Smart grid connection control method and system based on edge computing

Abstract

The present application provides a smart grid connection control method and system based on edge computing, which relates to the field of power system control technology, including: deploying edge computing equipment, establishing a communication network between edge computing nodes and central control; obtaining real-time monitoring data of the power grid, and performing grid-connected power feature identification and analysis; integrating the topological structure according to the topological structure of each grid-connected power grid, and building a complete grid-connected topological structure; determining the characteristic traversal path, identifying and locating differential grid nodes; performing grid-connected deviation regulation, and determining the grid-connected control strategy. This application can solve the problem in the prior art that the traditional grid connection control relies on the central server, resulting in slow data processing speed and affecting the stability of the grid operation. By deploying edge computing equipment at key nodes, building a complete grid topology, identifying and regulating differential grid nodes, the stability and operation efficiency of the grid connection can be improved.

Description

Technical Field

[0001] The present application relates to the field of power system control technology, and in particular to a smart grid connection control method and system based on edge computing. Background Art

[0002] With the growth of energy demand and the access of new energy sources, the complexity and dynamics of the power grid are increasing. As a new type of power grid structure, smart grid realizes the intelligent management of the power grid by integrating advanced communication, computing and automation technologies. Among them, grid connection control is the core component of smart grid, involving the stability, efficiency and security of the power grid. In the existing smart grid connection control technology, it mainly relies on a centralized control system, which is usually located in the center of the power grid and is responsible for collecting and processing data from various power grid nodes. Since all data processing depends on centralized servers or control systems, the data processing and response speed are slow. During the grid connection process, the rapid changes in the power grid status require real-time response and processing, and traditional centralized systems are difficult to meet this demand.

[0003] In summary, the existing technology has the problem that the traditional grid connection control relies on the central server, resulting in slow data processing speed, which affects the stability of grid operation. Summary of the invention

[0004] The purpose of this application is to provide a smart grid connection control method and system based on edge computing, so as to solve the problem in the prior art that the traditional grid connection control relies on a central server, resulting in slow data processing speed and affecting the stability of grid operation.

[0005] In view of the above problems, the present application provides a smart grid connection control method and system based on edge computing.

[0006] In a first aspect, the present application provides a smart grid grid-connected control method based on edge computing, which is implemented by a smart grid grid-connected control system based on edge computing, wherein the smart grid grid-connected control method based on edge computing includes: identifying key nodes of the grid-connected power grid to deploy edge computing devices, and establishing a communication network between the edge computing nodes and the central control; obtaining real-time monitoring data of the power grid, and performing grid-connected power feature identification and analysis on the real-time monitoring data by matching the edge computing nodes according to the deployment relationship between the power grid and the edge computing nodes, to obtain the power characteristics of the power grid, wherein the power characteristics of the power grid include at least voltage, frequency, and power; according to the topological structure of each grid-connected power grid, the topological structure is integrated according to the grid location distance to construct a complete grid-connected topological structure; based on the complete grid-connected topological structure, a characteristic traversal path is determined, and according to the power transmission order of the characteristic traversal path, voltage, frequency, and power deviation are traversed respectively according to the grid power characteristics, and differential grid nodes are identified and located; grid deviation regulation is performed according to the position distribution relationship of the differential grid nodes, and a grid control strategy is determined.

[0007] In the second aspect, the present application also provides an edge computing-based smart grid on-grid control system for executing the edge computing-based smart grid on-grid control method as described in the first aspect, wherein the edge computing-based smart grid on-grid control system includes: a key node deployment module, the key node deployment module is used to identify the key node deployment edge computing devices of the grid-connected power grid, and establish a communication network between the edge computing nodes and the central control; a feature recognition module, the feature recognition module is used to obtain real-time monitoring data of the power grid, and according to the deployment relationship between the power grid and the edge computing nodes, the real-time monitoring data is matched by the edge computing nodes to perform grid-connected power feature recognition and analysis to obtain the power characteristics of the power grid, and the power characteristics of the power grid are obtained. The grid power characteristics include at least voltage, frequency, and power; a topology integration module, which is used to integrate the topology structures according to the topology structures of each grid-connected power grid and the distance between the power grid locations to construct a complete grid-connected topology structure; a traversal path determination module, which is used to determine a characteristic traversal path based on the complete grid-connected topology structure, traverse the voltage, frequency, and power deviation amounts according to the power transmission sequence of the characteristic traversal path and the grid power characteristics, and identify and locate differential grid nodes; a grid deviation control module, which is used to control the grid deviation according to the position distribution relationship of the differential grid nodes and determine the grid control strategy.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By identifying the key nodes of the grid-connected power grid and deploying edge computing devices, a communication network between the edge computing nodes and the central control is established; the real-time monitoring data of the power grid is obtained, and the grid power characteristics are identified and analyzed by matching the edge computing nodes according to the deployment relationship between the power grid and the edge computing nodes, and the power characteristics of the power grid are obtained, and the power characteristics of the power grid include at least voltage, frequency, and power; according to the topological structure of each grid-connected power grid, the topological structure is integrated according to the grid location distance to build a complete grid-connected topological structure; based on the complete grid-connected topological structure, the characteristic traversal path is determined, and the voltage, frequency, and power deviation are traversed according to the power transmission sequence of the characteristic traversal path and the power characteristics of the power grid, and the difference grid nodes are identified and located; the grid deviation is regulated according to the position distribution relationship of the difference grid nodes, and the grid control strategy is determined. In other words, by deploying edge computing devices at key nodes, a complete grid topological structure is constructed, and grid nodes with differences are identified and regulated, thereby improving the stability and operation efficiency of the grid connection.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 This is a flow chart of a smart grid connection control method based on edge computing in this application;

[0013] Figure 2 This is a structural diagram of the smart grid control system based on edge computing in this application.

