Digital twin driven low-voltage power distribution network regional self-healing control method and device

Abstract

The application discloses a digital twin driven low-voltage power distribution network regional self-healing control method and device, relates to the technical field of power systems, and comprises the following steps: establishing a power distribution network driven simulation model of a target low-voltage power distribution network based on a digital twin driven platform, mapping real-time fault data sets to the model, and outputting a first power distribution network topology and a second power distribution network topology, i.e., a protection response power distribution network at the time of fault occurrence and after the fault; calculating self-healing priority weights of fault lines according to the state characteristics of the first power distribution network topology and the second power distribution network topology, and performing fault line priority self-healing control on the first power distribution network topology. The application solves the technical problems of long response time, low recovery efficiency and insufficient power supply reliability of the existing low-voltage power distribution network after a fault occurs and relies on manual intervention, and achieves the technical effects of realizing fast-response power distribution network fault recovery, improving fault recovery efficiency and power supply reliability through the digital twin driven self-healing control method.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and more specifically to a digital twin-driven method and apparatus for regional self-healing control of low-voltage distribution networks. Background Technology

[0002] In modern power systems, the low-voltage distribution network, as the final link connecting power supply and end users, directly impacts users' electricity experience and power quality. Low-voltage distribution networks are complex in structure, contain numerous devices, and are significantly affected by environmental factors, making them prone to various faults such as line short circuits and equipment overloads. If power cannot be restored promptly after a fault, it will severely impact users' lives and production. However, traditional distribution network fault recovery typically relies on manual intervention, resulting in a cumbersome process and long response time, failing to meet the demands of modern power systems for efficient and rapid recovery. Furthermore, existing fault recovery methods primarily rely on manual analysis, control, and dispatch, making it difficult to respond in real-time to complex fault conditions in the distribution network, leading to prolonged fault repair times and affecting the stability and reliability of power supply to users. Summary of the Invention

[0003] This application provides a digital twin-driven self-healing control method and device for low-voltage distribution networks, which solves the technical problems of existing low-voltage distribution networks relying on manual intervention after a fault, resulting in long response times, low recovery efficiency, and insufficient power supply reliability.

[0004] The first aspect of this application provides a digital twin-driven method for regional self-healing control of low-voltage distribution networks. The method includes: establishing a distribution network driving simulation model of a target low-voltage distribution network based on a digital twin driving platform; mapping a real-time fault dataset of the target low-voltage distribution network to the distribution network driving simulation model, and outputting a first distribution network topology and a second distribution network topology, wherein the first distribution network topology is the distribution network where the fault occurred, and the second distribution network topology is the protection response distribution network after the fault; calculating the self-healing priority weight of the faulted lines according to the state characteristics of the first distribution network topology and the second distribution network topology, and performing faulted line priority self-healing control on the first distribution network topology according to the comprehensive self-healing priority weight of the faulted lines.

[0005] A second aspect of this application provides a digital twin-driven self-healing control device for a low-voltage distribution network area. The device includes: a twin simulation model construction module for establishing a distribution network driving simulation model of a target low-voltage distribution network based on a digital twin-driven platform; a distribution network topology construction module for mapping real-time fault datasets of the target low-voltage distribution network to the distribution network driving simulation model, outputting a first distribution network topology and a second distribution network topology, wherein the first distribution network topology is the fault-occurring distribution network, and the second distribution network topology is the protection response distribution network after the fault; and a fault self-healing control module for calculating the fault line self-healing priority weight based on the state characteristics of the first and second distribution network topologies, and performing fault line priority self-healing control on the first distribution network topology according to the comprehensive weight of the fault line self-healing priority.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] This application provides a digital twin-driven self-healing control method and device for low-voltage distribution networks, relating to the field of power system technology. It constructs a simulation model of the low-voltage distribution network through a digital twin-driven platform, and generates the distribution network topology before and after the fault by real-time fault data mapping. Using topology state characteristics, it calculates the self-healing priority weight of the faulty lines, prioritizes the faulty lines, and then executes self-healing control, achieving efficient fault recovery of the distribution network. This solves the technical problems of existing low-voltage distribution networks relying on manual intervention after a fault, resulting in long response times, low recovery efficiency, and insufficient power supply reliability. It achieves rapid response distribution network fault recovery through a digital twin-driven self-healing control method, improving fault recovery efficiency and power supply reliability. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0009] Figure 1 A schematic flowchart of a digital twin-driven self-healing control method for low-voltage distribution network areas provided in an embodiment of this application;

[0010] Figure 2 This is a schematic diagram of the structure of a digital twin-driven low-voltage distribution network area self-healing control device provided in an embodiment of this application.

[0011] Figure labeling: Twin simulation model construction module 11, distribution network topology construction module 12, fault self-healing control module 13. Detailed Implementation

[0012] This application provides a digital twin-driven self-healing control method and device for low-voltage distribution networks, which solves the technical problems of existing low-voltage distribution networks relying on manual intervention after a fault, resulting in long response times, low recovery efficiency, and insufficient power supply reliability.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0015] Example 1, as Figure 1 As shown, this application provides a digital twin-driven self-healing control method for low-voltage distribution network areas, the method comprising:

[0016] P10: Establish a distribution network drive simulation model for the target low-voltage distribution network based on the digital twin drive platform.

[0017] Specifically, the first step is to establish a distribution network drive simulation model of the target low-voltage distribution network based on a digital twin drive platform. The digital twin drive platform is a virtual simulation environment integrating multiple advanced technologies. It can construct a virtual model highly consistent with the physical entity through real-time data acquisition and processing, and achieve dynamic interaction and synchronous updates between the two. Specifically, the platform utilizes IoT technology to collect various equipment operating data, environmental parameters, and topology information in the low-voltage distribution network. This data serves as the basic input for building the simulation model, ensuring that the model accurately reflects the actual operating status and characteristics of the power grid.

