Low-voltage transformer area user phase identification method and system

Abstract

The invention relates to a low-voltage transformer area user phase identification method and system, and the method comprises the following steps: obtaining the voltage correlation between user nodes through a Pearson correlation coefficient, and obtaining a transformer area user node electrical distance matrix through calculation; clustering by adopting a DBSCAN (Density Based Spatial Clustering of Applications with Noise) algorithm on the basis of the transformer area electrical distance matrix to obtain groups of transformer area user nodes; establishing a split-phase power balance equation to carry out regression analysis on each group of transformer area user nodes after grouping, determining the phase of each group of transformer area user nodes, and completing initial identification; judging whether the initial identification result of the phase of each group of transformer area user nodes is valid or not through a preset rule, and if the initial identification result is invalid, measuring node voltage correlation by using an SWW-DTW algorithm to complete secondary identification; and checking and correcting a primary identification result and a secondary identification result.

Description

Technical Field

[0001] The invention relates to a method and system for identifying phase differences of users in a low-voltage transformer area, and belongs to the technical field of transformer area phase identification. Background Art

[0002] In low-voltage distribution networks, phase identification of users in the substation is an important task in the operation and management of power systems. Low-voltage substations are usually powered by a three-phase four-wire system, and user loads are distributed on different phase lines. Accurately identifying the phase to which the user belongs is of great significance for realizing the refined management of smart grids. Ensuring the accuracy of the basic information files of substation users is the key to ensuring the safety of electricity use by substation users and improving the electricity use experience of substation users. However, due to the large volume and wide range of low-voltage distribution networks in substations, the probability of expansion and modification is very high, and there are certain hidden wiring projects, the phase information of some users may be missing or recorded incorrectly. Traditional methods based on manual inspections or simple electrical parameter measurements are inefficient and difficult to meet the requirements of modern power systems for real-time and accuracy. Therefore, the development of an efficient and accurate method for phase identification of low-voltage substation users has become an urgent need in the current distribution network management. In recent years, with the rapid development of smart meters, data acquisition technology and big data analysis methods, a solid foundation has been laid for phase identification methods based on electricity consumption data. Therefore, this patent fully explores the characteristics of voltage and power data stored in the acquisition system and proposes a method for phase identification of users in low-voltage areas.

[0003] The current low-voltage distribution network phase identification methods are mainly divided into the following three categories:

[0004] 1) Correlation analysis method based on the assumption that the voltage curves of the same-phase users are similar. This type of method only focuses on the correlation of voltage curves between nodes. However, the assumption that the voltage curves of the same-phase users are similar is generally only approximately true for two nodes with close electrical distances. Therefore, its recognition ability is limited and it is easy to make misjudgments.

[0005] 2) Clustering methods based on the assumption that the voltage curves of users in the same phase are similar or that the curve features are similar. This type of method generally has strong recognition ability and adaptability, but requires large differences in the voltage fluctuation characteristics between phases, and is prone to misjudgment in scenarios where the voltage fluctuation characteristics between phases are not obvious.

[0006] 3) Identification method based on the basic balance assumption of the sum of the power of the same-phase users and the head-end power. There are two types of such methods. One is to take the phase difference of all users as a variable and establish an optimization model for solution; the other is to establish a phase power balance model and use the multivariate linear regression method to determine the phase difference of the user. This method has good identification ability and adaptability, but only focuses on power and does not consider the similarity of the voltage curves of the same-phase nodes. It may cause the voltage curves of the same-phase users to violate the assumption of basic similarity, resulting in misjudgment.

