A method, device, equipment and medium for topology verification of a distribution network substation area

Abstract

The present invention discloses a method, device, equipment and medium for topology verification of a distribution network substation area. The topology of the distribution network substation area includes multiple topology nodes. The method includes: obtaining voltage information corresponding to each topology node during the occurrence period of a preset change event; trimming the voltage information to generate an information-rich entropy segment and calculating the voltage information entropy corresponding to the information-rich entropy segment; clustering the topology nodes according to the voltage information mean and voltage information entropy corresponding to the information-rich entropy segments of any two topology nodes to obtain multiple node clustering clusters; calculating the node correlation degrees corresponding to the topology nodes within each node clustering cluster, and determining target abnormal nodes according to the node correlation degrees, so as to quickly and accurately perform topology verification of the substation area while ensuring that the calculation time and verification calculation amount required by the substation area topology verification method are relatively low.

Description

Technical Field

[0001] The present invention relates to the technical field of substation area topology verification, and particularly to a method, device, equipment and medium for verifying the topology of a distribution network substation area. Background Art

[0002] With the continuous development of the distribution network, good achievements have been made in various fields. However, there is still a large gap between the low-voltage part of the distribution network and the transmission network in terms of construction and maintenance. For example, the topological information of the network has not been fully digitized, and there are missing and many errors in the substation area file data, resulting in the inability to achieve the integration of operation and distribution and integrated operation and maintenance.

[0003] At present, power grid enterprises promote the digitalization of the physical power grid through the construction of the ubiquitous power Internet of Things and the digital power grid. Based on the fusion terminal of the distribution network gateway, combined with broadband carrier and new intelligent meters, the automatic identification of the topological relationship of the substation area is realized, and the full amount of data of the substation area is obtained to carry out intelligent operation and maintenance of the substation area. However, due to the rapid change of the load in the substation area, the business expansion and transformation will cause frequent changes in the topology of the substation area, and a self-verification mechanism for the substation area topology needs to be established to regularly identify incorrect topologies.

[0004] Therefore, at the present stage, the Pearson correlation coefficient or the Fréchet distance of voltage time series data is mainly used to determine the similarity between the transformer substation and users, a multiple regression model is established using voltage data, and the solution is carried out with the optimization goal of minimizing the sum of the squared residuals of the equations established for each branch line, or the Kmeans clustering analysis method is used to classify the transformer substation and users on the same branch into the same category. However, the above methods require a long calculation time and a large verification calculation amount, and it is difficult to quickly and accurately verify the topology of the substation area. Summary of the Invention

[0005] The present invention provides a method, device, equipment and medium for verifying the topology of a distribution network substation area, and solves the technical problem that the existing methods for verifying the topology of the substation area require a long calculation time and a large verification calculation amount, and it is difficult to quickly and accurately verify the topology of the substation area.

[0006] A method for verifying the topology of a distribution network substation area provided in the first aspect of the present invention, wherein the distribution network substation area topology includes multiple topological nodes, and the method includes:

[0007] Obtain the voltage information corresponding to each of the topological nodes during the occurrence period of a preset change event;

[0008] Crop the voltage information to generate an information-rich entropy segment and calculate the voltage information entropy corresponding to the information-rich entropy segment;

[0009] Cluster the topological nodes according to the voltage information mean and the voltage information entropy corresponding to the information-rich entropy segment of any two of the topological nodes to obtain multiple node clustering clusters;

[0010] Calculate the node correlation degrees corresponding to the topological nodes within each of the node clustering clusters, and determine the target abnormal nodes according to the node correlation degrees.

[0011] Optionally, the voltage information includes multiple voltage point information; the step of clipping the voltage information, generating an information-rich entropy segment, and calculating the voltage information entropy corresponding to the information-rich entropy segment includes:

[0012] Divide the multiple voltage point information according to a preset number of point information to obtain multiple segments of voltage point information segments;

[0013] Based on the extreme value detection results of each of the voltage point information segments, determine the information-rich entropy segment from the multiple voltage point information segments;

[0014] Use a preset voltage point information entropy calculation formula to calculate the voltage point information entropies corresponding to each voltage point information in the information-rich entropy segment;

[0015] Calculate the variance of all the voltage point information entropies to obtain the voltage information entropy corresponding to the information-rich entropy segment;

[0016] The voltage point information entropy calculation formula is:

[0017]

[0018] where en i is the voltage point information entropy corresponding to the i-th voltage point information, (u i-t , u i+t ) represents the information complexity within the range of t voltage point information on both the left and right sides of the voltage point information u i , Var is the variance calculation formula, and m is the number of the point information.

