A method, device, terminal device and storage medium for identifying the topology of a low-voltage distribution network

Abstract

The present invention discloses a method, device, terminal device and storage medium for identifying the topology of a low-voltage distribution network. The method includes: ignoring the secondary equipment in the topology model of the low-voltage distribution network, and merging and deleting the branches in the topology model of the low-voltage distribution network to obtain a simplified topology model; constructing a power flow formula for describing the node power balance based on the low-voltage distribution network data in the simplified topology model, and constructing a topology identification model for the low-voltage distribution network according to the power flow formula for describing the node power balance; according to the characteristics of the distribution network system, using the topology identification model of the low-voltage distribution network to perform linear regression processing on the node data, and when the convergence condition is satisfied, outputting the network topology structure and line parameters of the distribution network. By ignoring the secondary equipment in the topology model of the low-voltage distribution network and merging and deleting specific branches, the present invention effectively reduces the data processing volume and processing difficulty, and can effectively improve the efficiency of topology identification of the low-voltage distribution network.

Description

Technical Field

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

[0002] For the stable operation of the power grid, power grid staff need to timely understand the topological structure of the power grid and the operating status of the entire network. The observability and controllability of the power grid are the keys to ensuring its safe and economic operation. In the intelligent distribution network advanced application software system, the identification and real-time update of the distribution network topology are crucial. The identification of the distribution network topology is an important part of the advanced application software of the distribution network management system and the basis for realizing various advanced auxiliary software functions in the distribution automation system, and can provide decision-making for power system dispatching.

[0003] The existing methods for identifying the topology of a low-voltage distribution network usually rely on manual regular inspection of all equipment and lines of the low-voltage distribution network to achieve the identification of the topology of the low-voltage distribution network. However, due to the large scale of the low-voltage distribution network, the inspection workload is large and time-consuming, resulting in low efficiency of identifying the topology of the low-voltage distribution network. Summary of the Invention

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

[0005] The present invention provides a method for identifying the topology of a low-voltage distribution network, including:

[0006] Neglect the secondary equipment in the topology model of the low-voltage distribution network, and merge and delete the branches in the topology model of the low-voltage distribution network to obtain a simplified topology model; wherein, the topology model of the low-voltage distribution network is constructed based on power system components;

[0007] Construct a power flow formula for describing the 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 the node power balance;

[0008] According to the characteristics of the distribution network system, perform linear regression processing on the node data by using the low-voltage distribution network topology identification model, and when the convergence condition is met, output the network topology structure and line parameters of the distribution network.

[0009] Further, the merging and deleting of the branches in the topology model of the low-voltage distribution network includes:

[0010] When deleting the connection point between two branches that are directly connected and have no other load connections in the low-voltage distribution network topology model, merge the two branches into one branch;

[0011] Delete the branch containing a switch in the low-voltage distribution network topology model.

[0012] Further, constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model includes:

[0013] Construct a node power equation based on the active power generated by the power source of the node, 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 nodes in the simplified topology model;

[0014] Convert the node power equation into a power flow formula for describing node power balance.

[0015] Further, 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 further includes:

[0016] Traverse each node in the low-voltage distribution network data. When traversing, 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;

[0017] Select a set of known data of nodes as sample data, and perform a regression operation on the partial correlation coefficient using the sample data to obtain an estimated value of each partial correlation coefficient;

[0018] 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 partial correlation coefficient, and the low-voltage distribution network data of the corresponding other nodes;

[0019] Fill in the low-voltage distribution network data of the central node according to the missing value.

[0020] Further, when performing a linear regression process on the node data using the low-voltage distribution network topology identification model, when the convergence condition is met, output the network topology structure and line parameters of the distribution network, including:

[0021] Input the node data into the low-voltage distribution network topology identification model; wherein, the node data includes the active power, reactive power, and voltage of the node;

[0022] Establish a regression model, perform linear regression processing on the distribution network data of the node, and determine the admittance matrix of the node;

[0023] When the regression model meets the convergence condition, solve the current admittance matrix and output the corresponding topological structure and line parameters.

