Topology identification method and device for low-voltage power distribution network, terminal equipment and storage medium

Abstract

The invention discloses a low-voltage power distribution network topology identification method and device, terminal equipment and a storage medium, and the method comprises the steps: carrying out the neglect processing of secondary equipment in a low-voltage power distribution network topology model, and carrying out the merging and deletion processing of branches in the low-voltage power distribution network topology model, and obtaining a simplified topology model; constructing a power flow formula used for describing node power balance based on low-voltage distribution network data in the simplified topology model, and constructing a low-voltage distribution network topology identification model according to the power flow formula used for describing the node power balance; and according to system characteristics of the power distribution network, performing linear regression processing on the node data by using the low-voltage power distribution network topology identification model, and outputting a network topology structure and line parameters of the power distribution network when convergence conditions are met. According to the method, secondary equipment in the low-voltage power distribution network topology model is ignored, and specific branches are combined and deleted, so that the data processing amount and processing difficulty are effectively reduced, and the low-voltage power distribution network topology identification efficiency can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network, and in particular to a method, device, terminal equipment and storage medium for identifying low-voltage distribution network topology. Background Art

[0002] For the stable operation of the power grid, the grid staff needs to know the topology of the power grid and the operation status of the entire network in a timely manner. The observability and controllability of the power grid are the key to ensure its safe and economical operation. In the advanced application software system of the smart distribution network, the identification and real-time update of the distribution network topology are crucial. Distribution network topology identification is an important part of the advanced application software of the distribution network management system. It is the basis for the realization of various advanced auxiliary software functions in the distribution automation system and can provide decision-making for power system dispatching.

[0003] Existing low-voltage distribution network topology identification methods usually rely on manual regular inspections of all equipment and lines in the low-voltage distribution network to achieve low-voltage distribution network topology identification. However, due to the large scale of the low-voltage distribution network and the large and time-consuming inspection workload, the efficiency of low-voltage distribution network topology identification is low. Summary of the invention

[0004] The present invention provides a low-voltage distribution network topology identification method, device, terminal equipment and storage medium to solve the technical problem that the existing low-voltage distribution network topology identification method usually relies on manual regular inspection of all equipment and lines of the low-voltage distribution network to realize the low-voltage distribution network topology identification, but due to the large scale of the low-voltage distribution network, the inspection workload is large and time-consuming, resulting in low efficiency of low-voltage distribution network topology identification.

[0005] The present invention provides a low-voltage distribution network topology identification method, comprising: Ignore the secondary equipment in the low-voltage distribution network topology model, and merge and delete the branches in the low-voltage distribution network topology model to obtain a simplified topology model; wherein the low-voltage distribution network topology model is constructed based on power system components; Constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, and constructing a low-voltage distribution network topology identification model according to the power flow formula for describing node power balance; According to the characteristics of the distribution network system, the low-voltage distribution network topology identification model is used to perform linear regression processing on the node data, and when the convergence conditions are met, the network topology structure and line parameters of the distribution network are output.

[0006] Furthermore, the merging and deleting of branches in the low-voltage distribution network topology model includes: When deleting the contact point between two branches that are directly connected and have no other loads connected in the low-voltage distribution network topology model, the two branches are merged into one branch; The branch including the switch in the low-voltage distribution network topology model is deleted.

[0007] Furthermore, the power flow formula for describing the node power balance is constructed based on the low-voltage distribution network data in the simplified topology model, including: Constructing a node power equation based on the active power generated by the power source of the node in the simplified topology model, the reactive power generated by the power source, the active power consumed by the load, the reactive power consumed by the load, the conductance matrix, the susceptance matrix, the voltage amplitude and the voltage phase angle difference between the nodes; The node power equation is converted into a power flow formula for describing node power balance.

[0008] Furthermore, before constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, it also includes: Traverse each node in the low-voltage distribution network data, and during the traversal, take the currently traversed node as the central node, and determine the theoretical value of the low-voltage distribution network data of the central node according to the low-voltage distribution network data of the remaining nodes within the preset range of the central node and the corresponding partial correlation coefficient; Selecting a group of known data of nodes as sample data, and using the sample data to perform a regression operation on the partial correlation coefficient to obtain an estimated value of each partial correlation coefficient; Determine the missing value of the low-voltage distribution network data of the central node according to the theoretical value of the low-voltage distribution network data of the central node, the estimated value of each of the partial correlation coefficients and the corresponding low-voltage distribution network data of other nodes; According to the missing values, the low-voltage distribution network data of the central node is filled.

