Power distribution network fault recovery strategy determination method and electronic device

Abstract

The application discloses a kind of power distribution network fault recovery strategy determination method and electronic equipment.The method comprises: based on the current operating data corresponding to each of a plurality of nodes in target power distribution network, determine the fault detection result of target power distribution network;In the case where the fault detection result indicates that there is a fault in target power distribution network at the current time, determine the fault node in the plurality of nodes, and divide target power distribution network into first area and second area;In the process of supplying power to the first area based on the target energy storage configuration electric quantity, the operating state of the first area is detected;In the case where the operating state is normal operation, the initial fault recovery strategy of target power distribution network is optimized based on the operating data corresponding to the first area and the second area, to obtain the target fault recovery strategy of target power distribution network.The application solves the technical problem of insufficient resilience and fault recovery efficiency of mountainous power distribution network in the face of extreme disasters.

Description

Technical Field

[0001] This invention relates to the field of power distribution network operation and control technology, and more specifically, to a method for determining fault recovery strategies for power distribution networks and an electronic device thereof. Background Technology

[0002] Mountainous power distribution networks, as crucial infrastructure ensuring the lives and economic development of residents in remote areas, have long faced severe challenges such as complex terrain, harsh climate, vulnerable lines, and difficulties in restoration. During extreme weather events (such as heavy rain, blizzards, and landslides), relevant technical solutions for the post-disaster recovery and resilience enhancement of mountainous power distribution networks generally adopt a "passive response + manual intervention" model, primarily focusing on the fault isolation and recovery phase after the disaster, lacking a systematic and intelligent collaborative control mechanism for the entire disaster process (pre-disaster prevention, disaster response, and post-disaster recovery). The significant shortcomings of related technologies in fault recovery for mountainous power distribution networks are mainly reflected in the following aspects:

[0003] The use of empirical or static planning methods to configure capacity and location fails to consider the unique characteristics of mountainous areas, such as fluctuating wind and solar power output, uneven spatial and temporal load distribution, and the need for prioritizing critical loads in extreme scenarios. This results in low utilization of energy storage resources and insufficient power supply capacity for critical loads, making it impossible to effectively support isolated autonomous operation during disasters. When a fault occurs, a simple "disconnection of the faulty section" operation is typically performed. After the faulty area is cut off, the lack of an intelligent collaborative scheduling mechanism between energy storage and distributed power sources leads to prolonged power outages in localized loads. Post-disaster recovery relies on manual on-site surveys and operations, resulting in crude recovery path planning that is prone to inrush currents, voltage fluctuations, and even secondary faults. This leads to low recovery efficiency and a low success rate, failing to achieve the full lifecycle resilience improvement from "pre-disaster preventative configuration" to "self-healing operation during disasters" and "smooth post-disaster reconstruction." Although fault recovery methods in related technologies can achieve a certain degree of power restoration within a certain range, the failure to achieve full-cycle control of the mountainous distribution network in the face of extreme disasters leads to problems with the resilience and fault recovery efficiency of the mountainous distribution network.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method and electronic device for determining fault recovery strategies for power distribution networks, in order to at least address the technical problems of insufficient resilience and fault recovery efficiency in mountainous power distribution networks when facing extreme disasters.

[0006] According to one aspect of the present invention, a method for determining a fault recovery strategy for a distribution network is provided, comprising: determining a fault detection result of a target distribution network based on current operating data corresponding to multiple nodes in the target distribution network, wherein the current operating data includes at least the current, voltage, and power of the corresponding node at the current moment; when the fault detection result indicates that a fault exists in the target distribution network at the current moment, determining a faulty node among the multiple nodes, and dividing the target distribution network into a first region and a second region, wherein the first region is the region associated with the faulty node, and the second region is the region in the target distribution network other than the first region; during the process of supplying power to the first region based on a target energy storage configuration quantity, detecting the operating status of the first region, wherein the target energy storage configuration quantity is used to indicate the amount of power allocated to the first region by the energy storage device within a predicted period, the predicted period being a period of a first predetermined duration after the current moment; and when the operating status is normal operation, optimizing the initial fault recovery strategy of the target distribution network based on the operating data corresponding to the first region and the second region respectively, to obtain a target fault recovery strategy for the target distribution network.

[0007] According to another aspect of the present invention, a fault recovery strategy determination device for a distribution network is also provided, comprising: a fault detection result determination module, configured to determine a fault detection result of a target distribution network based on the current operating data corresponding to each of multiple nodes in the target distribution network, wherein the current operating data includes at least the current, voltage, and power of the corresponding node at the current moment; a target distribution network division module, configured to determine the faulty node among the multiple nodes and divide the target distribution network into a first region and a second region when the fault detection result indicates that a fault exists in the target distribution network at the current moment, wherein the first region is the region associated with the faulty node, and the second region is the region in the target distribution network other than the first region; a first region operation status detection module, configured to detect the operation status of the first region during the process of supplying power to the first region based on the target energy storage configuration power, wherein the target energy storage configuration power is used to indicate the power allocated to the first region by the energy storage device within a predicted period, and the predicted period is a period of a first predetermined duration after the current moment; and a target fault recovery strategy determination module, configured to optimize the initial fault recovery strategy of the target distribution network based on the operating data corresponding to the first region and the second region when the operation status is normal operation, to obtain the target fault recovery strategy of the target distribution network.