[0024] Further, when solving the current admittance matrix, it includes:

[0025] If the ratio of the nodal 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 nodal conductance of the branch formed by the current node and another node is set to zero.

[0026] Further, after obtaining the network topological structure and line parameters of the distribution network, it further includes:

[0027] Based on the network topological structure and the line parameters, use the multi-granularity density peak clustering algorithm and the multivariate feature statistical detection algorithm to cluster the distribution network users, and obtain the affiliated substation information and phase information of each distribution network user.

[0028] The present invention also provides a low-voltage distribution network topology identification device, including:

[0029] A simplified topology model determination module, configured to ignore the secondary equipment in the low-voltage distribution network topology model, and perform merging and deletion processing on 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;

[0030] A low-voltage distribution network topology identification model construction module, configured 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;

[0031] A topology identification result output module, configured to perform linear regression processing on the node data by using the low-voltage distribution network topology identification model according to the characteristics of the distribution network system, and output the network topological structure and line parameters of the distribution network when the convergence condition is met.

[0032] 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. When the processor executes the computer program, the above-mentioned low-voltage distribution network topology identification method is implemented.

[0033] The present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the low-voltage distribution network topology identification method as described above.

[0034] By ignoring secondary equipment in the low-voltage distribution network topology model and merging and deleting specific branches, the present invention can reduce the secondary equipment and branches to be processed without affecting the low-voltage distribution network topology identification result, without the need for manual inspection of all equipment and branches of the distribution network, effectively reducing the data processing volume and processing difficulty, and can effectively improve the efficiency of low-voltage distribution network topology identification.

[0035] Furthermore, by setting a reasonable threshold, the present invention can effectively distinguish whether there is an actual connection between nodes. When the ratio of the node conductance to the self-conductance is less than the threshold, the branch conductance is set to zero at this time, which can avoid misjudgment of the connection relationship and can further reduce the complexity of the model, thereby further improving the efficiency of low-voltage distribution network topology identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a schematic flow chart of the low-voltage distribution network topology identification method provided by an embodiment of the present invention;

[0037] Figure 2 is a schematic flow chart of performing linear regression processing on node data provided by an embodiment of the present invention;

[0038] Figure 3 is a schematic diagram of dynamic programming of the DTW distance provided by an embodiment of the present invention;

[0039] Figure 4 is a schematic structural diagram of the low-voltage distribution network topology identification device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0041] In the description of the present application, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0042] In the description of the present application, it should be noted that unless otherwise clearly specified and limited, the terms "installed", "connected" and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0043] Please refer to Figure 1 , the present invention provides a method for identifying the topology of a low-voltage distribution network, including:

[0044] S1. Ignore the secondary equipment in the topology model of the low-voltage distribution network, and merge and delete the branches in the topology model of the low-voltage distribution network to obtain a simplified topology model; wherein, the topology model of the low-voltage distribution network is constructed based on power system components;

[0045] In the embodiments of the present invention, the power system components include feeders, substations, switch stations, distribution substations, transformers, and loads, etc. Among them, a feeder is a cable or wire that transports electric power from a power generation station to a substation, usually having a large power transmission capacity and transmission distance. In the electrical topology of a distribution network, the feeder is connected to the substation and the switch station. A substation is a place where high-voltage electric energy is converted into medium- and low-voltage electric energy, and it is also an important node in the distribution network. A substation usually includes three parts: a high-voltage side, a medium-voltage side, and a low-voltage side, responsible for receiving high-voltage electric energy from the feeder and converting it into medium- and low-voltage electric energy suitable for being transported to the switch station and the distribution substation. A switch station is a node that distributes electric energy to each distribution substation. It is usually a branch node connecting the feeder and the distribution substation. Switching equipment is usually installed inside the switch station to distribute electric energy to different distribution substations or transformers according to power demands. The main function of the switch station is to control the flow direction of electric energy and ensure the safe operation of the distribution network. A distribution substation is the final node in the distribution network, and its main function is to transport electric energy to the electrical equipment of each user. In a distribution substation, transformers, switching equipment, protection equipment, and metering equipment, etc. are usually installed to ensure the reliable transportation and accurate metering of electric energy. Finally, the user load is the end of the distribution network, that is, the place where electric energy is finally used for various electrical equipment. The size and type of the load vary, so the characteristics of the load need to be considered in the design and planning of the distribution network to ensure the stable supply and reasonable distribution of electric energy.