[0018] When establishing a distribution network simulation model, the first step is to model the physical structure of the distribution network, including power equipment, lines, transformers, switches, loads, and generating nodes. These devices and their connections are represented in the simulation model through nodes and branches. The physical parameters of the distribution network, such as current, voltage, and power, also need to be accurately represented in the simulation model to ensure that the model can comprehensively reflect various states of the power grid during operation.

[0019] Subsequently, algorithms and mathematical models, such as load flow analysis and transient stability analysis, are used to describe the characteristics of power flow, load distribution, and fault propagation in the distribution network. The digital twin platform will calibrate the model in real time based on real-time collected monitoring data, ensuring that the simulation results are highly consistent with the actual operating state of the distribution network. This allows the platform to predict and simulate various fault modes and their possible consequences, thereby providing decision support for self-healing control after a fault.

[0020] To ensure the real-time performance and accuracy of the simulation model, the digital twin-driven platform utilizes data synchronization technology to enable real-time data interaction between the physical power grid and the virtual model. This means that the simulation model can receive operational data from the actual power grid in real time and dynamically adjust its own state based on this data, thereby maintaining a high degree of consistency with the physical power grid. This makes the simulation model not merely a static virtual copy, but a dynamic system that can reflect the real-time operating status of the physical power grid.

[0021] After the model is built, rigorous verification and optimization are required. The accuracy and reliability of the model are verified by comparing the output of the simulation model with the actual operating data of the power grid. If deviations are found, the model parameters need to be adjusted and optimized to improve the simulation accuracy. This process may require multiple iterations until the model can accurately simulate the operating characteristics of the actual power grid.

[0022] P20: Map the real-time fault dataset of the target low-voltage distribution network to the distribution network driving simulation model, and output the first distribution network topology and the second distribution network topology. The first distribution network topology is the distribution network where the fault occurred, and the second distribution network topology is the protection response distribution network after the fault.

[0023] Furthermore, step P20 in this embodiment of the application also includes:

[0024] P21: Obtain the real-time fault dataset of the target low-voltage distribution network, which includes fault current waveform data, fault topology metadata, protection device action signals, and circuit breaker switch status; P22: Map the fault current waveform data and fault topology metadata to the distribution network drive simulation model for simulation, and output the first distribution network topology; P23: Map the protection device action signals and circuit breaker switch status to the distribution network drive simulation model for simulation until the protection action topology update is completed and the second distribution network topology is output.

[0025] It should be understood that mapping the real-time fault dataset of the target low-voltage distribution network to the distribution network drive simulation model generates the distribution network topology before and after the fault, ensuring that the simulation model can reflect the distribution network state after the fault occurs and the protection response, and providing accurate decision-making basis for subsequent self-healing control.

[0026] First, a real-time fault dataset of the target low-voltage distribution network is acquired. This dataset encompasses various key information, including fault current waveform data, fault topology metadata, protection device action signals, and circuit breaker switch status. The fault current waveform data records the current changes during a fault, serving as the basis for determining the nature and location of the fault. The fault topology metadata includes the distribution network's topology information at the time of the fault, indicating the operational status of the faulty line and related equipment. The protection device action signals and circuit breaker switch status reflect the response of the protection devices after the fault occurs, including whether the circuit breaker action was successful and whether the protection equipment functioned.

[0027] Next, the fault current waveform data and fault topology metadata are mapped to the distribution network drive simulation model for simulation. Through the mapping of these data, the distribution network simulation model can accurately reconstruct the distribution network topology at the time of the fault and output the first distribution network topology. This topology represents the distribution network state before the fault occurred and can reflect the current and voltage distribution of the distribution network and the state of the faulty line at the time of the fault, helping to analyze the root cause and scope of the fault.

[0028] Subsequently, the protection device action signals and circuit breaker switch states are mapped to the distribution network drive simulation model for further simulation. At this point, the model adjusts the distribution network topology based on the protection device action signals and circuit breaker switch states, outputting a second distribution network topology. This second distribution network topology represents the state of the distribution network after a fault, following the protection response, including whether the circuit breaker successfully isolated the fault area, whether the protection device was correctly activated, and the power flow in the remaining normal power supply areas. This topology reflects the protection response results of the power grid after a fault and provides important reference for subsequent self-healing control. Specifically, the protection device action signals and circuit breaker switch states are first mapped to the distribution network drive simulation model, and a protection action topology update is performed. The protection device action signals reflect the protection response of the distribution network after a fault, including whether the protection device has detected the fault and issued an isolation signal. The circuit breaker switch states indicate whether the circuit breaker has successfully operated, disconnecting the faulty line and isolating the fault area. By inputting these data into the simulation model, the model can perform topology updates based on the protection device action signals and circuit breaker switch states, simulating the state adjustment of the distribution network after a fault. For example, when a protection device trips a circuit breaker on a line, the simulation model updates the line's state accordingly, reflecting the topological changes in the power grid after the protection action. In this way, the simulation model can accurately simulate the power grid's operating state after the protection device's action and obtain the protection response simulation results.

[0029] The simulation process will then continue until all protection actions are completed and the topology update is finished. After the protection action topology update is complete, the simulation model will generate protection response simulation results, reflecting the distribution network operation status after the protection devices operate and the circuit breakers switch. Based on these results, the distribution network topology will be updated to a second distribution network topology, which represents the distribution network state after the protection response. This topology typically includes the isolated fault area and the still-operating power supply area. For example, if a line is disconnected due to a fault, the second distribution network topology will show the status change of that line and the updates of related equipment and nodes. By outputting the second distribution network topology, detailed grid status information can be provided for subsequent fault analysis and self-healing control, helping to develop more effective self-healing strategies.

