Transparent panoramic management and control system based on low-voltage power distribution network

Abstract

The invention discloses a transparent panoramic management and control system based on a low-voltage power distribution network, and relates to the technical field of power distribution networks. Compared with a previous power distribution network management and control system, the problem that the accuracy and the reliability of an existing power distribution network transparency system cannot be guaranteed is solved; the data acquisition and processing difficulty is high; the intelligent level and the automation level need to be improved. A topological optimization algorithm and a transparent management and control technology are combined, so that operation data of the power distribution network can be obtained in real time, and accurate analysis and prediction can be carried out; and by utilizing technologies such as artificial intelligence and the Internet of Things, rapid fault positioning, automatic isolation and power supply recovery are realized, and the reliability and the safety of power supply are improved. Through the transparent management and control platform for the power distribution network, full transparency and full perception of the power distribution network are realized, comprehensive, real-time and accurate operation data of the power distribution network are provided, and a user is helped to better understand the real-time state of the power distribution network, predict the future operation trend, optimize resource configuration, improve the operation efficiency and ensure the reliability and safety of power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution networks, and particularly to a transparent panoramic control system based on a low-voltage distribution network. Background Art

[0002] In China, with the rapid development of new energy and the gradual opening of the power market, the construction of transparent distribution networks has become an important development direction in the power industry. In recent years, China has increased its research and application efforts on transparent distribution network technologies and achieved many results. For example, by introducing advanced information technologies, big data, cloud computing and other technical means, the real-time monitoring and data analysis of the operation status of the distribution network have been realized, improving the fault handling efficiency and power supply reliability. At the same time, the intelligent upgrade and digital transformation of the distribution network have been promoted, enhancing the management level and operation efficiency of the distribution network.

[0003] Internationally, the construction of transparent distribution networks has also received extensive attention. Developed countries such as those in Europe and America started earlier in the automation and intelligence of distribution networks and have formed relatively mature technical systems and application experiences. In the construction of transparent distribution networks, these countries pay attention to the combination of technology research and development and application practice, promoting the digitalization, intelligence and sustainable development of distribution networks. At the same time, international exchanges and cooperation on transparent distribution network technologies have been strengthened, promoting the development of global transparent distribution network technologies. The development history of foreign transparent distribution networks can be summarized into the following key stages, each stage being accompanied by technological progress and application expansion: 1) Initial exploration stage: Countries began to explore the use of digital and information technologies to improve the transparency of distribution networks. For example, by installing simple sensors and data acquisition devices, the preliminary collection and analysis of the operation data of the distribution network were realized. 2) Concept formation stage: The concept of a transparent power grid gradually took shape, emphasizing the core of digital data to achieve the visibility, knowability and controllability of the power system, with any state being transparent. 3) Technology verification and pilot stage: Countries began to verify the feasibility and effectiveness of transparent power grid technologies through actual projects. For example, deploying small intelligent sensors in the distribution network to monitor the operation status of power equipment and the operation of the power grid in real time. At the same time, pilot projects of transparent power grids were carried out in many countries and regions. 4) Large-scale deployment and application stage: With the continuous maturity of technologies and the continuous expansion of applications, transparent power grid technologies have gradually been widely recognized and applied. Countries began to deploy transparent power grid technologies on a large scale, promoting the digital and intelligent transformation of distribution networks. 5) Continuous innovation and development stage: With the continuous development of new generation technologies such as 5G, Internet of Things, artificial intelligence, etc., transparent power grid technologies are also constantly innovating and progressing. The application fields of transparent power grid technologies are also constantly expanding, such as distributed energy access, microgrid operation, demand response, etc.

[0004] However, the construction of the transparent distribution network still faces some challenges and issues that need further research. First of all, how to ensure the accuracy and reliability of the distribution network data is an important issue. Due to the complexity and diversity of the distribution network, it is difficult to collect and process data, and advanced technical means and methods are needed to ensure the accuracy and reliability of the data. Secondly, how to achieve the intelligence and automation of the distribution network is also an important issue. At present, the level of intelligence and automation of the distribution network still needs to be improved, and further strengthening of technology research and development and application practice is required. In addition, it is also necessary to study the impact of the construction of the transparent distribution network on aspects such as the power market and the energy consumption structure, and how to better promote the sustainable development of the construction of the transparent distribution network.