[0007] At present, there are certain deficiencies in the above three methods, and it is urgent to study a method that takes into account the similarity hypothesis of the voltage curves of in-phase users and the basic balance hypothesis between the sum of the powers of in-phase users and the power at the head end, so as to improve the accuracy of identifying the phase of users in low-voltage distribution areas. Summary of the Invention

[0008] In order to solve the problems existing in the above-mentioned prior art, the present invention proposes a method and system for identifying the phase of users in a low-voltage distribution area. First, the voltage correlation between nodes is obtained by using the Pearson correlation coefficient, and the electrical distance matrix of the nodes in the distribution area is calculated. Secondly, the DBSCAN algorithm is used to group the nodes of the electrical distance matrix in the distribution area. Thirdly, a phase-separated power balance equation is established to perform regression analysis on each group of nodes, determine the phase of each group of nodes, and complete the initial identification of the phases in the distribution area. Then, for the node groups whose phases are difficult to determine, the SWW-DTW algorithm is used to measure the voltage correlation of the nodes to complete the secondary identification of the phases in the distribution area. Finally, the identification results of the phases in the distribution area are tested and corrected according to the phase-separated line loss level in the distribution area, and the phase error situation can be judged and the phases can be corrected.

[0009] The technical solution of the present invention is as follows:

[0010] On the one hand, the present invention proposes a method for identifying the phase of users in a low-voltage distribution area, including the following steps:

[0011] Obtain the voltage correlation between user nodes by using the Pearson correlation coefficient, and calculate the electrical distance matrix of the user nodes in the distribution area;

[0012] Based on the electrical distance matrix of the distribution area, use the DBSCAN algorithm for clustering to obtain the grouping of the user nodes in the distribution area;

[0013] Establish a phase-separated power balance equation to perform regression analysis on each group of user nodes in the distribution area after grouping, determine the phase of each group of user nodes in the distribution area, and complete the initial identification;

[0014] Determine whether the initial identification result of the phase of each group of user nodes in the distribution area is valid through a preset rule. If it is invalid, use the SWW-DTW algorithm to measure the voltage correlation of the nodes to complete the secondary identification;

[0015] Perform the inspection and correction of the initial identification result and the secondary identification result.

[0016] As a preferred embodiment, the step of obtaining the voltage correlation between user nodes by using the Pearson correlation coefficient and calculating the electrical distance matrix of the user nodes in the distribution area is specifically as follows:

[0017] Equivalent the three-phase users to three single-phase users, regard each single-phase user as a node, and for any two nodes, obtain the voltage correlation coefficient between the nodes by using the Pearson correlation coefficient;

[0018] Calculate the voltage distance between any two nodes in the distribution area through the voltage correlation coefficient between nodes, and construct the electrical distance matrix of the user nodes in the distribution area.

[0019] As a preferred embodiment, the steps of clustering the user nodes in the distribution area by using the DBSCAN algorithm based on the electrical distance matrix of the distribution area are specifically as follows:

[0020] Initialize the DBSCAN algorithm, use the minimum electrical distance between phases of the main meter in the distribution area as the neighborhood radius, and set the minimum number of points included in the neighborhood to 2;

[0021] Cluster the electrical distance matrix of the user nodes in the distribution area through the initialized DBSCAN algorithm to obtain the grouping of the user nodes in the distribution area. The user nodes that are not grouped are outliers, and each outlier is used as a grouping of the user nodes in a distribution area alone.

[0022] As a preferred embodiment, the steps of establishing a phase power balance equation to perform regression analysis on each group of user nodes in the distribution area after grouping, determining the phase of each group of user nodes in the distribution area, and completing the initial identification of the phases of the user nodes in the distribution area are as follows:

[0023] Calculate the sum of the powers of each group of user nodes in the distribution area. Use the sum of the powers of each group of user nodes in the distribution area as the independent variable and the three-phase power of the main meter as the dependent variable to establish a phase power balance equation;

[0024] Relying on the meter measurement data, use the least squares method to solve the phase power balance equation to obtain three groups of regression parameters corresponding to the three phases, and calculate the grouping evaluation index according to the three groups of regression parameters;

[0025] Sort the three grouping evaluation indexes of each group of user nodes in the distribution area, and take the phase of the phase power balance equation corresponding to the largest one as the initial phase identification result of this group.

