruction according to the conflict detection result.To improve the accuracy and efficiency of power grid topology, the power grid SVG optimization module modifies the standardized SVG model correction process based on the number of standardized SVG model inconsistencies, modifies the SVG visual attribute scheme correction process based on the number of SVG visual attribute scheme inconsistencies, and updates the SVG change instructions based on the number of power grid SVG change instruction inconsistencies, thereby improving the security of the power grid system and enhancing the intelligence of the system's automatic optimization.

[0023] Specifically, the data acquisition module is used to collect electrical parameters and electrical measurement data. The electrical parameters include discrimination, voltage value, line impedance, load capacity and visual discrimination. The discrimination refers to the difference in the operating status of the power grid in different areas. The voltage value refers to the numerical value of the power grid voltage. The line impedance refers to the impedance value of the electrical equipment connection line. The load capacity refers to the size of the load in the electrical equipment connection line. The visual discrimination refers to the visualization of electrical equipment and topological structure by the power grid through visualization technology. The visualization technology refers to the technology that can extract visual features of electrical equipment and topological structure. The electrical equipment refers to the equipment connected for work in the power grid. The electrical equipment includes transformers, circuit breakers and busbars. The topological structure refers to the connection relationship of the power grid network. The visual feature extraction refers to visual distinction through different display states. The data acquisition module uses the system of the power grid dispatching department The system parameter database collects the electrical parameters, the power grid dispatching department refers to the department that specializes in dispatching power grid parameters, the system parameter database refers to the sum of data of power grid parameters including electrical parameters, the electrical measurement data includes current value, load rate, fault state type and line width, the current value refers to the numerical value of the power grid current, the load rate refers to an indicator of the stability of power grid operation, the fault state type refers to the type of fault when a power grid fault occurs, and the line width refers to the maximum power that the power grid can carry during transmission. The data acquisition module collects the electrical measurement data through the SCADA system, the full name of the SCADA system is Supervisory Control And Data Acquisition, and the Chinese name is Monitoring and Data Acquisition System, and the full name of SVG is Scalable Vector Graphics, and the Chinese name is Scalable Vector Graphics.

[0024] Specifically, the data acquisition module collects electrical parameters and electrical measurement data to subsequently generate a smart grid SVG, thereby optimizing the smart grid SVG and improving system efficiency.

[0025] Specifically, the power grid SVG generation module constructs the SVG model according to the SVG model construction method to obtain the SVG model, compares the discrimination W in the electrical parameters with the preset discrimination W0, judges the standard state of the SVG model according to the comparison result, and outputs the standardized SVG model according to the judgment result, wherein: When W≥W0, the power grid SVG generation module determines that the standard state of the SVG model is the standard state, and outputs the SVG model as a standardized SVG model; When W<W0, the power grid SVG generation module determines that the standard state of the SVG model is a non-standard state, and does not output the SVG model as a standardized SVG model.

[0026] Specifically, the SVG model refers to an SVG model that inputs the electrical parameters and outputs an embedded electrical parameter. In this embodiment, the power grid SVG generation module constructs the SVG model according to an SVG model construction method, which includes: 70% of the electrical analysis data set is divided into an electrical analysis training set, 15% is divided into an electrical analysis validation set, and 15% is divided into an electrical analysis test set. The electrical analysis training set is input into the recurrent neural network model to train the recurrent neural network model, and the electrical analysis validation set is input into the trained recurrent neural network model. The hyperparameters of the trained recurrent neural network model are iteratively optimized, and the electrical analysis test set is input into the iteratively optimized recurrent neural network model to perform electrical analysis testing on the iteratively optimized recurrent neural network model to obtain the electrical analysis test results. The total number of samples in the electrical analysis test set is set to d0, the number of correct electrical analysis test samples is set to d, and the electrical analysis test accuracy is set to D, D=d / d0. The electrical analysis test accuracy D is compared with the preset electrical analysis test accuracy D0. According to the comparison result, the training compliance of the iteratively optimized recurrent neural network model is judged, and the judgment result is output, where: When D≥D0, the power grid SVG generation module determines that the iteratively optimized recurrent neural network model has met the training standards, outputs the iteratively optimized recurrent neural network model as an SVG model, and provides the SVG model to the power grid SVG generation module; When D<D0, the power grid SVG generation module determines that the training of the iteratively optimized recurrent neural network model does not meet the standards, updates the electrical analysis data set to obtain an updated electrical analysis data set, and trains, iteratively optimizes hyperparameters, and analyzes and tests the recurrent neural network model based on the updated electrical analysis data set until the recurrent neural network model training meets the standards. The electrical analysis data set refers to a data set used to construct the SVG model, the electrical analysis data set includes historically acquired electrical parameters and an SVG model with embedded electrical parameters corresponding to the historically acquired electrical parameters, the electrical analysis data set refers to a data set divided in the electrical analysis data set for training the recurrent neural network model, the recurrent neural network model refers to a model infrastructure for constructing the SVG model, the electrical analysis verification set refers to a data set divided in the electrical analysis data set for verifying the training results of the recurrent neural network model, the electrical analysis test set refers to a data set divided in the electrical analysis data set for testing the recurrent neural network model, the electrical analysis test accuracy refers to the ratio of the number of correct electrical analysis test samples to the total number of samples in the electrical analysis test set, and the preset electrical analysis test accuracy refers to the accuracy of the electrical analysis test used for the iterative The preset value for judging the compliance of the training of the iteratively optimized recurrent neural network model is used. This embodiment does not limit the preset electrical analysis test accuracy rate. Those skilled in the art can set it according to actual needs. It only needs to meet the requirements for judging the compliance of the training of the iteratively optimized recurrent neural network model. For example, the preset electrical analysis test accuracy rate D0 can be set to: 90%≤D0≤95%. The compliance of the training of the iteratively optimized recurrent neural network model refers to the compliance of the accuracy of the trained recurrent neural network model. The compliance of the training of the iteratively optimized recurrent neural network model includes compliance and non-compliance. The preset discrimination refers to a preset value for judging the discrimination. This embodiment does not limit the specific value of the preset discrimination rate. Those skilled in the art can set it according to actual needs. It only needs to meet the requirements for judging the standard state of the SVG model. For example, the preset discrimination rate W0 can be set to: 0≤W0≤1. The standard state of the SVG model refers to whether the SVG model is standard based on the discrimination and the preset discrimination rate. The standard state of the SVG model includes a standard state and a non-standard state. The standardized SVG model refers to the SVG model output when the standard state of the SVG model is the standard state.

