Method and device for determining fault area of power distribution network, equipment and medium

Abstract

The embodiment of the invention discloses a method, device and equipment for determining a fault area of a power distribution network and a medium, and the method comprises the steps: obtaining a current power parameter of power distribution network equipment and a network topology of a current power distribution network, and enabling network nodes in the network topology to represent the power distribution network equipment; inputting the current power parameter into a pre-trained fault model, and determining a direct fault node; determining an associated fault node of a direct fault node based on the connection relationship of the network nodes in the network topology and the direct fault node; and determining a fault area according to the direct fault node and the associated fault node. According to the technical scheme provided by the invention, when the power distribution network equipment fails, the fault area is accurately determined, the accuracy of determining the fault area is improved, and the safety of the power distribution network is ensured.

Description

Technical Field

[0001] The present invention relates to the field of fault detection, and in particular to a method, device, equipment and medium for determining a fault area of ​​a distribution network. Background Art

[0002] The distribution network is a network that supplies electricity to end users and residents, and is the main link in the power system's supply of electricity to users. The distribution network is at the end of the power system, with a wide geographical distribution, large grid scale, many types of equipment, diverse network connections, and variable operating modes, making the analysis of its operating status difficult and complex.

[0003] Furthermore, distribution network equipment is usually responsible for power tasks within a certain area. If a distribution network equipment fails, it will not only affect the power supply to all users in the area it covers, but different distribution network equipment are also associated with each other. Therefore, the failure of a distribution network equipment may also affect the normal operation of other distribution network equipment associated with it.

[0004] The current method of determining the fault area is to divide the fault range based on the feedback from each user after the fault. However, this method has a lag, the accuracy of determining the fault area is low, and it cannot guarantee the safety of residents' electricity use. Summary of the invention

[0005] The technical solution of the present invention provides a method, device, equipment and medium for determining the fault area of ​​a distribution network. Through the technical solution of the present invention, the fault area of ​​the distribution network can be accurately determined when the distribution network equipment fails, thereby improving power safety.

[0006] In a first aspect, an embodiment of the present invention provides a method for determining a fault area of ​​a distribution network, comprising:

[0007] Acquire current power parameters of the distribution network equipment and the network topology of the current distribution network, wherein the network nodes in the network topology represent the distribution network equipment;

[0008] Inputting the current power parameter into a pre-trained fault model to determine a direct fault node, wherein the fault model is used to predict whether the network node corresponding to the distribution network device is a direct fault node where a fault occurs based on the current power parameter;

[0009] Determine the associated fault nodes of the direct fault nodes based on the connection relationship of the network nodes and the direct fault nodes in the network topology, wherein the connection relationship includes a connection path and a connection range;

[0010] A fault area is determined according to the direct fault node and the associated fault nodes.

[0011] In a second aspect, an embodiment of the present invention provides a device for determining a fault area of ​​a distribution network, including:

[0012] An acquisition module, used to acquire current power parameters of the distribution network equipment and the network topology of the current distribution network, wherein the network nodes in the network topology represent the distribution network equipment;

[0013] A direct fault node determination module, used to input the current power parameters into a pre-trained fault model to determine the direct fault node, wherein the fault model is used to predict whether the network node corresponding to the distribution network equipment is a direct fault node where a fault occurs based on the current power parameters;

[0014] An associated fault node determination module, configured to determine an associated fault node of the direct fault node based on a connection relationship of the network nodes and a direct fault node in the network topology, wherein the connection relationship includes a connection path and a connection range;

[0015] The area determination module is used to determine the fault area according to the direct fault node and the associated fault nodes.

[0016] According to a third aspect, an electronic device includes:

[0017] at least one processor; and,

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining a fault area of ​​a distribution network as described in any one of the embodiments of the present invention.

[0020] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a distribution network fault area as described in any one of the embodiments of the present invention when executed.

