Method and device for identifying affiliation relationship of small-load users based on multi-dimensional feature sequence, medium and equipment

Through the combination of multi-dimensional feature sequence and communication topology network, the affiliation relationship between small load users in the low-voltage distribution station area is accurately identified, which solves the problem of identification in traditional technology and improves the management efficiency and fault positioning capabilities of the distribution network.

CN118983771APending Publication Date: 2024-11-19POWER SUPPLY SERVICE & MANAGEMENT CENT STATE GRID JIANGXI ELECTRIC POWER CO LTD +1
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410908665.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-08
Publication Date
2024-11-19

Smart Images

  • Figure CN118983771A_ABST
    Figure CN118983771A_ABST
Patent Text Reader

Abstract

The invention discloses a method and device for recognizing the affiliation relation of small-load users based on a multi-dimensional feature sequence, a medium and equipment, and the method comprises the steps: carrying out the recognition of the affiliation relation of the small-load users according to the multi-dimensional feature sequence of each meter box in a target area, the multi-dimensional feature sequence of a known user corresponding to each meter box, and the multi-dimensional feature sequence of the small-load users; determining a first meter box to which the small-load user belongs; clustering the nodes according to the wireless signal intensity received by each node in the communication topology network, and determining a second meter box to which the small-load user belongs according to a clustering result; if the first meter box to which the small-load user belongs is different from the second meter box, returning to the step of determining the first meter box to which the small-load user belongs according to the multi-dimensional feature sequence of each meter box in the target area, the multi-dimensional feature sequence of the known user corresponding to each meter box and the multi-dimensional feature sequence of the small-load user in the target area; the first meter box and the second meter box to which the small-load user belongs are the same. The method is used for accurately identifying the affiliation relation of small-load users in a transformer area.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of power distribution networks, and in particular to a method and device, a storage medium, and a computer device for identifying the affiliation of small-load users based on a multi-dimensional feature sequence. Background Art

[0002] In the development of distribution network technology, we often face problems such as accurate repair of power outages, line loss analysis and abnormal location, three-phase imbalance control, and line impedance analysis. Accurate physical topology of low-voltage distribution substations can provide strong support for solving the above problems. The physical topology of low-voltage distribution substations refers to the multi-level relationship between transformers, branch boxes, meter boxes, and user meters within the substation.

[0003] In traditional technology, the ownership relationship of transformer-branch box-meter box-user is usually identified based on the principle of conservation of electric quantity. However, the ownership relationship of small-load users within the substation cannot be accurately identified in traditional technology. Summary of the invention

[0004] In view of this, the present application provides a method and apparatus, a storage medium, and a computer device for identifying the affiliation of small-load users based on a multi-dimensional feature sequence, which are used to accurately identify the affiliation of small-load users within a substation.

[0005] According to one aspect of the present application, a method for identifying affiliation of low-load users based on a multidimensional feature sequence is provided, comprising:

[0006] Determine the first meter box to which the light-load user belongs according to the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the light-load user in the target area, wherein the multidimensional feature sequence includes power, current and voltage;

[0007] According to the wireless signal strength received by each node in the communication topology network, the nodes are clustered, and the second meter box to which the light-load user belongs is determined according to the clustering result, wherein the nodes of the communication topology network include nodes corresponding to the known users and nodes corresponding to the light-load users;

[0008] If the first meter box to which the small load user belongs is different from the second meter box, the process returns to the step of determining the first meter box to which the small load user belongs based on the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small load user in the target area, until the first meter box to which the small load user belongs is the same as the second meter box, and the first meter box is taken as the meter box to which the small load user belongs.

[0009] According to another aspect of the present application, a device for identifying the belonging relationship of small-load users in a substation based on a multi-dimensional feature sequence is provided, comprising:

[0010] A first determination module is used to determine the first meter box to which the light-load user belongs based on the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the light-load user in the target area, wherein the multidimensional feature sequence includes power, current and voltage;

[0011] A second determination module is used to cluster the nodes according to the wireless signal strength received by each node in the communication topology network, and determine the second meter box to which the light-load user belongs according to the clustering result, wherein the nodes of the communication topology network include nodes corresponding to the known users and nodes corresponding to the light-load users;

[0012] A return module is used to return to the step of determining the first meter box to which the small load user belongs based on the multidimensional feature sequence of each meter box in the target substation, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small load user in the target substation if the first meter box to which the small load user belongs is different from the second meter box, until the first meter box to which the small load user belongs is the same as the second meter box, and the first meter box is used as the meter box to which the small load user belongs.

[0013] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for identifying the belonging relationship of light-load users based on a multi-dimensional feature sequence is implemented.

[0014] According to another aspect of the present application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the program, the method for identifying the affiliation of light-load users based on a multidimensional feature sequence is implemented.

[0015] By means of the above technical scheme, the present application provides a method and device, storage medium, and computer equipment for identifying the ownership relationship of small-load users based on a multidimensional feature sequence. The first meter box to which the small-load user belongs is determined through the multidimensional feature sequences of the meter boxes, known users, and small-load users in the target area, and the second meter box to which the small-load user belongs is determined through the communication topology network. Finally, the meter box to which the small-load user belongs is determined based on the first meter box and the second meter box. After identifying the first meter box to which the small-load user belongs, the present application also verifies the identification result through the second meter box, so that the ownership relationship of the small-load user can be accurately identified. The above description is only an overview of the technical scheme of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification, and in order to make the above and other purposes, features, and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A flow chart of a method for identifying the belonging relationship of light-load users based on a multi-dimensional feature sequence provided in an embodiment of the present application is shown;

[0018] Figure 2 A flow chart of a method for identifying the affiliation of small-load users in a substation based on a multi-dimensional feature sequence provided in an embodiment of the present application is shown;

[0019] Figure 3 A schematic diagram showing the relationship between a transformer, a branch box, a meter box and a user provided in an embodiment of the present application is shown;

[0020] Figure 4 A schematic diagram of the relationship between a user and a meter box provided in an embodiment of the present application is shown;

[0021] Figure 5 A schematic diagram of a communication topology network and clustering results provided by an embodiment of the present application is shown;

[0022] Figure 6 A schematic diagram of a clustering result provided in an embodiment of the present application is shown;

[0023] Figure 7 A schematic diagram of the structure of a device for identifying the belonging relationship of small-load users in a substation area based on a multi-dimensional feature sequence provided in an embodiment of the present application is shown;

[0024] Figure 8A schematic diagram of the device structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0026] In this embodiment, a method for identifying the belonging relationship of light-load users based on a multi-dimensional feature sequence is provided. Figure 1 As shown, the method includes:

[0027] Step 101, determining the first meter box to which the small-load user belongs based on the multidimensional feature sequence of each meter box in the target substation, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small-load user in the target substation, wherein the multidimensional feature sequence includes a power data sequence, a current data sequence, and a voltage data sequence.

