Power distribution network line change relation identification method and system based on voltage key subsequence

Abstract

The invention discloses a power distribution network line-transformer relation identification method and system based on a voltage key subsequence. The method comprises the following steps: obtaining measurement, ledger and topological relation data of a feeder line and a distribution transformer of a power distribution network; carrying out bounded maximum and minimum normalization on the voltage sequence of the feeder line and the distribution transformer; screening local extreme points in the normalized voltage sequence, and combining the local extreme points with similar timestamps to obtain voltage key subsequences of the feeder line and the distribution transformer; calculating an alignment coefficient between the feeder line and the distribution transformer; a misclassification cost matrix is defined, a self-adaptive alignment coefficient threshold value is obtained by minimizing misclassification total cost, and whether the distribution transformation and line transformation relation is wrong or not is judged; and obtaining a suspicious feeder set based on the contact relationship and the geographic distance, calculating an alignment coefficient of the suspicious feeder and the distribution transformer, and obtaining a recommended hanging feeder of the distribution transformer. The method can solve the problems that a traditional method has high requirements for integrity and accuracy of measured data, and misalignment of a feeder line and a distribution transformer voltage clock cannot be well handled.

Description

Technical Field

[0001] The present invention relates to the identification technology of the line-transformer relationship in the medium-voltage distribution network, and specifically relates to a method, system, device and storage medium for identifying the line-transformer relationship in the distribution network based on voltage key subsequences. Background Art

[0002] The line-transformer relationship in the distribution network refers to the connection relationship between the distribution transformer and the feeder. Accurate identification of the line-transformer relationship is the basis for the operation and management of the distribution network, directly affecting services such as power flow calculation, fault location and new energy consumption. Due to the complex and changeable operation mode of the distribution network, the connection switch frequently changes due to faults, power transfer and other states, and the line-transformer relationship maintained manually often does not match the on-site operation situation. At present, the identification of the line-transformer relationship in the medium-voltage distribution network mainly relies on the calculation of the voltage correlation between the feeder and the distribution transformer, and it is considered that the distribution transformer with a low voltage correlation with the feeder has an incorrect line-transformer relationship. However, the traditional method has high requirements for the integrity and accuracy of the measurement data, and cannot handle the problem of misalignment of the voltage clocks of the feeder and the distribution transformer well. Summary of the Invention

[0003] Object of the Invention: The object of the present invention is to provide a method, system, device and storage medium for identifying the line-transformer relationship in the distribution network based on voltage key subsequences, which can solve the problems that the traditional method has high requirements for the integrity and accuracy of the measurement data and cannot handle the problem of misalignment of the voltage clocks of the feeder and the distribution transformer well.

[0004] Technical Solution: A method for identifying the line-transformer relationship in the distribution network based on voltage key subsequences of the present invention includes:

[0005] Obtain the measurement, ledger and topological relationship data of the feeder and the distribution transformer in the distribution network; extract the voltage sequences of the feeder and the distribution transformer from the obtained data;

[0006] Perform bounded maximum and minimum normalization on the voltage sequences of the feeder and the distribution transformer to obtain normalized voltage sequences;

[0007] Screen the local extreme points in the normalized voltage sequences, merge the local extreme points with similar timestamps to obtain the voltage key subsequences of the feeder and the distribution transformer;

[0008] Considering the clock offset of the voltage key subsequences, use the dynamic time warping method with constraints, and combine the lengths of the voltage key subsequences of the feeder and the distribution transformer to calculate the alignment coefficient between the feeder and the distribution transformer;

[0009] Define the misclassification cost matrix, obtain the adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judge whether the line-transformer relationship of the distribution transformer is incorrect according to the relationship between the alignment coefficient and the adaptive alignment coefficient threshold;

[0010] For distribution transformers with incorrect line - transformation relationships, based on the connection relationship and geographical location of the distribution transformer to the currently connected feeder, obtain the set of recommended connected feeders for the distribution transformer, calculate the alignment coefficient between each feeder in the set and the distribution transformer, and select the feeder with the largest alignment coefficient as the recommended connected feeder for the distribution transformer.

[0011] Furthermore, obtain the measurement, inventory, and topological relationship data of the feeders and distribution transformers in the distribution network, including:

[0012] Obtain feeder measurement data, including three - phase voltage measurement data;

[0013] Obtain feeder inventory data, including voltage level and geographical location;

[0014] Obtain feeder topological relationship data, including connection relationships with other feeders and connection relationships with distribution transformers;

[0015] Obtain the measurement data of the distribution transformer, including three - phase voltage measurement data;

[0016] Obtain the inventory data of the distribution transformer, including voltage level and geographical location;

[0017] Obtain the topological relationship data of the distribution transformer, including the relationship with the affiliated feeder.

[0018] Furthermore, perform bounded maximum - minimum normalization on the voltage sequences of the feeders and distribution transformers to obtain the normalized voltage sequences, including:

[0019] Obtain the voltage levels of the feeders and distribution transformers, and set the upper and lower bounds of the reasonable voltage range according to the voltage levels;

[0020] Use the bounded maximum - minimum normalization method to normalize the voltages of the feeders and distribution transformers:

[0021]

[0022] Where V’ is the normalized voltage data; V is the original voltage data; lb is the upper bound of the reasonable voltage range corresponding to the voltage level of the obtained feeder or distribution transformer; ub is the lower bound of the reasonable voltage range corresponding to the voltage level of the obtained feeder or distribution transformer.

