A method and device for analyzing an operation state of a power distribution network and an online monitoring system

Abstract

The application provides a kind of power distribution network operating state analysis method, device and online monitoring system.The application in the access scene of high penetration rate distributed power supply, through entity mechanism model and digital twin model mutual cooperation, both ensure the accuracy of detection through entity mechanism model, and ensure the detection efficiency of detection through digital twin model, solve the problem of low detection efficiency and low accuracy of power distribution network operating state detection in the access scene of high penetration rate distributed power supply, can simultaneously take into account the detection efficiency and accuracy of power distribution network operating state detection.The application comprehensively analyzes the historical data of multiple nodes, establishes training samples, and the digital twin model trained adapts to the high complexity in the access scene of high penetration rate distributed power supply, improves the detection accuracy of power distribution network operating state under this condition.

Description

Technical Field

[0001] This invention relates to the field of power distribution network technology, and in particular to a method, apparatus, and online monitoring system for analyzing the operating status of power distribution networks. Background Technology

[0002] With the rapid growth of urban power distribution network load and the increasing demands for power reliability, the load scale is gradually increasing, and the distribution network topology is becoming increasingly complex. Furthermore, with the high penetration rate of distributed energy access and the application of large-scale distributed power sources, the operational complexity of the distribution network has greatly increased. For such a complex distribution network, a systemic failure can have severe consequences, even triggering electrical accidents and causing significant losses to society. Power outages in the distribution network are unavoidable; weather-related outages and tree-related faults cause power outages and affect the network's reliability indicators. However, many outages are caused by recurring defects or the gradual failure of equipment, which may have existed for weeks or months before the eventual outage. Therefore, traditional distribution network fault diagnosis techniques are no longer adequate for the safe, economical, and reliable operation requirements of active distribution networks.

[0003] Currently, in distribution network status monitoring, the operating data of the distribution network can be simulated based on the principles of energy balance and basic circuit principles to obtain the operating status of the distribution network. However, due to the high penetration rate of distributed power sources, the distribution network is highly complex. Using this method to detect the operating status of the distribution network is time-consuming, cannot achieve real-time monitoring of the distribution network, and has low detection efficiency.

[0004] In addition, in the state detection of distribution networks, fault data can be used to construct fault samples, train neural networks, and predict the operating state of the distribution network based on the prediction model obtained from the training. However, this method only considers the relationship between fault data and operating state, without considering the principle of energy balance and the basic principle of circuits, which may lead to inaccurate predictions of the operating state of the distribution network based on the prediction model.

[0005] Therefore, in scenarios where distributed power sources have high penetration rates, it is urgent to address how to simultaneously ensure the real-time performance and accuracy of power distribution network operation status monitoring. Summary of the Invention

[0006] This invention provides a method, device, and online monitoring system for analyzing the operating status of a distribution network. It can solve the problems of low efficiency and low accuracy in detecting the operating status of the distribution network in scenarios with high penetration of distributed power sources, and can simultaneously take into account both the detection efficiency and accuracy of the operating status detection of the distribution network.

[0007] In a first aspect, the present invention provides a method for analyzing the operating status of a distribution network, comprising: acquiring historical data of each line and node in the distribution network; the historical data including voltage data, current data, frequency data, and phase data; constructing a physical mechanism model based on basic circuit principles, and performing steady-state and transient analyses on the historical data of each line and node based on the physical mechanism model to obtain the operating status of the distribution network and the historical data corresponding to each operating status; the operating status includes normal state, fault state, early warning state, and recovery state; constructing training samples based on the operating status of the distribution network and the historical data corresponding to each operating status; and training a neural network based on the training samples to obtain a digital twin model; and analyzing the real-time data of each line and node in the distribution network based on the digital twin model to obtain the real-time operating status of each line and node in the distribution network, thereby realizing the state monitoring of the distribution network.

[0008] In one possible implementation, a physical mechanism model is constructed based on the basic principles of circuitry, including: determining the steady-state and transient analysis equations for each line and node; determining the stability and transient analysis results for each line and node, and their value ranges under each operating state; and determining the physical mechanism model based on the steady-state and transient analysis equations for each line and node, and the value ranges of the stability and transient analysis results under each operating state.