[0005] To solve the above problems, the present invention proposes a transparent panoramic control system based on the low-voltage distribution network. Summary of the Invention

[0006] The purpose of the present invention is to propose a transparent panoramic control system based on the low-voltage distribution network to solve the problems raised in the background technology: The accuracy and reliability of the existing distribution network transparency system cannot be guaranteed; the difficulty of data collection and processing is large; the level of intelligence and automation needs to be improved.

[0007] To achieve the above purpose, the present invention adopts the following technical solutions: A transparent panoramic control system based on the low-voltage distribution network, comprising: A transparent topology identification and display module: used for multi-dimensional transparent panoramic display of the distribution network; A power outage area visualization module: used to build the matching relationship between the power outage equipment and the power outage scope at the regional level, and realize the full-dimensional visualization display of the power outage area; A transparent panoramic display module: used for comprehensively and dynamically displaying the information of each dimension of the low-voltage distribution network; The transparent topology identification and display module includes: A first data collection and processing module: used to collect power parameters and power equipment information based on a number of data collection devices, and preprocess the collected data; A topology identification and establishment module: used to identify the topology of the distribution network based on the topology optimization algorithm, and build a grid transparent topology relationship model based on this, and draw a distribution network frame topology diagram; A first visualization module: used to display the topology structure of the distribution network in a graphical manner; An intelligent analysis and decision-making module: used to monitor and warn the operation status of the distribution network in real time, quickly locate and handle faults, and optimize the dispatching of the network; The power outage area visualization module includes: The second data acquisition and processing module: used to collect, clean, and store information related to power outages in the distribution network; The power outage event correlation analysis module: used to identify the equipment and connection relationships of the distribution network in the power outage area based on the topology optimization algorithm and conduct correlation analysis; The power outage scope prediction module: used to build a prediction model for the power outage scope based on historical data and real-time data; The second visualization module: used to visually display the distribution network equipment and the power outage area based on map visualization and interactive visualization technologies and interact with users; The analysis model construction module: used to build a visual analysis model for the power outage area based on the topology structure, equipment parameters, and real-time data of the distribution network, and analyze the power outage area through the visual analysis model of the power outage area.

[0008] Preferably, the first data acquisition and processing module and the second data acquisition and processing module collect relevant data based on radio frequency identification technology, barcode technology, sensor technology, M2M technology, remote sensing technology, and intelligent information devices.

[0009] Preferably, the specific identification steps of the topology optimization algorithm in the topology identification and establishment module are as follows: Define the mapping relationship between the device information of each node in the distribution network and the power pulse signal collector, set the power pulse signal collector at each node in the distribution network, and collect the power pulse signal ; there is a one-to-one mapping relationship between the power pulse signal collector and the corresponding circuit information and equipment information; Use the adjacency matrix as the logical matrix for topology identification. For any directed line segment in the system from node output, to node input, without passing through any other nodes in between, then nodes and are called adjacent nodes; thus, a -dimensional logical matrix is established through the power pulse signal. When and are adjacent nodes, then the logical matrix element ; otherwise, the logical matrix element , and the upper triangular matrix of the adjacency matrix is intercepted and input into the topology structure identification model; After the establishment of the logical matrix is completed, the adjacency matrix is topologically identified for three basic structures one by one according to the criterion, specifically as follows: Series structure identification criterion:

[0010] Among them, 、 、 All represent logical matrix elements; Nodes that satisfy the above formula are identified as the topological relationship of the series structure; Criterion for identifying the shunt structure:

[0011] Among them, 、 、 、 All represent logical matrix elements; Nodes that satisfy the above formula are identified as the topological relationship of the shunt structure; Criterion for identifying the convergence structure:

[0012] Among them, 、 All represent logical matrix elements; Nodes that satisfy the above formula are identified as the topological relationship of the convergence structure; Through the above steps, the conversion from the logical matrix to the topological information is completed. Based on the improved brainstorm optimization algorithm, the distribution network is traversed, and the topological relationship between nodes is determined in turn to realize the intelligent identification of the distribution network topological structure; the specific improved brainstorm optimization algorithm is as follows: Initialize the distribution network nodes, perform initial clustering processing on the distribution network nodes based on the k-means algorithm, and define the optimal individual of each class, that is, the key nodes in the topological structure are the class centers; The algorithm randomly selects one or two node individuals in the class and mutates the node individuals based on the following method, that is, the local optimization of the topological structure:

[0013] Among them, is the mutated node individual, is the node individual to be mutated; 、 、 、 are the node individuals randomly selected from the parent population; is the mutation factor; For the node individuals of a selected class, the mutated node individuals are used as the final node individuals; for the node individuals from different clusters, the following fusion is performed:

[0014] Among them, is the mutated node individual generated after the fusion of two node individuals, and are the two node individuals accepting the fusion; is a random number between; Update the node individuals in the following way:

[0015] wherein, is the node individual before the -th iteration update; is the node individual after the -th iteration update; is the globally optimal node individual; is the globally optimal influence coefficient of the -th iteration; is the probability of the node individual to be mutated;

[0016] wherein, is the probability of selecting a node individual through a class; is the probability of selecting the class center after selecting a class; is the probability of selecting the class center for fusion after selecting two classes;

[0017] wherein, and are the maximum and minimum values of the globally optimal influence coefficient respectively; is the maximum number of iterations.

[0018] Preferably, the power outage range prediction module is combined with a graph neural network based on the topology recognition result, constructs a graph network corresponding to the topology recognition result, and each node and edge has corresponding power attributes; constructs a power outage prediction model based on the graph neural network, wherein the graph neural network combines a variant convolution structure, specifically as follows:

[0019] wherein, is the dilated convolution kernel; is the dilation coefficient; is the input value; corresponding time; represents the index of the convolution kernel; At the same time, gated temporal convolution is adopted, specifically as follows:

[0020] wherein, is the output of the gated temporal convolution; and are the tanh and sigmod activation functions respectively; is the Hadamard product; 、 , , are model parameters; Also, the optimization of model parameters is carried out based on an improved brainstorming algorithm, and the power outage range is predicted based on the graph neural network built in the above steps.

[0021] Preferably, in the second visualization module, map visualization is based on GIS technology to visually display distribution network equipment and top regions on the map; interactive visualization designs an interactive visualization interface.

[0022] Preferably, the transparent panoramic display module sorts out the substation-line-transformer-user topological relationship based on the visualization results of the transparent topology recognition display module and the power outage area visualization module, constructs the physical topology of the low-voltage distribution network, and visually displays the physical form of the distribution network in the digital space in digital form, and performs anomaly prediction and anomaly warning.

[0023] Compared with the prior art, the present invention provides a transparent panoramic control system based on a low-voltage distribution network, which has the following beneficial effects: The present invention combines a topology optimization algorithm and a transparent control technology, can obtain the operation data of the distribution network in real time, and perform accurate analysis and prediction; helps to timely discover potential problems and faults, optimize resource allocation, improve the operation efficiency of the distribution network, and further improve its reliability and stability. It also uses technologies such as artificial intelligence and the Internet of Things to achieve rapid fault location, automatic isolation, and power supply restoration, thereby reducing power outage time and improving power supply reliability and security. Through the transparent control platform of the distribution network, the full transparency and full perception of the distribution network are realized, providing comprehensive, real-time, and accurate operation data of the distribution network, helping power operators better understand the real-time state of the distribution network, predict future operation trends, optimize resource allocation, improve operation efficiency, and ensure the reliability and security of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is the system block diagram mentioned in Embodiment 1 of the present invention; Figure 2 is the variant convolution structure diagram mentioned in Embodiment 1 of the present invention; Figure 3 is the gated temporal convolution schematic diagram mentioned in Embodiment 1 of the present invention; Figure 4 is the overall architecture diagram mentioned in Embodiment 2 of the present invention.

[0025] Meanings of the marks in the figure: 1. Transparent topology identification and display module; 11. First data acquisition and processing module; 12. Topology identification and establishment module; 13. First visualization module; 14. Intelligent analysis and decision-making module; 2. Power outage area visualization module; 21. Second data acquisition and processing module; 22. Power outage event correlation analysis module; 23. Power outage range prediction module; 24. Second visualization module; 25. Analysis model construction module; 3. Transparent panoramic display module. Detailed implementation mode

[0026] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0027] The present invention combines topology optimization algorithms and transparent management and control technologies, can obtain the operation data of the distribution network in real time, and perform accurate analysis and prediction; helps to timely discover potential problems and faults, optimize resource allocation, improve the operation efficiency of the distribution network, and further improve its reliability and stability. It also uses technologies such as artificial intelligence and the Internet of Things to achieve rapid fault location, automatic isolation, and power restoration, thereby reducing power outage time and improving power supply reliability and safety. Through the transparent management and control platform of the distribution network, the distribution network is fully transparent and fully perceptible, providing comprehensive, real-time, and accurate operation data of the distribution network, helping power operators better understand the real-time state of the distribution network, predict future operation trends, optimize resource allocation, improve operation efficiency, and ensure the reliability and safety of power supply. The specific contents are as follows.