[0046] It should be noted that the topological analysis of the distribution network usually reduces the topological scale without changing the original topological connection relationship of the electrical components of the distribution network. The embodiments 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 relationships, and then perform simplification processing on this basis.

[0047] In the embodiments of the present invention, the secondary equipment includes relay protection equipment and monitoring equipment. The embodiments of the present invention ignore the secondary equipment in the low-voltage distribution network topological model and only consider the buses, branches, and lines where switching equipment that affects the topological structure exists, without considering all the equipment of the distribution network, thereby reducing the complexity of the topological structure and then being able to effectively improve the efficiency of topological identification.

[0048] S2. Construct a power flow formula for describing the node power balance based on the low-voltage distribution network data in the simplified topological model, and construct a low-voltage distribution network topological identification model according to the power flow formula for describing the node power balance;

[0049] The embodiments of the present invention construct a power flow formula based on the actual operation data of the low-voltage distribution network and the simplified topological model, and further construct a low-voltage distribution network topological identification model, which can ensure the consistency of the model with the actual operation state while reducing the processing volume of equipment and branches, thereby being able to effectively improve the accuracy of low-voltage distribution network topological identification.

[0050] S3. According to the characteristics of the distribution network system, linearly regress the node data using the low-voltage distribution network topology identification model, and when the convergence condition is met, output the network topology structure and line parameters of the distribution network.

[0051] Through linear regression processing in the embodiments of the present invention, the model parameters can be dynamically adjusted, enabling the low-voltage distribution network topology identification model to adapt to various complex scenarios in the low-voltage distribution network, thereby effectively improving the accuracy and reliability of the low-voltage distribution network topology identification and outputting accurate network topology structures and line parameters.

[0052] In one embodiment, step S1: Merge and delete branches in the low-voltage distribution network topology model, including:

[0053] S11. Delete the connection point between two directly connected branches in the low-voltage distribution network topology model that have no other load connections, and merge the two branches into one branch;

[0054] S12. Delete the branches containing switches in the low-voltage distribution network topology model.

[0055] In the embodiments of the present invention, when deleting the branch containing a switch, if the network does not split after deleting the branch, it indicates 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.

[0056] By ignoring the secondary equipment in the low-voltage distribution network topology model and merging and deleting specific branches in the embodiments of the present invention, the secondary equipment and branches to be processed can be reduced without affecting the low-voltage distribution network topology identification result, thereby effectively improving the efficiency of the low-voltage distribution network topology identification.

[0057] In one embodiment, step S2: Construct a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model, including:

[0058] S21. Based on the active power generated by the power source, reactive power generated by the power source, active power consumed by the load, reactive power consumed by the load, conductance matrix, susceptance matrix, voltage amplitude, and voltage phase angle difference between nodes in the simplified topology model, construct a node power equation;

[0059] In the embodiments of the present invention, the low-voltage distribution network data includes power, voltage, etc. The node power equation is constructed as follows:

[0060]

[0061] Among them, For node numbering , is the node where the active power and reactive power are generated by the power source, is the node where the active and reactive power consumed by the load is located, is the active power and reactive power injected into node ; , is the admittance matrix composed of the conductance and susceptance corresponding to the nodes and node ; , is the voltage amplitude of node and node ; is the voltage phase angle difference between node and node .

[0062] S22. Transform the node power equation into a power flow formula for describing node power balance.

[0063] In the embodiment of the present invention, the active power, reactive power, and voltage data in the distribution network can be obtained by smart meters. Therefore, the problem of solving the admittance matrix is transformed into the problem of solving , parameters, that is, transforming the node power equation into a power flow formula for describing node power balance, as follows:

[0064] .

