Power distribution network voltage abnormity diagnosis method and system based on graph model

Abstract

The invention discloses a power distribution network voltage abnormity diagnosis method and system based on a graph model, and the method comprises the steps: constructing a power distribution network graph model according to the geographic topology of a power distribution network; detecting the voltage of a load node in the power distribution network graph model to obtain a voltage anomaly diagnosis to-be-selected set; a to-be-detected branch in the voltage anomaly diagnosis candidate set is diagnosed through a hierarchical backtracking screening algorithm, and a voltage anomaly positioning result is obtained; and formulating a power distribution network maintenance plan according to a voltage abnormity positioning result. According to the invention, voltage abnormity diagnosis can be accurately carried out without depending on an intelligent algorithm, and occupation of computing resources is reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of power grid voltage monitoring, and specifically relates to a distribution network voltage anomaly diagnosis method and system based on a graphical model. Background Art

[0002] The distribution network receives electrical energy from the transmission network or regional power plants, and supplies electricity to various users locally or step by step through distribution facilities. Abnormal voltage in the distribution network caused by load changes, equipment failures, external forces, etc. will lead to reduced stability and reliability of the power supply system, damage to users' electrical equipment, and may even cause large-scale power outages in the system. Therefore, it is necessary to diagnose abnormal distribution network voltage.

[0003] In the existing technology, most distribution network voltage anomaly diagnosis methods rely on intelligent algorithms such as neural networks and machine learning. However, intelligent algorithms have a high computing resource occupancy rate and slow convergence. They require a large amount of high-quality data for training and learning. In addition, intelligent algorithms are sensitive to the settings of initial parameters or given parameters. When there is a certain deviation in the parameter setting, it may lead to erroneous distribution network voltage anomaly diagnosis results, which is time-consuming and labor-intensive. Summary of the invention

[0004] The present application proposes a distribution network voltage anomaly diagnosis method and system based on a graphical model, which can accurately diagnose voltage anomalies without relying on intelligent algorithms and reduce the occupation of computing resources.

[0005] A first aspect of the present application provides a method for diagnosing abnormal voltage in a distribution network based on a graphical model, the method comprising:

[0006] According to the geographical topology of the distribution network, a distribution network graph model is constructed;

[0007] Detect the voltage of the load node in the distribution network diagram model and obtain a voltage anomaly diagnosis candidate set;

[0008] The branches to be detected in the voltage anomaly diagnosis candidate set are diagnosed through a hierarchical backtracking screening algorithm to obtain the voltage anomaly location result;

[0009] Develop a distribution network maintenance plan based on the voltage anomaly location results.

[0010] The above scheme first constructs a graph model that accurately describes the distribution network information based on the geographical topology of the distribution network, and then performs voltage detection on the load nodes of the distribution network based on the graph model. The power supply branches that may have voltage abnormalities are determined through the load nodes with voltage abnormalities, and these power supply branches are placed in the voltage abnormality diagnosis candidate set to provide data support for subsequent branch detection. Then, the power supply branches that may have voltage abnormalities are diagnosed in turn through the hierarchical backtracking screening algorithm. Only certain power supply branches need to be detected to accurately obtain the voltage anomaly location results. There is no need for neural networks to detect all power supply branches, saving a lot of computing resources. In addition, there is no need to set parameters during the detection process, reducing the risk of detection errors caused by parameter setting problems.

[0011] In a possible implementation method of the first aspect, the voltage of the load node in the distribution network diagram model is detected to obtain a voltage anomaly diagnosis candidate set, specifically:

[0012] Obtain the voltage of the load node in the distribution network diagram model;

[0013] Based on a preset reference voltage interval, the voltage of each load node is compared with the corresponding reference voltage interval to determine the load nodes with abnormal voltage in the distribution network diagram model;

[0014] The power supply branches of the distribution network diagram model are screened according to the load nodes with abnormal voltage to obtain a voltage abnormality diagnosis candidate set.

[0015] The above scheme locates the voltage anomaly diagnosis by performing voltage detection on the load nodes of the distribution network. The voltage of the load node is compared with the corresponding reference voltage to determine the load node with voltage anomaly. Then, the power supply branch where the load node with voltage anomaly is located and the connected power supply branches are screened, and these branches are listed as branches that may have voltage anomaly risks and added to the voltage anomaly diagnosis candidate set to provide data support for subsequent branch detection.