[0021] The embodiment of the present invention provides a method, device, equipment and medium for determining the fault area of ​​a distribution network. The method includes: obtaining the current power parameters of the distribution network equipment and the network topology of the current distribution network, wherein the network nodes in the network topology represent the distribution network equipment; inputting the current power parameters into a pre-trained fault model to determine the direct fault node, wherein the fault model is used to predict whether the network node corresponding to the distribution network equipment is a direct fault node that has a fault according to the current power parameters; determining the associated fault nodes of the direct fault node based on the connection relationship of the network nodes and the direct fault nodes in the network topology, wherein the connection relationship includes a connection path and a connection range; determining the fault area according to the direct fault nodes and the associated fault nodes. Specifically, the fault model predicts the direct fault nodes in the current distribution network according to the current power parameters, and then the associated fault nodes that may cause faults due to the influence of the direct fault nodes can be determined through the connection relationship of the network nodes and the direct fault nodes in the network topology, and then the fault area can be determined according to the direct fault nodes and the associated fault nodes. Through the technical solution of the embodiment of the present invention, the fault area affected by the fault of the distribution network equipment can be accurately determined, the accuracy of the fault area determination is improved, and the power safety of the distribution network is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flow chart of a method for determining a fault area of ​​a distribution network provided in Embodiment 1 of the present invention;

[0024] Figure 2 A flow chart of a method for determining a distribution network fault area provided in Embodiment 2 of the present invention;

[0025] Figure 3 A device for determining a fault area of ​​a distribution network provided in Embodiment 3 of the present invention;

[0026] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0030] Embodiment 1

[0031] Figure 1 A flowchart of a method for determining a distribution network fault area provided in Embodiment 1 of the present invention can be applied to the situations of determining faults of distribution network equipment and determining the scope of fault impact. The method can be executed by a device for determining a distribution network fault area, which can be composed of software and / or hardware and configured in a computer or server.

[0032] like Figure 1 As shown, including:

[0033] Step 110: Acquire current power parameters of the distribution network equipment and the network topology of the current distribution network, wherein the network nodes in the network topology represent the distribution network equipment.

[0034] Among them, the distribution network equipment may include power supply stations, electric poles, transformers and other power devices. All the distribution network equipment together constitute the network nodes in the current distribution network. Network communication and power transmission can be carried out between the distribution network equipment. The network topology is a virtual topology network formed by the current distribution network. The network nodes in the network topology represent the distribution network equipment. The network communication and power transmission relationship between the distribution networks can constitute the path of each network node in the network topology. Among them, the current power parameter is the power parameter obtained within a preset time period, which is the input of the fault model use phase. The parameter type is the same as the target power parameter described in the embodiment of the present invention. If the target power parameter includes the voltage, current and resistance of the distribution network equipment, the current power parameter includes the voltage, current and resistance of the distribution network equipment within the preset time period. Further, the target power parameter is a parameter determined by the historical power parameter after principal component analysis. The target power parameter is an input parameter in the fault model training phase. By using the target power parameter and the current power parameter, the amount of calculation required for model training and use can be reduced.

[0035] Furthermore, the current power parameters can be obtained through a DTU (date transfer unit) preset on the distribution network. The DTU can be used to obtain data such as voltage, power and resistance of the distribution network equipment.

[0036] Specifically, the connection relationship between the distribution network devices can be determined through the network topology of the current distribution network, and then the current power parameters of the distribution network devices can be used to determine whether the distribution network devices are faulty and to judge the fault area of ​​the current distribution network.

[0037] Step 120: Input the current power parameters into a pre-trained fault model to determine a direct fault node, wherein the fault model is used to predict whether a network node corresponding to the distribution network equipment is a direct fault node where a fault occurs based on the current power parameters.

[0038] Among them, the fault model is used to predict whether the network node corresponding to the distribution network equipment is a direct fault node where a fault occurs based on the current power parameters. The direct fault node is obtained by the fault model through the current power parameter prediction. If the network node is a direct fault node, it means that the distribution network equipment represented by the network node fails due to abnormal power parameters.

