A simulation system and test method for defects in medium and low voltage distribution networks

Abstract

This invention discloses a simulation system and test method for defects in a medium- and low-voltage distribution network, relating to the field of power system fault diagnosis and recovery technology. The method includes: deploying sensors to collect distribution network operation data and preprocessing and integrating the distribution network dataset; extracting distribution network fault feature vectors from the dataset using FFT transformation; constructing a fault diagnosis model based on the distribution network fault feature vectors using Support Vector Machine (SVM); establishing a simulation model of the medium- and low-voltage distribution network using power system simulation software PSCAD; simulating distribution network faults in the simulation model; diagnosing faults in the simulation model using the fault diagnosis model; formulating and implementing recovery strategies based on the diagnosis results; evaluating the effectiveness of the recovery strategies; adjusting the recovery strategies based on the evaluation results; and repeatedly testing in the simulation environment until the optimal recovery strategy is found. Finally, the optimal recovery strategy is applied to the actual distribution network, and its performance is continuously monitored and improved.

Description

Technical Field

[0001] This invention relates to the field of power system fault diagnosis and recovery technology, and in particular to a medium- and low-voltage true-type distribution network defect simulation system and its test method. Background Technology

[0002] With the development of smart distribution network technology, the complexity of medium and low voltage distribution networks is constantly increasing. The detection and diagnosis of distribution network faults has become a key link in ensuring the safe and stable operation of the distribution network. Traditional fault detection methods mainly rely on manual inspection and simple automated equipment. These methods are inadequate when faced with increasingly complex distribution network structures. In recent years, with the advancement of sensing technology and data processing technology, it has become possible to monitor the operating status of the distribution network in real time by deploying sensor networks. However, how to effectively extract valuable fault features from a large amount of collected data and use these features to accurately diagnose the fault type and location remains a challenge. In addition, traditional fault recovery strategies are often based on static models and cannot adapt to the dynamic changes in the distribution network operating environment.

[0003] Currently, some research has attempted to improve the accuracy of fault diagnosis through data-driven methods. Fourier transform (FFT) is used to perform frequency domain analysis on distribution network data to extract fault features, and then machine learning algorithms such as support vector machines (SVM) are combined to build fault diagnosis models. This method can improve the accuracy of fault diagnosis to some extent, but it still has some limitations in practical applications. First, traditional FFT analysis usually only considers single-type signal features, making it difficult to comprehensively capture the complex characteristics of distribution network faults. Second, existing fault diagnosis models perform poorly when dealing with multivariate data, especially when faced with multiple different types of signals. Furthermore, most existing fault recovery strategies are based on static optimization methods, failing to fully consider the real-time changes in the operating state of the distribution network, thus limiting the effectiveness of the recovery strategies. Therefore, a fault diagnosis and recovery strategy that can effectively integrate multiple signal features and adapt to the dynamic changes of the distribution network in real time is needed. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a simulation system and test method for defects in medium and low voltage distribution networks to solve the problem that traditional FFT analysis usually only considers a single type of signal feature and is difficult to fully capture the complex characteristics of distribution network faults.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for simulating defects in a medium- and low-voltage real-type distribution network, comprising,

[0008] Deploy sensors to collect power distribution network operation data, and preprocess and integrate the power distribution network dataset;

[0009] FFT transformation is used to extract distribution network fault feature vectors from the distribution network dataset, and a fault diagnosis model is constructed based on the distribution network fault feature vectors using support vector machine (SVM).

[0010] Using the power system simulation software PSCAD, a simulation model of a medium- and low-voltage distribution network was established, and distribution network faults were simulated in the simulation model.

[0011] Use a fault diagnosis model to diagnose faults in a simulation model, formulate and implement recovery strategies based on the diagnosis results, and evaluate the effectiveness of the recovery strategies.

[0012] Adjust the recovery strategy based on the evaluation results and test it repeatedly in the simulation environment until the optimal recovery strategy is found. Apply the optimal recovery strategy to the actual distribution network and continuously monitor and improve its performance.