[0014] Explanation of the reference numerals: key node deployment module 11, feature identification module 12, topology structure integration module 13, traversal path determination module 14, grid-connected deviation control module 15. DETAILED DESCRIPTION

[0015] This application provides a smart grid connection control method and system based on edge computing, which solves the problem in the prior art that the traditional grid connection control relies on the central server, resulting in slow data processing speed and affecting the stability of grid operation. By deploying edge computing devices at key nodes, building a complete grid topology, identifying and regulating grid nodes with differences, the stability and operation efficiency of the grid connection are improved.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0017] For example, please refer to the attached Figure 1 The present application provides a smart grid connection control method based on edge computing, wherein the smart grid connection control method based on edge computing is applied to a smart grid connection control system based on edge computing, and the smart grid connection control method based on edge computing specifically includes the following steps:

[0018] Step 1: Identify the key nodes of the grid-connected power grid, deploy edge computing devices, and establish a communication network between edge computing nodes and central control.

[0019] Specifically, the topological structure data and power operation data of the power grid are collected, and the power flow analysis tools are used to identify the load concentration areas, that is, the areas with high power demand. According to the historical high-frequency fault points and fault characteristics of the grid-connected power grid, the key nodes of the grid-connected power grid are determined. The power demand, data transmission volume, processing complexity and other aspects of the key nodes are analyzed to determine the edge computing device configuration suitable for these nodes, and these devices are deployed on the key nodes. A communication network between the edge computing nodes and the central control system is established to ensure efficient data transmission and rapid execution of decisions, including configuring appropriate communication protocols and network equipment, as well as ensuring the stability and security of the network. By identifying the key nodes of the grid-connected power grid, deploying edge computing devices, and establishing a communication network between the edge computing nodes and the central control, the intelligent and real-time control of the key nodes of the power grid is realized.

[0020] Step 2: Obtain real-time monitoring data of the power grid. According to the deployment relationship between the power grid and the edge computing nodes, the real-time monitoring data is matched with the edge computing nodes to identify and analyze the grid power characteristics, and the grid power characteristics include at least voltage, frequency, and power.

[0021] Specifically, sensors, including but not limited to voltage sensors, current sensors, frequency sensors, power sensors, etc., are deployed at key nodes of the power grid (such as substations, feeders, distribution lines, etc.) to monitor the operating status of the power grid in real time. Ensure data synchronization between edge computing nodes and central control systems to avoid information lag. Transmit sensor data to edge computing nodes through the data acquisition system. According to the deployment relationship between the power grid and the edge computing nodes, match the acquired real-time monitoring data with the corresponding edge computing nodes. Preprocess the real-time monitoring data, such as filtering, denoising, and normalization, to improve data quality. Perform grid-connected power feature recognition and analysis on the preprocessed data, and use time domain analysis, frequency domain analysis, machine learning and other methods to extract features and extract power features such as voltage, frequency, and power. Analyze the extracted power features, including trend analysis, anomaly detection, fault diagnosis, etc., to identify the operating status and potential problems of the power grid. Summarize the analyzed power features to form a comprehensive description of the current operating status of the power grid. By obtaining real-time monitoring data of the power grid, matching the data according to the deployment relationship between the power grid and the edge computing nodes, and then using the edge computing nodes to identify and analyze the power characteristics, the power characteristics of the power grid can be obtained, which helps to accurately grasp the operating status of the power grid.

[0022] Step 3: Based on the topological structures of each grid-connected power grid, the topological structures are integrated according to the grid location distance to build a complete grid-connected topological structure.

[0023] Specifically, the topological structure data of each grid-connected power grid is collected, including all nodes in the grid (such as substations, power stations, load points, etc.) and the transmission lines connecting these nodes. A grid-connected power grid refers to a power grid system that connects multiple power grids or power sources and operates together. Geographic coordinates are assigned to each node in the grid (such as substations, lines, etc.). The geographical distance between grid nodes is calculated using a geographic information system or other algorithms. According to the location distance of each node in the grid, the collected topological structure data is integrated, the nodes and lines of different grids are connected according to the actual location distance, and the repeated parts of adjacent grid nodes and lines are merged to construct a preliminary grid connection. The preliminary grid is evaluated for power flow, node load and grid coverage stability through power flow simulation, and the preliminary grid topological relationship is optimized based on the simulation evaluation results to obtain a complete grid-connected topological structure. By integrating the topological structures of each grid-connected power grid, a complete grid-connected topological structure is constructed.

[0024] Step 4: Determine a characteristic traversal path based on the complete grid-connected topology structure, traverse the voltage, frequency, and power deviations according to the power characteristics of the power grid in the order of power transmission of the characteristic traversal path, and identify and locate differential power grid nodes.