[0039] The training method of the training model includes:

[0040] Acquire historical power parameters of the distribution network equipment and corresponding status identifiers, wherein the status identifier includes equipment failure or equipment normal.

[0041] Specifically, after obtaining the current power parameters, the current power parameters need to be preprocessed, such as identifying missing values, abnormal values, unifying data formats, and converting data types.

[0042] Among them, the historical power parameters are the power parameters of the distribution network equipment during its historical operation, which may include voltage, power, resistance, etc. It is necessary to determine the target power parameters from the historical power parameters to reduce the amount of calculation in the training process. The status identification includes equipment failure or equipment normal, which is used to characterize whether the power grid equipment is faulty.

[0043] Performing principal component analysis on the historical power parameters to obtain analysis results of the historical power parameters, and determining whether the historical power parameters are target power parameters according to the analysis results of the historical power parameters;

[0044] The principal component analysis is to perform feature analysis on historical power parameters (power data), thereby determining key parameters in the historical power parameters, and achieving dimensionality reduction of the historical power parameters and determination of parameter weights. Specifically, the principal component analysis includes:

[0045] Standardize data: standardize the data so that the mean of each feature is 0 and the standard deviation is 1; calculate the covariance matrix: find out the main change direction of the data through the covariance matrix; solve parameter weights and eigenvectors: calculate the parameter weights and eigenvectors of the covariance matrix; select principal components: according to the size of the parameter weights, select the principal components whose parameter weights exceed the predetermined threshold of 90%; construct a projection matrix: construct a projection matrix using the selected principal components; dimension reduction: project the original data into a new feature space to achieve data dimension reduction.

[0046] Furthermore, there may be parameters in the historical characteristic parameters that have little impact on the fault prediction results. The target power parameters are parameters determined after screening the historical power parameters. The target power parameters will play a key role in the fault prediction results. In this way, the number of training parameters can be reduced, thereby reducing the amount of data required for training.

[0047] Optionally, the analysis result of the historical power parameters includes parameter weights of the historical power parameters, and the historical power parameters whose parameter weights are greater than a preset weight threshold can be determined as target power parameters.

[0048] Through the fault model, the state prediction result of the distribution network equipment is determined according to the target power parameters; the prediction deviation is determined according to the state identification and state prediction result corresponding to the historical power parameters. If the prediction deviation meets the deviation condition, the training ends.

[0049] Among them, the state prediction result is whether the distribution network equipment corresponding to the historical power parameters is faulty, which can be represented by 1 or 0. Furthermore, the prediction deviation can be determined by the state identification corresponding to the historical power parameters and the state prediction result. Specifically, the prediction deviation can be a covariance calculation result. The prediction deviation can also be calculated by a preset error function, which is not limited here.

[0050] Optionally, the fault model may include a random forest model, wherein the random forest model includes a feature importance scoring formula:

[0051] importance(F) = average reduction in impurity / standard deviation;

[0052] Among them, F is the power parameter, the average reduced impurity represents the average contribution of feature F to the purity of the node in all decision trees, and the standard deviation represents the stability of the contribution.

[0053] Specifically, the key features can be determined by determining the feature importance of the power parameters, and then the feature screening can be completed.

[0054] Furthermore, the decision tree training formula for each tree in the random forest is: Where D is the data set and p is the relative frequency of the sample in the data set D.

[0055] Step 130: Determine the associated fault nodes of the direct fault nodes based on the connection relationship of the network nodes in the network topology and the direct fault nodes, wherein the connection relationship includes a connection path and a connection range.

[0056] Since the current distribution network is composed of multiple distribution network devices, the failure of a single distribution network device may cause a chain reaction, resulting in simultaneous or subsequent failure of multiple distribution network devices associated with it. Therefore, for fault detection of the distribution network, the direct fault node and the associated fault node should be determined at the same time to ensure timely discovery of the fault and improve the accuracy of fault area determination.