[0026] As a preferred embodiment, in the step of determining whether the initial identification result of the phase of each group of user nodes in the distribution area is valid by using a preset rule, the preset rule is specifically as follows:

[0027] If the sum of the powers of any group of user nodes in the distribution area is zero, the initial phase identification result of this group is invalid;

[0028] If any phase grouping evaluation index of any group of user nodes in the distribution area is less than the set first threshold, the initial phase identification result of this group is invalid;

[0029] If the t-test value of any phase of any group of user nodes in the distribution area is less than the set second threshold, the initial phase identification result of this group is invalid;

[0030] If the degree of deviation of any phase regression parameter of any group of substation area user nodes from 1 is greater than the set third threshold, the initial phase identification result of this group is invalid.

[0031] As a preferred embodiment, the steps of using the SWW-DTW algorithm to measure the node voltage correlation and complete the secondary identification are as follows:

[0032] For the group of substation area user nodes with invalid initial phase identification results, obtain the voltage sequences of the user nodes in the group of substation area user nodes, and normalize the voltage sequences to the interval [0, 1];

[0033] Divide the normalized voltage sequences into multiple subsequences, calculate the Pearson correlation coefficients between the subsequences, and calculate the weight coefficients between the subsequences through the Pearson correlation coefficients between the subsequences;

[0034] Calculate the DTW distances between the subsequences, and calculate the SWW-DTW distance according to the DTW distances between the subsequences and the weight coefficients;

[0035] For each group of substation area user nodes with invalid initial phase identification results, sort the average values of the SWW-DTW distances between it and the groups of substation area user nodes with determined phases, select the minimum value of the average value of the SWW-DTW distances, obtain the phase of the group of substation area user nodes with determined phases corresponding to this minimum value, and use it as the phase of this group of substation area user nodes with invalid initial phase identification results.

[0036] As a preferred embodiment, the steps of checking and correcting the initial identification result and the secondary identification result include:

[0037] Check whether the initial identification result and the secondary identification result are correct through the phase line loss rate level;

[0038] For the identification results with incorrect inspection results, calculate the SWW-DTW distances between each user node in the negative loss phase and each user node in the high loss phase. If there are n1 user nodes in the negative loss phase and n2 user nodes in the high loss phase, a total of n1×n2 SWW-DTW distances are calculated;

[0039] For any user node in the negative loss phase, set the SWW-DTW distances between it and all nodes in the high loss phase as a group. Traversing all user nodes in the negative loss phase can obtain n1 groups in total. One group contains n2 numbers. Sort the maximum values of the SWW-DTW distances in each group from small to large as the suspicion ranking of the phase anomaly nodes;

[0040] Sort the user nodes in descending order of suspicion, move them out of the negative loss phase and into the high loss phase one by one, and then check through the phase line loss rate level. If the check is passed, it is considered that the true phase of the moved-out user node is the high loss phase, and the correction is terminated; if the check fails, move the user node moved out this time back to the negative loss phase.

[0041] On the other hand, the present invention also proposes a low-voltage substation area user phase identification system, including:

[0042] An electrical distance matrix construction module, configured to obtain the voltage correlation between user nodes by using the Pearson correlation coefficient, and calculate the electrical distance matrix of the substation area user nodes;

[0043] A grouping and clustering module, which performs clustering based on the electrical distance matrix of the substation area by using the DBSCAN algorithm to obtain the grouping of the substation area user nodes;

[0044] A primary identification module, configured to establish a phase power balance equation to perform regression analysis on each group of substation area user nodes after grouping, determine the phase of each group of substation area user nodes, and complete the primary identification;

[0045] A secondary identification module, configured to determine whether the primary identification result of the phase of each group of substation area user nodes is valid through a preset rule. If it is invalid, use the SWW-DTW algorithm to measure the node voltage correlation and complete the secondary identification;

[0046] An inspection and correction module, configured to perform inspection and correction on the primary identification result and the secondary identification result.

[0047] On yet another aspect, the present invention also proposes an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the low-voltage substation area user phase identification method according to any embodiment of the present invention.

[0048] On yet another aspect, the present invention also proposes a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the low-voltage substation area user phase identification method according to any embodiment of the present invention.