[0028] In this embodiment, the target substation refers to the substation where the small load user whose affiliation needs to be determined is located. The above-mentioned multidimensional feature sequences can all include power data sequences, current data sequences and voltage data sequences. Known users are children of the meter box, and the meter box to which each known user belongs is determined. Small load users refer to users with smaller loads. Small load users are children connected to a certain meter box, and their level is the same as that of the known users, but the meter box to which the small load users belong is not determined. The first meter box refers to the meter box to which the small load user belongs.

[0029] In the present application, the target substation may be a low-voltage distribution substation. It should be noted that the physical topological relationship of the low-voltage distribution substation refers to the multi-level affiliation relationship between the transformer, branch box, meter box, and user meter within the substation. The present application is used to identify the relationship between small-load users and meter boxes in the physical topological relationship of the low-voltage distribution substation. Small-load users are children of a certain meter box, and each small-load user corresponds to only one meter box. However, each meter box may have multiple children, and each child may be a small-load user or an ordinary user, i.e., a known user. Before the meter box affiliation of small-load users is identified, the relationship between the transformer-branch box-meter box-known user in the substation has been clearly identified. The present application does not limit the method for identifying the relationship between the transformer-branch box-meter box-known user in the substation. Optionally, the relationship between the transformer-branch box-meter box-known user may be identified by the principle of conservation of electric quantity.

[0030] After determining the multidimensional feature sequence corresponding to each meter box, each known user and small-load user, the first meter box to which the small-load user belongs is determined based on the power data sequence, current data sequence and voltage data sequence of each meter box in the target substation, the power data sequence, current data sequence and voltage data sequence of each known user corresponding to each of the meter boxes, and the power data sequence, current data sequence and voltage data sequence of the small-load user in the target substation.

[0031] Step 102, clustering the nodes according to the wireless signal strength received by each node in the communication topology network, and determining the second meter box to which the small load user belongs according to the clustering result, wherein the nodes of the communication topology network include nodes corresponding to the known users and nodes corresponding to the small load users.

[0032] The communication topology network is a network that is pre-built based on the known users and small-load users and communicates via HRF (micro-power radio). Each known user and small-load user can serve as a node in the communication topology network.

[0033] Optionally, each node in the communication topology network can transmit wireless signals and can also receive wireless signals. Specifically, the nodes in the communication topology network can be clustered according to the strength of the wireless signals received by each node, and the meter boxes to which the nodes under each classification result belong are the same, and the second meter box to which the small load user belongs is determined according to other nodes under the classification result to which the small load user belongs.

[0034] Step 103, if the first meter box to which the small-load user belongs is different from the second meter box, then return to the step of determining the first meter box to which the small-load user belongs based on the multidimensional feature sequence of each meter box in the target substation, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small-load user in the target substation, until the first meter box to which the small-load user belongs is the same as the second meter box, and the first meter box is used as the meter box to which the small-load user belongs.

[0035] If the first meter box and the second meter box to which the small load user belongs are different, another set of multidimensional feature sequences is obtained, and the process returns to the step of determining the first meter box to which the small load user belongs based on the multidimensional feature sequence of each meter box in the target substation, the multidimensional feature sequence of each known user corresponding to each of the meter boxes, and the multidimensional feature sequence of the small load user in the target substation, and the first meter box and the second meter box of the small load user are recalculated until the first meter box and the second meter box to which the small load user belongs are the same, and the first meter box at this time is used as the meter box to which the small load user belongs.

[0036] By applying the technical solution of this embodiment, the first meter box to which the small load user belongs is determined through the multi-dimensional feature sequence of the meter boxes, known users and small load users in the target area, the second meter box to which the small load user belongs is determined through the communication topology network, and finally the meter box to which the small load user belongs is determined based on the first meter box and the second meter box. After identifying the first meter box to which the small load user belongs, the application also verifies the identification result through the second meter box, so that the belonging relationship of the small load user can be accurately identified.

[0037] In the embodiment of the present application, optionally, step 101 includes:

[0038] Step 101-1, based on the power data sequence, current data sequence and voltage data sequence corresponding to any meter box, and the power data sequence, current data sequence and voltage data sequence of each known user corresponding to any meter box, calculate the multi-dimensional error sequence corresponding to the any meter box.

[0039] In this embodiment, the collection method of the multi-dimensional feature sequence is not limited. Optionally, the data corresponding to each dimensional feature can be collected periodically within a preset time to obtain the corresponding data sequence. For example, the collection method of the power data sequence of the meter box is to collect the power of the meter box once every 15 minutes within 24 hours (a preset time). The power data sequence of the meter box can be obtained by arranging the multiple power data collected within a preset time in chronological order. The data sequences of other dimensions of the meter box, the data sequences of each dimension of known users, and the data sequences of each dimension of small-load users can all be collected in the above manner, which will not be repeated here.

[0040] Optionally, the power error sequence of any meter box is calculated based on the power data sequence corresponding to any meter box and the power data sequence of each known user corresponding to the meter box. The current error sequence of the meter box is calculated based on the current data sequence corresponding to any meter box and the current data sequence of each known user corresponding to the meter box. The voltage error sequence of the meter box is calculated based on the voltage data sequence corresponding to any meter box and the voltage data sequence of each known user corresponding to the meter box. The multidimensional error sequence corresponding to any meter box is the power error sequence, current error sequence and voltage error sequence of the meter box.

