A power distribution network fault early warning method and related device

Abstract

The application discloses a power distribution network fault early warning method and related device, the method comprises the following steps: acquiring network topology information, historical fault information and historical maintenance information of the power distribution network; determining the fault frequency and maintenance frequency of each network unit based on the network topology information, the historical fault information and the historical maintenance information; selecting the network unit with the fault frequency greater than the preset fault frequency threshold as the candidate fault unit, and selecting the network unit with the maintenance frequency greater than the preset maintenance frequency threshold as the candidate maintenance unit; correlating and discriminating each candidate fault unit and each candidate maintenance unit to obtain the correlation coefficient; calculating the early warning coefficient of each network unit according to the fault frequency, the maintenance frequency and the correlation coefficient; selecting the network unit with the early warning coefficient greater than the preset early warning threshold as the target early warning unit, generating and outputting the early warning information of the target early warning unit, which can effectively early warn the faults caused between the network units and improve the accuracy of the early warning result.

Description

Technical Field

[0001] This invention relates to the field of power distribution network technology, and in particular to a fault early warning method and related device for power distribution networks. Background Technology

[0002] Currently, with the development of technology, the power industry is becoming increasingly integrated into people's lives. For power users, the stability of the distribution network is crucial to the quality of electricity supply. However, due to the large number of devices and the high complexity of the distribution network, it is more prone to failure.

[0003] For power maintenance departments, the failure frequency of each network unit can provide early warnings for units in the distribution network, allowing for targeted deployment of maintenance resources.

[0004] However, the causes of faults in distribution networks are complex. Faults in network units are not necessarily caused by their own faults, and faults can also be caused by the interaction between network units. Existing early warning methods cannot predict such faults, which affects the accuracy of the early warning results and fails to effectively reduce the probability of fault occurrence. Summary of the Invention

[0005] This invention provides a fault early warning method and related device for power distribution networks, which solves the technical problem that existing early warning methods cannot predict faults caused between network units, thus affecting the accuracy of early warning results and failing to effectively reduce the probability of fault occurrence.

[0006] This invention provides a fault early warning method for a power distribution network, the method comprising:

[0007] The network topology information, historical fault information, and historical maintenance information of the distribution network are acquired; the distribution network includes multiple network units.

[0008] The fault frequency and maintenance frequency of each network unit are determined based on the network topology information, the historical fault information, and the historical maintenance information.

[0009] Network units with a failure frequency greater than a preset failure frequency threshold are selected as candidate failure units, and network units with a maintenance frequency greater than a preset maintenance frequency threshold are selected as candidate maintenance units.

[0010] The correlation coefficient is obtained by performing correlation determination on each of the candidate fault units and each of the candidate maintenance units;

[0011] Calculate the early warning coefficient for each network unit based on the fault frequency, the maintenance frequency, and the correlation coefficient;

[0012] Network units with warning coefficients greater than preset warning thresholds are selected as target warning units, and warning information of the target warning units is generated and output.

[0013] Optionally, before the step of determining the fault frequency and maintenance frequency of each network element based on the network topology information, the historical fault information, and the historical maintenance information, the method includes:

[0014] In response to fault feedback requests from the distribution network, obtain information on pending faults in the distribution network;

[0015] When the status of the pending fault information changes to processed, the updated historical fault information is obtained.

[0016] Optionally, before the step of determining the fault frequency and maintenance frequency of each network element based on the network topology information, the historical fault information, and the historical maintenance information, the method further includes:

[0017] In response to a request to update historical maintenance information of the distribution network, the update time of the historical maintenance information is obtained;

[0018] If a fault occurs in the distribution network within a preset time period after the update time, the updated historical maintenance information and historical fault information are obtained.

[0019] If no fault occurs in the distribution network within a preset time period after the update time, the updated historical maintenance information is obtained.

[0020] Optionally, the step of determining the association coefficient between each candidate fault unit and each candidate maintenance unit includes:

[0021] The load overlap ratio of each candidate fault unit and each candidate maintenance unit is calculated to obtain the unit overlap coefficient.

[0022] Based on the fault cause information of the candidate fault units, data is extracted from the preset fault level table to determine the fault level coefficient of each candidate fault unit.

[0023] Based on the unit overlap coefficient and the fault level coefficient, the correlation coefficient between each candidate fault unit and each candidate maintenance unit is calculated.