[0028] Embodiment 1: Please refer to Figures 1-3 , the transparent panoramic management and control system of the present invention based on the low-voltage distribution network includes: Transparent topology identification and display module 1: For application objects such as substation buildings, lines, and distribution transformers, establish a display model of the transparent topology relationship of the power grid, draw the topology diagram of the distribution network grid, connect dynamic data such as dispatching D5000, distribution automation, power consumption information collection system, and on-site video images, build a dynamic power grid map, realize the intelligent operation and maintenance, lean management, and transparent observation of the intelligent distribution network, realize the real-time tracking of the operation of the distribution system, and realize the unified display and analysis of various operation data and parameters of the distribution system.

[0029] The transparent topology identification and display module 1 specifically includes: The first data acquisition and processing module 11: It is used to collect power parameters and power equipment information based on a number of data acquisition devices, and preprocess the collected data; The transparency of the distribution network first requires high-precision data acquisition, including power parameters such as voltage, current, power factor, and harmonics, as well as information such as equipment status and location. At the same time, the collected data is efficiently and accurately preprocessed for subsequent topology identification and analysis.

[0030] The first data acquisition and processing module 11 combines radio frequency identification technology, bar code technology, sensor technology, M2M technology, remote sensing technology, and intelligent information devices to collect relevant data. Among them, M2M technology refers to machine-to-machine communication, that is, M2M is the integration of wireless communication and information technology, enabling information sharing among systems, sensing terminal devices, back-end information systems, and operators. The main long-distance connection technologies are GSM, GPRS, and UMTS, and its short-distance connection technologies mainly include 802.11b / g, Bluetooth technology, Zigbee, radio frequency identification technology, and wireless sensing technology. In addition, there are some other technologies, such as hypertext language and Corba, as well as location service technologies based on the global positioning system, wireless terminals, and networks.

[0031] The topology identification and establishment module 12: It is used to identify the topology of the distribution network based on the topology optimization algorithm, and build a transparent topology relationship model of the power grid accordingly; The specific identification steps of the topology optimization algorithm are as follows: Define the mapping relationship between the device information of each node in the distribution network and the power pulse signal collector, set the power pulse signal collector at each node in the distribution network, and collect the power pulse signal ; There is a one-to-one mapping relationship between the power pulse signal collector and the corresponding circuit information and equipment information; Use the adjacency matrix as the logical matrix for topology identification. For any directed line segment in the system from node output, to node input, without passing through any other nodes in between, then nodes and are called adjacent nodes; In this way, a -dimensional logical matrix is established through the power pulse signal. When and are adjacent nodes, then the logical matrix element ; Otherwise, the logical matrix element , and the upper triangular matrix of the adjacency matrix is intercepted and input into the topology structure identification model; After the establishment of the logical matrix is completed, the topology of the adjacency matrix is identified for three basic structures in turn according to the criterion, as follows: Series structure identification criterion:

[0032] Among them, and and all represent the logical matrix elements; The nodes satisfying the above formula are identified as the topological relationship of the series structure; Criterion for identifying the shunt structure:

[0033] Among them, and and and all represent the logical matrix elements; The nodes satisfying the above formula are identified as the topological relationship of the shunt structure; Criterion for identifying the convergence structure:

[0034] Among them, and all represent the logical matrix elements; The nodes satisfying the above formula are identified as the topological relationship of the convergence structure; Through the above steps, the conversion from the logical matrix to the topological information is completed. Based on the improved brainstorm optimization algorithm, the distribution network is traversed, and the topological relationship between nodes is determined in sequence to realize the intelligent identification of the topological structure of the distribution network; the specific improved brainstorm optimization algorithm is as follows: Initialize the distribution network nodes, perform initial clustering processing on the distribution network nodes based on the k-means algorithm, and define the optimal individual of each class, that is, the key nodes in the topological structure are the class centers; The algorithm randomly selects one or two node individuals in a class and mutates the node individuals based on the following method, that is, local optimization of the topological structure:

[0035] Among them, is the mutated node individual, is the node individual to be mutated; and and and are the node individuals randomly selected from the parent population; is the mutation factor; For the node individuals of a selected class, the mutated node individuals are used as the final node individuals; for the node individuals from different clusters, the following fusion is performed:

[0036] Among them, is the mutated node individual generated after the fusion of two node individuals, and are the two node individuals that accept the fusion; is a random number between; Update the node individuals in the following way:

[0037] where, is the node individual before the -th iteration update; is the node individual after the -th iteration update; is the global optimal node individual; is the global optimal influence coefficient of the -th iteration;

[0038] where, is the probability of selecting a node individual through a class; is the probability of selecting the class center after selecting a class; is the probability of selecting the class centers for fusion after selecting two classes;

[0039] where, and are the maximum and minimum values of the global optimal influence coefficient respectively; is the maximum number of iterations.

[0040] Based on the improved brainstorming algorithm, traversing the topology identification process can achieve traversing a large number of possible topological structures in a short time, effectively avoid blind search, and quickly focus on the potential solution space area. It can be easily parallelized to make full use of the multi-core processors or distributed computing resources of modern computers. Each search individual can search in different regions simultaneously, further accelerating the traversal speed.

[0041] It can conduct extensive searches in the entire solution space and avoid falling into local optimal solutions. This is very important for the topology identification problem because the topological structure of the distribution network may be very complex and there are multiple local optimal solutions. It can maintain the diversity of solutions. Different search individuals represent different topological structure schemes, and the differences and diversities among them help to cover a wider solution space and increase the chance of finding the optimal solution.

[0042] Whether it is a small-scale distribution network or a large-scale complex network, the improved brainstorming algorithm can effectively perform topological identification traversal. It can automatically adjust the search strategy and parameters according to the network scale to adapt to different application scenarios. The operating state of the distribution network changes over time, such as load fluctuations, equipment failures, access and withdrawal of distributed power sources, etc. The improved brainstorming algorithm can adapt to this dynamic change, timely adjust the search direction, and re-perform topological identification to ensure the accuracy and adaptability of the topological structure.

[0043] In practical applications, the distribution network may be affected by various interference factors, such as noise, measurement errors, etc. The improved brainstorming algorithm has a certain anti-interference ability and can still perform effective topological identification traversal in the presence of interference. The algorithm shows high stability during operation. It will not be affected by the abnormal performance of individual search individuals or the failure of local search, thus affecting the progress of the entire search process. Even in some adverse situations, the algorithm can continue to search until a satisfactory solution is found.

[0044] The first visualization module 13: used to display the topological structure of the distribution network in a graphical way; the first visualization module 13 displays the topological structure of the distribution network in a graphical way. Through the first visualization module 13, information such as the topological structure, equipment status, and operation conditions of the distribution network can be intuitively understood.

[0045] The intelligent analysis and decision-making module 14: used to monitor and warn the operating state of the distribution network in real time, quickly locate and handle faults, and optimize the dispatching of the distribution network; On the basis of the transparency of the distribution network, the intelligent analysis and decision-making function is also realized based on the intelligent analysis and decision-making module 14. This includes real-time monitoring and warning of the operating state of the distribution network, quick location and handling of faults, and optimization of the dispatching of the distribution network, etc.

[0046] The power outage area visualization module 2: used to fully integrate multi-source heterogeneous data of the distribution network, establish a visualization analysis model for the power outage area of the distribution network fault from three dimensions of the number of power outage households, power outage duration, and power outage household-times, realize early warning of multi-level power outage events such as distribution lines, distribution transformers, communities, and users, assist operators to scientifically formulate fault handling plans according to the degree of fault impact, optimize the handling sequence between multiple faults, reasonably guide the on-site allocation of repair resources, and improve the dispatching staff's command level for fault handling.

[0047] The power outage area visualization module 2 specifically includes: The second data acquisition and processing module 21: used to collect, clean, and store information related to power outages in the distribution network; similar to the first data acquisition and processing module 11, the second data acquisition and processing module 21 applies multiple technologies to collect information related to power outages in the distribution network and performs preprocessing and storage operations.

[0048] Power outage event correlation analysis module 22: It is used to identify the equipment and connection relationships of the power distribution network in the power outage area based on the topology optimization algorithm and conduct correlation analysis; based on the recognition results of the topology recognition establishment module 12 and the drawn topology diagram of the power distribution network grid, the topology diagram of the power outage area can be extracted. Based on the extracted topology diagram, the equipment and connection relationships of the power distribution network in the power outage area can be accurately reflected.