[0025] Specifically, according to the constructed grid-connected complete topology, the main path of power transmission is determined, considering the high-voltage, medium-voltage, and low-voltage hierarchical structures and key nodes of the power grid. According to the operation characteristics and analysis results of the power grid, the characteristic traversal path is planned, and the traversal path should cover the key areas and main transmission paths of the power grid. According to the operation mode of the power grid and the priority of power transmission, the order of power transmission in the traversal path is determined. For example, the high-voltage power grid is traversed first, followed by the medium-voltage and low-voltage power grids. According to the power characteristics of the power grid, the deviation of voltage, frequency, and power is calculated. According to the power transmission order, the voltage, frequency, and power deviation are traversed along the characteristic traversal path, and at each node, the values ​​of these characteristics are checked to understand the changes. Compare the deviation values ​​on the traversal path, identify the nodes or lines with abnormal deviations, which are caused by equipment failure, load changes, insufficient transmission capacity, etc. According to the difference identification results, locate the location of the difference power grid node, and determine the specific location and impact range of the difference node in the power grid. By determining the characteristic traversal path and traversing the power characteristics of the power grid, identifying and locating the problem nodes of the power grid, it is helpful to have a deep understanding of the operation status of the power grid.

[0026] Step 5: Regulate the grid connection deviation according to the position distribution relationship of the differential grid nodes and determine the grid connection control strategy.

[0027] Specifically, the geographic coordinates of the difference grid nodes are obtained, the geographic distribution is determined, and the geographic environment data is obtained. When adjusting the grid parameters, the environmental impact should be fully considered, especially for those key nodes that are sensitive to the environment or have a significant environmental impact. The degree of impact of each node on the environment is evaluated based on the geographical location, ecological sensitivity, climate change impact, etc. The environmental sensitivity of each node is rated and divided into three levels: high, medium, and low. Nodes with high environmental sensitivity require special attention, while nodes with low environmental sensitivity require more adjustments. According to the analysis results, the grid is regulated for grid connection deviation. Grid connection deviation regulation refers to adjusting the grid operation parameters to reduce the deviation during the grid connection process. Real-time monitoring data is analyzed and compared with standard values ​​or historical data to identify grid connection deviations, including high or low voltage, high or low frequency, etc. According to the deviation analysis results, the grid connection control strategy is designed, including adjustment measures and expected goals. The rapid response capability of edge computing nodes is used to execute the control strategy, including adjusting the output of power generation equipment, starting standby equipment, adjusting load distribution, etc. Based on real-time monitoring data, the grid connection control strategy is adjusted in real time to ensure the stable transition of key parameters such as voltage and frequency during the grid connection process. According to the results of grid-connected deviation control, the grid-connected control strategy is determined. By analyzing the location distribution relationship of differential grid nodes, grid-connected deviation control is carried out, and the grid-connected control strategy is determined accordingly to reduce the deviation in the grid-connected process and improve the overall performance of the grid.

[0028] Furthermore, step one of this application includes:

[0029] Collect the grid topology and its power operation data, and use power flow analysis tools to identify substation equipment and transmission lines in load-concentrated areas; identify and mark the substation equipment and transmission lines through historical high-frequency grid-connected fault points and fault characteristics, and determine the key nodes; analyze the power operation characteristics of the key nodes, determine the edge computing device configuration, including computing power, storage capacity and communication modules, and deploy the edge computing devices to the key nodes.

[0030] Specifically, the topological structure data of the power grid is collected, including all nodes in the power grid (such as substations, power stations, load points, etc.) and the transmission lines connecting these nodes. At the same time, the monitoring and data acquisition system is used to collect power operation data, such as voltage, current, power, etc. The collected power grid topology and power operation data are processed and analyzed using power flow analysis tools, such as PSS / E, DIgSILENT PowerFactory, etc. Power flow analysis is used to identify load concentration areas in the power grid, that is, areas with high power demand. In the load concentration areas, key substation equipment (such as transformers) and transmission lines are identified. High-frequency fault points that have occurred in the past period of time during the grid connection process, that is, the locations where faults often occur, are collected, and fault characteristics are recorded, such as the time of the fault, the type of fault, the scope of impact, etc. Based on the collected historical fault points and fault characteristics, the substation equipment and transmission lines in the power grid are identified and marked to determine whether these equipment and lines are key nodes. Key nodes are nodes that have an important impact on the stability of power grid operation, such as key equipment and lines in fault-frequent areas.

[0031] Conduct an in-depth analysis of the power operation characteristics of the identified key nodes, including an assessment of the node's power demand, data transmission volume, and processing complexity. Power operation characteristics reflect the needs and capabilities of key nodes in power operation. According to the power operation characteristics of key nodes, determine the edge computing device configuration suitable for these nodes, including parameters such as computing power, storage capacity, and communication modules. Computing power refers to the ability of edge computing devices to process and analyze data based on power operation characteristics. Determine storage capacity to store real-time data and historical data. Configure appropriate communication modules to ensure efficient and reliable communication between edge computing devices and central control systems and other edge nodes. Deploy edge computing devices on identified key nodes, including equipment installation, configuration, and testing to ensure that the equipment can operate normally and meet the needs of the nodes. By collecting the topology and power operation data of the power grid, using power flow analysis tools to identify load concentration areas, analyze key nodes, determine the configuration of edge computing devices, reduce the frequency and impact of failures, and improve the overall performance of the power grid.

[0032] Further, step three of this application includes:

[0033] A graph theory algorithm is used to identify the key topological nodes of each grid-connected power grid, the power flow relationship of the key topological nodes is analyzed, and the main transmission path of power transmission is determined; the distance between each grid node is calculated according to the geographical location of the grid node; adjacent nodes are gradually connected according to the node distance from near to far, and a preliminary grid connection is established based on the key topological nodes and the main transmission path; the power flow, node load and grid coverage stability of the preliminary power grid are evaluated through power flow simulation, and the preliminary power grid topological relationship is optimized based on the simulation evaluation results to obtain the complete grid-connected topological structure.

