Power distribution network cascading failure prediction method, device, equipment, medium and program product

Abstract

The present disclosure provides a power distribution network cascading failure prediction method, device, equipment, medium and program product, the method comprising: acquiring detection data of a power distribution network, analyzing the detection data, and determining a fault branch in the power distribution network; predicting the predicted load of each region in the power distribution network based on a pre-constructed load prediction model of the power distribution network; searching for a target line parallel to the fault branch in the power distribution network based on a pre-constructed topological directed graph of the power distribution network, analyzing the electricity distribution ratio of the fault branch and the target line based on historical electricity consumption data; predicting the electrical parameters of the target line based on the predicted load and the electricity distribution ratio; and predicting the fault prediction result of the target line based on the electrical parameters of the target line and the bearing capacity of the target line. The present disclosure reduces the calculation of fault-free samples and shortens the prediction efficiency of cascading failures.

Description

Technical Field

[0001] This disclosure relates to the field of power system technology, and in particular to a method, device, equipment, medium and program product for predicting cascading faults in distribution networks. Background Technology

[0002] This section is intended to provide background or context for the embodiments of this disclosure as set forth in the claims. The description herein is not intended to be a prior art simply because it is included in this section.

[0003] A distribution network refers to a power grid that receives electrical energy from the transmission network or regional power plants and distributes it locally or in stages according to voltage to various users through distribution facilities. It consists of overhead lines, cables, poles, distribution transformers, disconnect switches, reactive power compensators, and some auxiliary facilities, and plays an important role in distributing electrical energy within the power grid.

[0004] In a power distribution network, each component (such as transformers, lines, and switches) bears a certain electrical load. When a component fails due to overload, aging, short circuit, or other reasons, it is disconnected, altering the power flow balance and causing a redistribution of load across other components. If these previously functioning components cannot handle the excess load, they may fail again, creating a cascading effect. This cascading effect can lead to the failure of more components, and may even cause the collapse of the entire power distribution network. Summary of the Invention

[0005] In view of this, the purpose of this disclosure is to propose a method, device, equipment, medium and program product for predicting cascading faults in power distribution networks, which at least to some extent solves one of the technical problems in related technologies.

[0006] To achieve the above objectives, the first aspect of this exemplary embodiment provides a method for predicting cascading faults in a distribution network, comprising:

[0007] Acquire detection data of the power distribution network, analyze the detection data, and determine the faulty branch in the power distribution network;

[0008] The predicted load of each area in the distribution network is predicted based on the pre-built load prediction model of the distribution network.

[0009] Based on the pre-constructed topology directed graph of the distribution network, search for target lines in the distribution network that are connected in parallel with the faulty branch, and analyze the power distribution ratio between the faulty branch and the target lines based on historical power consumption data.

[0010] The electrical parameters of the target line are predicted based on the predicted load and the power allocation ratio.

[0011] Based on the electrical parameters and the carrying capacity of the target line, the fault prediction result of the target line is predicted.

[0012] In some exemplary embodiments, acquiring detection data of the distribution network, analyzing the detection data, and determining the faulty branch in the distribution network includes:

[0013] The detection data is acquired through sensors in the power distribution network;

[0014] The faulty branch is determined by performing threshold judgment, trend analysis and / or correlation analysis on the detection data.

[0015] In some exemplary embodiments, predicting the forecast load of each area in the distribution network based on a pre-built load forecasting model of the distribution network includes:

[0016] Obtain historical load data and influencing factor data of the power distribution network;

[0017] A time series prediction model is trained based on the historical load data;

[0018] A regression model was trained based on the data of the aforementioned influencing factors;

[0019] The time series forecasting model and the regression model are fused to obtain the load forecasting model;

[0020] The predicted load of each area in the distribution network is predicted based on the load prediction model.

[0021] In some exemplary embodiments, the step of searching for target lines in the distribution network that are in parallel with the faulty branch based on a pre-constructed directed graph of the distribution network topology, and analyzing the power distribution ratio between the faulty branch and the target lines based on historical electricity consumption data, includes:

[0022] In the topological directed graph of the power distribution network, starting from the starting node and ending node of the faulty branch, the search is performed along the direction parallel to the faulty branch to obtain the target line;

[0023] Obtain historical electricity consumption data of the power distribution network, and analyze the power distribution ratio between the faulty branch and the target line based on the historical electricity consumption data.

[0024] In some exemplary embodiments, predicting the electrical parameters of the target line based on the predicted load and the power allocation ratio includes:

[0025] Based on the correspondence between the target line and the load point, the predicted load value of the load point corresponding to the target line is extracted from the predicted load.

[0026] For each target line, a predicted power consumption is obtained based on the predicted load value of the load point corresponding to the target line and the power distribution ratio, wherein the electrical parameters of the target line include the predicted power consumption.

[0027] In some exemplary embodiments, predicting the fault prediction result of the target line based on the electrical parameters and the carrying capacity of the target line includes:

[0028] Based on the electrical parameters of the target line and the carrying capacity of the target line, the load rate of the target line is determined;

[0029] Using a pre-built fault prediction model, based on the historical fault data of the distribution network, the electrical parameters of the target line, the carrying capacity of the target line, and the load rate, the fault prediction result of the target line is predicted.

[0030] Based on the same inventive concept, a second aspect of the exemplary embodiments of this disclosure provides a distribution network cascading fault prediction device, comprising:

[0031] The fault branch location module is configured to acquire detection data of the distribution network, analyze the detection data, and determine the fault branch in the distribution network.

[0032] The load forecasting module is configured to forecast the load of each area in the distribution network based on a pre-built load forecasting model of the distribution network.

[0033] The power allocation ratio determination module is configured to search for target lines in the distribution network that are connected in parallel with the faulty branch based on a pre-built directed graph of the distribution network topology, and analyze the power allocation ratio between the faulty branch and the target lines based on historical power consumption data.