[0030] Through the above steps, the simulation model can not only accurately reconstruct the distribution network topology before and after the fault, but also simulate how the distribution network recovers through protection responses after the fault. The outputs of these two topologies provide accurate grid state information for subsequent calculation of fault line self-healing priority weights and self-healing control, ensuring the accuracy and effectiveness of the self-healing control strategy.

[0031] Furthermore, step P22 in the embodiments of this application also includes:

[0032] P22-1: Read the initial operating status dataset of the target low-voltage distribution network; P22-2: Synchronize the initial operating status dataset to the distribution network drive simulation model for initial state synchronization, map the fault current waveform data and fault topology metadata to the synchronized distribution network drive simulation model for simulation, and obtain the simulated operating status dataset; P22-3: Compare the simulated operating status dataset with the pre-stored healthy operating status dataset to locate the fault, and output the first distribution network topology.

[0033] Optionally, the process of mapping fault current waveform data and fault topology metadata to the distribution network drive simulation model and outputting the first distribution network topology can be further refined. Specifically, it is first necessary to read the initial operating state dataset of the target low-voltage distribution network. This dataset contains various operating parameters and status information of the distribution network before the fault occurs, such as current, voltage, power, and equipment operating status. This initial operating state data is an important foundation for fault simulation and analysis, providing accurate initial conditions for subsequent simulations.

[0034] Next, the initial operating state dataset is synchronized to the distribution network drive simulation model to ensure that the initial state of the simulation model is consistent with the initial operating state of the actual distribution network. This synchronization process can be achieved through the data synchronization mechanism of the digital twin drive platform to ensure that the simulation model can accurately reflect the actual operating status of the distribution network before the fault occurs. After completing the initial state synchronization, the fault current waveform data and fault topology metadata are mapped to the distribution network drive simulation model that has been synchronized to the initial state for simulation. The fault current waveform data helps the simulation model accurately reflect the change process of the fault current, while the fault topology metadata provides detailed information about the distribution network topology at the time of the fault. With the input of these data, the simulation model can simulate the operating state of the distribution network at the time of the fault and generate a simulated operating state dataset. This dataset contains operating parameters of the grid such as current, voltage, and power after the fault occurs, as well as the location of the fault point and information on the affected equipment, which can provide data support for fault location.

[0035] Subsequently, the generated simulated operating state dataset is compared with the pre-stored healthy operating state dataset. The healthy operating state dataset is constructed based on typical state data of the distribution network during normal operation and reflects the ideal operating state of the distribution network under fault-free conditions. By comparing the simulated operating state dataset and the healthy operating state dataset, the changes in the power grid state after a fault can be clearly identified, and the specific location and cause of the fault can be found. Based on the comparison results, a first distribution network topology is output, which represents the distribution network state at the time of the fault and can provide the specific location of the fault, the impact range of the faulty line, and the operating status of the system.

[0036] P30: Calculate the priority weight of fault line self-healing based on the state characteristics of the first and second distribution network topologies, and implement fault line priority self-healing control on the first distribution network topology according to the comprehensive weight of fault line self-healing priority.

[0037] Furthermore, based on the state characteristics of the first and second distribution network topologies, the priority weight for fault line self-healing is calculated. In this embodiment, step P30 further includes:

[0038] P31: Decompose the first distribution network topology into faulty lines, outputting multiple faulty lines; P32: Identify multiple first-group self-healing priority weights for the multiple faulty lines based on the first group of fault self-healing impact indicators of the first distribution network topology; wherein, the first group of fault self-healing impact indicators includes fault current level indicators, near-area voltage drop indicators, and protection action failure risk indicators. P33: Identify multiple second-group self-healing priority weights for the multiple faulty lines based on the second group of fault self-healing impact indicators of the second distribution network topology; wherein, the second group of fault self-healing impact indicators includes power outage load key indicators, affected user scale indicators, power restoration feasibility indicators, and power supply key indicators of the line to which the faulty lines belong. P34: Perform a weighted fitting of the multiple first-group self-healing priority weights and the multiple second-group self-healing priority weights to obtain multiple self-healing priority comprehensive weights for the multiple faulty lines.

[0039] It should be understood that, based on the distribution network topology at the time of the fault, namely the state characteristics of the first and second distribution network topologies, the self-healing priority of each faulty line should be comprehensively assessed to ensure that the most critical faulty lines can be repaired first, thereby improving the recovery efficiency and reliability of the distribution network.

[0040] Specifically, the first step is to decompose the faulty lines in the first distribution network topology. By analyzing the fault points and affected lines in the first distribution network topology, the complex fault network is decomposed into multiple independent faulty lines to facilitate subsequent self-healing priority weight calculations. Since each line has a different impact on the overall operation of the distribution network after a fault, each faulty line must be assigned a separate priority for subsequent priority-based self-healing control.

[0041] Next, based on the first set of fault self-healing impact indicators for the first distribution network topology, multiple first-set self-healing priority weights are identified for multiple faulty lines. The first set of fault self-healing impact indicators includes fault current level indicators, near-area voltage drop indicators, and protection action failure risk indicators. These indicators reflect the severity of the faulty line at the time of the fault and its impact on grid operation. For example, the fault current level indicator measures the magnitude of the fault current; a higher fault current may lead to more severe equipment damage and power outages. The near-area voltage drop indicator reflects the impact of the fault on the voltage level of the surrounding area; a larger voltage drop may affect the normal power supply to users. The protection action failure risk indicator assesses the risk that protection devices may fail at the time of the fault; a higher risk means that the fault may further expand. Through comprehensive analysis of these indicators, such as based on actual needs and grid operation strategies, different weights are assigned to different indicators to reflect the importance of different factors in self-healing control. The scores of different indicators are then weighted to assign a first-set self-healing priority weight to each faulty line, reflecting its importance and urgency in restoration.