[0034] Specifically, the power grid is abstracted into a graph, where nodes represent power grid equipment (such as substations, lines, etc.) and edges represent connections between equipment. Graph theory algorithms, such as node degree centrality, betweenness centrality, and closeness centrality, are used to identify key nodes in the graph, i.e., nodes that have an important impact on the stability of power grid operation. The power flow relationships of key topological nodes are analyzed to determine the flow pattern of power in the power grid and the mutual influence between nodes. Based on the power flow relationships of key topological nodes, the main transmission paths for power transmission are determined. These paths are the main channels for power flow in the power grid and have a significant impact on the stable operation of the power grid. The geographic location data of each node in the power grid is collected, including the latitude and longitude coordinates of the nodes. Using the geographic location, the distance between each node in the power grid is calculated through various geographic information system tools or algorithms, such as using the Euclidean distance formula. According to the distance between the nodes, the adjacent nodes are gradually connected from near to far to form a preliminary power grid connection. While connecting adjacent nodes, special attention is paid to key topological nodes and the main transmission paths for power transmission.

[0035] Use power system simulation software to simulate the power flow of the preliminary power grid. Power flow simulation can simulate the power flow of the power grid under various operating conditions, including normal operation and fault conditions. Through power flow simulation, the power flow, node load and grid coverage stability of the power grid are evaluated, and the operating efficiency and stability of the power grid under various conditions are analyzed. Through the simulation evaluation results, the problem of mismatching of power data matching relationships is identified. The reasons for the mismatch are analyzed, including too long node connection distance, insufficient transmission capacity or uneven load distribution. Within the distance range, consider configuring other nodes to improve stability, power flow and load matching, including adding new substations, adjusting line connections, adding transmission lines, etc. Adjust the preliminary topological relationship to optimize node connections. If necessary, add intermediate nodes to shorten the distance between nodes and improve power flow efficiency. Redefine the distance standard between nodes based on the actual operation of the power grid and the optimization goals, and appropriately relax the maximum allowable distance between nodes while ensuring the stability of the power grid. Use the relaxed distance standard to re-evaluate the topology structure to determine which node connections can be maintained and which need to be adjusted. Based on the results of the re-evaluation, an optimization plan for the topology structure is formulated, including specific node adjustment measures, new line layout and equipment configuration. Through optimization, the final grid-connected complete topology structure is obtained. Using graph theory algorithms and power flow simulation, from the identification of key topological nodes to the optimization of the grid topology structure, not only the physical layout of the grid is considered, but also the operational performance of the grid is ensured through simulation and optimization.

[0036] Furthermore, the present application also includes the following steps:

[0037] According to the simulation evaluation results, abnormal nodes are determined, including load mismatch, insufficient transmission capacity, and abnormal stability; the node distance is expanded with the abnormal node as the center, and power flow matching is performed on the grid nodes covered in the expanded circle. The node connection distance and power flow matching relationship are used as comprehensive evaluation targets and the target weights are configured to determine the optimized node connection relationship; the abnormal nodes are inserted and replaced using the optimized node connection relationship to obtain the complete grid-connected topology structure.

[0038] Specifically, according to the results of power flow simulation evaluation, abnormal nodes in the power grid are identified, including load mismatch, insufficient transmission capacity or abnormal stability. The identified abnormal nodes are analyzed to determine the causes of their abnormality, including inaccurate power demand forecasts, equipment aging, design defects, etc. The location, type and impact range of the abnormal nodes are recorded. With the identified abnormal node as the center, the circle is expanded according to a certain distance range, and the grid nodes around the abnormal node are considered. Within the expanded circle, the covered grid nodes are matched with power flow, and the power flow relationship between these nodes is analyzed to ensure that the power flow matches the needs and operating conditions of the grid. The node connection distance and power flow matching relationship are used as comprehensive evaluation targets, and these two factors are considered simultaneously when optimizing the connection relationship of grid nodes. The weights of each target are configured, and an optimization model is established, and the comprehensive evaluation target is used as the optimization target. Use optimization algorithms (such as genetic algorithms, simulated annealing algorithms, etc.) to find the optimal or approximately optimal node connection relationship, including adjusting the connection mode between nodes or adding / reducing certain equipment. After determining the optimized node connection relationship, the identified abnormal nodes are inserted and replaced, including adding new connections, adjusting existing connections or replacing equipment. The optimized node connection relationship is applied to the abnormal nodes to improve their operating status. By inserting and replacing, the corrected grid-connected complete topology is obtained to ensure that the new topology can effectively solve the problem of abnormal nodes and improve the overall performance of the power grid. By identifying and optimizing abnormal nodes in the power grid, the topology of the power grid is improved, thereby improving the stability and operating efficiency of the power grid.

[0039] Furthermore, step five of this application includes:

[0040] Acquire historical operation data of the grid-connected power grid, perform time series feature learning through fault time series samples, and obtain a time series fault prediction model; fit the time series fault prediction model to the edge computing device deployed by the grid-connected power grid; the edge computing device extracts target time series data from the monitored operation data based on a sliding window, and regularly predicts faults of the grid-connected power grid through the time series fault prediction model according to the time length of the sliding window; locate the predicted fault nodes and fault impact range of the power grid equipment according to the fault prediction results, adjust the grid-connected control strategy based on the predicted fault nodes and fault impact range, and determine the grid-connected control strategy.

