A method, device, electronic device and storage medium for phase division of distribution station area

Abstract

The present invention discloses a phase division method, device, electronic device, and storage medium for power distribution substations, which are used to solve the technical problem that traditional methods have difficulty identifying the topology and phase information of end-users of the power grid. The present invention includes: collecting the user voltage sequence of each user in the power grid and the transformer voltage sequence of each transformer substation; calculating the distance similarity between the user voltage sequence and the transformer voltage sequence; judging the affiliation between the user and the transformer substation based on the distance similarity to obtain user clusters under each transformer substation; performing phase clustering on the user voltage sequences of all users under the user cluster to obtain phase clusters; calculating the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs; and determining the phase of the user voltage sequence based on the mathematical confidence.

Description

Technical Field

[0001] The present invention relates to the field of power distribution technology, and in particular to a method, device, electronic equipment and storage medium for phase division of a power distribution station area. Background Art

[0002] With the continuous development of distribution networks, the access of distributed energy resources and the increasing penetration of devices such as energy storage and electric vehicles in terminal distribution networks have reduced the observability of low-voltage distribution networks and increased information uncertainty. This reduced observability has limited the control, prediction, and management capabilities of distribution networks. Therefore, it is necessary to establish a physical model of the low-voltage distribution network to enhance network observability. The physical model of the low-voltage distribution network mainly includes a physical topology model and a phase model. The topology model helps power supply companies understand the physical connection relationships between substations and can be used to achieve accurate line loss analysis, control the operating status of distributed power sources, provide early warnings for users experiencing power outages, and calculate power outage duration. The phase model helps to identify three-phase imbalance issues in substations, adjust user phase sequences in a targeted manner, improve equipment reliability, and reduce network losses.

[0003] However, due to observability limitations, traditional methods have difficulty identifying the topology and phase information of end-users in the power grid. Summary of the Invention

[0004] The present invention provides a phase division method, device, electronic device and storage medium for a power distribution area, which are used to solve the technical problem that traditional methods are difficult to identify the topology and phase information of end users of the power grid.

[0005] The present invention provides a phase division method for a distribution station area, comprising:

[0006] Collect the user voltage sequence of each user in the power grid and the transformer voltage sequence of each transformer substation;

[0007] Calculating the distance similarity between the user voltage sequence and the transformer voltage sequence;

[0008] Determine the affiliation between the user and the transformer substation according to the distance similarity, and obtain user clusters under each transformer substation;

[0009] performing phase clustering on user voltage sequences of all users under the user clustering to obtain phase clusters;

[0010] Calculate the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs;

[0011] The phase of the user voltage sequence is determined according to the mathematical confidence level.

[0012] Optionally, the step of calculating the distance similarity between the user voltage sequence and the transformer voltage sequence includes:

[0013] Calculating an average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence;

[0014] Calculating the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence;

[0015] Calculating a dynamic bending distance of a difference sequence between the user voltage sequence and the transformer voltage sequence;

[0016] The distance similarity between the user voltage sequence and the transformer voltage sequence is calculated using the average character sequence Euclidean distance, the variance character sequence and cosine distance, and the difference sequence dynamic bending distance.

[0017] Optionally, the user voltage sequence includes a plurality of user voltage data; the transformer voltage sequence includes a plurality of transformer voltage data; and the step of calculating the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence includes:

[0018] Performing average segmentation on the user voltage sequence to obtain a user voltage mean value sequence;

[0019] Performing average segmentation on the transformer voltage sequence to obtain a transformer voltage mean value sequence;

[0020] Performing character conversion on the user voltage mean value sequence to obtain a user voltage average character sequence;

[0021] Performing character conversion on the transformer voltage mean value sequence to obtain a transformer voltage average character sequence;

[0022] The average character sequence of the user voltage and the average character sequence of the transformer voltage are used to calculate the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence.

[0023] Optionally, the step of calculating the variance symbol sequence cosine distance between the user voltage sequence and the transformer voltage sequence includes:

[0024] Calculating the variance of user voltage data in each segment of the user voltage sequence to obtain a user voltage variance sequence;

[0025] Calculating the variance of transformer voltage data in each segment of the transformer voltage sequence to obtain a transformer voltage variance sequence;

[0026] Performing character conversion on the user voltage variance sequence to obtain a user voltage variance character sequence;

[0027] Performing character conversion on the transformer voltage variance sequence to obtain a transformer voltage variance character sequence;

[0028] The user voltage variance character sequence and the transformer voltage variance character sequence are used to calculate a variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence.