[0009] In one possible implementation, steady-state and transient analyses are performed on historical data of each line and node based on a physical mechanism model to obtain the operating status of the distribution network and the historical data corresponding to each operating status. This includes: inputting the historical data of each line and node into the physical mechanism model to obtain the operating status of each line and node at each time; splitting the historical data of each line and node based on the operating status of each line and node at each time; and determining the operating status of the distribution network and the historical data corresponding to each operating status based on the operating status of each line and node at each time and the split historical data of each line and node.

[0010] In one possible implementation, training samples are constructed based on the operating status of the distribution network and the historical data corresponding to each operating status. This includes: for any line or node, determining a first training sample by taking the historical data of the line or node at any time as input and the operating status at that time as output; determining a second training sample by taking the historical data of the line or node for a predetermined period prior to any time as input and the operating status at that time as output; determining a third training sample for any line or node at any time by taking the historical data of the line or node and its adjacent nodes at that time as input and the operating status at that time as output; wherein, the adjacent nodes of the line or node are one or more nodes adjacent to the line or node; and determining training samples based on the first, second, and third training samples.

[0011] In one possible implementation, a digital twin model is obtained by training a neural network based on training samples, including: determining the business scenarios of each line and each node; wherein the mapping relationship between historical data and operating status of lines or nodes corresponding to the same business scenario is the same; dividing the training samples based on the business scenarios of each line and each node to obtain training samples corresponding to each business scenario; for any business scenario, training a new neural network model based on the training samples corresponding to that business scenario to obtain a digital twin sub-model; and determining the digital twin model based on the digital twin sub-models corresponding to each business scenario.

[0012] In one possible implementation, real-time data of each line and node in the distribution network is analyzed based on a digital twin model to obtain the real-time operating status of each line and node in the distribution network, thereby realizing the status monitoring of the distribution network. This includes: determining the business scenario corresponding to each line or node; for any line or node, inputting the real-time data of the line or node into the digital twin sub-model corresponding to the business scenario of the line or node to obtain the real-time operating status of the line or node.

[0013] In one possible implementation, the method further includes: analyzing real-time data of each line and node in the distribution network based on the physical mechanism model to obtain the actual operating status of each line and node in the distribution network; comparing whether the actual operating status and the real-time operating status are consistent; if they are inconsistent, recording the moment when the actual operating status and the real-time operating status are inconsistent as the target moment, and recording the line or node whose actual operating status and the real-time operating status are inconsistent as the target line or target node; updating the digital twin model based on the real-time data of the target line or target node at the target moment, and the actual operating status of the target line or target node at the target moment; and monitoring the status of each line and node in the distribution network based on the updated digital twin model.

[0014] In one possible implementation, the digital twin model is updated based on real-time data of the target line or target node at the target time, as well as the actual operating status of the target line or target node at the target time. This includes: constructing retraining samples based on the real-time data of the target line or target node at the target time, as well as the actual operating status of the target line or target node at the target time; determining the business scenario corresponding to the target line or target node; determining the digital twin sub-model corresponding to the business scenario in the digital twin model based on the business scenario corresponding to the target line or target node; and retraining the digital twin sub-model corresponding to the business scenario in the digital twin model based on the retraining samples, updating the model parameters of the digital twin sub-model, and obtaining the updated digital twin model.

[0015] Secondly, embodiments of the present invention provide an analysis device for the operating status of a distribution network, comprising: a communication module for acquiring historical data of each line and node in the distribution network; the historical data includes voltage data, current data, frequency data, and phase data; a processing module for constructing a physical mechanism model based on basic circuit principles, and performing steady-state and transient analysis on the historical data of each line and node based on the physical mechanism model to obtain the operating status of the distribution network and the historical data corresponding to each operating status; the operating status includes normal state, fault state, early warning state, and recovery state; constructing training samples based on the operating status of the distribution network and the historical data corresponding to each operating status; and training a neural network based on the training samples to obtain a digital twin model; and analyzing the real-time data of each line and node in the distribution network based on the digital twin model to obtain the real-time operating status of each line and node in the distribution network, thereby realizing the status monitoring of the distribution network.

[0016] In one possible implementation, the processing module is specifically used to determine the steady-state analysis equations and transient analysis equations for each line and each node; determine the range of values ​​for the stability analysis results and transient analysis results for each line and each node under each operating state; and determine the entity mechanism model based on the steady-state analysis equations and transient analysis equations for each line and each node, as well as the range of values ​​for the stability analysis results and transient analysis results under each operating state.

