A distribution network self-healing mode planning method, device and storage medium

Abstract

The present invention discloses a method, device, and storage medium for planning a self-healing mode for a distribution network, wherein the method comprises: obtaining a plurality of distribution network samples with a self-healing function; parsing the distribution network samples one by one to obtain a corresponding number of training samples; using the power supply area type, distribution line type, communication method, and distribution automation mode in the training samples as a training data set, and using the self-healing mode as a label, training an initial classification model to obtain a self-healing mode classification model; inputting basic information of the distribution network to be planned into the self-healing mode classification model to obtain the self-healing mode of the distribution network to be planned. The present invention inputs the basic information of the distribution network to be planned into the trained classification model to obtain the corresponding self-healing mode, which can provide a reliable technical basis for selecting the self-healing mode of the distribution network, and has a unified standard for selecting the corresponding self-healing mode for the distribution network, thereby effectively improving the efficiency of the self-healing of the distribution network.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution networks, and in particular to a distribution network self-healing mode planning method, device and storage medium. Background Art

[0002] Distribution network self-healing is a comprehensive technology that uses automated devices and systems to monitor the operating status of distribution lines, detect line faults in a timely manner, isolate faulty sections, and automatically restore power to non-faulty sections, without requiring or with minimal human intervention. The planning of distribution network self-healing construction is based on a primary system plan. It is based on the local economic development, distribution network grid structure, equipment status, load levels, and the actual needs of power supply reliability in different regions, taking into account the distribution lines, communication networks, and switchgear, and rationally selecting a self-healing mode. The distribution network is large in scale, and especially with the access of a large number of new energy, energy storage, and charging and swapping facilities, the operation, control, and protection of the distribution network face enormous challenges. Distribution network self-healing technology is an advancement and extension of traditional distribution automation technology. It can adapt to the various challenges of future power grids and promote the improvement of distribution network power supply reliability and asset utilization.

[0003] The existing distribution network self-healing mode planning method cannot unify the standard to select the corresponding self-healing mode for distribution networks under different situations, resulting in low efficiency of distribution network self-healing. Summary of the Invention

[0004] The present invention provides a distribution network self-healing mode planning method, device and storage medium to solve the technical problem that the existing distribution network self-healing mode planning method cannot unify the standard to select the corresponding self-healing mode for the distribution network under different circumstances, resulting in low efficiency of distribution network self-healing.

[0005] An embodiment of the present invention provides a method for planning a self-healing mode of a distribution network, comprising:

[0006] Obtain multiple distribution network samples with self-healing capabilities;

[0007] The distribution network samples are parsed one by one to obtain a corresponding number of training samples, wherein the data of the training samples include the power supply area type, distribution line type, communication mode, distribution automation mode and self-healing mode of the distribution network;

[0008] The power supply area type, distribution line type, communication mode, and distribution automation mode in the training samples are used as a training data set, and the self-healing mode is used as a label to train an initial classification model to obtain a self-healing mode classification model;

[0009] The basic information of the distribution network to be planned is input into the self-healing mode classification model to obtain the self-healing mode of the distribution network to be planned, wherein the basic information of the distribution network to be planned includes the power supply area type, distribution line type, communication mode and distribution automation mode of the distribution network to be planned.

[0010] Furthermore, the obtaining of multiple distribution network samples with self-healing functions includes:

[0011] Obtain multiple distribution network cases with self-healing capabilities;

[0012] The distribution network case is filtered according to a preset filtering condition to obtain a distribution network sample, wherein the preset filtering condition is that the self-healing mode is not compatible with the distribution network.

[0013] Furthermore, the power supply area includes a first type of power supply area, a second type of power supply area and a third type of power supply area. The first type of power supply area satisfies σ≥15, the second type of power supply area satisfies 6≤σ<15, and the third type of power supply area satisfies σ<6, wherein σ is the load density of the power supply area, and the unit is megawatt / square kilometer; the distribution lines include cable lines and overhead lines; the communication methods include optical fiber communication, wireless public network communication and no communication conditions; the distribution automation modes include intelligent distributed local control type, centralized control type, differential protection local control type and local overlap local control type; the self-healing modes include master station centralized type, master station and differential protection collaborative type, master station and voltage time / current collaborative type and master station and intelligent distributed collaborative type.