[0029] Optionally, the step of calculating a dynamic bending distance of a difference sequence between the user voltage sequence and the transformer voltage sequence includes:

[0030] Calculating the difference between adjacent user voltage data in each segment of the user voltage sequence to obtain a user voltage difference sequence;

[0031] Calculating the difference between adjacent transformer voltage data in each segment of the transformer voltage sequence to obtain a transformer voltage difference sequence;

[0032] The user voltage difference sequence and the transformer voltage difference sequence are used to calculate a difference sequence dynamic bending distance between the user voltage sequence and the transformer voltage sequence.

[0033] Optionally, the step of calculating the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs includes:

[0034] Calculating the Spearman correlation coefficient matrix between the user voltage sequences of every two users under the user clustering;

[0035] Performing Fisher transformation on the Spearman correlation coefficient matrix to obtain a standard correlation coefficient matrix;

[0036] The standard correlation coefficient matrix is ​​used to calculate the mathematical confidence between each user voltage sequence and the corresponding phase cluster.

[0037] Optionally, the step of determining the phase of the user voltage sequence according to the mathematical confidence level includes:

[0038] Determining whether the mathematical confidence level is greater than or equal to a preset confidence threshold;

[0039] If so, the phase corresponding to the phase cluster to which the user voltage sequence belongs is determined as the phase of the user voltage sequence.

[0040] The present invention also provides a phase division device for a distribution station area, comprising:

[0041] The acquisition module is used to collect the user voltage sequence of each user in the power grid and the transformer voltage sequence of each transformer station;

[0042] A distance similarity calculation module, configured to calculate the distance similarity between the user voltage sequence and the transformer voltage sequence;

[0043] A user clustering module is used to determine the affiliation between the user and the transformer substation according to the distance similarity, and obtain user clusters under each transformer substation;

[0044] A phase clustering module, configured to perform phase clustering on user voltage sequences of all users in the user cluster to obtain phase clusters;

[0045] A mathematical confidence calculation module is used to calculate the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs;

[0046] A phase division module is used to determine the phase of the user voltage sequence according to the mathematical confidence level.

[0047] The present invention further provides an electronic device, comprising a processor and a memory:

[0048] The memory is used to store program code and transmit the program code to the processor;

[0049] The processor is configured to execute any one of the above methods for dividing the phase of a power distribution area according to instructions in the program code.

[0050] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to execute the phase division method of the power distribution station area as described in any one of the above items.

[0051] As can be seen from the above technical solutions, the present invention has the following advantages: It identifies the topological relationships of end-users in the power grid by collecting the user voltage sequences of each user in the power grid and the transformer voltage sequences of each transformer substation; calculating the distance similarity between the user voltage sequences and the transformer voltage sequences; determining the affiliation between the user and the transformer substation based on the distance similarity, and obtaining user clusters under each transformer substation. The present invention also obtains the phase information of end-users in the power grid by performing phase clustering on the user voltage sequences of each user in the user cluster to obtain phase clusters; calculating the mathematical confidence level between each user voltage sequence and the phase cluster to which it belongs; and determining the phase of the user voltage sequence based on the mathematical confidence level. This reduces the difficulty of identifying the topology and phase information of end-users in the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 A flowchart of a phase division method for a distribution station area provided by an embodiment of the present invention;

[0054] Figure 2 A flowchart of a phase division method for a distribution station area provided in another embodiment of the present invention;

[0055] Figure 3 This is a structural block diagram of a phase division device for a distribution station area provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The embodiments of the present invention provide a method, device, electronic device and storage medium for phase division of a power distribution area, which are used to solve the technical problem that traditional methods are difficult to identify the topology and phase information of end users of the power grid.

[0057] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0058] See also Figure 1 , Figure 1 A flowchart of the steps of a phase division method for a distribution station area provided by an embodiment of the present invention.

[0059] The present invention provides a method for phase division of a distribution station area, which may specifically include the following steps:

[0060] Step 101, collecting the user voltage sequence of each user in the power grid and the transformer voltage sequence of each transformer substation;

[0061] In the embodiment of the present invention, firstly, user voltage data of each user in the power grid and transformer voltage data of the transformer may be collected to obtain a user voltage sequence and a transformer voltage sequence of the transformer substation.