[0065] In the embodiment of the present invention, a low-voltage distribution network topology identification model can be constructed based on the power flow formula for describing node power balance.

[0066] 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, further includes:

[0067] S201. Traverse each node in the low-voltage distribution network data. 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 and the corresponding partial correlation coefficients of the remaining nodes within the preset range of the central node;

[0068] In the embodiment of the present invention, arbitrarily select the low-voltage distribution network data of a node as the node data of the central node, and there are missing values in the node data of this central node. This node data has b adjacent nodes, which are successively , 。

[0069] In the embodiment of the present invention, the theoretical value of the node data of the central node has the following expression:

[0070]

[0071] where t represents the time, respectively represent the data sensed by the point at time t, is the partial correlation coefficient corresponding to , The influence degree of on can be reflected by

[0072] S202. Select a set of known data of nodes as sample data, and perform a regression operation on the partial correlation coefficient by using the sample data to obtain an estimated value of each partial correlation coefficient;

[0073] In the embodiment of the present invention, select groups of data as sample data, and perform a regression operation on the partial correlation coefficient through the sample data to obtain an estimated value of the partial correlation coefficient 。

[0074] S203. 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 fixed central node, the estimated value of each partial correlation coefficient, and the low-voltage distribution network data of the corresponding other nodes;

[0075] In the embodiment of the present invention, substitute the estimated value of the partial correlation coefficient into the expression of the theoretical value of the central node data to obtain the missing numerical value of the node data of the central node, as shown in the following formula:

[0076]

[0077] where, The estimated value of is represented by , and the true observed value of the point at time t is represented by

[0078] S204. Fill the low-voltage distribution network data of the central node according to the missing value.

[0079] In the embodiments of the present invention, the processing of steps S201 - S203 can be performed for each missing data to obtain the node data missing values of all central nodes, and each node data missing value is filled into the corresponding position in the low - voltage distribution network data, which can accurately complete the missing data of the low - voltage distribution network data, and further effectively improve the accuracy of low - voltage distribution network topology recognition.

[0080] In one embodiment, step S3: perform linear regression processing on the node data using the low - voltage distribution network topology recognition model, and when the convergence condition is met, output the network topology structure and line parameters of the distribution network, including:

[0081] S31: Input the node data into the low - voltage distribution network topology recognition model; wherein, the node data includes the active power, reactive power, and voltage of the node.

[0082] In the embodiments of the present invention, the objective function and constraint conditions of the low - voltage distribution network topology recognition model can be constructed. Specifically: solving the power flow formula for describing node power balance, it can be known that the minimum value of this formula is 0. Divide both sides by and after transformation, we get:

[0083]

[0084] When the distribution network system is in a steady state, the voltage phase angles between two nodes are small, and in the power flow equation, the trigonometric function is approximately considered , and the linearized power flow equation is obtained. The objective function is as follows:

[0085]

[0086] In the formula: , .

[0087] S32: Establish a regression model, perform linear regression processing on the distribution network data of the node, and determine the admittance matrix of the node.

[0088] In the embodiments of the present invention, the above matrices are the power and voltage data information collected at the same moment. , represents the approximate values of the conductance matrix and susceptance matrix, The solution of is expressed as:

[0089]

[0090] In order to obtain more accurate results, in the preliminary identification, the linear regression should adopt measurement values with a certain redundancy, that is, the 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, it is necessary to process the approximate admittance matrix, and the constraint conditions are set as shown in the following formula:

[0091]

[0092] Wherein: is a symmetric conductance matrix; is a symmetric susceptance matrix.

[0093] S33. When the regression model meets the convergence condition, solve the current admittance matrix and output the corresponding topological structure and line parameters.

[0094] In the embodiment of the present invention, a regression model is established through the active power, reactive power and voltage data of nodes, which can more comprehensively reflect the electrical relationship between nodes. Linear regression processing can accurately calculate the node admittance matrix, thereby accurately identifying the network topological structure; and using a linear regression model can reduce the complex processing of large-scale data, reduce the consumption of computing resources, and thus can effectively improve the efficiency of identifying the network topological structure and calculating the relevant line parameters.

