Multi-level low-voltage transformer area topology identification method based on linear regression and related system

Abstract

The invention belongs to the field of low-voltage power distribution of an electric power system, and discloses a multi-level low-voltage transformer area topology identification method based on linear regression and a related system. The connection relation between each meter box and a branch node, a main line and a transformer in a low-voltage transformer area can be identified more accurately, and identification errors are reduced. According to the method, the complex connection relation between the meter box and the branch nodes can be effectively processed and analyzed by using the multi-scale similarity measurement and hierarchical clustering method, and the problem that the traditional method is difficult to identify when facing a complex topological structure is solved. According to the invention, by automatically acquiring and processing the voltage load data, the current data and the correlation information thereof, manual intervention can be greatly reduced, and the efficiency of topology identification is improved.

Description

Technical Field

[0001] The present invention belongs to the field of low-voltage power distribution in electric power systems, and in particular relates to a multi-level low-voltage substation topology identification method based on linear regression and a related system. Background Art

[0002] In the power system, the low-voltage area refers to the power supply area of ​​the low-voltage distribution transformer of the power line, which usually includes multiple users and multiple power-consuming equipment. The topological structure of the low-voltage area refers to the connection relationship and organizational structure between various power equipment in the area. The accuracy of the area topological structure information is of great significance for improving the line loss management efficiency of the low-voltage distribution network, optimizing the operation mode of the distribution network, improving the power service level, and promoting the digital transformation of power companies.

[0003] Among the existing technologies, the common substation topology identification technologies are: (1) manual inspection and manual drawing. This method is not only inefficient but also prone to errors. Moreover, due to the dynamic changes in the substation, the effectiveness of this method cannot be guaranteed. (2) Installing pulse current sensors at each branch node in the substation. Although this method has a high recognition accuracy, it is limited by the power and cost of the equipment and cannot be widely promoted. (3) With the rise and development of big data and artificial intelligence in recent years, big data analysis methods based on power data have been increasingly used for topology identification. Compared with the previous two methods, this method saves manpower and equipment costs, but it requires higher data integrity and can only generate simple meter box groupings. It cannot identify and divide the more complex branches and trunk layers above the meter box, and cannot complete the identification of more detailed substation topology connection methods. Summary of the invention

[0004] The purpose of the present invention is to overcome the problem in the prior art that the complex branches and trunk levels of the meter box cannot be identified and divided, and to provide a multi-level low-voltage area topology identification method and related system based on linear regression.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a multi-level low-voltage area topology identification method based on linear regression, comprising the following steps:

[0007] Obtain the voltage load data of the low-voltage user within a preset time, generate a voltage load curve based on the obtained voltage load data, and obtain the access phase of the low-voltage user based on the voltage correlation of the low-voltage user;

[0008] Obtain the relationship data between the meter box and the electric energy meter, determine the ownership of each electric energy meter, and select the low-voltage user with the highest voltage at the same time in different meter boxes as the voltage value of the current meter box at the current moment in combination with the voltage load curve, and calculate the current value of the corresponding meter box;

[0009] According to the voltage and current values ​​of all meter boxes, a hierarchical clustering method is used to perform cluster analysis on each meter box based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes;

[0010] According to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage data and line impedance data of different branch nodes are obtained, and the current data of different branch nodes are obtained in combination with the current value of the meter box;

[0011] According to the voltage data, line impedance data and current data of different branch nodes, the correlation analysis is carried out on all branch nodes to obtain the branch-trunk-transformer connection relationship;

[0012] Based on the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user, a complete topology connection relationship is generated.

[0013] A further improvement of the present invention is that the step of obtaining the access phase of the low-voltage user according to the voltage correlation of the low-voltage user is as follows:

[0014]

[0015] Among them, Cosine is the access phase of the low-voltage user, X is the electric energy meter data of the low-voltage user, and Y is the three-phase data of the total meter.

[0016] A further improvement of the present invention is that in the step of calculating the current value of the corresponding meter box, the specific method is as follows:

[0017]

[0018]

[0019] Among them, U bt is the voltage data of the meter box at time t, n is the number of low-voltage users in a meter box, U nt is the voltage data of the nth meter box at time t, l bt is the current data of the meter box at time t, I nt is the current data of the nth meter box at time t.