[0062] Step 102, calculating the distance similarity between the user voltage sequence and the transformer voltage sequence;

[0063] Step 103: Determine the affiliation between the user and the transformer sub-area based on the distance similarity, and obtain the user clusters under each transformer sub-area;

[0064] After obtaining the user voltage sequence and the transformer voltage sequence, the distance similarity between the two can be calculated to determine the affiliation between each user and each transformer substation based on the distance similarity, and obtain the user clustering under each transformer substation, thereby forming the topological relationship of the transformer substation.

[0065] Step 104: performing phase clustering on the user voltage sequences of all users in the user clustering to obtain phase clusters;

[0066] After obtaining the user clusters under each transformer substation, phase clustering can be performed on the user voltage sequences of all users in the user cluster under each transformer substation to obtain multiple phase clusters.

[0067] In one example, the phases of the user voltage may include phase A voltage, phase B voltage, and phase C voltage; therefore, in the embodiment of the present invention, the phase cluster may include phase A phase cluster, phase B phase cluster, and phase C phase cluster.

[0068] Step 105 , calculating the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs;

[0069] Step 106: Determine the phase of the user voltage sequence according to the mathematical confidence level.

[0070] After determining the phase cluster of each user's user voltage sequence, the mathematical confidence level between each user's user voltage sequence and the phase cluster to which it belongs can be calculated. Based on the corresponding mathematical confidence level, it is determined whether the phase division of the user voltage sequence for that user is correct. If not, the user voltage sequence is divided into another phase cluster, and the mathematical confidence level is calculated again until the corresponding mathematical confidence level meets the division criteria.

[0071] The present invention identifies the topological relationships of end-users in the power grid by collecting the user voltage sequences of each user and the transformer voltage sequences of each transformer substation; calculating the distance similarity between the user voltage sequences and the transformer voltage sequences; determining the affiliation between the users and the transformer substations based on the distance similarity to obtain user clusters under each transformer substation; and finally, by performing phase clustering on the user voltage sequences of each user within the user clusters to obtain phase clusters; calculating the mathematical confidence level between each user voltage sequence and the phase cluster to which it belongs; and determining the phase of the user voltage sequence based on the mathematical confidence level to obtain the phase information of the end-users in the power grid. This reduces the difficulty of identifying the topology and phase information of end-users in the power grid.

[0072] See also Figure 2 , Figure 2 This is a flowchart of a phase division method for a distribution station area provided by another embodiment of the present invention. Specifically, the following steps may be included:

[0073] Step 201, collecting the user voltage sequence of each user in the power grid and the transformer voltage sequence of each transformer substation;

[0074] In the embodiment of the present invention, the user voltage data u of each user in the power grid can be collected first. i And the transformer voltage data of the transformer t i , get the user voltage sequence U={u i} and the transformer voltage sequence T in the transformer area = {t i}, where i = 1, 2, ..., n, and n represents the number of voltage data points.

[0075] Step 202, calculating the distance similarity between the user voltage sequence and the transformer voltage sequence;

[0076] In this embodiment of the present invention, step 202 may include the following sub-steps:

[0077] S21, calculating the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence;

[0078] S22, calculating the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence;

[0079] S23, calculating a dynamic bending distance of a difference sequence between a user voltage sequence and a transformer voltage sequence;

[0080] S24, the distance similarity between the user voltage sequence and the transformer voltage sequence is calculated using the average character sequence Euclidean distance, the variance character sequence and cosine distance, and the difference sequence dynamic bending distance.

[0081] Euclidean distance is a commonly used distance definition, which refers to the real distance between two points in m-dimensional space, or the natural length of a vector (that is, the distance from the point to the origin). The Euclidean distance in two-dimensional and three-dimensional space is the actual distance between two points.

[0082] Cosine distance, also known as cosine similarity, uses the cosine value of the angle between two vectors in vector space as a measure of the size of the difference between two individuals.

[0083] Dynamic time warping distance (DTW) is a metric for measuring the distance between two time series data.

[0084] In a specific implementation, after collecting the user voltage sequence and the transformer voltage sequence, the average character sequence Euclidean distance, variance character sequence cosine distance and difference sequence dynamic bending distance of the user voltage sequence and the transformer voltage sequence can be calculated to analyze the distance similarity between the two.

