Method and device for identifying topological structure of power distribution network and computer equipment
Through pre-trained classification model and variational Bayesian Gaussian hybrid model, combined with sparrow optimization algorithm, automatic labeling and real-time identification of the distribution network topology structure, the problem of long topology recognition time in the existing technology is solved, and the distribution network is realized Accurate real-time identification of topology.
Patent Information
- Application Number
- CN202411015999.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-15
AI Technical Summary
The existing distribution network topology identification algorithm requires topology labeling in advance or manually, and the topology identification time is long, making it difficult to realize real-time identification of distribution network topology.
By obtaining the voltage and current values of the target moment, inputting a pre-trained classification model, and determining the topological labels using the variational Bayesian Gaussian hybrid model and sparrow optimization algorithm, real-time identification of the topological structure of the distribution network is achieved.
Real-time accurate identification of the distribution network topology structure is realized, the problem of historical data needing to be marked in advance or manually, and the efficiency and accuracy of topology recognition is improved.
Smart Images

Figure CN118965160A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of distribution networks, and in particular to a distribution network topology identification method, device and computer equipment. Background Art
[0002] With the access of new energy and the continuous increase in the scale of distribution networks, the dynamic changes in the topology of distribution networks are becoming more frequent and difficult to identify. Compared with the transmission network, the distribution network has not yet achieved real-time monitoring of the topology structure, and the topology structure of the distribution network has frequently changed due to load reversal, frequent line changes, and sudden failures. This structural change affects the protection action of the distribution network and the stability of the power system. Accurate distribution network topology identification is a key part of the modern distribution management system and the cornerstone for ensuring the safe and stable operation of the power system. Therefore, accurate and real-time topology identification is crucial to the operation of future distribution networks and provides the necessary foundation for ensuring the reliability and safety of the system. However, the historical data used by the existing distribution network topology identification algorithm needs to be topologically labeled in advance or manually, and the topology identification time is long, making it difficult to achieve real-time identification of the distribution network topology.
[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0004] The embodiments of the present invention provide a distribution network topology structure identification method, device and computer equipment to at least solve the technical problem that it is difficult to realize real-time identification of distribution network topology because the historical data used in the existing distribution network topology identification algorithm needs to be topologically labeled in advance or manually and the topology identification time is long.
[0005] According to one aspect of an embodiment of the present invention, there is provided a distribution network topology structure identification, including: obtaining voltage values and current values of each of multiple nodes in a target distribution network at a target moment; inputting the voltage values and current values of each of the multiple nodes into a pre-trained classification model, and the pre-trained classification model outputs the topology structure of the distribution network at the target moment, wherein the classification model is obtained by training an original classification model through training samples, the training samples include multiple historical data and topology labels of each of the multiple historical data, the multiple historical data each include voltage values and current values of each of multiple sample nodes in the sample distribution network, and the topology labels of each of the multiple historical data are determined through a variational Bayesian-Gaussian mixture model.
[0006] Optionally, the topological labels corresponding to the historical data are determined in the following manner: obtaining multiple historical data of the sample distribution network within a historical period; determining multiple topological structures of the sample distribution network; and based on the multiple topological structures, determining the topological labels corresponding to each of the multiple historical data by a variational Bayesian-Gaussian mixture model.
[0007] Optionally, based on multiple topological structures, the variational Bayesian Gaussian mixture model is used to determine the topological labels corresponding to multiple historical data, including: clustering the multiple historical data using the variational Bayesian Gaussian mixture model to obtain multiple groups of historical data, wherein the historical data in each group of historical data corresponds to the same topological structure; and determining the topological labels corresponding to the multiple groups of historical data using the variational Bayesian Gaussian mixture model.
