Method and device for processing configuration data of distribution network system, and computer equipment

Abstract

The invention relates to a processing method and device for configuration data of a distribution network system and computer equipment. The method comprises the following steps: acquiring line loss preprocessing data of different voltage grades; acquiring a real-time line topological structure, and determining an updated data transmission path based on the changed line topological structure under the condition that the line topological structure changes; determining a line loss calculation deviation percentage based on the updated data transmission path and the line loss preprocessing data, and adjusting weight parameters of the line loss preprocessing data of different voltage grades based on the line loss calculation deviation percentage under the condition that the line loss calculation deviation percentage exceeds a preset threshold value; and calculating the line loss preprocessing data of the different voltage levels based on the target data transmission path to obtain configuration data of the multiple lines, and performing weighted summation on the configuration data of the multiple lines based on the weight parameters of the line loss preprocessing data of the different voltage levels to obtain configuration data of the distribution network system.

Description

Technical Field

[0001] This application relates to the field of information technology, and in particular, to a method, device, and computer device for processing configuration data of a distribution network system. Background Art

[0002] Analysis of distribution network line losses is an important part of power system operation and maintenance. In the edge computing environment, a large amount of line loss data and line topology information are scattered in each edge node, and there are significant differences in data formats and computing capabilities among different edge nodes. Traditional centralized computing methods are difficult to meet the distributed collaborative analysis requirements of lines with different voltage levels. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method, device, and computer device for processing configuration data of a distribution network system.

[0004] In a first aspect, this application provides a method for processing configuration data of a distribution network system. The method includes:

[0005] Obtain preprocessed data of line losses for different voltage levels in the distribution network system;

[0006] Obtain the real-time line topology structure. When the line topology structure changes, determine the updated data transmission path based on the changed line topology structure;

[0007] Based on the updated data transmission path and the preprocessed data of line losses, determine the percentage deviation of line loss calculation. When the percentage deviation of line loss calculation exceeds a preset threshold, adjust the weight parameters of the preprocessed data of line losses for different voltage levels based on the percentage deviation of line loss calculation;

[0008] Calculate the configuration data of multiple lines based on the target data transmission path for the preprocessed data of line losses for different voltage levels, and perform weighted summation on the configuration data of multiple lines based on the weight parameters of the preprocessed data of line losses for different voltage levels to obtain the configuration data of the distribution network system.

[0009] In one embodiment, the process of obtaining the preprocessed data of line losses includes:

[0010] Obtain the operation data of the distribution network system;

[0011] Based on the operation data of the distribution network system, extract the physical connection relationship between line nodes from the line topology structure to obtain line node correlation data;

[0012] Based on a pre-designed calculation model, the operation data of the distribution network system, and the line node correlation data, obtain a loss prediction quantization index;

[0013] Classify the original line loss data of different voltage levels in the distribution network system based on the clustering algorithm and the loss prediction quantization index, and obtain the original line loss data of different voltage levels after classification;

[0014] Calculate the original line loss data of different voltage levels after classification based on a preset rule to obtain the preprocessed line loss data of different voltage levels.

[0015] In one embodiment, the update process of the data transmission path includes:

[0016] Obtain communication bandwidth measurement data from the edge nodes of the line topology structure, and calculate communication delay parameters according to the physical distance between line nodes;

[0017] Based on the communication bandwidth measurement data and the communication delay parameters, obtain a data transmission path quality index;

[0018] When the data transmission path quality index is less than the preset quality index, recalculate the data transmission path based on the ant colony algorithm to obtain data transmission paths with different priorities;

[0019] Update the data transmission path based on the priority order of the data transmission path.

[0020] In one embodiment, the update process of the data transmission path further includes:

[0021] Obtain the changed line topology data, and construct a new line topology structure based on the changed line topology data;

[0022] Using the edge nodes in the new line topology structure as the starting and ending points, and taking the line communication quality parameter as the edge weight, search for the data transmission path between the edge nodes using the shortest path algorithm to obtain the primary data transmission path;

[0023] Add a Gaussian random perturbation value to the primary data transmission path and repeat the path search to obtain the secondary data transmission path.

[0024] In one embodiment, the calculation process of the line loss calculation deviation percentage includes:

[0025] Obtain the real-time communication status data between the edge nodes in the line topology structure, and the communication status data includes transmission delay data, bandwidth utilization data, and packet loss rate data;

[0026] Hierarchize the data transmission path based on the communication status data to obtain a transmission path level value, and extract the line loss data of the voltage level corresponding to the data transmission path level value from the preprocessed line loss data of different voltage levels;

[0027] Calculate the percentage deviation of the line loss calculation based on the line loss data of the voltage level.

[0028] In one embodiment, the method further includes:

[0029] Obtain the operating status of the edge nodes in the line topology and the change trend of the line loss data, and trigger an early warning mechanism when the operating status of the edge nodes in the line topology and the change trend of the line loss data are abnormal.

[0030] In one embodiment, the method further includes:

[0031] Obtain the line topology data in the historical operation database;

[0032] Establish a long short-term memory neural network prediction model based on the line topology data, and obtain the probability of line topology structure change based on the long short-term memory neural network prediction model;

[0033] Traverse the area where the probability of line topology structure change is greater than the preset threshold based on the depth-first search algorithm, and obtain the physical distance, communication bandwidth, and transmission delay parameters between the edge nodes;

[0034] Obtain the main transmission path, standby transmission path, and emergency transmission path based on the physical distance, communication bandwidth, and transmission delay parameters between the edge nodes.

[0035] In a second aspect, the present application further provides a processing device for the configuration data of a distribution network system, and the device includes:

[0036] An acquisition module, configured to acquire the preprocessed line loss data of different voltage levels in the distribution network system;

[0037] A selection module, configured to acquire the real-time line topology structure, and determine the updated data transmission path based on the changed line topology structure when the line topology structure changes;

[0038] A calculation module, configured to determine the percentage deviation of the line loss calculation based on the updated data transmission path and the preprocessed line loss data, and adjust the weight parameters of the preprocessed line loss data of different voltage levels based on the percentage deviation of the line loss calculation when the percentage deviation of the line loss calculation exceeds the preset threshold;

[0039] A configuration module is used to calculate the pre - processed data of line losses for different voltage levels based on the target data transmission path, obtain the configuration data of multiple lines, and perform weighted summation on the configuration data of multiple lines based on the weight parameters of the pre - processed data of line losses for different voltage levels to obtain the configuration data of the distribution network system.

[0040] In a third aspect, the present disclosure also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method for processing the configuration data of the distribution network system.

[0041] In a fourth aspect, the present disclosure also provides a computer - readable storage medium. The computer - readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps of the method for processing the configuration data of the distribution network system.