[0019] Optionally, the step of determining the information-rich entropy segment from the multiple voltage point information segments based on the extreme value detection results of each of the voltage point information segments includes:

[0020] Detect whether there are extreme value voltage point information with a preset number of extreme values in each of the voltage point information segments;

[0021] If the voltage point information segment has the extreme value voltage point information with the number of extreme values, detect whether the extreme value voltage point information exists continuously;

[0022] If it is detected that the extreme value voltage point information exists continuously, determine the voltage point information segment as the information-rich entropy segment;

[0023] If the extreme value voltage point information of the extreme value quantity does not exist in the voltage point information segment, or the extreme value voltage point information does not exist continuously, then the voltage point information segment is determined as a non-information-rich entropy segment.

[0024] Optionally, the step of clustering the topological nodes according to the voltage information mean value and the voltage information entropy corresponding to the information-rich entropy segment of any two of the topological nodes to obtain a plurality of node clustering clusters includes:

[0025] Determine the matching degree between any two of the topological nodes according to the voltage information mean value and the voltage information entropy corresponding to the information-rich entropy segment of any two of the topological nodes;

[0026] Cluster the topological nodes according to the matching degree between any two of the topological nodes to obtain a plurality of node clustering clusters.

[0027] Optionally, the step of determining the matching degree between any two of the topological nodes according to the voltage information mean value and the voltage information entropy corresponding to the information-rich entropy segment of any two of the topological nodes includes:

[0028] Use the voltage information mean values corresponding to any two of the topological nodes in the information-rich entropy segment to calculate the information square difference between the voltage information mean values;

[0029] Calculate the information square root corresponding to the information square difference;

[0030] Select the maximum voltage information entropy from the voltage information entropy corresponding to the information-rich entropy segment;

[0031] Calculate the information ratio between the information square root and the maximum voltage information entropy, and use the information ratio to determine the matching degree between any two of the topological nodes.

[0032] Optionally, the step of clustering the topological nodes according to the matching degree between any two of the topological nodes to obtain a plurality of node clustering clusters includes:

[0033] Connect any two of the topological nodes with a matching degree greater than or equal to a preset first matching degree threshold to obtain an initial topological graph;

[0034] Successively select the topological nodes in the initial topological graph as target topological nodes, and select the topological nodes connected to the target topological nodes as to-be-determined topological nodes;

[0035] Judge whether the matching degree between the target topological node and the to-be-determined topological node is greater than or equal to a preset second matching degree threshold;

[0036] If so, classify the to-be-determined topological node into the node clustering cluster corresponding to the target topological node.

[0037] Optionally, the step of calculating the node association degrees corresponding to the topological nodes in each node clustering cluster and determining the target abnormal node according to the node association degrees includes:

[0038] Respectively obtain the number of associated edges and the number of topological nodes corresponding to each topological node in each node clustering cluster, and determine the number of associated edges as the node association degree corresponding to each topological node;

[0039] Use the number of topological nodes and a preset association degree parameter to determine an association degree threshold;

[0040] Compare each node association degree with the association degree threshold;

[0041] If the node association degree is less than the association degree threshold, determine the topological node corresponding to the node association degree as the target abnormal node.

[0042] A distribution network substation area topology verification device provided in the second aspect of the present invention, the distribution network substation area topology includes multiple topological nodes, and the device includes:

[0043] A voltage information acquisition module, configured to acquire voltage information corresponding to each topological node during the occurrence period of a preset change event;

[0044] A voltage information entropy calculation module, configured to clip the voltage information, generate an information-rich entropy segment, and calculate the voltage information entropy corresponding to the information-rich entropy segment;

[0045] A node clustering module, configured to determine the matching degree between any two topological nodes according to the voltage information mean value and the voltage information entropy corresponding to the information-rich entropy segment of the two topological nodes;

[0046] An abnormal node determination module, configured to calculate the node association degrees corresponding to the topological nodes in each node clustering cluster, and determine the target abnormal node according to the node association degrees.

[0047] An electronic device provided in the third aspect of the present invention includes a memory and a processor, and a computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the distribution network substation area topology verification method as described in the first aspect of the present invention.

[0048] A computer-readable storage medium provided in the fourth aspect of the present invention has a computer program stored thereon. When the computer program is executed, it implements the distribution network substation area topology verification method as described in any one of the first aspects of the present invention.

[0049] As can be seen from the above technical solutions, the present invention has the following advantages:

[0050] The present invention monitors in real time whether a plurality of topology nodes included in the topology of a distribution network area have preset change events. If it is detected that any topology node has a change event, the voltage information of the topology node during the occurrence period of the change event is obtained, and then the voltage information is trimmed to obtain information-rich entropy segments corresponding to each topology node. At the same time, the voltage information entropy corresponding to the information-rich entropy segment is calculated. Based on the voltage information mean value and voltage information entropy corresponding to any two voltage information entropies, the topology nodes to which they belong are clustered, thereby obtaining a plurality of node clustering clusters; finally, the node association degree corresponding to the topology node is determined according to the number of associations between each topology node in the node clustering cluster and other topology nodes, and the target abnormal node is determined according to the comparison result between the node association degree and the association degree threshold corresponding to the node clustering cluster, so as to realize the analysis and verification of all topology nodes in the topology of the distribution network area at one time, while ensuring that the calculation time and verification calculation amount required by the area topology verification method are relatively low, and quickly and accurately performing the area topology verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a flowchart of the steps of a method for verifying the topology of a distribution network area provided in Embodiment 1 of the present invention

[0053] Figure 2 It is a flowchart of the steps of a method for verifying the topology of a distribution network area provided in Embodiment 2 of the present invention.