[0024] Optionally, the step of extracting data from a preset fault level table based on the fault cause information of the candidate fault units and determining the fault level coefficient of each candidate fault unit includes:

[0025] The fault cause information of the candidate fault units is divided into a set of faults caused by equipment and a set of faults caused by non-equipment.

[0026] Based on the preset fault level table, extract the equipment cause fault level coefficient corresponding to the equipment cause fault set and the non-equipment cause fault level coefficient corresponding to the non-equipment cause fault set.

[0027] The first level coefficient of the equipment cause failure set is determined by using all the equipment cause failure level coefficients described above.

[0028] The second level coefficient of the non-equipment cause fault set is determined by pre-setting environmental coefficients and all the non-equipment cause fault level coefficients;

[0029] The maximum value between the first level coefficient and the second level coefficient is selected as the fault level coefficient of the candidate fault unit.

[0030] Optionally, the warning coefficient is:

[0031]

[0032] In the formula: Q i Let be the early warning coefficient of network unit i, α be the fault frequency of network unit i, and β be the maintenance frequency of network unit i. Let be the correlation coefficient between network unit i and network unit τ, and U represent the set of all network units in the distribution network.

[0033] The present invention also provides a fault early warning device for a power distribution network, comprising:

[0034] The information acquisition module is used to acquire network topology information, historical fault information, and historical maintenance information of the distribution network; the distribution network includes multiple network units;

[0035] A frequency determination module is used to determine the fault frequency and maintenance frequency of each network unit based on the network topology information, the historical fault information, and the historical maintenance information.

[0036] The candidate unit selection module is used to select network units with a fault frequency greater than a preset fault frequency threshold as candidate fault units, and to select network units with a maintenance frequency greater than a preset maintenance frequency threshold as candidate maintenance units.

[0037] The association discrimination module is used to perform association discrimination between each of the candidate fault units and each of the candidate maintenance units to obtain the association coefficient;

[0038] The early warning coefficient calculation module is used to calculate the early warning coefficient of each network unit based on the fault frequency, the maintenance frequency and the correlation coefficient;

[0039] The early warning information output module is used to select network units with an early warning coefficient greater than a preset early warning threshold as target early warning units, and generate and output early warning information of the target early warning units.

[0040] Optionally, the association discrimination module includes:

[0041] The unit overlap coefficient calculation submodule is used to calculate the load overlap between each of the candidate fault units and each of the candidate maintenance units to obtain the unit overlap coefficient.

[0042] The fault level coefficient determination submodule is used to extract data from a preset fault level table based on the fault cause information of the candidate fault units, and determine the fault level coefficient of each candidate fault unit.

[0043] The correlation coefficient calculation submodule is used to calculate the correlation coefficient between each candidate fault unit and each candidate maintenance unit based on the unit overlap coefficient and the fault level coefficient.

[0044] The present invention also provides an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the fault early warning method for the power distribution network is run.

[0045] The present invention also provides a storage medium storing a computer program thereon, wherein the computer program, when executed by the processor, runs the aforementioned fault early warning method for the power distribution network.

[0046] As can be seen from the above technical solutions, the present invention has the following advantages:

[0047] This invention acquires network topology information, historical fault information, and historical maintenance information of a distribution network. The distribution network comprises multiple network units. Based on the network topology information, historical fault information, and historical maintenance information, the fault frequency and maintenance frequency of each network unit are determined. Network units with fault frequencies greater than a preset fault frequency threshold are selected as candidate fault units, and network units with maintenance frequencies greater than a preset maintenance frequency threshold are selected as candidate maintenance units. Correlation is determined between each candidate fault unit and each candidate maintenance unit to obtain a correlation coefficient. Based on the fault frequency, maintenance frequency, and correlation coefficient, a warning coefficient for each network unit is calculated. Network units with warning coefficients greater than a preset warning threshold are selected as target warning units, and warning information for the target warning units is generated and output. This invention predicts the relationship between the current maintenance resource layout and the fault frequency, incorporating the influence of the effectiveness of maintenance resource layout into the warning judgment process. The output warning information for the target warning units is more referential, thus solving the technical problem that existing warning methods cannot warn of faults caused between network units, thereby affecting the accuracy of warning results and failing to effectively reduce the probability of fault occurrence. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Please see Figure 1 , Figure 1 A flowchart illustrating the steps of a fault early warning method for a power distribution network provided in an embodiment of the present invention;

[0050] Please see Figure 2 , Figure 2 A flowchart illustrating the steps of a fault early warning method for a power distribution network, provided as an optional embodiment of the present invention;

[0051] Please see Figure 3 , Figure 3 A structural block diagram of a fault early warning device for a power distribution network provided in an embodiment of the present invention;

[0052] Please see Figure 4 , Figure 4 This is a structural diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0053] This invention provides a fault early warning method and system for power distribution networks, which addresses the technical problem that existing early warning methods cannot predict faults caused between network units, thus affecting the accuracy of early warning results and failing to effectively reduce the probability of fault occurrence.