[0042] In a fifth aspect, the present disclosure also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method for processing the configuration data of the distribution network system.

[0043] The above - mentioned method for processing the configuration data of the distribution network system has at least the following beneficial effects:

[0044] The embodiment solution provided by the present disclosure obtains the pre - processed data of line losses for different voltage levels. According to the change of the real - time line topology structure, it determines the updated data transmission path. It also introduces a collaborative analysis mechanism to perform weighted summation on the pre - processed data of line losses for different voltage levels to obtain the overall line loss of the distribution network system, which can ensure the calculation accuracy while improving the data transmission efficiency and effectively cope with the dynamic change of the distribution network topology.

[0045] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is an application environment diagram of the method for processing the configuration data of the distribution network system in an embodiment;

[0048] Figure 2Schematic flowchart of a method for processing configuration data of a distribution network system in an embodiment;

[0049] Figure 3 Schematic diagram of processing configuration data of a distribution network system in an embodiment;

[0050] Figure 4 Schematic diagram of processing configuration data of a distribution network system in an embodiment;

[0051] Figure 5 Block diagram of the structure of a processing device for configuration data of a distribution network system in an embodiment;

[0052] Figure 6 Internal structure diagram of a computer device in an embodiment;

[0053] Figure 7 Internal structure diagram of a server in an embodiment. Detailed implementation manners

[0054] To enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0055] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims. The term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, product or device. Without further limitation, there is no exclusion of the existence of additional identical or equivalent elements in the process, method, product or device including the said elements. For example, if the terms first, second, etc. are used to denote names, they do not denote any specific order.

[0056] The embodiments of the present disclosure provide a method for processing configuration data of a distribution network system, which can be applied to such as Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0057] In some embodiments of the present disclosure, as Figure 2 shown, a method for processing configuration data of a network configuration system is provided. Taking the application of this method to Figure 1 the server in it to process the configuration data as an example for illustration. It can be understood that this method can be applied to the server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In a specific embodiment, the method may include the following steps:

[0058] S202: Obtain the preprocessing data of line losses at different voltage levels in the network configuration system.

[0059] In the network configuration system, line losses will occur during the operation of lines at different voltage levels. According to the distribution line operation parameters and load data obtained from the network configuration system by the data acquisition device, the preprocessing data of line losses at different voltage levels is calculated.

[0060] S204: Obtain the real-time line topology structure. When the line topology structure changes, determine the updated data transmission path based on the changed line topology structure.

[0061] Obtain the substation feeder switch status information and line topology structure data from the distribution network monitoring terminal, process the switch status information and topology structure data using data verification methods to obtain a real-time topology dataset; according to the real-time topology dataset, traverse the switch connection relationships in the real-time topology dataset using the depth-first search algorithm, trace the line connection relationships starting from the substation outgoing line to obtain the real-time line topology structure; for the real-time line topology structure, obtain the communication bandwidth measurement data from the edge nodes, calculate the communication delay parameters based on the physical distance data between nodes, and use a combined evaluation method to perform weighted calculations on communication bandwidth, communication delay, and packet loss rate to obtain a link quality index; if the link quality index is lower than the preset reference value, use the ant colony algorithm to recalculate the data transmission path, represent the path passing frequency through pheromone concentration, set the path selection probability based on the link quality index, and use a path scoring method to perform priority sorting on the transmission path to obtain a transmission path priority list; according to the transmission path priority list, reconstruct the data channels of the edge nodes, and establish data transmission channels between nodes step by step in the order of path priorities.

[0062] S206: Based on the updated data transmission path and the line loss preprocessing data, determine the line loss calculation deviation percentage. In the case where the line loss calculation deviation percentage exceeds the preset threshold, adjust the weight parameters of the line loss preprocessing data for different voltage levels based on the line loss calculation deviation percentage.

[0063] Use a communication monitoring device to obtain the real-time communication status data between edge nodes. The communication status data includes transmission delay data, bandwidth utilization data, and packet loss rate data; classify the transmission path according to the communication status data to obtain a transmission path level value, and extract the line loss data of the voltage level corresponding to the transmission path level value from the line loss preprocessing data; calculate the line loss calculation deviation percentage through the voltage level line loss data. The line loss calculation deviation percentage is obtained by dividing the calculated loss value minus the original loss value by the original loss value; use the double exponential smoothing algorithm to perform trend prediction on the line loss calculation deviation percentage to obtain a predicted deviation value. In the case where the line loss calculation deviation percentage exceeds the preset threshold, calculate the loss contribution degree values of the lines of different voltage levels, and adjust the weight parameters of the line loss preprocessing data for different voltage levels based on the line loss calculation deviation percentage.

[0064] S208: Calculate the configuration data of multiple lines based on the target data transmission path for the line loss preprocessing data of different voltage levels, and perform weighted summation on the configuration data of multiple lines based on the weight parameters of the line loss preprocessing data of different voltage levels to obtain the configuration data of the distribution network system.

[0065] Obtain the communication data between edge nodes, record the data transmission rate and transmission delay parameters between nodes through the communication data, and establish a mapping relationship between the communication parameters and the transmission efficiency using the multiple linear regression algorithm; obtain the data transmission efficiency evaluation value according to the mapping relationship, calculate the historical optimal value of the transmission efficiency using the cumulative probability distribution method, and record the communication parameters of the historical optimal transmission path; calculate the prediction error value of the line loss data using the mean square error loss function, where the prediction error value is obtained by dividing the sum of the squared residuals of the original line loss data and the calculated line loss data by the number of samples; if the data transmission efficiency evaluation value is greater than the historical optimal value and the prediction error value is less than the preset error threshold, then use the depth-first search algorithm to traverse the data transmission path and configure the data transmission channels of the edge nodes according to the node connectivity and link bandwidth.