[0054] Figure 3 It is a structural block diagram of a device for verifying the topology of a distribution network area provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The embodiments of the present invention provide a method, device, equipment and medium for verifying the topology of a distribution network area, which are used to solve the technical problems that the existing area topology verification method requires a long calculation time and a large verification calculation amount, and it is difficult to quickly and accurately perform the area topology verification.

[0056] In order to make the object, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0057] Please refer to Figure 1 , Figure 1 which is a flowchart of the steps of a method for checking the topology of a distribution network substation area provided in Embodiment 1 of the present invention.

[0058] A method for checking the topology of a distribution network substation area provided by the present invention, where the topology of the distribution network substation area includes multiple topology nodes. The method includes the following steps:

[0059] Step 101: Obtain the voltage information corresponding to each topology node during the occurrence period of a preset change event;

[0060] In the embodiments of the present invention, the topology of the distribution network substation area refers to a method of studying the relationship between points and lines that is independent of size and shape in topology. Each distribution network terminal in the distribution network, such as a transformer, a fusion terminal, an electric meter, etc., is abstracted as a topology node, and the transmission medium or connection relationship is abstracted as a line. The geometric figure composed of points and lines, and the topological structure of the network reflects the structural relationship of each entity in the distribution network.

[0061] In the embodiments of the present invention, in order to implement the verification of the topology of the distribution network substation area, when it is detected that any topology node has a preset change event, the voltage information corresponding to each topology node during the occurrence period of the change event is obtained.

[0062] It should be noted that the preset change events may include, but are not limited to: (1) the load of the substation area is greater than the preset load peak value; (2) the voltage in the substation area is lower than the preset voltage threshold; (3) the output of the distributed power source in the substation area is greater than the preset output threshold; (4) the transformer tap or the capacity of the reactive power compensation device is adjusted.

[0063] Step 102: Clip the voltage information to generate an information-rich entropy segment and calculate the voltage information entropy corresponding to the information-rich entropy segment;

[0064] The information-rich entropy segment refers to an information segment composed of voltage point information with more information in the voltage information. The voltage information entropy refers to the sum of the voltage point information entropies corresponding to each voltage point information in the information-rich entropy segment. The information entropy refers to the probability of a certain specific information appearing in a segment of information, which increases with the increase of the probability and is used to measure the level of information value.

[0065] After obtaining the voltage information of each topological node during the occurrence period of the change event, in order to reduce the amount of subsequent information processing and improve the calculation speed, the voltage information can be further trimmed to obtain at least one information-rich entropy segment in the voltage information, and calculate the voltage point information entropy corresponding to each voltage information point in each information-rich entropy segment, and sum up the voltage point information entropy to obtain the corresponding voltage information entropy.

[0066] Step 103: Cluster the topological nodes according to the voltage information mean and voltage information entropy of the information-rich entropy segments corresponding to any two topological nodes, and obtain multiple node clustering clusters;

[0067] After obtaining the voltage information entropy corresponding to each information-rich entropy segment, the voltage information mean of the information-rich entropy segment can be calculated by combining the voltage information corresponding to each voltage point in the information-rich entropy segment. Calculate the matching degree between the topological nodes to which the information-rich entropy segments belong according to the voltage information entropy and voltage information mean of any two information-rich entropy segments, and cluster the topological nodes based on the matching degree to obtain multiple node clustering clusters, so as to determine the other topological nodes associated with it and classify them with the topological node as the center.

[0068] Step 104: Calculate the node association degree corresponding to the topological nodes in each node clustering cluster, and determine the target abnormal node according to the node association degree.

[0069] In a specific implementation, after obtaining multiple node clustering clusters, the association relationship between the topological nodes included therein and other topological nodes can be used to determine the node association degree corresponding to each topological node. Finally, according to the comparison result of the node association degree and the association degree threshold corresponding to each node clustering cluster, the target abnormal node is determined, so as to realize the verification of the distribution network station area topology and quickly and accurately determine the topological nodes that need to be repeatedly verified from it.