[0017] In one possible implementation, the processing module is specifically used to input the historical data of each line and each node into the entity mechanism model to obtain the operating status of each line and each node at each time; based on the operating status of each line and each node at each time, the historical data of each line and each node is split; based on the operating status of each line and each node at each time, and the split historical data of each line and each node, the operating status of the distribution network and the historical data corresponding to each operating status are determined.

[0018] In one possible implementation, the processing module is specifically configured to, for any line or node, determine a first training sample by taking the historical data of the line or node at any given time as input and its operating state at that time as output; determine a second training sample by taking the historical data of the line or node for a predetermined period prior to any given time as input and its operating state at that time as output; and determine a third training sample for any line or node at any given time by taking the historical data of the line or node and its neighboring nodes at that time as input and its operating state at that time as output; wherein the neighboring nodes of the line or node are one or more nodes adjacent to the line or node; and determine training samples based on the first training sample, the second training sample, and the third training sample.

[0019] In one possible implementation, the processing module is specifically used to determine the business scenarios of each line and each node; wherein the mapping relationship between the historical data and the operating status of the lines or nodes corresponding to the same business scenarios is the same; based on the business scenarios of each line and each node, the training samples are divided to obtain the training samples corresponding to each business scenario; for any business scenario, a new neural network model is trained based on the training samples corresponding to that business scenario to obtain a digital twin sub-model; based on the digital twin sub-models corresponding to each business scenario, the digital twin model is determined.

[0020] In one possible implementation, the processing module is specifically used to determine the business scenario corresponding to each line or node; for any line or node, the real-time data of the line or node is input into the digital twin sub-model corresponding to the business scenario of the line or node to obtain the real-time operating status of the line or node.

[0021] In one possible implementation, the processing module is further configured to: analyze real-time data of each line and node in the distribution network based on the entity mechanism model to obtain the actual operating status of each line and node in the distribution network; compare whether the actual operating status and the real-time operating status are consistent; if they are inconsistent, record the time when the actual operating status and the real-time operating status are inconsistent as the target time, and record the line or node whose actual operating status and the real-time operating status are inconsistent as the target line or target node; update the digital twin model based on the real-time data of the target line or target node at the target time, and the actual operating status of the target line or target node at the target time; and perform status monitoring of each line and node in the distribution network based on the updated digital twin model.

[0022] In one possible implementation, the processing module is specifically used to construct retraining samples based on real-time data of the target line or target node at the target time and the actual operating status of the target line or target node at the target time; determine the business scenario corresponding to the target line or target node; determine the digital twin sub-model corresponding to the business scenario in the digital twin model based on the business scenario corresponding to the target line or target node; and retrain the digital twin sub-model corresponding to the business scenario in the digital twin model based on the retraining samples, update the model parameters of the digital twin sub-model, and obtain the updated digital twin model.

[0023] Thirdly, embodiments of the present invention provide an online monitoring system for a power system. The online monitoring system includes an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to perform the steps of the method as described in the first aspect and any possible implementation thereof.

[0024] Fourthly, embodiments of the present invention provide a power system including an online monitoring system as described in the third aspect above, which performs the steps of the method as described in the first aspect and any possible implementation thereof, to realize online status monitoring of each line or node in the distribution network.

[0025] Fifthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the method as described in the first aspect and any possible implementation thereof.

[0026] This invention provides a method / device and online monitoring system for analyzing the operating status of a distribution network. The invention establishes a physical mechanism model based on basic circuit principles to analyze historical data of the distribution network, obtaining the network's operating status and corresponding historical data. Then, training samples are built to train a neural network, resulting in a digital twin model. Based on this trained digital twin model, real-time status monitoring of the distribution network is performed, achieving real-time status monitoring of the distribution network. On one hand, this invention uses a physical mechanism model to identify the status of historical data and construct training samples, ensuring the accuracy of the training samples and thus guaranteeing the accuracy of the digital twin model's predictions. On the other hand, this invention directly performs status detection through the digital twin model, reducing model complexity, decreasing detection time, and improving status detection efficiency. This invention solves the problems of low efficiency and low accuracy in distribution network operating status detection in scenarios with high penetration of distributed power sources, simultaneously achieving both efficiency and accuracy in distribution network operating status detection. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating a method for analyzing the operating status of a power distribution network according to an embodiment of the present invention.