[0013] Secondly, this invention provides a fault simulation system for medium- and low-voltage distribution networks, comprising:

[0014] Data acquisition module: Deploys sensors to collect power distribution network operation datasets, providing raw data sources for subsequent analysis;

[0015] Data preprocessing module: Cleans and formats the collected data to ensure that the data quality meets the analysis requirements;

[0016] Feature extraction module: Uses FFT transformation to extract feature vectors related to distribution network faults from the processed data, providing a basis for modeling;

[0017] Fault diagnosis model construction module: Based on the extracted distribution network fault feature vectors, a fault diagnosis model is constructed using support vector machines;

[0018] Simulation environment setup module: Use power system simulation software such as PSCAD to build a simulation model of medium and low voltage distribution networks to simulate fault conditions in real distribution network environments;

[0019] Fault diagnosis module: The fault diagnosis model is used in the simulation model to identify faults and formulate preliminary recovery strategies accordingly;

[0020] Recovery Strategy Optimization Module: Evaluates the effectiveness of diagnostic results and recovery strategies, and continuously adjusts and optimizes the recovery strategies based on evaluation feedback until the best results are achieved;

[0021] Continuous Improvement Module: The finalized recovery strategy is applied to the actual distribution network, and its performance is further improved through continuous monitoring.

[0022] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the method for simulating defects in a medium- and low-voltage distribution network as described in the first aspect of the present invention.

[0023] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for simulating defects in a medium- and low-voltage real-type distribution network as described in the first aspect of the present invention.

[0024] The beneficial effects of this invention are as follows: by deploying a sensor network to comprehensively collect distribution network operation data, and using FFT transformation to extract fault feature vectors from multiple types of signals, a fault diagnosis model is constructed using support vector machine based on these feature vectors, which improves the accuracy and robustness of fault diagnosis. By establishing a simulation model in the power system simulation software PSCAD and simulating distribution network faults, the fault recovery strategy is further optimized, enabling it to better adapt to the dynamic changes of the distribution network, thereby improving the overall operating efficiency and reliability of the distribution network. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of the method for simulating defects in a low-voltage, medium-voltage distribution network in Example 1.

[0027] Figure 2 This is a system diagram of the low-voltage distribution network defect simulation system in Example 1. Detailed Implementation

[0028] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0029] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides a method for simulating defects in a medium- and low-voltage distribution network, comprising the following steps:

[0030] S1 deploys sensors to collect power distribution network operation data and preprocesses and integrates the power distribution network dataset;

[0031] Current transformers, voltage transformers, temperature sensors, and power meters are deployed at substations, feeder outlets, load concentration areas, and distributed energy access points to collect distribution network operation datasets. Wavelet transform is used to denoise the collected distribution network operation datasets.

[0032] Current transformers, voltage transformers, temperature sensors, and power meters are deployed at substations, feeder outlets, load concentration areas, and distributed energy access points to collect current, voltage, temperature, and power data. Wavelet transform is used to denoise the collected distribution network operation dataset.

[0033] The data after noise reduction are current x1, voltage x2, temperature x3, and power x4;

[0034] Let the collected power distribution network dataset be x, where x = (x1, x2, ..., x4).

[0035] S2 uses FFT transformation to extract distribution network fault feature vectors from the preprocessed distribution network operation dataset, and uses support vector machine (SVM) to build a fault diagnosis model based on the distribution network fault feature vectors.

[0036] The FFT transform is used to extract the distribution network fault feature vector from the preprocessed distribution network operation dataset. The expression is as follows:

[0037]

[0038] Among them, X i Let f represent the frequency domain representation of the i-th type of data; f represents the frequency, t represents the time index, N represents the number of sampling points of the signal, and x represents the frequency. i Let represent the i-th type of distribution network operation data, e represent the base of the natural logarithm, j represent the imaginary unit, and π represent pi.