[0070] In an embodiment of the present invention, by real-time monitoring of whether a preset change event occurs in multiple topological nodes included in the distribution network substation topology, if a change event is detected for any topological node, the voltage information of the topological node during the period of the change event is obtained, and then the voltage information is trimmed to obtain the information rich entropy segment corresponding to each topological node. At the same time, the voltage information entropy corresponding to the information rich entropy segment is calculated, and based on the voltage information mean and the voltage information entropy corresponding to any two voltage information entropies, the topological nodes to which they belong are clustered, thereby obtaining multiple node clustering clusters; finally, the node association degree corresponding to the topological node is determined according to the number of associations between each topological node in the node clustering cluster and other topological nodes, and the target abnormal node is determined according to the comparison result of the node association degree and the association degree threshold corresponding to the node clustering cluster, thereby realizing a one-time analysis and verification of all topological nodes in the distribution network substation topology, while ensuring that the calculation time and verification calculation amount required by the substation topology verification method are low, the substation topology verification is performed quickly and accurately.

[0071] See also Figure 2 , Figure 2 This is a flowchart of the steps of a distribution network substation topology verification method provided in the second embodiment of the present invention.

[0072] The present invention provides a method for verifying the topology of a distribution network area, wherein the topology of the distribution network area includes multiple topological nodes, and the method includes the following steps:

[0073] Step 201: Obtain voltage information corresponding to each topological node during a period of occurrence of a preset change event;

[0074] In an embodiment of the present invention, the distribution network area topology refers to a method in topology that studies the relationship between points and lines that is independent of size and shape. Each distribution network terminal in the distribution network, such as a transformer, a fusion terminal, and an electric meter, is abstracted as a topological node, and the transmission medium or connection relationship is abstracted as a line, a geometric figure composed of points and lines, and the topological structure of the network reflects the structural relationship between each entity in the distribution network.

[0075] In an embodiment of the present invention, in order to verify the topology of the distribution network area, when a preset change event is detected at any topology node, the voltage information corresponding to each topology node during the period of occurrence of the change event is obtained.

[0076] It should be noted that the preset change events may include but are not limited to: (1) the load in the substation is greater than the preset load peak; (2) the voltage in the substation is lower than the preset voltage threshold; (3) the output of the distributed power source in the substation is greater than the preset output threshold; (4) the transformer tap or the capacity of the reactive compensation device is adjusted.

[0077] Step 202: Clip the voltage information to generate an information-rich entropy segment and calculate the voltage information entropy corresponding to the information-rich entropy segment.

[0078] Optionally, the voltage information includes multiple voltage point information. Step 202 may include the following sub-steps S11 - S14:

[0079] S11: Divide the multiple voltage point information according to the preset number of point information to obtain multiple segments of voltage point information segments.

[0080] S12: Based on the extreme value detection results of each segment of voltage point information segments, determine the information-rich entropy segment from the multiple segments of voltage point information segments.

[0081] In the embodiments of the present invention, after obtaining the voltage information of the topological node during the occurrence period of the change event, divide the multiple voltage point information in the voltage information according to the preset number of point information to obtain multiple segments of voltage point information segments. Further, to determine the clipping position of the information-rich entropy segment, extreme value detection can be performed on each segment of voltage point information segments respectively to determine whether there are preset extreme value numbers and continuous extreme value voltage point information in each segment of voltage point information segments, and determine the information-rich entropy segment from the multiple segments of voltage point information segments.

[0082] Further, step S12 may include the following sub-steps:

[0083] Detect whether there is preset extreme value number of extreme value voltage point information in each segment of voltage point information segments;

[0084] If the voltage point information segment has extreme value number of extreme value voltage point information, then detect whether the extreme value voltage point information exists continuously;

[0085] If it is detected that the extreme value voltage point information exists continuously, then determine the voltage point information segment as the information-rich entropy segment;

[0086] If the voltage point information segment does not have extreme value number of extreme value voltage point information, or the extreme value voltage point information does not exist continuously, then determine the voltage point information segment as a non-information-rich entropy segment.

[0087] In a specific implementation, after obtaining multiple segments of voltage point information segments, detect one by one whether there is preset extreme value number of extreme value voltage point information in each segment of voltage point information segments. If so, further detect whether the extreme value voltage point information appears or exists continuously. If so, determine the voltage point information segment to which the extreme value voltage point information belongs as the information-rich entropy segment.

[0088] At the same time, if the voltage point information segment does not have extreme value number of extreme value voltage point information, or the extreme value voltage point information does not exist continuously, then determine the corresponding voltage point information segment as a non-information-rich entropy segment and do not perform further processing.

[0089] It should be noted that to improve the operation efficiency of the present invention, the number of preset point information can be set to 50, and the number of preset extreme values can be set to 6 to 12. The embodiments of the present invention do not limit the specific numerical values.

[0090] S13. Calculate the voltage point information entropy corresponding to each voltage point information in the information-rich entropy segment by using a preset voltage point information entropy calculation formula;

[0091] The voltage point information entropy calculation formula is:

[0092]

[0093] where en i is the voltage point information entropy corresponding to the i-th voltage point information, (u i-t , u i+t ) represents the information complexity within the range of t voltage point information on both the left and right sides of the voltage point information u i , Var is the variance calculation formula, and m is the number of point information.