[0008] Optionally, the variational Bayesian-Gaussian mixture model is used to determine the topological labels corresponding to each of the multiple groups of historical data, including: determining the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures respectively by the variational Bayesian-Gaussian mixture model; determining the topological labels corresponding to the target group historical data based on the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures respectively; and determining the topological labels corresponding to the multiple groups of historical data by the variational Bayesian-Gaussian mixture model using the above-mentioned method for determining the topological labels corresponding to the target group historical data.
[0009] Optionally, based on the matching probabilities between multiple data included in the target group historical data and multiple topological structures, a topological label corresponding to the target group historical data is determined, including: based on the matching probabilities between multiple data included in the target group historical data and multiple topological structures, an average matching probability of each of the multiple topological structures is determined; and the topological structure with the largest average matching probability is determined as the topological label corresponding to the target group historical data.
[0010] Optionally, in the process of training the original classification model using the training samples, model parameters are determined based on the sparrow optimization algorithm to obtain the classification model.
[0011] According to another aspect of an embodiment of the present invention, a distribution network topology structure identification device is also provided, including: an acquisition module, used to obtain the voltage value and current value of each of the multiple nodes in the target distribution network at the target moment; an identification module, used to input the voltage value and current value of each of the multiple nodes into a pre-trained classification model, and the pre-trained classification model outputs the topology structure of the distribution network at the target moment, wherein the classification model is obtained by training the original classification model through training samples, the training samples include multiple historical data and topological labels of each of the multiple historical data, the multiple historical data each include the voltage value and current value of each of the multiple sample nodes in the sample distribution network, and the topological labels of each of the multiple historical data are determined by a variational Bayesian Gaussian mixture model.
[0012] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, the non-volatile storage medium including a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute any one of the above-mentioned distribution network topology identification methods.
[0013] According to yet another aspect of an embodiment of the present invention, a computer device is provided. The computer device includes a processor, and the processor is used to run a program. When the program is run, any one of the above-mentioned distribution network topology identification methods is executed.
[0014] According to yet another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, any one of the above-mentioned methods for identifying a topology of a distribution network is implemented.
[0015] In an embodiment of the present invention, by obtaining the voltage value and current value of each of the multiple nodes in the target distribution network at the target moment; inputting the voltage value and current value of each of the multiple nodes into a pre-trained classification model, the pre-trained classification model outputs the topological structure of the distribution network at the target moment, wherein the classification model is obtained by training the original classification model through training samples, the training samples include multiple historical data and the topological labels of the multiple historical data, the multiple historical data each include the voltage value and current value of each of the multiple sample nodes in the sample distribution network, and the topological labels of the multiple historical data are determined by the variational Bayesian Gaussian mixture model, so as to achieve the purpose of automatic topological labeling and classification of the multiple historical data, thereby realizing the technical effect of real-time and accurate identification of the topological structure of the distribution network, and further solving the technical problem that it is difficult to realize real-time identification of the distribution network topology because the historical data used in the existing distribution network topology identification algorithm needs to be topologically labeled in advance or manually and the topological identification time is long. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0017] Figure 1 A hardware structure block diagram of a computer terminal for implementing a method for identifying a distribution network topology is shown;
[0018] Figure 2 is a schematic diagram of a flow chart of a distribution network topology identification method provided according to an embodiment of the present invention;
[0019] Figure 3 is a schematic diagram of a topology identification process provided according to an optional embodiment of the present invention;
[0020] Figure 4 It is a structural block diagram of a distribution network topology identification device provided according to an embodiment of the present invention. DETAILED DESCRIPTION
[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0023] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:
[0024] Field Programmable Gate Array (FPGA) is a programmable semiconductor device that allows hardware to be reconfigured and programmed after manufacturing, with high flexibility and customizability.
[0025] Sparrow Search Algorithm (SSA) is an optimization algorithm inspired by the group behavior of sparrows in nature. Its main advantages lie in its excellent global search capability and fast convergence speed, which makes it perform well in accelerating the solution of optimization problems.
[0026] Double Data Rate Synchronous Dynamic Random Access Memory (DDR SDRAM) is a memory technology that can provide high data transfer rates.