[0095] In one embodiment, when solving the current admittance matrix in step S33, it includes:

[0096] If the ratio of the node conductance between the current node and another node to the self-conductance of the current guiding 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.

[0097] In the embodiment of the present invention, due to errors in the measured data obtained or deviations in the linear regression admittance matrix, there are noise data in the obtained admittance matrix, and the noise elements in the admittance matrix need to be removed to reduce the influence of noise on the topological identification result. The embodiment of the present invention can set a preset threshold , if on the branch is less than the set value , it is considered that the branch does not exist, and then the corresponding is zero Set as:

[0098]

[0099] Wherein, is the self-conductance of node ; —node , the conductance between.

[0100] In the embodiment of the present invention, the corresponding of the branch that meets the above threshold condition is set to zero, and the corresponding of the branch that does not meet the above threshold condition is not set to zero and is processed with the actual value.

[0101] In the embodiment of the present invention, the maximum number of branches connected to a node is n - 1. In a radial network and a weak loop network, the number of branches connected to a node is less than n - 1. During the initial identification process, 1 / (n - 1) is selected as the value, increasing the value to eliminate more incorrect branches. If the iteration result does not converge during the next precise identification process, it indicates that some branches existing in the original distribution network have been incorrectly deleted, and the size should be readjusted, decreasing the value until the iteration result converges. During the initial identification, the threshold is generally set to 0.05.

[0102] Please refer to Figure 2 for a schematic flowchart of a process for performing linear regression processing on node data provided by the embodiment of the present invention.

[0103] By setting a reasonable threshold in the embodiment of the present invention, it is possible to effectively distinguish whether there is an actual connection between nodes. When the ratio of the node conductance to the self-conductance is less than the threshold, the branch conductance is set to zero at this time, which can avoid misjudging the connection relationship and can further reduce the complexity of the model, thereby further improving the efficiency of low-voltage distribution network topology identification.

[0104] In one embodiment, after step S3 of obtaining the network topology structure and line parameters of the distribution network, it further includes:

[0105] S4. Based on the network topology structure and line parameters, using a multi-granularity density peak clustering algorithm and a multi-feature statistical detection algorithm to perform clustering processing on distribution network users, and obtaining the affiliated substation area information and phase information of each distribution network user.

[0106] In the embodiment of the present invention, a multi-granularity density peak clustering (DPC) and multi-feature statistical detection method is used to perform coarse-grained clustering on all users at the distribution transformer substation area level. By extracting appropriate data features, the similarity features of different phases within the same substation area are enhanced, and the interference of different-phase difference features within the same substation area is reduced, obtaining the affiliated substation area of each user, and further performing fine-grained clustering on the users in the same substation area to obtain the phase information of each user.

[0107] In the embodiment of the present invention, the DPC algorithm is an algorithm that can spontaneously calculate the clustering centers and achieve clustering for any distribution characteristics. The DPC algorithm follows two basic principles: ① The clustering centers are the sample points with the highest density in the local distribution of the data; ② The samples are divided into the categories of the nearest clustering centers to them. The calculation process is as follows:

[0108] Calculate the density of the sample point of , as shown below:

[0109]

[0110] In the formula: is the sample point and the distance between; is the truncation distance.

[0111] Find the neighborhood sample points that are closest to the sample point and have a density greater than according to the following formula .

[0112]

[0113] In the formula: is the minimum distance between the sample point and the samples with a density higher than . If there are no samples with a density higher than , then set the maximum value of the distances between and other samples as ; is the sample number of the samples with a density higher than .

[0114] Select the cluster centers. The cluster centers usually have a relatively high density and distance . Select the cluster centers by defining the normalized value:

[0115]

[0116]

[0117]

[0118] In the formula: , are the density vector and the distance vector respectively, is the number of samples; , are the normalized density vector and the distance vector respectively; the subscripts and represent the minimum and maximum values in the vectors respectively; represents the inner product of the vectors; ; is the unit vector.