[0054] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0055] Please see Figure 1 , Figure 1 A flowchart illustrating the steps of a fault early warning method for a power distribution network provided in an embodiment of the present invention.

[0056] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology; wherein, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results;

[0057] Artificial intelligence foundational technologies generally include technologies such as sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics; artificial intelligence software technologies mainly include computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0058] The fault early warning method provided in this application can be applied to a terminal or a server, or it can be software running on a terminal or a server. The terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides 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, and big data and artificial intelligence platforms; the software can be an application that implements the fault early warning method for power distribution networks, etc., but is not limited to the above forms.

[0059] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations, such as: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.; this application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network; in distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0060] This invention provides a fault early warning method for a power distribution network, the method comprising:

[0061] Step 101: Obtain network topology information, historical fault information, and historical maintenance information of the distribution network; the distribution network includes multiple network units.

[0062] In this embodiment of the application, a network unit represents a distribution network node, network topology information includes the topology information of all network units, historical fault information represents the fault information of all network units within a certain period, and historical maintenance information represents the maintenance information of all network units within a certain period.

[0063] It is understood that there are various ways to obtain the above information, such as calling it from the interface of the power distribution network monitoring system or manually inputting it. Those skilled in the art can determine the specific information acquisition method according to the actual situation, and this application does not limit it in this regard.

[0064] In particular, due to the complexity of power distribution maintenance and the different maintenance requirements, some network units may only require periodic maintenance, while others require specific maintenance measures within a certain period after a fault occurs. Based on this, the historical maintenance information of the power distribution network obtained in this application includes periodic maintenance or inspection of network units and maintenance measures implemented within a certain period when a network unit has a problem but has not yet failed or has failed, but does not include emergency repairs after a network unit fails. Therefore, for a network unit, the corresponding number of maintenance operations should be greater than the number of faults.

[0065] Step 102: Determine the fault frequency and maintenance frequency of each network unit based on network topology information, historical fault information, and historical maintenance information.

[0066] It should be noted that the failure frequency of each network unit can be determined based on network topology information and historical fault information, and the maintenance frequency of each network unit can be determined based on network topology information and historical maintenance information.

[0067] For example, network unit A has a sub-network unit B. Network unit B experiences 2 failures and 4 maintenance cycles within N months, while network unit A experiences 1 failure and 4 maintenance cycles within N months. Therefore, the failure frequency of network unit B is 2 / N times per month, and the maintenance frequency is 4 / N times per month; the failure frequency of network unit A is 1 / N times per month, and the maintenance frequency is 4 / N times per month.

[0068] The frequency time unit corresponding to the above-mentioned fault frequency and maintenance frequency can be N times per year or N times per month. The specific time setting can be selected according to the actual application. At the same time, if there are decimals when calculating the frequency, in order to improve the subsequent calculation accuracy and the calculation efficiency of the server or terminal, the time unit can be converted to an integer, thereby reducing the impact of decimals.

[0069] Step 103: Select network units with a fault frequency greater than a preset fault frequency threshold as candidate fault units, and select network units with a maintenance frequency greater than a preset maintenance frequency threshold as candidate maintenance units.

[0070] It should be noted that after obtaining the fault frequency and maintenance frequency of the network unit, the fault frequency of the network unit is compared with the preset fault frequency threshold, and the maintenance frequency of the network unit is compared with the preset maintenance frequency. Network units with a fault frequency greater than the preset fault frequency threshold are selected as candidate fault units, and network units with a maintenance frequency greater than the preset maintenance frequency threshold are selected as candidate maintenance units.

[0071] Step 104: Assess the correlation between each candidate fault unit and each candidate maintenance unit to obtain the correlation coefficient.

[0072] In this embodiment of the application, by performing association discrimination between each candidate fault unit and each candidate maintenance unit, the obtained association coefficient can determine whether there is a causal relationship between the fault and the maintenance; specifically, the feature information of the candidate fault unit and the candidate maintenance unit can be extracted, and the similarity between the feature information of the two can be calculated as a technical means of association discrimination.