[0057] Among them, the associated fault node is a network node that has an associated fault due to the failure of the direct fault node, and the connection relationship includes a connection path and a connection range, wherein the connection path can be a communication path of an external distribution network equipment or a power transmission path (network path of the network topology), and the connection range can be a node hop range or a distance range.

[0058] Specifically, since the failure of distribution network equipment may be delayed, that is, a failure of a distribution network equipment may cause failures of other related distribution network equipment several hours later, in order to accurately determine the actual impact range of the failure, it is necessary not only to determine the direct fault node but also to determine the associated fault node. The method for determining the associated fault node can be found later.

[0059] Step 140: determine the fault area according to the direct fault node and the associated fault nodes.

[0060] The fault area is the area where the power supply is affected by the fault of the distribution network equipment represented by the direct fault node and the associated fault nodes.

[0061] Optionally, this step includes: determining the power coverage area of ​​the direct fault node and the associated fault nodes according to the power impact area of ​​the distribution network equipment;

[0062] The power coverage area is determined as a fault area.

[0063] The power impact area is the area where the distribution network equipment is responsible for power supply. If the distribution network equipment fails, the power impact area will be affected by the power. Furthermore, since both the direct fault node and the associated fault node will have a negative impact on the power supply in their power impact area, the power impact area of ​​the direct fault node and the associated fault node can be determined as the power coverage area, and then the power coverage area can be determined as the fault area.

[0064] Optionally, obtaining the number of faults in which the power impact area of ​​the distribution network equipment is a fault area within a set time interval;

[0065] The failure probability of the distribution network equipment is determined according to the number of failures, and the fault troubleshooting priority of the distribution network equipment is determined according to the failure probability.

[0066] Specifically, the set time interval can be a preset historical time interval, such as the past year or month. Furthermore, the failure probability of the distribution network equipment can be calculated by counting the number of failures and the number of non-failures in the power impact area of ​​the distribution network equipment, and then the fault troubleshooting priority of the distribution network equipment with a high failure probability can be set to a high priority, and then key troubleshooting can be carried out to prevent failures from occurring in advance and reduce the negative impact of power failures.

[0067] The embodiment of the present invention improves a method for determining a power grid fault area, the method comprising: obtaining current power parameters of a distribution network device and a network topology of the current distribution network, wherein the network nodes in the network topology represent the distribution network device; inputting the current power parameters into a pre-trained fault model to determine a direct fault node, wherein the fault model is used to predict whether the network node corresponding to the distribution network device is a direct fault node that has a fault according to the current power parameters; determining the associated fault nodes of the direct fault node based on the connection relationship of the network nodes in the network topology and the direct fault nodes, wherein the connection relationship includes a connection path and a connection range; determining the fault area according to the direct fault nodes and the associated fault nodes. Specifically, the fault model predicts the direct fault nodes in the current distribution network according to the current power parameters, and then the associated fault nodes that may cause a fault due to the influence of the direct fault nodes can be determined through the connection relationship of the network nodes in the network topology and the direct fault nodes, and then the fault area can be determined according to the direct fault nodes and the associated fault nodes. Through the technical solution of the embodiment of the present invention, the fault area affected by the fault of the distribution network device can be accurately determined, the accuracy of the fault area determination is improved, and the power safety of the distribution network is guaranteed.

[0068] Embodiment 2

[0069] Figure 2 This is a flow chart of a method for determining a fault area of ​​a distribution network provided in the second embodiment of the present invention. Based on the above embodiments, this embodiment of the present invention further defines a method for determining associated fault nodes.

[0070] like Figure 2 As shown, including:

[0071] Step 210: Acquire current power parameters of the distribution network equipment and the network topology of the current distribution network, wherein the network nodes in the network topology represent the distribution network equipment.