[0020] A further improvement of the present invention is that, according to the voltage and current values ​​of all meter boxes, a hierarchical clustering method is used to perform cluster analysis on each meter box based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes. The specific method is as follows:

[0021] According to the voltage and current values ​​of all meter boxes, the Euclidean distance of load data between different meter boxes, the Euclidean distance of load difference vectors and the DTW distance are calculated;

[0022] According to the Euclidean distance of load data between different meter boxes, the Euclidean distance of load difference vector and DTW distance, the distance characteristics, trend characteristics and time characteristics between different meter boxes are obtained, and the connection relationship between the meter box and different branch nodes is obtained.

[0023] A further improvement of the present invention is that the steps are to obtain voltage data and line impedance data of different branch nodes according to the voltage load curve and the connection relationship between the meter box and different branch nodes, and to obtain current data of different branch nodes in combination with the current value of the meter box. The specific method is as follows:

[0024] According to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage and current of each branch node at each moment, as well as the impedance value from each branch node to the corresponding meter box are calculated;

[0025] According to the voltage and current of each branch node at each moment, and the impedance value from each branch node to the corresponding meter box, the voltage data of different branch nodes and the impedance data of the line are coupled to obtain;

[0026] The current data of all meter boxes under the branch node are summed separately to obtain the current data of different branch nodes.

[0027] A further improvement of the present invention is that, according to the voltage data, line impedance data and current data of different branch nodes, the correlation analysis is performed on all branch nodes to obtain the branch-trunk-transformer connection relationship. The specific method is as follows:

[0028] According to the voltage data, line impedance data and current data of different branch nodes, the voltage and current upstream of each branch node are obtained and compared with the voltage and current of the head-end transformer master meter. If the difference meets the conditions, the upstream branch node is determined to be the head-end transformer master meter; if the difference does not meet the conditions, the upstream branch node is determined to be an adjacent branch node. After all branch nodes are determined, the branch-trunk-transformer connection relationship is obtained.

[0029] A further improvement of the present invention is that, according to the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user, a specific method for generating a complete topology connection relationship is as follows:

[0030] According to the branch-trunk-transformer connection relationship, identify the connection relationship between branch-meter box, trunk-branch, trunk-head end and the voltage drop trend analysis results, as well as the voltage data, current data and resistance data of each branch node;

[0031] Based on the connection relationship and voltage drop trend analysis results of branch-meter box, trunk-branch, and trunk-headend, as well as the voltage data, current data, and resistance data of each branch node, combined with the access phase of the low-voltage user, a complete topological connection relationship including transformer, trunk, branch, meter box, user, phase, and impedance is generated.

[0032] In a second aspect, the present invention provides a multi-level low-voltage area topology identification system based on linear regression, comprising:

[0033] The low-voltage user data acquisition module is used to acquire the voltage load data of the low-voltage user within a preset time, generate a voltage load curve based on the acquired voltage load data, and acquire the access phase of the low-voltage user based on the voltage correlation of the low-voltage user;

[0034] The meter box data acquisition module is used to obtain the relationship data between the meter box and the electric energy meter, determine the ownership of each electric energy meter, and select the low-voltage user with the largest voltage at the same time in different meter boxes as the voltage value of the current meter box at the current moment in combination with the voltage load curve, and calculate the current value of the corresponding meter box;

[0035] A connection relationship acquisition module is used to perform cluster analysis on each meter box based on the voltage and current values ​​of all meter boxes and the hierarchical clustering method based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes;

[0036] The branch node data acquisition module is used to obtain the voltage data and line impedance data of different branch nodes according to the voltage load curve and the connection relationship between the meter box and different branch nodes, and obtain the current data of different branch nodes in combination with the current value of the meter box;

[0037] The data association module is used to perform correlation analysis on all branch nodes according to the voltage data, line impedance data and current data of different branch nodes to obtain the branch-trunk-transformer connection relationship;

[0038] The topology relationship generation module is used to generate a complete topology connection relationship based on the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user.

[0039] A further improvement of the present invention is that the function of the connection relationship acquisition module is implemented by the following method:

[0040] Steps: According to the voltage and current values ​​of all meter boxes, a hierarchical clustering method is used to perform cluster analysis on each meter box based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes. The specific method is as follows:

[0041] According to the voltage and current values ​​of all meter boxes, the Euclidean distance of load data between different meter boxes, the Euclidean distance of load difference vectors and the DTW distance are calculated;

[0042] According to the Euclidean distance of load data between different meter boxes, the Euclidean distance of load difference vector and DTW distance, the distance characteristics, trend characteristics and time characteristics between different meter boxes are obtained, and the connection relationship between the meter box and different branch nodes is obtained.