[0041] Specifically, historical operation data of the grid-connected power grid is obtained, including parameters such as voltage, current, power, frequency, and the operation status of the power grid at different time points. Fault time series samples are data samples containing the time when the power grid fault occurs. The fault time series samples are learned using machine learning algorithms to identify the time series patterns and features in the operation of the power grid. Based on the results of time series feature learning, a time series fault prediction model is constructed to predict possible future faults in the power grid. The time series fault prediction model is fitted and the parameters of the model are adjusted to the optimal state so that the model can accurately predict faults in the power grid. The fitted time series fault prediction model is deployed to the edge computing device deployed by the grid-connected power grid to ensure that the device can run the model in real time and extract key time series features. The edge computing device uses the sliding window technology to process the monitoring operation data, and regularly uses the previously fitted time series fault prediction model to predict the faults of the extracted target time series data, identify potential fault modes, and give prediction results. The sliding window is a data processing technology that extracts target time series data by intercepting data samples at fixed time intervals. According to the fault prediction results, locate the predicted fault nodes and the fault impact range, and determine the equipment or areas that may be affected. According to the predicted fault nodes and the fault impact range, adjust the grid control strategy, such as optimizing the operating parameters of the power grid, adjusting the settings of the protection device, strengthening monitoring, and launching the emergency plan. Establish a fast exception handling mechanism. When the edge computing node detects an abnormal situation, it immediately starts the emergency plan, including switching the backup power supply, adjusting the load distribution, isolating the fault node, and issuing an alarm signal. Based on the prediction results and control strategy adjustments, determine the final grid control strategy. By locating the predicted fault nodes and the fault impact range, and adjusting the grid control strategy based on this information, real-time monitoring and fault prediction of the grid-connected power grid can be achieved, and the control strategy can be adjusted in time according to the prediction results to improve the stability and security of the power grid.

[0042] Furthermore, the present application also includes the following steps:

[0043] Obtain the geographical coordinates and grid topology data of the difference grid nodes; determine the geographical distribution of the difference grid nodes based on the geographical coordinates and obtain the geographical environment data; identify the nodes with strong correlation as the strategy optimization nodes based on the positional relationship of the difference grid nodes in the grid topology; adjust the risk assessment based on the geographical environment data and establish the environmental adjustment coefficient; configure the optimization weight according to the environmental adjustment coefficient and regulate and optimize the strategy optimization nodes.

[0044] Specifically, the geographic coordinate data of the difference power grid nodes, including the latitude and longitude coordinates of the nodes, are collected to determine the specific location of the nodes in the power grid. The positional relationship data of the difference power grid nodes in the power grid topology are extracted from the power grid management system, including the connection relationship between nodes, transmission lines and other information. According to the geographic coordinates, the distribution of the difference power grid nodes in the geographic space is determined, including the location, distribution density and relationship between the nodes. The geographical environment data of the area where the difference power grid nodes are located, such as topography, meteorological conditions, soil type, etc., are collected. The positional relationship of the difference power grid nodes in the power grid topology is analyzed to understand how these nodes are connected and affect each other. According to the analysis results, the nodes with strong correlation are identified, that is, they play a key role in the power grid and have an important impact on the stability and efficiency of the power grid. The identified nodes with strong correlation are used as strategy optimization nodes. In the optimization and regulation of the power grid, these nodes will receive special attention and treatment.

[0045] Analyze geographic environmental data, adjust risk assessment, and evaluate the risks of the power grid under specific environmental conditions, such as natural disasters, extreme weather, etc. According to the results of risk assessment, establish environmental adjustment coefficients to reflect the degree of influence of different environmental factors on the operation of the power grid. Based on the environmental adjustment coefficients, configure optimization weights for different nodes in the power grid to reflect the importance of nodes in power grid optimization and their sensitivity to environmental changes. Evaluate the degree of influence of each node on the environment, and rate the environmental sensitivity of each node, which is divided into three levels: high, medium, and low. According to the environmental sensitivity rating, assign an adjustment coefficient weight to each node. The more environmentally sensitive the node, the smaller its adjustment coefficient weight should be to reduce the adjustment of parameters. The less environmentally sensitive the node, the larger its adjustment coefficient weight should be so that more adjustments can be made when necessary. According to the configured optimization weights, the strategy optimization nodes are regulated and optimized, that is, according to the node weights, their operating parameters are adjusted to improve the efficiency and stability of the power grid. By analyzing geographic environmental data, risk assessment is performed and environmental adjustment coefficients are established. The optimization weights are configured according to these coefficients, and the strategy optimization nodes are regulated and optimized. The degree of impact of different nodes on the environment is taken into consideration. By adjusting the coefficient weights, various factors in the power grid optimization process are balanced to ensure the reliability and economy of power supply.

[0046] Furthermore, the present application also includes the following steps:

[0047] According to the historical sample set, multi-objective fitting is performed based on the geographical environment data to determine the influence of each geographical environment data on the power grid node, and the evaluation weights are configured according to the influence of each geographical environment data to construct the environmental risk evaluation function: The environmental adjustment coefficient is obtained, where R ik is the risk impact of the kth geographical environment factor on the grid node i, ω kis the evaluation weight of the kth geographical environmental factor; the environmental adjustment coefficient is converted into the optimization weight, and the conversion expression is: Among them, W i is the optimization weight of the i-th optimization node, R i is the environmental adjustment coefficient of node i, reflecting the impact of environmental risks on the node, R min is the minimum risk assessment value, R max is the maximum risk assessment value, α is the basic weight, which indicates the lowest optimization weight of all nodes, and β is the amplification factor, which is used to adjust the influence of the environmental adjustment coefficient on the optimization weight.