[0094] In an example of the present invention, after determining at least one information-rich entropy segment corresponding to a topological node, a preset voltage point information entropy calculation formula can be used to calculate the voltage point information entropy corresponding to each voltage point information in the information-rich entropy segment.

[0095] S14. Calculate the variance of all voltage point information entropies to obtain the voltage information entropy corresponding to the information-rich entropy segment;

[0096] In this embodiment, after obtaining the voltage point information entropy corresponding to all voltage point information in the information-rich entropy segment, to determine the voltage information entropy corresponding to the information-rich entropy segment, the variance of all voltage point information entropies is calculated and determined as the voltage information entropy corresponding to the information-rich entropy segment.

[0097] In a specific implementation, the voltage information entropy can be calculated in the following manner:

[0098]

[0099] where Var(en j ) is the voltage information entropy corresponding to the j-th information-rich entropy segment, m is the number of point information, en i is the voltage point information entropy corresponding to the i-th voltage point information, is the information entropy mean value of all voltage point information entropies.

[0100] Step 203. Determine the matching degree between any two topological nodes according to the voltage information mean value and voltage information entropy of the information-rich entropy segments corresponding to the two topological nodes;

[0101] Optionally, step 203 may include the following sub-steps:

[0102] Adopt the mean value of the voltage information of any two information-rich entropy segments corresponding to topological nodes to calculate the information square difference between the mean values of the voltage information;

[0103] Calculate the information square root corresponding to the information square difference;

[0104] Select the maximum voltage information entropy from the voltage information entropy corresponding to the information-rich entropy segment;

[0105] Calculate the information ratio between the information square root and the maximum voltage information entropy, and adopt the information ratio to determine the matching degree between any two topological nodes.

[0106] In the embodiment of the present invention, after obtaining the voltage information entropy corresponding to the information-rich entropy segment corresponding to each topological node, the mean value of the voltage information of the information-rich entropy segment contained therein can be calculated respectively according to each topological node as a category, and the information square difference between the two is calculated by adopting any two voltage means. Further calculate the information square root corresponding to the information square difference. At the same time, select the maximum voltage information entropy from the voltage information entropy corresponding to the information-rich entropy segment, calculate the information ratio between the information square root and the maximum voltage information entropy, and adopt the information ratio to determine the matching degree between any two topological nodes.

[0107] Among them, the mean value of the voltage information can be obtained by calculating the mean value of the voltage point information in the information-rich entropy segment.

[0108] In a specific implementation, the matching degree co ab between any two topological nodes can be determined by the following method:

[0109]

[0110] Among them, is the mean value of the voltage information of the k-th information-rich entropy segment in topological node a, is the mean value of the voltage information of the j-th information entropy segment in topological node b, Var(en k ) is the voltage information entropy of the k-th information-rich entropy segment in topological node a, Var(en j ) is the voltage information entropy of the k-th information-rich entropy segment in topological node a.

[0111] Step 204, cluster the topological nodes according to the matching degree between any two topological nodes to obtain multiple node clustering clusters;

[0112] Further, step 204 may include the following sub-steps:

[0113] Connect any two topological nodes whose connection matching degree is greater than or equal to a preset first matching degree threshold to obtain an initial topological graph;

[0114] Select topological nodes in the initial topological graph as target topological nodes in sequence, and select topological nodes connected to the target topological nodes as to-be-judged topological nodes;

[0115] Judge whether the matching degree between the target topological node and the to-be-judged topological node is greater than or equal to a preset second matching degree threshold;

[0116] If so, classify the to-be-judged topological node into the node clustering cluster corresponding to the target topological node.

[0117] In an example of the present invention, after obtaining the matching degree between any two topological nodes, compare the matching degree with the first matching degree threshold. If the matching degree is greater than or equal to the first matching degree threshold, it indicates that there is a connection relationship between the nodes. At this time, the above two topological nodes can be connected. After traversing all topological nodes, an initial topological graph is obtained to complete the preliminary screening of topological nodes; if the matching degree is less than the first matching degree threshold, the above two topological nodes are not connected. Then, select topological nodes in the initial topological graph as target topological nodes in sequence, and at the same time select topological nodes connected to the target topological nodes as to-be-judged topological nodes; judge whether the matching degree between the target topological node and the to-be-judged topological node is greater than or equal to a preset second matching degree threshold. If so, it indicates that the to-be-judged topological node belongs to a category with a higher matching degree with the target topological node. At this time, it can be classified into the node clustering cluster corresponding to the target topological node. If the matching degree is less than the second matching degree threshold, the to-be-judged topological node is not processed until the matching degrees of all topological nodes are compared with the second matching degree threshold.

