Fault positioning method and system containing distributed photovoltaic power distribution network, and storage medium

Abstract

The invention discloses a fault positioning method and system containing a distributed photovoltaic power distribution network and a storage medium, and relates to the technical field of power distribution network fault positioning, and the method comprises the steps: carrying out the digital modeling and division of a target power distribution network containing distributed photovoltaic, and obtaining a line unit sequence; when it is detected that the switch electrical parameter at any key switch is larger than or equal to a threshold value, upstream and downstream abnormal switch electrical parameters of upstream and downstream adjacent key switches are obtained, and compensation downstream abnormal switch electrical parameters are obtained through calculation; dividing in the line unit sequence to obtain a plurality of implicit abnormal line units, and performing line unit fault rate prediction to obtain a plurality of line unit fault rates; and performing fault electrical parameter prediction to obtain a plurality of predicted upstream and downstream abnormal switch electrical parameters, respectively calculating similarities, and optimizing and selecting a fault line unit as a fault positioning result in combination with a plurality of line unit fault rates. According to the invention, the technical problem of inaccurate fault positioning of the power distribution network in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network fault location, and in particular to a fault location method, system and storage medium for a distributed photovoltaic distribution network. Background Art

[0002] In modern power systems, the reliability and quality of distribution networks directly impact the daily lives of users and the normal operation of industrial production. With the transformation of energy structures and the rapid development of renewable energy, the penetration of distributed photovoltaics in distribution networks continues to increase. However, this integration also introduces new challenges for fault location.

[0003] In the existing technology, the technical problem of low fault location accuracy in distributed photovoltaic distribution networks needs to be solved urgently. Summary of the Invention

[0004] The present application provides a fault location method, system and storage medium for a distributed photovoltaic distribution network, which are used to solve the technical problem in the prior art of inaccurate distribution network fault location caused by the influence of the distributed photovoltaic distribution network.

[0005] In view of the above problems, the present application provides a fault location method, system and storage medium for a distributed photovoltaic distribution network.

[0006] In a first aspect, the present application provides a fault location method for a distributed photovoltaic distribution network, the method comprising: A target distribution network including distributed photovoltaics is digitally modeled and divided into line units to obtain a line unit sequence, wherein the target distribution network includes multiple key switches configured at multiple locations.

[0007] When it is detected that the switch electrical parameter at any key switch is greater than or equal to the electrical parameter threshold, the electrical parameter of the upstream abnormal switch and the electrical parameter of the downstream abnormal switch adjacent to the downstream key switch are obtained, and the compensated electrical parameter of the downstream abnormal switch is calculated.

[0008] A plurality of implicit abnormal line units are obtained by dividing the line unit sequence, and a line unit failure rate prediction is performed based on the electrical parameters of the upstream abnormal switch and the electrical parameters of the compensated downstream abnormal switch to obtain a plurality of line unit failure rates.

[0009] Fault electrical parameters are predicted based on multiple implicit abnormal line units to obtain multiple predicted upstream abnormal switch electrical parameters and multiple predicted downstream abnormal switch electrical parameters. The similarity with the upstream abnormal switch electrical parameters and the compensated downstream abnormal switch electrical parameters is calculated respectively. Combined with the failure rates of the multiple line units, the fault line unit is optimized and selected as the fault location result.

[0010] In a second aspect, the present application provides a fault location system for a distributed photovoltaic distribution network, comprising: The digital modeling module is used to digitally model a target distribution network including distributed photovoltaics, divide the network into line units, and obtain a line unit sequence, wherein the target distribution network includes multiple key switches configured at multiple locations.

[0011] The compensation parameter calculation module is used to obtain the electrical parameters of the upstream abnormal switch and the electrical parameters of the downstream abnormal switch of the downstream adjacent key switch when it is detected that the switch electrical parameters at any key switch are greater than or equal to the electrical parameter threshold, and calculate the electrical parameters of the compensated downstream abnormal switch.

[0012] The failure rate prediction module is used to obtain multiple implicit abnormal line units within the line unit sequence, predict the line unit failure rate based on the electrical parameters of the upstream abnormal switch and the compensated downstream abnormal switch electrical parameters, and obtain multiple line unit failure rates.

[0013] The fault location module is used to predict fault electrical parameters based on multiple implicit abnormal line units, obtain multiple predicted upstream abnormal switch electrical parameters and multiple predicted downstream abnormal switch electrical parameters, calculate the similarity with the upstream abnormal switch electrical parameters and the compensated downstream abnormal switch electrical parameters, and optimize the selection of the faulty line unit based on the failure rates of the multiple line units as the fault location result.