[0029] Figure 2 This is a flowchart illustrating another method for analyzing the operating status of a power distribution network provided in an embodiment of the present invention.

[0030] Figure 3 This is a schematic diagram of the structure of a power distribution network operation status analysis device provided in an embodiment of the present invention;

[0031] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0032] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0033] In the description of this invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" and "more than one" refer to two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0034] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0035] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or device.

[0036] To make the objectives, technical solutions, and advantages of the present invention clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0037] Figure 1 This is a flowchart illustrating a method for analyzing the operating status of a power distribution network according to an embodiment of the present invention. The method is executed by an analysis device. The method includes steps S101-S105.

[0038] S101. Obtain historical data for each line and node in the distribution network.

[0039] In this embodiment of the application, historical data includes voltage data, current data, frequency data, and phase data.

[0040] S102. Construct a physical mechanism model based on the basic principles of circuits, and perform steady-state and transient analyses on the historical data of each line and node based on the physical mechanism model to obtain the operating status of the distribution network and the historical data corresponding to each operating status.

[0041] It should be noted that this invention is aimed at the scenario of high-penetration distributed power source access to medium and low voltage distribution networks. Considering the strong uncertainty and strong randomness of distributed power sources, based on the energy balance mechanism and basic circuit principles, a physical mechanism model of the distribution network under the scenario of large-scale distributed power source access is established, and the operating mechanism of the distribution network under different operating states is analyzed.

[0042] In this embodiment of the application, the operating states include normal state, fault state, warning state, and recovery state.

[0043] As one possible implementation, the analysis device can construct a physical mechanism model based on steps S1021-S1023.

[0044] S1021. Determine the steady-state and transient analysis equations for each line and each node.

[0045] S1022. Determine the stability analysis results and transient analysis results of each line and each node, and the range of values ​​under each operating state.

[0046] S1023. Based on the steady-state and transient analysis equations of each line and node, and the range of values ​​of the steady-state and transient analysis results under each operating state, determine the entity mechanism model.

[0047] As one possible implementation, the analysis device can obtain the operating status of the power distribution network and the historical data corresponding to each operating status based on steps S1024-S1026.

[0048] S1024. Input the historical data of each line and each node into the entity mechanism model to obtain the operating status of each line and each node at each time.

[0049] S1025. Based on the operating status of each line and each node at each time, split the historical data of each line and each node.

[0050] S1026. Based on the operating status of each line and node at each time, and the historical data of each line and node after splitting, determine the operating status of the distribution network and the historical data corresponding to each operating status.

[0051] S103. Based on the operating status of the distribution network and the historical data corresponding to each operating status, construct training samples; and train the neural network based on the training samples to obtain a digital twin model.

[0052] It should be noted that this invention takes into account the current situation where distributed power sources in medium and low voltage distribution networks are not fully measurable and controllable, and performs online processing on the data in the active distribution network data space; establishes a dynamic matching relationship between the data model and the mechanism model of the active distribution network data space, and studies a method for accurately mapping the dynamic change mechanism model and the online data model of the active distribution network.

[0053] It should be noted that this invention compares new data obtained from online knowledge discovery in distribution networks under scenarios with high proportion of distributed power sources with historical data, and performs online dynamic interaction between the two. Based on online learning and other methods, new expert knowledge and rules are generated; the expert experience knowledge and refined rule base are updated; and the mapping relationship between the new rules and the physical space, data space and virtual space models are established respectively.

[0054] As one possible implementation, the analysis device can construct training samples based on steps S1031-S1034.

[0055] S1031. For any line or node, take the historical data of the line or node at any time as input and the operating status at that time as output to determine the first training sample.

[0056] S1032. Using the historical data of the line or node for a set period of time before any given moment as input and the operating status at that moment as output, determine the second training sample.

[0057] S1033. For any line or node at any time, take the historical data of the line or node and its neighboring nodes at that time as input and the operating status of the line or node at that time as output to determine the third training sample.

[0058] The adjacent nodes of the line or node are one or more nodes that are adjacent to the line or node.

[0059] S1034. Based on the first training sample, the second training sample, and the third training sample, determine the training sample.