[0016] In a possible implementation method of the first aspect, the power supply branches of the distribution network graph model are screened according to the load nodes with voltage abnormalities to obtain a voltage abnormality diagnosis candidate set, specifically:

[0017] Based on the distribution network graph model, determine the power supply branch where each load node with abnormal voltage is located, which is recorded as the first branch;

[0018] Through the load node with abnormal voltage, the power supply branch connected with the first branch in the distribution network diagram model is screened to obtain a branch to be detected;

[0019] According to the branch to be detected, a voltage anomaly diagnosis candidate set is obtained.

[0020] In a possible implementation method of the first aspect, a voltage anomaly locating result is obtained by diagnosing the branches to be detected in the voltage anomaly diagnosis candidate set through a hierarchical backtracking screening algorithm, specifically:

[0021] Select a starting point from the non-load nodes of the branch to be detected;

[0022] Taking the starting point as the starting point and the load node with voltage abnormality corresponding to the starting point as the end point, the non-load nodes of all branches to be detected are diagnosed for abnormality through a hierarchical backtracking screening algorithm to determine the power supply branch with voltage abnormality;

[0023] The voltage anomaly location result is determined based on all power supply branches with voltage anomalies.

[0024] In a possible implementation method of the first aspect, an abnormal diagnosis is performed on non-load nodes of all branches to be detected through a hierarchical backtracking screening algorithm to determine a power supply branch with a voltage abnormality, specifically:

[0025] Based on the historical failure rate of the branch, an abnormality diagnosis is performed on the second branch where the starting point is located; wherein, among all the branches to be detected where the starting point is located, the second branch has the highest historical failure rate of the branch;

[0026] If the second branch has a voltage abnormality, stop the abnormality diagnosis, and determine that the second branch is a power supply branch with a voltage abnormality;

[0027] If the second branch does not have voltage abnormality, abnormality diagnosis is performed on the next level of branches to be detected of the second branch until a power supply branch with voltage abnormality is determined.

[0028] In the above scheme, the branch with the highest historical failure rate is first selected to start voltage diagnosis. Then, when the current detection branch is normal, the next level branch of the branch is detected to improve the rate of finding the power supply branch with abnormal voltage. Moreover, only some power supply branches need to be detected to accurately obtain the voltage anomaly location result, without the need for the neural network to detect all power supply branches, saving a lot of computing resources.

[0029] The second aspect of the present application provides a distribution network voltage anomaly diagnosis system based on a graph model, the system comprising: a graph model construction module, an abnormal diagnosis to-be-selected set construction module, an abnormal location result acquisition module and a distribution network maintenance module;

[0030] Wherein, the graph model construction module is used to construct a distribution network graph model according to the geographical topology of the distribution network;

[0031] The abnormal diagnosis candidate set construction module is used to detect the voltage of the load node in the distribution network diagram model to obtain the voltage abnormal diagnosis candidate set;

[0032] The abnormality location result acquisition module is used to diagnose the branches to be detected in the voltage abnormality diagnosis candidate set through a hierarchical backtracking screening algorithm to obtain a voltage abnormality location result;

[0033] The distribution network maintenance module is used to formulate a distribution network maintenance plan according to the voltage anomaly positioning result.

[0034] In a possible implementation of the second aspect, the abnormal diagnosis candidate set construction module includes: a voltage abnormality detection unit;

[0035] Among them, the voltage anomaly detection unit is used to obtain the voltage of the load node in the distribution network diagram model; based on the preset reference voltage interval, the voltage of each load node is compared with the corresponding reference voltage interval to determine the load node with voltage abnormality in the distribution network diagram model; according to the load node with voltage abnormality, the power supply branch of the distribution network diagram model is screened to obtain the voltage anomaly diagnosis candidate set.

[0036] In a possible implementation of the second aspect, the abnormal diagnosis candidate set construction module includes: a to-be-detected branch acquisition unit;

[0037] Among them, the to-be-detected branch acquisition unit is used to determine the power supply branch where each load node with voltage abnormality is located based on the distribution network graph model, which is recorded as the first branch; through the load node with voltage abnormality, the power supply branch connected to the first branch in the distribution network graph model is screened to obtain the to-be-detected branch; according to the to-be-detected branch, a voltage abnormality diagnosis candidate set is obtained.