[0014] Furthermore, the master station centralized type obtains real-time operation information and fault signals of the distribution network and distribution equipment through two-way communication between the distribution master station and the distribution terminal, so that the distribution master station controls the switching of the switch equipment according to the operation information and fault signals.

[0015] Furthermore, the master station and the differential protection cooperate to complete the precise fault location, isolation and power restoration of the non-fault section through the distribution master station, and complete the upstream isolation of the fault through on-site tripping of the distribution terminal.

[0016] Furthermore, the master station and the voltage-time / current collaborative type complete fault location and isolation on-site through the distribution terminal, and complete power transfer and restoration in the non-fault section through the distribution master station or the distribution terminal. When the distribution terminal completes power transfer and restoration on-site, the distribution master station verifies the correctness of the on-site action and optimizes fault handling as a backup protection.

[0017] Furthermore, the master station and the intelligent distributed collaborative type complete fault location, isolation and power restoration on-site through the distribution terminal, and verify the correctness of the on-site action through the distribution master station, and serve as backup protection to optimize fault handling.

[0018] An embodiment of the present invention provides a distribution network self-healing mode planning device, comprising:

[0019] The distribution network sample acquisition module is used to obtain multiple distribution network samples with self-healing functions;

[0020] A distribution network sample parsing module is used to parse the distribution network samples one by one to obtain a corresponding number of training samples, wherein the data of the training samples includes the power supply area type, distribution line type, communication mode, distribution automation mode and self-healing mode of the distribution network;

[0021] A model training module is configured to train an initial classification model using the power supply area type, distribution line type, communication mode, and distribution automation mode in the training samples as a training data set and the self-healing mode as a label to obtain a self-healing mode classification model;

[0022] The self-healing mode planning module is used to input the basic information of the distribution network to be planned into the self-healing mode classification model to obtain the self-healing mode of the distribution network to be planned. The basic information of the distribution network to be planned includes the power supply area type, distribution line type, communication mode and distribution automation mode of the distribution network to be planned.

[0023] One embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the distribution network self-healing mode planning method as described above.

[0024] The embodiment of the present invention collects data of an existing distribution network with a self-healing function and analyzes and processes the data one by one to obtain multiple training samples. The initial classification model is then trained based on the training samples to obtain a trained self-healing mode classification model. The basic information of the distribution network to be planned is input into the trained classification model to obtain the corresponding self-healing mode. This provides a reliable technical basis for the selection of the self-healing mode of the distribution network, and has a unified standard for selecting the corresponding self-healing mode for the distribution network, thereby effectively improving the efficiency of the self-healing of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 1 is a flow chart of a method for planning a distribution network self-healing mode according to an embodiment of the present invention;

[0026] Figure 2 Schematic diagram of the structure of the distribution network self-healing mode planning device provided by an embodiment of the present invention;

[0027] Figure 3 It is a structural diagram of a distribution network self-healing mode planning device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0029] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0030] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0031] See also Figure 1 An embodiment of the present invention provides a method for planning a self-healing mode of a distribution network, comprising:

[0032] S1. Obtain multiple distribution network samples with self-healing functions;

[0033] In an embodiment of the present invention, a distribution network case with a self-healing function may be obtained, and then a plurality of distribution network samples may be filtered from the distribution network case using a preset filtering condition.

[0034] In one embodiment, a filtering condition may be set to that the self-healing mode is not compatible with the distribution network, thereby filtering out distribution network cases that meet the filtering condition and obtaining distribution network samples with self-healing function.

[0035] It is understandable that distribution network cases are usually marked with whether the self-healing mode is compatible with the distribution network. Distribution network cases whose self-healing mode is not compatible with the distribution network can be directly filtered out through marking.

[0036] S2. Analyze the distribution network samples one by one to obtain a corresponding number of training samples, where the data of the training samples includes the power supply area type, distribution line type, communication mode, distribution automation mode, and self-healing mode of the distribution network;

[0037] In the embodiment of the present invention, the training samples obtained through analysis include several data. Since the selection of the self-healing mode needs to consider the power supply area type, distribution line type, communication method, and distribution automation mode of the distribution network, the embodiment of the present invention can parse the above data when performing analysis.