[0073] Step 105: Calculate the early warning coefficient for each network unit based on the fault frequency, maintenance frequency, and correlation coefficient.

[0074] It should be noted that the early warning degree is calculated based on the failure frequency, maintenance frequency and correlation coefficient of the network unit to obtain the early warning coefficient. This coefficient is then used to predict the relationship between the current maintenance resource deployment and the failure frequency, thus incorporating the effective influencing factors of maintenance resource deployment into the early warning judgment process.

[0075] Since the correlation coefficient represents the relationship between candidate fault units and candidate maintenance units, the early warning coefficient actually represents the relationship between a network unit and all other network units. For example, network unit A calculates its early warning degree based on its own fault frequency, maintenance frequency, and the correlation coefficient between network unit A and network unit B. The impact of network unit B's fault or maintenance on network unit A is quantified through the correlation coefficient between A and B, and the sub-coefficient of B on A is obtained. Furthermore, the early warning coefficient of network unit A is obtained through all the sub-coefficients.

[0076] Step 106: Select network units with a warning coefficient greater than the preset warning threshold as target warning units, and generate and output the warning information of the target warning units.

[0077] It should be noted that the warning information output by the target warning unit includes the maintenance information and the proportion of fault types of the target warning unit. The staff then arrange maintenance resources for the target warning unit based on the output warning information, thereby reducing the probability of power distribution network faults.

[0078] This application provides a fault early warning method for a distribution network, including acquiring network topology information, historical fault information, and historical maintenance information of the distribution network; the distribution network includes multiple network units; determining the fault frequency and maintenance frequency of each network unit based on the network topology information, historical fault information, and historical maintenance information; selecting network units with fault frequencies greater than a preset fault frequency threshold as candidate fault units, and selecting network units with maintenance frequencies greater than a preset maintenance frequency threshold as candidate maintenance units; performing correlation discrimination between each candidate fault unit and each candidate maintenance unit to obtain a correlation coefficient; calculating the early warning coefficient of each network unit based on the fault frequency, maintenance frequency, and correlation coefficient; selecting network units with early warning coefficients greater than a preset early warning threshold as target early warning units, generating and outputting early warning information for the target early warning units, thereby achieving effective early warning of faults caused between network units, improving the accuracy of early warning results, and effectively reducing the probability of fault occurrence.

[0079] Please see Figure 2 , Figure 2 The flowchart illustrates the steps of a fault early warning method for a power distribution network, as provided in an optional embodiment of the present invention.

[0080] This invention provides a fault early warning method for a power distribution network, the method comprising:

[0081] Step 201: Obtain network topology information, historical fault information, and historical maintenance information of the distribution network; the distribution network includes multiple network units.

[0082] In this embodiment of the application, the specific implementation process of step 201 is similar to that of step 101, and will not be repeated here.

[0083] Step 202: Determine the fault frequency and maintenance frequency of each network unit based on network topology information, historical fault information, and historical maintenance information.

[0084] It should be noted that before executing step 202, the process includes: responding to a fault feedback request from the distribution network and obtaining information on pending faults in the distribution network; when the status of the pending fault information changes to "processed", obtaining updated historical fault information.

[0085] Specifically, when a fault occurs in the distribution network system, the distribution network monitoring system receives fault feedback and obtains information on faults to be processed. The distribution department will then carry out emergency repairs based on this information. The status of these faults is monitored, and when the status is "processed," the information is updated to historical fault information. For a particular network unit, if the fault frequency was insufficient before the fault occurred, but became sufficient afterward, the network unit's fault frequency will affect subsequent early warning judgments. Therefore, it is necessary to increase the priority of fault information and obtain the latest historical fault information. By responding to updates to historical fault information, the impact of the network unit's fault frequency threshold on the accuracy of early warning information is weakened, improving the accuracy of early warnings and the effectiveness of resource allocation.

[0086] Before performing step 202, the method further includes: responding to the historical maintenance information update request of the distribution network, obtaining the update time of the historical maintenance information; within a preset time length after the update time, if a fault occurs in the distribution network, obtaining the updated historical maintenance information and historical fault information; within a preset time length after the update time, if no fault occurs in the distribution network, obtaining the updated historical maintenance information.