[0027] Specifically, the power grid SVG generation module constructs the SVG model according to the SVG model construction method to obtain the SVG model, and compares the discrimination W in the electrical parameters with the preset discrimination W0, judges the standard state of the SVG model based on the comparison result, and outputs the standardized SVG model based on the judgment result, thereby improving the efficiency of electrical parameter analysis and the accuracy of outputting the standardized SVG model.

[0028] Specifically, the grid SVG generation module analyzes the electrical connection relationship based on the grid equipment to obtain an electrical connection result, and constructs an electrical path model based on a graph theory algorithm to obtain an electrical path model. The electrical connection result, line impedance, and load capacity are input into the electrical path model to output an optimal electrical path. The graph theory algorithm includes: 70% of the electrical path data set is divided into an electrical path training set, 15% is divided into an electrical path verification set, and 15% is divided into an electrical path test set. The electrical path training set is input into the Floyd-Warshall algorithm to train the Floyd-Warshall algorithm, and the electrical path verification set is input into the trained Floyd-Warshall algorithm. The hyperparameters of the trained Floyd-Warshall algorithm are iteratively optimized, and the electrical path test set is input into the iteratively optimized Floyd-Warshall algorithm to perform an electrical path test on the iteratively optimized Floyd-Warshall algorithm to obtain the electrical path test results. The total number of samples in the electrical path test set is set to h0, the number of correct electrical path test samples is set to h, and the electrical path test accuracy is set to H, H=h / h0. The electrical path test accuracy H is compared with the preset electrical path test accuracy H0. According to the comparison result, the training compliance of the iteratively optimized Floyd-Warshall algorithm is judged, and the judgment result is output, where: When H≥H0, the power grid SVG generation module determines that the iteratively optimized Floyd-Warshall algorithm training meets the standard, outputs the iteratively optimized Floyd-Warshall algorithm as an electrical path model, and provides the electrical path model to the power grid SVG generation module; When H<H0, the power grid SVG generation module determines that the iteratively optimized Floyd-Warshall algorithm training does not meet the standards, updates the electrical path dataset to obtain an updated electrical path dataset, and trains the Floyd-Warshall algorithm, iteratively optimizes hyperparameters, and performs analysis and testing based on the updated electrical path dataset until the Floyd-Warshall algorithm training meets the standards.

[0029] Specifically, the electrical connection relationship refers to the connection relationship between electrical devices. This embodiment does not limit the method of the electrical connection relationship. Those skilled in the art can set it according to actual needs. For example, the electrical connection relationship can be set as: the busbar is connected to the transformer. The electrical connection result refers to the result obtained by analyzing the electrical connection relationship. The graph theory algorithm refers to a method for constructing an electrical path model. The electrical path model refers to a model with electrical connection results, line impedance and load capacity as input and the optimal electrical path as output. The electrical path dataset refers to a data set used to construct the electrical path model. The electrical path dataset includes historically obtained electrical connection results, line impedance and load capacity and historically obtained electrical connection results, line impedance and load capacity corresponding to the optimal electrical path. The electrical path training set refers to a dataset divided in the electrical path dataset for training the Floyd-Warshall algorithm. The Floyd-Warshall algorithm refers to a model infrastructure for constructing the electrical path model. The electrical path verification set refers to a dataset divided in the electrical path dataset for Fl The Floyd-Warshall algorithm is used to verify the training results of the Floyd-Warshall algorithm. The electrical path test set refers to a data set divided from the electrical path data set for testing the Floyd-Warshall algorithm. The electrical path test accuracy refers to the ratio of the number of correct electrical path test samples to the total number of samples in the electrical path test set. The preset electrical path test accuracy refers to a preset value used to judge whether the training of the iteratively optimized Floyd-Warshall algorithm meets the standard. This embodiment does not limit the preset electrical path test accuracy. Those skilled in the art can set it according to actual needs. It only needs to meet the requirements for judging the training standard of the iteratively optimized Floyd-Warshall algorithm. For example, the preset electrical path test accuracy H0 can be set to: 90%≤H0≤95%. The training standard of the iteratively optimized Floyd-Warshall algorithm refers to whether the accuracy of the trained Floyd-Warshall algorithm meets the standard. The training standard of the iteratively optimized Floyd-Warshall algorithm includes meeting the standard and failing to meet the standard.

[0030] Specifically, the power grid SVG generation module constructs an electrical path model based on a graph theory algorithm to obtain an electrical path model, inputs the electrical connection results, line impedance and load capacity into the electrical path model, outputs an optimal electrical path, and implements load balancing pre-layout through the optimal electrical path.

[0031] Specifically, the power grid SVG generation module maps the electrical measurement data using a mapping method to obtain an SVG visual attribute solution, wherein the mapping method includes: Step S01: The power grid SVG generation module establishes a mapping method; Step S02: The power grid SVG generation module maps the electrical measurement data using the mapping method. Compare the visual distinction Y with the preset visual distinction Y0, judge the visual distinction based on the comparison result, and output the SVG visual attribute solution based on the judgment result, where: When Y≥Y0, the power grid SVG generation module determines that the visual distinction is normal and outputs the SVG visual attribute solution; When Y<Y0, the power grid SVG generation module determines that the visual distinction is abnormal and does not output the SVG visual attribute solution.