[0048] Specifically, using historical sample sets, a multi-objective fitting analysis is performed on the operating data of power grid nodes in different geographical environments to identify the relationship between geographical environmental factors and power grid node performance. Based on the results of the multi-objective fitting analysis, the influence of each geographical environmental data on the power grid nodes is determined, and it is identified which factors have a significant impact on the performance of the power grid nodes and which have a smaller impact. According to the influence of each geographical environmental data, the evaluation weights are configured to reflect the importance of different geographical environmental factors in the power grid risk assessment. An environmental risk assessment function is constructed to evaluate the risk impact of power grid nodes under specific geographical environmental factors. The expression of the environmental risk assessment function is: Among them, R i is the total environmental risk score of grid node i, R ik is the risk impact of the kth geographical environment factor on the power grid node i, reflecting the specific impact of the factor on the node i, ω k is the evaluation weight of the kth geographical environmental factor, indicating the degree of influence of this factor on environmental risk. By constructing the environmental risk evaluation function, the risk score of each power grid node under different geographical environmental factors is obtained, and the environmental adjustment coefficient is calculated.

[0049] The environmental adjustment factor R i Converted into weight W for optimizing decision making i , the conversion expression is Among them, W i is the optimization weight of the i-th optimization node, representing the importance of the node in the optimization decision; R i It is a quantitative representation of the impact of environmental risks on node i, reflecting the impact of environmental risks on the node; R min is the minimum risk assessment value, which is the lowest value of the environmental risk assessment values ​​of all nodes in the entire power grid; R maxis the maximum risk assessment value, which is the highest value among the environmental risk assessment values ​​of all nodes in the entire power grid. α is the basic weight, which represents the lowest optimization weight of all nodes, which means that even when the environmental adjustment coefficient is zero, each node still has a certain weight for optimization. β is the amplification factor, which is used to adjust the degree of influence of the environmental adjustment coefficient on the optimization weight. The value of β can amplify or reduce the influence of the environmental adjustment coefficient on the optimization weight. At nodes with greater environmental risks, their optimization weights are relatively small, while at nodes with smaller environmental risks, their optimization weights are relatively large. Ensure that during the power grid optimization process, nodes with greater environmental risks receive proper attention, while nodes with smaller environmental risks can undergo more optimization adjustments, thereby improving the operating efficiency of the power grid, protecting the environment, and achieving sustainable development.

[0050] In summary, the smart grid connection control method based on edge computing provided by this application has the following technical effects:

[0051] By identifying the key nodes of the grid-connected power grid and deploying edge computing devices, a communication network between the edge computing nodes and the central control is established; the real-time monitoring data of the power grid is obtained, and the grid power characteristics are identified and analyzed by matching the edge computing nodes according to the deployment relationship between the power grid and the edge computing nodes, and the power characteristics of the power grid are obtained, and the power characteristics of the power grid include at least voltage, frequency, and power; according to the topological structure of each grid-connected power grid, the topological structure is integrated according to the grid location distance to build a complete grid-connected topological structure; based on the complete grid-connected topological structure, the characteristic traversal path is determined, and the voltage, frequency, and power deviation are traversed according to the power transmission sequence of the characteristic traversal path and the power characteristics of the power grid, and the difference grid nodes are identified and located; the grid deviation is regulated according to the position distribution relationship of the difference grid nodes, and the grid control strategy is determined. In other words, by deploying edge computing devices at key nodes, a complete grid topological structure is constructed, and grid nodes with differences are identified and regulated, thereby improving the stability and operation efficiency of the grid connection.

[0052] Embodiment 2, based on the same inventive concept as the smart grid connection control method based on edge computing in the previous embodiment, this application also provides a smart grid connection control system based on edge computing, please refer to the attached Figure 2 , the smart grid grid-connected control system based on edge computing includes:

[0053] The key node deployment module 11 is used to identify the key nodes of the grid-connected power grid, deploy edge computing devices, and establish a communication network between the edge computing nodes and the central control.

[0054] The feature recognition module 12 is used to obtain real-time monitoring data of the power grid. According to the deployment relationship between the power grid and the edge computing nodes, the real-time monitoring data is subjected to grid-connected power feature recognition and analysis by matching the edge computing nodes to obtain power characteristics of the power grid, which at least include voltage, frequency, and power.

[0055] The topology integration module 13 is used to integrate the topology structures of the grid-connected power grids according to the topology structures of the grid-connected power grids and the distance between the grid locations, so as to construct a complete grid-connected topology structure.

[0056] The traversal path determination module 14 is used to determine the characteristic traversal path based on the complete grid-connected topology structure, traverse the voltage, frequency, and power deviation amounts according to the power characteristics of the power grid in the power transmission sequence of the characteristic traversal path, and identify and locate the difference power grid nodes.

[0057] The grid-connected deviation control module 15 is used to perform grid-connected deviation control according to the position distribution relationship of the differential grid nodes and determine the grid-connected control strategy.