[0042] Subsequently, based on the second set of fault self-healing impact indicators for the second distribution network topology, multiple second-set self-healing priority weights were identified for several faulty lines. The second set of fault self-healing impact indicators includes indicators of load loss criticality, affected user scale, power restoration feasibility, and power supply criticality of the associated line. These indicators reflect the state of the faulty line after protection response and its impact on users. For example, the load loss criticality indicator measures the importance of the lost load, with restoration of power to critical loads being more urgent; the affected user scale indicator reflects the number of users affected by the fault, with faulty lines affecting a larger number of users having higher priority; the power restoration feasibility indicator assesses the ease of power restoration, with lines easier to restore being prioritized; and the power supply criticality indicator considers the power supply importance of the line itself, with fault restoration of critical lines having higher priority. Through the analysis of these indicators, a second set of self-healing priority weights was also assigned to each faulty line, reflecting its impact on system recovery.

[0043] After collecting the first and second sets of fault self-healing impact indicators, a weighted fitting of the self-healing priority weights for each faulty line is required. The purpose of the weighted fitting is to comprehensively consider the performance of the faulty line in both the first and second distribution network topologies and generate a comprehensive priority weight for each faulty line. The weighted fitting process can be tailored to actual needs and grid operation strategies, assigning different weights to the first and second sets of self-healing priority weights for each faulty line before weighting them to obtain the comprehensive self-healing priority weight for each faulty line.

[0044] Finally, based on the calculated comprehensive priority weights, the faulty lines are prioritized and self-healing control is implemented to ensure that the faulty lines most in need of restoration receive priority processing, thereby achieving rapid restoration. The self-healing control mechanism, based on these comprehensive priority weights, will first process high-priority lines, ensuring that the distribution network can restore power supply in the shortest possible time while minimizing the impact of the fault on users.

[0045] Furthermore, step P34 in this embodiment of the application also includes:

[0046] P34-1: The operating mode of the target low-voltage distribution network determines the dynamic weighting coefficients, which include a first set of weighting coefficients and a second set of weighting coefficients; P34-2: When the operating mode of the target low-voltage distribution network is the equipment safety operating mode, the first set of weighting coefficients is set greater than the second set of weighting coefficients; when the operating mode of the target low-voltage distribution network is the power supply safety operating mode, the first set of weighting coefficients is set less than or equal to the second set of weighting coefficients; P34-3: Based on the dynamic weighting coefficients, a weighted linear fit is performed on the multiple first set of self-healing priority weights and the multiple second set of self-healing priority weights to obtain multiple self-healing priority comprehensive weights for the multiple faulty lines.

[0047] Optionally, the calculation method for the self-healing priority weight can be dynamically adjusted according to different operating modes of the distribution network to ensure that the distribution network can perform fault recovery more flexibly and efficiently under different system requirements.

[0048] First, dynamic weighting coefficients are determined based on the operating mode of the target low-voltage distribution network. These dynamic weighting coefficients include a first set of weighting coefficients and a second set of weighting coefficients. This process is based on the different needs and priorities of the distribution network for fault self-healing under different operating modes. For example, when the operating mode of the distribution network focuses on equipment safety, indicators related to equipment safety, such as fault current levels, are more important; while when the operating mode focuses on power supply safety, indicators related to power supply safety, such as the criticality of power outage loads, are more critical.

[0049] Specifically, when the target low-voltage distribution network operates in the equipment safety mode, the first set of weighting coefficients is set greater than the second set of weighting coefficients. This is because, in this mode, indicators such as fault current level, near-zone voltage drop, and risk of protection action failure are more critical for protecting equipment from damage. Therefore, the first set of self-healing priority weights is given a higher weight to ensure that equipment safety is given priority during the self-healing process.

[0050] Conversely, when the target low-voltage distribution network operates in a power supply safety mode, the weighting coefficients of the first group are set to be less than or equal to those of the second group. In this mode, indicators such as the criticality of the lost load, the scale of affected users, the feasibility of power restoration, and the criticality of the power supply to the affected lines are more important, as these indicators directly relate to the power supply safety of users and the priority of power restoration. Therefore, the second group of self-healing priority weights is assigned a higher weight to ensure that critical loads and important users are restored first during the self-healing process.

[0051] Finally, based on the determined dynamic weight coefficients, a weighted linear fit is performed on multiple first-group self-healing priority weights and multiple second-group self-healing priority weights. This process involves multiplying each group of self-healing priority weights by the corresponding dynamic weight coefficients and then performing a linear combination to obtain the comprehensive self-healing priority weight for each faulty line. The formula for the weighted linear fit can be expressed as: Comprehensive self-healing priority weight = (first-group self-healing priority weight × first-group weight coefficient) + (second-group self-healing priority weight × second-group weight coefficient).

[0052] Ultimately, the resulting self-healing priority weight will serve as the basis for the self-healing control strategy, determining the priority of each faulty line during the recovery process. This will ensure that the distribution network can perform fault recovery more accurately under different operating modes, and maximize recovery efficiency and system reliability.

[0053] Furthermore, before calculating the priority weight of fault line self-healing based on the state characteristics of the first and second distribution network topologies, step P30 in this embodiment of the application further includes:

[0054] P31a: Analyze the ratio of the first distribution network topology to the target low-voltage distribution network and output the fault impact range; P32a: When the fault impact range is less than or equal to the preset impact range threshold, decompose the fault lines in the first distribution network topology and output multiple fault lines.