[0023] Furthermore, screen the local extreme points in the normalized voltage sequences, merge the local extreme points with similar timestamps, and obtain the key sub - sequences of the voltages of the feeders and distribution transformers, including:

[0024] Define the local extreme points in the normalized voltage sequence:

[0025]

[0026] In the formula, label i is the data point type with timestamp i; v iThe voltage data point with timestamp i; n is the length of the voltage sequence; local_min, local_max, and trival are the local minimum, local maximum, and trivial value respectively;

[0027] Filter all local maxima and local minima, sort them in the order of the original timestamps, and obtain the local extreme value sequence C of the feeder and the distribution transformer:

[0028]

[0029] where, t l is the timestamp of the l-th point in the normalized voltage sequence; is the voltage data point with timestamp t l in the local extreme value sequence; l is the length of the local extreme value sequence.

[0030] Perform an iterative merging operation on the local extreme value sequence C. Each time, select the data point with the smallest time difference from the neighboring data points, and delete the selected data points until the sequence length meets the requirements, to obtain the voltage key subsequence of the feeder and the distribution transformer.

[0031] Furthermore, considering the clock offset of the voltage key subsequence, use the dynamic time warping method with constraints, and combine the lengths of the voltage key subsequences of the feeder and the distribution transformer to calculate the alignment coefficient between the feeder and the distribution transformer, including:

[0032] Define the allowable amplitude of the clock offset of the voltage key subsequence as r, and use the dynamic time warping method with constraints to calculate the distance matrix between the feeder and the distribution transformer:

[0033]

[0034] In the formula, dist(i,j) is the distance function between the data with timestamp i in the voltage key subsequence of the feeder and the data with timestamp j in the voltage key subsequence of the distribution transformer;

[0035] According to the distance matrix between the feeder and the distribution transformer, calculate the alignment coefficient D between the feeder and the distribution transformer:

[0036]

[0037] In the formula, n i is the length of the voltage key subsequence of the feeder; n j is the length of the voltage key subsequence of the distribution transformer.

[0038] Furthermore, define the misclassification cost matrix, obtain the adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judge whether the line-transformer relationship of the distribution transformer is incorrect according to the relationship between the alignment coefficient and the adaptive alignment coefficient threshold, including:

[0039] Define the misclassification cost matrix for line change relationships, and calculate the total misclassification cost Total_cost of line change relationships in combination with the misclassification cost matrix for line change relationships:

[0040] Total_cost = FP × cost FP + FN × cost FN

[0041] In the formula, FP represents the number of false positives in line change relationship judgment; FN represents the number of false negatives in line change relationship judgment; cost FP represents the cost of false positives in line change relationship judgment, and cost FN represents the cost of false negatives in line change relationship judgment;

[0042] Based on the correct and incorrect cases of historical line change relationships, through the search of the alignment coefficient threshold, minimize the total misclassification cost of line change relationships to obtain an adaptive threshold D φ , and judge whether the line change relationship is incorrect according to the alignment coefficient between the feeder and the distribution transformer and the threshold D φ Relationship.

[0043] Furthermore, for the distribution transformer with incorrect line change relationship, based on the connection relationship and geographical location of the feeder currently connected to the distribution transformer, obtain the set of recommended feeders for the distribution transformer, calculate the alignment coefficient between each feeder in the set and the distribution transformer, and select the feeder with the largest alignment coefficient as the recommended feeder for the distribution transformer, including:

[0044] According to the connection relationship between the current feeder and other feeders, obtain the set of connected feeders L1;

[0045] According to the geographical location of the current distribution transformer, screen the set of feeders L2 with close geographical locations;

[0046] Take the union of L1 and L2 to obtain the set of possible feeders L for the distribution transformer;

[0047] For each feeder in the set of possible feeders L for the distribution transformer, calculate the alignment coefficient with the current distribution transformer, sort from large to small, and output the feeder corresponding to the largest alignment coefficient as the recommended feeder for the distribution transformer.

[0048] Based on the same inventive concept, a distribution network line change relationship identification system based on voltage key subsequences of the present invention includes:

[0049] A data acquisition module for acquiring measurement, account, and topological relationship data of feeders and distribution transformers in the distribution network; extracting voltage sequences of feeders and distribution transformers from the acquired data;

[0050] A data preprocessing module for performing bounded maximum and minimum normalization on the voltage sequences of feeders and distribution transformers to obtain normalized voltage sequences;

[0051] The voltage key subsequence acquisition module is used to screen the local extreme points in the normalized voltage sequence, merge the local extreme points with close timestamps, and obtain the voltage key subsequences of the feeder and the distribution transformer.

[0052] The alignment coefficient calculation module is used to consider the clock offset of the voltage key subsequences, and use the constrained dynamic time warping method to calculate the alignment coefficient between the feeder and the distribution transformer in combination with the lengths of the voltage key subsequences of the feeder and the distribution transformer.

[0053] The distribution transformer-line transformer relationship judgment module is used to define the misclassification cost matrix, obtain the adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judge whether the distribution transformer-line transformer relationship is incorrect according to the relationship between the alignment coefficient and the adaptive alignment coefficient threshold.