[0038] S3. Using the power supply area type, distribution line type, communication mode, and distribution automation mode in the training samples as a training data set and the self-healing mode as a label, an initial classification model is trained to obtain a self-healing mode classification model;

[0039] In an embodiment of the present invention, after determining the training data set and training labels, the initial classification model is trained to obtain a classification model for planning the self-healing mode of the distribution network.

[0040] S4. Input the basic information of the distribution network to be planned into the self-healing mode classification model to obtain the self-healing mode of the distribution network to be planned, wherein the basic information of the distribution network to be planned includes the power supply area type, distribution line type, communication mode and distribution automation mode of the distribution network to be planned.

[0041] The embodiment of the present invention collects data of an existing distribution network with a self-healing function and analyzes and processes the data one by one to obtain multiple training samples. The initial classification model is then trained based on the training samples to obtain a trained self-healing mode classification model. The basic information of the distribution network to be planned is input into the trained classification model to obtain the corresponding self-healing mode. This provides a reliable technical basis for the selection of the self-healing mode of the distribution network, and has a unified standard for selecting the corresponding self-healing mode for the distribution network, thereby effectively improving the efficiency of the self-healing of the distribution network.

[0042] In one embodiment, obtaining a plurality of distribution network samples with self-healing function includes:

[0043] Obtain multiple distribution network cases with self-healing capabilities;

[0044] The distribution network case is filtered according to a preset filtering condition to obtain a distribution network sample, wherein the preset filtering condition is that the self-healing mode is not compatible with the distribution network.

[0045] In the embodiment of the present invention, distribution network cases where the self-healing mode does not match the distribution network can be determined based on pre-marked information and filtered out.

[0046] In one embodiment, the power supply area includes a first type of power supply area, a second type of power supply area and a third type of power supply area, the first type of power supply area satisfies σ≥15, the second type of power supply area satisfies 6≤σ<15, and the third type of power supply area satisfies σ<6, wherein σ is the load density of the power supply area, and the unit is megawatt / square kilometer; the distribution line includes a cable line and an overhead line; the communication mode includes optical fiber communication, wireless public network communication and no communication conditions; the distribution automation mode includes intelligent distributed local control type, centralized control type, differential protection local control type and local overlap local control type; the self-healing mode includes a master station centralized type, a master station and differential protection collaborative type, a master station and voltage time / current collaborative type and a master station and intelligent distributed collaborative type.

[0047] In one embodiment, the power supply area can be divided into multiple categories based on the load density (in megawatts per square kilometer) of the power supply area. For example, the first category of power supply areas satisfies σ ≥ 15, the second category of power supply areas satisfies 6 ≤ σ < 15, and the third category of power supply areas satisfies σ < 6. Different self-healing modes can be generated for different power supply areas.

[0048] In one embodiment, the centralized master station acquires real-time operating information and fault signals of the distribution network and distribution equipment through two-way communication between the distribution master station and the distribution terminal, so that the distribution master station controls the switching of the switch equipment according to the operating information and fault signals.

[0049] Please refer to Table 1. In one embodiment, different self-healing modes may be determined for different power supply area types, distribution line types, communication modes, and distribution automation modes.

[0050] Table 1 Training samples

[0051]

[0052]

[0053] As you can understand, machine learning is a field of study that involves learning algorithms from a training set. Classification is a task that requires a machine learning algorithm to learn how to assign class labels to a dataset. In machine learning, classification refers to predictive modeling problems where the class label is predicted for a given example input data. From a modeling perspective, classification requires a training dataset containing the input and output data to learn from. The model uses the training dataset and calculates how to most accurately map input data samples to specific class labels. Therefore, the training dataset must be sufficiently representative, with each class label used in a large number of examples. Class labels are typically string values.