[0119] Compared with non-cluster centers, the value of the cluster center is relatively large. It can be based on Judge the number of clustering centers based on the magnitude of the value and select the clustering centers.

[0120] In the embodiment of the present invention, a coarse-grained clustering model for identifying the household-transformer relationship can be established:

[0121] S401. Extract the coarse-grained features of the data: The kurtosis and skewness of the voltage fluctuation curve can be used to extract the coarse-grained features of the voltage sequence. The calculation formulas are as follows:

[0122]

[0123]

[0124] In the formula: is the deviation coefficient, which is set as in this paper; is the length of the voltage sequence within a period of time; is the th voltage value; is the mean value of the voltage sequence ; is the standard deviation of the voltage sequence ;

[0125] S402. Select the neighborhood: The k-nearest neighbor algorithm can be used to select the k samples that are closest to the kurtosis and skewness of each user sample as the neighborhood sample set.

[0126] S403. Calculate the sample density: The density of each sample in the neighborhood sample set obtained in the second step can be calculated according to the defined normalized value ;

[0127] S404. Complete the DPC algorithm clustering: Output the clustering result in the coarse-grained feature space, that is, the set of users included in each substation area , where is the clustering result of the substation area , is the number of substation areas.

[0128] In the embodiment of the present invention, assume 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 within the local time range between the two voltage sequences through dynamic programming to obtain the matching path between the data points, so as to minimize the global distance between the two voltage sequences. The DTW distance between the two voltage sequences is calculated as follows:

[0129]

[0130] Wherein: is the Euclidean distance between and in the s - th step matching path.

[0131] When calculating the DTW distance, the influence of the time delay magnitude is not considered. The schematic diagram of the dynamic programming of the DTW distance is as shown in Figure 3 shown.

[0132] The definition formula of the TDTW distance between two voltage sequences is:[[]]

[0133]

[0134] Wherein: is the time difference between and in the s - th step matching path.

[0135] In the same substation area, the heterogeneous characteristics between the user voltage data of different phases are mainly manifested as the local weak differences of the data. The DTW distance considers the local spatial similarity between the data, but ignores the influence of the local time delay effect between the data on the spatial similarity. The TDTW distance comprehensively considers the local spatial similarity and the local time delay effect of the data, which is more helpful for extracting the heterogeneous characteristics between different - phase data in the same substation area.[[ID=D39]]

[0136] In the embodiment of the present invention, the specific steps of using the fine - grained clustering method for user phase identification are as follows:

[0137] S411. Perform data max - min normalization processing.

[0138] S412. Calculate the TDTW distance.

[0139] S413. Calculate the neighborhood relationship based on the KNN algorithm. Use the KNN algorithm to select the k samples with the smallest TDTW distance from each sample as the neighborhood sample set.

[0140] S414. Calculate the sample density, and calculate the density of each sample in the neighborhood sample set obtained in the third step according to the defined normalized value

[0141] S415. Use the DPC algorithm for clustering and output the clustering result of the fine - grained feature space , where are the clustering results of phases A, B, and C in substation area i respectively. ​

[0142] In the embodiments of the present invention, through the multi-granularity density peak clustering algorithm, the features of user voltage data can be extracted at different granularity levels, thus more comprehensively reflecting the electrical characteristics of users; combined with the multi-feature statistical detection algorithm, multi-dimensional data such as voltage, current, and power can be comprehensively considered to further improve the accuracy of identification; and by optimizing the density calculation process through the dynamic time warping distance algorithm, the phase relationship of users can be more accurately identified, avoiding misjudgment caused by voltage fluctuations and noise interference.

[0143] Implementing the embodiments of the present invention has the following beneficial effects:

[0144] In the embodiments of the present invention, by ignoring the secondary equipment in the low-voltage distribution network topology model and merging and deleting specific branches, the secondary equipment and branches to be processed can be reduced without affecting the low-voltage distribution network topology recognition result, without the need for manual inspection of all equipment and branches of the distribution network, effectively reducing the data processing volume and processing difficulty, and effectively improving the efficiency of low-voltage distribution network topology recognition.