[0009] Furthermore, the low-voltage distribution network topology identification model is used to perform linear regression processing on the node data, and when the convergence condition is met, the network topology structure and line parameters of the distribution network are output, including: Inputting node data into the low-voltage distribution network topology identification model; wherein the node data includes active power, reactive power and voltage of the node; Establishing a regression model, performing linear regression processing on the distribution network data of the node, and determining the admittance matrix of the node; When the regression model meets the convergence condition, the current admittance matrix is ​​solved and the corresponding topological structure and line parameters are output.

[0010] Furthermore, when solving the current admittance matrix, it includes: If the ratio of the node conductance between the current node and another node to the self-conductance of the current node is less than a preset threshold, it is determined that there is no branch between the current node and another node, and the node conductance of the branch formed by the current node and another node is set to zero.

[0011] Furthermore, after obtaining the network topology and line parameters of the distribution network, it also includes: Based on the network topology and the line parameters, a multi-granularity density peak clustering algorithm and a multivariate feature statistical detection algorithm are used to cluster the distribution network users to obtain the affiliated substation information and phase information of each distribution network user.

[0012] The present invention also provides a low-voltage distribution network topology identification device, comprising: A simplified topology model determination module is used to ignore the secondary equipment in the low-voltage distribution network topology model, and merge and delete the branches in the low-voltage distribution network topology model to obtain a simplified topology model; wherein the low-voltage distribution network topology model is constructed based on power system components; A low-voltage distribution network topology identification model construction module, used to construct a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, and to construct a low-voltage distribution network topology identification model according to the power flow formula for describing node power balance; The topology identification result output module is used to perform linear regression processing on node data using the low-voltage distribution network topology identification model according to the characteristics of the distribution network system, and output the network topology structure and line parameters of the distribution network when the convergence conditions are met.

[0013] The present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the low-voltage distribution network topology identification method as described above when executing the computer program.

[0014] The present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the low-voltage distribution network topology identification method as described above.

[0015] The present invention ignores the secondary equipment in the low-voltage distribution network topology model and merges and deletes specific branches. This can reduce the secondary equipment and branches that need to be processed without affecting the low-voltage distribution network topology identification result. There is no need for manual inspection of all equipment and branches in the distribution network, which effectively reduces the data processing volume and processing difficulty, and can effectively improve the efficiency of low-voltage distribution network topology identification.

[0016] Furthermore, the present invention can effectively distinguish whether there is an actual connection between nodes by setting a reasonable threshold. When the ratio of node conductance to self-conductance is less than the threshold, the branch conductance is set to zero, which can avoid misjudgment of the connection relationship and further reduce the complexity of the model, thereby further improving the efficiency of low-voltage distribution network topology identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of a flow chart of a low-voltage distribution network topology identification method provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of a process of performing linear regression processing on node data provided by an embodiment of the present invention; Figure 3 is a schematic diagram of dynamic programming of DTW distance provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of a low-voltage distribution network topology identification device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0020] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0021] See also Figure 1 The present invention provides a low-voltage distribution network topology identification method, comprising: S1. Ignore the secondary equipment in the low-voltage distribution network topology model, merge and delete the branches in the low-voltage distribution network topology model, and obtain a simplified topology model; wherein the low-voltage distribution network topology model is constructed based on power system components; In an embodiment of the present invention, the power system elements include feeders, substations, switch stations, distribution stations, transformers and loads, etc., wherein the feeder is a cable or wire that transmits electricity from a power station to a substation, and usually has a large transmission capacity and transmission distance. In the electrical topology of the distribution network, the feeder connects the substation and the switch station. The substation is a place where high-voltage electric energy is converted into medium- and low-voltage electric energy, and is also an important node in the distribution network. The substation usually includes three parts: the high-voltage side, the medium-voltage side and the low-voltage side, which are responsible for receiving the high-voltage electric energy from the feeder and converting it into medium- and low-voltage electric energy suitable for transmission to the switch station and the distribution station. The switch station is a node that distributes electric energy to each distribution station. It is usually a branch node that connects the feeder and the distribution station. Switchgear is usually installed inside the switch station to distribute electric energy to different distribution stations or transformers according to power demand. The main function of the switch station is to control the flow of electric energy and ensure the safe operation of the distribution network. The distribution station is the final node in the distribution network, and its main function is to transmit electric energy to the power equipment of each user. In distribution stations, transformers, switchgear, protection equipment and metering equipment are usually installed to ensure reliable transmission and accurate metering of electric energy. Finally, user load is the end of the distribution network, that is, where the electric energy is finally used for various electrical equipment. The size and type of loads vary, so the characteristics of the loads need to be considered in the design and planning of the distribution network to ensure a stable supply and reasonable distribution of electric energy.