[0087] Specifically, since historical maintenance information needs to be uploaded by maintenance personnel, due to various factors, maintenance personnel may be able to upload it to the system a certain time later than scheduled. For a certain network unit, before this maintenance, the maintenance frequency of the network unit was not sufficient to identify the network unit as a candidate maintenance unit. After this maintenance, the maintenance frequency is sufficient to identify the network unit as a candidate maintenance unit. Whether a network unit is identified as a candidate maintenance unit will also affect the subsequent early warning judgment. Therefore, after responding to the maintenance update, it is necessary to obtain the maintenance update time. Starting from the update time, a certain buffer space should be given to maintenance personnel to upload maintenance information, thereby reducing the impact of incomplete maintenance information.

[0088] Furthermore, within a preset time period after the update time, historical fault information is updated. That is, after the current period of maintenance has elapsed, a network unit in the distribution network experiences a fault. When the historical fault information is updated, the subsequent uploaded maintenance information will weaken the impact of this fault and reduce the accuracy of the early warning. To avoid this situation affecting the subsequent allocation of maintenance resources, this historical fault information needs to be included in the execution process of the current early warning method and the buffering wait needs to be stopped. If the distribution network does not report a fault within the preset time period, it proves that the distribution network is stable. Furthermore, by extending the collection of historical maintenance information by the preset time period, the completeness of historical maintenance information and the accuracy of the early warning are improved.

[0089] It is understandable that if historical fault information is updated during the execution of step 202, the updated historical fault information will not be used as historical fault information in the current method execution, but will be used as historical fault information in the next method execution.

[0090] Step 203: Select network units with a fault frequency greater than a preset fault frequency threshold as candidate fault units, and select network units with a maintenance frequency greater than a preset maintenance frequency threshold as candidate maintenance units.

[0091] In an optional embodiment of this application, by setting a preset fault frequency threshold and a preset maintenance frequency threshold, the targeting of the target determination is improved. Candidate units are filtered out by the threshold, the number of targets is reduced and the target prediction accuracy is improved, thereby improving the effectiveness of the allocation of distribution network maintenance resources.

[0092] Step 204: Calculate the load overlap between each candidate fault unit and each candidate maintenance unit to obtain the unit overlap coefficient.

[0093] Specifically, the unit overlap coefficient refers to the degree of equipment overlap between the candidate fault unit and the candidate maintenance unit. The higher the unit overlap coefficient, the higher the load overlap between the equipment associated with the candidate fault unit and the equipment associated with the candidate maintenance unit. When the unit overlap coefficient is 100%, it indicates that the candidate fault unit and the candidate maintenance unit are the same network unit.

[0094] In simple network conditions, the similarity of the number of devices that overlap between candidate fault units and candidate maintenance units can be compared, and the ratio can be used as the unit overlap coefficient to improve computational efficiency.

[0095] Step 205: Extract data from the preset fault level table based on the fault cause information of the candidate fault units, and determine the fault level coefficient of each candidate fault unit.

[0096] It should be noted that the fault severity coefficient indicates the degree to which a candidate maintenance unit causes a candidate fault unit to fail.

[0097] In an optional embodiment of this application, step 205 includes the following steps:

[0098] Step S1: Divide the fault cause information of the candidate fault units into a set of faults caused by equipment and a set of faults caused by non-equipment.

[0099] It should be noted that there should be multiple causes of failure for candidate fault units. These multiple causes should be classified into a set of faults caused by equipment and a set of faults caused by non-equipment.

[0100] Step S2: Based on the preset fault level table, extract the equipment cause fault level coefficient corresponding to the equipment cause fault set and the non-equipment cause fault level coefficient corresponding to the non-equipment cause fault set.

[0101] Step S3: Determine the first level coefficient of the equipment cause failure set by using all equipment cause failure level coefficients;

[0102] Specifically, after extracting all equipment cause failure level coefficients, the first level coefficient of the equipment cause failure set is determined by adding all the equipment cause failure level coefficients together. Each equipment cause failure set has a unique first level coefficient.

[0103] Step S4: Determine the second level coefficient of the non-equipment cause fault set by using preset environmental coefficients and all non-equipment cause fault level coefficients;

[0104] It should be noted that since some network units are located in harsh environments, failures caused by environmental factors are unavoidable. The preset environmental coefficient here represents the severity of the environment in which the network unit is located. By introducing the preset environmental coefficient, the comprehensiveness of the target early warning unit and the accuracy of the early warning are improved. The equipment cause failure set has a unique second-level coefficient.

[0105] Step S5: Select the maximum value between the first-level coefficient and the second-level coefficient as the fault level coefficient of the candidate fault unit.