[0085] The user voltage sequence may include multiple user voltage data; the transformer voltage sequence may include multiple transformer voltage data; and step S21 may be calculated by the following steps:

[0086] S211, performing average segmentation on the user voltage sequence to obtain a user voltage mean value sequence;

[0087] S212, performing average segmentation on the transformer voltage sequence to obtain a transformer voltage mean value sequence;

[0088] S213, performing character conversion on the user voltage mean value sequence to obtain a user voltage average character sequence;

[0089] S214, performing character conversion on the transformer voltage mean value sequence to obtain a transformer voltage average character sequence;

[0090] S215 , using the average character sequence of the user voltage and the average character sequence of the transformer voltage, to calculate the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence.

[0091] In the specific implementation, in order to calculate the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence, the user voltage sequence U and the transformer voltage sequence T can be divided into p segments respectively, and the user voltage mean sequence is obtained. and transformer voltage mean value series in:

[0092]

[0093]

[0094] in, is the element of the user voltage mean value sequence, is the element of the transformer voltage mean sequence, and n is the number of voltage data points.

[0095] After obtaining the user voltage mean sequence and the transformer voltage mean sequence, the two can be symbolized and mapped to characters in the character space to obtain the user voltage mean character sequence. and transformer voltage average character sequence

[0096] Then calculate the Euclidean distance between the average character sequence of user voltage and the average character sequence of transformer voltage to obtain the average character sequence Euclidean distance between the two This distance considers the similarity of the long-time-scale local morphological characteristics of the user voltage series curve and the transformer voltage series curve.

[0097] In the embodiment of the present invention, the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence can be calculated by the following steps:

[0098] S221, calculating the variance of user voltage data in each segment of the user voltage sequence to obtain a user voltage variance sequence;

[0099] S222, calculating the variance of the transformer voltage data in each segment of the transformer voltage sequence to obtain a transformer voltage variance sequence;

[0100] S223, converting the user voltage variance sequence into characters to obtain a user voltage variance character sequence;

[0101] S224, performing character conversion on the transformer voltage variance sequence to obtain a transformer voltage variance character sequence;

[0102] S225 , using the user voltage variance character sequence and the transformer voltage variance character sequence, calculate the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence.

[0103] In the specific implementation, the variance of the user voltage data in each segment of the user voltage sequence can be calculated separately to obtain the user voltage variance sequence And calculate the variance of transformer voltage data in each segment of transformer voltage sequence respectively to obtain transformer voltage variance sequence in:

[0104]

[0105]

[0106] represents the elements in the user voltage variance sequence, Represents the elements in the transformer voltage variance series.

[0107] The user voltage variance sequence is calculated and transformer voltage variance series After that, the two can be symbolized and mapped to the characters in the character space to obtain the user voltage variance character sequence. and transformer voltage variance character sequence

[0108] Then calculate the cosine distance between the user voltage variance character sequence and the transformer voltage variance character sequence to obtain the cosine distance of the variance character sequences of the two. This distance considers the similarity of the short-time-scale local morphological features of the user voltage series curve and the transformer voltage series curve.

[0109] In an embodiment of the present invention, the dynamic bending distance of the difference sequence between the user voltage sequence and the transformer voltage sequence can be calculated by the following steps:

[0110] S231, calculating the difference between adjacent user voltage data in each segment of the user voltage sequence to obtain a user voltage difference sequence;

[0111] S232, calculating the difference between adjacent transformer voltage data in each segment of the transformer voltage sequence to obtain a transformer voltage difference sequence;

[0112] S233 , using the user voltage difference sequence and the transformer voltage difference sequence, calculate a dynamic bending distance of the difference sequence between the user voltage sequence and the transformer voltage sequence.

[0113] In the specific implementation, the difference between the adjacent user voltage data in each segment of the user voltage sequence can be calculated to obtain the user voltage difference sequence And, respectively calculate the difference between adjacent transformer voltage data in each segment of the transformer voltage sequence to obtain the transformer voltage difference sequence in:

[0114] Δu i =u i+1 -u i

[0115] Δt i =t i+1 -t i

[0116] Then, the dynamic bending distance DTW (Δu ) between the user voltage sequence and the transformer voltage sequence can be calculated based on the obtained user voltage difference sequence and transformer voltage difference sequence. i , Δt i ). This distance considers the similarity of the overall change trends of the user voltage sequence curve and the transformer voltage sequence curve.