[0066] Specifically, a data monitoring device is used to obtain the communication data between edge nodes, record the data transmission rate, transmission delay, and bandwidth utilization parameters between nodes, establish a mapping relationship between communication parameters and transmission efficiency through a multiple linear regression algorithm, and obtain the data transmission efficiency evaluation value. The transmission paths are classified according to the data transmission efficiency evaluation value, the historical optimal value of the transmission efficiency is calculated using the cumulative probability distribution method, and the communication parameter configuration of the historical optimal transmission path is recorded. The mean square error loss function is used to calculate the prediction error of the line loss data. The actual value in the loss function is the original line loss data, the predicted value is the calculated line loss data, and the mean square error value is obtained by dividing the sum of squared residuals by the number of samples. If the data transmission efficiency evaluation value is greater than the historical optimal value and the mean square error value is less than the preset error threshold, the depth-first search algorithm is used to traverse the data transmission path, and the search conditions include node connectivity, link bandwidth, and communication delay. For the searched transmission path, a routing optimization method is used to configure the data transmission channels of the edge nodes, and the configuration parameters include routing table entries, forwarding rules, and communication protocol parameters. The calculation weights in the collaborative analysis mechanism are updated according to the routing configuration parameters. The calculation weight value is positively correlated with the communication quality of the transmission path and negatively correlated with the transmission delay, and the data processing priorities of each node are re-sorted. In the operation of the distribution network, the data transmission efficiency between edge nodes is closely related to the accuracy of line loss calculation. Taking a certain urban distribution network as an example, 156 edge nodes are set in this area, and the communication status parameters between nodes are collected in real time through a data monitoring device. On a typical data transmission path, the original data recorded by the monitoring device shows that the data transmission rate is 100 megabits per second, the transmission delay is 15 milliseconds, and the bandwidth utilization rate is 75%. These parameters are analyzed using a multiple linear regression algorithm to establish a transmission efficiency evaluation model, and the calculated transmission efficiency evaluation value of this path is 0.82. Through the cumulative probability distribution statistics, the historical data of this transmission path in the past 30 days shows that the historical optimal value of the transmission efficiency is 0.85, and the corresponding communication parameter configuration is a transmission rate of 120 megabits per second, a transmission delay of 12 milliseconds, and a bandwidth utilization rate of 82%. This set of parameter configurations is used as the optimization target to guide subsequent path adjustments. For the evaluation of the accuracy of line loss calculation, the mean square error loss function is used for calculation. In the distribution area covered by this transmission path, the original line loss rate is 3.2%, the calculated line loss rate is 3.4%, and the number of samples is 1000 data points. The mean square error value calculated through the sum of squared residuals is 0.0025, which is lower than the preset threshold of 0.005. When it is found that the transmission efficiency evaluation value of this path is increased to 0.86 and the mean square error is reduced to 0.002, the depth-first search algorithm is triggered to optimize the transmission path. The search process shows that this path contains 5 nodes, the link bandwidth between nodes is greater than 100 megabits per second, and the communication delay is less than 20 milliseconds, meeting the connectivity requirements. According to the search results, the routing configuration of the edge nodes is updated.The new routing table entry contains the source node address 192.168.1.1, the destination node address 192.168.1.5, the next-hop address 192.168.1.2, the link bandwidth of 110 megabits per second, and the forwarding rule is set to high priority. At the same time, the communication protocol parameters are adjusted accordingly. The TCP window size is set to 64 kilobytes, and the keep-alive time interval is set to 60 seconds. After the routing configuration is updated, the calculation weight in the collaborative analysis mechanism is also adjusted. Originally, the calculation weight of this transmission path was 0.4. Considering the improvement of communication quality and the decrease in delay, the new calculation weight is adjusted to 0.5, which improves the priority of this path in data processing and enables the path with better transmission quality to undertake more data processing tasks.

[0067] In the method for processing the configuration data of the above distribution network system, preprocessing data of line losses at different voltage levels is obtained. According to the change of the real-time line topology structure, the updated data transmission path is determined. A collaborative analysis mechanism is also introduced to perform weighted summation on the preprocessing data of line losses at different voltage levels to obtain the overall line loss of the distribution network system, which can ensure the calculation accuracy while improving the data transmission efficiency and effectively cope with the dynamic change of the distribution network topology.

[0068] In some embodiments of the present disclosure, the process of obtaining the preprocessing data of line losses includes:

[0069] Obtain the operation data of the distribution network system;

[0070] Based on the operation data of the distribution network system, extract the physical connection relationship between line nodes from the line topology structure to obtain line node correlation data;

[0071] Based on a pre-designed calculation model, the operation data of the distribution network system, and the line node correlation data, obtain a loss prediction quantization index;

[0072] Based on a clustering algorithm and the loss prediction quantization index, classify the original line loss data at different voltage levels in the distribution network system to obtain the classified original line loss data at different voltage levels;

[0073] Based on a preset rule, calculate the preprocessing data of line losses at different voltage levels from the classified original line loss data at different voltage levels.

[0074] According to the data acquisition device, operating parameters and load data of the distribution line are obtained from the distribution system, and the maximum-minimum normalization method is used to standardize the operating parameters and load data to obtain standardized distribution line operating data; for the standardized distribution line operating data, the physical connection relationship between line nodes is extracted from the line topology structure, and the line node correlation data is calculated according to the physical connection relationship between line nodes and impedance parameters; a distribution line loss prediction model is constructed using the random forest algorithm, the standardized distribution line operating data and the line node correlation data are input into the prediction model, and a loss quantification index is obtained through training on historical loss data; for the loss quantification index, a clustering algorithm is used to classify and grade the distribution line loss data, and three distribution line levels of low loss, medium loss, and high loss are obtained according to the loss rate interval; an edge computing node is used to perform distributed processing on the classified and graded distribution line loss data, and the original line loss data of different voltage levels after classification is calculated according to the preset data aggregation rule to obtain the preprocessed line loss data of different voltage levels.

[0075] For example, in the distribution system of a certain city, there are distribution lines with four voltage levels of 380V, 10kV, 35kV, and 110kV. The data acquisition device collects operation parameters such as voltage, current, and power factor on each line. Taking one of the 10kV main lines as an example, the acquisition device records a set of data every 5 minutes, including phase voltage of 217V, line current of 42A, and power factor of 0.92. Such raw data is standardized using the maximum-minimum normalization method, normalizing the voltage value to the 0-1 interval, the current value to the 0-1 interval, and the power factor to the 0-1 interval, obtaining the standardized operation data. At the level of the distribution system topology, the total length of this 10kV main line is 2.4 kilometers, with 5 distribution nodes, and the resistance value of each phase conductor is 0.27 ohms per kilometer. The node correlation is calculated based on the physical distance between nodes and the wire resistance value. The correlation between adjacent nodes is 0.85, the correlation between nodes separated by one node is 0.62, and the correlation between nodes separated by two nodes is 0.43. These correlation data and the standardized operation data are jointly used as the input features of the random forest algorithm. By analyzing the operation data of this 10kV main line in the past 6 months, a loss prediction quantization index is established. The index shows that when the line loss rate is 3.5%, the prediction accuracy reaches 92.4%. After setting the loss rate benchmark value to 3%, in-depth analysis is carried out on the lines exceeding the benchmark value. The gradient descent method is used to extract characteristic parameters, and the key factors affecting the loss are found to include load rate, power factor, environmental temperature, etc. Based on the characteristic parameters, a clustering algorithm is used to classify the distribution lines according to the loss rate: a loss rate less than 2.5% is low loss, a loss rate between 2.5% - 4% is medium loss, and a loss rate greater than 4% is high loss. The loss data of this 10kV main line is classified as the medium loss level. The edge computing node performs distributed processing on the loss data of each level, using the MapReduce parallel computing framework, and classifying and summarizing the processing results according to the voltage level. In the distribution system of this city, the average loss rate of 380V lines is 2.8%, the average loss rate of 10kV lines is 3.2%, the average loss rate of 35kV lines is 2.4%, and the average loss rate of 110kV lines is 1.8%. These data reflect the loss levels of lines with different voltage levels and provide data support for subsequent line loss management. By analyzing the loss data of lines with each voltage level, key governance areas can be identified, high-loss lines can be accurately located, and refined management of the distribution system can be achieved.

