Power distribution network topological structure identification method, device, equipment and medium
By obtaining the power data of the user monitoring terminal and transformer, establishing mathematical models and using genetic algorithms to optimize, the problems of low economy and local optimality in the existing technology are solved, and efficient and accurate identification of distribution network topology is achieved.
Patent Information
- Application Number
- CN202510683942.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-26
- Publication Date
- 2025-08-26
AI Technical Summary
In the prior art, the distribution network topology recognition method relies on additional devices to lead to low economic efficiency, the convex optimization approximate solution results are different from the actual situation, and it is easy to fall into local optimal problems.
By obtaining the power data of the user's monitoring terminal and transformer, a mathematical model based on the actual topological connection relationship is established, and a genetic algorithm is used to iteratively update the population, and the topological matrix is optimized using Gray code encoding and fitness calculation to avoid local optimization and gradually approximate the real topological structure.
It improves the accuracy and solution efficiency of topological structure identification, reduces costs, and adapts to the management needs of dynamic changes in the distribution network.
Smart Images
Figure CN120542011A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power systems, and in particular to a method, device, equipment and medium for identifying the topology of a distribution network. Background Art
[0002] In modern power systems, stable operation of the distribution network is a prerequisite for ensuring that users obtain high-quality electricity, and accurate understanding of the topological structure of the distribution network is the key foundation for realizing regional intelligent management. However, the frequent expansion, transformation and operation adjustments of the distribution network lead to delayed or inaccurate records. Traditional manual verification and recording methods face the challenges of high cost, low efficiency and difficulty in ensuring accuracy.
[0003] The existing technology mainly uses power carrier communication and pulse current method to identify distribution network topology. Since power carrier communication is affected by distributed capacitance and external environmental interference, the signal attenuation affects the topology identification accuracy of users far away from the transformer. The pulse current method is technically complex and requires the installation of a large number of additional equipment and instruments, which is less economical. In addition, the topology matrix solution in the existing scheme is often approximated as a convex optimization problem. Therefore, there are problems such as affected identification accuracy, poor economy, and the discrepancy between the solution results and the actual situation. Summary of the Invention
[0004] The present invention provides a distribution network topology structure identification method, device, equipment and medium, which can solve the problems in the prior art such as reliance on additional devices resulting in low economy, the discrepancy between the approximate solution results of convex optimization and the actual situation, and the susceptibility to falling into local optimality.
[0005] In a first aspect, an embodiment of the present invention provides a method for identifying a distribution network topology, comprising:
[0006] Obtaining first user monitoring terminal power data of each user monitoring terminal in the distribution network, and obtaining first transformer power data of each transformer;
[0007] Establishing a mathematical model based on the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained based on the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship;
[0008] According to the mathematical model, a genetic algorithm is used to iteratively update the population until the optimal individual in the current iteration population meets the preset requirements or the current iteration number reaches the preset iteration number, and the optimal individual in the current iteration population is output;
[0009] The topology of the power distribution network is determined according to the output optimal individual.
[0010] Compared with the prior art, the above embodiments have the following beneficial effects: the present application obtains the power data of the user monitoring terminal and the transformer, establishes a mathematical model based on the actual topological connection relationship, avoids dependence on additional devices, reduces costs and improves data utilization efficiency; adopts a genetic algorithm to iteratively optimize the population, and utilizes its global search characteristics to effectively avoid falling into the local optimum, ensuring that the solution process can more accurately approximate the actual topological structure, and at the same time gradually selects the optimal individuals through the iterative mechanism, thereby improving the accuracy of topological structure identification and solution efficiency, so that the method can more efficiently and reliably determine the distribution network topology structure, and adapt to the management needs of dynamic changes in the distribution network.
[0011] As a preferred example of the first aspect, the obtaining of first user monitoring terminal power data of each user monitoring terminal in the distribution network and the obtaining of first transformer power data of each transformer are specifically as follows:
[0012] Obtaining second terminal power data of each user monitoring terminal in the distribution network, and obtaining second transformer power data of each transformer;
[0013] Newton interpolation is used to process missing values in the second terminal power data and the second transformer power data to obtain third terminal power data and third transformer power data, and time series of the third terminal power data and the third transformer power data are unified through a time interval sampling method to obtain first user monitoring terminal power data and first transformer power data.