[0027] The Processor Local Bus (PLB) is a high-speed bus technology used to connect the processor and other system components, allowing the processor to communicate quickly with other parts of the system.
[0028] Support Vector Machine (SVM) is a supervised learning algorithm mainly used for classification and regression analysis, with excellent performance and effectiveness in dimensional space.
[0029] The Data Local Memory Bus (DLMB) is a device bus that can provide high-speed data transmission services for processors and other logic units.
[0030] Block Random Access Memory (BRAM) is a random access memory implemented in FPGA, which can be configured into different storage structures to meet different application requirements.
[0031] Internal Logic Memory Block (ILMB) is a module that implements memory functions in FPGA, such as RAM, ROM, etc. ILMB is usually integrated in the logic unit of FPGA and can be used to store program instructions, data, etc. ILMB can realize fast data access and storage functions in FPGA.
[0032] According to an embodiment of the present invention, a method embodiment for identifying a distribution network topology is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0033] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing a method for identifying a distribution network topology is shown. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1More or fewer components as shown, or with Figure 1 Different configurations shown.
[0034] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).
[0035] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the distribution network topology structure identification method in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the distribution network topology structure identification method of the above-mentioned application program is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0036] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .
[0037] Figure 2 FIG. 1 is a flow chart of a method for identifying a distribution network topology according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:
[0038] Step S202, obtaining voltage values and current values of each of a plurality of nodes in a target distribution network at a target time.
[0039] In this step, the target time is the time when the real-time topological structure of the distribution network is obtained during this identification, which can be any time of the day; the target distribution network is the distribution network targeted by this identification, which can be a distribution network with any number of nodes and equipment; multiple nodes are various types of electrical equipment and network equipment that constitute the target distribution network, and their number is fixed; the voltage value is the operating voltage collected on the branches and nodes in the target distribution network, which can be the peak voltage, effective value or average value; the voltage value is the operating current collected on the branches and nodes in the target distribution network, which can be the current peak value, effective value or average value.
[0040] Step S204, inputting the voltage value and current value of each of the multiple nodes into a pre-trained classification model, and the pre-trained classification model outputs the topological structure of the distribution network at the target time, wherein the classification model is obtained by training the original classification model through training samples, the training samples include multiple historical data and topological labels of the multiple historical data, the multiple historical data each include the voltage value and current value of each of the multiple sample nodes in the sample distribution network, and the topological labels of the multiple historical data are determined by the variational Bayesian Gaussian mixture model.
[0041] In this step, pre-training refers to training the classification model with historical data before topology identification to find the optimal parameters of the classification model; the training sample can be divided into training data and test data according to a certain ratio, generally 80% training data and 20% test data, wherein the training data is used to train the classification model, and the test data is used to verify the effect of the classification model training; the classification model can be a classification method based on machine learning, such as decision tree, random forest, long short memory neural network. The topological structure refers to the connection relationship between each node in the network; the sample distribution network refers to the distribution network used to collect sample data, which can be one or more; the sample nodes can be various types of electrical equipment and network equipment in the distribution network, wherein each piece of historical data in the training sample includes the voltage and current values of multiple sample nodes.
[0042] The variational Bayesian-Gaussian mixture model is a model that combines variational Bayesian and Gaussian distribution and can be used for aggregate classification. The topological label can be letters, numbers, or a combination of the two to mark different distribution network topologies for training classification models.
[0043] Through the above steps, the purpose of automatic topological labeling and classification of multiple historical data is achieved, thereby realizing the technical effect of real-time and accurate identification of the distribution network topology structure, and further solving the technical problem that it is difficult to realize real-time identification of the distribution network topology because the historical data used in the existing distribution network topology identification algorithm need to be topologically labeled in advance or manually and the topological identification time is long.