[0058] Furthermore, the key node deployment module 11 in the edge computing-based smart grid grid-connected control system is also used for:

[0059] Collect the grid topology and its power operation data, and use power flow analysis tools to identify substation equipment and transmission lines in load-concentrated areas; identify and mark the substation equipment and transmission lines through historical high-frequency grid-connected fault points and fault characteristics, and determine the key nodes; analyze the power operation characteristics of the key nodes, determine the edge computing device configuration, including computing power, storage capacity and communication modules, and deploy the edge computing devices to the key nodes.

[0060] Furthermore, the topology structure integration module 13 in the smart grid grid-connected control system based on edge computing is also used for:

[0061] A graph theory algorithm is used to identify the key topological nodes of each grid-connected power grid, the power flow relationship of the key topological nodes is analyzed, and the main transmission path of power transmission is determined; the distance between each grid node is calculated according to the geographical location of the grid node; adjacent nodes are gradually connected according to the node distance from near to far, and a preliminary grid connection is established based on the key topological nodes and the main transmission path; the power flow, node load and grid coverage stability of the preliminary power grid are evaluated through power flow simulation, and the preliminary power grid topological relationship is optimized based on the simulation evaluation results to obtain the complete grid-connected topological structure.

[0062] Furthermore, the topology structure integration module 13 in the smart grid grid-connected control system based on edge computing is also used for:

[0063] According to the simulation evaluation results, abnormal nodes are determined, including load mismatch, insufficient transmission capacity, and abnormal stability; the node distance is expanded with the abnormal node as the center, and power flow matching is performed on the grid nodes covered in the expanded circle. The node connection distance and power flow matching relationship are used as comprehensive evaluation targets and the target weights are configured to determine the optimized node connection relationship; the abnormal nodes are inserted and replaced using the optimized node connection relationship to obtain the complete grid-connected topology structure.

[0064] Furthermore, the grid-connected deviation control module 15 in the edge computing-based smart grid grid-connected control system is also used for:

[0065] Acquire historical operation data of the grid-connected power grid, perform time series feature learning through fault time series samples, and obtain a time series fault prediction model; fit the time series fault prediction model to the edge computing device deployed by the grid-connected power grid; the edge computing device extracts target time series data from the monitored operation data based on a sliding window, and regularly predicts faults of the grid-connected power grid through the time series fault prediction model according to the time length of the sliding window; locate the predicted fault nodes and fault impact range of the power grid equipment according to the fault prediction results, adjust the grid-connected control strategy based on the predicted fault nodes and fault impact range, and determine the grid-connected control strategy.

[0066] Furthermore, the grid-connected deviation control module 15 in the edge computing-based smart grid grid-connected control system is also used for:

[0067] Obtain the geographical coordinates and grid topology data of the difference grid nodes; determine the geographical distribution of the difference grid nodes based on the geographical coordinates and obtain the geographical environment data; identify the nodes with strong correlation as the strategy optimization nodes based on the positional relationship of the difference grid nodes in the grid topology; adjust the risk assessment based on the geographical environment data and establish the environmental adjustment coefficient; configure the optimization weight according to the environmental adjustment coefficient and regulate and optimize the strategy optimization nodes.

[0068] Furthermore, the grid-connected deviation control module 15 in the edge computing-based smart grid grid-connected control system is also used for:

[0069] According to the historical sample set, multi-objective fitting is performed based on the geographical environment data to determine the influence of each geographical environment data on the power grid node, and the evaluation weights are configured according to the influence of each geographical environment data to construct the environmental risk evaluation function: The environmental adjustment coefficient is obtained, where R ikis the risk impact of the kth geographical environment factor on the grid node i, ω k is the evaluation weight of the kth geographical environmental factor; the environmental adjustment coefficient is converted into the optimization weight, and the conversion expression is: Among them, W i is the optimization weight of the i-th optimization node, R i is the environmental adjustment coefficient of node i, reflecting the impact of environmental risks on the node, R min is the minimum risk assessment value, R max is the maximum risk assessment value, α is the basic weight, indicating the lowest optimization weight of all nodes, and β is the amplification factor, which is used to adjust the influence of the environmental adjustment coefficient on the optimization weight.

[0070] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The smart grid grid-connected control method based on edge computing and the specific examples in the first embodiment are also applicable to the smart grid grid-connected control system based on edge computing in this embodiment. Through the above detailed description of the smart grid grid-connected control method based on edge computing, those skilled in the art can clearly know the smart grid grid-connected control system based on edge computing in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0071] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0072] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A smart grid connection control method based on edge computing, characterized in that: The smart grid connection control methods based on edge computing include: Identify key nodes of the grid-connected power grid to deploy edge computing devices and establish a communication network between edge computing nodes and central control; Acquire real-time monitoring data of the power grid, and perform grid-connected power feature identification and analysis on the real-time monitoring data by matching edge computing nodes according to the deployment relationship between the power grid and the edge computing nodes, to acquire power characteristics of the power grid, where the power characteristics of the power grid include at least voltage, frequency, and power; According to the topological structure of each grid-connected power grid, the topological structure is integrated according to the location distance of the grid to build a complete grid-connected topological structure; Determine a characteristic traversal path based on the complete grid-connected topology structure, traverse the voltage, frequency, and power deviations according to the power characteristics of the power grid in the power transmission order of the characteristic traversal path, and identify and locate differential power grid nodes; Grid connection deviation control is performed according to the position distribution relationship of the differential grid nodes to determine the grid connection control strategy; Grid connection deviation control is performed according to the position distribution relationship of the differential grid nodes, including: Obtain geographical coordinates and grid topology data of different grid nodes; According to the geographic coordinates, determining the geographic distribution of the difference power grid nodes and acquiring geographic environment data; According to the positional relationship of the difference power grid nodes in the power grid topology structure, identifying nodes with strong correlation as strategy optimization nodes; Conduct risk assessment adjustment based on the geographic environment data and establish environmental adjustment coefficients; The optimization weight is configured according to the environmental adjustment coefficient, and the strategy optimization node is regulated and optimized.