[0041] Step 101 - 2 , calculating a multi-dimensional offset sequence corresponding to any meter box according to the power data sequence, current data sequence and voltage data sequence of the small load user and the multi-dimensional error sequence corresponding to any meter box.

[0042] Optionally, the power offset sequence corresponding to any meter box is calculated based on the power data series of the small load user and the power error sequence corresponding to any meter box. The current offset sequence corresponding to the meter box is calculated based on the current data series of the small load user and the current error sequence corresponding to any meter box. The voltage offset sequence corresponding to the meter box is calculated based on the voltage data series of the small load user and the voltage error sequence corresponding to any meter box. The multi-dimensional offset sequence corresponding to any meter box is the power offset sequence, current offset sequence and voltage offset sequence of the meter box.

[0043] Step 101-3, based on the multi-dimensional error sequence and coefficient of variation method of any meter box, calculate the power weight, current weight and voltage weight corresponding to any meter box, and calculate the target offset corresponding to any meter box based on the power weight, current weight, voltage weight and the multi-dimensional offset sequence of any meter box.

[0044] Optionally, the power weight corresponding to any meter box is calculated according to the power error sequence and the coefficient of variation method of any meter box, the current weight corresponding to any meter box is calculated according to the current error sequence and the coefficient of variation method of any meter box, and the voltage weight corresponding to any meter box is calculated according to the voltage error sequence and the coefficient of variation method of any meter box. According to the corresponding power weight, current weight, voltage weight of any meter box and the power offset sequence, current offset sequence and voltage offset sequence corresponding to the meter box, the target offset corresponding to the meter box can be calculated accordingly.

[0045] Step 101 - 4 , determining the meter box with the smallest target offset as the first meter box to which the small-load user belongs.

[0046] The target offsets corresponding to the meter boxes are compared, and the meter box with the smallest target offset is determined as the first meter box to which the small-load user belongs.

[0047] This embodiment determines the first meter box to which the small-load user belongs through the power data sequences, current data sequences and voltage data sequences of the meter boxes, known users and small-load users in the target substation area, thereby enabling rapid identification of the first meter box of the small-load user.

[0048] In an embodiment of the present application, optionally, step 101-1 includes: adding the power data sequence, current data sequence and voltage data sequence of each known user corresponding to any meter box to obtain the user power sequence, user current sequence and user voltage sequence corresponding to any meter box; and calculating the error sequence of any meter box in each dimension based on the power data sequence, current data sequence and voltage data sequence corresponding to any meter box, as well as the user power sequence, user current sequence and user voltage sequence.

[0049] In this embodiment, the power data sequence of each known user corresponding to any meter box is added to obtain the user power sequence corresponding to the meter box. The calculation method is shown in formula (1):

[0050]

[0051] in, represents the user power sequence, Represents the data corresponding to time t in the user power sequence corresponding to the x-th meter box, that is, the sum of the powers of all known users corresponding to the x-th meter box at time t. t=1, 2, ...T are different collection times. It should be noted that the present application does not limit the collection method of the multidimensional feature sequence. Optionally, the data sequence corresponding to each dimensional feature can be obtained by periodic collection within a preset time. It should be noted that whether it is a multidimensional feature sequence of a meter box or a multidimensional feature sequence of a known user or a small-load user, the collection cycle and time are the same, that is, the collection time corresponding to t in each data sequence is the same, and the number of data contained in each data sequence is also the same. n is the number of known users in the x-th meter box. m i represents the i-th known user, represents the power of the i-th known user in the time table box at time t. represents the power data sequence of the i-th known user.

[0052] The current data sequence of each known user corresponding to any meter box is added together to obtain the user current sequence corresponding to the meter box. The calculation method is shown in formula (2):

[0053]

[0054] in, Represents the user current sequence, It represents the data corresponding to time t in the user current sequence corresponding to the x-th meter box, that is, the sum of the currents of all known users corresponding to the x-th meter box at time t. t = 1, 2, ... T are different collection times. n is the number of known users in the x-th meter box. m i represents the i-th known user, Represents the current of the i-th known user in the time table box at time t. Represents the current data sequence of the i-th known user.

[0055] The voltage data sequence of each known user corresponding to any meter box is added together to obtain the user voltage sequence corresponding to the meter box. The calculation method is shown in formula (3):

[0056]

[0057] in, Indicates the user voltage sequence, It represents the data corresponding to time t in the user voltage sequence corresponding to the x-th meter box, that is, the sum of the voltages of all known users corresponding to the x-th meter box at time t. t=1,2,…T are different collection times. n is the number of known users in the x-th meter box. m i represents the i-th known user, Represents the voltage of the i-th known user in the table box at time t. Represents the voltage data sequence of the i-th known user.

[0058] According to the power data sequence and user power sequence corresponding to any meter box, the power error sequence of the meter box in the power dimension can be calculated. The calculation method is shown in formula (4):

[0059]

[0060] in, is the power error sequence of the xth meter box in the power dimension, b x Refers to the xth table box, for example, when x = 5, is the power error sequence of meter box 5 in the power dimension, b 5 Refers to meter box 5. Refers to the power data sequence of the xth meter box.

[0061] According to the current data sequence corresponding to any meter box and the user current sequence, the current error sequence of the meter box in the current dimension can be calculated. The calculation method is shown in formula (5):

[0062]

[0063] in, is the current error sequence of the xth meter box in the current dimension, b x Refers to the xth table box, for example, when x = 5, is the current error sequence of meter box 5 in the current dimension, b 5 Refers to meter box 5. Refers to the current data sequence of the xth meter box.

[0064] According to the voltage data sequence corresponding to any meter box and the user voltage sequence, the voltage error sequence of the meter box in the voltage dimension can be calculated. The calculation method is shown in formula (6):

[0065]

[0066] in, is the voltage error sequence of the xth meter box in the voltage dimension, bx Refers to the xth table box, for example, when x = 5, is the voltage error sequence of meter box 5 in the voltage dimension, b 5 Refers to meter box 5. Refers to the voltage data sequence of the xth meter box.