[0032] Specifically, the mapping method refers to a method for mapping electrical measurement data. This embodiment does not limit the specific mapping method. Those skilled in the art can set it according to actual conditions. For example, when the current value I=1A, the line width WA can be set to: 0.3mm≤WA≤0.7mm; when the load rate V>90%, the overload line is set to trigger a red pulsating alarm; when the fault state type is abnormal, the fault line automatically switches to a dotted line flashing mode. The overload line refers to a line with a line load rate value that is too large. The red pulsating alarm refers to a periodic SVG highlighted alarm mode. The dotted line flashing mode refers to the SVG graphic becoming a dotted line. The preset visual distinction refers to a preset value for judging the visual distinction. This embodiment does not limit the specific value of the preset visual distinction. Those skilled in the art can set it according to actual conditions, as long as the judgment requirements for the visual distinction situation are met. For example, the preset visual distinction Y0 can be set to: 25ΔΕ≤Y0≤35ΔΕ. The visual distinction situation refers to whether the visual distinction is normal based on the visual distinction and the preset visual distinction. The visual distinction situation includes normal data and abnormal data. The SVG visual attribute scheme refers to the SVG visual scheme obtained by mapping electrical measurement data.

[0033] Specifically, the power grid SVG generation module maps the electrical measurement data through a mapping method to obtain an SVG visual attribute solution, thereby enhancing the deep integration of power grid visualization management and real-time monitoring of operating status.

[0034] Specifically, the grid SVG generation module judges the structural characteristics according to the voltage value U in the electrical parameter, and outputs the optimal layout solution according to the judgment result, wherein: When U=500kV, the grid SVG generation module determines that the structural characteristics are the backbone network and outputs the optimal layout solution. In this case, the optimal layout solution uses a force-directed algorithm. When U=220kV, the grid SVG generation module determines that the structural characteristics are regional network and outputs the optimal layout solution, which is a grid layout. When U=110kV, the grid SVG generation module determines that the structural characteristics are a distribution network and outputs the optimal layout solution, which is a radial layout. When U=35kV, the grid SVG generation module determines that the structural characteristics are critical load centers and outputs the optimal layout solution. At this time, the optimal layout solution includes applying gravitational field constraints.

[0035] Specifically, the structural characteristic situation refers to the structural characteristic situation judged according to the voltage value, and the structural characteristic situation includes the backbone network, regional network, distribution network and key load center. The optimal layout scheme refers to the scheme output according to the structural characteristic situation judged according to the voltage value. The force-directed algorithm refers to a method for optimizing the SVG layout scheme. This embodiment does not limit the specific calculation method of the force-directed algorithm. Those skilled in the art can set it up according to actual conditions, and only need to meet the requirements for optimizing the SVG layout scheme. For example, an electrical parameter weighted model can be used for calculation. The electrical parameter weighted model refers to a calculation method of the force-directed algorithm. The grid layout refers to the gridding method of the power grid layout. This embodiment does not limit the specific method of the grid layout. Those skilled in the art can set it up according to actual conditions. Personnel can set it up according to actual conditions. For example, an impedance matrix grid can be used. The impedance matrix grid is a grid method based on the distance between electrical equipment. The radial layout refers to the radial layout of the power grid. This embodiment does not limit the specific method of the radial layout. Those skilled in the art can set it up according to actual conditions. For example, a capacity-weighted radial layout can be used. The capacity-weighted radial layout refers to a layout that considers the impact of capacity on the radial layout. The imposition of gravitational field constraints refers to a method of imposing a gravitational field to constrain the SVG layout. This embodiment does not limit the specific method of imposing gravitational field constraints. Those skilled in the art can set it up according to actual conditions. For example, a multi-point gravitational field can be used. The multi-point gravitational field refers to a gravitational field with multiple gravitational centers, and the gravitational center refers to the center of the gravitational field.

[0036] Specifically, the grid SVG generation module judges the structural characteristics based on the voltage value U in the electrical parameters and outputs the optimal layout plan based on the judgment result, thereby improving the efficiency of understanding the structural characteristics of the grid and enhancing the timeliness of the optimal layout plan for different structural characteristics.

[0037] Specifically, the power grid SVG generation module constructs an SVG generation model using an SVG generation model construction method to obtain an SVG generation model, inputs the standardized SVG model, the optimal electrical path, the SVG visual attribute solution, and the optimal layout solution into the SVG generation model, and obtains a smart grid SVG output by the SVG generation model. The SVG generation model construction method includes: 70% of the generated data set is divided into a solution generation training set, 20% is divided into a solution generation verification set, and 10% is divided into a solution generation test set. The solution generation training set is input into the convolutional neural network to train the convolutional neural network, and the solution generation verification set is input into the trained convolutional neural network. The hyperparameters of the trained convolutional neural network are iteratively optimized, and the solution generation test set is input into the iteratively optimized convolutional neural network to perform a solution generation test on the iteratively optimized convolutional neural network to obtain the solution generation test result. The total number of samples in the solution generation test set is set to j0, the number of correct solution generation test samples is set to j, and the solution generation test accuracy is set to J. J=j / j0 is set. The solution generation test accuracy J is compared with the preset solution generation test accuracy J0. According to the comparison result, the training compliance of the iteratively optimized convolutional neural network is judged, and the SVG generation model is output according to the judgment result, where: When J≥J0, the power grid SVG generation module determines that the iteratively optimized convolutional neural network training meets the standards, outputs the iteratively optimized convolutional neural network as an SVG generation model, and provides the SVG generation model to the power grid SVG generation module; When J<J0, the power grid SVG generation module determines that the iteratively optimized convolutional neural network training does not meet the standards, updates the generated data set to obtain an updated generated data set, and trains the convolutional neural network, iteratively optimizes hyperparameters, and performs analysis and testing based on the updated generated data set until the convolutional neural network training meets the standards.