[0054] The recommended feeder for the distribution transformer connection acquisition module is used for the distribution transformer with an incorrect line-transformer relationship. Based on the connection relationship and geographical location of the feeder currently connected to the distribution transformer, obtain the set of recommended feeders for the distribution transformer connection, calculate the alignment coefficient between each feeder in the set and the distribution transformer, and select the feeder with the largest alignment coefficient as the recommended feeder for the distribution transformer connection.

[0055] Based on the same inventive concept, a distribution network line-transformer relationship identification device of the present invention includes a processor and a memory. Computer instructions are stored in the memory, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the above-mentioned distribution network line-transformer relationship identification method based on voltage key subsequences.

[0056] Based on the same inventive concept, a computer-readable storage medium of the present invention stores a computer program thereon. When the program is executed by a processor, the steps of the above-mentioned distribution network line-transformer relationship identification method based on voltage key subsequences are implemented.

[0057] Advantageous effects: Compared with the prior art, the remarkable technical effects of the present invention are as follows:

[0058] The present invention adopts a data-driven method, calculates and extracts the key features of the voltages of the distribution transformer and the feeder through voltage key subsequences, can capture complex data features, has strong accuracy, and avoids the drawbacks of manual judgment.

[0059] The present invention is applicable to situations such as noise interference and clock misalignment in the voltage curve through alignment coefficient calculation and threshold generation, and overcomes the problem of low generality of traditional voltage correlation methods.

[0060] The present invention is simple to calculate, has a clear principle, can help distribution network operators timely discover incorrect line-transformer relationships in the medium-voltage distribution network, and has good application prospects. Description of the Drawings

[0061] Figure 1 It is a schematic flow chart of a method for identifying the line-transformer relationship in a distribution network based on voltage key subsequences disclosed in an embodiment of the present invention;

[0062] Figure 2 It is a schematic structural diagram of a system for identifying the line-transformer relationship in a distribution network based on voltage key subsequences disclosed in an embodiment of the present invention;

[0063] Figure 3 It is a schematic structural diagram of a device for identifying the line-transformer relationship in a distribution network based on voltage key subsequences disclosed in an embodiment of the present invention. Detailed implementation manners

[0064] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. Those skilled in the art will understand that the purposes and advantages that can be achieved by the present invention are not limited to the specific beneficial effects described above, and the above and other purposes that the present invention can achieve will be more clearly understood according to the following detailed description.

[0065] Those of ordinary skill in the art should understand that the various exemplary components, systems, and methods described in connection with the embodiments disclosed in the present invention can be implemented in hardware, software, or a combination of both. Specifically, whether to execute in hardware or software depends on the specific application and design and tree conditions of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0066] The mention of "embodiment" in the present invention means that the specific features, structures, or characteristics described in connection with the embodiment may be included in at least one embodiment of the present invention. The appearance of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0067] Embodiment 1

[0068] Please refer to Figure 1 , Figure 1 It is a schematic flow chart of a method for identifying the line-transformer relationship in a distribution network based on voltage key subsequences disclosed in an embodiment of the present invention. Among them, Figure 1 The described method for identifying the line-transformer relationship in a distribution network is applied in a power system, such as for identifying the line-transformer relationship in a medium-voltage distribution network, etc., and the embodiments of the present invention do not make limitations. As Figure 1 shown, the method for identifying the line-transformer relationship in a distribution network based on voltage key subsequences may include the following operations:

[0069] S1. Obtain data such as measurements, inventory, and topological relationships of the feeders and distribution transformers in the distribution network; extract the voltage sequences of the feeders and distribution transformers from the obtained data. Specifically:

[0070] Obtain feeder measurement data, including three-phase voltage measurement data;

[0071] Obtain feeder inventory data, including voltage level and geographical location;

[0072] Obtain feeder topological relationship data, including connection relationships with other feeders and relationships of attached distribution transformers;

[0073] Obtain measurement data of the distribution transformer, including three-phase voltage measurement data;

[0074] Obtain distribution transformer inventory data, including voltage level and geographical location;

[0075] Obtain distribution transformer topological relationship data, including the relationship with the feeder to which it belongs.

[0076] S2. Perform bounded maximum and minimum normalization on the voltage sequences of the feeders and distribution transformers to obtain normalized voltage sequences. The specific steps are as follows:

[0077] S2.1. Obtain the voltage levels of the feeders and distribution transformers, and set the upper and lower bounds of the reasonable voltage range according to the voltage levels.

[0078] S2.2. Use the bounded maximum and minimum normalization method to normalize the voltages of the feeders and distribution transformers:

[0079]

[0080] where V’ is the normalized voltage data; V is the original voltage data; lb is the upper bound of the reasonable voltage range corresponding to the voltage level of the obtained feeder or distribution transformer; ub is the lower bound of the reasonable voltage range corresponding to the voltage level of the obtained feeder or distribution transformer.

[0081] S3. Screen the local extreme points in the normalized voltage sequences, merge the local extreme points with close timestamps, and obtain the voltage key subsequences of the feeders and distribution transformers. The specific steps are as follows:

[0082] S3.1. Define the local extreme points in the normalized voltage sequences:

[0083]

[0084] In the formula, label i is the data point type with timestamp i; v i is the voltage data point with timestamp i; n is the length of the voltage sequence; local_min, local_max, and trival are the local minimum value, local maximum value, and trivial value respectively.