[0014] In this preferred example, by acquiring power data from user monitoring terminals and transformers and using Newton interpolation to handle missing data values, the power data of different devices at different time points can be effectively supplemented, ensuring data integrity and continuity. By unifying the time series through time interval sampling, the problem of inconsistent time nodes across different devices is eliminated, making the power data consistent and comparable in the time dimension. The above operations improve the quality and availability of input data, providing a reliable data foundation for the subsequent establishment of accurate mathematical models and efficient iterative optimization of genetic algorithms, avoiding analytical errors caused by missing data or inconsistent time series, and thus improving the accuracy and stability of distribution network topology identification.
[0015] As a preferred example of the first aspect, a mathematical model is established according to the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained according to the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship, and are specifically:
[0016] The constraint conditions of the mathematical model are expressed as follows:
[0017]
[0018] Where a is the total number of transformers; b is the total number of user monitoring terminals; Indicates that at t k At time t, the topological connection relationship between the jth user monitoring terminal and the i-th transformer is 1 when connected and 0 when not connected; Indicates that the jth user monitoring terminal is at t k The power at the moment is obtained based on the power data of the first user monitoring terminal; Indicates that the i-th transformer is at t k The power at the moment is obtained based on the first transformer power data;
[0019] The objective function of the mathematical model is expressed as follows:
[0020] min(||Y-WX||2)
[0021] Where W is In matrix form, Y is The matrix form of X is Matrix form of .
[0022] In this preferred example, a mathematical model containing constraints and an objective function is constructed, using binary variables to accurately characterize the connection status between the user monitoring terminal and the transformer, ensuring that the model strictly adheres to the physical logic of the distribution network topology. Next, this application uses the L2 norm to quantify the difference between the transformer power prediction value and the actual measured value, transforming the topology identification problem into a computable optimization problem, enabling the solution process to approximate the actual topology in a data-driven manner. This model uniformly describes the power data and connection relationship in matrix form, providing a clear optimization target and feasible solution space for the genetic algorithm.
[0023] As a preferred example of the first aspect, the genetic algorithm is used to iteratively update the population according to the mathematical model, specifically:
[0024] Performing binary Gray code encoding on the topological matrix to be solved in the mathematical model to obtain an initial population; wherein the initial population includes information of a plurality of individuals;
[0025] The fitness of each individual information in the initial population is calculated using a fitness calculation method, and according to the fitness of each individual information, the current iterative population is selected, crossed and mutated to obtain an updated population.
[0026] In this preferred example, the present invention encodes the topological matrix through binary Gray code, converts complex topological problems into discrete spaces that can be processed by genetic algorithms, and uses the characteristics of Gray code to improve search efficiency; through fitness-driven selection, crossover and mutation operations, the population is dynamically optimized to achieve a balance between global search and local optimization, efficiently approximate the real topological structure, and improve recognition accuracy and robustness.
[0027] As a preferred example of the first aspect, the fitness calculation method is used to calculate the fitness of each individual information in the initial population, specifically:
[0028] The fitness calculation method is used to calculate the fitness of each individual information in the initial population. The formula of the fitness calculation method is as follows:
[0029]
[0030] Among them, f is the fitness function, Y is The matrix form of X is In matrix form, W1 is the decoding matrix of the individual information of the current iteration.
[0031] In this preferred example, by converting the power difference between the transformer and the user monitoring terminal into a fitness metric and quantifying the individual performance using the inverse of the L2 norm, the fitness value directly reflects the degree of match between the topology matrix and the actual power data. Individuals with high fitness, corresponding to smaller prediction errors, are prioritized during the genetic algorithm selection process, guiding the population to evolve towards a topology that approximates the true topology. This fitness calculation method provides a clear optimization target for genetic operations, ensuring that the algorithm can effectively select a topology matrix that conforms to the energy flow patterns of the distribution network.
[0032] In a second aspect, the present invention provides a distribution network topology identification device, comprising: a data acquisition module, a model building module, an iterative update module, and a result determination module;
[0033] The data acquisition module is used to obtain the first user monitoring terminal power data of each user monitoring terminal in the distribution network and obtain the first transformer power data of each transformer;
[0034] The model building module is configured to establish a mathematical model based on the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained based on the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship;
[0035] The iterative update module is used to iteratively update the population using a genetic algorithm according to the mathematical model until the optimal individual in the current iteration population meets the preset requirements or the current iteration number reaches the preset iteration number, and output the optimal individual in the current iteration population;
[0036] The result determination module is used to determine the topology of the distribution network according to the output optimal individual.