[0034] The electrical parameter determination module is configured to predict the electrical parameters of the target line based on the predicted load and the power allocation ratio;

[0035] The fault prediction module is configured to predict the fault prediction result of the target line based on the electrical parameters of the target line and the carrying capacity of the target line.

[0036] Based on the same inventive concept, a third aspect of the exemplary embodiments of this disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method as described in the first aspect.

[0037] Based on the same inventive concept, a fourth aspect of the exemplary embodiments of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method as described in the first aspect.

[0038] Based on the same inventive concept, a fifth aspect of the exemplary embodiments of this disclosure provides a computer program product including computer program instructions that, when run on a computer, cause the computer to perform the method as described in the first aspect.

[0039] As can be seen from the above, the distribution network cascading fault prediction method, apparatus, equipment, medium, and program products provided in this disclosure include: acquiring detection data of the distribution network; analyzing the detection data to determine faulty branches in the distribution network; predicting the predicted load of each area in the distribution network based on a pre-constructed load prediction model of the distribution network; searching for target lines in the distribution network connected in parallel with the faulty branches based on a pre-constructed topological directed graph of the distribution network; analyzing the power distribution ratio between the faulty branches and the target lines based on historical electricity consumption data; predicting the electrical parameters of the target lines based on the predicted load and the power distribution ratio; and predicting the fault prediction result of the target lines based on the electrical parameters and the carrying capacity of the target lines. This disclosure reduces the calculation of fault-free samples and shortens the prediction efficiency of cascading faults. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in this disclosure or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A schematic diagram of an application scenario of the distribution network cascading fault prediction method provided as an exemplary embodiment of this disclosure;

[0042] Figure 2 A schematic flowchart of a method for predicting cascading faults in a distribution network provided as an exemplary embodiment of this disclosure;

[0043] Figure 3 A schematic diagram of a distribution network cascading fault prediction device provided as an exemplary embodiment of the present disclosure;

[0044] Figure 4 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present disclosure. Detailed Implementation

[0045] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0046] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this application's technical solution, based on the prompt message.

[0047] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0048] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this application. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this application.

[0049] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0050] To make the objectives, technical solutions, and advantages of this disclosure clearer, the principles and spirit of this disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided merely to enable those skilled in the art to better understand and implement this disclosure, and are not intended to limit the scope of this disclosure in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0051] It is important to understand that any number of elements in the accompanying figures is for illustrative purposes only and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0052] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar words used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly. The article "a" or "an" preceding an element does not exclude the existence of multiple such elements.

[0053] The principles and spirit of this disclosure will be explained in detail below with reference to several representative embodiments.

[0054] As described in the background section, a distribution network refers to a power grid that receives electrical energy from the transmission network or regional power plants and distributes it locally or in stages according to voltage to various users through distribution facilities. It is a network composed of overhead lines, cables, poles, distribution transformers, disconnect switches, reactive power compensators, and some auxiliary facilities, playing a crucial role in distributing electrical energy within the power grid.

[0055] In a power distribution network, each component (such as transformers, lines, and switches) bears a certain electrical load. When a component fails due to overload, aging, short circuit, or other reasons, it is disconnected, altering the power flow balance and causing a redistribution of load across other components. If these previously functioning components cannot handle the excess load, they may fail again, creating a cascading effect. This cascading effect can lead to the failure of more components, and may even cause the collapse of the entire power distribution network.

[0056] Specifically, the hazards of cascading failures in a distribution network include:

[0057] A cascading failure can cause multiple lines or devices in a power distribution network to disconnect simultaneously, leading to a complete collapse of the entire network. This will result in widespread power outages, severely impacting people's daily lives and business operations.

[0058] The current and voltage fluctuations and overheating that occur during a cascading failure can cause serious damage to electrical equipment. This damage may render the equipment inoperable, requiring extensive repair and replacement work.

[0059] Widespread power outages will cause serious social problems, such as halted production, disruption of healthcare services, and traffic congestion. These impacts will severely hinder socio-economic development and progress.

[0060] A cascading failure can damage electrical equipment and cause power outages, leading to a range of safety hazards. For example, a power outage may cause fire alarm systems to malfunction or people to become trapped in elevators.

[0061] Therefore, predicting cascading failures in the distribution network is a necessary means to maintain its stability.

[0062] In related technologies, faults are searched using the Monte Carlo simulation method.

[0063] However, the inventors of this disclosure have found that when searching for faults using the Monte Carlo simulation method, risk indicators are mostly expressed as expected probabilities, which are difficult to understand and take too long to calculate. Fault-free samples consume a large amount of computation time.

[0064] To address the aforementioned problems, this disclosure provides a distribution network cascading fault prediction scheme, specifically including:

[0065] Acquire detection data of the distribution network, analyze the detection data, and identify faulty branches in the distribution network; predict the predicted load of each area in the distribution network based on a pre-constructed load prediction model of the distribution network; search for target lines in the distribution network that are connected in parallel with the faulty branches based on a pre-constructed topological directed graph of the distribution network, and analyze the power distribution ratio between the faulty branches and the target lines based on historical power consumption data; predict the electrical parameters of the target lines based on the predicted load and the power distribution ratio; and predict the fault prediction result of the target lines based on the electrical parameters and the carrying capacity of the target lines.

[0066] This disclosure reduces the computation of fault-free samples and shortens the prediction efficiency of cascading failures.

[0067] After introducing the basic principles of this disclosure, various non-limiting embodiments of this disclosure will be described in detail below.

[0068] refer to Figure 1 This is a schematic diagram of an application scenario of the distribution network cascading fault prediction method provided by the exemplary embodiments of this disclosure.

[0069] This application scenario includes a terminal device 101, a server 102, and a data storage system 103. The terminal device 101, server 102, and data storage system 103 can all be connected via wired or wireless communication networks to achieve data interaction.