[0038] Specifically, the smart grid SVG refers to an SVG diagram of a smart grid obtained by analyzing a standardized SVG model, an optimal electrical path, an SVG visual attribute scheme, and an optimal layout scheme through an SVG generation model. The SVG generation model refers to a convolutional neural network that inputs the standardized SVG model, the optimal electrical path, the SVG visual attribute scheme, and the optimal layout scheme, and outputs the smart grid SVG. The generation data set refers to a data set used to construct the SVG generation model. The generation data set includes the historically acquired standardized SVG model, the optimal electrical path, the SVG visual attribute scheme, and the optimal layout scheme, and the smart grid SVG corresponding to the historically acquired standardized SVG model, the optimal electrical path, the SVG visual attribute scheme, and the optimal layout scheme. The solution generation training set refers to a data set divided in the generation data set for training the convolutional neural network. The solution generation verification set refers to a data set divided in the generation data set for A data set for verifying the training results of a convolutional neural network, the scheme generation test set refers to a data set for testing the convolutional neural network divided in the generated data set, the scheme generation test accuracy refers to the ratio of the number of correct scheme generation test samples to the total number of samples in the scheme generation test set, the preset scheme generation test accuracy refers to a preset value for judging whether the training of the iteratively optimized convolutional neural network meets the standards, and this embodiment does not limit the preset scheme generation test accuracy. Those skilled in the art can set it by themselves according to actual needs, and only need to meet the requirements for judging whether the training of the iteratively optimized convolutional neural network meets the standards. For example, the preset scheme generation test accuracy J0 can be set to: 90%≤J0≤95%, and the training compliance of the iteratively optimized convolutional neural network refers to the accuracy compliance of the trained convolutional neural network, and the training compliance of the iteratively optimized convolutional neural network includes compliance and non-compliance.

[0039] Specifically, the power grid SVG generation module inputs the standardized SVG model, optimal electrical path, SVG visual attribute scheme, and optimal layout scheme into the SVG generation model to obtain a smart grid SVG output by the SVG generation model, thereby enhancing the comprehensiveness of the smart grid SVG and improving the intelligence of the power grid SVG generation.

[0040] Specifically, the grid SVG visualization module obtains the working status of the relay protection device based on the current value in the electrical measurement data, obtains the working status of the relay protection device, and outputs the working content of the SVG visualization area based on the working status of the relay protection device, wherein: When the working state of the relay protection device is the protection state, the grid SVG visualization module outputs the SVG visualization area, and the working content is to automatically highlight the associated device group and dynamically render the SVG visualization area; When the working state of the relay protection device is the maintenance state, the grid SVG visualization module outputs the SVG visualization area, and the working content is to display the device isolation boundary and dynamically render the SVG visualization area.

[0041] Specifically, the working state of the relay protection device refers to the state of obtaining the working state of the relay protection device through the current value. The relay protection device refers to a device that sends an alarm signal for the operating state of electrical equipment and automatic fault detection. This embodiment does not limit the specific method for obtaining the working state of the relay protection device. Those skilled in the art can set it according to actual conditions. It only needs to meet the need to obtain the working state of the relay protection device. For example, it can be set that when the current value I is: 1.5In≤I≤3In, the relay protection device is started and the working state of the relay protection device is obtained. The working state of the relay protection device includes the protection state and the maintenance state. The SVG visualization area refers to the working content output by the working state of the relay protection device. The highlight Association refers to connecting with electrical equipment by increasing the brightness of the SVG visualization area. The dynamic rendering refers to the method of adjusting the working status and equipment parameters of the SVG visualization area. This embodiment does not limit the specific adjustment method of dynamic rendering. Those skilled in the art can set it themselves according to actual conditions, such as adjusting the dynamic rendering by switching the constant group. The constant group switching refers to switching the preset constants of the relay protection device. The constant refers to the preset conditions for the electrical parameters set by the relay protection device. The equipment isolation boundary refers to isolating the maintenance equipment boundary in the maintenance state. This embodiment does not limit the specific division method of the equipment isolation boundary. Those skilled in the art can set it themselves according to actual conditions, such as dividing it by the boundary of the electrical bus.

[0042] Specifically, the power grid SVG visualization module obtains the working status of the relay protection device and outputs the working content of the SVG visualization area according to the working status of the relay protection device, solving the problem that traditional systems cannot intuitively display the protection area and improving the intuitiveness and operability of the system's SVG visualization area.

[0043] Specifically, the grid SVG reconstruction self-healing module adjusts the smart grid SVG according to the grid change event, verifies the load condition according to the adjustment process of the smart grid SVG, and obtains a grid SVG change instruction, wherein: When the grid change event is a device switching event, the smart grid SVG is adjusted to redraw the affected local topology; When the grid change event is a network reconstruction event, the smart grid SVG is adjusted, the optimal electrical path is recalculated, and the connection points are automatically magnetically attracted according to the recalculated optimal electrical path.

[0044] Specifically, the power grid change event refers to an event that causes a change in the electrical state due to situations such as equipment switching and network reconstruction in the power grid. The power grid change event includes equipment switching events and network reconstruction events. The equipment switching event refers to an event in which electrical equipment is switched on or off. This embodiment does not limit the specific manner of the equipment switching event. Those skilled in the art can set it up according to actual conditions. For example, in the event of maintenance, the network reconstruction event refers to an event that affects the power grid when the power grid network changes. This embodiment does not limit the specific manner of the network reconstruction event. Those skilled in the art can set it up according to actual conditions. For example, in the event of a short circuit, the load condition refers to the distribution of the power grid load after the power grid change event occurs. This embodiment does not limit the specific acquisition of load conditions. Those skilled in the art can set it according to actual conditions, such as through AI prediction and verification. The power grid SVG change instruction refers to an instruction obtained by adjusting the smart grid SVG. This embodiment does not limit the specific transmission method of the power grid SVG change instruction. Those skilled in the art can set it according to actual conditions, such as through differential coding transmission. The differential coding refers to a method of transmitting the power grid SVG change instruction. The local topology refers to the electrical connection relationship between certain electrical equipment in the power grid. The automatic magnetic adsorption connection point refers to the situation where the connection point of the electrical equipment is automatically adsorbed by attraction. The connection point refers to a location point where electrical equipment can be connected.