[0014] In a third aspect, the present application provides a non-transitory computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the fault location method for a distributed photovoltaic distribution network as described in the first aspect is implemented.

[0015] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application proposes a fault location method, system, and storage medium for distributed photovoltaic distribution networks. These methods effectively remove the contamination of fault signature signals caused by random photovoltaic injection current, restore the true electrical characteristics, and perform probabilistic predictions of potential faulty line units. Combined with similarity verification, this method integrates fault probability and feature matching to optimize decision-making, significantly improving the accuracy and robustness of fault location. Compared to traditional methods, the technical solution provided by this application significantly overcomes the current characteristic changes caused by distributed photovoltaic grid connection, avoiding misjudgments in fault location.

[0016] This application achieves the technical effect of accurately and reliably identifying fault sections of a distribution network containing distributed photovoltaics, and guiding operation and maintenance personnel to improve fault handling efficiency and grid operation safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 A schematic flow chart of a fault location method for a distributed photovoltaic distribution network provided in an embodiment of the present application.

[0019] Figure 2 A schematic diagram of the structure of a fault location system for a distributed photovoltaic distribution network provided in an embodiment of the present application.

[0020] Figure 3 A schematic diagram of the structure of the storage medium provided in an embodiment of the present application.

[0021] In the accompanying drawings, the components represented by the reference numerals are described as follows: Digital modeling module 100 , compensation parameter calculation module 200 , failure rate prediction module 300 , fault location module 400 , computer readable storage medium 500 , and computer program 511 . DETAILED DESCRIPTION

[0022] The present application provides a fault location method, system and storage medium for a distributed photovoltaic distribution network, which is used to solve the technical problem in the prior art of inaccurate distribution network fault location caused by the influence of the distributed photovoltaic distribution network.

[0023] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0024] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0025] Example 1, as Figure 1 As shown, the present application provides a fault location method for a distributed photovoltaic distribution network, wherein the method includes: S10: Digitally modeling a target distribution network including distributed photovoltaics and dividing the network into line units to obtain a line unit sequence, wherein the target distribution network includes a plurality of key switches configured at a plurality of locations.

[0026] In distribution networks with distributed photovoltaic access, traditional fault location methods usually use simplified models or fail to fully consider the impact of the distributed power source location on the current path, resulting in unclear definition of potential fault areas.

[0027] Step S10 in the method provided in the embodiment of the present application includes: Grid characteristic information of a target distribution network is obtained, and digital modeling is performed to obtain a distribution network model, wherein the target distribution network includes distributed photovoltaic power supply and includes multiple key switches configured at multiple locations.

[0028] The lines in the distribution network model are divided into line units to obtain a line unit sequence.

[0029] In the embodiment of the present application, grid characteristic information of the target distribution network, such as the location and type of distribution equipment, is obtained, and digital modeling is performed using software such as DIgSILENT to obtain a distribution network model. The target distribution network includes distributed photovoltaic power supply and multiple key switches configured at multiple locations.

[0030] Divide the lines in the distribution network model into line units to obtain a line unit sequence. Divide the lines in the distribution network model into several sections based on the non-branched sections to obtain line units, for example, every 50 meters is a line unit. These units are then integrated and numbered in sequence to obtain a line unit sequence, which provides the basic unit for subsequent fault location.

[0031] By constructing a precise digital model of distributed photovoltaics and dividing the line unit sequence based on topological relationships, a spatial analysis foundation for fault location was established. This operation clearly defined the connection boundaries between key switches in the distribution network. Structured modeling effectively overcomes the ambiguity of fault segments caused by coarse network differentiation in traditional methods, providing a reliable physical framework for subsequent accurate capture of abnormal signals.

[0032] S20: When it is detected that the switch electrical parameter at any key switch is greater than or equal to the electrical parameter threshold, the electrical parameter of the upstream abnormal switch and the electrical parameter of the downstream abnormal switch of the downstream adjacent key switch are obtained, and the compensated electrical parameter of the downstream abnormal switch is calculated.

[0033] When existing methods detect abnormal electrical parameters of switch nodes, they directly use monitoring values ​​to make fault judgments. However, distributed photovoltaics may continue to supply power during the fault, polluting the electrical parameters of downstream monitoring points. As a result, the downstream electrical quantities cannot truly reflect the current changes caused by the fault, causing distortion of fault characteristics and significantly reducing the reliability of positioning.

[0034] Step S20 in the method provided in the embodiment of the present application includes: Monitor the switch electrical parameters at multiple key switches. When any switch electrical parameter is greater than or equal to an electrical parameter threshold, obtain the upstream key switch and use the switch electrical parameter as the upstream abnormal switch electrical parameter.