[0070] Terminal device 101 may be an electronic device located close to the user side, possessing data transmission and multimedia input / output functions, including but not limited to desktop computers, mobile phones, portable computers, tablet computers, media players, smart wearable devices, personal digital assistants (PDAs), or other electronic devices capable of performing the aforementioned functions. This electronic device may include a processor and a display screen with touch input functionality. The display screen is used to present a graphical user interface (GUI), which can display an application interface. The processor is used to process application data, generate the GUI, and control the display of the GUI on the screen.

[0071] Both server 102 and data storage system 103 can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0072] When the distribution network cascading fault prediction method is running on server 102, server 102 is used to provide distribution network cascading fault prediction services to users of terminal device 101. Terminal device 101 has a client installed that communicates with server 102.

[0073] Server 102 acquires detection data from the power distribution network, analyzes the detection data, and identifies faulty branches in the power distribution network; predicts the predicted load of each area in the power distribution network based on a pre-built load prediction model of the power distribution network; searches for target lines in the power distribution network that are connected in parallel with the faulty branch based on a pre-built topological directed graph of the power distribution network, and analyzes the power distribution ratio between the faulty branch and the target line based on historical electricity consumption data; predicts the electrical parameters of the target line based on the predicted load and the power distribution ratio; and predicts the fault prediction result of the target line based on the electrical parameters of the target line and the carrying capacity of the target line.

[0074] Server 102 sends the fault prediction results to the client, which then displays the results to the user to help with power distribution network maintenance.

[0075] The data storage system 103 stores a large amount of training data. Each training data set includes a sample data set and its corresponding label data. Taking a load forecasting model as an example, the server 102 can train the load forecasting model based on this large amount of training data, enabling the model to predict the input sample data. The sources of the training data include, but are not limited to, existing databases, data crawled from the Internet, or data uploaded by users when using the client. When the accuracy of the load forecasting model reaches a certain requirement, the server 102 can provide load forecasting services to users based on the model. Furthermore, the server 102 can continuously optimize the load forecasting model based on newly added training data.

[0076] The following is combined Figure 1 The application scenarios described above illustrate the distribution network cascading fault prediction method according to exemplary embodiments of this disclosure. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this disclosure, and the embodiments of this disclosure are not limited in any way. Rather, the embodiments of this disclosure can be applied to any applicable scenario.

[0077] refer to Figure 2 This is a flowchart illustrating a distribution network cascading fault prediction method provided by an exemplary embodiment of the present disclosure.

[0078] The method for predicting cascading faults in power distribution networks includes the following steps:

[0079] Step S210: Obtain the detection data of the distribution network, analyze the detection data, and determine the faulty branch in the distribution network.

[0080] In some exemplary embodiments, acquiring detection data of the distribution network, analyzing the detection data, and determining the faulty branch in the distribution network includes:

[0081] The detection data is acquired through sensors in the power distribution network;

[0082] The faulty branch is determined by performing threshold judgment, trend analysis and / or correlation analysis on the detection data.

[0083] In practice, real-time monitoring data of the power distribution network is acquired through sensor networks and remote monitoring systems. This data includes, but is not limited to, key parameters such as current, voltage, power factor, and temperature. Subsequently, data analysis algorithms (such as threshold judgment and trend analysis) are used to process the monitoring data to accurately identify the specific branch where the faulty component (such as a transformer, circuit breaker, or line) is located. This step aims to quickly locate the problem and provide a foundation for subsequent operations.

[0084] As an example, suppose there is a power distribution network in a medium-sized city, consisting of multiple substations, transmission lines, distribution transformers, and electrical loads. To ensure the safe and stable operation of the power grid, the power company has installed sensor networks and remote monitoring systems.

[0085] In specific implementation, the detection data is acquired through sensors in the power distribution network, including:

[0086] Sensor deployment: Install current transformers, voltage transformers, temperature sensors, and power factor sensors at critical locations (such as substation outlets, key points of transmission lines, and distribution transformer inlets).

[0087] Data Acquisition: These sensors will collect key parameters such as current, voltage, temperature and power factor in real time, and transmit the data to a remote monitoring center via wired or wireless means.

[0088] Data storage: After receiving this data, the remote monitoring center will store it in the database for subsequent analysis and processing.

[0089] In specific implementation, threshold judgment, trend analysis, and / or correlation analysis are performed on the detection data to determine the faulty branch, including:

[0090] Data preprocessing: First, the collected raw data is preprocessed, including data cleaning, noise reduction, and outlier detection, to ensure the accuracy and reliability of the data.

[0091] Applications of data analysis algorithms:

[0092] Threshold judgment: Set normal range thresholds for current, voltage, temperature, and power factor. When any parameter exceeds the threshold, an alarm is triggered, indicating a possible fault.

[0093] Trend analysis: Analyze the changing trends of parameters such as current and voltage. If a parameter changes drastically within a short period of time, it may indicate a fault.

[0094] Correlation analysis: Analyzing the correlation between different parameters. For example, if the current suddenly increases while the voltage decreases, it may indicate a short circuit fault in a certain line.

[0095] Fault location:

[0096] Substation level: If the current or voltage at the substation outlet is abnormal, it may mean that there is a fault inside the substation or in the outlet line.

[0097] Line level: If the current or voltage of a transmission line is abnormal, it may indicate a fault in that line. By comparing data from different locations, the fault location can be further narrowed down.

[0098] Distribution transformer level: If the input or output voltage or current of the distribution transformer is abnormal, it may mean that the transformer is faulty.

[0099] In practical implementation, fault location techniques include:

[0100] Partial discharge location: Determine the location of the fault point by detecting partial discharge phenomena in electrical equipment.

[0101] Line or equipment location: Using sensors and monitoring equipment, real-time operating status information of lines or equipment is obtained, and the location of the fault is determined through data analysis.

[0102] In practice, artificial intelligence and machine learning can also be used to locate faults, including:

[0103] Algorithms are used to analyze and identify patterns in large amounts of power system data, thereby predicting and diagnosing potential faults.

[0104] By training the model, it can automatically identify fault characteristics, thereby improving the accuracy and efficiency of fault location.