[0037] As a preferred example of the second aspect, the data acquisition module includes a data acquisition unit and a data processing unit;
[0038] The data acquisition unit is used to acquire the second terminal power data of each user monitoring terminal in the distribution network and acquire the second transformer power data of each transformer;
[0039] The data processing unit is used to use Newton interpolation method to process missing values in the second terminal power data and the second transformer power data to obtain third terminal power data and third transformer power data, and unify the time series of the third terminal power data and the third transformer power data through a time interval sampling method to obtain first user monitoring terminal power data and first transformer power data.
[0040] As a preferred example of the second aspect, a mathematical model is established according to the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained according to the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship, and are specifically:
[0041] The constraint conditions of the mathematical model are expressed as follows:
[0042]
[0043] Where a is the total number of transformers; b is the total number of user monitoring terminals; Indicates that at t k At time t, the topological connection relationship between the jth user monitoring terminal and the i-th transformer is 1 when connected and 0 when not connected; Indicates that the jth user monitoring terminal is at t k The power at the moment is obtained based on the power data of the first user monitoring terminal; Indicates that the i-th transformer is at t k The power at the moment is obtained based on the first transformer power data;
[0044] The objective function of the mathematical model is expressed as follows:
[0045] min(||Y-WX||2)
[0046] Where W is In matrix form, Y is The matrix form of X is Matrix form of .
[0047] As a preferred example of the second aspect, the iterative update module includes an initial unit and an update unit;
[0048] The initial unit is used to perform binary Gray code encoding on the topological matrix to be solved in the mathematical model to obtain an initial population; wherein the initial population includes information of a plurality of individuals;
[0049] The updating unit is used to calculate the fitness of each individual information in the initial population using a fitness calculation method, and perform selection, crossover and mutation on the current iterative population according to the fitness of each individual information to obtain an updated population.
[0050] As a preferred example of the second aspect, the fitness calculation method is used to calculate the fitness of each individual information in the initial population, specifically:
[0051] The fitness calculation method is used to calculate the fitness of each individual information in the initial population. The formula of the fitness calculation method is as follows:
[0052]
[0053] Among them, f is the fitness function, Y is The matrix form of X is In matrix form, W1 is the decoding matrix of the individual information of the current iteration.
[0054] In summary, this application obtains power data from user monitoring terminals and transformers, establishes a mathematical model based on the actual topological connection relationship, avoids dependence on additional devices, reduces costs and improves data utilization efficiency; uses a genetic algorithm to iteratively optimize the population, and uses its global search characteristics to effectively avoid falling into local optimality, ensuring that the solution process can more accurately approximate the actual topological structure. At the same time, the optimal individuals are gradually screened out through an iterative mechanism, which improves the accuracy of topological structure identification and solution efficiency, enabling the method to more efficiently and reliably determine the distribution network topology structure and adapt to the management needs of dynamic changes in the distribution network.
[0055] Another embodiment of the present invention further 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. When the processor executes the computer program, the steps of the distribution network topology identification method of the present invention are implemented.
[0056] Another embodiment of the present invention further provides a computer-readable storage medium item, comprising: a stored computer program, which controls the device where the computer-readable storage medium is located to execute the steps of the distribution network topology identification method of the present invention when the computer program is running. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the implementation. Obviously, the drawings described below are only some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0058] Figure 1 A schematic flow chart of an embodiment of a method for identifying a distribution network topology provided by the present invention;
[0059] Figure 2 A cyclic iteration flow chart of a genetic algorithm of an embodiment of a method for identifying a distribution network topology provided by the present invention;
[0060] Figure 3 A schematic diagram of crossover and mutation operations in a genetic algorithm of an embodiment of a method for identifying a distribution network topology provided by the present invention;
[0061] Figure 4 This is a module structure diagram of an embodiment of a distribution network topology identification device provided by the present invention. DETAILED DESCRIPTION
[0062] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.
[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.
[0064] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.
[0065] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0066] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.
[0067] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).
[0068] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.
[0069] The distribution network topology refers to the electrical connection relationship between various devices (such as transformers, smart meters, lines, etc.) in the low-voltage distribution network. It is usually represented in the form of "node-edge", where "node" is the device (such as transformer, user terminal) and "edge" is the physical connection between devices.