[0039] The FFT transform is used to convert the time domain signal into the frequency domain signal and extract the fault feature vector from it, which enhances the ability to represent fault features.

[0040] The energy E of each signal within the target frequency range i for:

[0041]

[0042] Among them, f h f represents the upper limit of the target frequency range. l Indicates the lower limit of the target frequency range;

[0043] The expression for the fault feature vector E of the distribution network is:

[0044] E = [E1, E2, ..., E m ] T;

[0045] Where E1 represents the energy of the first type of signal within the target frequency range, E2 represents the energy of the second type of signal within the target frequency range, and E... m This represents the energy of the m-th type of signal within the target frequency range;

[0046] Traditional fault feature extraction methods only consider single-type signal features, making it difficult to fully capture the complex characteristics of distribution network faults. This invention extracts fault features of multiple types of signals through FFT transformation, improving the accuracy and robustness of fault diagnosis.

[0047] First, determine the kernel function K(E). i ,E), RBF is chosen as the kernel function:

[0048] K(E i E j )=exp(-γ∥E i -E j ∥ 2 );

[0049] Where exp represents an exponential function, γ represents a positive constant, and E i and E j This represents two distinct fault feature vectors;

[0050] By using SVM to build a fault diagnosis model and selecting an appropriate kernel function, the model can handle nonlinear problems and improve diagnostic accuracy.

[0051] Based on the fault feature vectors of the distribution network, a fault diagnosis model is constructed using Support Vector Machine (SVM), expressed as:

[0052]

[0053] Where D represents the fault diagnosis result, n represents the number of fault feature vectors, and α i Denotes Lagrange multipliers, y i K(E) represents the label of the training sample. i E j ) represents the kernel function, and b represents the bias term;

[0054] Existing fault diagnosis models perform poorly when dealing with multivariate data, especially when faced with various types of signals. This invention improves the accuracy of fault diagnosis by using an SVM model that combines multiple signal features.

[0055] S3 uses the power system simulation software PSCAD to build a simulation model of a medium- and low-voltage distribution network and simulates distribution network faults in the model.

[0056] In PSCAD, construct a basic model containing elements such as substations, feeders, load nodes, and distributed energy access points, and connect these components according to the actual distribution network topology.

[0057] Based on the actual power distribution network data, set the line resistance, transformer ratio, load type and size, and distributed power supply capacity in the basic model;

[0058] Set initial operating conditions, including the voltage level, frequency, and load distribution of the distribution network;

[0059] Define the various types of failures that may occur, and select the geographical location and time when the failure will occur;

[0060] Using PSCAD to build a simulation model of medium and low voltage distribution networks can simulate various fault scenarios in actual distribution networks. By simulating the occurrence and impact of faults in the simulation model, the behavior changes of the distribution network before and after the fault can be observed more intuitively, and the operation data of the distribution network during the fault can be recorded.

[0061] Start the PSCAD simulation, observe the behavior changes of the distribution network before and after the fault occurs, and record the distribution network operation data during the fault period.

[0062] S4 uses a fault diagnosis model to diagnose faults in the simulation model, formulates and implements recovery strategies based on the diagnosis results, and evaluates the effectiveness of the recovery strategies.

[0063] During the simulation, we collect real-time data on current I, voltage V, temperature T, and power P from the simulation model, convert them into a distribution network fault feature vector E, and then input it into the SVM model to obtain the fault diagnosis result D. We also record the fault recovery time T. rec Trouble-free uptime R sys The fault tolerance S is obtained by comparing the voltage fluctuations of the system before and after the fault. sys ;

[0064] Based on this data, fault recovery strategies can be continuously optimized. By disconnecting non-critical loads, attempting reclosing, and switching to backup power, the goal of minimizing fault recovery time and maximizing system reliability and stability can be achieved.