[0145] Furthermore, in the embodiments of the present invention, by setting a reasonable threshold, it is possible to effectively distinguish whether there is an actual connection between nodes. When the ratio of the node conductance to the self-conductance is less than the threshold, the branch conductance is set to zero at this time, which can avoid misjudging the connection relationship and can further reduce the complexity of the model, thereby further improving the efficiency of low-voltage distribution network topology recognition.

[0146] Please refer to Figure 4 , based on the same inventive concept as the above embodiments, the present invention also provides a low-voltage distribution network topology recognition device, including:

[0147] A simplified topology model determination module 10, configured to perform an ignoring process on the secondary equipment in the low-voltage distribution network topology model and perform a merging and deleting process on 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;

[0148] A low-voltage distribution network topology recognition model construction module 20, configured 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 recognition model according to the power flow formula for describing node power balance;

[0149] A topology recognition result output module 30, configured to perform linear regression processing on the node data by using the low-voltage distribution network topology recognition 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 condition is met.

[0150] In one embodiment, the simplified topology model determination module 10 is further configured to:

[0151] Delete the connection point between two branches that are directly connected and have no other load connections in the low-voltage distribution network topology model, and merge the two branches into one branch;

[0152] Delete the branch containing a switch in the low-voltage distribution network topology model.

[0153] In one embodiment, the low-voltage distribution network topology identification model construction module 20 is further configured to:

[0154] Based on the active power generated by the power source, 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 nodes in the simplified topology model, construct a node power equation;

[0155] Convert the node power equation into a power flow formula for describing node power balance.

[0156] In one embodiment, the device further includes a data completion module, which is used for:

[0157] Traverse each node in the low-voltage distribution network data. During the traversal, use 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 coefficients;

[0158] Select a set of known data of nodes as sample data, and perform a regression operation on the partial correlation coefficients using the sample data to obtain an estimated value of each partial correlation coefficient;

[0159] According to the theoretical value of the low-voltage distribution network data of the central node, the estimated value of each partial correlation coefficient, and the low-voltage distribution network data of the corresponding other nodes, determine the missing value of the low-voltage distribution network data of the central node;

[0160] Fill in the low-voltage distribution network data of the central node according to the missing value.

[0161] In one embodiment, the topology identification result output module 30 is further configured to:

[0162] Input the node data into the low-voltage distribution network topology identification model; wherein, the node data includes the active power, reactive power, and voltage of the node;

[0163] Establish a regression model, perform linear regression processing on the distribution network data of the node, and determine the admittance matrix of the node;

[0164] When the regression model meets the convergence condition, solve the current admittance matrix and output the corresponding topological structure and line parameters.

[0165] In one embodiment, when solving the current admittance matrix, it includes:

[0166] If the ratio of the nodal 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 the other node, and the nodal conductance of the branch formed by the current node and the other node is set to zero.

[0167] In one embodiment, the device further includes a clustering processing module for:

[0168] Based on the network topology structure 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.

[0169] Correspondingly, an embodiment of the present invention further 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. When the processor executes the computer program, the low-voltage distribution network topology identification method of any one of the above embodiments is implemented.

[0170] The terminal device of this embodiment includes: a processor, a memory, and computer programs and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, the various steps in the first embodiment above are implemented, such as Figure 1 The steps S1 to S3 shown. 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 construction module 20.

[0171] Exemplarily, the computer program can be divided into one or more modules / units. One or more modules / units are stored in the memory and executed by the processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing 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.

[0172] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the schematic diagram is only an example of the terminal device, and does not constitute a limitation on the terminal device. It may include more or fewer components than shown, or combine some components, or different components. For example, the terminal device may further include input / output devices, network access devices, a bus, etc.

[0173] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal device, and connects various parts of the entire terminal device through various interfaces and lines.

[0174] 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 by calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function, etc.; the data storage area may store data created according to the use of the mobile terminal, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0175] Among them, if the modules / units integrated in the terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included 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 electrical carrier signals and telecommunication signals.