[0067] In the embodiment of the present application, optionally, the multidimensional error sequence includes a power error sequence, a current error sequence, and a voltage error sequence. The step 203 of calculating the power weight, current weight, and voltage weight corresponding to any meter box according to the multidimensional error sequence and the coefficient of variation method of any meter box includes:

[0068] Step 401: Calculate a first mean and a first mean square error corresponding to the power error sequence according to the power error sequence of any meter box, and calculate a power variation coefficient according to the first mean and the first mean square error.

[0069] Optionally, the average of the power errors in the power error sequence corresponding to any meter box is calculated, and the average is the first mean. The mean square error of the power errors in the power error sequence of any meter box is calculated, and the mean square error is the first mean square error. According to the first mean and the first mean square error of any meter box, the power variation coefficient of any meter box is calculated, and the calculation formula (7) is as follows:

[0070] ε(ΔP)=v(ΔP) / s(ΔP)(7)

[0071] Where ε(ΔP) is the power variation coefficient, v(ΔP) is the first mean, and s(ΔP) is the first mean square error.

[0072] Step 402: Calculate a second mean and a second mean square error corresponding to the current error sequence according to the current error sequence of any meter box, and calculate a current variation coefficient according to the second mean and the second mean square error.

[0073] Optionally, the average of the current errors in the current error sequence of any meter box is calculated, and the average is the second mean. The mean square error of the current errors in the current error sequence of any meter box is calculated, and the mean square error is the second mean square error. According to the second mean and the second mean square error of any meter box, the current variation coefficient of any meter box is calculated, and the calculation formula (8) is as follows:

[0074] ε(ΔI)=v(ΔI) / s(ΔI)(8)

[0075] Wherein, ε(ΔI) is the current variation coefficient, v(ΔI) is the second mean, and s(ΔI) is the second mean square error. It should be noted that the present application does not limit the calculation formula of the second mean and the second mean square error.

[0076] Step 403: Calculate a third mean and a third mean square error corresponding to the voltage error sequence according to the voltage error sequence of any meter box, and calculate a voltage variation coefficient according to the third mean and the third mean square error.

[0077] Optionally, the average of the voltage errors in the voltage error sequence of any meter box is calculated, and the average is the third mean. The mean square error of the voltage errors in the voltage error sequence of any meter box is calculated, and the mean square error is the third mean square error. Based on the third mean and the third mean square error of any meter box, the voltage variation coefficient of any meter box is calculated, and the calculation formula (9) is as follows:

[0078] ε(ΔU)=v(ΔU) / s(ΔU)(9)

[0079] Wherein, ε(ΔU) is the voltage variation coefficient, v(ΔU) is the third mean, and s(ΔU) is the third mean square error. It should be noted that the present application does not limit the calculation formula of the third mean and the third mean square error.

[0080] Step 404, based on the power variation coefficient, the current variation coefficient, the voltage variation coefficient and the variation coefficient method, calculate the power weight, current weight and voltage weight of any meter box.

[0081] Optionally, based on the power variation coefficient, the current variation coefficient, the voltage variation coefficient and the variation coefficient method corresponding to any of the meter boxes, a formula (10) for calculating the power weight of the meter box is as follows:

[0082]

[0083] Among them, α is the power weight.

[0084] Based on the power variation coefficient, the current variation coefficient, the voltage variation coefficient and the variation coefficient method corresponding to any of the meter boxes, the formula (11) for calculating the current weight of the meter box is as follows:

[0085]

[0086] Where β is the current weight.

[0087] Based on the power variation coefficient, the current variation coefficient, the voltage variation coefficient and the variation coefficient method corresponding to any of the meter boxes, the formula (12) for calculating the voltage weight of the meter box is as follows:

[0088]

[0089] Among them, γ is the voltage weight.

[0090] In an embodiment of the present application, optionally, the target offset corresponding to any meter box is calculated according to the power weight, current weight, voltage weight and the multi-dimensional offset sequence corresponding to any meter box in step 203, including: for the multi-dimensional offset sequence corresponding to any meter box, performing modulo calculation on the offset sequence of each dimension to obtain the modulo result corresponding to each dimension; according to the modulo results corresponding to each dimension, and the power weight, current weight and voltage weight of any meter box, the target offset corresponding to any meter box is calculated.

[0091] Optionally, a modulus calculation is performed on the power offset sequence, current offset sequence and voltage offset sequence corresponding to any meter box to obtain the modulus results corresponding to the power offset sequence, current offset sequence and voltage offset sequence; according to the modulus results corresponding to the power offset sequence, current offset sequence and voltage offset sequence, and the power weight, current weight and voltage weight corresponding to the meter box, the target offset corresponding to the meter box is calculated. The calculation formula (13) for calculating the target offset corresponding to any meter box is as follows:

[0092] θ Ux =α||εP||+β||εI||+γ||εU|| (13)

[0093] Among them, θ Ux Refers to the target offset corresponding to the x-th meter box, εP refers to the power offset sequence of the x-th meter box, εI refers to the current offset sequence of the x-th meter box, and εU refers to the voltage offset sequence of the x-th meter box. ||·|| represents modulus, ||εP|| refers to the modulus result of the power offset sequence of the x-th meter box, ||εI|| refers to the modulus result of the current offset sequence of the x-th meter box, and ||εU|| refers to the modulus result of the voltage offset sequence of the x-th meter box. α is the power weight corresponding to the x-th meter box, β is the current weight corresponding to the x-th meter box, and γ is the voltage weight corresponding to the x-th meter box.

[0094] In the embodiment of the present application, optionally, step 102 clusters the nodes according to the wireless signal strength received by each node in the communication topology network, and determines the second meter box to which the light-load user belongs according to the clustering result, including:

[0095] Step 501: set any node in the communication topology network as a first signal transmitting node, set the remaining nodes as first signal receiving nodes, and obtain the wireless signal strength of each of the first signal receiving nodes corresponding to the first signal transmitting node.

[0096] It should be noted that the communication topology network is composed of nodes corresponding to known users and small-load users. Each known user and small-load user corresponds to a node one-to-one, and the nodes can send and receive wireless signals to each other. Assuming that there are N nodes in the communication topology network, and these N nodes send and receive wireless signals to each other, the host computer can directly obtain N wireless signal lists, each of which includes a transmitting node and the wireless signal strength information of the receiving node corresponding to the transmitting node.