[0065] Based on the diagnostic results, a recovery strategy is formulated and implemented. A recovery strategy R based on genetic algorithm optimization is adopted, and the goal of this strategy is to minimize the fault recovery time T. rec At the same time, maximize the system's fault-free uptime R. sys and fault tolerance S sysThe recovery strategy R will be implemented by disconnecting non-critical loads, attempting reclosing, and switching to backup power. The effectiveness of the recovery strategy will be evaluated using a comprehensive evaluation function F, which considers recovery time, system reliability, and stability. The expression for the comprehensive evaluation function F is:

[0066]

[0067] This process not only improves the efficiency of fault recovery, but also improves the overall operating efficiency and reliability of the distribution network through continuous optimization and testing.

[0068] Among them, w i w represents the importance weight of the i-th type of fault. 1,i w represents the weight of recovery time for the i-th type of fault. 2,i w represents the weight of the system's fault-free uptime for the i-th type of fault. 3,i This represents the weight of the system's fault tolerance capability for the i-th type of fault.

[0069] S5 adjusts the recovery strategy based on the evaluation results and repeatedly tests it in the simulation environment until the optimal recovery strategy is found. The optimal recovery strategy is then applied to the actual distribution network to continuously monitor and improve its performance.

[0070] Different strategy combinations are repeatedly tested in the simulation environment. The strategy parameters are adjusted based on the results of the previous round. A threshold T is set. When F(R(D))≤T, the strategy parameter adjustment continues in the next round until F(R(D))>T.

[0071] When F(R(D))>T, the recovery strategy R is applied to the actual distribution network. Current, voltage, temperature, and power data from the actual distribution network are continuously collected and converted into a distribution network fault feature vector. This vector is then input into the SVM model to obtain fault diagnosis results. The recovery strategy R is continuously improved by combining the comprehensive evaluation function. The expression for the updated recovery strategy R is as follows:

[0072]

[0073] Among them, R * This represents the updated recovery strategy, where t represents the number of iterations, and Δw i Indicates the increment of the weight;

[0074] By repeatedly testing and adjusting the recovery strategy in a simulation environment, the optimal recovery strategy can be found by dynamically adapting to changes in the operating state of the distribution network. This method overcomes the shortcomings of traditional methods in terms of dynamic adaptability and improves the real-time performance and effectiveness of the recovery strategy.

[0075] This embodiment also provides a fault simulation system for medium and low voltage distribution networks, including:

[0076] Data acquisition module: Deploys sensors to collect power distribution network operation datasets, providing raw data sources for subsequent analysis;

[0077] Data preprocessing module: Cleans and formats the collected data to ensure that the data quality meets the analysis requirements;

[0078] Feature extraction module: Uses FFT transformation to extract feature vectors related to distribution network faults from the processed data, providing a basis for modeling;

[0079] Fault diagnosis model construction module: Based on the extracted distribution network fault feature vectors, a fault diagnosis model is constructed using support vector machines;

[0080] Simulation environment setup module: Use power system simulation software such as PSCAD to build a simulation model of medium and low voltage distribution networks to simulate fault conditions in real distribution network environments;

[0081] Fault diagnosis module: The fault diagnosis model is used in the simulation model to identify faults and formulate preliminary recovery strategies accordingly;

[0082] Recovery Strategy Optimization Module: Evaluates the effectiveness of diagnostic results and recovery strategies, and continuously adjusts and optimizes the recovery strategies based on evaluation feedback until the best results are achieved;

[0083] Continuous Improvement Module: The finalized recovery strategy is applied to the actual distribution network, and its performance is further improved through continuous monitoring.

[0084] This embodiment also provides a computer device applicable to the simulation method of defects in a medium- and low-voltage real distribution network, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the simulation method of defects in a medium- and low-voltage real distribution network as proposed in the above embodiment.

[0085] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0086] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the method for simulating defects in a low-voltage, realistic distribution network as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0087] In summary, this invention improves the accuracy and robustness of fault diagnosis by: deploying a sensor network to comprehensively collect distribution network operation data; using FFT transform to extract fault feature vectors from multiple types of signals; and constructing a fault diagnosis model using support vector machines based on these feature vectors. Furthermore, by establishing a simulation model in the power system simulation software PSCAD and simulating distribution network faults, the fault recovery strategy is further optimized to better adapt to the dynamic changes of the distribution network, thereby improving the overall operating efficiency and reliability of the distribution network.