[0117] After obtaining the average character sequence Euclidean distance, variance character sequence and cosine distance, and difference sequence dynamic bending distance between the user voltage sequence and the transformer voltage sequence, the distance similarity co between the user voltage sequence and the transformer voltage sequence can be calculated. The specific calculation process is shown in the following formula:

[0118]

[0119] Step 203: Determine the affiliation between the user and the transformer sub-area based on the distance similarity, and obtain the user clusters under each transformer sub-area;

[0120] After obtaining the distance similarity between the user voltage sequence and the transformer voltage sequence, the affiliation between each user and each transformer substation can be determined based on the distance similarity, and the user clusters under each transformer substation can be obtained, thereby forming the topological relationship of the transformer substation.

[0121] Specifically, when co≥ε, it indicates that the user corresponding to the user voltage sequence belongs to the transformer substation, where ε represents the membership threshold.

[0122] Step 204: performing phase clustering on the user voltage sequences of all users in the user clustering to obtain phase clusters;

[0123] After obtaining the user clusters under each transformer substation, phase clustering can be performed on the user voltage sequences of all users in the user cluster under each transformer substation to obtain multiple phase clusters.

[0124] In one example, the phases of the user voltage may include phase A voltage, phase B voltage, and phase C voltage; therefore, in the embodiment of the present invention, the phase cluster may include phase A phase cluster, phase B phase cluster, and phase C phase cluster.

[0125] In a specific implementation, the K-means algorithm may be used for clustering, or other clustering algorithms may be used for clustering, and the embodiment of the present invention does not impose any specific limitation on this.

[0126] Step 205 , calculating the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs;

[0127] After determining the phase cluster of each user's user voltage sequence, the mathematical confidence between each user's user voltage sequence and the corresponding phase cluster can be calculated to determine whether the phase division of the user voltage sequence for that user is correct based on the corresponding mathematical confidence.

[0128] In one example, step 205 may include the following sub-steps:

[0129] S51, calculating the Spearman correlation coefficient matrix between the user voltage sequences of every two users under user clustering;

[0130] S52, perform Fisher transformation on the Spearman correlation coefficient matrix to obtain the standard correlation coefficient matrix;

[0131] S53: Calculate the mathematical confidence between each user voltage sequence and the phase cluster to which it belongs using a standard correlation coefficient matrix.

[0132] The Spearman correlation coefficient is a nonparametric measure of the dependence between two variables. It uses a monotonic equation to evaluate the correlation between two statistical variables. If there are no duplicate values ​​in the data and the two variables are completely monotonically correlated, the Spearman correlation coefficient is +1 or -1.

[0133] Fisher transformation is a statistical method used to test correlation coefficient hypotheses. After the sample correlation coefficient is transformed by Fisher transformation, it can be used to test the hypothesis about the population correlation coefficient.

[0134] In the specific implementation, the Spearman correlation coefficient s between the user voltage sequences of every two users under user clustering can be calculated first. i,j , forming the Spearman correlation coefficient matrix S = {s i,j}; where s i,j =s j,i , s i,i =1.

[0135] Then perform Fisher transformation on each Spearman coefficient in the Spearman coefficient matrix to obtain the standardized coefficient c i,j , forming the standard correlation coefficient matrix C={c i,j},in:

[0136]

[0137] Then calculate the average correlation coefficient u and the lower bound r of the correlation coefficient between each user's voltage sequence and the voltages of users in the other two phase clusters. The specific calculation formula is as follows:

[0138]

[0139] r=max(c i,j )-min(c i,j )

[0140] Where G represents the voltage set in the other two phase clusters, and g represents the number of user voltage data in G.

[0141] Next, the mathematical confidence level ce of the pairing of the user voltage sequence and its phase cluster can be calculated based on the following formula:

[0142]

[0143] Where M represents the number of user voltage data in the phase cluster to which the user voltage sequence belongs, and τ is the integral variable of u.

[0144] Step 206, determining whether the mathematical confidence level is greater than or equal to a preset confidence threshold;

[0145] Step 207: If yes, determine the phase corresponding to the phase cluster to which the user voltage sequence belongs as the phase of the user voltage sequence.

[0146] After calculating the mathematical confidence level ce of the user's voltage sequence, we can determine whether ce ≥ q holds. If so, the phase division is correct. Otherwise, the user is assigned to a different phase cluster, and the mathematical confidence level of the user's voltage sequence and the phase cluster to which it belongs is recalculated. q is the confidence threshold.

[0147] It should be noted that if there are users whose phases cannot be aggregated, it indicates that there is a topology identification error. For the users whose phases cannot be determined, steps 201-202 are re-executed to determine the correct substation affiliation.