[0076] In some embodiments of the present disclosure, the update process of the data transmission path includes:

[0077] Obtain communication bandwidth measurement data from the edge nodes of the line topology structure, and calculate communication delay parameters according to the physical distance between line nodes;

[0078] Obtain a data transmission path quality index based on the communication bandwidth measurement data and the communication delay parameter;

[0079] In the case where the data transmission path quality index is less than a preset quality index, recalculate the data transmission path based on the ant colony algorithm to obtain data transmission paths with different priorities;

[0080] Update the data transmission path based on the priority order of the data transmission paths.

[0081] Figure 3Schematic diagram for the processing of the configuration data of the distribution network system in an embodiment. Specifically, obtain the substation feeder switch status information, line breaker and disconnect switch status information, and distribution transformer operation status information from the distribution network monitoring terminal. Collect the current line topology structure data through the edge node, and use the data verification method to eliminate duplicate data and abnormal data to obtain the real-time topology data set. Use the depth-first search algorithm to traverse the switch connection relationship in the real-time topology data set, trace the line connection relationship starting from the substation outgoing line, calculate the line connection topology diagram according to the switch status flag bit, and record the physical distance data between each node in the line topology diagram. Obtain the communication bandwidth measurement data from the edge node, calculate the communication delay parameter according to the physical distance data between nodes, and use the combined evaluation method to perform weighted calculation on the communication bandwidth, communication delay, and packet loss rate to obtain the link quality index. If the link quality index is lower than the preset reference value, use the ant colony algorithm to recalculate the data transmission path, represent the path passing frequency through the pheromone concentration, set the path selection probability according to the link quality index, and calculate the optimal transmission path set. For the optimal transmission path set, set the path switching rule, use the path scoring method to perform priority sorting on the transmission path, and the scoring parameters include the path hop count, average delay, and link utilization rate to obtain the transmission path priority list. According to the transmission path priority list, use the dynamic routing allocation algorithm to reconstruct the data channel of the edge node, and establish the data transmission channel between nodes level by level in the order of path priority. During the operation of the distribution network line, the change of the line topology structure directly affects the efficiency and reliability of data transmission. Taking a certain urban distribution network as an example, 156 distribution network monitoring terminals are set in this area, and the feeder switch status, breaker status, and disconnect switch status information are collected in real time through these terminals. During the collection process, the monitoring terminal reports the switch quantity data every 30 seconds, and eliminates the duplicate reported switch status information and electrical quantity abnormal data, and retains the effective real-time topology data. Analyze the topology data based on the depth-first search algorithm, starting from the outgoing line of the No. 1 main transformer of the 110 kV substation, and sequentially traverse the breakers and disconnect switches on the 10 kV distribution line. When the breaker on a certain line is in the open state, the flag bit of this switch is recorded as 0, and when it is in the closed state, it is recorded as 1. Calculate the line connection relationship through the combination of the flag bits to form a complete topology connection diagram, and record the physical distance between adjacent nodes. For example, the distance from the No. 1 main transformer to the No. 2 ring main unit is 1.2 kilometers. For the communication status monitoring of the edge node, use the bandwidth test tool to measure the communication bandwidth between nodes every 5 minutes, and the measured communication bandwidth between the No. 1 main transformer and the No. 2 ring main unit is 100 megabits per second, the communication delay is 15 milliseconds, and the packet loss rate is 0.2%. Perform weighted calculation on these three indicators according to the weights of 4:3:3 to obtain the comprehensive link quality index of 0.92. When this index is lower than the preset reference value of 0.85, trigger the path reconstruction mechanism.During the path reconstruction process, the ant colony algorithm searches for the optimal transmission path through multiple rounds of iteration. The initial pheromone concentration is set to 1 on each possible path. Ants release pheromones when passing through a path, and the higher the pheromone concentration, the higher the frequency of selection of that path. At the same time, the path selection probability is set according to the link quality index, and the better the link quality, the higher the probability of being selected. After 200 rounds of iteration, 3 candidate transmission paths are obtained. Priority scores are given to these 3 candidate paths, and the scoring criteria include three dimensions: the number of path hops, the average delay, and the link utilization rate. Among them, the number of path hops reflects the number of nodes that data transmission needs to pass through, and the fewer the hops, the higher the score; the average delay represents the transmission delay of data packets on the path, and the shorter the delay, the higher the score; the link utilization rate represents the bandwidth occupancy on the path, and the lower the utilization rate, the higher the score. Through comprehensive scoring, a list of transmission paths sorted from high to low in priority is obtained. According to the path priority order, the dynamic routing allocation algorithm is used to reconstruct the data channels of the edge nodes. The path with the highest priority is used as the main transmission channel, and the other paths are used as backup channels. The routing forwarding tables of each node are updated, and a new data transmission strategy is established to ensure the continuity of data transmission after the network topology changes.

[0082] In some embodiments of the present disclosure, the update process of the data transmission path further includes:

[0083] Obtain the changed line topology data, and construct a new line topology structure based on the changed line topology data;

[0084] Based on the edge nodes in the new line topology structure as the starting and ending points, using the line communication quality parameter as the edge weight, and using the shortest path algorithm to search for the data transmission path between the edge nodes to obtain the primary data transmission path;

[0085] Add Gaussian random perturbation values to the primary data transmission path and repeat the path search to obtain the secondary data transmission path.

[0086] After obtaining the real-time line topology structure change data of the distribution network system, construct a line topology relationship graph through the graph database, use the shortest path algorithm, with the edge nodes as the starting and ending points and the line communication quality parameter as the edge weight, search for the data transmission path between the nodes, and introduce an exploration mechanism during the shortest path search process to select the sub-optimal path.

[0087] Create a node data table to record the edge node identifiers and operating status information, and record the physical connection relationships between nodes to obtain a line topology relationship diagram; use the maximum-minimum normalization method to process the communication bandwidth parameters, transmission delay parameters, and packet loss rate parameters collected by the edge nodes, and calculate the link communication quality value according to the parameters processed by the normalization method according to the weight ratio; calculate the weight coefficient of the edge according to the link communication quality value, and execute Dijkstra's algorithm on the line topology relationship diagram through the weight coefficient to obtain the shortest transmission path; add Gaussian random perturbation values to the shortest transmission path and repeat the path search, and sort the set of sub-optimal paths according to the total path weight value, the number of node hops, and the path overlap degree value to obtain the edge node transmission channel allocation result.