[0049] Power outage scope prediction module 23: It is used to build a prediction model for the power outage scope based on historical data and real-time data; based on the topology recognition results of the topology recognition establishment module 12, corresponding to the graph neural network, the nodes correspond to the topology structure nodes, the edges correspond to the connection relationships between the topology structure nodes, each node and edge has corresponding power attributes, the graph neural network also combines a variant convolution structure to effectively process time series, and multiple convolutional layers can also be stacked to achieve multi-level feature extraction of the input data, capture features at different scales and abstraction levels, so as to provide richer information for subsequent analysis and decision-making. The variant convolution structure can refer to Figure 2 , specifically as follows:

[0050] Among them, is the dilation convolution kernel; is the dilation coefficient; is the input value; corresponding time; represents the index of the convolution kernel; refer to Figure 3 , and at the same time, gated temporal convolution is adopted, specifically as follows:

[0051] Among them, is the output of the gated temporal convolution; and are the tanh and sigmod activation functions respectively; is the Hadamard product; , , , are the model parameters; It also optimizes the model parameters based on the improved brainstorming algorithm and predicts the power outage scope based on the graph neural network built in the above steps.

[0052] Combined with gated time convolution, it can adapt to different time scales, process long time series, automatically learn and dynamically adjust feature weights. It can reduce overfitting, enhance the stability of the model, and is also easy to combine with other models and adapt to different tasks and data sets. In the distribution network, it can better handle the changes in electrical signals, improve the accuracy and timeliness of tasks such as load forecasting and fault diagnosis, provide more effective support for the state monitoring and operation management of the distribution network, and has strong flexibility, versatility, and scalability.

[0053] The second visualization module 24: It is used to visually display the distribution network equipment and power outage areas based on map visualization and interactive visualization technologies and interact with users; Map visualization uses geographic information system (GIS) technology to visually display the distribution network equipment and power outage areas on the map. Interactive visualization: Design an interactive visualization interface to enable users to conveniently query, analyze, and operate power outage-related data.

[0054] The analysis model construction module 25: It is used to construct a visual analysis model for the power outage area based on the topological structure, equipment parameters, and real-time data of the distribution network, and use technologies such as machine learning and data mining to continuously optimize the performance and accuracy of the analysis model. And analyze the power outage area through the visual analysis model of the power outage area.

[0055] The transparent panoramic display module 3: It is used to carry out the research and development of the distribution network transparent panoramic control system around dimensions such as equipment, operation, monitoring, indicators, and topology, rely on existing results to sort out the topological relationship of "substation-line-transformer-user", form an accurate mapping based on "substation-line-transformer-user", construct the physical topology of the low-voltage distribution network, realize the automatic identification of the topological relationship of "substation-line-transformer-user", visually display the physical form of the distribution network in digital form in the digital space, and carry out in-depth application functions such as topological anomaly warning and power outage warning analysis to realize the visual display of the operation status of distribution transformers and low-voltage substations; Embodiment 2: Based on Embodiment 1, build a Figure 4 The overall architecture diagram of the state platform can refer to Figure 4 , The business layer of the system built based on Embodiment 1 conducts functional design for the transparency of the distribution network around dimensions such as equipment, operation, indicators, monitoring, and topology. The following functions can be specifically realized: ① Equipment transparency: Around dimensions such as "substation-line-transformer-user", display the equipment ledger information of substations, lines, transformers, users, etc., specifically including the ledger data of substations such as switch stations, distribution rooms, ring network rooms, ring network cabinets, and box-type substations, the ledger data of main lines / branch lines, the ledger data of transformers such as public transformers and special transformers, and user data such as the number of users and user capacity.

[0056] ② Operation transparency: Display real-time operation data in dimensions such as inspection tours, maintenance, and emergency repairs. Among them, the inspection tour part includes data on completed and uncompleted human inspections, machine inspections, etc. The maintenance part includes on-site operation conditions (completed work, risks above level 3, etc.) under power outage and non-power outage conditions. The emergency repair part includes the display of completed and uncompleted operations under different work order driving dimensions.

[0057] ③ Indicator transparency: Display basic data and details such as heavy load, overload, three-phase imbalance, power supply reliability, low voltage, frequently tripped lines, average power outage duration, new / unresolved defects, FA line coverage, etc.