[0044] As an optional embodiment, the topological labels corresponding to the historical data are determined in the following manner: obtaining multiple historical data of the sample distribution network within a historical period; determining multiple topological structures of the sample distribution network; and based on the multiple topological structures, determining the topological labels corresponding to each of the multiple historical data by a variational Bayesian-Gaussian mixture model.
[0045] Optionally, the topology label can be letters, numbers, or a combination of the two, marking different distribution network topologies; the sample distribution network is a distribution network that can collect sample data; the historical period can be a period of limited length, such as 10 minutes, 6 hours, or 2 days; multiple topologies refer to topologies that may appear in the sample distribution network, and their number is limited. Specifically, there are multiple adjustable switches in the sample distribution network. When the state of the switch changes, the topology of the distribution network will also change. However, since the number of switches is limited, the topologies that may appear in the sample distribution network are also limited; the topology labels corresponding to multiple historical data refer to the topologies corresponding to each historical data.
[0046] Specifically, the historical data consists of voltage amplitude and current amplitude. Each piece of historical data is expressed as [U i,ρ ,I i,ρ ],U i,ρ represents the voltage amplitude of the ρth node of the i-th data, I i,ρ represents the current amplitude of the ρth node of the i-th data, where i∈{1,...,m}, m is the number of historical data sets, is the number of distribution network nodes. When FPGA is used for distribution network identification, historical data is stored in the synchronous dynamic random access memory DDR SDRAM, and PLB is used to communicate data with the MicroBlaze soft-core processor.
[0047] We can first collect multiple historical data of the sample distribution network in the historical period and determine the various topological structures that may appear in the sample distribution network. Then we can use the variational Bayesian Gaussian mixture model to infer and determine the best matching topological structure corresponding to each historical data among the various topological structures, which is the topological label corresponding to the historical data.
[0048] As an optional embodiment, based on multiple topological structures, a variational Bayesian Gaussian mixture model is used to determine the topological labels corresponding to multiple historical data, including: clustering multiple historical data using a variational Bayesian Gaussian mixture model to obtain multiple groups of historical data, wherein the historical data in each group of historical data corresponds to the same topological structure; and determining the topological labels corresponding to multiple groups of historical data using a variational Bayesian Gaussian mixture model.
[0049] Optionally, the number of topological structures is related to the circuit connection structure of the sample distribution network itself. Clustering aims to divide each sample in the historical data into multiple groups, so that the historical data in the same group have high similarity, that is, the topological structures corresponding to the multiple samples in the same group are considered to be consistent, and then the variational Bayesian Gaussian mixture model can comprehensively judge the topological structure corresponding to the group of historical data based on the multiple historical data in each group. Compared with using the variational Bayesian Gaussian mixture model to separately judge the topological structure that a certain historical data may correspond to, the method provided by this optional embodiment takes into account multiple historical data in a group, which can improve the accuracy of topological structure judgment.
[0050] As an optional embodiment, a variational Bayesian-Gaussian mixture model is used to determine the topological labels corresponding to each of the multiple groups of historical data, including: determining the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures respectively by the variational Bayesian-Gaussian mixture model; determining the topological labels corresponding to the target group historical data based on the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures respectively; and determining the topological labels corresponding to the multiple groups of historical data by the variational Bayesian-Gaussian mixture model using the above-mentioned method of determining the topological labels corresponding to the target group historical data.
[0051] Optionally, the matching probability refers to the probability that the historical data contained in the target group belongs to a certain topological structure. Specifically, the variational Bayesian Gaussian mixture model determines the matching probability between each piece of historical data and each topological structure, and finally determines the topological label corresponding to the group of historical data based on the matching probability. That is to say, in this optional embodiment, when determining the topological structure corresponding to a certain piece of historical data, not only the matching probability between the historical data and a variety of topological structures is considered, but also the matching probability between other pieces of historical data similar to the historical data and a variety of topological structures is considered. Therefore, the accuracy of judging the topological structure is relatively high.