[0105] As an example, suppose that one evening at 8 PM, the remote monitoring center receives an alarm indicating a sudden increase in current and a decrease in voltage on a certain transmission line. Data analysts immediately review the historical and real-time data for this line and find that the current has risen sharply in a short period of time, while the voltage has continued to drop. Simultaneously, the data analysts also find that the current in other lines connected in parallel with this line has not shown significant changes.

[0106] Based on this data and analysis, the data analysts determined that a short-circuit fault might have occurred on the transmission line. They immediately notified maintenance personnel to inspect the site and take measures to isolate the faulty line and restore normal power supply to other lines.

[0107] Through the above exemplary embodiments, sensor networks and remote monitoring systems play a role in fault location in power distribution networks. They can collect key parameter data in real time and quickly and accurately locate faulty components and their branches through data analysis algorithms, providing timely and effective fault information for operation and maintenance personnel and ensuring the safe and stable operation of the power grid.

[0108] Step S220: Predict the predicted load of each area in the distribution network based on the pre-built load prediction model of the distribution network.

[0109] In some exemplary embodiments, predicting the forecast load of each area in the distribution network based on a pre-built load forecasting model of the distribution network includes:

[0110] Obtain historical load data and influencing factor data of the power distribution network;

[0111] A time series prediction model is trained based on the historical load data;

[0112] A regression model was trained based on the data of the aforementioned influencing factors;

[0113] The time series forecasting model and the regression model are fused to obtain the load forecasting model;

[0114] The predicted load of each area in the distribution network is predicted based on the load prediction model.

[0115] In practice, load forecasting models, such as Long Short-Term Memory (LSTM) models, are used to combine historical load data, weather forecasts, holiday information, and socio-economic activity patterns with other multi-dimensional features to accurately predict the load of various areas of the distribution network over a future period. LSTM models are particularly adept at handling the long-term dependencies of time-series data, effectively capturing complex patterns in load changes and improving forecast accuracy.

[0116] In specific implementation, historical load data and influencing factor data of the distribution network are obtained, including:

[0117] Historical load data:

[0118] Load data, including active power and reactive power, is collected from various load connection points in the power system over a period of time (such as the past few years).

[0119] Data is cleaned to remove outliers and missing values, ensuring data accuracy and integrity.

[0120] Influencing factors data:

[0121] Collect data on external factors related to load changes, such as weather forecasts (temperature, humidity, wind speed, etc.), holiday information, and socio-economic activity patterns.

[0122] These factor data are encoded and preprocessed so that they can be input into the predictive model along with the load data.

[0123] In specific implementation, a time series prediction model is trained based on the historical load data, including:

[0124] Select model:

[0125] Considering the time-series characteristics of load data, time-series forecasting models can be selected, such as ARIMA models, state-space models, or recurrent neural networks (RNNs) and their variants (such as LSTM) in machine learning.

[0126] These models are able to capture the time dependence and periodic changes in load data.

[0127] Model training:

[0128] The model is trained using historical load data, and the model parameters are adjusted to minimize prediction error.

[0129] During training, techniques such as cross-validation can be used to evaluate the model's performance and prevent overfitting.

[0130] In specific implementation, a regression model is trained based on the aforementioned influencing factor data, including:

[0131] Feature selection for influencing factor data:

[0132] Based on the correlation analysis of historical data and influencing factors, features that have a significant impact on load changes are selected.

[0133] These features may include temperature and humidity in weather forecasts, as well as holiday information and socioeconomic activity patterns.

[0134] Model selection:

[0135] Regression models that consider influencing factors (such as linear regression, decision trees, random forests, etc.).

[0136] In specific implementation, the time series forecasting model and the regression model are fused to obtain the load forecasting model, including:

[0137] Model fusion:

[0138] Integrate time series forecasting models with regression models that consider influencing factors (such as linear regression, decision trees, random forests, etc.).

[0139] By combining the prediction results of different models, the accuracy and robustness of predictions can be improved.

[0140] In specific implementation, the predicted load of each area in the distribution network is predicted based on the load prediction model, including:

[0141] Short-term load forecast:

[0142] Short-term load forecasts for the next few hours provide real-time decision support for power grid dispatch and operation.

[0143] A rolling forecasting approach can be adopted to continuously update the forecast results in order to adapt to the uncertainty of load changes.

[0144] Long-term load planning:

[0145] Long-term planning for loads over the next few years or longer provides strategic guidance for power grid construction and upgrading.

[0146] The load growth trend can be predicted and analyzed by combining factors such as socio-economic development trends and energy policies.

[0147] Prediction result optimization:

[0148] Post-processing of the prediction results, such as smoothing, outlier detection and correction, can improve the practicality and reliability of the prediction results.

[0149] Based on actual needs, the prediction results can be further analyzed and explored, such as load peak prediction and load characteristic analysis.

[0150] In practice, this also includes model evaluation and updates:

[0151] Model evaluation:

[0152] The performance of the prediction model is evaluated using appropriate evaluation metrics (such as mean squared error (MSE), mean absolute error (MAE), etc.).

[0153] By comparing the prediction results of different models, the model with the best performance is selected for practical application.

[0154] Model update:

[0155] As time goes on and load characteristics change, the forecasting model needs to be updated and optimized regularly.

[0156] New features and data sources can be introduced, and the model structure or algorithm can be improved to enhance the accuracy and adaptability of predictions.

[0157] Step S230: Based on the pre-constructed topology directed graph of the distribution network, search for target lines in the distribution network that are connected in parallel with the faulty branch, and analyze the power distribution ratio between the faulty branch and the target lines based on historical power consumption data.

[0158] In some exemplary embodiments, the step of searching for target lines in the distribution network that are in parallel with the faulty branch based on a pre-constructed directed graph of the distribution network topology, and analyzing the power distribution ratio between the faulty branch and the target lines based on historical electricity consumption data, includes:

[0159] In the topological directed graph of the power distribution network, starting from the starting node and ending node of the faulty branch, the search is performed along the direction parallel to the faulty branch to obtain the target line;

[0160] Obtain historical electricity consumption data of the power distribution network, and analyze the power distribution ratio between the faulty branch and the target line based on the historical electricity consumption data.