[0118] In specific implementation, all topological nodes can be used to form a to-be-analyzed node set X = {x a}, a = 1, 2,... n, and initialize the node clustering cluster

[0119] Select an arbitrary topological node from the set X as the target topological node x a Perform depth-first search, and traverse all topological nodes in X that are connected to it on the left and right as to-be-judged topological nodes x b , if the matching degree between the two is greater than or equal to the threshold δ, then move the node x b from X to the node clustering cluster cluster p

[0120] Traverse all nodes in the set X until X is an empty set, then several clusters cluster are formed p(p = 1, …, P), where P represents the number of node clustering clusters, p is the cluster number, and cluster p contains node c p,j .

[0121] Optionally, before comparing the matching degree and the first matching degree, each topological node can also be randomly arranged to obtain an initial undirected graph of nodes.

[0122] Step 205: Calculate the node association degrees corresponding to the topological nodes within each node clustering cluster, and determine the target abnormal nodes according to the node association degrees.

[0123] Optionally, step 205 may include the following sub-steps:

[0124] Respectively obtain the number of associated edges and the number of topological nodes corresponding to each topological node within each node clustering cluster, and determine the node association degrees corresponding to each topological node as the number of associated edges;

[0125] Use the number of topological nodes and a preset association degree parameter to determine the association degree threshold;

[0126] Compare each node association degree with the association degree threshold;

[0127] If the node association degree is less than the association degree threshold, then determine the topological node corresponding to the node association degree as the target abnormal node.

[0128] In an example of the present invention, respectively obtain the number of associated edges d p,q (q = 1, …, nn p ) and the number of topological nodes nn p corresponding to each topological node within each node clustering cluster, and further use the number of topological nodes and a preset association degree parameter to determine the association degree threshold A:

[0129]

[0130] Among them, Z is a preset association degree parameter, which can take the value of 3, and the specific value is not limited in the embodiments of the present invention.

[0131] By comparing each node association degree with the association degree threshold, if the node association degree is less than the association degree threshold, then determine the topological node corresponding to the node association degree as the target abnormal node.

[0132] In another example of the present invention, if the node association degree d p,j ≥ Z of the topological node, then retain the topological node until all node clustering clusters cluster pAll of them are processed. At this time, each topological node in each node cluster has a station-line-user change relationship. Other topological nodes with a correlation degree less than the correlation threshold are determined as target abnormal nodes and wait for further verification and processing.

[0133] In an embodiment of the present invention, by real-time monitoring of whether a preset change event occurs in multiple topological nodes included in the distribution network substation topology, if a change event is detected for any topological node, the voltage information of the topological node during the period of the change event is obtained, and then the voltage information is trimmed to obtain the information rich entropy segment corresponding to each topological node. At the same time, the voltage information entropy corresponding to the information rich entropy segment is calculated, and based on the voltage information mean and the voltage information entropy corresponding to any two voltage information entropies, the topological nodes to which they belong are clustered, thereby obtaining multiple node clustering clusters; finally, the node association degree corresponding to the topological node is determined according to the number of associations between each topological node in the node clustering cluster and other topological nodes, and the target abnormal node is determined according to the comparison result of the node association degree and the association degree threshold corresponding to the node clustering cluster, thereby realizing a one-time analysis and verification of all topological nodes in the distribution network substation topology, while ensuring that the calculation time and verification calculation amount required by the substation topology verification method are low, the substation topology verification is performed quickly and accurately.

[0134] See also Figure 3 , Figure 3 This is a structural block diagram of a distribution network area topology verification device provided in Example 3 of the present invention.

[0135] An embodiment of the present invention provides a distribution network area topology verification device, wherein the distribution network area topology includes multiple topology nodes, and the device includes:

[0136] The voltage information acquisition module 301 is used to acquire the voltage information corresponding to each topological node during the period of occurrence of a preset change event;

[0137] The voltage information entropy calculation module 302 is used to clip the voltage information, generate information-rich entropy segments, and calculate the voltage information entropy corresponding to the information-rich entropy segments;

[0138] The node clustering module 303 is used to cluster the topological nodes according to the voltage information mean and voltage information entropy of the information-rich entropy segments corresponding to any two topological nodes to obtain multiple node clusters;

[0139] The abnormal node determination module 304 is configured to calculate the node association degree corresponding to the topological nodes in each node cluster, and determine the target abnormal node according to the node association degree.

[0140] Optionally, the voltage information includes information of multiple voltage points; the voltage information entropy calculation module 302 includes:

[0141] The voltage point information segment division sub-module is used to divide multiple voltage point information according to the preset number of point information, and obtain multiple segments of voltage point information segments;

[0142] The information rich entropy segment determination sub-module is used to determine the information rich entropy segment from multiple segments of voltage point information segments based on the extreme value detection results of each segment of voltage point information segments;

[0143] The voltage point information entropy calculation sub-module is used to calculate the voltage point information entropy corresponding to each voltage point information in the information rich entropy segment by using a preset voltage point information entropy calculation formula;

[0144] The voltage information entropy calculation sub-module is used to calculate the variance of all voltage point information entropies, and obtain the voltage information entropy corresponding to the information rich entropy segment;

[0145] The voltage point information entropy calculation formula is:

[0146]

[0147] where, en i is the voltage point information entropy corresponding to the i-th voltage point information, (u i-t , u i+t ) represents the information complexity of the voltage point information u i within the range of t voltage point information on both the left and right sides, Var is the variance calculation formula, and m is the number of point information.