[0060] In this way, in scenarios with a high proportion of distributed power access, the present invention can establish samples of historical data and operating status of a single node, as well as samples of historical data and operating status of multiple nodes. Thus, during the training of the digital twin model, it can mine the digital features and relationships between the data and status of a single node, as well as the digital features and relationships between the data and status of multiple nodes. This adapts to the high complexity of scenarios with a high proportion of distributed power access and improves the accuracy of digital twin model detection.

[0061] As one possible implementation, the analysis device can train a digital twin model based on steps S1035-S1038.

[0062] S1035. Determine the business scenarios for each line and each node.

[0063] Among them, the mapping relationship between the historical data and the operating status of the lines or nodes corresponding to the same business scenarios is the same;

[0064] S1036. Based on the business scenarios of each line and each node, the training samples are divided to obtain the training samples corresponding to each business scenario.

[0065] S1037. For any business scenario, based on the training samples corresponding to that business scenario, train the new neural network model to obtain a digital twin model.

[0066] S1038. Based on the digital twin sub-models corresponding to each business scenario, determine the digital twin model.

[0067] In this way, the present invention can train each sub-model based on each business scenario, and each scenario can make predictions independently, thereby improving the model accuracy and prediction accuracy.

[0068] S104. Based on the digital twin model, analyze the real-time data of each line and node in the distribution network to obtain the real-time operating status of each line and node in the distribution network, and realize the status monitoring of the distribution network.

[0069] As one possible implementation, the analysis device can obtain the real-time operating status of each line and node in the power distribution network based on steps S1041-S1042.

[0070] S1041. Determine the business scenarios corresponding to each line or node.

[0071] S1042. For any line or node, input the real-time data of the line or node into the digital twin sub-model corresponding to the business scenario of the line or node to obtain the real-time operating status of the line or node.

[0072] This invention provides a method for analyzing the operating status of a distribution network. It establishes a physical mechanism model based on fundamental circuit principles to analyze historical data of the distribution network, obtaining the network's operating status and corresponding historical data. Then, it builds training samples to train a neural network, generating a digital twin model. Based on this trained digital twin model, it performs real-time status monitoring of the distribution network, achieving true state monitoring. On one hand, this invention uses a physical mechanism model to identify the state of historical data and construct training samples, ensuring the accuracy of the training samples and thus guaranteeing the accuracy of the digital twin model's predictions. On the other hand, this invention directly performs state detection through the digital twin model, reducing model complexity, decreasing detection time, and improving state detection efficiency. This invention solves the problems of low efficiency and low accuracy in distribution network operating status detection in scenarios with high penetration of distributed power sources, simultaneously achieving both efficiency and accuracy in distribution network operating status detection.

[0073] Optional, such as Figure 2 As shown, the method for analyzing the operating status of a power distribution network provided in this embodiment of the invention further includes steps S201-S205 after step S104.

[0074] S201. Based on the physical mechanism model, analyze the real-time data of each line and node in the distribution network to obtain the actual operating status of each line and node in the distribution network.

[0075] S202. Compare whether the actual operating status and the real-time operating status are consistent.

[0076] S203. If they are inconsistent, the time when the actual operating status and the real-time operating status are inconsistent shall be recorded as the target time, and the line or node whose actual operating status and the real-time operating status are inconsistent shall be recorded as the target line or target node.

[0077] S204. Update the digital twin model based on the real-time data of the target line or target node at the target time, and the actual operating status of the target line or target node at the target time.

[0078] As one possible implementation, the analysis device can update the digital twin model based on steps S2041-S2044.

[0079] S2041. Based on the real-time data of the target line or target node at the target time, and the actual operating status of the target line or target node at the target time, a retraining sample is formed.

[0080] S2042. Determine the business scenario corresponding to the target line or target node.

[0081] S2043. Based on the business scenario corresponding to the target line or target node, determine the digital twin sub-model in the digital twin model that corresponds to the business scenario.

[0082] S2044. Based on the retrained samples, retrain the digital twin sub-model corresponding to the business scenario in the digital twin model, update the model parameters of the digital twin sub-model, and obtain the updated digital twin model.

[0083] S205. Based on the updated digital twin model, the status of each line and node in the distribution network is monitored.