[0022] It should be noted that the topological analysis of the distribution network usually reduces the topological scale by analyzing the connection relationship of the electrical components of the distribution network without changing the original topological connection relationship. The embodiment of the present invention can construct a low-voltage distribution network topological model based on the characteristics of the above-mentioned power system components and the relevant connection relationship, and then simplify it on this basis.

[0023] In an embodiment of the present invention, the secondary equipment includes relay protection equipment and monitoring equipment. The embodiment of the present invention ignores the secondary equipment in the low-voltage distribution network topology model and only considers the busbars, branches, lines where switch devices exist, etc. that affect the topology structure. There is no need to consider all the equipment in the distribution network, thereby reducing the complexity of the topology structure and effectively improving the efficiency of topology identification.

[0024] S2. constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, and constructing a low-voltage distribution network topology identification model according to the power flow formula for describing node power balance; The embodiment of the present invention constructs a power flow formula based on the actual operation data of the low-voltage distribution network and a simplified topology model, and further constructs a low-voltage distribution network topology identification model, which can ensure that the model is consistent with the actual operation state while reducing the processing volume of equipment and branches, thereby effectively improving the accuracy of low-voltage distribution network topology identification.

[0025] S3. According to the characteristics of the distribution network system, the low-voltage distribution network topology identification model is used to perform linear regression processing on the node data. When the convergence conditions are met, the network topology structure and line parameters of the distribution network are output.

[0026] The embodiment of the present invention can dynamically adjust the model parameters through linear regression processing, so that the low-voltage distribution network topology identification model can adapt to various complex scenarios in the low-voltage distribution network, thereby effectively improving the accuracy and reliability of low-voltage distribution network topology identification and outputting accurate network topology structure and line parameters.

[0027] In one embodiment, step S1, merging and deleting branches in the low-voltage distribution network topology model, includes: S11, deleting the contact point between two branches that are directly connected and have no other loads connected in the low-voltage distribution network topology model, and merging the two branches into one branch; S12. Delete the branch including the switch in the low-voltage distribution network topology model.

[0028] In the embodiment of the present invention, when deleting a branch containing a switch, if the network does not split after deleting the branch, it means that the state of the switch in the branch does not affect the distribution network structure, and the branch can be deleted. If the network splits after deleting the branch, further classification processing can be performed.

[0029] The embodiment of the present invention ignores the secondary devices in the low-voltage distribution network topology model and merges and deletes specific branches, thereby reducing the secondary devices and branches that need to be processed without affecting the low-voltage distribution network topology identification result, thereby effectively improving the efficiency of low-voltage distribution network topology identification.

[0030] In one embodiment, step S2, constructing a power flow formula for describing node power balance based on low-voltage distribution network data in a simplified topology model, includes: S21, constructing a node power equation based on the active power generated by the power source of the node in the simplified topology model, the reactive power generated by the power source, the active power consumed by the load, the reactive power consumed by the load, the conductance matrix, the susceptance matrix, the voltage amplitude and the voltage phase angle difference between the nodes; In the embodiment of the present invention, the low-voltage distribution network data includes power, voltage, etc., and the node power equation is constructed as follows: in, Number the nodes , For Node The active power and reactive power generated by the power supply, For Node The active and reactive power consumed by the load, Injection node Active power and reactive power; , For Node With Node The admittance matrix composed of the corresponding conductance and admittance; , For Node ,node The voltage amplitude of For Node With Node The voltage phase angle difference between them.