[0148] The present invention identifies the topological relationships of end-users in the power grid by collecting the user voltage sequences of each user and the transformer voltage sequences of each transformer substation; calculating the distance similarity between the user voltage sequences and the transformer voltage sequences; determining the affiliation between the users and the transformer substations based on the distance similarity to obtain user clusters under each transformer substation; and finally, by performing phase clustering on the user voltage sequences of each user within the user clusters to obtain phase clusters; calculating the mathematical confidence level between each user voltage sequence and the phase cluster to which it belongs; and determining the phase of the user voltage sequence based on the mathematical confidence level to obtain the phase information of the end-users in the power grid. This reduces the difficulty of identifying the topology and phase information of end-users in the power grid.

[0149] See also Figure 3 , Figure 3 This is a structural block diagram of a phase division device for a distribution station area provided by an embodiment of the present invention.

[0150] An embodiment of the present invention provides a phase division device for a power distribution area, comprising:

[0151] The acquisition module 301 is used to acquire the user voltage sequence of each user in the power grid and the transformer voltage sequence of each transformer substation;

[0152] A distance similarity calculation module 302 is used to calculate the distance similarity between the user voltage sequence and the transformer voltage sequence;

[0153] The user clustering module 303 is used to determine the affiliation between users and transformer substations based on distance similarity, and obtain user clusters under each transformer substation;

[0154] The phase clustering module 304 is configured to perform phase clustering on the user voltage sequences of all users in the user cluster to obtain phase clusters;

[0155] The mathematical confidence calculation module 305 is used to calculate the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs;

[0156] The phase division module 306 is configured to determine the phase of the user voltage sequence according to the mathematical confidence level.

[0157] In this embodiment of the present invention, the distance similarity calculation module 302 includes:

[0158] An average character sequence Euclidean distance calculation submodule is used to calculate the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence;

[0159] A variance character sequence cosine distance calculation submodule is used to calculate the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence;

[0160] The difference sequence dynamic bending distance calculation submodule is used to calculate the difference sequence dynamic bending distance between the user voltage sequence and the transformer voltage sequence;

[0161] The distance similarity calculation submodule is used to calculate the distance similarity between the user voltage sequence and the transformer voltage sequence by using the average character sequence Euclidean distance, the variance character sequence and cosine distance, and the difference sequence dynamic bending distance.

[0162] In an embodiment of the present invention, the user voltage sequence includes a plurality of user voltage data; the transformer voltage sequence includes a plurality of transformer voltage data; and the average character sequence Euclidean distance calculation submodule includes:

[0163] A user voltage mean value sequence acquisition unit is used to average and segment the user voltage sequence to obtain a user voltage mean value sequence;

[0164] A transformer voltage mean value sequence acquisition unit is used to averagely segment the transformer voltage sequence to obtain a transformer voltage mean value sequence;

[0165] A user voltage average character sequence acquisition unit, configured to convert the user voltage average value sequence into characters to obtain a user voltage average character sequence;

[0166] The transformer voltage average character sequence acquisition unit is used to convert the transformer voltage mean value sequence into characters to obtain the transformer voltage average character sequence;

[0167] The average character sequence Euclidean distance calculation unit is used to calculate the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence using the user voltage average character sequence and the transformer voltage average character sequence.

[0168] In an embodiment of the present invention, the variance character sequence cosine distance calculation submodule includes:

[0169] A user voltage variance sequence acquisition unit is used to calculate the variance of user voltage data in each segment of the user voltage sequence to obtain a user voltage variance sequence;

[0170] A transformer voltage variance sequence acquisition unit is used to calculate the variance of transformer voltage data in each segment of the transformer voltage sequence to obtain the transformer voltage variance sequence;

[0171] A user voltage variance character sequence acquisition unit, configured to convert the user voltage variance sequence into characters to obtain a user voltage variance character sequence;

[0172] A transformer voltage variance character sequence acquisition unit is used to convert the transformer voltage variance sequence into characters to obtain a transformer voltage variance character sequence;

[0173] The variance character sequence cosine distance calculation unit is used to calculate the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence using the user voltage variance character sequence and the transformer voltage variance character sequence.

[0174] In an embodiment of the present invention, the difference sequence dynamic bending distance calculation submodule includes:

[0175] A user voltage difference sequence acquisition unit is used to calculate the difference between adjacent user voltage data in each segment of the user voltage sequence to obtain a user voltage difference sequence;

[0176] A transformer voltage difference sequence acquisition unit is used to calculate the difference between adjacent transformer voltage data in each segment of the transformer voltage sequence to obtain a transformer voltage difference sequence;

[0177] The difference sequence dynamic bending distance calculation unit is used to calculate the difference sequence dynamic bending distance between the user voltage sequence and the transformer voltage sequence using the user voltage difference sequence and the transformer voltage difference sequence.