[0072] Step 220: Input the current power parameters into a pre-trained fault model to determine a direct fault node, wherein the fault model is used to predict whether the network node corresponding to the distribution network equipment is a direct fault node where a fault occurs based on the current power parameters.

[0073] Step 230: According to the network topology, determine a network node that has a unique path to the direct fault node as a first associated fault node.

[0074] The associated fault nodes include a first associated fault node and a second associated fault node.

[0075] Specifically, the network topology consists of network nodes and the edges between network nodes, wherein the edges between network nodes can be determined by the power transmission path between the distribution network equipment and / or the communication connection path of the distribution network equipment. There may be multiple reachable paths between different network nodes. Furthermore, if there is a unique path between network node A and direct fault node B, it means that the power supply of network node A is completely dependent on direct fault node B. If direct fault node B fails, network node A will also fail. Therefore, network node A can be determined as the first associated fault node.

[0076] Optionally, based on the actual troubleshooting scope requirements, the network node that is within a preset path threshold from the direct fault node can be determined as the first associated fault node. The embodiment of the present invention only describes the case where the preset path quantity threshold is 1 (unique path), and other quantities are not described in detail.

[0077] Step 240: According to the network topology, network nodes that are within a preset number of hops of the direct fault node and are not the first associated fault node are determined as candidate test nodes.

[0078] Specifically, the preset hop count may represent the distance between network nodes. For example, if the connection relationship between the network nodes is ABCD, the hop count between A and D is 3, and the hop count between A and C is 2.

[0079] Specifically, since the distribution network equipment will preferentially affect the network nodes that are closer to itself, the network nodes within a preset number of hops of the direct fault node and which are not the first associated fault nodes can be determined as candidate test nodes, and then the second associated fault nodes of the direct fault node can be determined from the candidate test nodes.

[0080] Step 250: Determine a second associated fault node from the candidate test nodes according to the current power parameters of the candidate test nodes.

[0081] Optionally, obtaining rated power parameters of the candidate test node;

[0082] If the deviation between the rated power parameter and the current power parameter is greater than a preset deviation threshold, the second candidate test node is determined as a second associated fault node.

[0083] Specifically, the rated power parameters are the power parameters when the distribution network equipment is working stably. The preset deviation threshold is used to determine the impact of the fault of the direct fault node on the power supply of the candidate test node. If the deviation between the rated power parameters of the candidate test node and the current power parameters is too large, the fault of the direct fault node has a great impact on the power supply of the candidate test node. The candidate fault node may be about to fail or has already failed. Therefore, it can be determined as the second associated fault node.

[0084] Step 260: determine the fault area according to the direct fault node and the associated fault nodes.

[0085] An embodiment of the present invention provides a method for determining a fault area of ​​a distribution network. Through the method of the embodiment of the present invention, a direct fault node where a fault occurs can be accurately predicted. At the same time, the associated fault nodes that may fail due to the influence of the direct fault node can be determined through the connection relationship of the network nodes in the network topology, thereby improving the accuracy of fault prediction of distribution network equipment. Furthermore, the accuracy of determining the fault area of ​​the distribution network can be improved through the fault areas of the direct fault node and the associated fault nodes, thereby ensuring power safety.

[0086] Embodiment 3

[0087] Figure 3 A device for determining a distribution network fault area provided in Embodiment 3 of the present invention is used to execute a method for determining a distribution network fault area in any one of the embodiments of the present invention, and the device includes:

[0088] An acquisition module 310 is used to acquire current power parameters of a distribution network device and a network topology of a current distribution network, wherein a network node in the network topology represents the distribution network device;

[0089] A direct fault node determination module 320 is used to input the current power parameter into a pre-trained fault model to determine a direct fault node, wherein the fault model is used to predict whether the network node corresponding to the distribution network device is a direct fault node where a fault occurs based on the current power parameter;

[0090] An associated fault node determination module 330 is used to determine an associated fault node of the direct fault node based on the connection relationship of the network nodes and the direct fault node in the network topology, wherein the connection relationship includes a connection path and a connection range;

[0091] The region determination module 340 is configured to determine a fault region according to the direct fault node and the associated fault nodes.