[0058] ④ Monitoring transparency: Display information such as out-of-service lines / out-of-service distribution transformers / power outage-sensitive users, substation buildings, and distribution cables. Among them, the substation building information includes operation and alarm data of devices such as water immersion, temperature and humidity, smoke sensors, and security systems. The distribution cable includes operation and alarm data such as joint temperature, displacement, multi-function, and water accumulation.

[0059] ⑤ Topology transparency: Display the distribution of line / distribution transformer outages, drone inspections, bad weather, etc. in the form of a map.

[0060] The service layer provides multiple intelligent services such as cable monitoring services, ledger analysis services, two-side analysis services, and drone analysis services.

[0061] The platform layer is based on mainstream middleware servers such as Tomcat, Oracle, and Redis; adopts the SOAP protocol, adapts to the need for flexible integration of multiple systems, provides a rigorous security solution, and meets the requirements of security management.

[0062] The integration layer integrates the management platform and obtains ledger data, line / distribution variable measurements, line / distribution transformer power outages, etc. through the distribution automation cloud master station, measurement center, power grid resource business middle platform, homologous maintenance tool, cable lean management platform, etc. to support the acquisition of various types of information. It also provides basic map services and topology services through the power grid GIS platform, and combines the ledger and graphic information provided by the power grid resource center and power grid topology center of the business middle platform to comprehensively display the power grid topology trend and distribution, and calls the buffer analysis function to realize regional information statistical analysis. Through the above unified permission platform, it can provide convenient, fast, secure, and reliable account management, authentication management, permission management, and security audit management for business applications and microservices.

[0063] The transparency platform built through the above steps can monitor the operation status of the distribution network in real time. Once a fault occurs, the platform can quickly locate the fault point and automatically trigger the fault handling process, improving the fault handling efficiency, reducing the power outage time and the affected area. Through real-time monitoring and data analysis, the transparency platform can predict potential faults of equipment, perform maintenance in advance, thus avoiding power outages caused by sudden equipment failures, reducing the workload and inspection time of inspection personnel, and reducing the operation and maintenance costs. By analyzing the load situation and energy usage of the distribution network in real time, resources can be allocated according to actual needs. The platform can monitor the power consumption in real time, analyze the energy usage, provide energy-saving suggestions, and improve the energy efficiency level of the entire power grid.

[0064] As mentioned above, the above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, with equivalent substitution or change, should be covered by the protection scope of the present invention.

Claims

1. A transparent panoramic control system based on a low-voltage distribution network, characterized in that Including: Transparent topology identification and display module (1): For multi-dimensional transparent panoramic display of the distribution network; Power outage area visualization module (2): For building the matching relationship between area-level power outage equipment and power outage scope, and realizing the full-dimensional visualization display of the power outage area; Transparent panoramic display module (3): For comprehensively and dynamically displaying the information of each dimension of the low-voltage distribution network; The transparent topology identification and display module (1) includes: First data acquisition and processing module (11): For collecting power parameters and power equipment information based on several data acquisition devices, and preprocessing the collected data; Topology identification and establishment module (12): For identifying the topology of the distribution network based on the topology optimization algorithm, and building a transparent topology relationship model of the power grid and drawing the topology diagram of the distribution network grid; First visualization module (13): For displaying the topology structure of the distribution network in a graphical way; Intelligent analysis and decision-making module (14): For real-time monitoring and early warning of the operation state of the distribution network, quickly locating and handling faults, and optimizing the dispatching of the network; The power outage area visualization module (2) includes: Second data acquisition and processing module (21): For collecting, cleaning and storing the information related to the power outage of the distribution network; Power outage event correlation analysis module (22): For identifying the equipment and connection relationship of the power outage area distribution network based on the topology optimization algorithm, and conducting correlation analysis; Power outage scope prediction module (23): For building a prediction model of the power outage scope based on historical data and real-time data; Second visualization module (24): For visualizing and displaying the distribution network equipment and the power outage area based on map visualization and interactive visualization technologies, and interacting with users; Analysis model construction module (25): For building a power outage area visualization analysis model based on the topology structure, equipment parameters and real-time data of the distribution network, and analyzing the power outage area through the power outage area visualization analysis model.

2. The transparent panoramic control system based on a low-voltage distribution network according to claim 1, characterized in that The first data acquisition and processing module (11) and the second data acquisition and processing module (21) collect relevant data based on radio frequency identification technology, barcode technology, sensor technology, M2M technology, remote sensing technology and intelligent information devices.