[0038] In a possible implementation of the second aspect, the abnormality location result acquisition module includes: a voltage abnormal branch determination unit;

[0039] Among them, the voltage abnormal branch determination unit is used to select a starting point from the non-load nodes of the branch to be detected; taking the starting point as the starting point and the load node with voltage abnormality corresponding to the starting point as the end point, the non-load nodes of all branches to be detected are diagnosed for abnormality through a hierarchical backtracking screening algorithm to determine the power supply branch with voltage abnormality; based on all the power supply branches with voltage abnormalities, the voltage anomaly positioning result is determined.

[0040] In a possible implementation of the second aspect, the abnormality location result acquisition module includes: a branch level detection unit;

[0041] Among them, the branch level detection unit is used to perform abnormal diagnosis on the second branch where the starting point is located based on the historical failure rate of the branch; wherein, among all the branches to be detected where the starting point is located, the branch historical failure rate of the second branch is the highest; if there is a voltage abnormality in the second branch, the abnormal diagnosis is stopped, and the second branch is determined to be a power supply branch with a voltage abnormality; if there is no voltage abnormality in the second branch, the next level of branches to be detected of the second branch are subjected to abnormal diagnosis until a power supply branch with a voltage abnormality is determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the implementation manner will be briefly introduced below. Obviously, the drawings described below are only some implementation manners of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 It is a specific flow chart of a method for diagnosing abnormal voltage in a distribution network based on a graphical model provided in a certain embodiment of the present application;

[0044] Figure 2 It is a node-branch schematic diagram of a distribution network voltage anomaly diagnosis method based on a graphical model provided in a certain embodiment of the present application;

[0045] Figure 3 It is a specific structural diagram of a distribution network voltage anomaly diagnosis system based on a graphical model provided in a certain embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] It should be understood that the step numbers used in this article are only for the convenience of description and are not intended to limit the order in which the steps are executed.

[0048] First embodiment

[0049] Neural networks are commonly used to sample and detect voltage data of distribution networks to obtain voltage anomaly diagnosis results. However, these existing technologies that rely on neural networks often occupy a large amount of computing resources, and the data processing speed is slow, requiring a large amount of high-quality data for training and learning. In order to solve the above problems, the embodiments of the present application study how to reduce the occupation of computing resources while ensuring the accuracy of voltage anomaly diagnosis.

[0050] like Figure 1 As shown, Figure 1 A specific flow chart of a method for diagnosing abnormal voltage in a distribution network based on a graphical model is provided for a certain embodiment of the present application. The method for diagnosing abnormal voltage in a distribution network based on a graphical model in this embodiment includes steps S1 to S4, which are described in detail as follows:

[0051] Step S1, constructing a distribution network graph model according to the geographical topology of the distribution network.

[0052] In the embodiment of the present application, a distribution network graph model is first constructed based on the distribution network geographical topology of the target area. In the process of constructing the distribution network geographical topology, it is necessary to obtain the geographical location topology of the distribution transformers, overhead lines, cables, disconnectors, power loads, etc. of the distribution network.

[0053] To show the distribution network diagram model, Figure 2 A node-branch schematic diagram of some graph models is provided. As shown in the figure, node 1 is a power supply node, representing a distribution transformer of a higher voltage level; node 2 is an intermediate node, representing a substation transformer of an intermediate voltage level; node 4 is a high-voltage power load node, directly powered by the substation transformer of node 2, and node 5 is a primary power load node, which requires two backup power supply paths. The first one is from node 2 and then through the first low voltage level transformer of node 3 to supply power to the primary power load of node 5, and the second one is from node 2 and then through the second low voltage level transformer of node 6 to supply power to the primary power load of node 5.

[0054] The distribution network graph model construction method of the embodiment of the present application is not only applicable to the distribution network topology of the target area, but also to other more complex distribution network topologies.

[0055] Step S2, detecting the voltage of the load node in the distribution network diagram model to obtain a voltage anomaly diagnosis candidate set.

[0056] In an embodiment of the present application, based on the distribution network graph model, the power supply nodes, intermediate nodes, load nodes and power supply branches of the distribution network can be determined.