[0045] Specifically, the grid SVG reconstruction self-healing module adjusts the smart grid SVG according to the grid change event, verifies the load situation according to the adjustment process of the smart grid SVG, obtains the grid SVG change instruction, realizes the closed-loop control of the adjustment and load balancing of the smart grid SVG, and improves the system stability.

[0046] Specifically, the power grid SVG multi-terminal operation module constructs a conflict detection model using a conflict detection model construction method to obtain a conflict detection model, inputs the power grid SVG change instruction into the conflict detection model, and obtains a conflict detection result output by the conflict detection model.

[0047] Specifically, the conflict detection model construction method refers to dividing the conflict analysis data set into a 70% conflict analysis training set, a 20% conflict analysis validation set, and a 10% conflict analysis test set, inputting the conflict analysis training set into a graph neural network model to train the graph neural network model, and inputting the conflict analysis validation set into the trained graph neural network model, performing iterative optimization of hyperparameters on the trained graph neural network model, and inputting the conflict analysis test set into the iteratively optimized graph neural network model to perform a conflict analysis test on the iteratively optimized graph neural network model to obtain a conflict analysis test result, setting the total number of samples in the conflict analysis test set to f0, the number of correct conflict analysis test samples to f, the conflict analysis test accuracy to F, F=f / f0, comparing the conflict analysis test accuracy F with the preset conflict analysis test accuracy F0, judging the training compliance of the iteratively optimized graph neural network model based on the comparison result, and outputting the judgment result, wherein: When F≥F0, the power grid SVG multi-terminal operation module determines that the iteratively optimized graphical neural network model has met the training standards, outputs the iteratively optimized graphical neural network model as a conflict detection model, and provides the conflict detection model to the power grid SVG multi-terminal operation module; When F<F0, the power grid SVG multi-terminal operation module determines that the training of the iteratively optimized graphical neural network model does not meet the standards, updates the conflict analysis data set to obtain an updated conflict analysis data set, and trains, iteratively optimizes hyperparameters, and analyzes and tests the graphical neural network model based on the updated conflict analysis data set until the graphical neural network model training meets the standards. The conflict detection model refers to a graphical neural network model that takes the preprocessed power grid SVG change instruction as input and outputs the conflict detection result. The conflict analysis data set refers to a data set used to construct the conflict detection model. The conflict analysis data set includes historically obtained power grid SVG change instructions and conflict detection results corresponding to historically obtained power grid SVG change instructions. The conflict analysis training set refers to a data set divided from the conflict analysis data set for training the graphical neural network model. The conflict analysis verification set refers to a data set divided from the conflict analysis data set for verifying the training results of the graphical neural network model. The conflict analysis test set refers to the conflict analysis data set. The data set for testing the graph neural network model divided in the graph neural network model refers to the model infrastructure for constructing the conflict detection model. The conflict analysis test accuracy refers to the ratio of the number of correct conflict analysis test samples to the total number of samples in the conflict analysis test set. The preset conflict analysis test accuracy refers to the preset value used to judge whether the training of the iteratively optimized graph neural network model meets the standards. This embodiment does not limit the preset conflict analysis test accuracy. Those skilled in the art can set it according to actual needs. It only needs to meet the requirements for judging the training standards of the iteratively optimized graph neural network model. For example, the preset conflict analysis test accuracy F0 can be set to: 90%≤F0≤95%. The training standards of the iteratively optimized graph neural network model refer to the accuracy standards of the trained graph neural network model. The training standards of the iteratively optimized graph neural network model include standards and non-standards. The conflict detection result refers to the result output after the power grid SVG change instruction is input into the conflict detection model.

[0048] Specifically, the power grid SVG multi-terminal operation module constructs a conflict detection model through a conflict detection model construction method to obtain a conflict detection model, inputs the power grid SVG change instruction into the conflict detection model, obtains the conflict detection result output by the conflict detection model, and improves the coordination of power grid scheduling.

[0049] Specifically, the power grid SVG optimization module corrects the standardized SVG model, the SVG visual attribute scheme, and the power grid SVG change instruction according to the conflict detection result, wherein: When the conflict detection result is inconsistent with the standardized SVG model, the power grid SVG optimization module corrects the preset discrimination, calculates the preset discrimination W01 according to the error rate Sm and the first weight coefficient α1, sets W01=α1×Sm, obtains the corrected preset discrimination W01, replaces the preset discrimination W0 with the corrected preset discrimination W01, and re-compares the discrimination W with the corrected preset discrimination W01; When the conflict detection result is inconsistent with the SVG visual attribute scheme, the power grid SVG optimization module corrects the preset visual discrimination, calculates the preset visual discrimination Y01 according to the error rate Sm and the second weight coefficient α2, sets Y01=α2×Sm, obtains the corrected preset visual discrimination Y01, replaces the preset visual discrimination Y0 with the corrected preset visual discrimination Y01, and re-compares the visual discrimination Y with the corrected preset visual discrimination Y01; When the conflict detection result is inconsistent with the grid SVG change instruction, the grid SVG optimization module corrects the adjustment process of the smart grid SVG to obtain a corrected grid SVG change instruction, pushes the corrected grid SVG change instruction to the administrator terminal, and issues an alarm to the terminal.