[0070] Example 1
[0071] See also Figure 1In order to solve the problems in the prior art that the reliance on additional devices leads to low economic efficiency, the discrepancy between the approximate solution of convex optimization and the actual situation, and the tendency to fall into local optimality, an embodiment of the present invention provides a method for identifying the topology of a distribution network, comprising:
[0072] S1. Obtain first user monitoring terminal power data of each user monitoring terminal in the distribution network, and obtain first transformer power data of each transformer;
[0073] Furthermore, in some embodiments of the present application, the obtaining of the first user monitoring terminal power data of each user monitoring terminal in the distribution network and the obtaining of the first transformer power data of each transformer are specifically as follows:
[0074] Obtaining second terminal power data of each user monitoring terminal in the distribution network, and obtaining second transformer power data of each transformer;
[0075] Newton interpolation is used to process missing values in the second terminal power data and the second transformer power data to obtain third terminal power data and third transformer power data, and time series of the third terminal power data and the third transformer power data are unified through a time interval sampling method to obtain first user monitoring terminal power data and first transformer power data.
[0076] Specifically, in order to fully explain the above steps, the following scheme is used as an example:
[0077] There are a transformers and b user terminal smart meters (i.e. user monitoring terminals) in the distribution network. The power of each user terminal smart meter is recorded as [x1, x2, x3, ..., x b ], the power of each transformer is recorded as [y1,y2,y3,...,y a ] and record the corresponding relationship between the power of different devices and time nodes.
[0078] In view of the fact that there is a small amount of power missing in the extracted voltage time series, and different users may have data missing at different time nodes, and the time nodes of power recorded by different devices are not uniform, the Newton interpolation method is used to process the missing data. The interpolation method is used to obtain the power time series of equal length for all users in the same time period. Given a function f(x) and multiple independent variables x0, x1, x2, x3 of the function, the first-order difference quotient of this function is (f(x i )-f(x j )) / (x i -x j ), and the difference quotient is recorded as f[x i ,x j]. Based on the first-order difference quotient, the higher-order smart meter difference quotient can be recursively derived, and the calculation formula of the k-order difference quotient of the function is obtained as follows:
[0079] (f[x1,x2…x k ]-f[x0,x1…x k-1 ]) / (x k -x0)
[0080] The calculation formula of Newton interpolation method can be expressed by the difference quotient as follows:
[0081] f(x)=f(x0)+f[x,x0](x-x0)
[0082] f(x)=f(x0)+f[x0,x1](x-x0)+f[x,x0,x1](x-x0)(x-x1)
[0083] f(x)=f(x0)+f[x0,x1](x-x0)+f[x0,x1…x n ](x-x0)(x-x1)…(xx n-1 )
[0084] +f[x,x0…x n ](x-x0)(x-x1)…(xx n )
[0085] Taking the time series as the independent variable and the smart meter power as the corresponding function, after preprocessing with the Newton interpolation method, the complete power curve can be represented. On this basis, all data power curves are resampled at equal time intervals and the time series are uniformly marked. At this time, all device data have the same and complete time series. The time series are recorded as [t1, t2, t3, ..., t T For example, at time t1, the power of each user-side smart meter is recorded as The power of each transformer is recorded as
[0086] By acquiring power data from user monitoring terminals and transformers and using Newton interpolation to address missing data values, the team can effectively complete the power data of different devices at different time points, ensuring data integrity and continuity. By unifying the time series through time interval sampling, the problem of inconsistent time points across different devices is eliminated, making the power data consistent and comparable across the time dimension. This operation improves the quality and availability of input data, providing a reliable data foundation for the subsequent establishment of precise mathematical models and efficient iterative optimization using genetic algorithms. It avoids analytical errors caused by missing data or inconsistent time series, thereby improving the accuracy and stability of distribution network topology identification.
[0087] S2. Establishing a mathematical model based on the topological structure of the distribution network; wherein the objective function and constraints of the mathematical model are obtained based on the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship;
[0088] Furthermore, in some embodiments of the present application, a mathematical model is established according to the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained according to the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship, specifically:
[0089] The constraint conditions of the mathematical model are expressed as follows:
[0090]
[0091] Where a is the total number of transformers; b is the total number of user monitoring terminals; Indicates that at t k At time t, the topological connection relationship between the jth user monitoring terminal and the i-th transformer is 1 when connected and 0 when not connected; Indicates that the jth user monitoring terminal is at t k The power at the moment is obtained based on the power data of the first user monitoring terminal; Indicates that the i-th transformer is at t k The power at the moment is obtained based on the first transformer power data;
[0092] The objective function of the mathematical model is expressed as follows:
[0093] min(||Y-WX||2)
[0094] Where W is In matrix form, Y is The matrix form of X is Matrix form of .