[0084] In this way, this embodiment of the invention performs real-time prediction using a digital twin model while simultaneously detecting real-time data of the distribution network using a physical mechanism model to determine the actual operating status. The detection results of the physical mechanism model and the digital twin model are compared; if inconsistencies exist, it indicates that the digital twin model's detection is inaccurate. The analysis device then needs to retrain the digital twin model and update its parameters.

[0085] Understandably, since physical mechanism models take longer to process than digital twin models, this invention uses a method of real-time prediction with digital twin models and confirmation and correction with physical mechanism models to ensure the efficiency and accuracy of power distribution network operation status detection.

[0086] Furthermore, when updating model parameters, this invention only updates the sub-models in the digital twin model, and only updates the sub-models with inaccurate detection, avoiding a complete update of the digital twin model, reducing memory consumption for model updates, shortening model update time, and ensuring the real-time performance of model detection.

[0087] It should be noted that this invention integrates the dynamic changes of the physical mechanism model of the physical distribution network, dynamic knowledge discovery, and dynamic rule improvement to study the online dynamic updating of the 3D virtual space model of the distribution network under the high proportion of distributed power source access. Based on the 3D virtual space model, the operation of the distribution network under active conditions in different business scenarios is simulated and deduced, and the simulation data and conclusions are fed back to the data space and knowledge space respectively, forming a closed loop of online digital twin modeling in typical scenarios.

[0088] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0089] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0090] Figure 3 A schematic diagram of a power distribution network operation status analysis device according to an embodiment of the present invention is shown. The analysis device 300 includes a communication module 301 and a processing module 302.

[0091] The communication module 301 is used to acquire historical data of each line and node in the distribution network; the historical data includes voltage data, current data, frequency data and phase data.

[0092] The processing module 302 is used to construct a physical mechanism model based on the basic principles of circuits, and to perform steady-state and transient analysis on the historical data of each line and node based on the physical mechanism model to obtain the operating status of the distribution network and the historical data corresponding to each operating status. The operating status includes normal state, fault state, early warning state and recovery state. Based on the operating status of the distribution network and the historical data corresponding to each operating status, training samples are constructed. Based on the training samples, a neural network is trained to obtain a digital twin model. Based on the digital twin model, the real-time data of each line and node in the distribution network are analyzed to obtain the real-time operating status of each line and node in the distribution network, thereby realizing the state monitoring of the distribution network.

[0093] In one possible implementation, the processing module 302 is specifically used to determine the steady-state analysis equations and transient analysis equations for each line and each node; determine the range of values ​​for the stability analysis results and transient analysis results for each line and each node under each operating state; and determine the entity mechanism model based on the steady-state analysis equations and transient analysis equations for each line and each node, as well as the range of values ​​for the stability analysis results and transient analysis results under each operating state.

[0094] In one possible implementation, the processing module 302 is specifically used to input the historical data of each line and each node into the entity mechanism model to obtain the operating status of each line and each node at each time; based on the operating status of each line and each node at each time, to split the historical data of each line and each node; based on the operating status of each line and each node at each time, and the split historical data of each line and each node, to determine the operating status of the distribution network and the historical data corresponding to each operating status.

[0095] In one possible implementation, the processing module 302 is specifically configured to, for any line or node, determine a first training sample by taking the historical data of the line or node at any given time as input and its operating status at that time as output; determine a second training sample by taking the historical data of the line or node for a predetermined period prior to any given time as input and its operating status at that time as output; and determine a third training sample for any line or node at any given time by taking the historical data of the line or node and its neighboring nodes at that time as input and its operating status at that time as output; wherein the neighboring nodes of the line or node are one or more nodes adjacent to the line or node; and determine training samples based on the first training sample, the second training sample, and the third training sample.

[0096] In one possible implementation, the processing module 302 is specifically used to determine the business scenarios of each line and each node; wherein, the mapping relationship between the historical data and the operating status of the lines or nodes corresponding to the same business scenarios is the same; based on the business scenarios of each line and each node, the training samples are divided to obtain the training samples corresponding to each business scenario; for any business scenario, based on the training samples corresponding to the business scenario, the new neural network model is trained to obtain a digital twin sub-model; based on the digital twin sub-models corresponding to each business scenario, the digital twin model is determined.