[0085] S3.2. Screen all local maxima and local minima, sort them in the order of the original timestamps, and obtain the local extreme value sequences C of the feeder and the distribution transformer:

[0086]

[0087] where t l is the timestamp of the l-th point in the normalized voltage sequence, is the voltage data point with the timestamp t l in the local extreme value sequence; l is the length of the local extreme value sequence.

[0088] S3.3. Perform iterative merging operations on the local extreme value sequence C. Each time, select the data point with the smallest time difference from the neighboring data points, and delete the selected data points until the sequence length meets the requirements, obtaining the voltage key subsequences of the feeder and the distribution transformer.

[0089] S4. Consider the clock offset of the voltage key subsequences, and use the dynamic time warping method with constraints to calculate the alignment coefficient between the feeder and the distribution transformer in combination with the lengths of the voltage key subsequences of the feeder and the distribution transformer. The specific steps are as follows:

[0090] S4.1. Define the allowable amplitude of the clock offset of the voltage key subsequence as r, and use the dynamic time warping method with constraints to calculate the distance matrix between the feeder and the distribution transformer:

[0091]

[0092] where dist(i,j) is the distance function between the data with the timestamp i in the voltage key subsequence of the feeder and the data with the timestamp j in the voltage key subsequence of the distribution transformer.

[0093] S4.2. Calculate the alignment coefficient D between the feeder and the distribution transformer according to the distance matrix between the feeder and the distribution transformer:

[0094]

[0095] where n i is the length of the voltage key subsequence of the feeder; n j is the length of the voltage key subsequence of the distribution transformer.

[0096] S5. Define the misclassification cost matrix, obtain the adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judge whether the line-transformer relationship of the distribution transformer is incorrect according to the relationship between the alignment coefficient and the adaptive alignment coefficient threshold. The specific steps are as follows:

[0097] S5.1. Define the misclassification cost matrix for the line-transformer relationship:

[0098]

[0099] Among them, cost FP represents the false positive cost of the line change relationship judgment; cost FN represents the false negative cost of the line change relationship judgment.

[0100] S5.2. Calculate the total misclassification cost Total_cost of the line change relationship by combining the misclassification cost matrix of the line change relationship:

[0101] Total_cost = FP × cost FP + FN × cost FN

[0102] In the formula, FP represents the number of false positives in the line change relationship judgment; FN represents the number of false negatives in the line change relationship judgment.

[0103] S5.3. Based on the correct and incorrect cases of the historical line change relationship, through the search of the alignment coefficient threshold, minimize the total misclassification cost of the line change relationship to obtain the adaptive threshold D φ , and judge whether the line change relationship is incorrect according to the relationship between the alignment coefficient of the feeder and the distribution transformer and the threshold D φ relationship.

[0104] S6. For the distribution transformers with incorrect line change relationships, based on the connection relationship and geographical location of the feeder currently connected to the distribution transformer, obtain the set of recommended feeder lines for the distribution transformer, calculate the alignment coefficient between each feeder line in the set and the distribution transformer, and select the feeder line with the largest alignment coefficient as the recommended feeder line for the distribution transformer. Specifically as follows:

[0105] Obtain the set of connected feeder lines L1 according to the connection relationship between the current feeder line and other feeder lines;

[0106] Screen the set of feeder lines L2 with adjacent geographical locations according to the geographical location of the current distribution transformer;

[0107] Take the union of L1 and L2 to obtain the set of possible feeder lines L for the distribution transformer;

[0108] For each feeder line in the set of possible feeder lines L for the distribution transformer, calculate the alignment coefficient with the current distribution transformer, sort them from largest to smallest, and output the feeder line corresponding to the largest alignment coefficient as the recommended feeder line for the distribution transformer.

[0109] The present invention can capture the characteristics of complex voltage curves, judge incorrect line change relationships based on the calculation results and provide correction suggestions, and realizes effective identification of line change relationships in the distribution network.

[0110] The present invention proposes a judgment method based on voltage key subsequences, which can extract key features in the voltage sequence, effectively overcome problems such as measurement noise interference and clock misalignment, and achieve fast and accurate identification of abnormal line-transformer relationships. Therefore, the line-transformer relationship identification method for medium-voltage distribution networks is an important research topic, and the research results can help operators discover incorrect line-transformer relationships in a timely manner and empower upper-layer computing and other services with accurate topological bases.

[0111] Aiming at the problems of complex and changeable operating modes of distribution networks and the inconsistency between manually maintained line-transformer relationships and the field, the present invention proposes a line-transformer relationship identification method for distribution networks, which can be used to identify incorrect line-transformer relationships in medium-voltage distribution networks of any scale, with simple calculation and clear principles, and can help distribution network operators discover incorrect line-transformer relationship situations in a timely manner and provide correction suggestions.

[0112] The following describes the application principle of the present invention in detail through a specific embodiment.