[0043] A further improvement of the present invention is that the function of the branch node data acquisition module is implemented by the following method:

[0044] According to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage and current of each branch node at each moment, as well as the impedance value from each branch node to the corresponding meter box are calculated;

[0045] According to the voltage and current of each branch node at each moment, and the impedance value from each branch node to the corresponding meter box, the voltage data of different branch nodes and the impedance data of the line are coupled to obtain;

[0046] The current data of all meter boxes under the branch node are summed separately to obtain the current data of different branch nodes.

[0047] A further improvement of the present invention is that the function of the data association module is implemented by the following method:

[0048] According to the voltage data, line impedance data and current data of different branch nodes, the voltage and current upstream of each branch node are obtained and compared with the voltage and current of the head-end transformer master meter. If the difference meets the conditions, the upstream branch node is determined to be the head-end transformer master meter; if the difference does not meet the conditions, the upstream branch node is determined to be an adjacent branch node. After all branch nodes are determined, the branch-trunk-transformer connection relationship is obtained.

[0049] A further improvement of the present invention is that the function of the topology relationship generation module is realized by the following method:

[0050] According to the branch-trunk-transformer connection relationship, identify the connection relationship between branch-meter box, trunk-branch, trunk-head end and the voltage drop trend analysis results, as well as the voltage data, current data and resistance data of each branch node;

[0051] Based on the connection relationship and voltage drop trend analysis results of branch-meter box, trunk-branch, and trunk-headend, as well as the voltage data, current data, and resistance data of each branch node, combined with the access phase of the low-voltage user, a complete topological connection relationship including transformer, trunk, branch, meter box, user, phase, and impedance is generated.

[0052] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of a multi-level low-voltage substation topology identification method based on linear regression when executing the computer program.

[0053] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a multi-level low-voltage substation topology identification method based on linear regression are implemented.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The present invention can more accurately identify the connection relationship between each meter box and branch node, trunk line and transformer in the low-voltage area by acquiring the voltage load data of low-voltage users and combining the voltage load curve and current data, thereby reducing the recognition error. The present invention uses multi-scale similarity measurement and hierarchical clustering method to effectively process and analyze the complex connection relationship between the meter box and the branch node, and solves the recognition difficulty of the traditional method when facing a complex topological structure. The present invention can greatly reduce manual intervention and improve the efficiency of topological identification by automatically acquiring and processing voltage load data, current data and their correlation information. At the same time, the linear regression model and hierarchical clustering algorithm are used to make the topological identification process more systematic and efficient. The present invention can not only identify the connection relationship between the meter box and the branch node, but also further identify the multi-level topological relationship between the branch and the trunk, the trunk and the transformer, and form a complete power system topological structure diagram, providing basic data support for subsequent power grid management and optimization. By considering the voltage and current characteristics of different meter boxes and branch nodes at different time points, the present invention can effectively cope with the topological identification challenges caused by uneven load and different user access phases, and ensure the accuracy and integrity of the topological structure. In summary, the present invention uses big data analysis methods to realize automatic identification of substation topology, without the need for manual on-site drawing, thus reducing labor costs; at the same time, the load data is natively collected data of the power grid, thus avoiding the impact of external devices on the power grid and reducing equipment cost expenditure; based on multi-scale similarity metric analysis and voltage-constrained linear regression analysis methods, a method combining big data analysis with power characteristic constraints is applied to improve the accuracy and depth of substation topology identification, which is suitable for widespread promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a flow chart of Example 1;

[0057] Figure 2 is a system diagram of Example 2;

[0058] Figure 3 This is the topological diagram of Example 3;

[0059] Figure 4 is a flow chart of Example 3;

[0060] Figure 5 It is the equivalent diagram of the multi-level area in Example 3;

[0061] Figure 6 This is a system diagram of Example 4. DETAILED DESCRIPTION

[0062] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0063] Embodiment 1:

[0064] See also Figure 1 , a multi-level low-voltage area topology identification method based on linear regression includes the following steps:

[0065] S1, obtaining voltage load data of a low-voltage user within a preset time, generating a voltage load curve according to the obtained voltage load data, and obtaining an access phase of the low-voltage user according to the voltage correlation of the low-voltage user.

[0066] S2, obtain the relationship data between the meter box and the electric energy meter, determine the ownership of each electric energy meter, combine the voltage load curve, select the low-voltage user with the largest voltage at the same time in different meter boxes as the voltage value of the current meter box at the current moment, and calculate the current value of the corresponding meter box.