[0178] In this embodiment of the present invention, the mathematical confidence calculation module 305 includes:

[0179] A Spearman correlation coefficient matrix calculation submodule is used to calculate the Spearman correlation coefficient matrix between the user voltage sequences of every two users under user clustering;

[0180] The standard correlation coefficient matrix generation submodule is used to perform Fisher transformation on the Spearman correlation coefficient matrix to obtain the standard correlation coefficient matrix;

[0181] The mathematical confidence calculation submodule is used to calculate the mathematical confidence between each user voltage sequence and the phase cluster to which it belongs using a standard correlation coefficient matrix.

[0182] In this embodiment of the present invention, the phase division module 306 includes:

[0183] A judgment submodule is used to judge whether the mathematical confidence level is greater than or equal to a preset confidence threshold;

[0184] The phase division submodule is configured to determine, if yes, the phase corresponding to the phase cluster to which the user voltage sequence belongs as the phase of the user voltage sequence.

[0185] An embodiment of the present invention further provides an electronic device, the device including a processor and a memory:

[0186] The memory is used to store program codes and transmit the program codes to the processor;

[0187] The processor is configured to execute the phase division method for a power distribution station area according to the instructions in the program code.

[0188] An embodiment of the present invention further provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the phase division method for power distribution station area according to the embodiment of the present invention.

[0189] Those skilled in the art will 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 aforementioned method embodiments and will not be repeated here.

[0190] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0191] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0192] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0193] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0194] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0195] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0196] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0197] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A phase division method for a distribution station area, characterized in that: include: Collect the user voltage sequence of each user in the power grid and the transformer voltage sequence of each transformer substation; Calculating the distance similarity between the user voltage sequence and the transformer voltage sequence; Determine the affiliation between the user and the transformer substation according to the distance similarity, and obtain user clusters under each transformer substation; performing phase clustering on user voltage sequences of all users under the user clustering to obtain phase clusters; Calculate the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs; determining a phase of the user voltage sequence according to the mathematical confidence level; The step of calculating the distance similarity between the user voltage sequence and the transformer voltage sequence includes: Calculating an average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence; Calculating the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence; Calculating a dynamic bending distance of a difference sequence between the user voltage sequence and the transformer voltage sequence; The distance similarity between the user voltage sequence and the transformer voltage sequence is calculated using the average character sequence Euclidean distance, the variance character sequence and cosine distance, and the difference sequence dynamic bending distance; the calculation formula of the distance similarity is: Where co is the distance similarity between the user voltage sequence and the transformer voltage sequence, n is the number of voltage data points, p is the number of segments of the user voltage sequence and the transformer voltage sequence, DTW(Δu i , Δt i ) is the dynamic bending distance of the difference sequence between the user voltage sequence and the transformer voltage sequence, is the cosine distance of the variance character sequence between the user voltage sequence and the transformer voltage sequence, is the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence, Δu i is the user voltage difference of the i-th user, Δt i is the transformer voltage difference of the i-th transformer, is the user voltage variance character of the i-th user, is the transformer voltage variance character of the i-th transformer, is the average voltage character of the i-th user, is the average transformer voltage of the i-th transformer; The step of calculating the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs includes: Calculating the Spearman correlation coefficient matrix between the user voltage sequences of every two users under the user clustering; Performing Fisher transformation on the Spearman correlation coefficient matrix to obtain a standard correlation coefficient matrix; The standard correlation coefficient matrix is ​​used to calculate the mathematical confidence between each user voltage sequence and the corresponding phase cluster.

2. The method according to claim 1, characterized in that The user voltage sequence includes a plurality of user voltage data; the transformer voltage sequence includes a plurality of transformer voltage data; and the step of calculating the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence includes: Performing average segmentation on the user voltage sequence to obtain a user voltage mean value sequence; Performing average segmentation on the transformer voltage sequence to obtain a transformer voltage mean value sequence; Performing character conversion on the user voltage mean value sequence to obtain a user voltage average character sequence; Performing character conversion on the transformer voltage mean value sequence to obtain a transformer voltage average character sequence; The average character sequence of the user voltage and the average character sequence of the transformer voltage are used to calculate the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence.