[0113] As Figure 1 shown, the line-transformer relationship identification method for distribution networks based on voltage key subsequences of the present invention includes the following steps:

[0114] S1. Obtain data such as measurements, account books, and topological relationships of feeders and distribution transformers in the distribution network; extract the voltage sequences of feeders and distribution transformers from the obtained data. The specific implementation process is as follows:

[0115] Select the feeder to be processed in the power consumption information acquisition system (i.e., the pms system, which is a system existing in the prior art), and read the basic feeder data stored in the existing system, including basic account book data and various equipment connection relationship data;

[0116] Export the feeder voltage measurement data sampled every 15 minutes in the power consumption information acquisition system. The sampling frequency of sampling every 15 minutes mentioned above can be modified according to actual situations;

[0117] Select the distribution transformer to be processed in the power consumption information acquisition system, and read the basic distribution transformer data stored in the existing system, including basic account book data and various equipment connection relationship data;

[0118] Export the distribution transformer voltage measurement data sampled every 15 minutes in the power consumption information acquisition system. The sampling frequency of sampling every 15 minutes mentioned above can be modified according to actual situations.

[0119] S2. Perform bounded maximum and minimum normalization on the voltage sequences of the feeder and the distribution transformer to obtain normalized voltage sequences. The specific implementation process is as follows:

[0120] Obtain the voltage levels of the feeder and the distribution transformer, and set the upper and lower bounds of the reasonable voltage range according to the voltage levels;

[0121] Using the bounded maximum - minimum normalization method, normalize the voltages of the feeder and the distribution transformer:

[0122]

[0123] Among them, V’ is the normalized voltage data; V is the original voltage data; lb is the upper bound of the reasonable voltage range corresponding to the voltage level of the feeder or the distribution transformer; ub is the lower bound of the reasonable voltage range corresponding to the voltage level of the feeder or the distribution transformer.

[0124] S3. Screen the local extreme points in the normalized voltage sequence, merge the local extreme points with close timestamps, and obtain the key subsequences of the voltages of the feeder and the distribution transformer. The specific implementation process is as follows:

[0125] Define the local extreme points in the voltage sequence:

[0126]

[0127] In the formula, label i is the data point type with timestamp i; v i is the voltage data point with timestamp i; n is the length of the voltage sequence; local_min, local_max, and trival are the local minimum value, local maximum value, and trivial value respectively.

[0128] Screen all local maximum values and local minimum values, sort them in the order of the original timestamps, and obtain the local extreme value sequence C of the feeder and the distribution transformer:

[0129]

[0130] Among them, t i is the timestamp of the i - th point in the normalized voltage sequence; l is the length of the local extreme value sequence.

[0131] Based on the obtained length of the local extreme value sequence, define the length of the target voltage key subsequence as c. If the length of the local extreme value sequence is less than or equal to c, no processing is performed;

[0132] If the length of the local extreme value sequence is greater than c, perform iterative merging operations on the local extreme value sequence. Each time, select the data point with the smallest time - stamp difference from the adjacent data points, and delete this data point until the sequence length is equal to c, to obtain the key subsequences of the voltages of the feeder and the distribution transformer.

[0133] S4. Consider the clock offset of the voltage key subsequence, and use the dynamic time warping method with constraints to calculate the alignment coefficients of the feeder and the distribution transformer in combination with the lengths of the voltage key subsequences of the feeder and the distribution transformer. The specific implementation process is as follows:

[0134] Define the allowable amplitude of clock offset for the voltage key subsequence as r, and use the constrained dynamic time warping method to calculate the distance matrix between the feeder and the distribution transformer:

[0135]

[0136] In the formula, dist(i,j) is the distance function between the data with timestamp i of the voltage key subsequence of the feeder and the data with timestamp j of the voltage key subsequence of the distribution transformer, such as the Euclidean distance.

[0137] Calculate the alignment coefficient D between the feeder and the distribution transformer according to the distance matrix between the feeder and the distribution transformer:

[0138]

[0139] In the formula, n i is the length of the voltage key subsequence of the feeder; n j is the length of the voltage key subsequence of the distribution transformer.

[0140] S5. Define the misclassification cost matrix, obtain the adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judge whether the line-transformer relationship of the distribution transformer is incorrect according to the relationship between the alignment coefficient and the adaptive alignment coefficient threshold. The specific implementation process is as follows:

[0141] Define the misclassification cost matrix for the line-transformer relationship:

[0142]

[0143] Among them, cost FP represents the false positive cost of the line-transformer relationship judgment; cost FN represents the false negative cost of the line-transformer relationship judgment.

[0144] For example, if it is necessary to discover line-transformer relationship error cases as comprehensively as possible to meet the business requirements of a certain place, the false negative cost weight is increased, and cost FP : cost FN = 1:3.

[0145] Define the calculation of the total misclassification cost of the line-transformer relationship:

[0146] Total_cost = FP × cost FP + FN × cost FN

[0147] In the formula, FP represents the number of false positives in the line-transformer relationship judgment; FN represents the number of false negatives in the line-transformer relationship judgment.