[0052] As an optional embodiment, the topology label corresponding to the target group historical data is determined according to the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures, including: determining the average matching probability of the multiple topological structures according to the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures; and determining the topology structure with the largest average matching probability as the topology label corresponding to the target group historical data.
[0053] Optionally, for each piece of data in the target group's historical data, the degree of matching between it and each topological structure is calculated, and this matching degree is expressed in the form of probability. The level of matching probability reflects the rationality or accuracy of the data under a specific topological structure. Then, the matching probability of each piece of data in the target group's historical data and each topological structure can be summarized, and then the average matching probability of each topological structure can be calculated. The level of average matching probability reflects the overall matching degree of the entire data set under a specific topological structure. Finally, the topological structure with the highest average matching probability is selected as the "topological label" of the target group's historical data, which represents the most likely or most reasonable data organization method of the data set among multiple possible topological structures. Specifically, when using FPGA for distribution network identification, after the topological labeling of the historical data is completed, the relevant data is also retained in BANK2 and BANK3 of DDR SDRAM. When the parameters of the variational Gaussian mixture model are determined, the data is stored in BRAM through the DLMB high-speed data bus.
[0054] As an optional embodiment, in the process of training the original classification model using training samples, model parameters are determined based on the sparrow optimization algorithm to obtain the classification model.
[0055] Optionally, the training sample is historical data with topological labels used to train the original classification model; the sparrow optimization algorithm can accelerate the parameter optimization process of the classification model. During the training process, the historical data in the training sample can be input into the original classification model, and then the parameters of the original classification model can be adjusted according to the gap between the topological model corresponding to the historical data output by the original classification model and the label of the historical data, until relatively optimal model parameters are found, and the classification model can be obtained. However, in the process of parameter adjustment, it usually takes a lot of time to optimize the parameters. At this time, the sparrow optimization algorithm can be used. First, determine the parameter optimization target of the neural network model, such as minimizing the loss function or maximizing the accuracy, and then randomly generate a group of sparrow individuals as the initial population. Each individual represents a parameter combination of the neural network model. Then, according to the performance of the neural network model corresponding to each individual, its fitness value is calculated. Secondly, a certain number of individuals can be selected as parents according to the fitness value to breed the next generation of sparrow individuals. Then, the selected parent individuals are crossovered to generate new sparrow individuals, and the newly generated sparrow individuals are mutated to introduce random disturbances to increase the diversity of the population. Finally, the fitness of the new individuals is evaluated and the population is updated until a certain optimization target or number of iterations is reached. The algorithm is terminated and the optimal combination of neural network model parameters is output as the final optimization result.
[0056] Specifically, the historical data for determining topological labels are divided into 80% training samples and 20% test samples; the training data and test data are normalized; the initial SVM model parameters are stored in BRAM; using the training samples, the optimal SVM model parameters are generated based on the SSA-SVM model embedded in MicroBlaze, and the SVM model parameters are stored in BRAM through DLMB.
[0057] Figure 3 is a schematic diagram of a topology identification process provided according to an optional embodiment of the present invention, such as Figure 3 As shown, the topology identification process provided by the embodiment of the present invention can be divided into two steps. The first step is to determine the topology labels corresponding to the historical data using the variational Bayesian-Gaussian mixture model based on FPGA. When FPGA is used for distribution network identification, the historical data is stored in the synchronous dynamic random access memory DDR SDRAM, and the PLB is used to communicate with the MicroBlaze soft-core processor. When the historical data topology labeling is completed, the related data is also retained in BANK2 and BANK3 of the DDR SDRAM, where T i It indicates the type of topological structure corresponding to the i-th data, that is, the topological label of the data. When the variational Gaussian mixture model parameters are determined, the data is stored in BRAM through the DLMB high-speed data bus. In the above process, TIMER, as a timer module, can trigger interrupts regularly to control the data transmission rate, timed data sampling, implement timing logic, and transmit data between computing devices and external devices based on RS232 serial communication protocol.