[0049] The beneficial effects of the present invention are as follows:

[0050] A low-voltage substation area user phase identification method and system provided by the present invention can give full play to the advantages of the massive data stored in the power consumption acquisition system, fully integrate the advantages and characteristics of the clustering method based on the assumption of similar voltage curves or curve characteristics of in-phase users and the identification method based on the assumption that the sum of in-phase user powers is basically balanced with the head-end power, make up for the shortcomings of the two methods, can efficiently and accurately realize the identification of the substation area phase, and can be considered to be encapsulated and put into the power consumption acquisition system to provide services for the power grid company's line loss management, operation and maintenance control, and safe operation.

[0051] Additional aspects and advantages of the present invention will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present invention. Additionally, various aspects and advantages of the present invention may be realized and obtained by means of the method steps and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic flow chart of the method according to the first embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only a part of the embodiments of the present invention, rather than all of 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.

[0054] It should be understood that the step numbers used herein are only for convenience of description and do not limit the order of execution of the steps.

[0055] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0056] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0057] The term " / and" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0058] Embodiment 1:

[0059] Refer to Figure 1 , this embodiment provides a method for identifying the phase of users in a low-voltage substation area, including the following steps:

[0060] S100. Obtain the voltage correlation between user nodes by using the Pearson correlation coefficient, and calculate the electrical distance matrix of the user nodes in the substation area;

[0061] S200. Based on the electrical distance matrix of the substation area, perform clustering using the DBSCAN algorithm to obtain the grouping of the user nodes in the substation area;

[0062] S300. Establish a split-phase power balance equation to perform regression analysis on each group of substation area user nodes after grouping, determine the phase of each group of substation area user nodes, and complete the initial identification;

[0063] S400. Determine whether the initial identification results of the phases of each group of substation area user nodes are valid through preset rules. If they are invalid, use the SWW-DTW algorithm to measure the node voltage correlation and complete the secondary identification;

[0064] S500. Conduct the inspection and correction of the initial identification results and the secondary identification results.

[0065] Specifically, in this embodiment, step S100 is as follows:

[0066] Equivalent three-phase users to three single-phase users, regard each single-phase user as a node. For any two nodes, obtain the node voltage correlation coefficient using the Pearson correlation coefficient. For node i and node j, their voltage correlation coefficient ρ ij is:

[0067]

[0068] where l represents the time series length; U i,t and U j,t are the voltage values of node i and node j at time t respectively; and are the voltage means of node i and node j respectively.

[0069] Define the electrical distance d ij between node i and node j as:

[0070] d ij = 1 - ρ ij ;

[0071] For all nodes in the substation area, calculate the electrical distance between each pair to obtain the substation area electrical distance matrix D, as shown specifically below:

[0072]

[0073] where m represents the number of substation area electric meters.

[0074] When the voltage similarity between two nodes is higher, their electrical distance is smaller. The electrical distances of in-phase nodes in the same meter box or adjacent meter boxes are generally relatively small. Based on this, in this embodiment, the DBSCAN clustering algorithm is used to group the nodes in the transformer substation area. DBSCAN is a density-based clustering algorithm that defines a cluster as the largest set of density-connected points and can divide areas with sufficient high density into clusters. DBSCAN requires two parameters: the neighborhood radius Eps and the minimum number of points MinPts in the neighborhood. In this embodiment, the minimum number of points MinPts in the neighborhood is set to 2; the minimum electrical distance between the phases of the main meter in the transformer substation area is used as the neighborhood radius Eps, as shown in the following formula:

[0075] Eps = min(d 0,AB , d 0,AC , d 0,BC );

[0076] where, min(·) represents taking the minimum value; d 0,AB , d 0,AC and d 0,BC respectively represent the electrical distances between phase A and phase B, phase A and phase C, and phase B and phase C of the main meter in the transformer substation area.

[0077] Cluster the electrical distance matrix D of the user nodes in the transformer substation area through the initialized DBSCAN algorithm to obtain the grouping of the user nodes in the transformer substation area. The user nodes that are not grouped are outliers, and each outlier is taken as a grouping of the user nodes in a transformer substation area.