[0067] S3, according to the voltage and current values ​​of all meter boxes, a hierarchical clustering method is used based on multi-scale similarity measurement information to perform cluster analysis on each meter box, and the connection relationship between the meter box and different branch nodes is obtained.

[0068] S4, according to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage data and line impedance data of different branch nodes are obtained, and the current data of different branch nodes are obtained in combination with the current value of the meter box.

[0069] S5, performing correlation analysis on all branch nodes according to the voltage data, line impedance data and current data of different branch nodes, and obtaining the branch-trunk-transformer connection relationship.

[0070] S6, generating a complete topology connection relationship according to the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user.

[0071] Embodiment 2:

[0072] See also Figure 2, a multi-level low-voltage area topology identification system based on linear regression, including:

[0073] The low-voltage user data acquisition module is used to acquire the voltage load data of the low-voltage user within a preset time, generate a voltage load curve based on the acquired voltage load data, and acquire the access phase of the low-voltage user based on the voltage correlation of the low-voltage user;

[0074] The meter box data acquisition module is used to obtain the relationship data between the meter box and the electric energy meter, determine the ownership of each electric energy meter, and select the low-voltage user with the largest voltage at the same time in different meter boxes as the voltage value of the current meter box at the current moment in combination with the voltage load curve, and calculate the current value of the corresponding meter box;

[0075] A connection relationship acquisition module is used to perform cluster analysis on each meter box based on the voltage and current values ​​of all meter boxes and the hierarchical clustering method based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes;

[0076] The branch node data acquisition module is used to obtain the voltage data and line impedance data of different branch nodes according to the voltage load curve and the connection relationship between the meter box and different branch nodes, and obtain the current data of different branch nodes in combination with the current value of the meter box;

[0077] The data association module is used to perform correlation analysis on all branch nodes according to the voltage data, line impedance data and current data of different branch nodes to obtain the branch-trunk-transformer connection relationship;

[0078] The topology relationship generation module is used to generate a complete topology connection relationship based on the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user.

[0079] Embodiment 3:

[0080] See also Figure 4 , a multi-level low-voltage area topology identification method based on linear regression includes the following steps:

[0081] Step 1: Based on the high coverage of HPLC electric energy meters for low-voltage users, obtain high-frequency data such as voltage and current on the secondary side of the transformer and low-voltage users. Since the branch voltage of each phase will fluctuate with the fluctuation of the total meter voltage, the branch voltage has a strong correlation with the total meter voltage. Therefore, the distance between the user voltage curve and the total meter voltage curve is used to judge the similarity between the two. The closer the distance, the higher the similarity, and the user phase can be identified. The specific implementation method is as follows:

[0082] Cosine distance:

[0083]

[0084] Among them, X is the household meter data, size is m×n, Y is the total meter three-phase data, size is n×3, n is the number of voltage records, and m is the number of users. The resulting matrix size is m×3, representing the cosine distance between m users and each phase.

[0085] The user's access phase is analyzed based on the calculation result of the cosine distance, so as to realize the intelligent identification of the low-voltage user's access phase.

[0086] Step 2: In the low-voltage area, the same-phase load nodes coupled at the same point can be regarded as connected in parallel. Since the electrical distance between them and the transformer outlet is close, the voltage values ​​between these meters are very small, and the line length in the meter box is short. The voltage drop from the meter box inlet to the user's electric energy meter is extremely small. Therefore, for the same meter box, the user with the largest voltage at the same moment in the meter box is selected as the voltage value of the meter box at this moment, and the sum of the user currents in the meter box is used as the meter box current based on the KCL equation.

[0087]

[0088]

[0089] U bt is the voltage data of a meter box at time t, I bt Here, t is the current data of a meter box at time t, and n is the number of users in a meter box.

[0090] Step 3: Based on the voltage load data of the meter boxes, the comprehensive correlation between the meter boxes is calculated based on the improved correlation calculation method. The specific method is as follows:

[0091] (1) Calculate the Euclidean distance. For two load sequence curves X and Y, we have:

[0092]

[0093] Where: n is the dimension of the load curve;

[0094] (2) Calculate the difference vector. For the n-dimensional load curve X = (x1, x2, ..., x n )Use the first-order difference vector to convert it into an n-1-dimensional load trend sequence X′=(x1, x2, …, x n-1 ) is used to describe the local dynamic characteristics of the curve.