[0050] Specifically, the error rate refers to the probability of being inconsistent with the preset value, and the preset value includes the preset discrimination and the preset visual discrimination. The first weight coefficient is a coefficient for calculating the preset discrimination. This embodiment does not limit the first weight coefficient. Those skilled in the art can set it by themselves according to actual needs. It only needs to meet the need to calculate the preset discrimination. For example, the first weight coefficient α1 can be set to: 1<α1<1.5. The second weight coefficient refers to the coefficient for calculating the preset visual discrimination. This embodiment does not limit the second weight coefficient. Those skilled in the art can set it by themselves according to actual needs. It only needs to meet the need to calculate the preset visual discrimination. For example, the second weight coefficient α2 can be set to: 1<α2<1.5. The administrator terminal refers to a system terminal with administrator authority.

[0051] Specifically, the power grid SVG optimization module corrects the standardized SVG model, SVG visual attribute scheme, and power grid SVG change instructions according to the conflict detection result, thereby improving the accuracy and efficiency of the power grid topology.

[0052] Specifically, the power grid SVG optimization module compares the number of standardized SVG model inconsistencies P with a preset number of standardized SVG model inconsistencies p0, determines the inconsistency of the standardized SVG model based on the comparison result, and modifies the standardized SVG model correction process based on the determination result, wherein: When P≤P0, the power grid SVG optimization module determines that the inconsistency of the standardized SVG model is normal and does not modify the preset discrimination correction process; When P>P0, the grid SVG optimization module determines that the inconsistency of the standardized SVG model is an abnormal situation, and corrects the process of the preset discrimination correction by using the coefficient g to correct the preset discrimination W01 and set , e is the base of the natural logarithm, and the corrected preset discrimination W02 is obtained. Set W02 = α1 / (0.47+g), replace the preset discrimination W0 with the corrected preset discrimination W02, and re-compare the discrimination W with the corrected preset discrimination W02; The power grid SVG optimization module compares the number of SVG visual attribute scheme inconsistencies X with the preset number of SVG visual attribute scheme inconsistencies X0, determines the inconsistency of the SVG visual attribute scheme based on the comparison result, and modifies the SVG visual attribute scheme correction process based on the judgment result, wherein: When X≤X0, the power grid SVG optimization module determines that the inconsistency of the SVG visual attribute scheme is normal and does not modify the preset visual discrimination correction process; When X>X0, the power grid SVG optimization module determines that the inconsistency of the SVG visual attribute scheme is an abnormal situation, and corrects the preset visual discrimination correction process, corrects the preset visual discrimination Y01 by the visual coefficient N, and sets , e is the base of the natural logarithm, and the corrected preset visual discrimination Y02 is obtained. Set Y02 = α2 / (0.47+g), replace the preset visual discrimination Y0 with the corrected preset visual discrimination Y02, and re-compare the visual discrimination Y with the corrected preset visual discrimination Y02; Specifically, the number of standardized SVG model inconsistencies refers to the number of times the conflict detection result is inconsistent with the standardized SVG model. This embodiment does not limit the method for obtaining the number of standardized SVG model inconsistencies. Those skilled in the art can set it by themselves according to actual needs, such as through a power grid conflict detection platform. The power grid conflict detection platform refers to a platform for obtaining power grid conflict detection. The preset number of standardized SVG model inconsistencies refers to a preset value for judging the number of standardized SVG model inconsistencies. This embodiment does not limit the specific numerical value of the preset standardized SVG model inconsistencies. Those skilled in the art can set it by themselves according to actual conditions. It only needs to meet the judgment requirements for the standardized SVG model inconsistency situation. For example, the preset standardized SVG model inconsistency number P0 can be set to: 3 times / day ≤ Sf0 ≤ 4 times / day. The standardized SVG model inconsistency situation refers to whether the number of standardized SVG model inconsistencies is normal based on the number of standardized SVG model inconsistencies and the preset standardized SVG model inconsistency number. The standardized SVG model inconsistency situation includes normal Normal and abnormal situations, the number of SVG visual attribute scheme inconsistencies refers to the number of times the conflict detection result is inconsistent with the SVG visual attribute scheme. This embodiment does not limit the method for obtaining the number of SVG visual attribute scheme inconsistencies. Those skilled in the art can set it by themselves according to actual needs, such as obtaining it through the power grid conflict detection platform. The preset number of SVG visual attribute scheme inconsistencies refers to the preset value for judging the number of SVG visual attribute scheme inconsistencies. This embodiment does not limit the specific numerical value of the preset number of SVG visual attribute scheme inconsistencies. Those skilled in the art can set it by themselves according to actual conditions, and only needs to meet the judgment requirements for the SVG visual attribute scheme inconsistency. For example, the preset number of SVG visual attribute scheme inconsistencies X0 can be set to: 10 times / day ≤ Sf0 ≤ 12 times / day. The SVG visual attribute scheme inconsistency refers to whether the number of SVG visual attribute scheme inconsistencies is normal based on the number of SVG visual attribute scheme inconsistencies and the preset SVG visual attribute scheme inconsistency number. The SVG visual attribute scheme inconsistency includes normal and abnormal situations.

[0053] Specifically, the power grid SVG optimization module corrects the process of correcting the standardized SVG model according to the number of inconsistencies in the standardized SVG model, and corrects the process of correcting the SVG visual attribute scheme according to the number of inconsistencies in the SVG visual attribute scheme, thereby improving the security of the power grid system and enhancing the intelligence of the system's automatic optimization.

[0054] Specifically, the power grid SVG optimization module compares the number of inconsistencies K of the power grid SVG change instructions with a preset number of inconsistencies K0 of the SVG change instructions, determines the inconsistency of the SVG change instructions based on the comparison result, and updates the SVG change instructions based on the determination result, wherein: When K≤K0, the power grid SVG optimization module determines that the inconsistency of the SVG change instruction is normal and does not update the SVG change instruction; When K>K0, the power grid SVG optimization module determines that the inconsistency of the SVG change instruction is an abnormal situation, updates the SVG change instruction, and updates the inconsistent SVG change instruction as a new SVG change instruction.