[0161] In practical implementation, the methods for constructing the directed graph of the distribution network topology include:

[0162] Data collection:

[0163] Collect the connection relationships of all substations, busbars, lines (including DC transmission lines and lines equipped with flexible AC transmission equipment (FACTS)) and transformers in the power system.

[0164] Collect active power flow data to determine the power flow direction of lines or transformers.

[0165] Definitions of nodes and edges:

[0166] Node: Define a substation or busbar as a node in the diagram.

[0167] Edge: A line (including DC transmission lines and FACTS lines) or transformer is defined as an edge in the diagram. The direction of the edge is determined by the direction of active power flow.

[0168] Build steps:

[0169] Drawing nodes: Based on the collected data, draw all substation and busbar nodes on drawings or in graphics software.

[0170] Connection edges: Based on the connection relationship between the lines and transformers, the nodes are connected by directed edges. The direction of the edges should be consistent with the direction of active power flow.

[0171] For transformers, if their connection method is different (such as Y / Δ connection), special attention needs to be paid to the phase relationship between current and voltage to ensure that the direction of the side is correct.

[0172] Labeling information:

[0173] Mark the name and number of the substation or busbar on the node.

[0174] Label the line or transformer with its name, number, and power flow direction (which can be indicated by an arrow).

[0175] At the same time, based on the capacity of the equipment corresponding to the node or edge, the capacity parameters (standard voltage / current, etc.) are marked for the node and edge.

[0176] Verification and adjustment:

[0177] Check that the nodes and edges in the graph are correctly connected and that there are no omissions or errors. Adjust the layout of the graph as needed to make it clearer and easier to read.

[0178] In the above exemplary embodiment, a directed graph of the power system is constructed based on the topology and active power flow direction of the power system.

[0179] In practice, the methods for searching the target route include:

[0180] Power grid topology analysis:

[0181] Clearly define the connection relationships between nodes (such as substations and buses) in the directed graph of the power grid topology;

[0182] Locate the starting and ending nodes of the faulty branch in the graph to provide a basis for subsequent searches.

[0183] Parallel circuit traversal:

[0184] Starting from the beginning and end nodes of the faulty branch, search along the direction parallel to the faulty branch.

[0185] Traverse all lines connected to the faulty branch at the same node and check their capacity, impedance, and other parameters.

[0186] Power flow calculation and evaluation:

[0187] Use power flow calculation software or methods to assess whether parallel lines can handle part or all of the power flow of a faulty branch.

[0188] Considering the power grid's operating mode and power flow distribution, ensure the stability and security of the power grid after power transfer.

[0189] In practical implementation, the complexity and diversity of the power grid should be taken into account:

[0190] Ring network structure processing: Identify changes in loop current and power flow distribution in a ring network structure.

[0191] The impact of loop current on power transfer search can be eliminated by adjusting the power grid operation mode or taking control measures.

[0192] Multiple power supply scenarios: Analyze the mutual influence and power flow distribution between different power sources.

[0193] Ensure that the power transfer scheme does not cause overload or unstable operation of other power sources.

[0194] In practice, the filtering and sorting processes are as follows:

[0195] Screening criteria: Based on factors such as line impedance, capacity, and historical power flow data, parallel lines that are close to the faulty branch, have a large capacity, and are not overloaded are selected.

[0196] Exclude lines that cannot meet the transfer requirements, such as those with insufficient capacity or excessive impedance.

[0197] Sorting method: Sort according to the priority of the selected lines.

[0198] Prioritization can take into account factors such as line capacity margin, impedance, and historical operating data.

[0199] Prioritize high-priority lines to ensure the feasibility and effectiveness of the transfer plan.

[0200] In practice, the power distribution ratio between the faulty branch and the target line is analyzed, including:

[0201] Collect historical electricity consumption data: Collect load data for each line for a period of time before and after the fault occurred, including active power and reactive power.

[0202] These data should be as detailed and accurate as possible for subsequent analysis.

[0203] Calculate the power allocation ratio: Based on the collected historical power consumption data, calculate the power allocation ratio between the faulty branch and each target line.

[0204] The power distribution ratio can be determined by comparing the load data of each line, such as calculating the percentage or relative value of the load of each line.

[0205] In the calculation process, factors such as power flow distribution, load changes, and network losses of the power grid need to be considered.

[0206] Verification and Adjustment: Compare the calculated power distribution ratio with the actual measurement data to evaluate its accuracy and reliability.

[0207] If the calculation results are found to deviate significantly from the actual situation, the model needs to be adjusted and optimized, such as taking into account the automatic adjustment capability of the power grid and the action strategy of the protection device.

[0208] Application of Results: Based on the predicted power distribution ratio, develop reasonable fault handling plans, such as adjusting the power grid operation mode, disconnecting overloaded lines, and activating backup power sources.

[0209] At the same time, the power allocation ratio can be used as an important reference for power grid planning, design and operation and maintenance to improve the reliability and security of the power grid.

[0210] Step S240: Predict the electrical parameters of the target line based on the predicted load and the power allocation ratio.

[0211] In some exemplary embodiments, predicting the electrical parameters of the target line based on the predicted load and the power allocation ratio includes:

[0212] Based on the correspondence between the target line and the load point, the predicted load value of the load point corresponding to the target line is extracted from the predicted load.

[0213] For each target line, a predicted power consumption is obtained based on the predicted load value of the load point corresponding to the target line and the power distribution ratio, wherein the electrical parameters of the target line include the predicted power consumption.

[0214] In specific implementation, step S240 includes:

[0215] Data preparation:

[0216] Obtain the load values ​​predicted for each load point in step S220. These values ​​are typically given in the form of a time series or a specific time point.