[0054] Among them, there are many different types of classification algorithms that can model classification prediction problems. There is no fixed pattern guideline on how to apply the appropriate algorithm to a specific classification problem. But it can be determined through experiments. Usually, the experimenter uses controlled experiments to select which algorithm and algorithm configuration has the best performance in a given classification task. Classification accuracy is a commonly used metric that evaluates the performance of the model by predicting the category label. Some tasks may require predicting the probability of each sample category member instead of the label, which provides additional uncertainty for the prediction. A common judgment method for evaluating the prediction probability is the ROC curve (integral area).

[0055] Unlike binary classification, multiclass classification does not have the concept of normal and abnormal results. Instead, samples are classified as belonging to one of a set of known categories. In some problems, the number of class labels can be very large. For example, problems involving predicting word sequences, such as text translation models, can also be considered a special type of multiclass classification. Each word in the sequence to be predicted involves a multiclass classification, where the vocabulary size defines the number of possible categories that can be predicted, which can number in the tens of thousands of words. Multiclass classification tasks are often modeled using a Multinoulli probability distribution for each example. The Multinoulli probability distribution is a discrete probability distribution covering cases where an event will have a well-defined outcome, such as k in {1, 2, 3, ..., k}. For classification, this means that the model can predict the probability that an example belongs to each class label.

[0056] Many algorithms used for binary classification can also be used to solve multi-class classification problems. Popular algorithms for multi-class classification include k-Nearest Neighbors, Decision Trees, Naive Bayes, Random Forest, and Gradient Boosting. These algorithms involve using a strategy that fits multiple binary classification models for each class against all other classes (called "one-vs-many") or one model for each pair of classes (called "one-vs-one"). Binary classification algorithms that can use these strategies for multi-class classification include Logistic Regression and Support Vector Machines.

[0057] The classification model selected in the embodiment of the present invention is a multi-category classification model. Multi-category classification refers to a classification task with more than two category labels.

[0058] In one embodiment, the model training uses four specific labels: centralized master station type, coordinated master station and differential protection type, coordinated master station and voltage-time / current type, and coordinated master station and intelligent distributed type. This embodiment uses the power supply area type, distribution line type, communication method, and distribution automation mode in the training samples as the training dataset, and uses the self-healing mode as the label to train a multi-class classification model, thereby obtaining a self-healing mode classification model.

[0059] After obtaining the self-healing mode classification model, the power supply area type, distribution line type, communication method, and distribution automation mode of the planned distribution network are input into the trained self-healing mode classification model to output a self-healing mode. The self-healing modes include master station centralized mode, master station and differential protection coordinated mode, master station and voltage-time / current coordinated mode, and master station and intelligent distributed coordinated mode.

[0060] In a specific implementation example, the power supply area type (first-class power supply area), distribution line type (overhead line), communication mode (fiber optic communication), and distribution automation mode (centralized control type) are input into the trained self-healing mode classification model, and the output self-healing mode is 85% with a probability of being a master station centralized type, 8% with a probability of being a master station and differential protection collaborative type, 4% with a probability of being a master station and voltage-time / current collaborative type, and 3% with a probability of being a master station and intelligent distributed collaborative type; the embodiment of the present invention takes the master station centralized type with the highest probability as the current distribution automation mode, that is, determines that the current distribution automation mode is a master station centralized type.

[0061] In one embodiment, the master station cooperates with the differential protection type to complete the precise fault location, isolation and power restoration of non-fault sections through the distribution master station, and completes the upstream isolation of the fault through on-site tripping of the distribution terminal.

[0062] In one embodiment, the master station and the voltage-time / current collaborative type complete fault location and isolation on-site through the distribution terminal, and complete power transfer and restoration in the non-fault section through the distribution master station or the distribution terminal. When the distribution terminal completes power transfer and restoration on-site, the distribution master station verifies the correctness of the on-site action and optimizes fault handling as a backup protection.

[0063] In one embodiment, the master station and the intelligent distributed collaborative type complete fault location, isolation and power restoration on-site through the distribution terminal, and verify the correctness of the on-site action through the distribution master station, and serve as backup protection to optimize fault processing.