[0095] The first-order difference operation is defined as

[0096] x′ t =x t+1 -x t

[0097] Where: x′ tis the value of the tth dimension of the difference sequence; x t is the value of the tth dimension of the load curve. t=1,2,…,n-1.

[0098] (3) Calculate the DTW distance. Assume that there are time series C and time series Q with lengths of m and n respectively.

[0099] C=c1,c2,…,c m

[0100] Q=q1,q2,…,q n

[0101] In order to align time series C and time series Q, an m×n matrix is ​​constructed, and the position (i, j) of the matrix is ​​used to store point c i With dot q j The distance (usually the distance is the Euclidean distance, i.e. The purpose of the DTW algorithm is to find a path (warping path) from (1,1) to (m,n) with the lowest cost in the matrix.

[0102] The path W is a continuous element in the matrix that gives the correspondence between the time series C and the time series Q. The kth element of W is defined as w k =(i,j)k, then: W = w1,w2,…,w k ,…,w K , where max(m,n)≤K≤m+n-1;

[0103] According to the characteristics of time series data, the path should meet the following conditions:

[0104] 1. Boundary conditions:

[0105] w1=(1,1) and w k =(m,n). That is, the alignment at the beginning and the end is certain, and the path must start from the lower left corner and end at the upper right corner.

[0106] 2. Continuity:

[0107] If w k-1 =(a′, b′), then for the next path point w k =(a,b) needs to satisfy:

[0108] aa′≤1

[0109] bb′≤1

[0110] That is, when two time series data are aligned, there will be no omissions and the alignment will be performed across a certain point.

[0111] 3. Monotonicity:

[0112] If w k-1 =(a',b'), then for the next point w on the path k =(a,b) needs to satisfy:

[0113] 0≤aa'

[0114] 0≤bb'

[0115] That is, the points on the path must be monotonically changed over time.

[0116] According to the above analysis, the DTW algorithm is to find a continuous path with the minimum cumulative distance from the upper left corner to the upper right corner. Define λ(i,j) to represent the minimum cumulative distance from point (1,1) to point (i,j), then:

[0117] λ(i,j)=d(c i ,c j )+min{λ(i-1,j),λ(i,j-1),λ(i-1,j-1)}

[0118] (4) The Euclidean distance of load data, load difference vector, and Euclidean distance of DTW time warping algorithm are used as comprehensive similarity criteria to replace the traditional correlation to measure the similarity between curves, taking into account the three characteristics of distance, trend, and time.

[0119] The measurement method of multi-scale similarity distance can be expressed as

[0120] D all (W,V)=αD eu (W,V)+βD eu (W',V')+χD eu (W”,V”)

[0121] Where: D eu (W,V) is the Euclidean distance between curves W and V; D eu (W', V') is the Euclidean distance between the curve difference sequences; D eu (W”, V”) is the DTW distance of the curve; D all (W,V) is the multi-scale similarity distance of curves U, W, and V, D all The smaller (W, V) is, the closer the distance between the two curves is and the higher the similarity is; α, β, and χ are the weights of Euclidean distance, differential Euclidean distance, and DTW distance, respectively.

[0122] Based on the comprehensive correlation distance calculated above, nodes with distance values ​​greater than a set threshold are determined to have the same parent node, thereby obtaining a table box-branch node connection relationship.

[0123] Step 4: According to the meter box-branch connection relationship, several branch nodes are obtained. Based on Ohm's law, the node voltage is equal to the voltage drop from the node to the corresponding meter box plus the meter box voltage. The meter boxes coupled to the same branch node all follow this principle, so the following formula is established:

[0124] U A i=U ai +I ai R a (1)

[0125] U Ai =U bi +I bi R b (2)

[0126] U Ai =U ci +I ci R c (3)

[0127] Among them, U Ai is the voltage of the branch node at time i, U ai is the voltage of the meter box at time i, I ai is the current of the meter box at time i, R a is the impedance value from the meter box to the branch node. According to the constraint that the voltage of the branch node is consistent, the user voltage and current in the three equations are known quantities, and R a , R b , R c , U Ai The quantity to be determined is the quantity. According to the curve data at multiple time points, a regression equation can be established. Under the constraint condition that the resistance R>0, the above equation is fitted to calculate the impedance of the line from the branch node to each meter box. At the same time, the voltage U of the branch node at each time point can be calculated. ai .