[0217] Suppose there are n load points, and each load point has m predicted load values ​​at time points, forming an n×m matrix A, where A(i,j) represents the predicted load value of the i-th load point at the j-th time point.

[0218] Obtain the power allocation ratio in step S230. These ratios are usually determined based on factors such as historical data, load characteristics, and power grid structure.

[0219] Suppose there are n load points, each with a corresponding power allocation ratio, forming an n×1 vector B, where B(i) represents the power allocation ratio of the i-th load point.

[0220] Data processing:

[0221] Obtain the predicted load value of the load point corresponding to the target line:

[0222] Based on the correspondence between the target line and the load point, the predicted load value of the load point corresponding to the target line is extracted from matrix A.

[0223] Assuming the target line corresponds to k load points, a k×m matrix C is extracted, where C(i,j) represents the predicted load value of the i-th target load point at the j-th time point.

[0224] Calculate the predicted power consumption for each target line:

[0225] For each target line, the predicted power consumption is calculated based on the predicted load value and power distribution ratio of its corresponding load point.

[0226] For the i-th target line, its predicted power consumption can be calculated using the following formula:

[0227] Predicted energy i = Σ(C(i,j)×B(i) / ΣB)×Total energy

[0228] Where Σ(C(i,j)×B(i) / ΣB) represents the sum of the predicted load values ​​of the i-th target line at all time points, weighted according to the power distribution ratio, and the total power represents the predicted total power of the entire power grid or a specific area.

[0229] Wherein, ΣB represents the sum of the power distribution ratios of all load points, used for normalization.

[0230] Data consistency: Ensure that the data in S220 and S230 are consistent in time and space, that is, the predicted load value in S220 and the power distribution ratio in S230 should correspond to the same load point and time point.

[0231] Data accuracy: Verify and clean the data in S220 and S230 to ensure the accuracy and integrity of the data.

[0232] For abnormal or missing data, appropriate processing measures should be taken, such as interpolation, smoothing, or deletion.

[0233] Calculation accuracy: During the calculation process, pay attention to maintaining calculation accuracy and avoid the impact of rounding or truncation errors on the results.

[0234] High-precision computing tools or algorithms can be used to improve computing accuracy.

[0235] Result verification: Verify and compare the calculation results to ensure their reasonableness and accuracy.

[0236] The performance of the predictive model can be evaluated by comparing it with actual data or historical data.

[0237] Step S250: Based on the electrical parameters of the target line and the carrying capacity of the target line, predict the fault prediction result of the target line.

[0238] In some exemplary embodiments, predicting the fault prediction result of the target line based on the electrical parameters and the carrying capacity of the target line includes:

[0239] Based on the electrical parameters of the target line and the carrying capacity of the target line, the load rate of the target line is determined;

[0240] Using a pre-built fault prediction model, based on the historical fault data of the distribution network, the electrical parameters of the target line, the carrying capacity of the target line, and the load rate, the fault prediction result of the target line is predicted.

[0241] In practice, the electrical parameters of the target line are collected, including:

[0242] In the exemplary embodiments described above, the electrical parameters of the target line include the predicted electrical quantity, and may also include the line's rated voltage, rated current, resistance, inductance, capacitance, etc. These parameters can typically be obtained from the line's design documents, data provided by the manufacturer, or actual measurements.

[0243] In practical implementation, the carrying capacity of the target line should be determined, including:

[0244] Withstand capacity may include the line's maximum permissible current, maximum permissible temperature, and maximum permissible voltage drop. These withstand capacities are typically determined based on the line's specifications, materials, environmental conditions, and safety standards.

[0245] In practical implementation, the load rate of the target line is calculated, including:

[0246] Load factor can be calculated by comparing the predicted power consumption with the maximum allowable power consumption of the target line. For example, if the predicted power consumption is close to or exceeds the maximum allowable power consumption of the line, the load factor will be high, which may increase the chance of failure.

[0247] In practical implementation, a fault prediction model is applied, including:

[0248] Statistical methods, machine learning algorithms, or expert systems are used to build fault prediction models. These models can predict the probability of failure based on historical fault data, electrical parameters, tolerance, and other relevant factors. For example, algorithms such as logistic regression, decision trees, random forests, or neural networks can be used to train the models.

[0249] In practice, the model is validated and adjusted, including:

[0250] Use real or simulated data to validate the model's accuracy. Adjust and optimize the model based on the validation results to improve its predictive performance.

[0251] In practice, the prediction results are output, including:

[0252] Presenting forecasts in an easy-to-understand manner to relevant personnel, such as through charts, reports, or alarm systems, helps them take timely action to prevent or reduce failures.

[0253] As can be seen from the above, the distribution network cascading fault prediction method provided in this disclosure includes: acquiring detection data of the distribution network, analyzing the detection data, and determining the faulty branch in the distribution network; predicting the predicted load of each area in the distribution network based on a pre-constructed load prediction model of the distribution network; searching for target lines in the distribution network that are connected in parallel with the faulty branch based on a pre-constructed topological directed graph of the distribution network, and analyzing the power distribution ratio between the faulty branch and the target line based on historical power consumption data; predicting the electrical parameters of the target line based on the predicted load and the power distribution ratio; and predicting the fault prediction result of the target line based on the electrical parameters of the target line and the carrying capacity of the target line.

[0254] This disclosure reduces the computation of fault-free samples and shortens the prediction efficiency of cascading failures.

[0255] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0256] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0257] Based on the same inventive concept, corresponding to any of the above embodiments, this disclosure also provides a distribution network cascading fault prediction device.

[0258] refer to Figure 3 This is a schematic diagram of a distribution network cascading fault prediction device provided in an exemplary embodiment of the present disclosure.

[0259] The power distribution network cascading fault prediction device includes the following modules:

[0260] The fault branch location module 310 is configured to acquire detection data of the distribution network, analyze the detection data, and determine the fault branch in the distribution network.