[0092] An embodiment of the present invention provides a device for determining a fault area of ​​a distribution network, which can accurately predict a direct fault node where a fault occurs. At the same time, the associated fault nodes that may fail due to the influence of the direct fault node can be determined through the connection relationship of the network nodes in the network topology, thereby improving the accuracy of fault prediction of distribution network equipment. Furthermore, the accuracy of determining the fault area of ​​the distribution network can be improved through the fault areas of the direct fault node and the associated fault nodes, thereby ensuring the safety of electricity use.

[0093] Optionally, the device for determining a distribution network fault area further includes: a training module, used to train the training model, the training module including:

[0094] An acquisition unit, configured to acquire historical power parameters and corresponding status identifiers of the distribution network equipment, wherein the status identifier includes equipment failure or equipment normal;

[0095] a target power parameter determination unit, configured to perform principal component analysis on the historical power parameter to obtain an analysis result of the historical power parameter, and determine whether the historical power parameter is a target power parameter according to the analysis result of the historical power parameter;

[0096] A prediction unit, configured to determine a state prediction result of the distribution network equipment according to the target power parameter through a fault model;

[0097] The circulation unit is used to determine the prediction deviation according to the state identification and state prediction result corresponding to the historical power parameter. If the prediction deviation meets the deviation condition, the training ends.

[0098] The analysis result of the historical power parameter includes a parameter weight of the historical power parameter. Specifically, the target power parameter determination unit is specifically configured to determine the historical power parameter whose parameter weight is greater than a preset weight threshold as the target power parameter.

[0099] Optionally, the associated fault node includes a first associated fault node and a second associated fault node, and the associated fault node determination module 330 includes:

[0100] Determining an associated fault node of the direct fault node based on a connection relationship of the network nodes in the network topology and the direct fault node includes:

[0101] A first determining unit, configured to determine, according to the network topology, a network node having a unique path to the direct fault node as a first associated fault node;

[0102] A candidate test node determination unit, configured to determine, according to the network topology, a network node within a preset number of hops of the direct fault node and not being the first associated fault node as a candidate test node;

[0103] The second associated fault node determining unit is used to determine a second associated fault node from the candidate test nodes according to the current power parameters of the candidate test nodes.

[0104] Specifically, the second associated fault node determination unit is specifically used to obtain the rated power parameters of the candidate test node;

[0105] If the deviation between the rated power parameter and the current power parameter is greater than a preset deviation threshold, the second candidate test node is determined as a second associated fault node.

[0106] Optionally, the region determination module 340 includes:

[0107] A power coverage area determination unit, configured to determine the power coverage area of ​​the direct fault node and the associated fault nodes according to the power impact area of ​​the distribution network equipment;

[0108] The fault area determining unit is used to determine the power coverage area as a fault area.

[0109] The fault area determination unit is specifically used to obtain the number of faults in which the power influence area of ​​the distribution network equipment is the fault area within a set time interval;

[0110] The failure probability of the distribution network equipment is determined according to the number of failures, and the fault troubleshooting priority of the distribution network equipment is determined according to the failure probability.

[0111] The device for determining a distribution network fault area provided in an embodiment of the present invention can execute the method for determining a distribution network fault area provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0112] Embodiment 4

[0113] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0114] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0115] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0116] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining a fault area of ​​a distribution network.

[0117] In some embodiments, the method for determining the fault area of ​​the distribution network may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the fault area of ​​the distribution network described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining the fault area of ​​the distribution network by any other appropriate means (e.g., by means of firmware).