[0095] S3. According to the mathematical model, a genetic algorithm is used to iteratively update the population until the optimal individual in the current iteration population meets a preset requirement or the current iteration number reaches a preset iteration number, and the optimal individual in the current iteration population is output;
[0096] Specifically, the conversion relationship of each variable in the above steps can be as follows:
[0097] All Arrange them in the order of subscripts and write them in matrix form, The above user-side smart meter power vector and transformer power vector are respectively denoted as and The above relationship can be simplified into the following matrix relationship expression:
[0098]
[0099] For the above problem, we should hope that the topological matrix The value of The calculation result is close to the transformer power vector The value of this optimization problem is transformed into minimizing the L2 norm, omitting the matrix and vector and Time series subscript t k Written as:
[0100]
[0101] By constructing a mathematical model that includes constraints and an objective function, a binary variable is used to accurately represent the connection status between the user monitoring terminal and the transformer, ensuring that the model strictly adheres to the physical logic of the distribution network topology. Next, this application uses the L2 norm to quantify the difference between the transformer power prediction value and the actual measured value, transforming the topology identification problem into a computable optimization problem, enabling the solution process to approximate the actual topology in a data-driven manner. This model uniformly describes the power data and connection relationship in matrix form, providing a clear optimization target and feasible solution space for the genetic algorithm.
[0102] Furthermore, in some embodiments of the present application, the population is iteratively updated using a genetic algorithm according to the mathematical model, specifically:
[0103] Performing binary Gray code encoding on the topological matrix to be solved in the mathematical model to obtain an initial population; wherein the initial population includes information of a plurality of individuals;
[0104] The fitness of each individual information in the initial population is calculated using a fitness calculation method, and according to the fitness of each individual information, the current iterative population is selected, crossed and mutated to obtain an updated population.
[0105] Furthermore, in some embodiments of the present application, the fitness calculation method is used to calculate the fitness of each individual information in the initial population, specifically:
[0106] The fitness calculation method is used to calculate the fitness of each individual information in the initial population. The formula of the fitness calculation method is as follows:
[0107]
[0108] Among them, f is the fitness function, Y is The matrix form of X is In matrix form, W1 is the decoding matrix of the individual information of the current iteration.
[0109] S4. Determine the topology of the distribution network according to the output optimal individual.
[0110] Specifically, in order to fully explain the iterative solution process of the genetic algorithm in the above steps, the following case is used for illustration:
[0111] like Figure 2 Figure 1 shows the iterative solution flow chart for the genetic algorithm. Considering that the topological structures corresponding to adjacent moments are relatively similar, the initial population at the first moment is randomly generated using a sequence of 0s and 1s or based on historical data. The initial populations at all other moments inherit the population from the last round of the previous moment. The topological matrix corresponding to each moment is generated through several rounds of genetic iterations. Each round consists of the following steps: performing a crossover operation; performing a mutation operation; decoding the genetic information into a topological matrix and calculating the fitness; performing a selection operation and determining whether to exit the iteration. These steps are repeated until the maximum number of iterations is reached or the L2 norm reaches the desired level. Finally, the genetic information of the optimal individual is decoded to obtain the linear regression matrix.
[0112] The individual encoding method uses binary Gray code. If there are 500 user-side smart meters and 100 transformers, each chromosome can be divided into 500 parts, each part representing a column of the topological matrix W. Since each column of the topological matrix contains only one 1, binary Gray code is used to represent the position of the 1 element. Each column of the topological matrix contains 100 elements, and a code length of 7 bits can fully express all the information. Therefore, the length of each part is set to 7, resulting in a total code length of 7*500, a total of 3500 bits of Gray code.
[0113] Selection operation refers to the process of retaining more individuals with high fitness to improve the fitness level of the entire population. Whether parental information is inherited is determined by the roulette wheel selection method.
[0114] like Figure 3 As shown, this is a schematic diagram of mutation and crossover operations:
[0115] A crossover operation involves exchanging some of the genes of two or more paired individuals (chromosomes) in some way, thereby generating two or more new individuals. The crossover probability is set to P1, and individuals are selected based on this probability, and genetic segments are randomly exchanged at the same chromosome location. Consider the following parental situation as an example:
[0116] Parental chromosome m: 1111001…;
[0117] Parental chromosome n: 0100011…;
[0118] At this time, the mth chromosome and the nth chromosome of the parent cross over.
[0119] Taking the crossover operation of the first segment as an example, the first segment of the parent's m-th chromosome indicates that the 81st bit in the first column of the topological matrix is 1, and the first segment of the parent's n-th chromosome indicates that the 61st bit in the first column of the topological matrix is 1.