[0055] Specifically, before calculating the priority weight of self-healing for faulty lines, it is necessary to analyze the scope of the fault's impact and preprocess the faulty lines to ensure that the impact of the fault on the distribution network can be fully assessed before self-healing control, thereby achieving more accurate and efficient fault recovery.

[0056] First, the ratio of the first distribution network topology to the target low-voltage distribution network is analyzed to determine the scope of the fault's impact. This process can be achieved by calculating the proportional relationship between the distribution network topology at the time of the fault (the first distribution network topology) and the entire target low-voltage distribution network. Specifically, information such as the faulty lines, affected equipment, and nodes in the first distribution network topology can be quantified and then compared with the corresponding information in the entire target low-voltage distribution network to obtain a specific numerical value for the fault's impact scope. For example, the impact scope can be quantified by calculating the proportion of the total length of the faulty lines to the total length of the entire distribution network lines, or by calculating the proportion of the number of affected users to the total number of users.

[0057] Subsequently, the calculated fault impact range is compared with a preset impact range threshold. The preset impact range threshold is a reference value pre-set based on the power grid's operation strategy and safety requirements, used to determine the severity of the fault and whether its impact on power grid operation is within acceptable limits. If the fault impact range is less than or equal to the preset impact range threshold, it indicates that the fault's impact is within a controllable range; a localized area may be affected, and large-scale fault isolation and repair are not required. In this case, the first distribution network topology can be decomposed into faulty lines, outputting multiple faulty lines. Each faulty line will be evaluated and processed individually to more accurately restore power supply to the faulty area in self-healing control. That is, if the impact range is small, the local faulty line will be decomposed into independent lines for analysis and priority ranking. This preprocessing effectively narrows the processing scope of self-healing control and improves the efficiency and accuracy of fault recovery.

[0058] Furthermore, before calculating the priority weight of fault line self-healing based on the state characteristics of the first and second distribution network topologies, step P30 in this embodiment of the application further includes:

[0059] P33a: When the fault impact range is greater than the preset impact range threshold, the first distribution network topology is decomposed into fault nodes, and multiple fault nodes are output; P34a: Calculate the multiple self-healing priority comprehensive weights of the multiple fault nodes, and perform fault line priority self-healing control on the first distribution network topology according to the self-healing priority comprehensive weights of the fault nodes.

[0060] Optionally, when the analysis shows that the proportion of the first distribution network topology to the target low-voltage distribution network, i.e., the fault impact range, is greater than the preset impact range threshold, it indicates that the fault has a relatively wide impact on the entire distribution network, possibly involving multiple nodes or lines. In this case, it is necessary to decompose the first distribution network topology into fault nodes, thereby outputting multiple fault nodes. This decomposition process is based on a detailed analysis of the fault points and affected equipment in the first distribution network topology, breaking down the complex fault network into multiple independent fault nodes. Each fault node can correspond to a specific device, such as a transformer, circuit breaker, or a specific line segment and node. Through fault node decomposition, the specific location of the fault and its impact range can be accurately located, and the recovery priority of each node can be calculated individually, thereby providing more detailed data support for subsequent self-healing control.

[0061] After decomposing the fault nodes, the next step is to calculate the comprehensive weight of self-healing priority for these fault nodes. The weight calculation is based on the state characteristics of the fault nodes and their impact on the power grid operation, comprehensively considering multiple factors such as fault current level, near-area voltage drop, risk of protection failure, criticality of the lost-power load, scale of affected users, feasibility of power restoration, and criticality of the power supply to the associated line. For example, a high fault current level may lead to severe equipment damage and power outage; a large near-area voltage drop may interfere with normal power consumption; a high risk of protection failure means the fault may spread further; a high criticality of the lost-power load makes power restoration more urgent; a large scale of affected users increases the priority of the fault node; high feasibility of power restoration allows for priority handling; and a high criticality of the power supply to the associated line makes fault restoration even more prioritized. Based on these factors, a self-healing priority weight is assigned to each fault node. The determination of the weight can be based on expert experience, historical data, or machine learning algorithms to ensure its rationality and scientific validity.

[0062] Finally, based on the calculated self-healing priority comprehensive weight, the fault line priority self-healing control is implemented on the first distribution network topology. The recovery order is dynamically adjusted according to the fault node weight, and the fault nodes with high weights are dealt with first to gradually restore power supply, reduce the impact of the fault on users, and ensure that the power supply of critical loads and important users is restored first.

[0063] Furthermore, according to the self-healing priority weight of the faulty lines, the first distribution network topology is subjected to faulty line priority self-healing control. Step P34a in this embodiment of the application further includes:

[0064] P34-1a: Prioritize multiple faulty lines in the first distribution network topology according to the comprehensive weight of their self-healing priority, and obtain the self-healing priority execution sequence of the faulty lines; P34-2a: Perform network reconfiguration optimization analysis based on the self-healing priority execution sequence of the faulty lines to generate a set of self-healing control commands; wherein, the network reconfiguration optimization analysis includes calculating the score value of each faulty line with respect to the candidate self-healing control parameter space under safe operation constraints, and the score value includes the average weighted calculation result of resource occupancy rate, restored load amount and execution time complexity.

[0065] It should be understood that the process of implementing fault line priority self-healing control for the first distribution network topology based on the comprehensive weight of the fault line's self-healing priority can be further refined. Specifically, firstly, multiple fault lines in the first distribution network topology are prioritized according to the magnitude of their comprehensive weight of self-healing priority, thus obtaining a fault line self-healing priority execution sequence. This prioritization process is based on the previously calculated comprehensive weight of self-healing priority for each fault line; fault lines with higher weights will be assigned higher priority and placed at the front of the execution sequence. For example, if a fault line has a high comprehensive weight of self-healing priority, it indicates that the line had a greater impact on the power grid when the fault occurred, or that restoring power to the user from this line is more critical; therefore, it should be prioritized during the self-healing control process.