[0058] The second step is to train the classifier using FPGA and apply the trained classification model to identify the topology of the distribution network in real time. The historical data containing the topology label can be divided into training samples and test samples, and then the training data and test data are normalized, and the initial SVM model parameters are stored in BRAM through ILMB. Using the training samples, the optimal model parameters are generated based on the initial SVM model embedded in the MicroBlaze soft-core processor, and the optimal SVM model is obtained. The optimal SVM model parameters are stored in BRAM through DLMB. Then the data of the target distribution network measured in real time can be input into the optimal SVM model, and the model will output the corresponding distribution network topology structure, realizing the real-time identification of the distribution network topology.
[0059] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.
[0060] Through the description of the above implementation methods, those skilled in the art can clearly understand that the distribution network topology identification method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0061] According to an embodiment of the present invention, a distribution network topology structure identification device for implementing the above distribution network topology structure identification method is also provided. Figure 4 is a structural block diagram of a distribution network topology identification device provided according to an embodiment of the present invention, such as Figure 4 As shown, the distribution network topology structure identification device includes: an acquisition module 41 and an identification module 42. The distribution network topology structure identification device is described below.
[0062] The acquisition module 41 is used to acquire the voltage value and current value of each of the multiple nodes in the target distribution network at the target time.
[0063] The identification module 42 is used to input the voltage value and current value of each of the multiple nodes into a pre-trained classification model, and the pre-trained classification model outputs the topological structure of the distribution network at the target time, wherein the classification model is obtained by training the original classification model through training samples, and the training samples include multiple historical data and the topological labels of the multiple historical data. The multiple historical data each include the voltage value and current value of each of the multiple sample nodes in the sample distribution network, and the topological labels of the multiple historical data are determined by the variational Bayesian Gaussian mixture model.
[0064] It should be noted that the acquisition module 41 and the identification module 42 correspond to steps S202 to S204 in the embodiment, and the examples and application scenarios implemented by the multiple modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above modules, as part of the device, can be run in the computer terminal 10 provided in the embodiment.
[0065] An embodiment of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one network device among multiple network devices of a computer network. The computer device includes a memory and a processor.
[0066] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the distribution network topology structure identification method and device in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the above-mentioned distribution network topology structure identification method is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0067] The processor can call the information and application programs stored in the memory through the transmission device to execute the following steps: obtain the voltage value and current value of each of the multiple nodes in the target distribution network at the target moment; input the voltage value and current value of each of the multiple nodes into a pre-trained classification model, and the pre-trained classification model outputs the topological structure of the distribution network at the target moment, wherein the classification model is obtained by training the original classification model through training samples, the training samples include multiple historical data and the topological labels of the multiple historical data, the multiple historical data each include the voltage value and current value of each of the multiple sample nodes in the sample distribution network, and the topological labels of the multiple historical data are determined by the variational Bayesian Gaussian mixture model.
[0068] Optionally, the topological labels corresponding to the historical data are determined in the following manner: obtaining multiple historical data of the sample distribution network within a historical period; determining multiple topological structures of the sample distribution network; and based on the multiple topological structures, determining the topological labels corresponding to each of the multiple historical data by a variational Bayesian-Gaussian mixture model.
[0069] Optionally, based on multiple topological structures, the variational Bayesian Gaussian mixture model is used to determine the topological labels corresponding to multiple historical data, including: clustering the multiple historical data using the variational Bayesian Gaussian mixture model to obtain multiple groups of historical data, wherein the historical data in each group of historical data corresponds to the same topological structure; and determining the topological labels corresponding to the multiple groups of historical data using the variational Bayesian Gaussian mixture model.
[0070] Optionally, the variational Bayesian-Gaussian mixture model is used to determine the topological labels corresponding to each of the multiple groups of historical data, including: determining the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures respectively by the variational Bayesian-Gaussian mixture model; determining the topological labels corresponding to the target group historical data based on the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures respectively; and determining the topological labels corresponding to the multiple groups of historical data by the variational Bayesian-Gaussian mixture model using the above-mentioned method for determining the topological labels corresponding to the target group historical data.