[0120] After performing the crossover operation:
[0121] The mth chromosome of the offspring: 1110001…;
[0122] The nth chromosome of the offspring: 0101011…;
[0123] At this time, the 4th bit of the mth chromosome and the nth chromosome cross over, and the first fragment of the mth and nth chromosomes in the offspring respectively indicates that the 94th and 50th bits of the first column of the topological matrix are 1.
[0124] Mutation involves changing a specific location on the chromosome of the offspring compared to the parent. The probability of mutation is set to P2, and the selected gene location mutates according to this probability, changing to the opposite binary code.
[0125]
[0126] Among them, s is a random number in the interval [0,1], k2 is a preset constant, g is the current number of evolutions, G max is the maximum number of evolutions.
[0127] If an invalid binary code appears in the offspring, the mutation or selection algorithm is considered unsuccessful and the operation is canceled.
[0128] Parental chromosome m: 1111001…;
[0129] If the mth chromosome is 1111101 after the mutation operation;
[0130] At this time, the fifth gene locus representing the mth chromosome mutates, and the first segment of the mth chromosome of the offspring represents that the 86th bit in the first column of the topological matrix is 1.
[0131] The genetic algorithm is put into use. Initially, if the initial population is randomly generated as a sequence of 0s and 1s, even with insufficient iterations and an insufficiently small L2 norm, the topology matrix may differ from the actual topology matrix. However, every 10 minutes, each round of the genetic algorithm inherits the final population from the previous time node. Because the topology structure of adjacent time nodes does not change significantly, it will enter a stable state after a few time nodes. At this point, the genetic algorithm uses crossover and mutation to select the optimal individual. The Gray code genetic information of each individual is decoded piece by piece to obtain the linear regression matrix of the topology structure, thus determining the topology of the distribution network.
[0132] In this way, by obtaining the power data of user monitoring terminals and transformers, a mathematical model is established based on the actual topological connection relationship, avoiding dependence on additional devices, reducing costs and improving data utilization efficiency; a genetic algorithm is used to iteratively optimize the population, and its global search characteristics are used to effectively avoid falling into local optimality, ensuring that the solution process can more accurately approximate the actual topological structure. At the same time, the optimal individuals are gradually screened out through an iterative mechanism, which improves the accuracy of topological structure identification and solution efficiency, enabling the method to more efficiently and reliably determine the distribution network topology structure and adapt to the management needs of dynamic changes in the distribution network.
[0133] Example 2
[0134] like Figure 4 As shown, based on the above method embodiment, a corresponding device embodiment is provided;
[0135] An embodiment of the present invention provides a distribution network topology identification device, comprising: a data acquisition module 41, a model building module 42, an iterative update module 43, and a result determination module 44;
[0136] Furthermore, in some embodiments of the present application, the data acquisition module 41 is used to obtain the first user monitoring terminal power data of each user monitoring terminal in the distribution network, and obtain the first transformer power data of each transformer; the model establishment module 42 is used to establish a mathematical model based on the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained based on the first user monitoring terminal power data, the first transformer power data and the topological connection relationship; the iterative update module 43 is used to iteratively update the population using a genetic algorithm according to the mathematical model until the optimal individual in the current iteration population meets the preset requirements or the current iteration number reaches the preset iteration number, and output the optimal individual in the current iteration population; the result determination module 44 is used to determine the topological structure of the distribution network based on the output optimal individual.
[0137] Furthermore, in some embodiments of the present application, the data acquisition module 41 includes a data acquisition unit and a data processing unit; the data acquisition unit is used to obtain the second terminal power data of each user monitoring terminal in the distribution network, and obtain the second transformer power data of each transformer; the data processing unit is used to use Newton interpolation method to process the missing values in the second terminal power data and the second transformer power data to obtain third terminal power data and third transformer power data, and unify the time series of the third terminal power data and the third transformer power data through a time interval sampling method to obtain the first user monitoring terminal power data and the first transformer power data.
[0138] Furthermore, in some embodiments of the present application, a mathematical model is established according to the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained according to the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship, specifically:
[0139] The constraint conditions of the mathematical model are expressed as follows:
[0140]
[0141] Where a is the total number of transformers; b is the total number of user monitoring terminals; Indicates that at t k At time t, the topological connection relationship between the jth user monitoring terminal and the i-th transformer is 1 when connected and 0 when not connected; Indicates that the jth user monitoring terminal is at t k The power at the moment is obtained based on the power data of the first user monitoring terminal; Indicates that the i-th transformer is at t k The power at the moment is obtained based on the first transformer power data;
[0142] The objective function of the mathematical model is expressed as follows:
[0143] min(||Y-WX||2)
[0144] Where W is In matrix form, Y is The matrix form of X is Matrix form of .