[0055] Specifically, the number of inconsistent power grid SVG change instructions refers to the number of times the conflict detection result is inconsistent with the power grid SVG change instruction. This embodiment does not limit the method for obtaining the number of inconsistent power grid SVG change instructions. Those skilled in the art can set it by themselves according to actual needs, such as obtaining it through the power grid conflict detection platform. The preset number of inconsistent power grid SVG change instructions refers to a preset value for judging the number of inconsistent power grid SVG change instructions. This embodiment does not limit the specific numerical value of the preset number of inconsistent power grid SVG change instructions. Those skilled in the art can set it by themselves according to actual conditions, and only needs to meet the judgment requirements for inconsistent power grid SVG change instructions. For example, the preset number of inconsistent power grid SVG change instructions K0 can be set to: 3 times / day ≤ Sf0 ≤ 5 times / day. The inconsistent power grid SVG change instruction refers to whether the number of inconsistent power grid SVG change instructions is normal, as judged based on the number of inconsistent power grid SVG change instructions and the preset number of inconsistent power grid SVG change instructions. The inconsistent power grid SVG change instruction includes normal and abnormal situations.

[0056] Specifically, the power grid SVG optimization module updates the SVG change instruction according to the number of inconsistencies in the power grid SVG change instruction, thereby enhancing the intelligence of the automatic optimization of the system.

[0057] See also Figure 2 As shown, it is a flow chart of the method for constructing a smart grid topology network system based on SVG in this embodiment, including: Step S1 collects electrical parameters and electrical measurement data; Step S2: Outputting the standardized SVG model according to the electrical parameters using the standardized SVG model to obtain a standardized SVG model; analyzing the optimal electrical path according to the electrical parameters using a graph theory algorithm to obtain the optimal electrical path; mapping the electrical measurement data using a mapping method to obtain an SVG visual attribute scheme; optimizing the layout of the SVG according to the electrical parameters to obtain an optimal layout scheme; and outputting a smart grid SVG according to the standardized SVG model, the optimal electrical path, the SVG visual attribute scheme, and the optimal layout scheme to obtain a smart grid SVG; Step S3 obtains the working state of the relay protection device according to the electrical parameters, and outputs the working content of the SVG visualization area according to the working state of the relay protection device; Step S4: acquiring a grid SVG change instruction according to the grid change event; Step S5: obtaining conflict detection results according to the power grid SVG change instruction using the conflict detection model; Step 6 corrects the standardized SVG model, the SVG visual attribute scheme, and the power grid SVG change instruction according to the conflict detection result, corrects the process of correcting the standardized SVG model, corrects the process of correcting the SVG visual attribute scheme, and updates the SVG change instruction.

[0058] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A smart grid topology networking system based on SVG, characterized by: include: Data acquisition module, used to collect electrical parameters and electrical measurement data; a power grid SVG generation module, configured to output the standardized SVG model based on the electrical parameters using a standardized SVG model to obtain a standardized SVG model, analyze an optimal electrical path based on the electrical parameters using a graph theory algorithm to obtain an optimal electrical path, map the electrical measurement data using a mapping method to obtain an SVG visual attribute solution, optimize the layout of the SVG based on the electrical parameters to obtain an optimal layout solution, and output a smart grid SVG based on the standardized SVG model, the optimal electrical path, the SVG visual attribute solution, and the optimal layout solution to obtain a smart grid SVG; The power grid SVG visualization module is used to obtain the working status of the relay protection device based on electrical parameters and output the working content of the SVG visualization area based on the working status of the relay protection device; The grid SVG reconstruction self-healing module is used to obtain grid SVG change instructions based on grid change events; A power grid SVG multi-terminal operation module, configured to obtain conflict detection results according to the power grid SVG change instruction using a conflict detection model; The power grid SVG optimization module is used to correct the standardized SVG model, SVG visual attribute scheme and power grid SVG change instructions based on the conflict detection results, and is also used to correct the process of correcting the standardized SVG model, the process of correcting the SVG visual attribute scheme, and the update of the SVG change instructions.

2. The SVG-based smart grid topology networking system according to claim 1, characterized in that: The power grid SVG generation module constructs the SVG model according to the SVG model construction method to obtain the SVG model, compares the discrimination W in the electrical parameters with the preset discrimination W0, judges the standard state of the SVG model based on the comparison result, and outputs the standardized SVG model based on the judgment result. The power grid SVG generation module analyzes the electrical connection relationship according to the power grid equipment to obtain the electrical connection result, and constructs the electrical path model according to the graph theory algorithm to obtain the electrical path model. The electrical connection result, line impedance and load capacity are input into the electrical path model, and the optimal electrical path is output. The power grid SVG generation module maps the electrical measurement data through a mapping method to obtain an SVG visual attribute scheme. The power grid SVG generation module judges the structural characteristics according to the voltage value U in the electrical parameters, and outputs the optimal layout scheme based on the judgment result.

3. The SVG-based smart grid topology networking system according to claim 2, characterized in that: The power grid SVG generation module constructs an SVG generation model using an SVG generation model construction method to obtain an SVG generation model, inputs the standardized SVG model, the optimal electrical path, the SVG visual attribute scheme, and the optimal layout scheme into the SVG generation model, and obtains a smart grid SVG output by the SVG generation model.

4. The SVG-based smart grid topology networking system according to claim 3, characterized in that: The grid SVG visualization module obtains the working status of the relay protection device according to the current value in the electrical appliance measurement data, obtains the working status of the relay protection device, and outputs the working content of the SVG visualization area according to the working status of the relay protection device, wherein: When the working state of the relay protection device is the protection state, the grid SVG visualization module outputs the SVG visualization area, and the working content is to automatically highlight the associated device group and dynamically render the SVG visualization area; When the working state of the relay protection device is the maintenance state, the grid SVG visualization module outputs the SVG visualization area, and the working content is to display the device isolation boundary and dynamically render the SVG visualization area.