[0031] S22. Convert the node power equation into a power flow formula for describing node power balance.

[0032] In the embodiment of the present invention, the active power, reactive power and voltage data in the distribution network can be obtained by the smart meter, so the problem of solving the admittance matrix is ​​transformed into solving it using the least squares method , The problem of parameters is to transform the node power equation into the power flow formula used to describe the node power balance, as shown below: .

[0033] In the embodiment of the present invention, a low-voltage distribution network topology identification model can be constructed based on a power flow formula for describing node power balance.

[0034] In one embodiment, before step S2, constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, the method further includes: S201, traversing each node in the low-voltage distribution network data, during the traversal, taking the currently traversed node as the central node, and determining the theoretical value of the low-voltage distribution network data of the central node according to the low-voltage distribution network data of the remaining nodes within the preset range of the central node and the corresponding partial correlation coefficient; In the embodiment of the present invention, the low-voltage distribution network data of the node is optionally taken As the node data of the central node, and the node data of the central node The data is missing. The node data has b adjacent nodes, which are , .

[0035] In the embodiment of the present invention, the theoretical value of the node data of the central node is The expression is as follows: Among them, t represents the time, Respectively indicate points The data perceived at time t, It corresponds to The partial correlation coefficient of right The impact can be measured through To reflect.

[0036] S202, selecting a group of known data of nodes as sample data, and using the sample data to perform a regression operation on the partial correlation coefficients to obtain an estimated value of each of the partial correlation coefficients; In the embodiment of the present invention, select Group Data As sample data, the partial correlation coefficient is Regression operation to obtain the estimated value of the partial correlation coefficient .

[0037] S203, determining the missing value of the low-voltage distribution network data of the central node according to the theoretical value of the low-voltage distribution network data of the central node, the estimated value of each of the partial correlation coefficients and the corresponding low-voltage distribution network data of other nodes; In this embodiment of the present invention, the estimated value of the partial correlation coefficient Substitute the theoretical value into the central node data In the expression of , the missing value of the node data of the central node is obtained as follows: in, The estimated value of Indicates, point The actual observation value at time t is express.

[0038] S204. Fill in the low-voltage distribution network data of the central node according to the missing values.

[0039] In an embodiment of the present invention, steps S201-S203 can be performed for each missing data to obtain the missing values ​​of the node data of all central nodes, and each missing value of the node data can be filled in the corresponding position in the low-voltage distribution network data, so as to accurately complete the actual data of the low-voltage distribution network data, thereby effectively improving the accuracy of low-voltage accessories network topology identification.

[0040] In one embodiment, step S3, using the low-voltage distribution network topology identification model to perform linear regression processing on the node data, and when the convergence condition is met, outputting the network topology structure and line parameters of the distribution network, includes: S31, inputting node data into a low-voltage distribution network topology identification model; wherein the node data includes active power, reactive power and voltage of the node; In the embodiment of the present invention, the objective function and constraint conditions of the low-voltage distribution network topology identification model can be constructed. Specifically, the power flow formula used to describe the node power balance is solved, and it is known that the minimum value of the formula is 0. Divide both sides by And after transformation we get: When the distribution network system is in a steady state, the voltage phase angle difference between the two nodes is small, and the trigonometric function in the power flow equation is approximately considered to be , we get the linearized power flow equation, and the objective function is as follows: Where: , .

[0041] S32, establishing a regression model, performing linear regression processing on the distribution network data of the node, and determining the admittance matrix of the node; In the embodiment of the present invention, the above matrix is ​​the power and voltage data information collected at the same time. , represents the approximate values ​​of the conductance matrix and the susceptance matrix, The solution is expressed as: In order to obtain more accurate results, linear regression in preliminary identification should use measurement values ​​with a certain degree of redundancy, that is, P, Q, and V information of multiple time sections. In order to meet the characteristic that the admittance matrix in the distribution network is always a symmetric matrix, the approximate admittance matrix needs to be processed, and the constraints are set as shown in the following formula: Where: is a symmetric conductivity matrix; is a symmetrical susceptance matrix.