Claims

1. A method for simulating defects in a medium- and low-voltage distribution network, characterized in that, include: Data on power distribution network operation is collected by sensors, and the data is preprocessed to generate a power distribution network dataset. FFT transform is used to extract distribution network fault feature vectors from the distribution network dataset. A fault diagnosis model is then constructed based on these feature vectors using a Support Vector Machine (SVM). The expression for the distribution network fault feature vector E is: E=[E1,E2,...,E m ] T ; Where E1 represents the energy of the first type of signal within the target frequency range, E2 represents the energy of the second type of signal within the target frequency range, and E... m This represents the energy of the m-th type of signal within the target frequency range; Using the power system simulation software PSCAD, a simulation model of a medium- and low-voltage distribution network was established, and distribution network faults were simulated in the simulation model. A fault diagnosis model is used to diagnose distribution network faults in a simulation model. Based on the diagnosis results, recovery strategies are formulated and implemented, and the effectiveness of these strategies is evaluated. During the simulation, real-time data on current (I), voltage (V), temperature (T), and power (P) are collected from the simulation model and converted into a distribution network fault feature vector (E). This vector is then input into the SVM model to obtain the fault diagnosis result (D), and the fault recovery time (T) is recorded. rec Trouble-free uptime R sys The fault tolerance S is obtained by comparing the voltage fluctuations of the system before and after the fault. sys ; Based on the diagnostic results, a recovery strategy is formulated and implemented. A recovery strategy R based on genetic algorithm optimization is adopted, and the goal of this strategy is to minimize the fault recovery time T. rec At the same time, maximize the system's fault-free uptime R. sys and fault tolerance S sys The recovery strategy R will be implemented by disconnecting non-critical loads, attempting reclosing, and switching to backup power. The effectiveness of the recovery strategy will be evaluated by a comprehensive evaluation function F(R(D)), which takes into account three factors: recovery time, system reliability, and stability. The recovery strategy is adjusted based on the evaluation results and repeatedly tested in the simulation model until the optimal recovery strategy is found. The optimal recovery strategy is then applied to the actual distribution network, and the operation data of the distribution network is continuously monitored and the optimal recovery strategy is improved. Different strategy combinations are repeatedly tested in the simulation environment, and the strategy parameters are adjusted according to the results of the previous round. A threshold T is set. When F(R(D))≤T, the next round of strategy parameter adjustment continues until F(R(D))>T. The recovery strategy R when F(R(D))>T is applied to the actual distribution network. Current, voltage, temperature, and power data in the actual distribution network are continuously collected and converted into distribution network fault feature vectors. These vectors are then input into the SVM model to obtain fault diagnosis results. The recovery strategy R is continuously improved by combining the comprehensive evaluation function.

2. The method for simulating defects in a medium- and low-voltage distribution network as described in claim 1, characterized in that: The specific steps for collecting power distribution network operation data through sensors and preprocessing the data to generate a power distribution network dataset are as follows: Current transformers, voltage transformers, temperature sensors, and power meters are deployed at substations, feeder outlets, load concentration areas, and distributed energy access points to collect current, voltage, temperature, and power data. Wavelet transform is used to denoise the distribution network dataset. The data after noise reduction are current x1, voltage x2, temperature x3, and power x4; Let the collected power distribution network dataset be x, where x = (x1, x2, ..., x4); Extract distribution network fault feature vectors from the preprocessed distribution network operation dataset.

3. The method for simulating defects in a medium- and low-voltage distribution network as described in claim 2, characterized in that: The specific steps for extracting distribution network fault feature vectors from the distribution network dataset using FFT transformation are as follows: FFT transformation is used to extract distribution network fault feature vectors from preprocessed distribution network operation datasets.