[0078] As a preferred implementation manner of this embodiment, in step S300, assume that the clustering results in n groups. For these n groups of nodes, it is considered that all the nodes included in each group belong to the same phase. Determine the phase attribution of each group of nodes according to the phase power balance equation to complete the initial identification of the phases in the transformer substation area. The specific steps are as follows:

[0079] Calculate the sum of the powers of each group of user nodes in the transformer substation area:

[0080]

[0081] where, P i represents the sum of the powers of the i-th group of nodes; z i represents the number of nodes in the i-th group; P i,j represents the power of the j-th node in the i-th group.

[0082] Take the sum of the powers of each group of user nodes in the transformer substation area as the independent variable and the three-phase power of the main meter as the dependent variable to establish a phase power balance equation, as shown below:

[0083]

[0084] where, P0,A , P 0,B and P 0,C respectively represent the A, B, and C phase powers of the total meter in the transformer area; ε represents the residual; β A , β B and β C represent the intercept terms; β i,A , β i,B and β i,C respectively represent the regression parameters of the A, B, and C phase power balance models.

[0085] Relying on a large amount of measurement data of smart meters stored in the power consumption and acquisition system, the least squares method is used to solve the above-mentioned phase-separated balance equations, and three groups of regression parameters corresponding to the three phases are obtained. The grouping evaluation indexes are calculated according to the three groups of regression parameters, as shown below:

[0086]

[0087] Among them, α i,A , α i,B and α i,C represent the grouping evaluation indexes of the i-th group of nodes, T i,A , T i,B and T i,C represent the t-test values of the i-th group of nodes, all corresponding to the A, B, and C phase power balance equations respectively.

[0088] Sort the three grouping evaluation indexes of each group of transformer area user nodes, and take the phase corresponding to the largest one as the initial phase identification result of this grouping.

[0089] As a preferred implementation manner of this embodiment, to improve the accuracy of the identification result, in step S400, if the data of node grouping satisfies one of the following determination rules, the phase result determined by the above-mentioned initial transformer area phase identification method is invalid, and the phase needs to be determined by the secondary transformer area phase identification method. Assume that the phase of node grouping determined by the initial identification method is the α phase, and the determination rules are as follows:

[0090] Rule 1: If the sum of the powers of any group of transformer area user nodes is zero, the initial phase identification result of this grouping is invalid;

[0091] Rule 2: If the α-phase grouping evaluation index of any group of transformer area user nodes is less than the set first threshold, the initial phase identification result of this grouping is invalid;

[0092] Rule 3: If the α-phase t-test value of any group of transformer area user nodes is less than the set second threshold, the initial phase identification result of this grouping is invalid;

[0093] Rule 4: If the degree of deviation of the α-phase regression parameter of any group of substation area user nodes from 1 is greater than the set third threshold, the initial phase discrimination result of this group is invalid.

[0094] In this embodiment, for the first threshold, the second threshold, and the third threshold, they can be set to 20, 5, and 0.3.

[0095] As a preferred implementation manner of this embodiment, in step S400, the steps of using the SWW-DTW algorithm to measure the node voltage correlation and complete the secondary discrimination are as follows:

[0096] For the substation area user node group with an invalid initial phase discrimination result, obtain the voltage sequences U with length T of nodes i and j in the substation area user node group i and U j , and normalize the voltage sequences to the interval [0, 1];

[0097] Use a sliding window function with a window length of s and a step size of k for each window movement to divide the normalized voltage sequences into H subsequences. Taking the voltage sequence of node i as an example U i , its nth voltage subsequence L i,n can be expressed by the following formula:

[0098] L i,n =U i [1 + k(t - 1):1 + s + k(t - 1)];

[0099] Calculate the Pearson correlation coefficient ρ ij,n between each subsequence, and calculate the weight coefficient w ij,n between each subsequence through the Pearson correlation coefficient between each subsequence, as shown below:

[0100]

[0101] Then, calculate the DTW distance DTW(L i,n , L j,n ) between each subsequence, and calculate the SWW-DTW distance according to the DTW distance and weight coefficient between each subsequence, as shown below:

[0102]

[0103] The smaller the SWW-DTW distance between two node voltage sequences, the more similar their voltage curves are, and the greater the possibility that they belong to the same phase. Based on this principle, the secondary phase discrimination is performed in this embodiment, and the specific steps are as follows:

[0104] Calculate the average SWW-DTW distance between the grouped user nodes in the substations where the initial phase identification results are invalid and the grouped user nodes in the substations with the determined phases. The specific formula is as follows:

[0105]

[0106] Among them, SD ij represents the average SWW-DTW distance between the i-th grouped nodes with undetermined phases and the j-th grouped nodes with determined phases; ni represents the total number of nodes in the i-th grouped nodes with undetermined phases; n j represents the total number of nodes in the j-th grouped nodes with determined phases; Ui q represents the voltage sequence of the q-th node in the i-th grouped nodes with undetermined phases; U jp represents the p-th voltage sequence of the j-th grouped nodes with undetermined phases.

[0107] For each grouped user nodes in the substations where the initial phase identification results are invalid, sort the average SWW-DTW distances between them and the grouped user nodes in the substations with the determined phases, select the minimum value of the average SWW-DTW distances, obtain the phase of the grouped user nodes in the substation with the determined phases corresponding to this minimum value, and use it as the phase of the grouped user nodes in the substation where the initial phase identification results are invalid.

[0108] As a preferred implementation mode of this embodiment, in step S500, the steps of verifying and correcting the initial identification results and the secondary identification results include:

[0109] Verify whether the initial identification results and the secondary identification results are correct through the phase line loss rate level, as shown in the following formula:

[0110]

[0111] Among them, δ l and δ u are respectively the upper and lower limits of the normal range of the line loss rate, generally set to 0.5% and 4%; T represents the length of the time series; nA, nB, and nC respectively represent the number of nodes in phases A, B, and C; P 0,A,t , P 0,B,t and P 0,C,t respectively represent the powers of phases A, B, and C of the main meter at time t; P i,A,t , P i,B,t and P 0,C,t respectively represent the powers of phases A, B, and C of the sub-meter at time t.

[0112] The inspection of the phase discrimination results is carried out through the above formula. If there is one phase with high loss and one phase with negative loss, it is considered that the result of phase discrimination does not conform to the actual situation of the transformer substation area. Since the method proposed in this patent will not produce too many misjudgment phenomena, assuming that there is only one node with incorrect phase, the following method is used for correction:

[0113] For the incorrect discrimination results of the inspection results, calculate the SWW-DTW distances between each user node in the negative loss phase and each user node in the high loss phase. For any one user node in the negative loss phase, set its SWW-DTW distances from all nodes in the high loss phase as a group. Traverse all nodes in the negative loss phase to obtain all groups. Sort the maximum values of the SWW-DTW distances of each group from small to large as the suspicion ranking of the phase anomaly nodes;

[0114] Remove the user nodes from the negative loss phase and move them into the high loss phase in turn according to the suspicion ranking, and then conduct an inspection through the phase line loss rate level. If the inspection is passed, it is considered that the true phase of the removed user node is the high loss phase, and the correction is terminated; if the inspection is not passed, move the user node removed this time back to the negative loss phase.

[0115] Embodiment 2:

[0116] This embodiment proposes a low-voltage transformer substation area user phase discrimination system, including:

[0117] An electrical distance matrix construction module, which is used to obtain the voltage correlation between user nodes by using the Pearson correlation coefficient and calculate the electrical distance matrix of the user nodes in the transformer substation area; this module is used to implement the function of step S100 in Embodiment 1 and will not be elaborated here;

[0118] A grouping and clustering module, which is based on the electrical distance matrix of the transformer substation area and uses the DBSCAN algorithm for clustering to obtain the grouping of the user nodes in the transformer substation area; this module is used to implement the function of step S200 in Embodiment 1 and will not be elaborated here;