[0064] The implementation of the present invention has the following beneficial effects:

[0065] The embodiment of the present invention collects data of an existing distribution network with a self-healing function and analyzes and processes the data one by one to obtain multiple training samples. The initial classification model is then trained based on the training samples to obtain a trained self-healing mode classification model. The basic information of the distribution network to be planned is input into the trained classification model to obtain the corresponding self-healing mode. This provides a reliable technical basis for the selection of the self-healing mode of the distribution network, and has a unified standard for selecting the corresponding self-healing mode for the distribution network, thereby effectively improving the efficiency of the self-healing of the distribution network.

[0066] See also Figure 2 Based on the same inventive concept as the above embodiment, one embodiment of the present invention provides a distribution network self-healing mode planning device, comprising:

[0067] The distribution network sample acquisition module 10 is used to acquire multiple distribution network samples with self-healing function;

[0068] The distribution network sample parsing module 20 is used to parse the distribution network samples one by one to obtain a corresponding number of training samples, wherein the data of the training samples includes the power supply area type, distribution line type, communication mode, distribution automation mode and self-healing mode of the distribution network;

[0069] A model training module 30 is configured to train an initial classification model using the power supply area type, distribution line type, communication mode, and distribution automation mode in the training samples as a training data set and the self-healing mode as a label to obtain a self-healing mode classification model;

[0070] The self-healing mode planning module 40 is used to input the basic information of the distribution network to be planned into the self-healing mode classification model to obtain the self-healing mode of the distribution network to be planned. The basic information of the distribution network to be planned includes the power supply area type, distribution line type, communication mode and distribution automation mode of the distribution network to be planned.

[0071] In one embodiment, obtaining a plurality of distribution network samples with self-healing function includes:

[0072] Obtain multiple distribution network cases with self-healing capabilities;

[0073] The distribution network case is filtered according to a preset filtering condition to obtain a distribution network sample, wherein the preset filtering condition is that the self-healing mode is not compatible with the distribution network.

[0074] In one embodiment, the power supply area includes a first type of power supply area, a second type of power supply area and a third type of power supply area, the first type of power supply area satisfies σ≥15, the second type of power supply area satisfies 6≤σ<15, and the third type of power supply area satisfies σ<6, wherein σ is the load density of the power supply area, and the unit is megawatt / square kilometer; the distribution line includes a cable line and an overhead line; the communication mode includes optical fiber communication, wireless public network communication and no communication conditions; the distribution automation mode includes intelligent distributed local control type, centralized control type, differential protection local control type and local overlap local control type; the self-healing mode includes a master station centralized type, a master station and differential protection collaborative type, a master station and voltage time / current collaborative type and a master station and intelligent distributed collaborative type.

[0075] In one embodiment, the centralized master station acquires real-time operating information and fault signals of the distribution network and distribution equipment through two-way communication between the distribution master station and the distribution terminal, so that the distribution master station controls the switching of the switch equipment according to the operating information and fault signals.

[0076] In one embodiment, the master station cooperates with the differential protection type to complete the precise fault location, isolation and power restoration of non-fault sections through the distribution master station, and completes the upstream isolation of the fault through on-site tripping of the distribution terminal.

[0077] In one embodiment, the master station and the voltage-time / current collaborative type complete fault location and isolation on-site through the distribution terminal, and complete power transfer and restoration in the non-fault section through the distribution master station or the distribution terminal. When the distribution terminal completes power transfer and restoration on-site, the distribution master station verifies the correctness of the on-site action and optimizes fault handling as a backup protection.

[0078] In one embodiment, the master station and the intelligent distributed collaborative type complete fault location, isolation and power restoration on-site through the distribution terminal, and verify the correctness of the on-site action through the distribution master station, and serve as backup protection to optimize fault processing.

[0079] One embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the distribution network self-healing mode planning method as described above.

[0080] See also Figure 3An embodiment of the present invention provides a structural diagram of a distribution network self-healing mode planning device. The device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (for example, one or more processors) and a memory 320, and one or more storage media 330 (for example, one or more massive storage devices) for storing application programs 333 or data 332. Among them, the memory 320 and the storage medium 330 can be short-term storage or persistent storage. The program stored in the storage medium 330 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the device 300. Furthermore, the processor 310 can be configured to communicate with the storage medium 330 to execute a series of instruction operations in the storage medium on the device 300.