[0035] The electrical parameters of the switch of the adjacent key switch downstream in the current direction are obtained as the electrical parameters of the downstream abnormal switch.

[0036] According to the distributed photovoltaic operation and maintenance data, the distributed photovoltaic electrical parameters corresponding to the downstream adjacent key switches are obtained by indexing.

[0037] The electrical parameters of the downstream abnormal switch are subtracted from the distributed photovoltaic electrical parameters to obtain the compensated electrical parameters of the downstream abnormal switch.

[0038] In an embodiment of the present application, the switch electrical parameters such as current parameters at multiple key switches are monitored according to the monitoring and acquisition system of the distribution network. When it is detected that the electrical parameter of any switch is greater than or equal to the electrical parameter threshold, the upstream key switch is obtained, that is, the line where the switch whose electrical parameter is greater than or equal to the electrical parameter threshold is located is retrieved, and the key switch upstream and closest to the switch whose electrical parameter is greater than or equal to the electrical parameter threshold is found as the nearest key switch, and the electrical parameter of the upstream key switch is used as the electrical parameter of the upstream abnormal switch, such as the current parameter of the upstream key switch is used as the electrical parameter of the upstream abnormal switch. The electrical parameter threshold is a threshold value reflecting the size of the electrical parameter set according to the rated electrical parameter. For example, the electrical parameter threshold is set to 1.2 times the rated current. If the rated current is 100A, the electrical parameter threshold = 100×1.2 = 1220A.

[0039] The switch electrical parameters of the key switch most adjacent downstream in the current direction, such as the current parameters, are obtained as the electrical parameters of the downstream abnormal switch.

[0040] Based on the distributed photovoltaic operation and maintenance data, the distributed photovoltaic electrical parameters corresponding to the downstream adjacent key switches are obtained through indexing, such as the electrical parameters of the distributed photovoltaics.

[0041] When distributed photovoltaic systems are present, downstream switches may have PV panels connected to the grid and continue to supply power, resulting in inaccurate electrical parameters. Compensate for the abnormal downstream switch's electrical parameters by subtracting the distributed photovoltaic parameters from the abnormal downstream switch's electrical parameters. Compensate for the abnormal downstream switch's electrical parameters = abnormal downstream switch's electrical parameters - distributed photovoltaic parameters. For example, if the abnormal downstream switch's electrical parameters are 160A and the distributed photovoltaic parameters are 80A, the compensated downstream switch's electrical parameters = 160 - 80 = 80A.

[0042] This application introduces an electrical parameter compensation mechanism for distributed photovoltaic systems. When a critical switch triggers an anomaly, the system dynamically deducts the photovoltaic injection component from the electrical parameters of the downstream abnormal switch by indexing the real-time data of the associated photovoltaic system, generating compensation parameters for the downstream abnormal switch. This effectively eliminates the contamination of fault current characteristics caused by the continuous power supply of distributed photovoltaic systems, restores the true electrical parameter changes caused by pure faults, resolves the problem of downstream monitoring data distortion, and provides a high-fidelity input data foundation for subsequent fault probability prediction and feature matching.

[0043] S30: Divide the line unit sequence to obtain a plurality of implicit abnormal line units, perform line unit failure rate prediction based on the electrical parameters of the upstream abnormal switch and the compensated downstream abnormal switch electrical parameters, and obtain a plurality of line unit failure rates.

[0044] Traditional methods rely on fixed thresholds or simple rules to determine fault location, making them incapable of adapting to the complex, nonlinear nature of faults after distributed photovoltaic integration. Existing technologies lack the ability to quantitatively assess the probability of faults occurring in different line units under specific electrical parameter combinations, resulting in a location process that relies on experience and is susceptible to interference.

[0045] Step S30 in the method provided in the embodiment of the present application includes: The line cells between the upstream key switch and the downstream adjacent key switch are divided into a plurality of implicit abnormal line cells within the line cell sequence.

[0046] The electrical parameters of the upstream abnormal switch and the electrical parameters of the compensated downstream abnormal switch are input into a fault unit predictor, and a prediction output is obtained to obtain multiple line unit failure rates of multiple implicit abnormal line units.

[0047] The training step of the fault unit predictor includes: Based on the power grid fault monitoring data in the historical period, the electrical parameter sets of sample upstream abnormal switches and sample downstream abnormal switches with multiple faults are collected, and the proportion of line units at different locations in the multiple faults is collected, and multiple sample line unit probability sets are obtained by annotation.

[0048] Build a faulty unit predictor based on machine learning.