[0097] In one possible implementation, the processing module 302 is specifically used to determine the business scenario corresponding to each line or node; for any line or node, the real-time data of the line or node is input into the digital twin sub-model corresponding to the business scenario of the line or node to obtain the real-time operating status of the line or node.

[0098] In one possible implementation, the processing module 302 is further configured to: analyze the real-time data of each line and node in the distribution network based on the entity mechanism model to obtain the actual operating status of each line and node in the distribution network; compare whether the actual operating status and the real-time operating status are consistent; if they are inconsistent, record the time when the actual operating status and the real-time operating status are inconsistent as the target time, and record the line or node whose actual operating status and the real-time operating status are inconsistent as the target line or target node; update the digital twin model based on the real-time data of the target line or target node at the target time, and the actual operating status of the target line or target node at the target time; and perform status monitoring on each line and node in the distribution network based on the updated digital twin model.

[0099] In one possible implementation, the processing module 302 is specifically used to construct retraining samples based on the real-time data of the target line or target node at the target time and the actual operating status of the target line or target node at the target time; determine the business scenario corresponding to the target line or target node; determine the digital twin sub-model corresponding to the business scenario in the digital twin model based on the business scenario corresponding to the target line or target node; and retrain the digital twin sub-model corresponding to the business scenario in the digital twin model based on the retraining samples, update the model parameters of the digital twin sub-model, and obtain the updated digital twin model.

[0100] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. For example... Figure 4 As shown, the electronic device 400 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, it implements the steps in the above-described method embodiments, for example... Figure 1 Steps 101 to 104 are shown. Alternatively, when the processor 401 executes the computer program 403, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 3 The functions of the communication module 301 and the processing module 302 shown are illustrated.

[0101] For example, the computer program 403 can be divided into one or more modules / units, which are stored in the memory 402 and executed by the processor 401 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 403 in the electronic device 400. For example, the computer program 403 can be divided into... Figure 3The communication module 301 and the processing module 302 are shown.

[0102] The processor 401 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0103] The memory 402 can be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. The memory 402 can also be an external storage device of the electronic device 400, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 400. Furthermore, the memory 402 can include both internal and external storage units of the electronic device 400. The memory 402 is used to store the computer program and other programs and data required by the terminal. The memory 402 can also be used to temporarily store data that has been output or will be output.

[0104] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0105] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0106] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0107] In the embodiments provided by this invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0108] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0109] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0110] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0111] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for analyzing the operating status of a power distribution network, characterized in that, include: Historical data of each line and node in the distribution network is acquired; the historical data includes voltage data, current data, frequency data, and phase data. Based on the basic principles of circuits, a physical mechanism model is constructed, and steady-state and transient analyses are performed on the historical data of each line and node based on the physical mechanism model to obtain the operating status of the distribution network and the historical data corresponding to each operating status; the operating status includes normal state, fault state, early warning state and recovery state; Based on the operating status of the distribution network and the historical data corresponding to each operating status, training samples are constructed, including: for any line or node, using the historical data of the line or node at any time as input and the operating status at that time as output, a first training sample is determined; using the historical data of the line or node for a set period before any time as input and the operating status at that time as output, a second training sample is determined; for any line or node at any time, using the historical data of the line or node and its adjacent nodes at that time as input and the operating status at that time as output, a third training sample is determined; wherein, the adjacent nodes of the line or node are one or more nodes adjacent to the line or node; the training sample is determined based on the first training sample, the second training sample, and the third training sample. A digital twin model is obtained by training a neural network based on the training samples. Based on the digital twin model, real-time data of each line and node in the distribution network are analyzed to obtain the real-time operating status of each line and node in the distribution network, thereby realizing the status monitoring of the distribution network. This includes: determining the business scenario corresponding to each line or node; for any line or node, inputting the real-time data of the line or node into the digital twin sub-model corresponding to the business scenario of the line or node to obtain the real-time operating status of the line or node.

2. The method for analyzing the operating status of a power distribution network according to claim 1, characterized in that, The physical mechanism model constructed based on the basic principles of circuits includes: Determine the steady-state and transient analysis equations for each line and each node; Determine the stability analysis results and transient analysis results for each line and node, and their value ranges under each operating state; Based on the steady-state and transient analysis equations of each line and node, and the range of values ​​of the steady-state and transient analysis results under each operating state, the entity mechanism model is determined.