[0066] Subsequently, network reconfiguration optimization analysis is performed based on the obtained self-healing priority execution sequence of the faulty lines, generating a self-healing control command set. This network reconfiguration optimization analysis is conducted under safe operation constraints, aiming to find the optimal self-healing control scheme while ensuring the safe and stable operation of the power grid. Specifically, this analysis process includes calculating a score for each faulty line in the candidate self-healing control parameter space. The score is obtained by averaging and weighting resource utilization, restored load, and execution time complexity. Resource utilization reflects the amount of resources required during self-healing control; a lower resource utilization indicates more efficient self-healing control. Restored load measures the amount of power supply that self-healing control can restore; a higher restored load indicates better self-healing control. Execution time complexity represents the complexity and time required for self-healing control operations; lower time complexity indicates faster recovery speed. By weighting these three factors, a score for each faulty line under different self-healing control schemes can be obtained, generating a comprehensive score for each faulty line, thus providing a basis for selecting the optimal self-healing control scheme.

[0067] For example, for a faulty line, if a self-healing control scheme has low resource utilization, high load restoration, and low execution time complexity, then that scheme will have a higher score and is more likely to be selected as the final self-healing control scheme. In this way, it can be ensured that during the self-healing control process, schemes with low resource utilization, high load restoration, and fast execution speed are prioritized, thereby improving the self-healing efficiency and reliability of the entire power grid.

[0068] Finally, based on these scores, the optimal self-healing control scheme is selected for each faulty line, generating a set of self-healing control commands. These commands include specific self-healing control operations, such as circuit breaker opening and closing operations and equipment switching operations. By executing these self-healing control commands, the self-healing control of each faulty line can be performed sequentially according to the self-healing priority sequence, thereby gradually restoring the normal operation of the power grid.

[0069] Furthermore, after generating the self-healing control command set, step P30 in this embodiment of the application also includes:

[0070] P35: The digital twin drive platform performs simulation drive according to the self-healing control command set and collects the self-healing recovery simulation dataset; P36: The self-healing recovery simulation dataset is subjected to self-healing recovery security verification, self-healing recovery protection compatibility verification, and self-healing recovery operation stability verification. If all verifications are passed, the self-healing control command set is issued to control the target low-voltage distribution network.

[0071] Optionally, after generating the self-healing control command set, it can be further simulated and driven through a digital twin driving platform, and the security, protection compatibility and operational stability of the self-healing recovery simulation dataset can be verified.

[0072] Specifically, the digital twin-driven platform first performs simulation driving based on the generated self-healing control command set, collecting a self-healing recovery simulation dataset. For example, in the virtual environment of the digital twin-driven platform, the distribution network drive simulation model is operated according to the instructions in the self-healing control command set, simulating various operations in the actual self-healing control process, such as circuit breaker opening and closing, and equipment switching. Through these simulation operations, the platform can collect various data in the self-healing recovery process, forming a self-healing recovery simulation dataset. This dataset contains operating parameters of the power grid such as current, voltage, and power during the self-healing control process, as well as information such as equipment status and topology changes, providing detailed data support for subsequent verification processes.

[0073] Subsequently, the collected self-healing recovery simulation dataset underwent verification for self-healing recovery safety, protection compatibility, and operational stability. Self-healing recovery safety verification primarily checks whether the self-healing control process meets the safe operation requirements of the power grid, such as whether it will cause equipment overload or introduce new faults. Self-healing recovery protection compatibility verification ensures that the self-healing control commands are compatible with the power grid's protection devices, preventing malfunctions or failures to operate. Self-healing recovery operational stability verification assesses whether the self-healing control process will lead to power grid instability, such as voltage fluctuations or frequency deviations. Through these three verifications, the feasibility and reliability of the self-healing control command set can be comprehensively evaluated.

[0074] If the self-healing simulation dataset passes verification in terms of security, protection compatibility, and operational stability, it indicates that the self-healing process meets the requirements of safety, stability, and compatibility in all aspects. The platform will then officially issue the self-healing control command set and execute it in the target low-voltage distribution network. The verified self-healing control command set is transmitted to the actual low-voltage distribution network control system via the digital twin-driven platform. The control system then executes the corresponding self-healing control operations, thereby restoring power supply to the faulty line and improving the self-healing efficiency and reliability of the power grid.

[0075] In summary, the embodiments of this application have at least the following technical effects:

[0076] This application utilizes a digital twin-driven simulation model to analyze fault occurrences in real time and automatically generate recovery strategies, significantly improving fault recovery speed and reducing distribution network outage time. By combining real-time fault data with the distribution network topology, it automatically calculates the self-healing priority weight of faulty lines and automatically performs fault recovery based on priority, reducing manual intervention and improving the system's intelligence level. By prioritizing faulty lines, it ensures that critical lines and high-impact fault areas are repaired first, optimizing resource allocation and scheduling during the recovery process. Simultaneously, by leveraging real-time simulation and fault diagnosis using digital twin technology, it ensures stable operation of the distribution network during fault recovery, reducing new faults or instability caused by the recovery process.

[0077] The technology achieves the technical effect of rapid response to power distribution network fault recovery through a self-healing control method driven by digital twins, thereby improving fault recovery efficiency and power supply reliability.

[0078] Example 2, based on the same inventive concept as the digital twin-driven low-voltage distribution network area self-healing control method in the foregoing examples, such as... Figure 2 As shown, this application provides a digital twin-driven self-healing control device for low-voltage distribution network areas. The device and method embodiments in this application are based on the same inventive concept. The device includes:

[0079] The twin simulation model construction module 11 is used to establish a distribution network drive simulation model of the target low-voltage distribution network based on the digital twin drive platform.