[0049] The fault unit predictor is supervised trained using the sample upstream abnormal switch electrical parameter set, the sample downstream abnormal switch electrical parameter set and a plurality of sample line unit probability sets, and the training is completed after the training and testing converge.

[0050] In an embodiment of the present application, within a line unit sequence, the line units between an upstream key switch and an adjacent downstream key switch are divided into multiple implicit abnormal line units. Specifically, a search is performed within the line unit sequence, and the line units between the upstream key switch and the adjacent downstream key switch are divided into multiple implicit abnormal line units.

[0051] Based on the power grid fault monitoring data in the historical period, the electrical parameter sets of sample upstream abnormal switches and sample downstream abnormal switches with multiple faults are collected, and the proportion of failures in line units at different locations in multiple faults is collected. The line units are marked with the proportion of failures, and multiple sample line unit probability sets are obtained.

[0052] Machine learning is used to construct a fault unit predictor. For example, a three-layer structure is adopted. The input layer is used to receive the electrical parameters of the upstream abnormal switch and the downstream abnormal switch. The hidden layer uses 16 nodes and is activated by the ReLU function. The output layer outputs the predicted line unit probability, and the loss function uses the cross entropy function.

[0053] The faulty unit predictor is supervised and trained using a set of sample electrical parameters of upstream abnormal switches, a set of sample electrical parameters of downstream abnormal switches, and multiple sets of sample line unit probabilities until the test converges. For example, if the accuracy error of the output line unit probability is within ±5% when the electrical parameters of the upstream abnormal switch and the downstream abnormal switch are input, the training of the faulty unit predictor is completed.

[0054] The electrical parameters of the upstream abnormal switch and the compensated downstream abnormal switch are input into the faulty unit predictor, which outputs multiple line unit failure rates for multiple implicitly abnormal line units. For example, the predicted failure rate for line unit number 1002 is 60%, and the predicted failure rate for line unit number 2031 is 20%.

[0055] This application utilizes a pre-trained fault unit predictor, taking the electrical parameters of the upstream abnormal switch and the compensated downstream abnormal switch as inputs and outputting the line unit failure rate. Through machine learning, this predictor learns the deep correlation between electrical parameter patterns and fault locations in historical fault data. It automatically captures the complex patterns of fault characteristics, enabling predictions from electrical parameters to fault probability, significantly improving the objectivity and accuracy of candidate fault section assessments.

[0056] S40: Predict fault electrical parameters based on multiple implicit abnormal line units to obtain multiple predicted upstream abnormal switch electrical parameters and multiple predicted downstream abnormal switch electrical parameters, calculate the similarity with the upstream abnormal switch electrical parameters and the compensated downstream abnormal switch electrical parameters respectively, combine the failure rates of the multiple line units, and optimize and select the faulty line unit as the fault location result.

[0057] Relying solely on fault probability prediction still presents uncertainty, and a single probability value may not adequately distinguish candidate units with similar characteristics. Existing methods often neglect to verify the matching between theoretical fault signatures and actual monitoring values, or fail to incorporate probability information during verification, which can easily lead to positioning results that deviate from reality.

[0058] Step S40 in the method provided in the embodiment of the present application includes: The line unit number of each implicit abnormal line unit is input into the fault electrical parameter predictor, and the prediction output obtains multiple predicted upstream abnormal switch electrical parameters and multiple predicted downstream abnormal switch electrical parameters.

[0059] The steps of constructing the fault electrical parameter predictor include: Based on the distribution network fault monitoring data in the historical period, a sample line unit number set, a sample upstream abnormal switch electrical parameter set, and a sample downstream abnormal switch electrical parameter set are collected when faults occur in different line units.

[0060] A fault electrical parameter predictor is constructed by using the sample line unit number set, the sample upstream abnormal switch electrical parameter set, and the sample downstream abnormal switch electrical parameter set.

[0061] The average similarity between each set of predicted upstream abnormal switch electrical parameters and predicted downstream abnormal switch electrical parameters and the upstream abnormal switch electrical parameters and compensated downstream abnormal switch electrical parameters is calculated to obtain multiple fault similarities.

[0062] According to multiple fault similarities and multiple line unit failure rates, the faulty line unit is optimally selected and obtained as the fault location result.

[0063] The method includes optimizing and selecting a faulty line unit based on multiple fault similarities and multiple line unit failure rates as a fault location result, including: According to multiple fault similarities and multiple line unit failure rates, multiple comprehensive fault confidences are calculated and obtained.

[0064] The fault line unit with the largest comprehensive fault confidence is selected as the fault location result.