[0057] For example, Figure 2The middle power source node is node 1, the intermediate nodes are nodes 2, 3 and 6, the load nodes are 4 and 5, and the power supply branch is the path between any two nodes. The power supply branch can represent overhead lines, underground cables, cables, etc. The load node actually corresponds to the pure load node in the distribution network, the generator node with given active and reactive output, and the contact node with zero injected active and reactive power.

[0058] The voltage of the load node, i.e., the terminal voltage of the distribution network, is detected by the sensor to obtain the load node voltage data. Then, based on the preset reference voltage interval, the voltage of each load node is compared with the corresponding reference voltage interval, and the load node exceeding the reference voltage interval is determined as the load node with abnormal voltage in the distribution network diagram model.

[0059] Then, based on the distribution network graph model, the power supply branch where each load node with voltage abnormality is located is determined and recorded as the first branch. Then, through the load node with voltage abnormality, the power supply branch connected to the first branch in the distribution network graph model is screened to obtain the branch to be detected. According to the branch to be detected, a voltage abnormality diagnosis candidate set is obtained.

[0060] For example, in Figure 2 In the example, the voltages of load nodes 4 and 5 are detected and recorded as V4 and V5 respectively, and compared with the reference voltage range of their respective nodes. The specific comparison results are as follows:

[0061] Case 1: If the comparison result shows that V4 is abnormal and V5 is normal, then the voltage abnormality diagnosis candidate set in this case is S={L4}, that is, the power supply branch from node 1 to node 5 has no voltage abnormality, and the power supply branch from node 1 to node 4 may have voltage abnormality.

[0062] Case 2: If the comparison result shows that V4 is normal and V5 is abnormal, then the voltage abnormality diagnosis candidate set in this case is S = {L2, L3, L5, L6}, that is, one or more of the multiple power supply branches from node 1 to node 5 may have voltage abnormalities, and the power supply branch from node 1 to node 4 has no voltage abnormalities.

[0063] Case 3: If the comparison result shows that both V4 and V5 are normal, it is considered that there is no voltage anomaly in the distribution network. In this case, the voltage anomaly diagnosis candidate set is an empty set.

[0064] It should be noted that the reference voltage intervals of the above-mentioned voltages V4 and V5 are all set as a reference voltage hysteresis interval rather than a single voltage value; when the voltage V4 or V5 exceeds its respective reference voltage hysteresis interval, the voltage V4 or V5 is deemed to be abnormal, and when the voltage V4 or V5 is within its respective reference voltage hysteresis interval, the voltage V4 or V5 is deemed to be normal.

[0065] Step S3, diagnose the branches to be detected in the voltage anomaly diagnosis candidate set by using a hierarchical backtracking screening algorithm to obtain a voltage anomaly location result.

[0066] In the embodiment of the present application, it is first determined whether the element data in the voltage anomaly diagnosis candidate set is greater than 1. If it is less than 1, the power supply branch where the voltage anomaly occurs can be directly determined, and the voltage anomaly positioning result can be directly obtained.

[0067] If it is greater than 1, it is necessary to diagnose the branches to be detected in the voltage anomaly diagnosis candidate set through a hierarchical backtracking screening algorithm to obtain the voltage anomaly location result.

[0068] exist Figure 2 Based on the above, taking the second situation in step S2 as an example, since the voltage V4 is normal and the voltage V5 is abnormal, it can be determined that the direct path between the voltage V4 and the power supply node 1 is in normal working state, and the branch branch of the direct path connected to the node 5 is abnormal, so the node 2 should be determined as the starting point of the hierarchical backtracking screening algorithm. Based on the selection of the detection path of node 2, the branch with a larger historical failure rate among the branches L2 and L3 is selected as the element of the selected set for priority diagnosis. For example, if the historical failure rate of the branch L2 is greater than that of the branch L3, the branch L2 is selected to perform voltage anomaly diagnosis first, that is, the voltage of the node 3 is detected and judged whether it is normal. If the voltage of the node 3 is abnormal, the branch L2 is judged as the location where the voltage anomaly occurs in the distribution network. If the voltage of the node 3 is normal, the next level of branches will continue to be diagnosed. Specifically, starting from the starting point 2, ending at the load node 5, and taking the branch L2 as the path, the next level of abnormal diagnosis is continued, that is, the branch L5 which is lower than the branch L2 is diagnosed for voltage abnormality. If the branch L2 has no next-level branches, and there is no other path that can return to the starting point through the undiagnosed branch, it will directly trace back to the starting point 2 and select the undiagnosed branch for diagnosis. If the branch L5 is normal, continue to search for the next-level branch of the branch L5 or other paths that can return to the starting point to perform adjacent branch diagnosis.