3. The method for analyzing the operating status of a power distribution network according to claim 1, characterized in that, The steady-state and transient analyses of historical data for each line and node are performed based on the physical mechanism model to obtain the operating status of the distribution network and the corresponding historical data for each operating status, including: The historical data of each line and each node are input into the entity mechanism model to obtain the operating status of each line and each node at each time. Based on the operating status of each line and each node at each time, the historical data of each line and each node is broken down. Based on the operating status of each line and node at each time point, and the historical data of each line and node after being split, the operating status of the distribution network and the historical data corresponding to each operating status are determined.

4. The method for analyzing the operating status of a power distribution network according to claim 1, characterized in that, The process of training a neural network based on the training samples to obtain a digital twin model includes: Determine the business scenarios for each line and each node; wherein, the mapping relationship between the historical data and the operating status of lines or nodes corresponding to the same type of business scenario is the same; Based on the business scenarios of each line and each node, the training samples are divided to obtain training samples corresponding to each business scenario. For any business scenario, a new neural network model is trained based on the training samples corresponding to that business scenario to obtain a digital twin model; The digital twin model is determined based on the digital twin sub-models corresponding to each business scenario.

5. The method for analyzing the operating status of a power distribution network according to claim 1, characterized in that, The method further includes: Based on the physical mechanism model, the real-time data of each line and node in the distribution network are analyzed to obtain the actual operating status of each line and node in the distribution network. Compare whether the actual operating state and the real-time operating state are consistent; If they are inconsistent, the time when the actual operating state and the real-time operating state are inconsistent is recorded as the target time, and the line or node where the actual operating state and the real-time operating state are inconsistent is recorded as the target line or target node. The digital twin model is updated based on the real-time data of the target line or target node at the target time and the actual operating status of the target line or target node at the target time. Based on the updated digital twin model, the status of each line and node in the power distribution network is monitored.

6. The method for analyzing the operating status of a power distribution network according to claim 5, characterized in that, The step of updating the digital twin model based on the real-time data of the target line or target node at the target time, and the actual operating status of the target line or target node at the target time, includes: Based on the real-time data of the target line or target node at the target time, and the actual operating status of the target line or target node at the target time, a retraining sample is formed. Determine the business scenario corresponding to the target line or target node; Based on the business scenario corresponding to the target line or target node, determine the digital twin sub-model in the digital twin model that corresponds to the business scenario; Based on the retrained samples, the digital twin sub-model corresponding to the business scenario in the digital twin model is retrained, and the model parameters of the digital twin sub-model are updated to obtain the updated digital twin model.

7. A device for analyzing the operating status of a power distribution network, characterized in that, include: The communication module is used to acquire historical data of each line and node in the power distribution network; the historical data includes voltage data, current data, frequency data and phase data. The processing module is used to construct a physical mechanism model based on the basic principles of circuits, and to perform steady-state and transient analysis on the historical data of each line and each node based on the physical mechanism model to obtain the operating status of the distribution network and the historical data corresponding to each operating status; the operating status includes normal state, fault state, early warning state and recovery state; and to construct training samples based on the operating status of the distribution network and the historical data corresponding to each operating status. The neural network is trained based on the training samples to obtain a digital twin model; the real-time data of each line and node in the distribution network is analyzed based on the digital twin model to obtain the real-time operating status of each line and node in the distribution network, thereby realizing the status monitoring of the distribution network. The processing module is specifically used to determine the business scenario corresponding to each line or node; for any line or node, the real-time data of the line or node is input into the digital twin sub-model corresponding to the business scenario of the line or node to obtain the real-time operating status of the line or node. The processing module is specifically used to determine the first training sample for any line or node, taking the historical data of the line or node at any time as input and the operating status at that time as output. Using historical data of the line or node for a set period prior to any given time as input and its operating status at that time as output, a second training sample is determined. For any line or node at any given time, using historical data of the line or node and its neighboring nodes at that time as input and its operating status at that time as output, a third training sample is determined. The neighboring nodes of the line or node are one or more nodes adjacent to the line or node. The training sample is determined based on the first training sample, the second training sample, and the third training sample.

8. An online monitoring system for a power system, characterized in that, The online monitoring system includes a memory and a processor. The memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to perform the method as described in any one of claims 1 to 6.

Images