[0071] Optionally, based on the matching probabilities between multiple data included in the target group historical data and multiple topological structures, a topological label corresponding to the target group historical data is determined, including: based on the matching probabilities between multiple data included in the target group historical data and multiple topological structures, an average matching probability of each of the multiple topological structures is determined; and the topological structure with the largest average matching probability is determined as the topological label corresponding to the target group historical data.
[0072] Optionally, in the process of training the original classification model using the training samples, model parameters are determined based on the sparrow optimization algorithm to obtain the classification model.
[0073] By adopting the embodiment of the present invention, a solution for identifying the topology structure of a distribution network is provided. The topological labels of multiple historical data are determined by a variational Bayesian-Gaussian mixture model, so as to achieve the purpose of automatic topological labeling and classification of multiple historical data, thereby achieving the technical effect of real-time and accurate identification of the topological structure of the distribution network, thereby solving the technical problem that it is difficult to achieve real-time identification of the topology of the distribution network because the historical data used in the existing distribution network topology identification algorithm need to be topologically labeled in advance or manually and the topological identification time is long.
[0074] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a non-volatile storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0075] The embodiment of the present invention further provides a non-volatile storage medium. Optionally, in this embodiment, the non-volatile storage medium can be used to store the program code executed by the distribution network topology identification method provided in the above embodiment.
[0076] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.
[0077] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: obtaining the voltage value and current value of each of the multiple nodes in the target distribution network at the target moment; inputting the voltage value and current value of each of the multiple nodes into a pre-trained classification model, and the pre-trained classification model outputs the topological structure of the distribution network at the target moment, wherein the classification model is obtained by training the original classification model through training samples, the training samples include multiple historical data and topological labels of each of the multiple historical data, the multiple historical data each include the voltage value and current value of each of the multiple sample nodes in the sample distribution network, and the topological labels of each of the multiple historical data are determined by a variational Bayesian-Gaussian mixture model.
[0078] Optionally, the topological labels corresponding to the historical data are determined in the following manner: obtaining multiple historical data of the sample distribution network within a historical period; determining multiple topological structures of the sample distribution network; and based on the multiple topological structures, determining the topological labels corresponding to each of the multiple historical data by a variational Bayesian-Gaussian mixture model.
[0079] Optionally, based on multiple topological structures, the variational Bayesian Gaussian mixture model is used to determine the topological labels corresponding to multiple historical data, including: clustering the multiple historical data using the variational Bayesian Gaussian mixture model to obtain multiple groups of historical data, wherein the historical data in each group of historical data corresponds to the same topological structure; and determining the topological labels corresponding to the multiple groups of historical data using the variational Bayesian Gaussian mixture model.
[0080] Optionally, the variational Bayesian-Gaussian mixture model is used to determine the topological labels corresponding to each of the multiple groups of historical data, including: determining the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures respectively by the variational Bayesian-Gaussian mixture model; determining the topological labels corresponding to the target group historical data based on the matching probabilities between the multiple data included in the target group historical data and the multiple topological structures respectively; and determining the topological labels corresponding to the multiple groups of historical data by the variational Bayesian-Gaussian mixture model using the above-mentioned method for determining the topological labels corresponding to the target group historical data.
[0081] Optionally, based on the matching probabilities between multiple data included in the target group historical data and multiple topological structures, a topological label corresponding to the target group historical data is determined, including: based on the matching probabilities between multiple data included in the target group historical data and multiple topological structures, an average matching probability of each of the multiple topological structures is determined; and the topological structure with the largest average matching probability is determined as the topological label corresponding to the target group historical data.
[0082] Optionally, in the process of training the original classification model using the training samples, model parameters are determined based on the sparrow optimization algorithm to obtain the classification model.
[0083] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the distribution network topology identification method in each embodiment of the present application.