[0128] Assume that there are three meter boxes a, b, and c under the A branch node. Take the calculation of the A phase branch node as an example. Figure 5 , derive the calculation process:

[0129] First, the above three equations are satisfied at each time point. Since the three equations correspond to four unknowns, it is necessary to use data from multiple time points to solve them, so the above equations are transformed:

[0130] -I a1 R a +U A1 =U a1

[0131] -I b1 R b +U A1 =U b1

[0132] -I c1 R c +U A1 =U C1

[0133] -I α2 R a +U A2 =U a2

[0134] -I b2 R b +U A2 =U b2

[0135] -I c2 R c +U A2 =U c2 ...

[0137] -I an R a +U An =U an

[0138] -I bn R b +U An =U bn

[0139] -I Cn R c +U An =U cn

[0140] At this time, there are 3×n equations and 3+n unknowns.

[0141] Secondly, in order to solve, the above equation is converted into the matrix form of the general regression equation solution:

[0142]

[0143]

[0144]

[0145] Again, construct the regression equation, loss function and constraints.

[0146] XA=y

[0147] Using matrix multiplication, we can get:

[0148] (X T X) A = X T y

[0149] A=(X T X) -1 X T y

[0150] The loss function is:

[0151] S=||XA-y|| 2

[0152] The constraints are:

[0153] R a , R b , R c Both greater than 0

[0154] Finally, the regression coefficient A is solved by constrained least squares, that is, under the constraint conditions, the optimal unknown parameter A that minimizes the loss function is obtained, so as to obtain the voltage U of the coupling node. Ai And the resistance value R of each connection under the node a , R b , R c .

[0155] Step 5: According to the Kirchhoff current characteristic, sum the momentary currents of all meter boxes under the branch node to obtain the momentary current of the coupling node.

[0156]

[0157] I At is the current data of the branch node at time t, I bt is the current data of the meter box at time t, and n is the number of meter boxes under the branch node.

[0158] Step 6: Based on the voltage data of each branch node, the correlation analysis method in step 3 is used to calculate the correlation of each branch node. The branch nodes that meet the correlation threshold requirements have the same parent node, thereby obtaining the connection relationship between the branch node and the parent node (trunk node). At the same time, according to the methods of steps 4 and 5, the voltage and current data of the branch node are used to solve the voltage, resistance, and current data of the trunk node.

[0159] Step seven, for several branches derived from the same trunk node, analyze the voltage drop trend of each branch node according to the voltage drop principle. The connection position of the node with relatively low voltage is further back, and the connection position of the branch with voltage closer to the trunk node voltage is closer to the trunk node. Based on this logic, the spatial position of the branch node under each trunk node can be further determined.

[0160] Step 8: Based on the voltage, current and resistance data of the main node, repeat steps 3, 4 and 5 until the voltage and current difference between the upstream node and the voltage and current of the transformer meter at the head end of the substation area meets the threshold ε u , ε i , the identified upstream node coincides with the transformer total table, and the topology identification is completed.

[0161] Step 9, see Figure 3 According to the connection relationship between branch-meter box, trunk-branch, trunk-head end, voltage drop trend analysis results and voltage, current and resistance data of each node identified in the above steps, a complete topological structure diagram including transformer-trunk-branch-meter box-user-phase-impedance is generated.

[0162] Embodiment 4:

[0163] See also Figure 6 As shown, the present invention also provides an electronic device 100 for a multi-level low-voltage substation topology identification method based on linear regression; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0164] The memory 101 can be used to store the computer program 103, and the processor 102 implements the steps of the multi-level low-voltage area topology identification method based on linear regression described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0165] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0166] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a multi-level low-voltage area topology identification method based on linear regression, and the processor 102 can execute the plurality of instructions to implement:

[0167] Obtain the voltage load data of the low-voltage user within a preset time, generate a voltage load curve based on the obtained voltage load data, and obtain the access phase of the low-voltage user based on the voltage correlation of the low-voltage user;

[0168] Obtain the relationship data between the meter box and the electric energy meter, determine the ownership of each electric energy meter, and select the low-voltage user with the highest voltage at the same time in different meter boxes as the voltage value of the current meter box at the current moment in combination with the voltage load curve, and calculate the current value of the corresponding meter box;

[0169] According to the voltage and current values ​​of all meter boxes, a hierarchical clustering method is used to perform cluster analysis on each meter box based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes;

[0170] According to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage data and line impedance data of different branch nodes are obtained, and the current data of different branch nodes are obtained in combination with the current value of the meter box;

[0171] According to the voltage data, line impedance data and current data of different branch nodes, the correlation analysis is carried out on all branch nodes to obtain the branch-trunk-transformer connection relationship;

[0172] Based on the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user, a complete topology connection relationship is generated.