[0065] In an embodiment of the present application, based on the distribution network fault monitoring data in historical time, a sample line unit number set, a sample upstream abnormal switch electrical parameter set and a sample downstream abnormal switch electrical parameter set are collected when faults occur in different line units.

[0066] A neural network is used. A fault electrical parameter predictor is constructed. For example, a three-layer neural network fault electrical parameter predictor is constructed, wherein the input layer uses 1 node and inputs the line unit number, the hidden layer uses 16 nodes and is activated by the ReLU function, the output layer uses 2 nodes and outputs the predicted upstream abnormal switch electrical parameters and the predicted downstream abnormal switch electrical parameters, and the loss function uses the mean square error. A set of sample line unit numbers, a set of sample upstream abnormal switch electrical parameters, and a set of sample downstream abnormal switch electrical parameters when faults occur in different line units are used to perform supervised training on the constructed fault electrical parameter predictor until convergence. For example, if the line unit number is input and the accuracy of the output predicted upstream abnormal switch electrical parameters and the predicted downstream abnormal switch electrical parameters is above 90%, the training of the fault electrical parameter predictor is completed.

[0067] The line unit number of each implicitly abnormal line unit is input into the fault electrical parameter predictor, and the prediction output is a plurality of predicted upstream abnormal switch electrical parameters and a plurality of predicted downstream abnormal switch electrical parameters. The predicted electrical parameters reflect the possible fault electrical parameter conditions of the line unit when it fails.

[0068] Calculate the average similarity between each set of predicted upstream and downstream abnormal switch electrical parameters and the upstream and compensated downstream abnormal switch electrical parameters to obtain multiple fault similarities. For example, the upstream fault similarity = 1 - |predicted upstream abnormal switch electrical parameters - upstream abnormal switch electrical parameters| ÷ [(predicted upstream abnormal switch electrical parameters + upstream abnormal switch electrical parameters) ÷ 2], and the downstream fault similarity = 1 - |predicted downstream abnormal switch electrical parameters - compensated downstream abnormal switch electrical parameters| ÷ [(predicted downstream abnormal switch electrical parameters + compensated downstream abnormal switch electrical parameters) ÷ 2]. For example, if the predicted upstream abnormal switch electrical parameters are 100A and 80A, the upstream fault similarity = 1 - |100 - 80| ÷ [(100 + 80) ÷ 2] = 0.78. If the predicted downstream abnormal switch electrical parameters are 90A and 80A, the downstream fault similarity = 1 - |90 - 80| ÷ [(90 + 80) ÷ 2] = 0.88. Average similarity = (upstream anomaly similarity + downstream anomaly similarity) ÷ 2. For example, if the upstream anomaly similarity is 0.78 and the downstream anomaly similarity is 0.88, then the average similarity = (0.78 + 0.88) ÷ 2 = 0.83. A higher similarity indicates that the upstream and downstream electrical parameters of the line unit are closer to the possible upstream and downstream electrical parameters at the time of the fault, and the probability of the line unit fault is greater.

[0069] Based on multiple fault similarities and multiple line unit failure rates, multiple comprehensive fault confidence levels are calculated. Comprehensive fault confidence level = line unit fault similarity × line unit failure rate. For example, if the line unit fault similarity is 0.83 and the failure rate is 0.80, the comprehensive fault confidence level = 0.83 × 0.80 = 0.664.

[0070] The fault line unit with the largest comprehensive fault confidence is selected as the fault location result.

[0071] The fault electrical parameter predictor generates the predicted electrical parameters of the upstream and downstream abnormal switches for each line unit, calculates their similarity with the electrical parameters of the upstream abnormal switch and the compensated downstream abnormal switch, and calculates the comprehensive fault confidence to select the optimal faulty line unit. This dual verification mechanism combines the statistical advantages of probabilistic prediction with the physical consistency of feature matching, effectively overcoming the limitations of a single method, significantly improving the robustness and reliability of fault location results, and ensuring accurate identification of the true fault point.

[0072] Example 2, as Figure 2 As shown, based on the same inventive concept as the method for locating a fault in a distributed photovoltaic distribution network provided in the first embodiment, an embodiment of the present invention further provides a system for locating a fault in a distributed photovoltaic distribution network, comprising: The digital modeling module 100 is used to digitally model a target distribution network including distributed photovoltaics, and divide the network into line units to obtain a line unit sequence, wherein the target distribution network includes multiple key switches configured at multiple locations.

[0073] The compensation parameter calculation module 200 is used to obtain the electrical parameters of the upstream abnormal switch and the electrical parameters of the downstream abnormal switch of the downstream adjacent key switch when it is detected that the switch electrical parameters at any key switch are greater than or equal to the electrical parameter threshold, and calculate the compensated downstream abnormal switch electrical parameters.