[0088] Figure 4Schematic diagram for the processing of the configuration data of the distribution network system in an embodiment. Specifically, a graph database is used to record the change data of the distribution network line topology structure. A node data table is created in the database to record the edge node identifiers, operating status, and geographical location information. An edge data table is created to record the physical connection relationship between nodes, communication channel identifiers, and link status information. A unique index is established based on the node identifiers, and a line topology relationship graph is constructed through the edge data table. For each communication link in the line topology relationship graph, communication bandwidth parameters, transmission delay parameters, and packet loss rate parameters are collected from the edge nodes. The three types of parameters are normalized using the maximum-minimum normalization method, and a weighted calculation is performed according to the ratio of 4:3:3 to obtain the link communication quality value. The weight coefficient of the edge is calculated based on the link communication quality value. The weight coefficient is inversely proportional to the communication quality value. The smaller the weight coefficient is assigned to the link with the higher communication quality value. The Dijkstra algorithm is used to perform the shortest path search on the line topology relationship graph, and the shortest transmission path between pairwise edge nodes is calculated. During the shortest path search process, a perturbation value is added to the link weight coefficient through Gaussian random numbers. The mean value of the perturbation value is 0, and the standard deviation is 10% of the original weight coefficient. The shortest path search algorithm is repeatedly executed to obtain a set of sub-optimal paths. For each path in the set of sub-optimal paths, the sum of the weight coefficients of all links on the path is calculated as the total path weight value, the number of nodes passed by the path is counted as the node hop value, and the number of links shared by this path and other paths is calculated as the path overlap degree value. The weighted summation method is used to comprehensively calculate the total path weight value, node hop value, and path overlap degree value to obtain the path score. The set of sub-optimal paths is re-sorted according to the score value, and the main transmission channel and backup transmission channel are assigned to the edge nodes according to the sorting result. In the dynamic topology structure of the distribution network line, the graph database records the real-time state changes of the edge nodes and communication links. Taking the distribution network of a certain city as an example, the node data table in the graph database records the information of 126 edge nodes. Each node has a unique 16-bit identifier, and the operating status flag bit and geographical coordinate position of the node are recorded. The edge data table records 187 communication links between nodes, including the node identifiers at both ends of the link, fiber channel numbers, and link status flag bits. The topology relationship graph constructed in this way completely presents the structure of the distribution network. In the quality assessment of the communication link, the edge node collects communication parameters every 30 seconds. The collection results of a certain link show that the communication bandwidth is 1000 megabits per second, the transmission delay is 12 milliseconds, and the packet loss rate is 0.15%. These raw data are normalized, the bandwidth value is normalized to 0.95, the delay value is normalized to 0.88, and the loss rate is normalized to 0.92. The communication quality value of this link is calculated as 0.92 according to the weight ratio of 4:3:3. Based on the communication quality value, the link weight coefficient is calculated and converted using the reciprocal relationship. The link with a communication quality value of 0.92 obtains a weight coefficient of 1.09.During the shortest path search process, considering the volatility of the actual network environment, a random perturbation is added to the weight coefficient. Taking this link as an example, a Gaussian random number with a mean of 0 and a standard deviation of 0.109 is generated as the perturbation value. After multiple superpositions of the perturbation, 5 different sub-optimal paths are obtained, and these sub-optimal paths have different characteristic parameters. The total weight value of one path is 5.76, which needs to pass through 4 nodes and shares 2 links with other paths. The total weight value of another path is 6.12, passing through 5 nodes, but only sharing 1 link with other paths. Comprehensive scores are calculated for these characteristic parameters, and the weight ratios of the total weight value, the number of node hops, and the path overlap degree are set to 5:3:2. After weighted calculation, the comprehensive score of the first path is 7.83, and the comprehensive score of the second path is 7.56. According to the sorting result of the path scores, the path with the highest score is assigned as the main transmission channel, the second highest score path is used as the first backup channel, and the third highest score path is used as the second backup channel. This multi-path scheme not only ensures the optimality of data transmission but also provides alternative solutions when communication links fail. Practices in the real distribution network environment show that when the communication quality of the main transmission channel fluctuates, the backup channel can take over the data transmission task in a timely manner and maintain the stable operation of the network. This scheme based on the graph database and intelligent path planning realizes the dynamic optimization of the communication topology of the distribution network system.

[0089] In some embodiments of the present disclosure, the calculation process of the line loss calculation deviation percentage includes:

[0090] Obtain the real-time communication status data between edge nodes in the line topology structure, and the communication status data includes transmission delay data, bandwidth utilization data, and packet loss rate data;

[0091] Based on the communication status data, the data transmission path is graded to obtain a transmission path grade value, and the line loss data of the voltage grade corresponding to the data transmission path grade value is extracted from the preprocessed line loss data of different voltage grades;

[0092] Based on the line loss data of the voltage grade, the line loss calculation deviation percentage is calculated.