[0080] The distribution network topology construction module 12 is used to map the real-time fault dataset of the target low-voltage distribution network to the distribution network driving simulation model, and output a first distribution network topology and a second distribution network topology. The first distribution network topology is the distribution network where the fault occurred, and the second distribution network topology is the protection response distribution network after the fault.

[0081] The fault self-healing control module 13 is used to calculate the fault line self-healing priority weight based on the state characteristics of the first distribution network topology and the second distribution network topology, and to perform fault line priority self-healing control on the first distribution network topology according to the comprehensive weight of the fault line self-healing priority.

[0082] Furthermore, the power distribution network topology construction module 12 is also used to perform the following steps:

[0083] Obtain the real-time fault dataset of the target low-voltage distribution network, which includes fault current waveform data, fault topology metadata, protection device action signals, and circuit breaker switch status; map the fault current waveform data and fault topology metadata to the distribution network drive simulation model for simulation, and output the first distribution network topology; map the protection device action signals and circuit breaker switch status to the distribution network drive simulation model for simulation until the protection action topology update is completed and output the second distribution network topology.

[0084] Furthermore, the power distribution network topology construction module 12 is also used to perform the following steps:

[0085] Read the initial operating status dataset of the target low-voltage distribution network; synchronize the initial operating status dataset to the distribution network drive simulation model for initial state synchronization; map the fault current waveform data and fault topology metadata to the synchronized distribution network drive simulation model for simulation to obtain the simulated operating status dataset; compare the simulated operating status dataset with the pre-stored healthy operating status dataset to locate the fault and output the first distribution network topology.

[0086] Furthermore, the fault self-healing control module 13 is also used to perform the following steps:

[0087] The first distribution network topology is decomposed into faulty lines, outputting multiple faulty lines. Multiple first-group self-healing priority weights are identified for these faulty lines based on a first set of fault self-healing impact indicators for the first distribution network topology. These first-group indicators include fault current level, near-area voltage drop, and protection operation failure risk. Multiple second-group self-healing priority weights are identified for these faulty lines based on a second set of fault self-healing impact indicators for the second distribution network topology. These second-group indicators include load loss criticality, affected user scale, power restoration feasibility, and power supply criticality of the associated line. A weighted fitting is performed on the multiple first-group and multiple second-group self-healing priority weights to obtain a comprehensive self-healing priority weight for the multiple faulty lines.

[0088] Furthermore, the fault self-healing control module 13 is also used to perform the following steps:

[0089] The operating mode of the target low-voltage distribution network determines the dynamic weighting coefficients, which include a first set of weighting coefficients and a second set of weighting coefficients. When the operating mode of the target low-voltage distribution network is equipment safety operation mode, the first set of weighting coefficients is set greater than the second set of weighting coefficients; when the operating mode of the target low-voltage distribution network is power supply safety operation mode, the first set of weighting coefficients is set less than or equal to the second set of weighting coefficients. Based on the dynamic weighting coefficients, a weighted linear fit is performed on the plurality of first set self-healing priority weights and the plurality of second set self-healing priority weights to obtain the plurality of comprehensive self-healing priority weights for the plurality of faulty lines.

[0090] Furthermore, the fault self-healing control module 13 is also used to perform the following steps:

[0091] The fault impact range is output by analyzing the ratio of the first distribution network topology to the target low-voltage distribution network. When the fault impact range is less than or equal to a preset impact range threshold, the fault lines of the first distribution network topology are decomposed, and multiple fault lines are output.

[0092] Furthermore, the fault self-healing control module 13 is also used to perform the following steps:

[0093] When the scope of the fault impact exceeds the preset impact range threshold, the first distribution network topology is decomposed into fault nodes, and multiple fault nodes are output; multiple self-healing priority comprehensive weights of the multiple fault nodes are calculated, and fault line priority self-healing control is performed on the first distribution network topology according to the self-healing priority comprehensive weights of the fault nodes.

[0094] Furthermore, the fault self-healing control module 13 is also used to perform the following steps:

[0095] The faulty lines in the first distribution network topology are prioritized according to their self-healing priority weights to obtain a self-healing priority execution sequence. Network reconfiguration optimization analysis is performed based on the self-healing priority execution sequence to generate a self-healing control command set. The network reconfiguration optimization analysis includes calculating the score of each faulty line in the candidate self-healing control parameter space under safe operation constraints. The score includes the average weighted calculation result of resource occupancy rate, restored load amount, and execution time complexity.

[0096] Furthermore, the fault self-healing control module 13 is also used to perform the following steps:

[0097] The digital twin drive platform performs simulation drive according to the self-healing control command set and collects self-healing recovery simulation dataset; it performs self-healing recovery security verification, self-healing recovery protection compatibility verification, and self-healing recovery operation stability verification on the self-healing recovery simulation dataset. If all verifications pass, the self-healing control command set is issued to control the target low-voltage distribution network.