2. The smart grid connection control method based on edge computing according to claim 1, characterized in that: The method of identifying key nodes of the grid-connected power grid and deploying edge computing devices includes: Collect grid topology and power operation data, and use power flow analysis tools to identify substation equipment and transmission lines in load-concentrated areas; Identify and mark the substation equipment and transmission lines through historical high-frequency grid-connected fault points and fault characteristics to determine the key nodes; The power operation characteristics of the key nodes are analyzed to determine the edge computing device configuration, including computing power, storage capacity and communication modules, and the edge computing device is deployed on the key nodes.

3. The smart grid connection control method based on edge computing according to claim 1, characterized in that: The construction of a complete grid-connected topology structure includes: Using graph theory algorithms to identify key topological nodes of each grid-connected power grid, analyzing the power flow relationship of the key topological nodes, and determining the main transmission path for power transmission; According to the geographical location of the grid nodes, the distance between each grid node is calculated; According to the node distance from near to far, the adjacent nodes are gradually connected, and a preliminary grid connection is established based on the key topological nodes and the main transmission paths; The power flow, node load and grid coverage stability of the preliminary power grid are evaluated through power flow simulation, and the preliminary power grid topology relationship is optimized based on the simulation evaluation results to obtain the complete grid topology structure.

4. The smart grid connection control method based on edge computing according to claim 3, characterized in that: The optimizing of the preliminary grid topology relationship based on the simulation evaluation result to obtain the complete grid-connected topology structure includes: According to the simulation evaluation results, abnormal nodes are determined, including load mismatch, insufficient transmission capacity, and abnormal stability; The node distance circle is expanded with the abnormal node as the center, and the power flow matching is performed on the covered power grid nodes in the expanded circle. The node connection distance and the power flow matching relationship are used as comprehensive evaluation targets and the weights of each target are configured to determine the optimized node connection relationship; The abnormal nodes are inserted and replaced by using the optimized node connection relationship to obtain the complete grid-connected topology structure.

5. The smart grid connection control method based on edge computing according to claim 1, characterized in that: The determining of the grid connection control strategy further includes: Obtain the historical operation data of the grid-connected power grid, learn the time series features through the fault time series samples, and obtain the time series fault prediction model; Fitting the sequential fault prediction model to the edge computing device deployed in the grid-connected power grid; The edge computing device extracts target time series data from the monitoring operation data based on a sliding window, and regularly predicts faults of the grid-connected power grid through the time series fault prediction model according to the time length of the sliding window; The predicted fault nodes and the fault impact range of the power grid equipment are located according to the fault prediction results, and the grid connection control strategy is adjusted based on the predicted fault nodes and the fault impact range to determine the grid connection control strategy.

6. The smart grid connection control method based on edge computing according to claim 1, characterized in that: Configuring the optimization weight according to the environmental adjustment coefficient includes: According to the historical sample set, multi-objective fitting is performed according to the geographical environment data to determine the influence of each geographical environment data on the power grid node, and the evaluation weights are configured according to the influence of each geographical environment data to construct the environmental risk evaluation function: , obtain the environmental adjustment coefficient, where, is the risk impact of the kth geographical environment factor on the grid node i, is the evaluation weight of the kth geographical environment factor; The environmental adjustment coefficient is converted into the optimization weight, and the conversion expression is: ,in, is the optimization weight of the i-th optimization node, is the environmental adjustment coefficient of node i, reflecting the impact of environmental risks on the node. is the minimum risk assessment value, is the maximum risk assessment value, is the basic weight, indicating the lowest optimization weight of all nodes, It is the amplification factor, which is used to adjust the influence of the environmental adjustment coefficient on the optimization weight.

7. The smart grid connected control system based on edge computing is characterized by: The steps for implementing the smart grid connection control method based on edge computing according to any one of claims 1 to 6, wherein the smart grid connection control system based on edge computing comprises: A key node deployment module, which is used to identify key nodes of the grid-connected power grid to deploy edge computing devices and establish a communication network between the edge computing nodes and the central control; A feature recognition module, which is used to obtain real-time monitoring data of the power grid, and to perform grid-connected power feature recognition and analysis on the real-time monitoring data by matching edge computing nodes according to the deployment relationship between the power grid and the edge computing nodes, so as to obtain power characteristics of the power grid, wherein the power characteristics of the power grid include at least voltage, frequency, and power; A topology integration module, which is used to integrate the topology structures of the grid-connected power grids according to the topology structures of the grid-connected power grids and the distance between the grid locations, so as to construct a complete grid-connected topology structure; A traversal path determination module, the traversal path determination module is used to determine a characteristic traversal path based on the complete grid-connected topology structure, traverse the voltage, frequency, and power deviation amounts according to the power characteristics of the power grid in the power transmission sequence of the characteristic traversal path, and identify and locate differential power grid nodes; A grid-connected deviation control module is used to perform grid-connected deviation control according to the position distribution relationship of the difference power grid nodes and determine the grid-connected control strategy.

Images