[0097] Step 502: A first signal receiving node whose wireless signal strength is greater than a threshold is taken as a target node, and a first target set corresponding to the first signal transmitting node is constructed according to the target node and the first signal transmitting node.

[0098] It should be noted that the strength of the wireless signal received by the signal receiving node decays as the distance increases. Therefore, it is possible to determine whether each node belongs to the same meter box based on the strength of the wireless signal. The strength of the wireless signal received by the nodes belonging to the same meter box is greater than the threshold. This application does not limit the value of the threshold, and specific analysis is performed based on specific circumstances.

[0099] Optionally, a threshold is determined in advance according to the situation of the station area, the strength of the wireless signal received by each first signal receiving node is compared with the threshold, and the first signal receiving node whose wireless signal strength is greater than the threshold is used as the target node. According to the target node and the first signal transmitting node, a first target set corresponding to the first signal transmitting node is constructed. According to the first signal transmitting node and the first signal receiving node, it can be known that the nodes in the first target set belong to the same meter box.

[0100] Step 503: Set each of the target nodes in the first target set as a second signal transmitting node in turn, obtain the wireless signal strength of the second signal receiving node corresponding to each of the second signal transmitting nodes, so as to obtain a second target set corresponding to each of the target nodes.

[0101] It should be noted that if the number of target nodes is greater than 1, each time a target node is set as the second signal transmitting node, each target node must be set as the second signal transmitting node without duplication, the wireless signal strength of each second signal receiving node corresponding to each second signal transmitting node is found, the strength of the wireless signal received by each second signal receiving node is compared with the threshold, and the second signal receiving node with a wireless signal strength greater than the threshold is used as the second target node. According to each second target node and the corresponding second signal transmitting node, a second target set corresponding to each second signal transmitting node is constructed. The nodes in each second target set belong to the same meter box.

[0102] Step 504: Take the intersection of the first target set and the second target set to obtain a third target set, wherein the nodes in the third target set belong to the same table box.

[0103] Taking the intersection of the first target set and the second target set can verify each other and increase the probability that each node belongs to the same table box.

[0104] Step 505, identify the nodes to be divided in the communication topology network that do not belong to the third target set, set any node to be divided as the first signal transmitting node, and return to the step of obtaining the wireless signal strength of each first signal receiving node corresponding to the first signal transmitting node, until there are no nodes to be divided in the communication topology network.

[0105] Step 506: Identify a meter box including a node corresponding to the light-load user from the third target set as a second meter box to which the light-load user belongs.

[0106] Optionally, find the third target set A to which the node corresponding to the small load user belongs, select any node B from the third target set A, find the meter box C to which the node B belongs, and use the meter box C as the second meter box to which the small load user belongs.

[0107] The above embodiment determines the second meter box to which the small load user belongs through the communication topology network. The recognition result of the multi-dimensional feature sequence is verified by the recognition result of the communication topology network to improve the accuracy of identifying the belonging relationship of the small load user. Finally, the meter box to which the small load user belongs is accurately identified.

[0108] In the embodiment of the present application, optionally, before step 101, it also includes: normalizing the multidimensional feature sequence of the meter box, the multidimensional feature sequence of each known user in each meter box, and the multidimensional feature sequence of the small-load user.

[0109] Optionally, the power characteristic parameters, current characteristic parameters, and voltage characteristic parameters of the meter box are normalized, the power characteristic parameters, current characteristic parameters, and voltage characteristic parameters of each known user in each meter box are normalized, and the power characteristic parameters, current characteristic parameters, and voltage characteristic parameters of small load users are normalized.

[0110] The normalized formula (14) is as follows:

[0111]

[0112] Among them, x new For the normalized data, x iThe data needs to be normalized, max is the maximum value, min is the minimum value. This application does not limit the maximum and minimum values ​​of the data, and can be selected according to actual conditions.

[0113] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another method for identifying the belonging relationship of small-load users based on a multi-dimensional feature sequence is provided, such as Figure 2 As shown, the method includes:

[0114] Collect the power, current, and voltage data of the meter box, known users, and small-load users, and collect the wireless RSSI data of each user's meter in the entire substation network. The wireless RSSI data includes the data of the wireless signal strength. Since the power, current, and voltage data are at different levels, the data must be normalized first. The normalization formula (15) is as follows:

[0115]

[0116] After normalization, the power data sequence, current data sequence, and voltage data sequence of each known user, the power data sequence, current data sequence, and voltage data sequence of small-load users, and the power data sequence, current data sequence, and voltage data sequence of each meter box are obtained.

[0117] Calculate the multi-dimensional error sequence between the power data sequence, current data sequence, and voltage data sequence of each meter box and the power data sequence, current data sequence, and voltage data sequence of the known user corresponding to the meter box. Number the meter box and the sub-level corresponding to the meter box, i.e., the known user, as a combination. For example, combination 1{b 1 , m 1 , m 2 ,…m n}, where b 1 For meter box 1; m1, m2, ...m n For each child of meter box 1, that is, the known users corresponding to meter box 1, let:

[0118]

[0119] in, is the power error sequence of meter box 1 in the power dimension; is the power error sequence of meter box 1 in the current dimension,

[0120] is the power error sequence of meter box 1 in the voltage dimension, and t represents the number of collected data points. is the power data sequence of the i-th known user,

[0121] is the user power sequence corresponding to meter box 1, that is, the sum of the powers of all known users corresponding to meter box 1 at time t. Refers to the power data sequence of meter box 1. is the current data sequence of the i-th known user, is the user current sequence corresponding to meter box 1, that is, the sum of the currents of all known users corresponding to meter box 1 at time t. Refers to the current data sequence of meter box 1. represents the voltage data sequence of the i-th known user, is the mean value of the user voltage sequence corresponding to meter box 1. Refers to the voltage data sequence of meter box 1. Similarly, the calculation method of the power data sequence, current data sequence, and voltage data sequence of other meter boxes is the same as that of meter box 1.

[0122] The power offset sequence εP, current offset sequence εI and voltage offset sequence εU between the small load user and meter box 1 are calculated by the following formulas (16), (17), (18):

[0123]

[0124] in, is the power data sequence of the small load user Ua,

[0125] is the current data sequence of the small load user Ua, is the voltage data sequence of the small load user Ua. It can be understood that the power offset sequence, current offset sequence and voltage offset sequence between the small load user and other meter boxes can also be calculated by the above formula.