[0118] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0119] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0120] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0121] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0123] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0124] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0125] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a fault area of ​​a distribution network, characterized in that: include: Acquire current power parameters of the distribution network equipment and the network topology of the current distribution network, wherein the network nodes in the network topology represent the distribution network equipment; Inputting the current power parameter into a pre-trained fault model to determine a direct fault node, wherein the fault model is used to predict whether the network node corresponding to the distribution network device is a direct fault node where a fault occurs based on the current power parameter; Determine the associated fault nodes of the direct fault nodes based on the connection relationship of the network nodes and the direct fault nodes in the network topology, wherein the connection relationship includes a connection path and a connection range; A fault area is determined according to the direct fault node and the associated fault nodes.

2. The method according to claim 1, characterized in that The training method of the training model includes: Acquire historical power parameters and corresponding status identifiers of the distribution network equipment, wherein the status identifier includes equipment failure or equipment normal; Performing principal component analysis on the historical power parameters to obtain analysis results of the historical power parameters, and determining whether the historical power parameters are target power parameters according to the analysis results of the historical power parameters; Determine the state prediction result of the distribution network equipment according to the target power parameter through the fault model; The prediction deviation is determined according to the state identification corresponding to the historical power parameter and the state prediction result. If the prediction deviation meets the deviation condition, the training ends.

3. The method according to claim 2, characterized in that The analysis result of the historical power parameter includes the parameter weight of the historical power parameter; The step of determining the target power parameter from the historical power parameter according to the analysis result of the historical power parameter comprises: The historical power parameter whose parameter weight is greater than a preset weight threshold is determined as the target power parameter.

4. The method according to claim 1, characterized in that: The associated fault nodes include a first associated fault node and a second associated fault node; Determining an associated fault node of the direct fault node based on a connection relationship of the network nodes in the network topology and the direct fault node includes: According to the network topology, determining a network node having a unique path to the direct fault node as a first associated fault node; According to the network topology, a network node within a preset number of hops of the direct fault node and not being the first associated fault node is determined as a candidate test node; According to the current power parameters of the candidate test nodes, a second associated fault node is determined from the candidate test nodes.

5. The method according to claim 4, characterized in that The step of determining a second associated fault node from the candidate test nodes according to the current power parameters of the candidate test nodes comprises: Obtaining rated power parameters of the candidate test nodes; If the deviation between the rated power parameter and the current power parameter is greater than a preset deviation threshold, the second candidate test node is determined as a second associated fault node.

6. The method according to claim 1, characterized in that The determining the fault area according to the direct fault node and the associated fault nodes includes: Determine the power coverage area of ​​the direct fault node and the associated fault nodes according to the power impact area of ​​the distribution network equipment; The power coverage area is determined as a fault area.

7. The method according to claim 6, characterized in that Also includes: Obtain the number of faults in which the power impact area of ​​the distribution network equipment is a fault area within a set time interval; The failure probability of the distribution network equipment is determined according to the number of failures, and the fault troubleshooting priority of the distribution network equipment is determined according to the failure probability.

8. A device for determining a fault area of ​​a distribution network, characterized in that: include: An acquisition module, used to acquire current power parameters of the distribution network equipment and the network topology of the current distribution network, wherein the network nodes in the network topology represent the distribution network equipment; A direct fault node determination module, used to input the current power parameters into a pre-trained fault model to determine the direct fault node, wherein the fault model is used to predict whether the network node corresponding to the distribution network equipment is a direct fault node where a fault occurs based on the current power parameters; An associated fault node determination module, configured to determine an associated fault node of the direct fault node based on a connection relationship of the network nodes and a direct fault node in the network topology, wherein the connection relationship includes a connection path and a connection range; The area determination module is used to determine the fault area according to the direct fault node and the associated fault nodes.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for determining a fault area of ​​a power distribution network according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a distribution network fault area according to any one of claims 1 to 7 when executed.

Images