[0148] Based on the correct and incorrect cases of the historical line-transformer relationship, calculate the alignment coefficient of the correct cases of the historical line-transformer relationship and the alignment coefficient of the incorrect cases of the historical line-transformer relationship;

[0149] Search for the alignment coefficient threshold within the range of [0, 1], with a step size of k, which can be specified as 0.01 or other reasonable small values;

[0150] Judge the historical matching changes with alignment coefficients greater than the current threshold as incorrect line change relationships, and judge the historical matching changes with alignment coefficients less than or equal to the current threshold as correct line change relationships;

[0151] Calculate the false positive FP and false negative FN of the historical matching change line change relationship judgment under the current threshold:

[0152]

[0153] Calculate the total cost of misclassification of the line change relationship under the current threshold;

[0154] Through the search of the alignment coefficient threshold, the threshold that minimizes the total cost of misclassification of the line change relationship is the adaptive threshold D φ ;

[0155] If the above-mentioned weight of the misclassification cost matrix of the line change relationship and the threshold search step size are applied, the results of searching for the alignment coefficient threshold for the historical line change relationship of the distribution transformers under a certain feeder are as follows:

[0156] Alignment coefficient threshold FP FN Total_cost 0.9 0 3 9 0.91 0 2 6 0.92 2 1 5 0.93 6 1 9 0.94 11 1 14

[0157] According to the principle of minimizing the total cost of misclassification of the line change relationship, the adaptive threshold D φ = 0.92.

[0158] Judge whether the line change relationship of the current distribution transformer is incorrect according to the relationship between the current alignment coefficient of the distribution transformer and the threshold D φ Relationship.

[0159] S6. Obtain a set of suspicious feeders based on the connection relationship and geographical distance, calculate the alignment coefficient between the suspicious feeder and the distribution transformer, and obtain the recommended feeder for the distribution transformer to be connected. The specific implementation process is as follows:

[0160] Obtain the set of connected feeders L1 according to the connection relationship between the current feeder and other feeders;

[0161] Filter the set of feeders L2 with adjacent geographical locations according to the geographical location of the current distribution transformer;

[0162] Take the union of L1 and L2 to obtain the set of possible feeders L for the distribution transformer to be connected;

[0163] For each feeder in L, calculate the alignment coefficient with the current distribution transformer, sort them from largest to smallest, and output the feeder corresponding to the largest alignment coefficient as the recommended feeder for the distribution transformer to be connected.

[0164] Embodiment 2

[0165] Please refer toFigure 2 , Figure 2 is a schematic structural diagram of a distribution network line - transformer relationship recognition system based on voltage key subsequences disclosed in an embodiment of the present invention. This system can realize the recognition of the line - transformer relationship in the medium - voltage distribution network, and specifically includes:

[0166] A data acquisition module, which is used to acquire the measurement, ledger, and topological relationship data of the feeder and distribution transformer in the distribution network; extract the voltage sequences of the feeder and distribution transformer from the acquired data;

[0167] A data pre - processing module, which is used to perform bounded maximum - minimum normalization on the voltage sequences of the feeder and distribution transformer to obtain normalized voltage sequences;

[0168] A voltage key subsequence acquisition module, which is used to screen the local extreme points in the normalized voltage sequences, merge the local extreme points with close timestamps, and obtain the voltage key subsequences of the feeder and distribution transformer;

[0169] An alignment coefficient calculation module, which is used to consider the clock offset of the voltage key subsequences, use the constrained dynamic time warping method, and calculate the alignment coefficient between the feeder and distribution transformer in combination with the lengths of the voltage key subsequences of the feeder and distribution transformer;

[0170] A distribution transformer line - transformer relationship judgment module, which is used to define a misclassification cost matrix, obtain an adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judge whether the distribution transformer line - transformer relationship is incorrect according to the relationship between the alignment coefficient and the adaptive alignment coefficient threshold;

[0171] A recommended feeder for connecting the distribution transformer acquisition module, which is used for the distribution transformer with an incorrect line - transformer relationship. Based on the connection relationship and geographical location of the feeder currently connected to the distribution transformer, obtain a set of recommended feeders for connecting the distribution transformer, calculate the alignment coefficient between each feeder in the set and the distribution transformer, and select the feeder with the largest alignment coefficient as the recommended feeder for connecting the distribution transformer.

[0172] In an alternative embodiment, the distribution network line - transformer relationship recognition method includes: a) acquiring the measurement, ledger, and topological relationship data of the feeder and distribution transformer in the distribution network; b) performing bounded maximum - minimum normalization on the voltage sequences of the feeder and distribution transformer to obtain normalized voltage sequences; c) screening the local extreme points in the normalized voltage sequences, merging the local extreme points with close timestamps, and obtaining the voltage key subsequences of the feeder and distribution transformer; d) using the constrained dynamic time warping method to calculate the alignment coefficient between the feeder and distribution transformer; e) defining a misclassification cost matrix, obtaining an adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judging whether the distribution transformer line - transformer relationship is incorrect; f) obtaining a set of suspicious feeders based on the connection relationship and geographical distance, calculating the alignment coefficient between the suspicious feeders and the distribution transformer, and obtaining the recommended feeder for connecting the distribution transformer.

[0173] Embodiment 3

[0174] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of a distribution network line - transformer relationship recognition device based on voltage key subsequences disclosed in an embodiment of the present invention. Among them, Figure 3 the described device can be applied in a power system, such as for identifying the line - transformer relationship in a medium - voltage distribution network, and the embodiments of the present invention do not make limitations in this regard.

[0175] As Figure 3 shown, the device may include a processor and a memory. Computer instructions are stored in the memory, and the processor is configured to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method as described in the above - mentioned embodiments and can achieve the same technical effects as the above - mentioned method.