[0069] because Figure 2There is no next-level branch in the middle branch L5, but there is a path (L6-L3) starting from the load node V5 with voltage anomaly, ending at starting point 2, and returning to the starting point via the undiagnosed branch. Therefore, the branch adjacent to L5 is selected as the next diagnostic branch in the path that can be traced back to node 2 from branch L5, that is, voltage anomaly diagnosis is performed on branch L6. Here, if there is more than one diagnostic branch in the branch adjacent to L5, the branch with a higher historical failure rate is selected as the priority diagnostic branch for abnormality diagnosis. If branch L6 is diagnosed as normal, the branch with a higher probability of historical failure in the path tracing back to node 2 is continued to be searched as the next diagnostic branch, because Figure 2 Only branch L3 has not been diagnosed, so the voltage anomaly diagnosis is performed on branch L3 until the location of the distribution network voltage anomaly diagnosis is diagnosed, and the power supply branch with voltage anomaly is determined.

[0070] Step S4: formulate a distribution network maintenance plan based on the voltage anomaly location result.

[0071] In an embodiment of the present application, a distribution network maintenance plan is formulated for a maintenance team based on the voltage anomaly location results of the distribution network so that the distribution network anomalies can be resolved in a timely manner.

[0072] Implementing the embodiments of the present application has the following beneficial effects:

[0073] The embodiment of the present application first constructs a graphical model that accurately describes the information of the distribution network based on the geographical topology of the distribution network, and then performs voltage detection on the load nodes of the distribution network based on the graphical model, determines the power supply branches that may have voltage abnormalities through the load nodes with voltage abnormalities, and puts these power supply branches into the voltage abnormality diagnosis candidate set to provide data support for subsequent branch detection. Then, through the hierarchical backtracking screening algorithm, and supplemented by the historical failure rate of the branch, the power supply branches that may have voltage abnormalities are diagnosed in sequence. Only certain power supply branches need to be detected to accurately obtain the voltage abnormality location result, and there is no need for neural networks to detect all power supply branches, saving a lot of computing resources, and no parameter setting is required during the detection process, reducing the risk of detection errors caused by parameter setting problems.

[0074] Second embodiment

[0075] Furthermore, in order to execute the distribution network voltage anomaly diagnosis system based on the graphical model corresponding to the above method embodiment to achieve corresponding functions and technical effects, Figure 3 A structural diagram of a distribution network voltage anomaly diagnosis system based on a graphical model is provided. For ease of description, only the parts related to this embodiment are shown. The distribution network voltage anomaly diagnosis system based on a graphical model provided in the embodiment of the present application includes:

[0076] The graph model building module 201 is used to build a distribution network graph model according to the geographical topology of the distribution network.

[0077] In the embodiment of the present application, a distribution network graph model is first constructed based on the distribution network geographical topology of the target area. In the process of constructing the distribution network geographical topology, it is necessary to obtain the geographical location topology of the distribution transformers, overhead lines, cables, disconnectors, power loads, etc. of the distribution network.

[0078] The abnormal diagnosis candidate set construction module 202 is used to detect the voltage of the load node in the distribution network diagram model to obtain the voltage abnormality diagnosis candidate set.

[0079] In an embodiment of the present application, the voltage of the load nodes in the distribution network diagram model is obtained; based on a preset reference voltage interval, the voltage of each load node is compared with the corresponding reference voltage interval to determine the load nodes with abnormal voltage in the distribution network diagram model; the power supply branches of the distribution network diagram model are screened according to the load nodes with abnormal voltage to obtain a selected set for voltage abnormality diagnosis.

[0080] The abnormality location result acquisition module 203 is used to diagnose the branches to be detected in the voltage abnormality diagnosis candidate set through a hierarchical backtracking screening algorithm to obtain the voltage abnormality location result.