[0173] Embodiment 5:

[0174] If the module / unit integrated in the electronic device 100 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 present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0175] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, 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 disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0176] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to 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 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 device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes 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.

[0177] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0178] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing 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.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A multi-level low-voltage area topology identification method based on linear regression, characterized in that: The following steps are involved: Obtain the voltage load data of the low-voltage user within a preset time, generate a voltage load curve based on the obtained voltage load data, and obtain the access phase of the low-voltage user based on the voltage correlation of the low-voltage user; Obtain the relationship data between the meter box and the electric energy meter, determine the ownership of each electric energy meter, and select the low-voltage user with the highest voltage at the same time in different meter boxes as the voltage value of the current meter box at the current moment in combination with the voltage load curve, and calculate the current value of the corresponding meter box; According to the voltage and current values ​​of all meter boxes, a hierarchical clustering method is used to perform cluster analysis on each meter box based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes; According to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage data and line impedance data of different branch nodes are obtained, and the current data of different branch nodes are obtained in combination with the current value of the meter box; According to the voltage data, line impedance data and current data of different branch nodes, the correlation analysis is carried out on all branch nodes to obtain the branch-trunk-transformer connection relationship; Based on the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user, a complete topology connection relationship is generated.

2. The multi-level low-voltage area topology identification method based on linear regression according to claim 1 is characterized in that: The steps are as follows: According to the voltage correlation of the low-voltage user, the access phase of the low-voltage user is obtained. The specific method is as follows: Among them, Cosine is the access phase of the low-voltage user, X is the electric energy meter data of the low-voltage user, and Y is the three-phase data of the total meter.

3. The multi-level low-voltage area topology identification method based on linear regression according to claim 1 is characterized in that: Step 1: Calculate the current value of the corresponding meter box. The specific method is as follows: Among them, U bt is the voltage data of the meter box at time t, n is the number of low-voltage users in a meter box, U nt is the voltage data of the nth meter box at time t, I bt is the current data of the meter box at time t, I nt is the current data of the nth meter box at time t.

4. The multi-level low-voltage area topology identification method based on linear regression according to claim 1 is characterized in that: Steps: According to the voltage and current values ​​of all meter boxes, a hierarchical clustering method is used to perform cluster analysis on each meter box based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes. The specific method is as follows: According to the voltage and current values ​​of all meter boxes, the Euclidean distance of load data between different meter boxes, the Euclidean distance of load difference vectors and the DTW distance are calculated; According to the Euclidean distance of load data between different meter boxes, the Euclidean distance of load difference vector and DTW distance, the distance characteristics, trend characteristics and time characteristics between different meter boxes are obtained, and the connection relationship between the meter box and different branch nodes is obtained.

5. The multi-level low-voltage area topology identification method based on linear regression according to claim 1 is characterized in that: Steps: According to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage data and line impedance data of different branch nodes are obtained, and the current data of different branch nodes are obtained by combining the current value of the meter box. The specific method is as follows: According to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage and current of each branch node at each moment, as well as the impedance value from each branch node to the corresponding meter box are calculated; According to the voltage and current of each branch node at each moment, and the impedance value from each branch node to the corresponding meter box, the voltage data of different branch nodes and the impedance data of the line are coupled to obtain; The current data of all meter boxes under the branch node are summed separately to obtain the current data of different branch nodes.

6. The multi-level low-voltage area topology identification method based on linear regression according to claim 1 is characterized in that: Steps: According to the voltage data, line impedance data and current data of different branch nodes, the correlation analysis is performed on all branch nodes to obtain the branch-trunk-transformer connection relationship. The specific method is as follows: According to the voltage data, line impedance data and current data of different branch nodes, the voltage and current upstream of each branch node are obtained, and compared with the voltage and current of the head-end transformer master meter. If the difference meets the conditions, the upstream branch node is determined to be the head-end transformer master meter; If the difference does not meet the condition, the upstream branch node is determined to be an adjacent branch node, and all branch nodes are determined to obtain the branch-trunk-transformer connection relationship.

7. The multi-level low-voltage area topology identification method based on linear regression according to claim 1 is characterized in that: According to the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user, the specific method of generating a complete topology connection relationship is as follows: According to the branch-trunk-transformer connection relationship, identify the connection relationship between branch-meter box, trunk-branch, trunk-head end and the voltage drop trend analysis results, as well as the voltage data, current data and resistance data of each branch node; Based on the connection relationship and voltage drop trend analysis results of branch-meter box, trunk-branch, and trunk-headend, as well as the voltage data, current data, and resistance data of each branch node, combined with the access phase of the low-voltage user, a complete topological connection relationship including transformer, trunk, branch, meter box, user, phase, and impedance is generated.