[0176] The memory may include a computer - system - readable medium in the form of volatile memory, such as random - access memory (RAM) and / or cache memory. The device may further include other removable / non - removable, volatile / non - volatile computer - system storage media. By way of example only, the memory may be used to read and write non - removable, non - volatile magnetic media (commonly referred to as a "hard disk drive"). Programs / utilities with a set of (at least one) program modules may be stored in the memory, such as an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples. The program modules generally execute the functions and / or methods in the embodiments described in the present invention.

[0177] The processor executes various functional applications and data processing by running the programs stored in the memory, such as implementing the method provided in Embodiment 1 of the present invention.

[0178] Embodiment 4

[0179] Embodiment 4 of the present invention further provides a computer - readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the steps of the method as described in the above - mentioned embodiments and can achieve the same technical effects as the above - mentioned method.

[0180] The computer storage medium according to an embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable media may be computer-readable signal media or computer-readable storage media. The computer-readable storage media may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage media may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.

[0181] The computer-readable signal media may include data signals propagated in a baseband or as part of a carrier wave, in which computer-readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal media may also be any computer-readable media other than the computer-readable storage media, and the computer-readable media may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0182] The program codes contained on the computer-readable media may be transmitted by any appropriate media, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0183] The computer program codes for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program codes may be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0184] Of course, for a storage medium containing computer-executable instructions provided by an embodiment of the present invention, the computer-executable instructions are not limited to the above method operations, and can also execute relevant operations in the methods provided by any embodiment of the present invention.

[0185] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for identifying the line-transformer relationship in a distribution network based on voltage key subsequences, characterized in that Including: Obtain the measurement, inventory, and topological relationship data of the feeders and distribution transformers in the distribution network; Extract the voltage sequences of the feeders and distribution transformers from the obtained data; Perform bounded maximum and minimum normalization on the voltage sequences of the feeders and distribution transformers to obtain the normalized voltage sequences; Screen the local extreme points in the normalized voltage sequences, merge the local extreme points with similar timestamps, and obtain the voltage key subsequences of the feeders and distribution transformers; Consider the clock offset of the voltage key subsequences, use the dynamic time warping method with constraints, and combine the lengths of the voltage key subsequences of the feeders and distribution transformers to calculate the alignment coefficient between the feeders and distribution transformers; Define the misclassification cost matrix, obtain the adaptive alignment coefficient threshold by minimizing the total misclassification cost, and determine whether the line-transformer relationship of the distribution transformer is incorrect based on the relationship between the alignment coefficient and the adaptive alignment coefficient threshold; For the distribution transformer with an incorrect line-transformer relationship, based on the connection relationship and geographical location of the feeder currently connected to the distribution transformer, obtain the set of recommended feeders for the distribution transformer, calculate the alignment coefficient between each feeder in the set and the distribution transformer, and select the feeder with the largest alignment coefficient as the recommended feeder for the distribution transformer.

2. The method for identifying the line-transformer relationship of a distribution network based on voltage key subsequences according to claim 1, wherein Obtain the measurement, inventory, and topological relationship data of the feeders and distribution transformers in the distribution network, including: Obtain the feeder measurement data, including three-phase voltage measurement data; Obtain the feeder inventory data, including voltage level and geographical location; Obtain the feeder topological relationship data, including the connection relationship with other feeders and the relationship of connected distribution transformers; Obtain the measurement data of the distribution transformer, including three-phase voltage measurement data; Obtain the inventory data of the distribution transformer, including voltage level and geographical location; Obtain the topological relationship data of the distribution transformer, including the relationship of the affiliated feeder.

3. The method for identifying the line-transformer relationship of a distribution network based on a voltage key subsequence according to claim 1, wherein Perform bounded maximum and minimum normalization on the voltage sequences of the feeders and distribution transformers to obtain the normalized voltage sequences, including: Obtain the voltage levels of the feeders and distribution transformers, and set the upper and lower bounds of the reasonable voltage range according to the voltage levels; Use the bounded maximum and minimum normalization method to normalize the voltages of the feeders and distribution transformers: Where V’ is the normalized voltage data; V is the original voltage data; lb is the upper bound of the reasonable voltage range corresponding to the voltage level of the obtained feeder or distribution transformer; ub is the lower bound of the reasonable voltage range corresponding to the voltage level of the obtained feeder or distribution transformer.

4. The method for identifying the line-transformer relationship of a distribution network based on voltage key subsequences according to claim 1, wherein Screen the local extreme points in the normalized voltage sequences, merge the local extreme points with similar timestamps, and obtain the voltage key subsequences of the feeders and distribution transformers, including: Define the local extreme points in the normalized voltage sequences: where, label i is the data point type with timestamp i; v i is the voltage data point with timestamp i; n is the length of the voltage sequence; local_min, local_max, and trival are the local minimum value, local maximum value, and trivial value respectively; Screen all local maximum and local minimum values, sort them in the order of the original timestamps, and obtain the local extreme sequence C of the feeders and distribution transformers; where t l is the timestamp of the l-th point in the normalized voltage sequence; is the voltage data point with timestamp t l in the local extreme value sequence; l is the length of the local extreme value sequence; Perform iterative merging operations on the local extreme sequence C, each time select the data point with the smallest timestamp difference from the similar data points, and delete the selected data point until the sequence length meets the requirements, and obtain the voltage key subsequences of the feeders and distribution transformers.