[0081] In an embodiment of the present application, a starting point is selected from the non-load nodes of the branch to be detected; starting from the starting point, with the load node with voltage abnormality corresponding to the starting point as the end point, the non-load nodes of all branches to be detected are diagnosed for abnormality through a hierarchical backtracking screening algorithm to determine the power supply branch with voltage abnormality; based on all the power supply branches with voltage abnormalities, the voltage anomaly positioning result is determined.

[0082] The distribution network maintenance module 204 is used to formulate a distribution network maintenance plan according to the voltage anomaly location result.

[0083] In an embodiment of the present application, a distribution network maintenance plan is formulated for a maintenance team based on the voltage anomaly location results of the distribution network so that the distribution network anomalies can be resolved in a timely manner.

[0084] In some embodiments, the abnormal diagnosis candidate set construction module 202 is specifically:

[0085] In the embodiment of the present application, based on the distribution network graph model, the power source nodes, intermediate nodes, load nodes and power supply branches of the distribution network can be determined. The power supply branches can represent overhead lines, underground cables, cables, etc.; the load nodes actually correspond to the pure load nodes in the distribution network, the generator nodes with given active and reactive outputs, and the connection nodes with zero injected active and reactive power.

[0086] The voltage of the load node, i.e., the terminal voltage of the distribution network, is detected by the sensor to obtain the load node voltage data. Then, based on the preset reference voltage interval, the voltage of each load node is compared with the corresponding reference voltage interval, and the load node exceeding the reference voltage interval is determined as the load node with abnormal voltage in the distribution network diagram model.

[0087] Then, based on the distribution network graph model, the power supply branch where each load node with voltage abnormality is located is determined and recorded as the first branch. Then, through the load node with voltage abnormality, the power supply branch connected to the first branch in the distribution network graph model is screened to obtain the branch to be detected. According to the branch to be detected, a voltage abnormality diagnosis candidate set is obtained.

[0088] Exemplarily, the voltages of load nodes 4 and 5 are detected, respectively denoted as V4 and V5, and compared with the reference voltage ranges of the respective nodes. The specific comparison results are as follows:

[0089] Case 1: If the comparison result shows that V4 is abnormal and V5 is normal, then in this case, the voltage anomaly diagnosis candidate set is all connected power supply branches from the non-load node to node 4, and these power supply branches may have voltage anomalies.

[0090] Case 2: If the comparison result shows that V4 is normal but V5 is abnormal, then in this case, the voltage anomaly diagnosis candidate set is all connected power supply branches from the non-load node to node 5, and these power supply branches may have voltage anomalies.

[0091] Case 3: If the comparison result shows that both V4 and V5 are normal, it is considered that there is no voltage anomaly in the distribution network. In this case, the voltage anomaly diagnosis candidate set is an empty set.

[0092] It should be noted that the reference voltage intervals of the above-mentioned voltages V4 and V5 are all set as a reference voltage hysteresis interval rather than a single voltage value; when the voltage V4 or V5 exceeds its respective reference voltage hysteresis interval, the voltage V4 or V5 is deemed to be abnormal, and when the voltage V4 or V5 is within its respective reference voltage hysteresis interval, the voltage V4 or V5 is deemed to be normal.

[0093] In some embodiments, the abnormality location result acquisition module 203 is specifically:

[0094] In the embodiment of the present application, it is first determined whether the element data in the voltage anomaly diagnosis candidate set is greater than 1. If it is less than 1, the power supply branch where the voltage anomaly occurs can be directly determined, and the voltage anomaly positioning result can be directly obtained.

[0095] If it is greater than 1, it is necessary to diagnose the branches to be detected in the voltage anomaly diagnosis candidate set through the hierarchical backtracking screening algorithm to obtain the voltage anomaly location result. The specific steps are as follows:

[0096] (1) selecting a starting point from the non-load nodes of the branch to be detected; taking the starting point as the starting point and the load node with abnormal voltage corresponding to the starting point as the end point, selecting the second branch with the highest branch history failure rate among the branches directly connected to the starting point for abnormal diagnosis;