[0093] Use a communication monitoring device to obtain real-time communication status data between edge nodes, record the transmission delay data, bandwidth utilization data, and packet loss rate data between nodes, and use the maximum-minimum normalization method to standardize the collected data to obtain communication quality parameters. Classify the transmission paths according to the communication quality parameters, extract the line loss data of each voltage level corresponding to the path from the line loss preprocessing dataset, and use the random forest algorithm to calculate the adjusted line loss value of the transmission path. By comparing the original line loss data with the calculated line loss data, calculate the loss deviation percentage of each voltage level line, and the loss deviation percentage value is equal to (the calculated loss value minus the original loss value) divided by the original loss value. Use the double exponential smoothing algorithm to predict the trend of the loss deviation percentage, set the time series smoothing coefficient to 0.6 and the trend term smoothing coefficient to 0.4 to obtain the predicted deviation value. If the predicted deviation value exceeds the preset threshold, calculate the loss contribution degree of each voltage level line, and the loss contribution degree value is equal to the loss of the voltage level line divided by the total loss. Use the proportional integral algorithm to adjust the weight parameters in the collaborative analysis mechanism, and the adjustment amount is proportional to the loss contribution degree and inversely proportional to the original weight value, and update the weight coefficient of each voltage level data in the line loss calculation. During the operation of the distribution network, the communication quality between edge nodes directly affects the accuracy of line loss calculation. Taking a certain urban distribution network as an example, 87 edge nodes are set in this area, and the communication status data between nodes are collected every 30 seconds through a communication monitoring device. For a typical transmission path, the original collected data shows that the transmission delay is 25 milliseconds, the bandwidth utilization rate is 78%, and the packet loss rate is 0.3%. After processing with the maximum-minimum normalization method, the standardized transmission delay value is 0.85, the bandwidth utilization rate value is 0.78, and the loss rate value is 0.92. Based on the standardized communication quality parameters, the transmission path is divided into three levels: high quality, medium quality, and low quality. The comprehensive communication quality of this path is at the medium level, and the distribution lines involved include 2 35 kV buses and 4 10 kV outgoing lines. Extract the original loss data of these lines from the line loss preprocessing dataset. The loss rates of the 35 kV buses are 1.2% and 1.4%, and the loss rates of the 10 kV outgoing lines are 2.8%, 2.6%, 3.1%, and 2.9% respectively. After the path is adjusted, use the random forest algorithm to recalculate the line loss value. The calculation results show that the loss rates of the 35 kV buses become 1.3% and 1.5%, and the loss rates of the 10 kV outgoing lines become 3.0%, 2.7%, 3.3%, and 3.1% respectively. Through comparative analysis, the loss deviation percentages of the 35 kV buses are 8.3% and 7.1% respectively, and the loss deviation percentages of the 10 kV outgoing lines are 7.1%, 3.8%, 6.5%, and 6.9% respectively. Use the double exponential smoothing algorithm to predict the trend of these deviation data, and set the time series smoothing coefficient to 0.6 and the trend term smoothing coefficient to 0.4. The prediction results show that the loss deviation of the 35 kV bus will reach 9.2%, exceeding the preset 5% threshold.At this time, it is necessary to calculate the loss contribution degree of each voltage level line. The total loss of the 35 kV bus is 56 MWh, and the total loss of the 10 kV outgoing line is 122 MWh. Based on this, the loss contribution degree of the 35 kV voltage level is calculated to be 31.5%, and the loss contribution degree of the 10 kV voltage level is 68.5%. Based on the loss contribution degree data, the weight parameters in the collaborative analysis mechanism are adjusted using the proportional integral algorithm. The original weight coefficients of the 35 kV and 10 kV voltage levels are 0.4 and 0.6 respectively, and after adjustment, they become 0.35 and 0.65. The change in the weight coefficient reflects the importance of different voltage level lines in the overall line loss analysis. A higher weight value indicates that the line loss data of this voltage level occupies a larger proportion in the calculation. Through this dynamic weight adjustment mechanism, the accuracy of the line loss calculation result is improved.

[0094] In some embodiments of the present disclosure, the method further includes:

[0095] Obtain the operating status of the edge nodes in the line topology and the change trend of the line loss data. When the operating status of the edge nodes in the line topology and the change trend of the line loss data are abnormal, trigger the warning mechanism.

[0096] Obtain the processor occupancy rate, memory usage rate, bandwidth utilization rate, and processing delay parameters of the edge nodes, and record the node status data sequence according to the monitoring period; establish a prediction model using the long short-term memory neural network algorithm based on the node status data sequence, and obtain the node status parameters in the future monitoring period through the prediction model; use the sliding window method to calculate the node status parameters to obtain the loss data change sequence, and calculate the fluctuation amplitude, fluctuation frequency, and fluctuation duration according to the loss data change sequence; establish a transmission parameter state equation using the Kalman filter algorithm for the fluctuation amplitude, fluctuation frequency, and fluctuation duration, identify the state parameters of abnormal fluctuations through the transmission parameter state equation, and trigger a parameter adjustment instruction according to the deviation percentage between the state parameters and the steady-state parameter reference value.

[0097] Specifically, the monitoring device collects the processor occupancy rate, memory usage rate, communication bandwidth utilization rate, and data processing delay parameters of the edge nodes, records the node operation status data according to the monitoring period, and establishes a node status data sequence. The long short-term memory neural network algorithm is used to establish a prediction model for the node status data sequence. The input features include the processor occupancy rate, memory usage rate, bandwidth utilization rate, and processing delay, and the output prediction value includes the node status parameters within the future monitoring period. For the loss data of each line, the monitoring time window width is set to 24 hours, and the sliding window method is used to calculate the changes in line loss rate, line loss power, and line loss electricity, obtaining a loss data change sequence. According to the loss data change sequence, the fluctuation amplitude, fluctuation frequency, and fluctuation duration are calculated, and the loss data is subjected to anomaly detection according to the preset fluctuation criterion. An anomaly flag is triggered when the fluctuation amplitude exceeds 20% or the fluctuation frequency exceeds the preset value. The Kalman filter algorithm is used to establish a state equation for the transmission parameters. The state variables include the transmission channel parameters, routing configuration parameters, and communication delay parameters. The state parameters causing abnormal fluctuations are identified through filtering calculations. The steady-state operation records are extracted from the parameter monitoring database to establish the steady-state parameter reference values. The warning levels are divided according to the deviation percentage between the abnormal state parameters and the reference values, and corresponding-level parameter adjustment instructions are triggered. During the operation monitoring of the distribution network, the status monitoring of the edge nodes is closely related to the analysis of line loss data. Taking the edge node A of a certain urban distribution network as an example, the monitoring device records a set of status data every 5 minutes: the processor occupancy rate is 62%, the memory usage rate is 58%, the communication bandwidth utilization rate is 75%, and the data processing delay is 180 milliseconds. These status parameters constitute a continuous data sequence, reflecting the changes in the operation status of the node. When using the long short-term memory neural network to predict the node status, the status data sequence of the past 4 hours is used as the training sample. Through the learning of parameters such as the processor occupancy rate and memory usage rate, the prediction model shows that the processor occupancy rate of the node will rise to 85% within the next 2 hours, and this trend indicates a significant increase in the computing load. In terms of line loss data monitoring, a 24-hour sliding time window is set to record the changes in the line loss of the 10 kV distribution line. The monitoring data shows that the line loss rate of this line gradually rises from 2.8% at 4 am to 4.2% at 2 pm, the line loss power increases from 65 kW to 98 kW, and the cumulative line loss electricity increases by 792 kWh. The change trend of the loss data is obtained through the sliding window calculation. According to the preset fluctuation criterion, a line loss rate increase exceeding 20% within 1 hour is marked as an abnormal fluctuation. The line loss rate of this line increased by 25% during the period from 1 pm to 2 pm, triggering the anomaly detection mechanism. At the same time, the fluctuation frequency of the line loss power exceeds 6 times per hour, which also conforms to the characteristics of abnormal fluctuations. For in-depth analysis of the abnormal fluctuations, the Kalman filter algorithm is used to establish a state equation, with the transmission channel bandwidth set to 200 megabits per second, the routing hop count set to 3 hops, and the communication delay set to 150 milliseconds as the initial state.Through filtering calculations, it is found that the fluctuations of the communication delay parameters are the most significant and have deviated from the normal range. Query the steady-state operation records of this line in the past 30 days from the parameter monitoring database, and statistically obtain the steady-state parameter reference values: the communication delay reference value is 100 milliseconds, and the current communication delay exceeds the reference value by 50%, reaching the secondary warning standard. Based on the warning level, a communication parameter adjustment instruction is automatically triggered to increase the priority of the data packet, and the communication delay is reduced to 120 milliseconds. This multi-level monitoring and warning mechanism realizes the real-time monitoring and rapid response of the operation status of the distribution network. Through the multi-dimensional coordination of the monitoring and warning mechanism, not only the computing resource usage of the edge nodes is monitored, but also the change trend of the line loss data is tracked in real time. The anomaly detections in the two dimensions confirm each other and jointly construct an accurate and reliable warning system. When node load anomalies and line loss data anomalies occur simultaneously, the system can quickly locate the source of the problem and timely adjust the operation parameters to ensure the stable operation of the distribution network.