[0261] The load forecasting module 320 is configured to forecast the load of each area in the distribution network based on a pre-built load forecasting model of the distribution network.

[0262] The power allocation ratio determination module 330 is configured to search for target lines in the distribution network that are connected in parallel with the faulty branch based on the pre-constructed topology directed graph of the distribution network, and analyze the power allocation ratio between the faulty branch and the target line based on historical power consumption data.

[0263] The electrical parameter determination module 340 is configured to predict the electrical parameters of the target line based on the predicted load and the power allocation ratio;

[0264] The fault prediction module 350 is configured to predict the fault prediction result of the target line based on the electrical parameters of the target line and the carrying capacity of the target line.

[0265] In some exemplary embodiments, the fault branch location module 310 is specifically configured as follows:

[0266] The detection data is acquired through sensors in the power distribution network;

[0267] The faulty branch is determined by performing threshold judgment, trend analysis and / or correlation analysis on the detection data.

[0268] In some exemplary embodiments, the load forecasting module 320 is specifically configured as follows:

[0269] Obtain historical load data and influencing factor data of the power distribution network;

[0270] A time series prediction model is trained based on the historical load data;

[0271] A regression model was trained based on the data of the aforementioned influencing factors;

[0272] The time series forecasting model and the regression model are fused to obtain the load forecasting model;

[0273] The predicted load of each area in the distribution network is predicted based on the load prediction model.

[0274] In some exemplary embodiments, the power allocation ratio determination module 330 is specifically configured as follows:

[0275] In the topological directed graph of the power distribution network, starting from the starting node and ending node of the faulty branch, the search is performed along the direction parallel to the faulty branch to obtain the target line;

[0276] Obtain historical electricity consumption data of the power distribution network, and analyze the power distribution ratio between the faulty branch and the target line based on the historical electricity consumption data.

[0277] In some exemplary embodiments, the electrical parameter determination module 340 is specifically configured as follows:

[0278] Based on the correspondence between the target line and the load point, the predicted load value of the load point corresponding to the target line is extracted from the predicted load.

[0279] For each target line, a predicted power consumption is obtained based on the predicted load value of the load point corresponding to the target line and the power distribution ratio, wherein the electrical parameters of the target line include the predicted power consumption.

[0280] In some exemplary embodiments, the fault prediction module 350 is specifically configured as follows:

[0281] Based on the electrical parameters of the target line and the carrying capacity of the target line, the load rate of the target line is determined;

[0282] Using a pre-built fault prediction model, based on the historical fault data of the distribution network, the electrical parameters of the target line, the carrying capacity of the target line, and the load rate, the fault prediction result of the target line is predicted.

[0283] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, in implementing this disclosure, the functions of each module can be implemented in one or more software and / or hardware.

[0284] The apparatus in the above embodiments is used to implement the corresponding distribution network cascading fault prediction method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0285] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the distribution network cascading fault prediction method described in any of the above embodiments.

[0286] Figure 4 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0287] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0288] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0289] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0290] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0291] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0292] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0293] The electronic devices described above are used to implement the corresponding distribution network cascading fault prediction method in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0294] The memory 1020 stores machine-readable instructions executable by the processor 1010. When the electronic device is running, the processor 1010 communicates with the memory 1020 via the bus 1030, causing the processor 1010 to execute the following instructions during operation:

[0295] Acquire detection data of the power distribution network, analyze the detection data, and determine the faulty branch in the power distribution network;

[0296] The predicted load of each area in the distribution network is predicted based on the pre-built load prediction model of the distribution network.

[0297] Based on the pre-constructed topology directed graph of the distribution network, search for target lines in the distribution network that are connected in parallel with the faulty branch, and analyze the power distribution ratio between the faulty branch and the target lines based on historical power consumption data.

[0298] The electrical parameters of the target line are predicted based on the predicted load and the power allocation ratio.

[0299] Based on the electrical parameters and the carrying capacity of the target line, the fault prediction result of the target line is predicted.

[0300] In one possible implementation, the instructions executed by processor 1010, including acquiring detection data of the distribution network, analyzing the detection data, and determining the faulty branch in the distribution network, include:

[0301] The detection data is acquired through sensors in the power distribution network;

[0302] The faulty branch is determined by performing threshold judgment, trend analysis and / or correlation analysis on the detection data.

[0303] In one possible implementation, the instructions executed by processor 1010, which predict the forecast load of each area in the distribution network based on a pre-built load forecasting model of the distribution network, include:

[0304] Obtain historical load data and influencing factor data of the power distribution network;

[0305] A time series prediction model is trained based on the historical load data;

[0306] A regression model was trained based on the data of the aforementioned influencing factors;

[0307] The time series forecasting model and the regression model are fused to obtain the load forecasting model;

[0308] The predicted load of each area in the distribution network is predicted based on the load prediction model.

[0309] In one possible implementation, the instructions executed by processor 1010, including searching for target lines in the distribution network that are connected in parallel with the faulty branch based on a pre-built directed graph of the distribution network topology, and analyzing the power distribution ratio between the faulty branch and the target lines based on historical power consumption data, include:

[0310] In the topological directed graph of the power distribution network, starting from the starting node and ending node of the faulty branch, the search is performed along the direction parallel to the faulty branch to obtain the target line;

[0311] Obtain historical electricity consumption data of the power distribution network, and analyze the power distribution ratio between the faulty branch and the target line based on the historical electricity consumption data.

[0312] In one possible implementation, the instructions executed by processor 1010, which include predicting the electrical parameters of the target line based on the predicted load and the power allocation ratio, include:

[0313] Based on the correspondence between the target line and the load point, the predicted load value of the load point corresponding to the target line is extracted from the predicted load.

[0314] For each target line, a predicted power consumption is obtained based on the predicted load value of the load point corresponding to the target line and the power distribution ratio, wherein the electrical parameters of the target line include the predicted power consumption.