8. A multi-level low-voltage area topology identification system based on linear regression, characterized in that: include: The low-voltage user data acquisition module is used to acquire the voltage load data of the low-voltage user within a preset time, generate a voltage load curve based on the acquired voltage load data, and acquire the access phase of the low-voltage user based on the voltage correlation of the low-voltage user; The meter box data acquisition module is used to obtain the relationship data between the meter box and the electric energy meter, determine the ownership of each electric energy meter, and select the low-voltage user with the largest voltage at the same time in different meter boxes as the voltage value of the current meter box at the current moment in combination with the voltage load curve, and calculate the current value of the corresponding meter box; A connection relationship acquisition module is used to perform cluster analysis on each meter box based on the voltage and current values ​​of all meter boxes and the hierarchical clustering method based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes; The branch node data acquisition module is used to obtain the voltage data and line impedance data of different branch nodes according to the voltage load curve and the connection relationship between the meter box and different branch nodes, and obtain the current data of different branch nodes in combination with the current value of the meter box; The data association module is used to perform correlation analysis on all branch nodes according to the voltage data, line impedance data and current data of different branch nodes to obtain the branch-trunk-transformer connection relationship; The topology relationship generation module is used to generate a complete topology connection relationship based on the obtained branch-trunk-transformer connection relationship and the access phase of the low-voltage user.

9. The multi-level low-voltage area topology identification system based on linear regression according to claim 8 is characterized in that: The functions of the connection relationship acquisition module are implemented through the following methods: Steps: According to the voltage and current values ​​of all meter boxes, a hierarchical clustering method is used to perform cluster analysis on each meter box based on multi-scale similarity measurement information to obtain the connection relationship between the meter box and different branch nodes. The specific method is as follows: According to the voltage and current values ​​of all meter boxes, the Euclidean distance of load data between different meter boxes, the Euclidean distance of load difference vectors and the DTW distance are calculated; According to the Euclidean distance of load data between different meter boxes, the Euclidean distance of load difference vector and DTW distance, the distance characteristics, trend characteristics and time characteristics between different meter boxes are obtained, and the connection relationship between the meter box and different branch nodes is obtained.

10. The multi-level low-voltage area topology identification system based on linear regression according to claim 8, characterized in that: The functions of the branch node data acquisition module are implemented through the following methods: According to the voltage load curve and the connection relationship between the meter box and different branch nodes, the voltage and current of each branch node at each moment, as well as the impedance value from each branch node to the corresponding meter box are calculated; According to the voltage and current of each branch node at each moment, and the impedance value from each branch node to the corresponding meter box, the voltage data of different branch nodes and the impedance data of the line are coupled to obtain; The current data of all meter boxes under the branch node are summed separately to obtain the current data of different branch nodes.

11. The multi-level low-voltage area topology identification system based on linear regression according to claim 8, characterized in that: The functionality of the data association module is implemented through the following methods: According to the voltage data, line impedance data and current data of different branch nodes, the voltage and current upstream of each branch node are obtained, and compared with the voltage and current of the head-end transformer master meter. If the difference meets the conditions, the upstream branch node is determined to be the head-end transformer master meter; If the difference does not meet the condition, the upstream branch node is determined to be an adjacent branch node, and all branch nodes are determined to obtain the branch-trunk-transformer connection relationship.

12. The multi-level low-voltage area topology identification system based on linear regression according to claim 8, characterized in that: The functions of the topology generation module are implemented through the following methods: According to the branch-trunk-transformer connection relationship, identify the connection relationship between branch-meter box, trunk-branch, trunk-head end and the voltage drop trend analysis results, as well as the voltage data, current data and resistance data of each branch node; Based on the connection relationship and voltage drop trend analysis results of branch-meter box, trunk-branch, and trunk-headend, as well as the voltage data, current data, and resistance data of each branch node, combined with the access phase of the low-voltage user, a complete topological connection relationship including transformer, trunk, branch, meter box, user, phase, and impedance is generated.

13. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the multi-level low-voltage substation topology identification method based on linear regression described in any one of claims 1 to 7 are implemented.

14. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-level low-voltage substation topology identification method based on linear regression described in any one of claims 1 to 7 are implemented.

Images