[0074] The failure rate prediction module 300 is used to obtain multiple implicit abnormal line units within the line unit sequence, and perform line unit failure rate prediction based on the electrical parameters of the upstream abnormal switch and the compensated downstream abnormal switch electrical parameters to obtain multiple line unit failure rates.

[0075] The fault location module 400 is used to predict fault electrical parameters based on multiple implicit abnormal line units, obtain multiple predicted upstream abnormal switch electrical parameters and multiple predicted downstream abnormal switch electrical parameters, calculate the similarity with the upstream abnormal switch electrical parameters and the compensated downstream abnormal switch electrical parameters, and optimize and select the faulty line unit based on the failure rates of the multiple line units as the fault location result.

[0076] In one embodiment, the digital modeling module 100 is further configured to: Grid characteristic information of a target distribution network is obtained, and digital modeling is performed to obtain a distribution network model, wherein the target distribution network includes distributed photovoltaic power supply and includes multiple key switches configured at multiple locations.

[0077] The lines in the distribution network model are divided into line units to obtain a line unit sequence.

[0078] In one embodiment, the compensation parameter calculation module 200 is further configured to: Monitor the switch electrical parameters at multiple key switches. When any switch electrical parameter is greater than or equal to an electrical parameter threshold, obtain the upstream key switch and use the switch electrical parameter as the upstream abnormal switch electrical parameter.

[0079] The electrical parameters of the switch of the adjacent key switch downstream in the current direction are obtained as the electrical parameters of the downstream abnormal switch.

[0080] According to the distributed photovoltaic operation and maintenance data, the distributed photovoltaic electrical parameters corresponding to the downstream adjacent key switches are obtained by indexing.

[0081] The electrical parameters of the downstream abnormal switch are subtracted from the distributed photovoltaic electrical parameters to obtain the compensated electrical parameters of the downstream abnormal switch.

[0082] In one embodiment, the failure rate prediction module 300 is further configured to: The line cells between the upstream key switch and the downstream adjacent key switch are divided into a plurality of implicit abnormal line cells within the line cell sequence.

[0083] The electrical parameters of the upstream abnormal switch and the electrical parameters of the compensated downstream abnormal switch are input into a fault unit predictor, and a prediction output is obtained to obtain multiple line unit failure rates of multiple implicit abnormal line units.

[0084] The training step of the fault unit predictor includes: Based on the power grid fault monitoring data in the historical period, the electrical parameter sets of sample upstream abnormal switches and sample downstream abnormal switches with multiple faults are collected, and the proportion of line units at different locations in the multiple faults is collected, and multiple sample line unit probability sets are obtained by annotation.

[0085] Build a faulty unit predictor based on machine learning.

[0086] The fault unit predictor is supervised trained using the sample upstream abnormal switch electrical parameter set, the sample downstream abnormal switch electrical parameter set and a plurality of sample line unit probability sets, and the training is completed after the training and testing converge.

[0087] In one embodiment, the fault location module 400 is further configured to: The line unit number of each implicit abnormal line unit is input into the fault electrical parameter predictor, and the prediction output obtains multiple predicted upstream abnormal switch electrical parameters and multiple predicted downstream abnormal switch electrical parameters.

[0088] The steps of constructing the fault electrical parameter predictor include: Based on the distribution network fault monitoring data in the historical period, a sample line unit number set, a sample upstream abnormal switch electrical parameter set, and a sample downstream abnormal switch electrical parameter set are collected when faults occur in different line units.

[0089] A fault electrical parameter predictor is constructed by using the sample line unit number set, the sample upstream abnormal switch electrical parameter set, and the sample downstream abnormal switch electrical parameter set.

[0090] The average similarity between each set of predicted upstream abnormal switch electrical parameters and predicted downstream abnormal switch electrical parameters and the upstream abnormal switch electrical parameters and compensated downstream abnormal switch electrical parameters is calculated to obtain multiple fault similarities.

[0091] According to multiple fault similarities and multiple line unit failure rates, the faulty line unit is optimally selected and obtained as the fault location result.

[0092] The method includes optimizing and selecting a faulty line unit based on multiple fault similarities and multiple line unit failure rates as a fault location result, including: According to multiple fault similarities and multiple line unit failure rates, multiple comprehensive fault confidences are calculated and obtained.

[0093] The fault line unit with the largest comprehensive fault confidence is selected as the fault location result.

[0094] Example 3, as Figure 3 As shown, an embodiment of the present invention further provides a non-transitory computer-readable storage medium 500, in which a computer program 511 is stored. When the computer program 511 is executed by a processor, the fault location method for a distributed photovoltaic distribution network as described in Example 1 is implemented.