3. The transparent panoramic control system based on a low-voltage distribution network according to claim 1, wherein, The specific identification steps of the topology optimization algorithm in the topology identification and establishment module (12) are as follows: Define the mapping relationship between the device information of each node in the distribution network and the power pulse signal collector, and set the power pulse signal collector at each node in the distribution network to collect the power pulse signal ; There is a one-to-one mapping relationship between the power pulse signal collector and the corresponding circuit information and device information; Adopt an adjacency matrix as the logical matrix for topology recognition. For any directed line segment within the system, from node output, to node input, without passing through any other nodes in between, then nodes and are called adjacent nodes; thus establish a -dimensional logical matrix through the power pulse signal. When and are adjacent nodes, then the element of the logical matrix ; otherwise the element of the logical matrix , and intercept the upper triangular matrix of the adjacency matrix and input it into the topology structure recognition model; After the establishment of the logical matrix, the topology of the adjacency matrix is identified for three basic structures according to the criterion, specifically as follows: Series structure identification criterion: Among them, , , all represent logical matrix elements; The nodes satisfying the above formula are identified as the topology relationship of the series structure; Shunt structure identification criterion: Among them, , , , all represent logical matrix elements; The nodes satisfying the above formula are identified as the shunt structure topology relationship; Converging structure identification criterion: Among them, , both represent logical matrix elements; The nodes satisfying the above formula are identified as the converging structure topology relationship; Through the above steps, the conversion from the logical matrix to the topology information is completed, and the distribution network is traversed based on the improved brainstorm optimization algorithm to determine the topology relationship between nodes in turn, realizing the intelligent identification of the distribution network topology structure; The specific improved brainstorm optimization algorithm is as follows: Initialize the distribution network nodes, perform initial clustering processing on the distribution network nodes based on the k-means algorithm, and define the optimal individual of each class, that is, the key nodes in the topological structure are the class centers; The algorithm randomly selects node individuals in one or two classes and mutates the node individuals based on the following method, that is, local optimization of the topological structure: Among them, is the mutated node individual, is the node individual to be mutated; , , , are the node individuals randomly selected from the parental population; is the mutation factor; For the node individuals in one selected class, use the mutated node individuals as the final node individuals; for node individuals from different clusters, perform the following fusion: Among them, is the mutated node individual generated after the fusion of two node individuals, and are the two node individuals receiving the fusion; is a random number between; Update the node individuals in the following manner: Among them, is the node individual before the th iterative update; is the node individual after the th iterative update; is the globally optimal node individual; is the globally optimal influence coefficient in the th iteration; is the probability of the node individual to be mutated. wherein, is the probability of selecting an individual of a class through a class selection node; is the probability of selecting the class center after selecting a class; is the probability of selecting the class center for fusion after selecting two classes; Among them, and are the maximum and minimum values of the global optimal influence coefficient respectively; is the maximum number of iterations.

4. The transparent panoramic control system based on a low-voltage distribution network according to claim 3, wherein The power outage range prediction module (23) combines with the graph neural network based on the topological recognition result, constructs a graph network corresponding to the topological recognition result, and each node and edge have corresponding power attributes; build a power outage prediction model based on the graph neural network, where the graph neural network combines a variant convolutional structure, specifically as follows: Among them, is the dilated convolution kernel; is the dilation coefficient; is the input value; corresponding time; represents the index of the convolution kernel; At the same time, gated temporal convolution is adopted, specifically as follows: Among them, is the output of gated temporal convolution; and are the tanh and sigmod activation functions respectively; is the Hadamard product; , , , are model parameters; Also optimize the model parameters based on the improved brainstorming algorithm, and predict the power outage range based on the graph neural network built in the above steps.

5. The transparent panoramic control system based on a low-voltage distribution network according to claim 1, characterized in that, In the second visualization module (24), map visualization is based on GIS technology to visually display the distribution network equipment and the top area on the map; interactive visualization designs an interactive visualization interface.

6. The transparent panoramic control system based on a low-voltage distribution network according to claim 1, wherein The transparent panoramic display module (3) sorts out the substation-line-transformer-user topological relationship based on the visualization results of the transparent topological recognition display module (1) and the power outage area visualization module (2), constructs the low-voltage distribution network physical topology, and visually displays the physical form in the digital space in digital form, and performs anomaly prediction and anomaly warning.

Images