[0145] Furthermore, in some embodiments of the present application, the iterative update module 43 includes an initial unit and an update unit; the initial unit is used to perform binary Gray code encoding on the topological matrix to be solved in the mathematical model to obtain an initial population; wherein the initial population contains a plurality of individual information; the update unit is used to calculate the fitness of each individual information in the initial population using a fitness calculation method, and select, cross and mutate the current iterative population according to the fitness of each individual information to obtain an updated population.
[0146] Furthermore, in some embodiments of the present application, the fitness calculation method is used to calculate the fitness of each individual information in the initial population, specifically:
[0147] The fitness calculation method is used to calculate the fitness of each individual information in the initial population. The formula of the fitness calculation method is as follows:
[0148]
[0149] Among them, f is the fitness function, Y is The matrix form of X is In matrix form, W1 is the decoding matrix of the individual information of the current iteration.
[0150] For more detailed steps and working principles of this embodiment, please refer to, but not limited to, the relevant records of Embodiment 1.
[0151] In summary, this application obtains power data from user monitoring terminals and transformers, establishes a mathematical model based on the actual topological connection relationship, avoids dependence on additional devices, reduces costs and improves data utilization efficiency; uses a genetic algorithm to iteratively optimize the population, and uses its global search characteristics to effectively avoid falling into local optimality, ensuring that the solution process can more accurately approximate the actual topological structure. At the same time, the optimal individuals are gradually screened out through an iterative mechanism, which improves the accuracy of topological structure identification and solution efficiency, enabling the method to more efficiently and reliably determine the distribution network topology structure and adapt to the management needs of dynamic changes in the distribution network.
[0152] It can be understood that the above-mentioned device embodiment corresponds to the method embodiment of the present invention, and can implement the XXXX method provided by any of the above-mentioned method embodiments of the present invention.
[0153] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Furthermore, in the drawings of the device embodiments provided by the present invention, the topological connection relationship between modules indicates that they have a communication connection, which may be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement the present invention without inventive effort.
[0154] Based on the above-mentioned embodiment of the distribution network topology structure identification method, another embodiment of the present invention provides a terminal device, which includes 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 distribution network topology structure identification method of any embodiment of the present invention is implemented.
[0155] For example, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more module elements may 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.
[0156] The terminal device may be a computing device such as a desktop computer, a notebook computer, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.
[0157] 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. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, connecting various parts of the entire terminal device using various interfaces and lines.
[0158] Based on the above method embodiments, another embodiment of the present invention provides a 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 distribution network topology structure identification method described in any one of the above method embodiments of the present invention.
[0159] Wherein, the module / unit integrated in the device / terminal equipment, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.
[0160] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for identifying a distribution network topology, characterized in that: include: Obtaining first user monitoring terminal power data of each user monitoring terminal in the distribution network, and obtaining first transformer power data of each transformer; Establishing a mathematical model based on the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained based on the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship; According to the mathematical model, a genetic algorithm is used to iteratively update the population until the optimal individual in the current iteration population meets the preset requirements or the current iteration number reaches the preset iteration number, and the optimal individual in the current iteration population is output; The topology of the power distribution network is determined according to the output optimal individual.
2. A method for identifying a distribution network topology according to claim 1, characterized in that: The obtaining of the first user monitoring terminal power data of each user monitoring terminal in the distribution network and the obtaining of the first transformer power data of each transformer are specifically as follows: Obtaining second terminal power data of each user monitoring terminal in the distribution network, and obtaining second transformer power data of each transformer; Newton interpolation is used to process missing values in the second terminal power data and the second transformer power data to obtain third terminal power data and third transformer power data, and time series of the third terminal power data and the third transformer power data are unified through a time interval sampling method to obtain first user monitoring terminal power data and first transformer power data.
3. A method for identifying a distribution network topology according to claim 1, characterized in that: The mathematical model is established according to the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained according to the power data of the first user monitoring terminal, the power data of the first transformer and the topological connection relationship, specifically: The constraint conditions of the mathematical model are expressed as follows: Where a is the total number of transformers; b is the total number of user monitoring terminals; Indicates that at t k At time t, the topological connection relationship between the jth user monitoring terminal and the i-th transformer is 1 when connected and 0 when not connected; Indicates that the jth user monitoring terminal is at t k The power at the moment is obtained based on the power data of the first user monitoring terminal; Indicates that the i-th transformer is at t k The power at the moment is obtained based on the power data of the first transformer; The objective function of the mathematical model is expressed as follows: min(||Y-WX||2) Where W is The matrix form of Y is The matrix form of X is Matrix form of .