[0095] In summary, the embodiments of the present application have at least the following technical effects: This application proposes a fault location method, system and storage medium for a distributed photovoltaic distribution network. By establishing an accurate digital model and dividing the line unit sequence, when the electrical parameter anomaly of the key switch is detected, a compensation mechanism for the distributed photovoltaic power supply of the abnormal parameters of the downstream adjacent key switch is introduced, which effectively removes the contamination of the fault characteristic signal by the photovoltaic power supply and restores the true fault electrical quantity characteristics; then, based on the compensated upstream and downstream abnormal parameters, a pre-trained fault unit predictor is used to predict the potential fault line unit, and the similarity verification between the theoretical parameters generated by the fault electrical parameter predictor and the actual monitoring parameters is combined to optimize the decision-making by integrating the fault probability and feature matching, which significantly improves the accuracy and robustness of fault location. Compared with traditional methods, the technical solution provided by this application significantly overcomes the changes in fault current characteristics caused by distributed photovoltaic grid connection, and avoids the misjudgment or omission of fault location caused by continuous photovoltaic power supply.

[0096] This application achieves the technical effect of accurately and reliably identifying fault sections of a distribution network containing distributed photovoltaics, and guiding operation and maintenance personnel to improve fault handling efficiency and grid operation safety.

[0097] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0098] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0099] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for fault location and processing in a distributed photovoltaic distribution network, characterized in that: The method comprises: Digitally modeling a target distribution network including distributed photovoltaics and dividing it into line units to obtain a line unit sequence, wherein the target distribution network includes a plurality of key switches configured at a plurality of locations; When it is detected that the switch electrical parameter at any key switch is greater than or equal to the electrical parameter threshold, the electrical parameter of the upstream abnormal switch and the electrical parameter of the downstream abnormal switch adjacent to the downstream key switch are obtained, and the electrical parameter of the downstream abnormal switch is calculated to compensate; Dividing the line unit sequence to obtain a plurality of implicitly abnormal line units, and performing line unit failure rate prediction based on the electrical parameters of the upstream abnormal switch and the electrical parameters of the compensated downstream abnormal switch to obtain a plurality of line unit failure rates; Fault electrical parameters are predicted based on multiple implicit abnormal line units to obtain multiple predicted upstream abnormal switch electrical parameters and multiple predicted downstream abnormal switch electrical parameters. The similarity with the upstream abnormal switch electrical parameters and the compensated downstream abnormal switch electrical parameters is calculated respectively. Combined with the failure rates of the multiple line units, the fault line unit is optimized and selected as the fault location result.

2. The fault location processing method for a distributed photovoltaic distribution network according to claim 1, characterized in that: Digitally model the target distribution network including distributed photovoltaics and divide it into line units to obtain a line unit sequence, including: Obtaining grid characteristic information of a target distribution network, performing digital modeling, and obtaining a distribution network model, wherein the target distribution network includes distributed photovoltaic power supply and includes multiple key switches configured at multiple locations; The lines in the distribution network model are divided into line units to obtain a line unit sequence.

3. The fault location processing method for a distributed photovoltaic power distribution network according to claim 1, characterized in that: When it is detected that the switch electrical parameters at any key switch are greater than or equal to the electrical parameter threshold, the electrical parameters of the upstream abnormal switch and the electrical parameters of the downstream abnormal switch adjacent to the downstream key switch are obtained, and the electrical parameters of the downstream abnormal switch are calculated to compensate, including: Monitor switch electrical parameters at multiple key switches, and when any switch electrical parameter is greater than or equal to an electrical parameter threshold, obtain the upstream key switch and use the switch electrical parameter as the upstream abnormal switch electrical parameter; Obtaining electrical parameters of a key switch adjacent to the downstream side of the current flow as electrical parameters of the downstream abnormal switch; Based on the distributed photovoltaic operation and maintenance data, index and obtain the distributed photovoltaic electrical parameters corresponding to the downstream adjacent key switches; The electrical parameters of the downstream abnormal switch are subtracted from the distributed photovoltaic electrical parameters to obtain the compensated electrical parameters of the downstream abnormal switch.

4. The fault location processing method for a distributed photovoltaic power distribution network according to claim 1, characterized in that: A plurality of implicit abnormal line units are obtained by dividing the line unit sequence, and a line unit failure rate prediction is performed based on the electrical parameters of the upstream abnormal switch and the electrical parameters of the compensated downstream abnormal switch to obtain a plurality of line unit failure rates, including: dividing the line units between the upstream key switch and the downstream adjacent key switch in the line unit sequence as a plurality of implicit abnormal line units; The electrical parameters of the upstream abnormal switch and the electrical parameters of the compensated downstream abnormal switch are input into a fault unit predictor, and a prediction output is obtained to obtain multiple line unit failure rates of multiple implicit abnormal line units.