[0097] (2) If an abnormality is diagnosed, the voltage abnormality location result is directly determined; if no abnormality is diagnosed, it is determined whether the second branch has a next-level adjacent branch with the starting point as the starting point, the second branch as the passing path, and the load node with the voltage abnormality as the end point. If so, the branch with a larger historical failure rate among the next-level adjacent branches is used as the third branch for abnormality diagnosis until a directly connected branch of the load node with the voltage abnormality is diagnosed; if not, it is determined whether there is an undiagnosed branch with the load node with the voltage abnormality as the starting point and the starting point as the end point;

[0098] (3) If there are no undiagnosed branches, the starting point is taken as the starting point again, the load node with the voltage abnormality is taken as the end point, and the undiagnosed branch with the highest historical failure rate is selected as the fourth branch to continue diagnosis; if there are undiagnosed branches, the branch with the highest historical failure rate among the undiagnosed branches is selected as the fifth branch to perform abnormality diagnosis;

[0099] (4) If an abnormality is diagnosed, the voltage abnormality location result is directly determined; if no abnormality is diagnosed, it is determined whether the fifth branch has an upper-level adjacent branch with the load node of the voltage abnormality as the starting point, the fifth branch as the passing path, and the starting point as the end point; if so, the branch with the largest historical failure rate among the upper-level adjacent branches is used as the sixth branch for abnormality diagnosis until the directly connected branch of the starting point is diagnosed; if not, the voltage abnormality location result is output.

[0100] Implementing the embodiments of the present application has the following beneficial effects:

[0101] The embodiment of the present application first constructs a graphical model that accurately describes the information of the distribution network based on the geographical topology of the distribution network, and then performs voltage detection on the load nodes of the distribution network based on the graphical model, determines the power supply branches that may have voltage abnormalities through the load nodes with voltage abnormalities, and puts these power supply branches into the voltage abnormality diagnosis candidate set to provide data support for subsequent branch detection. Then, the power supply branches that may have voltage abnormalities are diagnosed with voltage abnormalities in turn through the hierarchical backtracking screening algorithm. Only certain power supply branches need to be detected to accurately obtain the voltage abnormality location result, and there is no need for neural networks to detect all power supply branches, which saves a lot of computing resources, and no parameter setting is required during the detection process, reducing the risk of detection errors caused by parameter setting problems.

[0102] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A distribution network voltage anomaly diagnosis method based on a graphical model, characterized in that: include: According to the geographical topology of the distribution network, a distribution network graph model is constructed; Detect the voltage of the load node in the distribution network diagram model and obtain a voltage anomaly diagnosis candidate set; The branches to be detected in the voltage anomaly diagnosis candidate set are diagnosed through a hierarchical backtracking screening algorithm to obtain the voltage anomaly location result; Develop a distribution network maintenance plan based on the voltage anomaly location results.

2. The method for diagnosing abnormal voltage in distribution network based on graphical model according to claim 1, characterized in that: The voltage of the load node in the distribution network diagram model is detected to obtain a voltage anomaly diagnosis candidate set, which is specifically: Obtain the voltage of the load node in the distribution network diagram model; Based on a preset reference voltage interval, the voltage of each load node is compared with the corresponding reference voltage interval to determine the load nodes with abnormal voltage in the distribution network diagram model; The power supply branches of the distribution network diagram model are screened according to the load nodes with abnormal voltage to obtain a voltage abnormality diagnosis candidate set.

3. The method for diagnosing abnormal voltage in distribution network based on graphical model according to claim 2, characterized in that: The power supply branches of the distribution network diagram model are screened according to the load nodes with abnormal voltage to obtain a voltage abnormality diagnosis candidate set, which is specifically: Based on the distribution network graph model, determine the power supply branch where each load node with abnormal voltage is located, which is recorded as the first branch; Through the load node with abnormal voltage, the power supply branch connected with the first branch in the distribution network diagram model is screened to obtain a branch to be detected; According to the branch to be detected, a voltage anomaly diagnosis candidate set is obtained.

4. The method for diagnosing abnormal voltage in distribution network based on graphical model according to claim 1, characterized in that: The hierarchical backtracking screening algorithm is used to diagnose the branches to be detected in the voltage anomaly diagnosis candidate set to obtain the voltage anomaly location result, which is specifically: Select a starting point from the non-load nodes of the branch to be detected; Taking the starting point as the starting point and the load node with voltage abnormality corresponding to the starting point as the end point, the non-load nodes of all branches to be detected are diagnosed for abnormality through a hierarchical backtracking screening algorithm to determine the power supply branch with voltage abnormality; The voltage anomaly location result is determined based on all power supply branches with voltage anomalies.