[0081] The device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.

[0082] 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 distribution network self-healing mode planning method, characterized in that: include: Obtain multiple distribution network samples with self-healing capabilities; The distribution network samples are parsed one by one to obtain a corresponding number of training samples, wherein the data of the training samples include the power supply area type, distribution line type, communication mode, distribution automation mode and self-healing mode of the distribution network; The power supply area type, distribution line type, communication mode, and distribution automation mode in the training samples are used as a training data set, and the self-healing mode is used as a label to train an initial classification model to obtain a self-healing mode classification model; The basic information of the distribution network to be planned is input into the self-healing mode classification model to obtain the self-healing mode of the distribution network to be planned, wherein the basic information of the distribution network to be planned includes the power supply area type, distribution line type, communication mode and distribution automation mode of the distribution network to be planned.

2. The method for planning a self-healing mode of a distribution network according to claim 1, wherein: The obtaining of multiple distribution network samples with self-healing functions includes: Obtain multiple distribution network cases with self-healing capabilities; The distribution network case is filtered according to a preset filtering condition to obtain a distribution network sample, wherein the preset filtering condition is that the self-healing mode is not compatible with the distribution network.

3. The method for planning a self-healing mode of a distribution network according to claim 1, wherein: The power supply area includes a first type of power supply area, a second type of power supply area and a third type of power supply area. The first type of power supply area satisfies σ≥15, the second type of power supply area satisfies 6≤σ<15, and the third type of power supply area satisfies σ<6, wherein σ is the load density of the power supply area, and the unit is megawatt / square kilometer; the distribution lines include cable lines and overhead lines; the communication methods include optical fiber communication, wireless public network communication and no communication conditions; the distribution automation modes include intelligent distributed local control type, centralized control type, differential protection local control type and local overlap local control type; the self-healing modes include master station centralized type, master station and differential protection collaborative type, master station and voltage time / current collaborative type and master station and intelligent distributed collaborative type.

4. The method for planning a self-healing mode of a distribution network according to claim 3, wherein: The master station centralized type obtains real-time operation information and fault signals of the distribution network and distribution equipment through two-way communication between the distribution master station and the distribution terminal, so that the distribution master station controls the switching of the switch equipment according to the operation information and fault signals.

5. The method for planning a self-healing mode of a distribution network according to claim 3, wherein: The master station and differential protection collaborative type completes the precise fault location, isolation and power restoration of non-fault sections through the distribution master station, and completes the upstream isolation of the fault through on-site tripping of the distribution terminal.

6. The method for planning a self-healing mode of a distribution network according to claim 3, wherein: The master station and the voltage-time / current collaborative type complete fault location and isolation on-site through the distribution terminal, and complete power transfer and restoration to the non-fault section through the distribution master station or the distribution terminal. When the distribution terminal completes power transfer and restoration on-site, the distribution master station verifies the correctness of the on-site action and serves as backup protection to optimize fault handling.

7. The method for planning a self-healing mode of a distribution network according to claim 3, wherein: The master station and the intelligent distributed collaborative type complete fault location, isolation and power restoration on-site through the distribution terminal, and verify the correctness of the on-site action through the distribution master station, and serve as backup protection to optimize fault processing.

8. A distribution network self-healing mode planning device, characterized in that: include: The distribution network sample acquisition module is used to obtain multiple distribution network samples with self-healing functions; A distribution network sample parsing module is used to parse the distribution network samples one by one to obtain a corresponding number of training samples, wherein the data of the training samples includes the power supply area type, distribution line type, communication mode, distribution automation mode and self-healing mode of the distribution network; A model training module is configured to train an initial classification model using the power supply area type, distribution line type, communication mode, and distribution automation mode in the training samples as a training data set and the self-healing mode as a label to obtain a self-healing mode classification model; The self-healing mode planning module is used to input the basic information of the distribution network to be planned into the self-healing mode classification model to obtain the self-healing mode of the distribution network to be planned. The basic information of the distribution network to be planned includes the power supply area type, distribution line type, communication mode and distribution automation mode of the distribution network to be planned.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the distribution network self-healing mode planning method according to any one of claims 1 to 7.

Images