[0126] Calculate the power error sequence of meter box 1 The average of the power errors in v(ΔP), v(ΔP) is the first mean, and the power error sequence of meter box 1 is calculated. The mean square error of each power error in s(ΔP), s(ΔP) is the first mean square error. The power variation coefficient ε(ΔP) corresponding to the meter box 1 is =v(ΔP) / s(ΔP).

[0127] Calculate the current error sequence of meter box 1 The average of the current errors in v(ΔI), v(ΔI) is the second mean, and the current error sequence of meter box 1 is calculated. The mean square error of each current error in is s(ΔP), s(ΔP) is the second mean square error. The current variation coefficient ε(ΔI) corresponding to the meter box 1 is =v(ΔI) / s(ΔI).

[0128] Calculate the voltage error sequence of meter box 1 The average of the voltage errors in v(ΔU), v(ΔU) is the second mean, and the voltage error sequence of meter box 1 is calculated. The mean square error of each voltage error in s(ΔU), s(ΔU) is the second mean square error. The voltage variation coefficient ε(ΔU) corresponding to the meter box 1 = v(ΔU) / s(ΔU).

[0129] Power weight corresponding to meter box 1 Current weight

[0130] Voltage Weight It should be noted that for the weights calculated by the coefficient of variation method, if the numerical difference of a certain indicator is large, it can clearly distinguish the evaluated objects, indicating that the indicator has rich discrimination information, and therefore the indicator should be given a larger weight; conversely, if the numerical difference of each evaluated object on a certain indicator is small, then the ability of this indicator to distinguish the evaluated objects is weak, and therefore the indicator should be given a smaller weight.

[0131] The target offset calculation formula (19) for small load users and meter box 1 is as follows:

[0132] θ U1 =α||εP||+β||εI||+γ||εU|| (19)

[0133] Among them, θ U1 It represents the target offset between the small load user and combination 1, that is, the target offset corresponding to meter box 1; ||·|| represents modulo.

[0134] It should be noted that the target offset corresponding to each meter box can be calculated in sequence using the above formula of this embodiment.

[0135] The combination of small load users and the smallest target offset is classified into the same meter box, that is, the meter box corresponding to the smallest target offset is the first meter box.

[0136] Through the above technical means, the relationship between transformer-branch box-meter box-user can be obtained, such as Figure 3 shown.

[0137] like Figure 4 As shown, the relationship between the small load user and the first meter box may be wrong, and then the wireless signal strength data is used to verify the meter box-user relationship.

[0138] It should be noted that the distribution network has deployed a large number of PLC (power line carrier communication) + HRF (micropower wireless) dual-mode solutions. Based on the HRF communication method, the wireless signal strength between each STA (user meter) can be obtained. Small load users also have corresponding STA (user meter). Each STA (user meter) is a node in the communication topology network in the above embodiment. Based on the characteristic that the strength of the wireless signal decays with the increase of distance, the clustering algorithm can be used to cluster users of the same meter box into a cluster, so that the users of meter box 2 and meter box 3 are correctly divided into a cluster.

[0139] The substation network is pre-formed based on the known users of small loads and meter boxes, such as Figure 5 As shown, cco (master station) sends a start topology identification instruction to the terminal, namely STA (user meter), to start the topology identification function, and each STA (user meter) sends and receives wireless signals to each other. Among them, the station area network is the communication topology network in the above embodiment. Each user meter corresponds to a node in the communication topology network one by one. Assuming that there are N nodes in the communication topology network, these N nodes send and receive wireless signals to each other, then the host computer can directly obtain N wireless information lists, each of which includes a transmitting node and the wireless signal strength information of the receiving node corresponding to the transmitting node.

[0140] The RSSI threshold is set according to the RSSI (radio signal strength information) data. If the radio signal strength received by each radio signal receiving node is greater than the threshold, the radio signal transmitting node and the radio signal receiving node greater than the threshold are classified into the same target set.

[0141] A node corresponding to a user's electric meter is randomly selected as the first signal transmitting node, and the wireless signal strength received by the first signal receiving node, i.e., the neighboring node of the first signal transmitting node, is obtained. A set of neighboring nodes greater than the RSSI threshold is queried in the wireless RSSI data of each neighboring node, and the set of neighboring users greater than the RSSI threshold is the target node in the above embodiment. When the neighboring nodes in the neighboring user set greater than the RSSI threshold are queried in turn as wireless signal transmitting nodes, the set of neighboring nodes greater than the RSSI threshold in the wireless RSSI data of each neighboring user is the second target set. The intersection of the first target set and the second target set is taken to obtain a clustering result, and the nodes in the clustering result are children of the same meter box.

[0142] The above methods are used to judge the non-clustered user meters in turn to achieve clustering of all user meters. The clustering result diagram is shown in the figure below: Figure 6 shown.

[0143] Find the clustering result to which the user electric meter corresponding to the small load user belongs, select any user electric meter a from the clustering result, find the meter box b to which the user electric meter a belongs, and use the meter box b as the second meter box to which the small load user belongs.

[0144] If the first meter box and the second meter box to which the small load user belongs are different, another set of corresponding data is obtained, and the process returns to the step of determining the first meter box to which the small load user belongs based on the multidimensional feature sequence of each meter box in the target substation, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small load user in the target substation, and the first meter box and the second meter box of the small load user are obtained again, and the process ends when the first meter box and the second meter box to which the small load user belongs are the same, and the first meter box is used as the meter box to which the small load user belongs.

[0145] The above method for identifying the ownership relationship of small load users based on multidimensional feature sequences determines the first meter box to which the small load user belongs through the multidimensional feature sequences of the meter boxes, known users and small load users in the target area. The second meter box to which the small load user belongs is determined through the communication topology network. The recognition result of the multidimensional feature sequence is verified through the recognition result of the communication topology network to improve the accuracy of identifying the ownership relationship of the small load user. Finally, the meter box to which the small load user belongs is accurately identified.