5. The method for diagnosing abnormal voltage in distribution network based on graphical model according to claim 4, characterized in that: The method of performing abnormal diagnosis on the non-load nodes of all branches to be detected by using a hierarchical backtracking screening algorithm to determine the power supply branch with abnormal voltage is specifically as follows: Based on the historical failure rate of the branch, an abnormality diagnosis is performed on the second branch where the starting point is located; wherein, among all the branches to be detected where the starting point is located, the second branch has the highest historical failure rate of the branch; If the second branch has a voltage abnormality, stop the abnormality diagnosis, and determine that the second branch is a power supply branch with a voltage abnormality; If the second branch does not have voltage abnormality, abnormality diagnosis is performed on the next level of branches to be detected of the second branch until a power supply branch with voltage abnormality is determined.

6. A distribution network voltage anomaly diagnosis system based on a graphical model, characterized in that: include: Graph model construction module, abnormal diagnosis candidate set construction module, abnormal location result acquisition module and distribution network maintenance module; Wherein, the graph model construction module is used to construct a distribution network graph model according to the geographical topology of the distribution network; The abnormal diagnosis candidate set construction module is used to detect the voltage of the load node in the distribution network diagram model to obtain the voltage abnormal diagnosis candidate set; The abnormality location result acquisition module is used to diagnose the branches to be detected in the voltage abnormality diagnosis candidate set through a hierarchical backtracking screening algorithm to obtain a voltage abnormality location result; The distribution network maintenance module is used to formulate a distribution network maintenance plan according to the voltage anomaly positioning result.

7. The distribution network voltage anomaly diagnosis system based on the graphical model according to claim 6, characterized in that: The abnormal diagnosis candidate set construction module includes: a voltage anomaly detection unit; Among them, the voltage anomaly detection unit is used to obtain the voltage of the load node in the distribution network diagram model; based on the preset reference voltage interval, the voltage of each load node is compared with the corresponding reference voltage interval to determine the load node with voltage abnormality in the distribution network diagram model; according to the load node with voltage abnormality, the power supply branch of the distribution network diagram model is screened to obtain the voltage anomaly diagnosis candidate set.

8. The distribution network voltage anomaly diagnosis system based on the graphical model according to claim 7 is characterized in that: The abnormal diagnosis candidate set construction module includes: a branch acquisition unit to be detected; Among them, the to-be-detected branch acquisition unit is used to determine the power supply branch where each load node with voltage abnormality is located based on the distribution network graph model, which is recorded as the first branch; through the load node with voltage abnormality, the power supply branch connected to the first branch in the distribution network graph model is screened to obtain the to-be-detected branch; according to the to-be-detected branch, a voltage abnormality diagnosis candidate set is obtained.

9. The distribution network voltage anomaly diagnosis system based on a graphical model according to claim 6, characterized in that: The abnormal location result acquisition module includes: a voltage abnormal branch determination unit; Among them, the voltage abnormal branch determination unit is used to select a starting point from the non-load nodes of the branch to be detected; taking the starting point as the starting point and the load node with voltage abnormality corresponding to the starting point as the end point, the non-load nodes of all branches to be detected are diagnosed for abnormality through a hierarchical backtracking screening algorithm to determine the power supply branch with voltage abnormality; based on all the power supply branches with voltage abnormalities, the voltage anomaly positioning result is determined.

10. The distribution network voltage anomaly diagnosis system based on the graphical model according to claim 9, characterized in that: The abnormality location result acquisition module includes: a branch level detection unit; Among them, the branch level detection unit is used to perform abnormal diagnosis on the second branch where the starting point is located based on the historical failure rate of the branch; wherein, among all the branches to be detected where the starting point is located, the branch historical failure rate of the second branch is the highest; if there is a voltage abnormality in the second branch, the abnormal diagnosis is stopped, and the second branch is determined to be a power supply branch with a voltage abnormality; if there is no voltage abnormality in the second branch, the next level of branches to be detected of the second branch are subjected to abnormal diagnosis until a power supply branch with a voltage abnormality is determined.

Images