[0042] S33. When the regression model meets the convergence condition, solve the current admittance matrix and output the corresponding topology structure and line parameters.

[0043] In the embodiment of the present invention, a regression model is established by using the active power, reactive power and voltage data of the nodes, which can more comprehensively reflect the electrical relationship between the nodes. Linear regression processing can accurately calculate the node admittance matrix, thereby accurately identifying the network topology; and the use of a linear regression model can reduce the complex processing of large-scale data and reduce the consumption of computing resources, thereby effectively improving the efficiency of identifying the network topology and calculating the relevant line parameters.

[0044] In one embodiment, when solving the current admittance matrix in step S33, it includes: If the ratio of the node conductance between the current node and another node to the self-conductance of the current node is less than a preset threshold, it is determined that there is no branch between the current node and another node, and the node conductance of the branch formed by the current node and another node is set to zero.

[0045] In the embodiment of the present invention, due to the error in the acquired measurement data or the deviation in the linear regression admittance matrix, the obtained admittance matrix contains noise data, and the noise elements in the admittance matrix need to be removed to reduce the impact of noise on the topology recognition result. The embodiment of the present invention can set a preset threshold , if the branch Less than the set value , it is considered that the branch does not exist, then the branch corresponding to Zero Set to: in, For Node The self-conductance of -node , The conductance between.

[0046] In the embodiment of the present invention, the branch that meets the above threshold condition corresponds to Set to zero, the branches that do not meet the above threshold conditions correspond to It is not set to zero and is processed with the actual value.

[0047] In the embodiment of the present invention, a node is connected to a maximum of n-1 branches. In a radial network and a weak ring network, the number of branches connected to a node is less than n-1. In the preliminary identification process, 1 / (n-1) is selected as value, increase If the iteration result does not converge in the next step of precise identification, it indicates that some branches in the original distribution network have been deleted by mistake and should be readjusted. Size, reduce The value of is adjusted until the iterative result converges. In the initial identification, the threshold is usually set =0.05.

[0048] See also Figure 2 , is a schematic diagram of a process of performing linear regression processing on node data provided by an embodiment of the present invention.

[0049] The embodiment of the present invention can effectively distinguish whether there is an actual connection between nodes by setting a reasonable threshold. When the ratio of node conductance to self-conductance is less than the threshold, the branch conductance is set to zero, which can avoid misjudgment of the connection relationship and further reduce the complexity of the model, thereby further improving the efficiency of low-voltage distribution network topology identification.

[0050] In one embodiment, after obtaining the network topology and line parameters of the distribution network in step S3, the method further includes: S4. Based on the network topology and line parameters, the multi-granularity density peak clustering algorithm and the multivariate feature statistical detection algorithm are used to cluster the distribution network users to obtain the affiliated substation information and phase information of each distribution network user.

[0051] In an embodiment of the present invention, a coarse-grained clustering method based on multi-granularity density peak clustering (DPC) and multivariate feature statistical detection is adopted to perform coarse-grained clustering of all users at the distribution transformer area level. By extracting appropriate data features, similar features of different phases in the same area are enhanced, and the interference of different features of different phases in the same area is reduced, the affiliated area of ​​each user is obtained, and the users in the same area are further fine-grained clustered to obtain the phase information of each user.

[0052] In the embodiment of the present invention, the DPC algorithm is an algorithm that can spontaneously calculate the cluster center and realize the clustering of arbitrary distribution features. The DPC algorithm follows two basic principles: ① The cluster center is the sample point with the highest density in the local distribution of data; ② The sample is divided into the category to which the cluster center closest to it belongs. The calculation process is as follows: Calculate sample points Density , as shown below: Where: For sample points and The distance between is the cutoff distance.

[0053] Find the distance sample points according to the following formula closest and with density greater than Neighborhood sample points .

[0054] Where: For sample points With density higher than The minimum distance between samples if there is no density higher than , then the sample The maximum distance between the samples is set to ; For density higher than The sample number.

[0055] Select the cluster center. The cluster center usually has a larger density. and distance , by defining the normalized Value to select cluster center: Where: , are density vector and distance vector respectively, is the sample size; , are the normalized density vector and distance vector respectively; subscript and Represent the minimum and maximum values ​​in the vector respectively; represents the inner product of vectors; ; is a unit vector.