[0315] In one possible implementation, the instruction executed by processor 1010, which includes predicting the fault prediction result of the target line based on the electrical parameters and the withstand capability of the target line, includes:

[0316] Based on the electrical parameters of the target line and the carrying capacity of the target line, the load rate of the target line is determined;

[0317] Using a pre-built fault prediction model, based on the historical fault data of the distribution network, the electrical parameters of the target line, the carrying capacity of the target line, and the load rate, the fault prediction result of the target line is predicted.

[0318] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the power distribution network cascading fault prediction method as described in any of the above embodiments.

[0319] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0320] The aforementioned non-transitory computer-readable storage media can be any available medium or data storage device that a computer can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0321] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the distribution network cascading fault prediction method as described in any of the embodiments in the exemplary method section above, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0322] Based on the same inventive concept, corresponding to the distribution network cascading fault prediction method described in any of the above embodiments, this disclosure also provides a computer program product, which includes computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer to cause the computer and / or the processor to execute the distribution network cascading fault prediction method. Corresponding to the execution entity for each step in each embodiment of the distribution network cascading fault prediction method, the processor executing the corresponding step can belong to the corresponding execution entity.

[0323] The computer program product of the above embodiments is used to enable the computer and / or the processor to execute the distribution network cascading fault prediction method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0324] Those skilled in the art will recognize that embodiments of this disclosure can be implemented as a system, method, or computer program product. Therefore, this disclosure can be implemented as entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this disclosure can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0325] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (not exhaustive) of a computer-readable storage medium may include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0326] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0327] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0328] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0329] It should be understood that each block of a flowchart and / or block diagram, as well as combinations of blocks in a flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine that, when executed by a computer or other programmable data processing device, creates means for implementing the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0330] These computer program instructions may also be stored in a computer-readable medium that enables a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable medium produce a product comprising an instruction apparatus that implements the functions / operations specified in the boxes of a flowchart and / or block diagram.

[0331] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable apparatus can provide a process for implementing the functions / operations specified in the boxes of a flowchart and / or block diagram.

[0332] Furthermore, although the operations of the methods of this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Rather, the steps depicted in the flowcharts may be executed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0333] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0334] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0335] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0336] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0337] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0338] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

[0339] While the spirit and principles of this disclosure have been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for convenience of expression. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the appended claims is to be interpreted in the broadest sense, thereby encompassing all such modifications and equivalent structures and functions.

Claims

1. A method for predicting cascading faults in a distribution network, characterized in that, include: Acquire detection data of the power distribution network, analyze the detection data, and determine the faulty branch in the power distribution network; The predicted load of each area in the distribution network is predicted based on the pre-built load prediction model of the distribution network. Based on the pre-constructed topology directed graph of the distribution network, search for target lines in the distribution network that are connected in parallel with the faulty branch, and analyze the power distribution ratio between the faulty branch and the target lines based on historical power consumption data. The electrical parameters of the target line are predicted based on the predicted load and the power allocation ratio. Based on the electrical parameters and the carrying capacity of the target line, the fault prediction result of the target line is predicted.

2. The method according to claim 1, characterized in that, The process of acquiring detection data from the distribution network, analyzing the detection data, and determining the faulty branch in the distribution network includes: The detection data is acquired through sensors in the power distribution network; The faulty branch is determined by performing threshold judgment, trend analysis and / or correlation analysis on the detection data.

3. The method according to claim 1, characterized in that, The prediction of the forecast load for each area in the distribution network based on the pre-built load forecasting model of the distribution network includes: Obtain historical load data and influencing factor data of the power distribution network; A time series prediction model is trained based on the historical load data; A regression model was trained based on the data of the aforementioned influencing factors; The time series forecasting model and the regression model are fused to obtain the load forecasting model; The predicted load of each area in the distribution network is predicted based on the load prediction model.

4. The method according to claim 1, characterized in that, The process of searching for target lines in the distribution network that are in parallel with the faulty branch based on a pre-constructed directed graph of the distribution network topology, and analyzing the power distribution ratio between the faulty branch and the target lines based on historical electricity consumption data, includes: In the topological directed graph of the power distribution network, starting from the starting node and ending node of the faulty branch, the search is performed along the direction parallel to the faulty branch to obtain the target line; Obtain historical electricity consumption data of the power distribution network, and analyze the power distribution ratio between the faulty branch and the target line based on the historical electricity consumption data.

5. The method according to claim 1, characterized in that, The prediction of the electrical parameters of the target line based on the predicted load and the power allocation ratio includes: Based on the correspondence between the target line and the load point, the predicted load value of the load point corresponding to the target line is extracted from the predicted load. For each target line, a predicted power consumption is obtained based on the predicted load value of the load point corresponding to the target line and the power distribution ratio, wherein the electrical parameters of the target line include the predicted power consumption.

6. The method according to claim 1, characterized in that, The method of predicting the fault prediction result of the target line based on its electrical parameters and its carrying capacity includes: Based on the electrical parameters of the target line and the carrying capacity of the target line, the load rate of the target line is determined; Using a pre-built fault prediction model, based on the historical fault data of the distribution network, the electrical parameters of the target line, the carrying capacity of the target line, and the load rate, the fault prediction result of the target line is predicted.

7. A distribution network cascading fault prediction device, characterized in that, include: The fault branch location module is configured to acquire detection data of the distribution network, analyze the detection data, and determine the fault branch in the distribution network. The load forecasting module is configured to forecast the load of each area in the distribution network based on a pre-built load forecasting model of the distribution network. The power allocation ratio determination module is configured to search for target lines in the distribution network that are connected in parallel with the faulty branch based on a pre-built directed graph of the distribution network topology, and analyze the power allocation ratio between the faulty branch and the target lines based on historical power consumption data. The electrical parameter determination module is configured to predict the electrical parameters of the target line based on the predicted load and the power allocation ratio; The fault prediction module is configured to predict the fault prediction result of the target line based on the electrical parameters of the target line and the carrying capacity of the target line.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer program instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 6.

Images