[0176] Correspondingly, an embodiment of the present invention further provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the low-voltage distribution network topology identification method of any one of the above embodiments.

[0177] The above specific embodiments have further elaborated in detail the purpose, technical solution, 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 used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying the topology of a low-voltage distribution network, characterized in that, Including: Neglect 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; the merging and deleting process of the branches in the low-voltage distribution network topology model includes: deleting the connection point between two directly connected branches without other load connections in the low-voltage distribution network topology model, and merging the two branches into one branch; deleting the branches containing switches in the low-voltage distribution network topology model; Traverse each node in the low-voltage distribution network data. 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 coefficients; select a set of known data of nodes as sample data, and use the sample data to perform a regression operation on the partial correlation coefficients to obtain the 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 partial correlation coefficient, and the low-voltage distribution network data of the corresponding other nodes; fill the low-voltage distribution network data of the central node according to the missing value; Based on the low-voltage distribution network data in the simplified topology model, construct a power flow formula for describing node power balance, and construct a low-voltage distribution network topology identification model according to the power flow formula for describing node power balance; the constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model includes: based on the active power generated by the power source of the node, 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 nodes in the simplified topology model, construct a node power equation; transform the node power equation into a power flow formula for describing node power balance; According to the characteristics of the distribution network system, use the low-voltage distribution network topology identification model to perform linear regression processing on the node data, and when the convergence condition is met, output the network topology structure and line parameters of the distribution network.

2. The low-voltage distribution network topology identification method according to claim 1, wherein The 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: Input the node data into the low-voltage distribution network topology identification model; wherein, the node data includes the active power, reactive power, and voltage of the node; Establish a regression model, perform linear regression processing on the distribution network data of the node, and determine the admittance matrix of the node; When the regression model meets the convergence condition, solve the current admittance matrix and output the corresponding topology structure and line parameters.

3. The low-voltage distribution network topology identification method according to claim 2, wherein, When solving the current admittance matrix, including: If the ratio of the branch 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 the other node, and the branch conductance of the branch formed by the current node and the other node is set to zero.

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

5. A low-voltage distribution network topology identification device, characterized in that It includes: A simplified topology model determination module, configured to ignore the secondary equipment in the low-voltage distribution network topology model, and perform merging and deletion processing on 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; the merging and deletion processing on the branches in the low-voltage distribution network topology model includes: deleting the connection point between two directly connected branches without other load connections in the low-voltage distribution network topology model, and merging the two branches into one branch; deleting the branches containing switches in the low-voltage distribution network topology model; A data completion module, configured to traverse each node in the low-voltage distribution network data. During the traversal, the currently traversed node is used as the central node, and based on the low-voltage distribution network data of the remaining nodes within the preset range of the central node and the corresponding partial correlation coefficients, determine the theoretical value of the low-voltage distribution network data of the central node; select a set of known data of nodes as sample data, and use the sample data to perform a regression operation on the partial correlation coefficients to obtain the estimated value of each partial correlation coefficient; based on the theoretical value of the low-voltage distribution network data of the central node, the estimated value of each partial correlation coefficient, and the low-voltage distribution network data of the corresponding other nodes, determine the missing value of the low-voltage distribution network data of the central node; fill the low-voltage distribution network data of the central node according to the missing value; A low-voltage distribution network topology recognition model construction module, configured 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 recognition model according to the power flow formula for describing node power balance; the constructing a power flow formula for describing node power balance based on the low-voltage distribution network data in the simplified topology model includes: constructing a node power equation based on the active power generated by the power source of the node, 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 nodes in the simplified topology model; converting the node power equation into a power flow formula for describing node power balance; A topology recognition result output module, configured to perform linear regression processing on the node data using the low-voltage distribution network topology recognition model according to the characteristics of the distribution network system, and when the convergence condition is met, output the network topology structure and line parameters of the distribution network.

6. A terminal device, characterized in that, It includes: 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 described in any one of claims 1-4 is implemented.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program; wherein, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the low-voltage distribution network topology identification method described in any one of claims 1-4.

Images