[0148] Optionally, the information rich entropy segment determination sub-module is specifically used for:

[0149] Detect whether there are extreme value voltage point information with a preset number of extreme values in each segment of voltage point information segments;

[0150] If there is extreme value voltage point information with the number of extreme values in the voltage point information segment, detect whether the extreme value voltage point information exists continuously;

[0151] If it is detected that the extreme value voltage point information exists continuously, determine the voltage point information segment as the information rich entropy segment; X

[0152] If there is no extreme value voltage point information with the number of extreme values in the voltage point information segment, or the extreme value voltage point information does not exist continuously, determine the voltage point information segment as a non-information rich entropy segment.

[0153] Optionally, the node clustering module 303 includes:

[0154] The matching degree determination sub-module is used to determine the matching degree between two topological nodes according to the voltage information mean value and voltage information entropy of the information rich entropy segments corresponding to any two topological nodes;

[0155] A node clustering sub-module, which is used to cluster topological nodes according to the matching degree between any two topological nodes, and obtain multiple node clustering clusters.

[0156] Optionally, the matching degree determination sub-module is specifically used for:

[0157] Adopt the mean value of the voltage information of the information-rich entropy segments corresponding to any two topological nodes, and calculate the information square difference between the mean values of the voltage information;

[0158] Calculate the information square root corresponding to the information square difference;

[0159] Select the maximum voltage information entropy from the voltage information entropy corresponding to the information-rich entropy segment;

[0160] Calculate the information ratio between the information square root and the maximum voltage information entropy, and adopt the information ratio to determine the matching degree between any two topological nodes.

[0161] Optionally, the node clustering sub-module is specifically used for:

[0162] Connect any two topological nodes whose matching degree is greater than or equal to a preset first matching degree threshold to obtain an initial topological graph;

[0163] Successively select the topological nodes in the initial topological graph as target topological nodes, and select the topological nodes connected to the target topological nodes as to-be-judged topological nodes;

[0164] Judge whether the matching degree between the target topological node and the to-be-judged topological node is greater than or equal to a preset second matching degree threshold;

[0165] If so, classify the to-be-judged topological node into the node clustering cluster corresponding to the target topological node.

[0166] Optionally, the abnormal node determination module 304 includes:

[0167] An association degree calculation sub-module, which is used to respectively obtain the number of associated edges and the number of topological nodes corresponding to each topological node in each node clustering cluster, and determine the node association degree corresponding to each topological node as the number of associated edges;

[0168] An association degree threshold determination sub-module, which is used to determine the association degree threshold by using the number of topological nodes and a preset association degree parameter;

[0169] An association degree comparison sub-module, which is used to compare each node association degree with the association degree threshold;

[0170] A target abnormal node determination sub-module, which is used to determine the topological node corresponding to the node association degree as the target abnormal node if the node association degree is less than the association degree threshold.

[0171] An electronic device provided by an embodiment of the present invention includes a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the distribution network substation area topology verification method described in any embodiment of the present invention.

[0172] A computer-readable storage medium provided by an embodiment of the present invention stores a computer program thereon. When the computer program is executed, it implements the distribution network substation area topology verification method described in any embodiment of the present invention.

[0173] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices, modules, and sub-modules can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0174] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0175] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0177] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0178] As described above, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of the present invention.

Claims

1. A method for verifying the topology of a distribution network area, characterized in that: The distribution network area topology includes a plurality of topology nodes, and the method includes: Obtaining voltage information corresponding to each of the topological nodes during a period of occurrence of a preset change event; The voltage information is trimmed to generate an information-entropy-rich segment and the voltage information entropy corresponding to the information-entropy-rich segment is calculated; the information-entropy-rich segment refers to a voltage point information segment having a preset number of continuous extreme value voltage point information; Clustering the topological nodes according to the voltage information mean values and the voltage information entropy of any two of the topological nodes corresponding to the information-rich entropy segments to obtain a plurality of node clusters; Calculating the node association degree corresponding to the topological nodes in each of the node clusters, and determining the target abnormal node according to the node association degree; The step of calculating the node association degree corresponding to each topological node in the node cluster and determining the target abnormal node according to the node association degree includes: Respectively obtaining the number of associated edges and the number of topological nodes corresponding to each topological node in each of the node clusters, and determining the number of associated edges as the node association degree corresponding to each topological node; Determining a correlation threshold using the number of topological nodes and a preset correlation parameter; Comparing the relevance of each node with the relevance threshold; If the node association degree is less than the association degree threshold, the topological node corresponding to the node association degree is determined as a target abnormal node.