3. The method according to claim 2, characterized in that The step of calculating the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence comprises: Calculating the variance of user voltage data in each segment of the user voltage sequence to obtain a user voltage variance sequence; Calculating the variance of transformer voltage data in each segment of the transformer voltage sequence to obtain a transformer voltage variance sequence; Performing character conversion on the user voltage variance sequence to obtain a user voltage variance character sequence; Performing character conversion on the transformer voltage variance sequence to obtain a transformer voltage variance character sequence; The user voltage variance character sequence and the transformer voltage variance character sequence are used to calculate a variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence.

4. The method according to claim 3, characterized in that The step of calculating the dynamic bending distance of the difference sequence between the user voltage sequence and the transformer voltage sequence includes: Calculating the difference between adjacent user voltage data in each segment of the user voltage sequence to obtain a user voltage difference sequence; Calculating the difference between adjacent transformer voltage data in each segment of the transformer voltage sequence to obtain a transformer voltage difference sequence; The user voltage difference sequence and the transformer voltage difference sequence are used to calculate a difference sequence dynamic bending distance between the user voltage sequence and the transformer voltage sequence.

5. The method according to claim 1, wherein The step of determining the phase of the user voltage sequence according to the mathematical confidence level comprises: Determining whether the mathematical confidence level is greater than or equal to a preset confidence threshold; If so, the phase corresponding to the phase cluster to which the user voltage sequence belongs is determined as the phase of the user voltage sequence.

6. A phase division device for a distribution station area, characterized in that: include: The acquisition module is used to collect the user voltage sequence of each user in the power grid and the transformer voltage sequence of each transformer station; A distance similarity calculation module, configured to calculate the distance similarity between the user voltage sequence and the transformer voltage sequence; A user clustering module is used to determine the affiliation between the user and the transformer substation according to the distance similarity, and obtain user clusters under each transformer substation; A phase clustering module, configured to perform phase clustering on user voltage sequences of all users in the user cluster to obtain phase clusters; A mathematical confidence calculation module is used to calculate the mathematical confidence between the user voltage sequence of each user and the phase cluster to which it belongs; a phase division module, configured to determine the phase of the user voltage sequence according to the mathematical confidence level; Among them, the distance similarity calculation module includes: An average character sequence Euclidean distance calculation submodule is used to calculate the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence; A variance character sequence cosine distance calculation submodule is used to calculate the variance character sequence cosine distance between the user voltage sequence and the transformer voltage sequence; The difference sequence dynamic bending distance calculation submodule is used to calculate the difference sequence dynamic bending distance between the user voltage sequence and the transformer voltage sequence; A distance similarity calculation submodule is used to calculate the distance similarity between the user voltage sequence and the transformer voltage sequence using the average character sequence Euclidean distance, the variance character sequence and cosine distance, and the difference sequence dynamic bending distance; The calculation formula of the distance similarity is: Where co is the distance similarity between the user voltage sequence and the transformer voltage sequence, n is the number of voltage data points, p is the number of segments of the user voltage sequence and the transformer voltage sequence, DTW(Δu i , Δt i ) is the dynamic bending distance of the difference sequence between the user voltage sequence and the transformer voltage sequence, is the cosine distance of the variance character sequence between the user voltage sequence and the transformer voltage sequence, is the average character sequence Euclidean distance between the user voltage sequence and the transformer voltage sequence, Δu i is the user voltage difference of the i-th user, Δt i is the transformer voltage difference of the i-th transformer, is the user voltage variance character of the i-th user, is the transformer voltage variance character of the i-th transformer, is the average voltage character of the i-th user, is the average transformer voltage of the i-th transformer; Among them, the mathematical confidence calculation module includes: A Spearman correlation coefficient matrix calculation submodule is used to calculate the Spearman correlation coefficient matrix between the user voltage sequences of every two users under user clustering; The standard correlation coefficient matrix generation submodule is used to perform Fisher transformation on the Spearman correlation coefficient matrix to obtain the standard correlation coefficient matrix; The mathematical confidence calculation submodule is used to calculate the mathematical confidence between each user voltage sequence and the phase cluster to which it belongs using a standard correlation coefficient matrix.

7. An electronic device, characterized in that: The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the distribution station area phase division method according to any one of claims 1 to 5 according to the instructions in the program code.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store program codes, and the program codes are used to execute the phase division method for power distribution area according to any one of claims 1 to 5.

Images