4. The method for simulating defects in a medium- and low-voltage distribution network as described in claim 3, characterized in that: The specific steps for extracting distribution network fault feature vectors from the preprocessed distribution network operation dataset using FFT transformation include: Determine the frequency domain representation of each type of distribution network data.

5. The method for simulating defects in a medium- and low-voltage distribution network as described in claim 4, characterized in that: The steps for extracting distribution network fault feature vectors from the preprocessed distribution network operation dataset using FFT transformation further include: Determine the energy E of each type of distribution network data within the target frequency range. i ; Obtain the expression for the fault feature vector E of the distribution network; A fault diagnosis model is constructed using support vector machine (SVM), which takes the fault feature vector of the distribution network as input and outputs the fault diagnosis result.

6. The method for simulating defects in a medium- and low-voltage distribution network as described in claim 5, characterized in that: The specific steps for constructing a fault diagnosis model based on distribution network fault feature vectors using Support Vector Machine (SVM) include: First, determine the kernel function K(E). i ,E), select RBF as the kernel function; establish a simulation model of a medium and low voltage distribution network in the power system simulation software PSCAD, and simulate distribution network faults.

7. The method for simulating defects in a medium- and low-voltage distribution network as described in claim 6, characterized in that: The method involves using the power system simulation software PSCAD to establish a simulation model of a medium- and low-voltage distribution network, and simulating distribution network faults within the simulation model. Specific steps include: An element-based basic model is constructed in the power system simulation software PSCAD, wherein the elements include substations, feeders, load nodes, and distributed energy access points, and the elements are connected according to the actual distribution network topology. Based on the actual power distribution network data, set the line resistance, transformer ratio, load type and size, and distributed power supply capacity in the basic model.

8. The method for simulating defects in a medium- and low-voltage distribution network as described in claim 7, characterized in that: The step of using power system simulation software PSCAD to establish a simulation model of a medium- and low-voltage distribution network and simulating distribution network faults in the model includes the following specific steps: Set initial running conditions; Define the various types of failures that may occur, and select the geographical location and time when the failure will occur; Start the power system simulation software PSCAD to perform simulation, observe the behavior changes of the distribution network before and after the fault occurs, and record the distribution network operation data during the fault period; The fault diagnosis model is used to diagnose the faults in the simulation model. Based on the diagnosis results, a recovery strategy is formulated and implemented, and the effectiveness of the recovery strategy is evaluated.

9. A system for simulating defects in a medium- and low-voltage distribution network, based on the method for simulating defects in a medium- and low-voltage distribution network as described in any one of claims 1 to 8, characterized in that: include, Data acquisition module: Deploys sensors to collect power distribution network operation datasets, providing raw data sources for subsequent analysis; Data preprocessing module: Cleans and formats the collected data to ensure that the data quality meets the analysis requirements; Feature extraction module: Uses FFT transformation to extract feature vectors related to distribution network faults from the processed data, providing a basis for modeling; Fault diagnosis model construction module: Based on the extracted distribution network fault feature vectors, a fault diagnosis model is constructed using support vector machines.

10. The medium- and low-voltage true-type distribution network defect simulation system according to claim 9, characterized in that: It also includes, Simulation environment setup module: Use PSCAD power system simulation software to build a simulation model of medium and low voltage distribution networks to simulate fault conditions in real distribution network environments; Fault diagnosis module: The fault diagnosis model is used in the simulation model to identify faults and formulate preliminary recovery strategies accordingly; Recovery Strategy Optimization Module: Evaluates the effectiveness of diagnostic results and recovery strategies, and continuously adjusts and optimizes the recovery strategies based on evaluation feedback until the best results are achieved; Continuous Improvement Module: The finalized recovery strategy is applied to the actual distribution network, and its performance is further improved through continuous monitoring.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for simulating defects in a medium- and low-voltage real-type distribution network as described in any one of claims 1 to 8.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for simulating defects in a medium- and low-voltage real-type distribution network as described in any one of claims 1 to 8.

Images