2. The method according to claim 1, characterized in that The voltage information includes information of multiple voltage points; the step of clipping the voltage information to generate information-rich entropy segments and calculating the voltage information entropy corresponding to the information-rich entropy segments includes: Divide the plurality of voltage point information according to the number of preset point information to obtain a plurality of voltage point information segments; determining an information-rich entropy segment from the plurality of voltage point information segments based on an extreme value detection result of each voltage point information segment; Calculating the voltage point information entropy corresponding to each voltage point information in the information-rich entropy segment using a preset voltage point information entropy calculation formula; Calculating the variance of the information entropy of all the voltage points to obtain the voltage information entropy corresponding to the information-rich entropy segment; The voltage point information entropy calculation formula is: Among them, i is the voltage point information entropy corresponding to the i-th voltage point information, (u i-t ,u i+t ) represents voltage point information u i The complexity of information within the range of t voltage points on the left and right, Var is the variance calculation formula, and m is the number of point information.

3. The method according to claim 2, characterized in that The step of determining an information-rich entropy segment from a plurality of voltage point information segments based on the extreme value detection results of each voltage point information segment comprises: Detecting whether there is a preset number of extreme value voltage point information in each voltage point information segment; If the voltage point information segment contains the extreme value number of extreme value voltage point information, detecting whether the extreme value voltage point information exists continuously; If it is detected that the extreme voltage point information exists continuously, determining the voltage point information segment as an information-rich entropy segment; If the voltage point information segment does not contain the extreme value number of extreme value voltage point information, or the extreme value voltage point information does not exist continuously, the voltage point information segment is determined to be a non-information-rich entropy segment.

4. The method according to claim 1, wherein The step of clustering the topological nodes according to the voltage information mean value and the voltage information entropy corresponding to the information-rich entropy segment of any two topological nodes to obtain a plurality of node clusters includes: Determining the matching degree between any two of the topological nodes according to the voltage information mean values and the voltage information entropy corresponding to the information-rich entropy segments of any two of the topological nodes; The topological nodes are clustered according to the matching degree between any two of the topological nodes to obtain a plurality of node clusters.

5. The method according to claim 4, characterized in that The step of determining the matching degree between any two topological nodes based on the voltage information mean values and the voltage information entropy corresponding to the information-rich entropy segments of any two topological nodes includes: Using the voltage information means of any two of the topological nodes corresponding to the information-rich entropy segments, calculate the information square difference between the voltage information means; Calculating the information square root corresponding to the information square difference; Selecting the maximum voltage information entropy from the voltage information entropies corresponding to the information-rich entropy segment; An information ratio between the information square root and the maximum voltage information entropy is calculated, and the information ratio is used to determine the matching degree between any two topological nodes.

6. The method according to claim 4, characterized in that The step of clustering the topological nodes according to the matching degree between any two topological nodes to obtain a plurality of node clusters includes: Connecting any two of the topological nodes whose matching degree is greater than or equal to a preset first matching degree threshold to obtain an initial topological graph; Selecting topological nodes in the initial topological graph in sequence as target topological nodes, and selecting topological nodes connected to the target topological nodes as topological nodes to be determined; Determine whether the matching degree between the target topological node and the topological node to be determined is greater than or equal to a preset second matching degree threshold; If so, the to-be-determined topological node is classified into the node cluster corresponding to the target topological node.

7. A distribution network area topology verification device, characterized in that: The distribution network area topology includes a plurality of topology nodes, and the device includes: A voltage information acquisition module, configured to acquire voltage information corresponding to each of the topological nodes during a period of occurrence of a preset change event; a voltage information entropy calculation module, configured to clip the voltage information, generate an information-entropy-rich segment, and calculate the voltage information entropy corresponding to the information-entropy-rich segment; the information-entropy-rich segment refers to a voltage point information segment containing a preset number of continuous extreme value voltage point information; A node clustering module, configured to cluster the topological nodes according to the voltage information mean value and the voltage information entropy of any two topological nodes corresponding to the information-rich entropy segment, to obtain a plurality of node clusters; An abnormal node determination module is used to calculate the node association degree corresponding to the topological nodes in each node cluster, and determine the target abnormal node according to the node association degree; The abnormal node determination module includes: The association degree calculation submodule is used to respectively obtain the number of associated edges and the number of topological nodes corresponding to each topological node in each of the node clusters, and determine the number of associated edges as the node association degree corresponding to each topological node; A correlation threshold determination submodule, configured to determine a correlation threshold using the number of topological nodes and a preset correlation parameter; A correlation comparison submodule, configured to compare the correlation of each node with the correlation threshold; The target abnormal node determination submodule is configured to determine the topological node corresponding to the node association degree as the target abnormal node if the node association degree is less than the association degree threshold.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the distribution network substation topology verification method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the distribution network substation topology verification method according to any one of claims 1 to 6 is implemented.

Images