[0056] Compared with non-cluster centers, cluster centers The value is large, and can be based on The size of the value determines the number of cluster centers and selects the cluster center.

[0057] In an embodiment of the present invention, a coarse-grained clustering model for household change relationship identification may be established: S401. Extracting coarse-grained features of data: The kurtosis of the voltage fluctuation curve can be used. and skewness Extract the coarse-grained features of the voltage series, The calculation formulas are: Where: is the deviation coefficient, and this paper sets ; is the voltage sequence over a period of time Length; For the Voltage value; The voltage sequence The mean of The voltage sequence The standard deviation of .

[0058] S402, selecting neighborhood: a k-nearest neighbor algorithm may be used to select, for each user sample, k samples that are closest to its kurtosis and skewness as a neighborhood sample set.

[0059] S403, calculate sample density: according to the normalized value after definition Calculate the density of each sample in the neighborhood sample set obtained in the second step.

[0060] S404, complete DPC algorithm clustering: output clustering results in the coarse-grained feature space, that is, the set of users included in each area ,in For Taiwan The clustering result of is the number of stations.

[0061] In the embodiment of the present invention, it is assumed that there are two voltage fluctuation sequences: and , where n' and m' are the lengths of the two voltage sequences respectively. The DTW algorithm adjusts the corresponding relationship of the data in the local time range between the two voltage sequences through dynamic programming to obtain the matching path between the data points. , so that the global distance between the two voltage sequences is minimized. DTW distance between two voltage sequences The calculation formula is: Where: Match the path in step s and The Euclidean distance between .

[0062] When calculating the DTW distance, Without considering the influence of time delay, the dynamic programming diagram of DTW distance is as follows: Figure 3 shown.

[0063] TDTW distance between two voltage sequences The definition of is: Where: Match the path in step s and The time difference between.

[0064] In the same substation, the heterogeneous features between user voltage data of different phases are mainly manifested as local slight differences in the data. The DTW distance considers the local spatial similarity between data, but ignores the impact of the local time delay effect between data on spatial similarity. The TDTW distance comprehensively considers the local spatial similarity and local time delay effect of data, which is more helpful to extract heterogeneous features between different related data in the same substation.

[0065] In the embodiment of the present invention, the specific steps of using the fine-grained clustering method to perform user phase identification are as follows: S411, perform data max-min normalization processing.

[0066] S412: Calculate the TDTW distance.

[0067] S413, calculate the neighborhood relationship based on the KNN algorithm. Use the KNN algorithm to select k samples with the smallest TDTW distance from each sample as the neighborhood sample set.

[0068] S414, calculate the sample density, according to the normalized value after definition Calculate the density of each sample in the neighborhood sample set obtained in the third step.

[0069] S415, use DPC algorithm to perform clustering and output the clustering results of fine-grained feature space ,in They are the clustering results of phases A, B, and C in station area i, respectively.

[0070] The embodiment of the present invention uses a multi-granularity density peak clustering algorithm to extract the characteristics of user voltage data at different granularity levels, thereby more comprehensively reflecting the user's electrical characteristics; combined with a multivariate feature statistical detection algorithm, it can comprehensively consider multi-dimensional data such as voltage, current, and power to further improve the accuracy of recognition; and through the dynamic time bending distance algorithm to optimize the density calculation process, it can more accurately identify the user's phase relationship and avoid misjudgment caused by voltage fluctuations and noise interference.

[0071] The implementation of the embodiments of the present invention has the following beneficial effects: The embodiment of the present invention ignores the secondary equipment in the low-voltage distribution network topology model, and merges and deletes specific branches. This can reduce the secondary equipment and branches that need to be processed without affecting the low-voltage distribution network topology identification result. There is no need for manual inspection of all equipment and branches in the distribution network, which effectively reduces the data processing volume and processing difficulty, and can effectively improve the efficiency of low-voltage distribution network topology identification.

[0072] Furthermore, the embodiment of the present invention can effectively distinguish whether there is an actual connection between nodes by setting a reasonable threshold. When the ratio of node conductance to self-conductance is less than the threshold, the branch conductance is set to zero, which can avoid misjudgment of the connection relationship and further reduce the complexity of the model, thereby further improving the efficiency of low-voltage distribution network topology identification.