4. A method for identifying a distribution network topology according to claim 3, characterized in that: According to the mathematical model, the genetic algorithm is used to iteratively update the population, specifically: Performing binary Gray code encoding on the topological matrix to be solved in the mathematical model to obtain an initial population; wherein the initial population includes information of a plurality of individuals; The fitness of each individual information in the initial population is calculated using a fitness calculation method, and according to the fitness of each individual information, the current iterative population is selected, crossed and mutated to obtain an updated population.
5. A method for identifying a distribution network topology according to claim 4, characterized in that: The fitness calculation method is used to calculate the fitness of each individual information in the initial population, specifically: The fitness calculation method is used to calculate the fitness of each individual information in the initial population. The formula of the fitness calculation method is as follows: Among them, f is the fitness function, Y is The matrix form of X is In matrix form, W1 is the decoding matrix of the individual information of the current iteration.
6. A distribution network topology identification device, characterized in that: include: Data acquisition module, model building module, iterative update module and result determination module; The data acquisition module is used to obtain the first user monitoring terminal power data of each user monitoring terminal in the distribution network and obtain the first transformer power data of each transformer; The model building module is configured to establish a mathematical model based on the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained based on the power data of the first user monitoring terminal, the power data of the first transformer, and the topological connection relationship; The iterative update module is used to iteratively update the population using a genetic algorithm according to the mathematical model until the optimal individual in the current iteration population meets the preset requirements or the current iteration number reaches the preset iteration number, and output the optimal individual in the current iteration population; The result determination module is used to determine the topology of the distribution network according to the output optimal individual.
7. A distribution network topology identification device according to claim 6, characterized in that: The data acquisition module includes a data acquisition unit and a data processing unit; The data acquisition unit is used to acquire the second terminal power data of each user monitoring terminal in the distribution network and acquire the second transformer power data of each transformer; The data processing unit is used to use Newton interpolation method to process missing values in the second terminal power data and the second transformer power data to obtain third terminal power data and third transformer power data, and unify the time series of the third terminal power data and the third transformer power data through a time interval sampling method to obtain first user monitoring terminal power data and first transformer power data.
8. The device for identifying a topology of a distribution network according to claim 6, wherein: The mathematical model is established according to the topological structure of the distribution network; wherein the objective function and constraint conditions of the mathematical model are obtained according to the power data of the first user monitoring terminal, the power data of the first transformer and the topological connection relationship, specifically: The constraint conditions of the mathematical model are expressed as follows: Where a is the total number of transformers; b is the total number of user monitoring terminals; Indicates that at t k At time t, the topological connection relationship between the jth user monitoring terminal and the i-th transformer is 1 when connected and 0 when not connected; Indicates that the jth user monitoring terminal is at t k The power at the moment is obtained based on the power data of the first user monitoring terminal; Indicates that the i-th transformer is at t k The power at the moment is obtained based on the power data of the first transformer; The objective function of the mathematical model is expressed as follows: min(||Y-WX||2) Where W is The matrix form of Y is The matrix form of X is Matrix form of .
9. The device for identifying a distribution network topology according to claim 8, wherein: The iterative update module includes an initial unit and an update unit; The initial unit is used to perform binary Gray code encoding on the topological matrix to be solved in the mathematical model to obtain an initial population; wherein the initial population includes information of a plurality of individuals; The updating unit is used to calculate the fitness of each individual information in the initial population using a fitness calculation method, and perform selection, crossover and mutation on the current iterative population according to the fitness of each individual information to obtain an updated population.
10. The device for identifying the topology of a distribution network according to claim 9, wherein: The fitness calculation method is used to calculate the fitness of each individual information in the initial population, specifically: The fitness calculation method is used to calculate the fitness of each individual information in the initial population. The formula of the fitness calculation method is as follows: Among them, f is the fitness function, Y is The matrix form of X is In matrix form, W1 is the decoding matrix of the individual information of the current iteration.
11. A terminal device, characterized in that: The method comprises 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 method for identifying the topology of a distribution network according to any one of claims 1 to 5 is implemented.
12. A computer-readable storage medium, characterized in that include: A stored computer program, wherein when the computer program is run, the device where the computer-readable storage medium is located is controlled to execute the distribution network topology identification method according to any one of claims 1 to 5.