[0119] A primary discrimination module, which is used to establish a phase power balance equation to conduct a regression analysis on each group of user nodes in the transformer substation area after grouping, determine the phase of each group of user nodes in the transformer substation area, and complete the primary discrimination; this module is used to implement the function of step S300 in Embodiment 1 and will not be elaborated here;

[0120] A secondary discrimination module, which is used to determine whether the primary discrimination results of the phase of each group of user nodes in the transformer substation area are valid through a preset rule. If they are invalid, use the SWW-DTW algorithm to measure the node voltage correlation and complete the secondary discrimination; this module is used to implement the function of step S400 in Embodiment 1 and will not be elaborated here;

[0121] The verification and correction module is used to verify and correct the primary identification result and the secondary identification result; this module is used to implement the function of step S500 in the first embodiment, and will not be elaborated here.

[0122] Embodiment 3:

[0123] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the low-voltage substation area user phase identification method as described in any embodiment of the present invention.

[0124] Embodiment 4:

[0125] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the low-voltage substation area user phase identification method as described in any embodiment of the present invention.

[0126] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent the situation of A existing alone, A and B existing simultaneously, and B existing alone. Among them, A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0127] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints 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 application.

[0128] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated here.

[0129] In several embodiments provided in the present application, if any function 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 application, in essence, or the part that contributes to the prior art, or a part of this 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 application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM for short), random access memories (RAM for short), magnetic disks, or optical discs that can store program codes.

[0130] The above are only the embodiments of the present invention, and thus do not limit the patent scope of the present invention. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for identifying low voltage area users, characterized in that: The following steps are involved: The voltage correlation between user nodes is obtained using the Pearson correlation coefficient, and the electrical distance matrix of user nodes in the substation area is calculated; Based on the electrical distance matrix of the substation, the DBSCAN algorithm is used for clustering to obtain the grouping of user nodes in the substation; Establish the phase power balance equation to perform regression analysis on the user nodes in each group of substations, determine the phase difference of the user nodes in each group of substations, and complete the initial identification; The preset rules are used to determine whether the initial identification results of each group of user nodes in each substation are valid. If invalid, the SWW-DTW algorithm is used to measure the node voltage correlation and complete the secondary identification. Check and correct the initial and secondary identification results.

2. A method for identifying low voltage area users according to claim 1, characterized in that: The steps of using the Pearson correlation coefficient to obtain the voltage correlation between user nodes and calculating the electrical distance matrix of the user nodes in the substation area are as follows: The three-phase user is equivalent to three single-phase users, and each single-phase user is regarded as a node. For any two nodes, the voltage correlation coefficient between nodes is obtained using the Pearson correlation coefficient. The voltage distance between any two nodes in the substation is calculated through the voltage correlation coefficient between nodes, and the electrical distance matrix of user nodes in the substation is constructed.

3. A method for identifying low voltage area users according to claim 1, characterized in that: The steps of clustering the user nodes in the substation area by using the DBSCAN algorithm based on the substation area electrical distance matrix to obtain the grouping of the substation area user nodes are as follows: Initialize the DBSCAN algorithm, set the minimum electrical distance between phases of the total meter in the substation area as the neighborhood radius, and set the minimum number of neighborhood points to 2; The electrical distance matrix of the user nodes in the substation area is clustered by the initialized DBSCAN algorithm to obtain the user node grouping in the substation area. The user nodes not included in the group are outliers, and each outlier is regarded as a separate user node group in the substation area.

4. A method for identifying low voltage area users according to claim 1, characterized in that: The steps of establishing the phase-splitting power balance equation and performing regression analysis on the grouped user nodes in each area to determine the phase difference of each group of user nodes in the area and complete the initial identification of the phase difference of the users in the area are as follows: Calculate the sum of the power of each group of user nodes in the substation area, take the sum of the power of each group of user nodes in the substation area as the independent variable, take the three-phase power of the total meter as the dependent variable, and establish the phase power balance equation; Relying on the meter measurement data, the least square method is used to solve the phase power balance equation to obtain three sets of regression parameters corresponding to the three phases. The group evaluation index is calculated based on the three sets of regression parameters. The three grouping evaluation indicators of each group of user nodes in the substation area are sorted, and the phase difference of the phase power balance equation corresponding to the largest one is taken as the initial phase difference identification result of the group.