[0073] See also Figure 4 Based on the same inventive concept as the above embodiment, the present invention also provides a low-voltage distribution network topology identification device, comprising: The simplified topology model determination module 10 is used to ignore the secondary equipment in the low-voltage distribution network topology model, and merge and delete the branches in the low-voltage distribution network topology model to obtain a simplified topology model; wherein the low-voltage distribution network topology model is constructed based on power system components; A low-voltage distribution network topology identification model construction module 20 is used to construct a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, and to construct a low-voltage distribution network topology identification model according to the power flow formula for describing node power balance; The topology identification result output module 30 is used to perform linear regression processing on the node data using the low-voltage distribution network topology identification model according to the characteristics of the distribution network system, and output the network topology structure and line parameters of the distribution network when the convergence conditions are met.

[0074] In one embodiment, the simplified topology model determination module 10 is further configured to: In the low-voltage distribution network topology model, the contact point between two branches that are directly connected and have no other load connections is deleted, and the two branches are merged into one branch; Delete the branch containing the switch in the low-voltage distribution network topology model.

[0075] In one embodiment, the low voltage distribution network topology identification model building module 20 is further used for: Constructing a node power equation based on the active power generated by the power source of the node in the simplified topology model, the reactive power generated by the power source, the active power consumed by the load, the reactive power consumed by the load, the conductance matrix, the susceptance matrix, the voltage amplitude and the voltage phase angle difference between the nodes; The node power equation is converted into a power flow formula for describing the node power balance.

[0076] In one embodiment, the device further includes a data completion module, which is used to: Traverse each node in the low-voltage distribution network data, and during the traversal, take the currently traversed node as the central node, and determine the theoretical value of the low-voltage distribution network data of the central node according to the low-voltage distribution network data of the remaining nodes within the preset range of the central node and the corresponding partial correlation coefficient; Selecting a group of known data of nodes as sample data, and performing a regression operation on the partial correlation coefficient using the sample data to obtain an estimated value of each partial correlation coefficient; Determine the missing value of the low-voltage distribution network data of the central node according to the theoretical value of the low-voltage distribution network data of the central node, the estimated value of each of the partial correlation coefficients and the corresponding low-voltage distribution network data of other nodes; According to the missing values, the low-voltage distribution network data of the central node is filled.

[0077] In one embodiment, the topology recognition result output module 30 is further used to: Inputting node data into a low-voltage distribution network topology identification model; wherein the node data includes active power, reactive power and voltage of the node; Establish a regression model, perform linear regression processing on the node's distribution network data, and determine the node's admittance matrix; When the regression model meets the convergence condition, the current admittance matrix is ​​solved and the corresponding topology structure and line parameters are output.

[0078] In one embodiment, when solving the current admittance matrix, it includes: If the ratio of the node conductance between the current node and another node to the self-conductance of the current node is less than a preset threshold, it is determined that there is no branch between the current node and another node, and the node conductance of the branch formed by the current node and another node is set to zero.

[0079] In one embodiment, the device further includes a clustering processing module, which is used to: Based on the network topology and line parameters, the multi-granularity density peak clustering algorithm and the multivariate feature statistical detection algorithm are used to cluster the distribution network users, and the affiliated substation information and phase information of each distribution network user are obtained.

[0080] Correspondingly, an embodiment of the present invention also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the low-voltage distribution network topology identification method of any one of the above embodiments.

[0081] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above embodiment 1 is implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment are implemented, such as the low-voltage distribution network topology identification model building module 20 .

[0082] Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device. For example, the low-voltage distribution network topology identification model construction module 20 is used to construct a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, and construct a low-voltage distribution network topology identification model according to the power flow formula for describing node power balance.

[0083] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0084] The processor may be a central processing unit (CPU), 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. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0085] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also 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 volatile solid-state storage devices.

[0086] Among them, if the module / unit integrated in the terminal device 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 processes 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 various 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 capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0087] Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the low-voltage distribution network topology identification method as described in any one of the above embodiments.