[0146] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a device for identifying the belonging relationship of small load users in a substation based on a multi-dimensional feature sequence, such as Figure 7 As shown, the device comprises:

[0147] The first determination module 601 is used to determine the first meter box to which the light-load user belongs according to the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the light-load user in the target area, wherein the multidimensional feature sequence includes power, current and voltage;

[0148] The second determination module 602 is used to cluster the nodes according to the wireless signal strength received by each node in the communication topology network, and determine the second meter box to which the light-load user belongs according to the clustering result, wherein the nodes of the communication topology network include the nodes corresponding to the known users and the nodes corresponding to the light-load users;

[0149] Return module 603 is used to return to the step of determining the first meter box to which the small load user belongs based on the multidimensional feature sequence of each meter box in the target substation, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small load user in the target substation if the first meter box to which the small load user belongs is different from the second meter box, until the first meter box to which the small load user belongs is the same as the second meter box, and the first meter box is used as the meter box to which the small load user belongs.

[0150] In one embodiment, the first determining module 601 of the device includes:

[0151] A multi-dimensional error calculation unit, used to calculate a multi-dimensional error sequence corresponding to any meter box according to a power data sequence, a current data sequence and a voltage data sequence corresponding to any meter box, and a power data sequence, a current data sequence and a voltage data sequence of each known user corresponding to the any meter box;

[0152] A multi-dimensional offset calculation unit, used to calculate a multi-dimensional offset sequence corresponding to any meter box according to a power data sequence, a current data sequence and a voltage data sequence of the small load user and a multi-dimensional error sequence corresponding to any meter box;

[0153] A comprehensive calculation unit, used to calculate the power weight, current weight and voltage weight corresponding to any meter box according to the multi-dimensional error sequence and the coefficient of variation method of any meter box, and calculate the target offset corresponding to any meter box according to the power weight, current weight, voltage weight and the multi-dimensional offset sequence corresponding to any meter box;

[0154] The first meter box determining unit is used to determine the meter box with the smallest target offset as the first meter box to which the small-load user belongs.

[0155] In one embodiment, the multi-dimensional error calculation unit of the device includes:

[0156] Adding the power data sequence, current data sequence and voltage data sequence of each known user corresponding to any meter box to obtain the user power sequence, user current sequence and user voltage sequence corresponding to any meter box;

[0157] According to the power data sequence, current data sequence and voltage data sequence corresponding to any meter box, and the user power sequence, user current sequence and user voltage sequence, the error sequence of any meter box in each dimension is calculated.

[0158] In one embodiment, the integrated computing unit of the device comprises:

[0159] According to the power error sequence of any meter box, a first mean and a first mean square error corresponding to the power error sequence are calculated, and a power variation coefficient is calculated according to the first mean and the first mean square error;

[0160] According to the current error sequence of any meter box, a second mean and a second mean square error corresponding to the current error sequence are calculated, and a current variation coefficient is calculated according to the second mean and the second mean square error;

[0161] According to the voltage error sequence of any meter box, a third mean and a third mean square error corresponding to the voltage error sequence are calculated, and a voltage variation coefficient is calculated according to the third mean and the third mean square error;

[0162] Based on the power variation coefficient, the current variation coefficient, the voltage variation coefficient and the variation coefficient method, the power weight, current weight and voltage weight of any meter box are calculated.

[0163] In one embodiment, the integrated computing unit of the device comprises:

[0164] For the multi-dimensional offset sequence corresponding to any one of the table boxes, a modulo calculation is performed on the offset sequence of each dimension to obtain a modulo result corresponding to each dimension;

[0165] According to the modulo results corresponding to each dimension, and the power weight, current weight and voltage weight of any meter box, the target offset corresponding to any meter box is calculated.

[0166] In one embodiment, the second determining module 602 of the device includes:

[0167] A first setting unit, configured to set any node in the communication topology network as a first signal transmitting node, and obtain the wireless signal strength of each of the first signal receiving nodes corresponding to the first signal transmitting node;

[0168] A construction unit, configured to take a first signal receiving node whose wireless signal strength is greater than a threshold as a target node, and construct a first target set corresponding to the first signal transmitting node according to the target node and the first signal transmitting node;

[0169] A second setting unit is used to sequentially set each of the target nodes in the first target set as a second signal transmitting node, and obtain the wireless signal strength of the second signal receiving node corresponding to each of the second signal transmitting nodes to obtain a second target set corresponding to each of the target nodes;

[0170] An intersection unit, configured to intersect the first target set with the second target set to obtain a third target set, wherein the nodes in the third target set belong to the same table box;

[0171] A third setting unit is used to identify the nodes to be divided that do not belong to the third target set in the communication topology network, set any node to be divided as the first signal transmitting node, and return to the step of obtaining the wireless signal strength of each first signal receiving node corresponding to the first signal transmitting node until there are no nodes to be divided in the communication topology network;

[0172] The second meter box determining unit is used to identify a meter box including a node corresponding to the small load user from the third target set as a second meter box to which the small load user belongs.

[0173] It should be noted that for other corresponding descriptions of the functional units involved in the device for identifying the belonging relationship of small load users in a substation provided in the embodiment of the present application, reference can be made to Figures 1 to 6 The corresponding description in the method will not be repeated here.

[0174] The present application also provides a computer device, which may be a personal computer, a server, a network device, etc. Figure 8 As shown, the computer device includes a bus, a processor, a memory and a communication interface, and may also include an input and output interface and a display device. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store location information. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in each method embodiment are implemented.

[0175] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0176] In one embodiment, a computer-readable storage medium is provided. The computer-readable storage medium may be non-volatile or volatile, and stores a computer program thereon. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0177] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0178] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0179] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0180] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0181] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for identifying the belonging relationship of small-load users based on multi-dimensional feature sequences, characterized in that: include: Determine the first meter box to which the small-load user belongs according to the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small-load user in the target area, wherein the multidimensional feature sequence includes a power data sequence, a current data sequence, and a voltage data sequence; According to the wireless signal strength received by each node in the communication topology network, the nodes are clustered, and the second meter box to which the light-load user belongs is determined according to the clustering result, wherein the nodes of the communication topology network include nodes corresponding to the known users and nodes corresponding to the light-load users; If the first meter box to which the small load user belongs is different from the second meter box, the process returns to the step of determining the first meter box to which the small load user belongs based on the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small load user in the target area, until the first meter box to which the small load user belongs is the same as the second meter box, and the first meter box is taken as the meter box to which the small load user belongs.