[0084] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0085] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0086] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0088] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0090] The above is only 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 principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for identifying a distribution network topology, characterized in that: include: Obtain the voltage and current values of multiple nodes in the target distribution network at the target time; The voltage values and current values of each of the multiple nodes are input into a pre-trained classification model, and the pre-trained classification model outputs the topological structure of the distribution network at the target moment, wherein the classification model is obtained by training an original classification model through training samples, and the training samples include multiple historical data and topological labels of each of the multiple historical data, and each of the multiple historical data includes the voltage value and current value of each of the multiple sample nodes in the sample distribution network, and the topological labels of each of the multiple historical data are determined by a variational Bayesian-Gaussian mixture model.
2. The method according to claim 1, characterized in that: The topology label corresponding to the historical data is determined in the following way: Acquire the plurality of pieces of historical data of the sample distribution network within a historical period; determining a plurality of topological structures of the sample power distribution network; According to the multiple topological structures, the variational Bayesian-Gaussian mixture model is used to respectively determine the topological labels corresponding to the multiple pieces of historical data.
3. The method according to claim 2, characterized in that The step of determining the topological labels corresponding to the plurality of historical data respectively by the variational Bayesian-Gaussian mixture model according to the plurality of topological structures includes: Clustering the plurality of historical data using the variational Bayesian-Gaussian mixture model to obtain a plurality of groups of historical data, wherein the historical data in each group of historical data corresponds to the same topological structure; The topological labels corresponding to each of the multiple groups of historical data are determined by the variational Bayesian-Gaussian mixture model.
4. The method according to claim 3, characterized in that The determining of the topological labels corresponding to the plurality of groups of historical data respectively by the variational Bayesian-Gaussian mixture model comprises: Determining the matching probabilities between the multiple pieces of data included in the target group historical data and the multiple topological structures respectively by the variational Bayesian-Gaussian mixture model; Determining a topology label corresponding to the target group historical data according to the matching probabilities of the multiple pieces of data included in the target group historical data and the multiple topological structures respectively; The above-mentioned method of determining the topological labels corresponding to the target group of historical data is adopted, and the topological labels corresponding to each of the multiple groups of historical data are determined by the variational Bayesian-Gaussian mixture model.
5. The method according to claim 4, characterized in that The determining, according to the matching probabilities of the plurality of pieces of data included in the target group historical data and the plurality of topological structures respectively, the topological label corresponding to the target group historical data comprises: Determine the average matching probability of each of the multiple topological structures according to the matching probabilities of the multiple data included in the target group historical data and the multiple topological structures respectively; The topological structure with the largest average matching probability is determined as the topological label corresponding to the historical data of the target group.
6. The method according to any one of claims 1 to 5, characterized in that In the process of training the original classification model using the training samples, model parameters are determined based on the sparrow optimization algorithm to obtain the classification model.
7. A distribution network topology identification device, characterized in that: include: An acquisition module is used to obtain the voltage and current values of multiple nodes in the target distribution network at the target time; An identification module is used to input the voltage value and current value of each of the multiple nodes into a pre-trained classification model, and the pre-trained classification model outputs the topological structure of the distribution network at the target moment, wherein the classification model is obtained by training the original classification model through training samples, and the training samples include multiple historical data and the topological labels of the multiple historical data, and the multiple historical data each include the voltage value and current value of each of the multiple sample nodes in the sample distribution network, and the topological labels of the multiple historical data are determined by a variational Bayesian Gaussian mixture model.
8. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the distribution network topology identification method according to any one of claims 1 to 6.
9. A computer device, characterized in that: include: Memory and processor, The memory stores a computer program; The processor is used to execute the computer program stored in the memory, and when the computer program is run, the processor executes the distribution network topology identification method according to any one of claims 1 to 6.
10. A computer program product comprising computer instructions, characterized in that: The computer instructions are executed by a processor to implement the distribution network topology identification method described in any one of claims 1 to 6.