5. The SVG-based smart grid topology networking system according to claim 4, characterized in that: The grid SVG reconstruction self-healing module adjusts the smart grid SVG according to the grid change event, verifies the load condition according to the adjustment process of the smart grid SVG, and obtains a grid SVG change instruction, wherein: When the grid change event is a device switching event, the smart grid SVG is adjusted to redraw the affected local topology; When the grid change event is a network reconstruction event, the smart grid SVG is adjusted, the optimal electrical path is recalculated, and the connection points are automatically magnetically attracted according to the recalculated optimal electrical path.

6. The SVG-based smart grid topology networking system according to claim 5, characterized in that: The power grid SVG multi-terminal operation module constructs a conflict detection model using a conflict detection model construction method to obtain a conflict detection model, inputs the power grid SVG change instruction into the conflict detection model, and obtains a conflict detection result output by the conflict detection model.

7. The SVG-based smart grid topology networking system according to claim 6, characterized in that: The power grid SVG optimization module corrects the standardized SVG model, the SVG visual attribute scheme, and the power grid SVG change instruction according to the conflict detection result, wherein: When the conflict detection result is inconsistent with the standardized SVG model, the power grid SVG optimization module corrects the preset discrimination, calculates the preset discrimination W01 according to the error rate Sm and the first weight coefficient α1, sets W01=α1×Sm, obtains the corrected preset discrimination W01, replaces the preset discrimination W0 with the adjusted preset discrimination W01, and re-compares the discrimination W with the adjusted preset discrimination W01; When the conflict detection result is inconsistent with the SVG visual attribute scheme, the power grid SVG optimization module corrects the preset visual discrimination, calculates the preset visual discrimination Y01 according to the error rate Sm and the second weight coefficient α2, sets Y01=α2×Sm, obtains the corrected preset visual discrimination Y01, replaces the preset visual discrimination Y0 with the corrected preset visual discrimination Y01, and re-compares the visual discrimination Y with the corrected preset visual discrimination Y01; When the conflict detection result is inconsistent with the grid SVG change instruction, the grid SVG optimization module corrects the adjustment process of the smart grid SVG to obtain a corrected grid SVG change instruction, pushes the corrected grid SVG change instruction to the administrator terminal, and issues an alarm to the terminal.

8. The SVG-based smart grid topology networking system according to claim 7, characterized in that: The power grid SVG optimization module compares the number of inconsistencies P of the standardized SVG model with the preset number of inconsistencies p0 of the standardized SVG model, determines the inconsistency of the standardized SVG model based on the comparison result, and modifies the preset discrimination correction process based on the determination result, wherein: When P≤P0, the power grid SVG optimization module determines that the inconsistency of the standardized SVG model is normal and does not modify the preset discrimination correction process; When P>P0, the grid SVG optimization module determines that the inconsistency of the standardized SVG model is an abnormal situation, and corrects the process of the preset discrimination correction by using the coefficient g to correct the preset discrimination W01 and set , e is the base of the natural logarithm, and the corrected preset discrimination W02 is obtained. Set W02 = α1 / (0.47+g), replace the preset discrimination W0 with the corrected preset discrimination W02, and re-compare the discrimination W with the corrected preset discrimination W02; The power grid SVG optimization module compares the number of SVG visual attribute scheme inconsistencies X with the preset number of SVG visual attribute scheme inconsistencies X0, determines the inconsistency of the SVG visual attribute scheme based on the comparison result, and modifies the preset visual discrimination correction process based on the judgment result, wherein: When X≤X0, the power grid SVG optimization module determines that the inconsistency of the SVG visual attribute scheme is normal and does not modify the preset visual discrimination correction process; When X>X0, the power grid SVG optimization module determines that the inconsistency of the SVG visual attribute scheme is an abnormal situation, and corrects the preset visual discrimination correction process, corrects the preset visual discrimination Y01 by the visual coefficient N, and sets , e is the base of the natural logarithm, and the corrected preset visual discrimination Y02 is obtained. Set Y02 = α2 / (0.47+g), replace the preset visual discrimination Y0 with the corrected preset visual discrimination Y02, and re-compare the visual discrimination Y with the corrected preset visual discrimination Y02.

9. The SVG-based smart grid topology networking system according to claim 7, characterized in that: The power grid SVG optimization module compares the power grid SVG change instruction inconsistency number K with the preset SVG change instruction inconsistency number K0, determines the SVG change instruction inconsistency based on the comparison result, and updates the SVG change instruction based on the determination result, wherein: When K≤K0, the power grid SVG optimization module determines that the inconsistency of the SVG change instruction is normal and does not update the SVG change instruction; When K>K0, the power grid SVG optimization module determines that the inconsistency of the SVG change instruction is an abnormal situation, updates the SVG change instruction, and updates the inconsistent SVG change instruction as a new SVG change instruction.

10. A method for the SVG-based smart grid topology networking system according to any one of claims 1 to 9, characterized in that: The method comprises: Step S1, collecting electrical parameters and electrical measurement data; Step S2: Outputting the standardized SVG model according to the electrical parameters using a standardized SVG model to obtain a standardized SVG model; analyzing an optimal electrical path according to the electrical parameters using a graph theory algorithm to obtain an optimal electrical path; optimizing the layout of the SVG according to the electrical parameters of the power grid to obtain an optimal layout solution; and outputting a smart grid SVG according to the standardized SVG model, the optimal electrical path, the optimal electrical path, and the optimal layout solution to obtain a smart grid SVG; Step S3, acquiring the working state of the relay protection device according to the electrical parameters, and outputting the working content of the SVG visualization area according to the working state of the relay protection device; Step S4, obtaining a power grid SVG change instruction according to the power grid change event; Step S5, using a conflict detection model to obtain a conflict detection result according to the power grid SVG change instruction; Step S6: Correct the standardized SVG model, the SVG visual attribute scheme, and the power grid SVG change instruction according to the conflict detection result, correct the standardized SVG model correction process, correct the SVG visual attribute scheme correction process, and update the SVG change instruction.

Images