[0106] It should be noted that by setting the first-level coefficient and the second-level coefficient, the effect of the parameter influence of a certain type of fault can be improved, so that the warning results are biased towards the target warning unit that is prone to failure caused by equipment or the target warning unit that is prone to failure caused by non-equipment. This improves the differentiation of the warning judgment results, makes the attributes between the target warning units more similar, and improves the purpose bias and accuracy of the warning.

[0107] Step 206: Calculate the correlation coefficient between each candidate fault unit and each candidate maintenance unit based on the unit overlap coefficient and the fault level coefficient.

[0108] It should be noted that after obtaining the unit overlap coefficient and the fault level coefficient, the correlation coefficient between each candidate fault unit and each candidate maintenance unit is obtained by multiplying the unit overlap coefficient and the fault level coefficient.

[0109] Furthermore, by using the unit overlap coefficient and the fault level coefficient, candidate fault units and candidate maintenance units are linked together along the fault dimension, thereby introducing the causal factor of "fault-maintenance" into the subsequent early warning coefficient calculation and improving the accuracy of the early warning.

[0110] Understandably, when a network unit is neither a candidate fault unit nor a candidate maintenance unit, the correlation coefficient of that network unit should be 0.

[0111] Step 207: Calculate the early warning coefficient for each network unit based on the fault frequency, maintenance frequency, and correlation coefficient.

[0112] The formula for calculating the early warning coefficient is as follows:

[0113]

[0114] In the formula: Q i Let be the early warning coefficient of network unit i, α be the fault frequency of network unit i, and β be the maintenance frequency of network unit i. Let be the correlation coefficient between network unit i and network unit τ, and U represent the set of all network units in the distribution network.

[0115] Step 208: Select network units with a warning coefficient greater than the preset warning threshold as target warning units, and generate and output the warning information of the target warning units.

[0116] This application optionally provides a method for early warning of distribution network faults, including acquiring network topology information, historical fault information, and historical maintenance information of the distribution network; the distribution network includes multiple network units; determining the fault frequency and maintenance frequency of each network unit based on the network topology information, historical fault information, and historical maintenance information; selecting network units with fault frequencies greater than a preset fault frequency threshold as candidate fault units, and selecting network units with maintenance frequencies greater than a preset maintenance frequency threshold as candidate maintenance units; calculating the load overlap between each candidate fault unit and each candidate maintenance unit to obtain the unit overlap coefficient; extracting data from a preset fault level table based on the fault cause information of the candidate fault units to determine the fault level coefficient of each candidate fault unit; calculating the correlation coefficient between each candidate fault unit and each candidate maintenance unit based on the unit overlap coefficient and the fault level coefficient; calculating the early warning coefficient of each network unit based on the fault frequency, maintenance frequency, and correlation coefficient; selecting network units with early warning coefficients greater than a preset early warning threshold as target early warning units, generating and outputting early warning information for the target early warning units, thereby providing effective early warning for faults caused between network units, improving the accuracy of early warning results, and effectively reducing the probability of fault occurrence.

[0117] Please see Figure 3 , Figure 3 This is a structural block diagram of a fault early warning device for a power distribution network provided in an embodiment of the present invention.

[0118] The present invention also provides a fault early warning system for a power distribution network, comprising:

[0119] Information acquisition module 301 is used to acquire network topology information, historical fault information and historical maintenance information of the distribution network; the distribution network includes multiple network units;

[0120] The frequency determination module 302 is used to determine the fault frequency and maintenance frequency of each network unit based on network topology information, historical fault information and historical maintenance information;

[0121] The candidate unit selection module 303 is used to select network units with a fault frequency greater than a preset fault frequency threshold as candidate fault units, and to select network units with a maintenance frequency greater than a preset maintenance frequency threshold as candidate maintenance units.

[0122] The correlation discrimination module 304 is used to perform correlation discrimination between each candidate fault unit and each candidate maintenance unit to obtain the correlation coefficient;

[0123] The early warning coefficient calculation module 305 is used to calculate the early warning coefficient of each network unit based on the fault frequency, maintenance frequency and correlation coefficient.

[0124] The early warning information output module 306 is used to select network units with an early warning coefficient greater than a preset early warning threshold as target early warning units, and generate and output early warning information of the target early warning units.

[0125] The device also includes:

[0126] The fault response module is used to respond to fault feedback requests from the distribution network and obtain information on pending faults in the distribution network.

[0127] The first acquisition module is used to acquire updated historical fault information when the status of the fault information to be processed changes to processed.