[0088] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying low voltage distribution network topology, characterized in that: include: Ignore the secondary equipment in the low-voltage distribution network topology model, and merge and delete the branches in the low-voltage distribution network topology model to obtain a simplified topology model; wherein the low-voltage distribution network topology model is constructed based on power system components; Constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, and constructing a low-voltage distribution network topology identification model according to the power flow formula for describing node power balance; According to the characteristics of the distribution network system, the low-voltage distribution network topology identification model is used to perform linear regression processing on the node data, and when the convergence conditions are met, the network topology structure and line parameters of the distribution network are output.

2. The low voltage distribution network topology identification method according to claim 1, characterized in that: The merging and deleting of branches in the low-voltage distribution network topology model includes: Deleting the contact point between two branches that are directly connected and have no other loads connected in the low-voltage distribution network topology model, and merging the two branches into one branch; The branch including the switch in the low-voltage distribution network topology model is deleted.

3. The low voltage distribution network topology identification method according to claim 1, characterized in that: The power flow formula for describing the node power balance is constructed based on the low-voltage distribution network data in the simplified topology model, including: Constructing a node power equation based on the active power generated by the power source of the node in the simplified topology model, the reactive power generated by the power source, the active power consumed by the load, the reactive power consumed by the load, the conductance matrix, the susceptance matrix, the voltage amplitude and the voltage phase angle difference between the nodes; The node power equation is converted into a power flow formula for describing node power balance.

4. The low voltage distribution network topology identification method according to claim 1, characterized in that: Before constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, it also includes: Traverse each node in the low-voltage distribution network data, and during the traversal, take the currently traversed node as the central node, and determine the theoretical value of the low-voltage distribution network data of the central node according to the low-voltage distribution network data of the remaining nodes within the preset range of the central node and the corresponding partial correlation coefficient; Selecting a group of known data of nodes as sample data, and performing a regression operation on the partial correlation coefficient using the sample data to obtain an estimated value of each partial correlation coefficient; Determine the missing value of the low-voltage distribution network data of the central node according to the theoretical value of the low-voltage distribution network data of the central node, the estimated value of each of the partial correlation coefficients and the corresponding low-voltage distribution network data of other nodes; According to the missing values, the low-voltage distribution network data of the central node is filled.

5. The low voltage distribution network topology identification method according to claim 1, characterized in that: The method of performing linear regression processing on node data using the low-voltage distribution network topology identification model and outputting the network topology structure and line parameters of the distribution network when the convergence condition is met includes: Inputting node data into the low-voltage distribution network topology identification model; wherein the node data includes active power, reactive power and voltage of the node; Establishing a regression model, performing linear regression processing on the distribution network data of the node, and determining the admittance matrix of the node; When the regression model meets the convergence condition, the current admittance matrix is ​​solved and the corresponding topological structure and line parameters are output.

6. The low voltage distribution network topology identification method according to claim 5, characterized in that: When solving the current admittance matrix, it includes: If the ratio of the node conductance between the current node and another node to the self-conductance of the current node is less than a preset threshold, it is determined that there is no branch between the current node and another node, and the node conductance of the branch formed by the current node and another node is set to zero.

7. The low voltage distribution network topology identification method according to claim 1, characterized in that: After obtaining the network topology and line parameters of the distribution network, it also includes: Based on the network topology and the line parameters, a multi-granularity density peak clustering algorithm and a multivariate feature statistical detection algorithm are used to cluster the distribution network users to obtain the affiliated substation information and phase information of each distribution network user.

8. A low voltage distribution network topology identification device, characterized in that: include: A simplified topology model determination module is used to ignore the secondary equipment in the low-voltage distribution network topology model, and merge and delete the branches in the low-voltage distribution network topology model to obtain a simplified topology model; wherein the low-voltage distribution network topology model is constructed based on power system components; A low-voltage distribution network topology identification model construction module, used to construct a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, and to construct a low-voltage distribution network topology identification model according to the power flow formula for describing node power balance; The topology identification result output module is used to perform linear regression processing on node data using the low-voltage distribution network topology identification model according to the characteristics of the distribution network system, and output the network topology structure and line parameters of the distribution network when the convergence conditions are met.

9. A terminal device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the low-voltage distribution network topology identification method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the low-voltage distribution network topology identification method according to any one of claims 1 to 7.

Images