[0098] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0099] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0100] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A digital twin-driven self-healing control method for low-voltage distribution network areas, characterized in that, The method includes: A distribution network drive simulation model of the target low-voltage distribution network is established based on a digital twin drive platform; The real-time fault dataset of the target low-voltage distribution network is mapped to the distribution network driving simulation model, and the first distribution network topology and the second distribution network topology are output. The first distribution network topology is the distribution network where the fault occurs, and the second distribution network topology is the protection response distribution network after the fault. The self-healing priority weight of fault lines is calculated based on the state characteristics of the first and second distribution network topologies. The fault line priority self-healing control is then implemented on the first distribution network topology according to the comprehensive self-healing priority weight of the fault lines. The method for calculating the priority weight of fault line self-healing based on the state characteristics of the first and second distribution network topologies includes: The first distribution network topology is decomposed into fault lines, and multiple fault lines are output. Based on the first set of fault self-healing impact indicators of the first distribution network topology, identify multiple first set of self-healing priority weights for the multiple faulty lines. Based on the second set of fault self-healing impact indicators of the second distribution network topology, identify multiple second set of self-healing priority weights for the multiple faulty lines; The multiple first-group self-healing priority weights and the multiple second-group self-healing priority weights are weighted and fitted to obtain the multiple self-healing priority comprehensive weights of the multiple faulty lines. The method for performing a weighted fitting of the plurality of first-group self-healing priority weights and the plurality of second-group self-healing priority weights includes: The operating mode of the target low-voltage distribution network determines the dynamic weighting coefficients, which include a first set of weighting coefficients and a second set of weighting coefficients. Wherein, when the target low-voltage distribution network is in the equipment safety operation mode, the first set of weight coefficients is greater than the second set of weight coefficients; when the target low-voltage distribution network is in the power supply safety operation mode, the first set of weight coefficients is less than or equal to the second set of weight coefficients. Based on the dynamic weighting coefficients, a weighted linear fit is performed on the plurality of first-group self-healing priority weights and the plurality of second-group self-healing priority weights to obtain the plurality of self-healing priority comprehensive weights for the plurality of faulty lines.

2. The method as described in claim 1, characterized in that, The method for mapping the real-time fault dataset of the target low-voltage distribution network to the distribution network driving simulation model includes: Obtain the real-time fault dataset of the target low-voltage distribution network, which includes fault current waveform data, fault topology metadata, protection device action signals, and circuit breaker switch status. The fault current waveform data and fault topology metadata are mapped to the distribution network drive simulation model for simulation, and the first distribution network topology is output. The protection device action signal and circuit breaker switch status are mapped to the distribution network drive simulation model for simulation until the protection action topology update is completed and the second distribution network topology is output.

3. The method as described in claim 2, characterized in that, The method involves mapping the fault current waveform data and fault topology metadata to the distribution network drive simulation model for simulation, and outputting the first distribution network topology. Read the initial operating status dataset of the target low-voltage distribution network; The initial operating state dataset is synchronized to the distribution network drive simulation model for initial state synchronization. The fault current waveform data and fault topology metadata are mapped to the synchronized distribution network drive simulation model for simulation to obtain the simulated operating state dataset. The simulated operating status dataset is compared with the pre-stored healthy operating status dataset to locate the fault and output the first distribution network topology.

4. The method as described in claim 1, characterized in that, The first set of fault self-healing impact indicators of the first distribution network topology is obtained. The first set of fault self-healing impact indicators includes fault current level indicators, near-area voltage drop indicators, and protection action failure risk indicators. The second group of fault self-healing impact indicators includes key indicators of power loss load, indicators of the scale of affected users, indicators of the feasibility of restoring power supply, and key indicators of power supply to the relevant lines.

5. The method as described in claim 1, characterized in that, Before calculating the priority weight of fault line self-healing based on the state characteristics of the first and second distribution network topologies, the method further includes: Analyze the ratio of the first distribution network topology to the target low-voltage distribution network to output the fault impact range; When the fault impact range is less than or equal to a preset impact range threshold, the first distribution network topology is decomposed into fault lines, and multiple fault lines are output. When the fault impact range is greater than the preset impact range threshold, the first distribution network topology is decomposed into fault nodes, and multiple fault nodes are output. Calculate the comprehensive weights of the self-healing priorities of the multiple fault nodes, and perform fault line priority self-healing control on the first distribution network topology according to the comprehensive weights of the self-healing priorities of the fault nodes.

6. The method as described in claim 1, characterized in that, The first distribution network topology is subjected to fault line priority self-healing control according to the comprehensive weight of the fault line self-healing priority. The method includes: The multiple faulty lines in the first distribution network topology are prioritized according to the comprehensive weight of the self-healing priority of the faulty lines to obtain the self-healing priority execution sequence of the faulty lines. Based on the self-healing priority execution sequence of the faulty line, network reconstruction optimization analysis is performed to generate a self-healing control command set. The network reconfiguration optimization analysis includes calculating the score of each faulty line with respect to the candidate self-healing control parameter space under safe operation constraints. The score includes the average weighted calculation result of resource utilization, recovery load, and execution time complexity.

7. The method as described in claim 6, characterized in that, After generating the self-healing control command set, the method also includes: The digital twin driving platform performs simulation driving according to the self-healing control command set and collects self-healing recovery simulation dataset; The self-healing recovery simulation dataset is subjected to self-healing recovery security verification, self-healing recovery protection compatibility verification, and self-healing recovery operation stability verification. If all verifications are passed, the self-healing control command set is issued to control the target low-voltage distribution network.

8. A digital twin-driven self-healing control device for low-voltage distribution network areas, characterized in that, The apparatus is used to perform the method according to any one of claims 1 to 7, the apparatus comprising: The twin simulation model construction module is used to build a distribution network drive simulation model of the target low-voltage distribution network based on the digital twin drive platform; The distribution network topology construction module is used to map the real-time fault dataset of the target low-voltage distribution network to the distribution network driving simulation model, and output a first distribution network topology and a second distribution network topology. The first distribution network topology is the distribution network where the fault occurred, and the second distribution network topology is the protection response distribution network after the fault. The fault self-healing control module is used to calculate the fault line self-healing priority weight based on the state characteristics of the first distribution network topology and the second distribution network topology, and to perform fault line priority self-healing control on the first distribution network topology according to the comprehensive weight of the fault line self-healing priority.

Images