[0098] In some embodiments of the present disclosure, the method further includes:

[0099] Obtain the line topology data in the historical operation database;

[0100] Based on the line topology data, establish a long short-term memory neural network prediction model, and obtain the line topology structure change probability based on the long short-term memory neural network prediction model;

[0101] Based on the depth-first search algorithm, traverse the area where the line topology structure change probability is greater than a preset threshold, and obtain the physical distance, communication bandwidth, and transmission delay parameters between edge nodes;

[0102] Based on the physical distance, communication bandwidth, and transmission delay parameters between the edge nodes, obtain the main transmission path, the standby transmission path, and the emergency transmission path.

[0103] Obtain the topology change records in the historical operation database, where the topology change records include the switch state sequence, the load transfer value, and the timestamp sequence; establish a long short-term memory neural network prediction model according to the topology change records, and obtain the topology structure change probability through the prediction model; use the depth-first search algorithm to traverse the area where the topology structure change probability is greater than a preset threshold, and obtain the physical distance, communication bandwidth, and transmission delay parameters between transmission nodes; calculate the path score value for the parameters between transmission nodes, divide the main transmission path, the standby transmission path, and the emergency transmission path according to the path score value, and allocate bandwidth resources to the main transmission path, the standby transmission path, and the emergency transmission path according to a preset ratio.

[0104] Specifically, extract the line topology change records from the historical operation database, record the switch switching time, the states before and after switching, the identification of the tie line, and the load transfer value. Standardize the topology change data through the numerical normalization method to obtain the training dataset. Use the long short-term memory neural network algorithm to establish a prediction model for the training dataset. The input features include the switch state sequence, the load change sequence, and the timestamp sequence, and the output result includes the probability of the topology structure change at future moments. Mark the high-probability change areas according to the probability of the topology structure change. Use the depth-first search algorithm to traverse the transmission nodes and record the physical distance, communication bandwidth, and transmission delay between the nodes. Score the traversed transmission paths. The scoring parameters include the path length, bandwidth capacity, and delay magnitude. Divide the transmission paths into the main transmission path, the backup transmission path, and the emergency transmission path according to the scoring results. Set the bandwidth allocation ratio for the main transmission path to 70%, the backup transmission path to 20%, and the emergency transmission path to 10%, and establish a transmission path bandwidth allocation table. Establish routing forwarding rules according to the bandwidth allocation table, including path priority, packet identification, and forwarding time window, and issue the routing rules to the transmission nodes to complete path pre-configuration. During the operation of the distribution network, the prediction of the change of the line topology structure is crucial for maintaining the accuracy of line loss calculation. Taking the distribution network of a certain city as an example, the historical operation database records the topology change data of the past 6 months. The record of a 10 kV feeder shows that the switch switching time is 8:30 every day, the state before switching is the sectional switch closed, the state after switching is the sectional switch open, the identification of the tie line is L1025, and the load transfer value is 2000 kW. After normalization processing of these original data, a standardized training dataset is formed. When using the long short-term memory neural network to process these training data, the switch state sequence, load change sequence, and timestamp sequence including 180 days are input. Through model training, the prediction shows that the probability of the topology structure change of this feeder during the period from 8:30 to 9:00 in the morning on weekdays is 85%. Such a high-probability event is marked as the key attention object. Conduct a depth-first search for the marked area and find that there are communication connections between this feeder and 3 adjacent transmission nodes. The physical distances between the nodes are 1.2 km, 1.5 km, and 1.8 km respectively, the communication bandwidths are 1000 Mbps, 800 Mbps, and 600 Mbps respectively, and the transmission delays are 12 ms, 15 ms, and 18 ms respectively. Conduct a comprehensive scoring of these transmission paths, where the weight of the path length is 0.3, the weight of the bandwidth capacity is 0.4, and the weight of the delay magnitude is 0.3. The path with a length of 1.2 km has the highest score and is set as the main transmission path, the path with a length of 1.5 km is used as the backup transmission path, and the path with a length of 1.8 km is used as the emergency transmission path.In terms of bandwidth allocation, the main transmission path is allocated a bandwidth of 700 megabits per second, accounting for 70% of the total bandwidth. The backup transmission path is allocated 200 megabits per second, and the emergency transmission path is allocated 100 megabits per second. This hierarchical bandwidth allocation strategy ensures the reliability of data transmission. In the finally established routing forwarding rules, the priority of the main transmission path is set to 1, the data packet identifier is 0x01, and the forwarding time window is 0 - 10 milliseconds. The priority of the backup path is 2, the data packet identifier is 0x02, and the forwarding time window is 10 - 20 milliseconds. The priority of the emergency path is 3, the data packet identifier is 0x03, and the forwarding time window is 20 - 30 milliseconds. This multi-level routing pre-configuration mechanism can quickly switch the transmission path when the topology changes, ensuring the real-time calculation of line loss data. Through prediction and pre-configuration driven by historical data, the adaptability of the distribution network in the face of topology changes is greatly improved.

[0105] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0106] Based on the same inventive concept, the embodiments of the present disclosure also provide a processing device for the configuration data of a distribution network system for implementing the processing method of the configuration data of the distribution network system involved above. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in the embodiments of the processing device for the configuration data of the distribution network system provided below can refer to the limitations on the processing method of the configuration data of the distribution network system in the above text, and will not be elaborated here.