[0128] The device also includes:

[0129] The maintenance response module is used to respond to requests for updating historical maintenance information of the distribution network and obtain the update time of the historical maintenance information.

[0130] The second acquisition module is used to acquire updated historical maintenance information and historical fault information if a fault occurs in the distribution network within a preset time period after the update time.

[0131] The third acquisition module is used to acquire updated historical maintenance information if no fault occurs in the distribution network within a preset time period after the update time.

[0132] The association discrimination module includes:

[0133] The unit overlap coefficient calculation submodule is used to calculate the load overlap between each candidate fault unit and each candidate maintenance unit to obtain the unit overlap coefficient.

[0134] The fault level coefficient determination submodule is used to extract data from the preset fault level table based on the fault cause information of the candidate fault units and determine the fault level coefficient of each candidate fault unit.

[0135] The correlation coefficient calculation submodule is used to calculate the correlation coefficient between each candidate fault unit and each candidate maintenance unit based on the unit overlap coefficient and the fault level coefficient.

[0136] The fault level coefficient determination subunit is specifically used for:

[0137] The fault cause information of candidate fault units is divided into a set of faults caused by equipment and a set of faults caused by non-equipment.

[0138] Based on the preset fault level table, extract the equipment cause fault level coefficients corresponding to the equipment cause fault set and the non-equipment cause fault level coefficients corresponding to the non-equipment cause fault set.

[0139] The first level coefficient of the equipment cause failure set is determined by using all equipment cause failure level coefficients.

[0140] The second-level coefficient of the non-equipment cause fault set is determined by preset environmental coefficients and all non-equipment cause fault level coefficients.

[0141] The maximum value between the first-level coefficient and the second-level coefficient is selected as the fault level coefficient of the candidate fault unit.

[0142] This application provides a fault early warning system for a distribution network, comprising: an information acquisition module for acquiring network topology information, historical fault information, and historical maintenance information of the distribution network; the distribution network includes multiple network units; a frequency determination module for determining the fault frequency and maintenance frequency of each network unit based on the network topology information, historical fault information, and historical maintenance information; a candidate unit selection module for selecting network units with fault frequencies greater than a preset fault frequency threshold as candidate fault units and selecting network units with maintenance frequencies greater than a preset maintenance frequency threshold as candidate maintenance units; an association discrimination module for performing association discrimination between each candidate fault unit and each candidate maintenance unit to obtain an association coefficient; an early warning coefficient calculation module for calculating the early warning coefficient of each network unit based on the fault frequency, maintenance frequency, and association coefficient; and an early warning information output module for selecting network units with early warning coefficients greater than a preset early warning threshold as target early warning units, generating and outputting early warning information for the target early warning units, thereby achieving effective early warning of faults caused between network units, improving the accuracy of early warning results, and effectively reducing the probability of fault occurrence.

[0143] Please see Figure 4 This application also provides an electronic device 900, which includes a processor 901 and a memory 902;

[0144] Memory 902 is used to store program code and transfer program code to processor 901;

[0145] The processor 901 is used to execute the fault early warning method for the power distribution network in the above method embodiment according to the instructions in the program code;

[0146] Furthermore, the memory 902 can be implemented in the form of read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM); the memory 902 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 902 and is called and executed by the processor 901.

[0147] The processor 901 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 application.

[0148] The input / output interface 903 is used to implement information input and output;

[0149] The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0150] Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904);

[0151] The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0152] This application also provides a computer-readable storage medium for storing program code for executing the fault early warning method for the power distribution network in the above method embodiments;

[0153] Furthermore, the memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs; in addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device; the memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network; examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0154] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0156] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0157] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0158] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0159] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fault early warning method for a power distribution network, characterized in that, The method includes: The network topology information, historical fault information, and historical maintenance information of the distribution network are acquired; the distribution network includes multiple network units. The fault frequency and maintenance frequency of each network unit are determined based on the network topology information, the historical fault information, and the historical maintenance information. Network units with a failure frequency greater than a preset failure frequency threshold are selected as candidate failure units, and network units with a maintenance frequency greater than a preset maintenance frequency threshold are selected as candidate maintenance units. The correlation coefficient is obtained by performing correlation determination on each of the candidate fault units and each of the candidate maintenance units; Calculate the early warning coefficient for each network unit based on the fault frequency, the maintenance frequency, and the correlation coefficient; Network units with warning coefficients greater than preset warning thresholds are selected as target warning units, and warning information of the target warning units is generated and output.