5. A method for identifying low voltage area users according to claim 4, characterized in that: In the step of determining whether the respective initial identification results of each group of user nodes in each area are valid by using the preset rules, the preset rules are specifically as follows: If the sum of the power of any group of user nodes in the area is zero, the initial phase identification result of the group is invalid; If any phase grouping evaluation index of any group of user nodes in the substation area is less than the set first threshold, the initial phase identification result of the group is invalid; If any phase t-test value of any group of user nodes in the substation area is less than the set second threshold, the initial phase identification result of the group is invalid; If the degree to which any phase regression parameter of any group of area user nodes deviates from 1 is greater than the set third threshold, the initial phase identification result of the group is invalid.

6. A method for identifying low voltage area users according to claim 1, characterized in that: The steps of using the SWW-DTW algorithm to measure the node voltage correlation and complete the secondary identification are as follows: For the user node grouping in the substation area whose initial phase identification result is invalid, the voltage sequence of the user nodes in the user node grouping in the substation area is obtained, and the voltage sequence is normalized to the interval [0,1]; The normalized voltage sequence is divided into multiple subsequences, the Pearson correlation coefficients between the subsequences are calculated, and the weight coefficients between the subsequences are calculated by the Pearson correlation coefficients between the subsequences; Calculate the DTW distance between each subsequence, and calculate the SWW-DTW distance based on the DTW distance and weight coefficient between each subsequence; For each group of area user node groups whose initial phase identification results are invalid, sort them with the average SWW-DTW distances of each area user node group that has been determined to be different, select the minimum SWW-DTW distance average value, obtain the phase difference of the area user node group that has been determined to be different corresponding to the minimum value, and use it as the phase difference of the area user node group whose initial phase identification results are invalid.

7. A method for identifying low voltage area users according to claim 1, characterized in that: The steps of checking and correcting the primary identification result and the secondary identification result include: Check whether the initial identification results and the secondary identification results are correct by dividing the phase line loss rate level; For the identification results that are incorrect, calculate the SWW-DTW distances between each user node in the negative loss phase and each user node in the high loss phase. If there are n1 user nodes in the negative loss phase and n2 user nodes in the high loss phase, calculate a total of n1×n2 SWW-DTW distances; For any user node in the negative loss phase, the SWW-DTW distance between it and all nodes in the high loss phase is set as a group. By traversing all user nodes in the negative loss phase, a total of n1 groups can be obtained, and a group contains n2 numbers. The maximum values ​​of the SWW-DTW distances of each group are sorted from small to large as the suspect sorting of phase abnormal nodes; The user nodes are moved out of the negative loss phase and into the high loss phase in order of suspicion, and then tested by the phase line loss rate level. If the test is passed, the real phase of the moved user node is considered to be the high loss phase, and the correction is terminated; if the test is not passed, the user node that was moved out this time is moved back to the negative loss phase.

8. A low voltage area user phase identification system, characterized in that: include: The electrical distance matrix building module is used to obtain the voltage correlation between user nodes using the Pearson correlation coefficient and calculate the electrical distance matrix of user nodes in the substation area; The grouping and clustering module uses the DBSCAN algorithm to perform clustering based on the electrical distance matrix of the substation area to obtain the grouping of user nodes in the substation area; The initial identification module is used to establish a phase-by-phase power balance equation to perform regression analysis on the user nodes in each group of substations, determine the phase difference of the user nodes in each group of substations, and complete the initial identification; The secondary identification module is used to determine whether the primary identification results of each group of user nodes in each substation area are valid through preset rules. If invalid, the SWW-DTW algorithm is used to measure the node voltage correlation to complete the secondary identification; The verification and correction module is used to verify and correct the initial identification results and the secondary identification results.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the low-voltage station area user phase identification method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for identifying low-voltage area users according to any one of claims 1 to 7 is implemented.

Images