[0107] The device may include a system (including a distributed system), software (application), module, component, server, client, etc. that uses the method described in the embodiments of this specification, and combines the necessary implementation hardware. Based on the same innovative concept, the devices in one or more embodiments provided by the embodiments of the present disclosure are as described in the following embodiments. Since the implementation solutions of the device to solve problems are similar to those of the method, the implementation of the specific device in the embodiments of this specification may refer to the implementation of the foregoing method, and the repeated parts will not be elaborated. As used hereinafter, the term "unit" or "module" may be a combination of software and / or hardware that can implement a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0108] In one embodiment, as Figure 5 shown, a processing device 500 for configuration data of a power distribution network system is provided. The device may be the aforementioned server, or a module, component, device, unit, etc. integrated in the server. The device 500 may include:

[0109] An acquisition module 502, configured to acquire preprocessed line loss data of different voltage levels in the power distribution network system;

[0110] A selection module 504, configured to acquire a real-time line topology structure, and based on the changed line topology structure, determine an updated data transmission path in the case of a change in the line topology structure;

[0111] A calculation module 506, configured to determine a line loss calculation deviation percentage based on the updated data transmission path and the preprocessed line loss data, and in the case where the line loss calculation deviation percentage exceeds a preset threshold, adjust the weight parameter of the preprocessed line loss data of different voltage levels based on the line loss calculation deviation percentage;

[0112] A configuration module 508, configured to calculate the configuration data of multiple lines based on the target data transmission path for the preprocessed line loss data of different voltage levels, and perform weighted summation on the configuration data of multiple lines based on the weight parameters of the preprocessed line loss data of different voltage levels to obtain the configuration data of the power distribution network system.

[0113] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0114] Each module in the above-mentioned processing device for the configuration data of the distribution network system can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0115] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store configuration data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for processing the configuration data of a distribution network system.

[0116] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for processing the configuration data of a distribution network system. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0117] Those skilled in the art can understand that Figure 6 、 Figure 7The structure shown is only a block diagram of some structures related to the present disclosure solution, and does not constitute a limitation on the computer device to which the present disclosure solution is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0118] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0119] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0120] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided by the present disclosure can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided by the present disclosure can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided by the present disclosure can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0121] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0122] The above-described embodiments merely represent several implementation manners of the present disclosure. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present disclosure. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present disclosure, several modifications and improvements can still be made, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the appended claims.

Claims

1. A method for processing configuration data of a distribution network system, characterized in that, The method includes: Obtaining pre - processed data of line losses for different voltage levels in the distribution network system; Obtaining the real - time line topology structure, and when the line topology structure changes, determining the updated data transmission path based on the changed line topology structure; Based on the updated data transmission path and the pre - processed data of line losses, determining the percentage deviation of line loss calculation. When the percentage deviation of line loss calculation exceeds the preset threshold, adjusting the weight parameters of the pre - processed data of line losses for different voltage levels based on the percentage deviation of line loss calculation; Calculating the configuration data of multiple lines based on the target data transmission path for the pre - processed data of line losses for different voltage levels, and performing weighted summation on the configuration data of multiple lines based on the weight parameters of the pre - processed data of line losses for different voltage levels to obtain the configuration data of the distribution network system.

2. The method according to claim 1, wherein The process of obtaining the pre - processed data of line losses includes: Obtaining the operation data of the distribution network system; Based on the operation data of the distribution network system, extracting the physical connection relationship between line nodes from the line topology structure to obtain line node correlation data; Based on a pre - designed calculation model, the operation data of the distribution network system, and the line node correlation data, obtaining a loss prediction quantization index; Based on a clustering algorithm and the loss prediction quantization index, classifying the original line loss data of different voltage levels in the distribution network system to obtain the classified original line loss data of different voltage levels; Calculating the pre - processed data of line losses for different voltage levels based on preset rules for the classified original line loss data of different voltage levels.

3. The method according to claim 1, characterized in that The process of updating the data transmission path includes: Obtaining communication bandwidth measurement data from the edge nodes of the line topology structure, and calculating communication delay parameters according to the physical distance between line nodes; Based on the communication bandwidth measurement data and the communication delay parameters, obtaining a data transmission path quality index; When the data transmission path quality index is less than the preset quality index, recalculating the data transmission path based on the ant colony algorithm to obtain data transmission paths with different priorities; Updating the data transmission path based on the priority order of the data transmission paths.

4. The method according to claim 3, characterized in that, The process of updating the data transmission path further includes: Obtaining the changed line topology data, and constructing a new line topology structure based on the changed line topology data; Using the edge nodes in the new line topology structure as the starting and ending points, taking the line communication quality parameter as the edge weight, and using the shortest path algorithm to search for the data transmission path between edge nodes to obtain the primary data transmission path; Adding Gaussian random perturbation values to the primary data transmission path and repeating the path search to obtain the secondary data transmission path.

5. The method according to claim 1, wherein The calculation process of the percentage deviation of line loss calculation includes: Obtaining the real - time communication status data between edge nodes in the line topology structure, where the communication status data includes transmission delay data, bandwidth utilization data, and packet loss rate data; Hierarchize the data transmission path based on the communication status data to obtain a transmission path level value, and extract the line loss data of the voltage level corresponding to the data transmission path level value from the preprocessed line loss data of different voltage levels; Calculate the percentage deviation of line loss calculation based on the line loss data of the voltage level.

6. The method according to claim 1, wherein The method further includes: Obtain the operating status of the edge nodes in the line topology structure and the change trend of the line loss data. When the operating status of the edge nodes in the line topology structure and the change trend of the line loss data are abnormal, trigger an early warning mechanism.

7. The method according to claim 1, wherein The method further includes: Obtain the line topology data in the historical operation database; Establish a long short-term memory neural network prediction model based on the line topology data, and obtain the probability of line topology structure change based on the long short-term memory neural network prediction model; Traverse the area where the probability of line topology structure change is greater than a preset threshold based on the depth-first search algorithm, and obtain the physical distance, communication bandwidth, and transmission delay parameters between the edge nodes; Based on the physical distance, communication bandwidth, and transmission delay parameters between the edge nodes, obtain the main transmission path, backup transmission path, and emergency transmission path.

8. A processing device for configuration data of a distribution network system, characterized in that, The device includes: An acquisition module, configured to acquire the preprocessed line loss data of different voltage levels in the distribution network system; A selection module, configured to acquire the real-time line topology structure, and based on the changed line topology structure, determine the updated data transmission path; A calculation module, configured to determine the percentage deviation of line loss calculation based on the updated data transmission path and the preprocessed line loss data. When the percentage deviation of line loss calculation exceeds a preset threshold, adjust the weight parameters of the preprocessed line loss data of different voltage levels based on the percentage deviation of line loss calculation; A configuration module, configured to calculate the preprocessed line loss data of different voltage levels based on the target data transmission path to obtain the configuration data of multiple lines, and perform weighted summation on the configuration data of multiple lines based on the weight parameters of the preprocessed line loss data of different voltage levels to obtain the configuration data of the distribution network system.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images