2. The method according to claim 1, characterized in that: The method of determining the first meter box to which the light-load user belongs according to the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the light-load user in the target area comprises: Calculate the multi-dimensional error sequence corresponding to any meter box according to the power data sequence, current data sequence and voltage data sequence corresponding to any meter box, and the power data sequence, current data sequence and voltage data sequence of each known user corresponding to any meter box; Calculate the multi-dimensional offset sequence corresponding to any meter box according to the power data sequence, current data sequence and voltage data sequence of the small load user and the multi-dimensional error sequence corresponding to any meter box; According to the multi-dimensional error sequence and coefficient of variation method of any meter box, the power weight, current weight and voltage weight corresponding to any meter box are calculated, and according to the power weight, current weight, voltage weight and the multi-dimensional offset sequence corresponding to any meter box, the target offset corresponding to any meter box is calculated; The meter box with the smallest target offset is determined as the first meter box to which the small-load user belongs.

3. The method according to claim 2, characterized in that The calculating of the multi-dimensional error sequence corresponding to any meter box according to the power data sequence, current data sequence and voltage data sequence corresponding to any meter box, and the power data sequence, current data sequence and voltage data sequence of each known user corresponding to the any meter box, comprises: Adding the power data sequence, current data sequence and voltage data sequence of each known user corresponding to any meter box to obtain the user power sequence, user current sequence and user voltage sequence corresponding to any meter box; According to the power data sequence, current data sequence and voltage data sequence corresponding to any meter box, and the user power sequence, user current sequence and user voltage sequence, the error sequence of any meter box in each dimension is calculated.

4. The method according to claim 2 or 3, characterized in that: The multidimensional error sequence includes a power error sequence, a current error sequence and a voltage error sequence; the power weight, current weight and voltage weight corresponding to any meter box are calculated according to the multidimensional error sequence and the coefficient of variation method of any meter box, including: According to the power error sequence of any meter box, a first mean and a first mean square error corresponding to the power error sequence are calculated, and a power variation coefficient is calculated according to the first mean and the first mean square error; According to the current error sequence of any meter box, a second mean and a second mean square error corresponding to the current error sequence are calculated, and a current variation coefficient is calculated according to the second mean and the second mean square error; According to the voltage error sequence of any meter box, a third mean and a third mean square error corresponding to the voltage error sequence are calculated, and a voltage variation coefficient is calculated according to the third mean and the third mean square error; Based on the power variation coefficient, the current variation coefficient, the voltage variation coefficient and the variation coefficient method, the power weight, current weight and voltage weight of any meter box are calculated.

5. The method according to claim 4, characterized in that The calculating the target offset corresponding to any meter box according to the power weight, the current weight, the voltage weight and the multi-dimensional offset sequence corresponding to any meter box includes: For the multi-dimensional offset sequence corresponding to any one of the table boxes, a modulo calculation is performed on the offset sequence of each dimension to obtain a modulo result corresponding to each dimension; According to the modulo results corresponding to each dimension, and the power weight, current weight and voltage weight of any meter box, the target offset corresponding to any meter box is calculated.

6. The method according to claim 1, characterized in that The node clustering is performed according to the wireless signal strength received by each node in the communication topology network, and the second meter box to which the light-load user belongs is determined according to the clustering result, including: Setting any node in the communication topology network as a first signal transmitting node, and obtaining the wireless signal strength of each first signal receiving node corresponding to the first signal transmitting node; Taking a first signal receiving node whose wireless signal strength is greater than a threshold as a target node, and constructing a first target set corresponding to the first signal transmitting node according to the target node and the first signal transmitting node; Setting each of the target nodes in the first target set as a second signal transmitting node in sequence, and obtaining the wireless signal strength of the second signal receiving node corresponding to each of the second signal transmitting nodes, so as to obtain a second target set corresponding to each of the target nodes; Taking the intersection of the first target set and the second target set to obtain a third target set, wherein the nodes in the third target set belong to the same table box; Identify the nodes to be divided that do not belong to the third target set in the communication topology network, set any node to be divided as the first signal transmitting node, and return to the step of obtaining the wireless signal strength of each first signal receiving node corresponding to the first signal transmitting node until there are no nodes to be divided in the communication topology network; From each of the third target sets, the third target set including the node corresponding to the small load user is identified, and the meter box to which the third target set including the node corresponding to the small load user belongs is used as the second meter box to which the small load user belongs.

7. The method according to claim 1, characterized in that Before determining the first meter box to which the light-load user belongs based on the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the light-load user in the target area, the method further includes: The multidimensional feature sequence of the meter box, the multidimensional feature sequence of each known user in each meter box, and the multidimensional feature sequence of the small-load user are normalized.

8. A device for identifying the affiliation of small load users in a substation based on a multi-dimensional feature sequence, characterized in that: include: A first determination module is used to determine the first meter box to which the light-load user belongs based on the multidimensional feature sequence of each meter box in the target area, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the light-load user in the target area, wherein the multidimensional feature sequence includes power, current and voltage; A second determination module is used to cluster the nodes according to the wireless signal strength received by each node in the communication topology network, and determine the second meter box to which the light-load user belongs according to the clustering result, wherein the nodes of the communication topology network include nodes corresponding to the known users and nodes corresponding to the light-load users; A return module is used to return to the step of determining the first meter box to which the small load user belongs based on the multidimensional feature sequence of each meter box in the target substation, the multidimensional feature sequence of each known user corresponding to each meter box, and the multidimensional feature sequence of the small load user in the target substation if the first meter box to which the small load user belongs is different from the second meter box, until the first meter box to which the small load user belongs is the same as the second meter box, and the first meter box is used as the meter box to which the small load user belongs.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Low-voltage transformer area undisturbed topology identification method and system, medium and terminal

    CN121355890A

  • A low-voltage area undisturbed topology identification method and system, medium and terminal

    CN121355890B