5. The fault location processing method for a distributed photovoltaic power distribution network according to claim 4, characterized in that: The training step of the fault unit predictor includes: Based on the historical power grid fault monitoring data, the electrical parameter sets of upstream abnormal switches and downstream abnormal switches with multiple faults are collected. The proportion of line units with faults at different locations in the multiple faults is collected, and the probability sets of multiple line units are obtained by annotation. Build a fault unit predictor based on machine learning; The fault unit predictor is supervised trained using the sample upstream abnormal switch electrical parameter set, the sample downstream abnormal switch electrical parameter set and a plurality of sample line unit probability sets, and the training is completed after the training and testing converge.

6. The fault location processing method for a distributed photovoltaic power distribution network according to claim 1, characterized in that: Fault electrical parameters are predicted based on multiple implicit abnormal line units to obtain multiple predicted electrical parameters of upstream abnormal switches and multiple predicted electrical parameters of downstream abnormal switches. Similarities with the electrical parameters of the upstream abnormal switches and the electrical parameters of the compensated downstream abnormal switches are calculated respectively. Combined with the failure rates of the multiple line units, the faulty line unit is optimally selected and obtained as the fault location result, including: Inputting the line unit number of each implicit abnormal line unit into the fault electrical parameter predictor, and predicting output to obtain a plurality of predicted upstream abnormal switch electrical parameters and a plurality of predicted downstream abnormal switch electrical parameters; Calculating the average similarity of each set of predicted upstream abnormal switch electrical parameters and predicted downstream abnormal switch electrical parameters with the upstream abnormal switch electrical parameters and compensated downstream abnormal switch electrical parameters to obtain multiple fault similarities; According to multiple fault similarities and multiple line unit failure rates, the faulty line unit is optimally selected and obtained as the fault location result.

7. The fault location processing method for a distributed photovoltaic power distribution network according to claim 6, characterized in that: The steps of constructing the fault electrical parameter predictor include: Based on the distribution network fault monitoring data in the historical period, a sample line unit number set, a sample upstream abnormal switch electrical parameter set, and a sample downstream abnormal switch electrical parameter set are collected when faults occur in different line units; A fault electrical parameter predictor is constructed by using the sample line unit number set, the sample upstream abnormal switch electrical parameter set, and the sample downstream abnormal switch electrical parameter set.

8. The fault location processing method for a distributed photovoltaic power distribution network according to claim 6, characterized in that: Based on multiple fault similarities and multiple line unit failure rates, the fault line unit is optimally selected as the fault location result, including: According to multiple fault similarities and multiple line unit failure rates, multiple comprehensive fault confidences are calculated and obtained; The fault line unit with the largest comprehensive fault confidence is selected as the fault location result.

9. A fault location and processing system for a distributed photovoltaic distribution network, characterized in that: A system for implementing a fault location processing method for a distributed photovoltaic distribution network according to any one of claims 1 to 8, comprising: a digital modeling module, configured to digitally model a target distribution network including distributed photovoltaics and divide the network into line units to obtain a line unit sequence, wherein the target distribution network includes a plurality of key switches configured at a plurality of locations; a compensation parameter calculation module, configured to obtain the electrical parameters of the upstream abnormal switch and the electrical parameters of the downstream abnormal switch adjacent to the downstream key switch when detecting that the switch electrical parameters at any key switch are greater than or equal to the electrical parameter threshold, and calculate the electrical parameters of the compensated downstream abnormal switch; a failure rate prediction module, configured to obtain a plurality of implicitly abnormal line units by dividing the line unit sequence, and predicting the line unit failure rate based on the electrical parameters of the upstream abnormal switch and the electrical parameters of the compensated downstream abnormal switch, to obtain a plurality of line unit failure rates; The fault location module is used to predict fault electrical parameters based on multiple implicit abnormal line units, obtain multiple predicted upstream abnormal switch electrical parameters and multiple predicted downstream abnormal switch electrical parameters, calculate the similarity with the upstream abnormal switch electrical parameters and the compensated downstream abnormal switch electrical parameters, and optimize the selection of the faulty line unit based on the failure rates of the multiple line units as the fault location result.

10. A non-transitory computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the method for fault location processing of a distributed photovoltaic distribution network according to any one of claims 1 to 8 is implemented.

Images