2. The fault early warning method for a distribution network according to claim 1, characterized in that, Before the step of determining the fault frequency and maintenance frequency of each network unit based on the network topology information, the historical fault information, and the historical maintenance information, the following steps are included: In response to fault feedback requests from the distribution network, obtain information on pending faults in the distribution network; When the status of the pending fault information changes to processed, the updated historical fault information is obtained.

3. The fault early warning method for a distribution network according to claim 1, characterized in that, Before the step of determining the fault frequency and maintenance frequency of each network unit based on the network topology information, the historical fault information, and the historical maintenance information, the method further includes: In response to a request to update historical maintenance information of the distribution network, the update time of the historical maintenance information is obtained; If a fault occurs in the distribution network within a preset time period after the update time, the updated historical maintenance information and historical fault information are obtained. If no fault occurs in the distribution network within a preset time period after the update time, the updated historical maintenance information is obtained.

4. The fault early warning method for a distribution network according to claim 1, characterized in that, The step of associating each candidate fault unit with each candidate maintenance unit to obtain a correlation coefficient includes: The load overlap ratio of each candidate fault unit and each candidate maintenance unit is calculated to obtain the unit overlap coefficient. Based on the fault cause information of the candidate fault units, data is extracted from the preset fault level table to determine the fault level coefficient of each candidate fault unit. Based on the unit overlap coefficient and the fault level coefficient, the correlation coefficient between each candidate fault unit and each candidate maintenance unit is calculated.

5. The fault early warning method for a distribution network according to claim 4, characterized in that, The step of extracting data from a preset fault level table based on the fault cause information of the candidate fault units and determining the fault level coefficient of each candidate fault unit includes: The fault cause information of the candidate fault units is divided into a set of faults caused by equipment and a set of faults caused by non-equipment. Based on the preset fault level table, extract the equipment cause fault level coefficient corresponding to the equipment cause fault set and the non-equipment cause fault level coefficient corresponding to the non-equipment cause fault set. The first level coefficient of the equipment cause failure set is determined by using all the equipment cause failure level coefficients described above. The second level coefficient of the non-equipment cause fault set is determined by pre-setting environmental coefficients and all the non-equipment cause fault level coefficients; The maximum value between the first level coefficient and the second level coefficient is selected as the fault level coefficient of the candidate fault unit.

6. The fault early warning method for a distribution network according to claim 1, characterized in that, The warning coefficient is: In the formula: Q i Let be the early warning coefficient of network unit i, α be the fault frequency of network unit i, and β be the maintenance frequency of network unit i. Let be the correlation coefficient between network unit i and network unit τ, and U represent the set of all network units in the distribution network.

7. A fault early warning device for a power distribution network, characterized in that, include: The information acquisition module is used to acquire network topology information, historical fault information, and historical maintenance information of the distribution network; the distribution network includes multiple network units; A frequency determination module is used to determine the fault frequency and maintenance frequency of each network unit based on the network topology information, the historical fault information, and the historical maintenance information. The candidate unit selection module is used to select network units with a fault frequency greater than a preset fault frequency threshold as candidate fault units, and to select network units with a maintenance frequency greater than a preset maintenance frequency threshold as candidate maintenance units. The association discrimination module is used to perform association discrimination between each of the candidate fault units and each of the candidate maintenance units to obtain the association coefficient; The early warning coefficient calculation module is used to calculate the early warning coefficient of each network unit based on the fault frequency, the maintenance frequency and the correlation coefficient; The early warning information output module is used to select network units with an early warning coefficient greater than a preset early warning threshold as target early warning units, and generate and output early warning information of the target early warning units.

8. The fault early warning device for a power distribution network according to claim 7, characterized in that, The association discrimination module includes: The unit overlap coefficient calculation submodule is used to calculate the load overlap between each of the candidate fault units and each of the candidate maintenance units to obtain the unit overlap coefficient. The fault level coefficient determination submodule is used to extract data from a preset fault level table based on the fault cause information of the candidate fault units, and determine the fault level coefficient of each candidate fault unit. The correlation coefficient calculation submodule is used to calculate the correlation coefficient between each candidate fault unit and each candidate maintenance unit based on the unit overlap coefficient and the fault level coefficient.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-readable instructions, which, when executed by the processor, run the fault early warning method for the power distribution network as described in any one of claims 1-6.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by this processor, it runs the fault early warning method for the power distribution network as described in any one of claims 1-6.

Images