5. The method for identifying the line-transformer relationship of a distribution network based on a voltage key subsequence according to claim 1, wherein Consider the clock offset of the voltage key subsequences, use the dynamic time warping method with constraints, and combine the lengths of the voltage key subsequences of the feeders and distribution transformers to calculate the alignment coefficient between the feeders and distribution transformers, including: Define the allowable amplitude of the clock offset of the voltage key subsequence as r, and use the dynamic time warping method with constraints to calculate the distance matrix between the feeders and distribution transformers: where dist(i,j) is the distance function between the data of the key sub-sequence of the feeder voltage with time stamp i and the data of the key sub-sequence of the distribution transformer voltage with time stamp j; Calculate the alignment coefficient D of the feeder and the distribution transformer according to the distance matrix of the feeder and the distribution transformer; Where n i is the length of the voltage key subsequence of the feeder; n j is the length of the voltage key subsequence of the distribution transformer.

6. The method for identifying the line-transformer relationship of a distribution network based on voltage key subsequences according to claim 1, characterized in that, Define the misclassification cost matrix, obtain the adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judge whether the line-transformer relationship of the distribution transformer is incorrect according to the relationship between the alignment coefficient and the adaptive alignment coefficient threshold, including: Define the misclassification cost matrix of the line-transformer relationship, and calculate the total misclassification cost Total_cost of the line-transformer relationship by combining the misclassification cost matrix of the line-transformer relationship; Total_cost = FP × cost FP + FN × cost FN Wherein, FP represents the number of false positives in the line change relationship judgment; FN represents the number of false negatives in the line change relationship judgment; cost FP represents the cost of false positives in the line change relationship judgment, and cost FN represents the cost of false negatives in the line change relationship judgment; Based on the correct and incorrect cases of the historical line change relationship, through the search of the alignment coefficient threshold, the total cost of misclassification of the line change relationship is minimized, and the adaptive threshold D is obtained φ , and determine whether the line change relationship is incorrect according to the alignment coefficient between the feeder and the distribution transformer and the threshold D φ relationship 7. The method for identifying the line-transformer relationship of a distribution network based on a voltage key subsequence according to claim 1, wherein For the distribution transformer with incorrect line-transformer relationship, based on the connection relationship and geographical location of the feeder currently connected to the distribution transformer, obtain the set of recommended feeders for the distribution transformer, calculate the alignment coefficient between each feeder in the set and the distribution transformer, and select the feeder with the largest alignment coefficient as the recommended feeder for the distribution transformer, including: Obtain the set of connected feeders L1 according to the connection relationship between the current feeder and other feeders; Screen the set of feeders L2 with adjacent geographical locations according to the geographical location of the current distribution transformer; Take the union of L1 and L2 to obtain the set of possible feeders L for the distribution transformer to be connected; For each feeder in the set of possible feeders L for the distribution transformer, calculate the alignment coefficient with the current distribution transformer, sort them from large to small, and output the feeder corresponding to the largest alignment coefficient as the recommended feeder for the distribution transformer.

8. A distribution network line-transformer relationship recognition system based on voltage key subsequences, characterized in that, Including: The data acquisition module is used to acquire the measurement, account, and topological relationship data of the feeder and the distribution transformer of the distribution network; Extract the voltage sequences of the feeder and the distribution transformer from the acquired data; The data preprocessing module is used to perform bounded maximum and minimum normalization on the voltage sequences of the feeder and the distribution transformer to obtain the normalized voltage sequences; The voltage key sub-sequence acquisition module is used to screen the local extreme points in the normalized voltage sequence, merge the local extreme points with similar time stamps, and obtain the voltage key sub-sequences of the feeder and the distribution transformer; The alignment coefficient calculation module is used to consider the clock offset of the voltage key sub-sequence, use the dynamic time warping method with constraints, and calculate the alignment coefficient between the feeder and the distribution transformer in combination with the lengths of the voltage key sub-sequences of the feeder and the distribution transformer; The distribution transformer line-transformer relationship judgment module is used to define the misclassification cost matrix, obtain the adaptive alignment coefficient threshold by minimizing the total misclassification cost, and judge whether the line-transformer relationship of the distribution transformer is incorrect according to the relationship between the alignment coefficient and the adaptive alignment coefficient threshold; The distribution transformer recommended connected feeder acquisition module is used to, for the distribution transformer with incorrect line-transformer relationship, based on the connection relationship and geographical location of the feeder currently connected to the distribution transformer, obtain the set of recommended feeders for the distribution transformer, calculate the alignment coefficient between each feeder in the set and the distribution transformer, and select the feeder with the largest alignment coefficient as the recommended feeder for the distribution transformer.

9. A device for identifying the line-transformer relationship in a distribution network based on voltage key subsequences, characterized in that Including a processor and a memory, wherein computer instructions are stored in the memory, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method for identifying the line-transformer relationship of the distribution network based on the voltage key sub-sequence as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the program is executed by a processor, the steps of the method for identifying the line-transformer relationship of a distribution network based on a voltage key subsequence as described in any one of claims 1 to 7 are implemented.

Images