[0008] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium storing a plurality of instructions, the instructions being adapted to be loaded by a processor and executed by any one of the methods for determining the fault recovery strategy of the power distribution network.

[0009] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the fault recovery strategy determination method for the power distribution network as described in any one of the present invention.

[0010] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the method for determining a fault recovery strategy for a power distribution network as described in any one of the present invention.

[0011] In this embodiment of the invention, the fault detection result of the target distribution network is determined based on the current operating data corresponding to multiple nodes in the target distribution network. The current operating data includes at least the current, voltage, and power of the corresponding node at the current moment. If the fault detection result indicates that a fault exists in the target distribution network at the current moment, the faulty node among the multiple nodes is identified, and the target distribution network is divided into a first region and a second region. The first region is the region associated with the faulty node, and the second region is the region in the target distribution network excluding the first region. During the process of supplying power to the first region based on the target energy storage configuration power, the operating status of the first region is detected. The target energy storage configuration power is used to indicate the amount of power allocated to the first region by the energy storage device within a predicted time period, where the predicted time period is the current moment. After the first predetermined time period; under normal operating conditions, based on the corresponding operating data of the first and second regions, the initial fault recovery strategy of the target distribution network is optimized to obtain the target fault recovery strategy of the target distribution network. This achieves the goal of obtaining the operating data of multiple nodes in the target distribution network at the current moment and the target energy storage configuration power, dividing the target distribution network into fault areas and non-fault areas when a fault exists, and independently supplying power to the fault areas. After the fault areas are operating normally, the target fault recovery strategy of the target distribution network is determined. This achieves the technical effect of improving the resilience and fault recovery efficiency of mountain distribution networks, and solves the technical problem of insufficient resilience and fault recovery efficiency of mountain distribution networks in the face of extreme disasters. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0013] Figure 1 This is a flowchart of a method for determining a fault recovery strategy for a power distribution network according to an embodiment of the present invention;

[0014] Figure 2 This is a schematic diagram of an optional distribution network division and fault recovery method according to an embodiment of the present invention;

[0015] Figure 3 This is a flowchart of an optional method for determining a fault recovery strategy for a power distribution network according to an embodiment of the present invention;

[0016] Figure 4 This is a schematic diagram of a fault recovery strategy determination device for a power distribution network according to an embodiment of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 the invention 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 a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] According to an embodiment of the present invention, a method embodiment for determining a fault recovery strategy for a power distribution network is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0020] Figure 1 This is a flowchart of a method for determining a fault recovery strategy for a distribution network according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0021] Step S102: Based on the current operating data of each of the multiple nodes in the target distribution network, determine the fault detection result of the target distribution network. The current operating data includes at least the current, voltage and power of the corresponding node at the current moment.

[0022] Optionally, firstly, sensors installed at each node in the target distribution network are used to collect real-time operational data such as current, voltage, and power at each node. A node is an electrical connection point in the target distribution network (including but not limited to load nodes, renewable energy power source nodes, and energy storage device access points). Each node represents an independent electrical monitoring unit, used to reflect the operational status of the area corresponding to that node in the target distribution network. The current operational data of any node can be represented in the following way: ,in, This represents the current running data of any node. This represents the current at any node at the current moment. This represents the voltage at any node at the current moment. Let t represent the power of any node at the current moment, and t represent the index of the current moment. Then, the real-time operating data of multiple nodes are input into a detection model with intelligent analysis capabilities (such as a deep reinforcement learning model) for detection to determine whether a fault has occurred in the target distribution network at the current moment. This method can significantly improve the fault detection capability and emergency response speed of the target distribution network under extreme weather and complex mountainous terrain, providing a highly reliable decision-making basis for subsequent post-disaster recovery.

[0023] In one optional embodiment, determining the fault detection result of the target distribution network based on the current operating data corresponding to each of the multiple nodes in the target distribution network includes: obtaining multiple monitoring values ​​based on the current operating data corresponding to each of the multiple nodes, wherein the multiple monitoring values ​​correspond one-to-one with the multiple nodes, and the monitoring values ​​are used to indicate whether the corresponding nodes are in a normal state; if any of the multiple monitoring values ​​does not exceed a preset normal threshold, the fault detection result is determined to be that there is a fault in the target distribution network at the current time; if all of the multiple monitoring values ​​exceed the preset normal threshold, the fault detection result is determined to be that there is no fault in the target distribution network at the current time.

[0024] Optionally, based on the real-time collected current operating data of each node in the target distribution network, a deep reinforcement learning model is used to extract features and evaluate the state of this operating data, outputting a monitoring value corresponding to each node. To identify fault conditions (including but not limited to overload and voltage fluctuations) in the target distribution network, the deep reinforcement learning model continuously learns, optimizes, and trains to detect anomalies in multiple monitoring values. The monitoring value corresponding to any node (any monitoring value) can be obtained in the following way: ,in, This represents the monitoring value corresponding to any node. A function representing a deep reinforcement learning model. This represents the weight parameters of the deep reinforcement learning model, and t represents the index at the current time step. If the monitoring value corresponding to any node is lower than the preset normal threshold... ,Right now If the value of a node is above the preset normal threshold, it indicates that a fault has occurred at that node, triggering the early warning mechanism to output an early warning signal, indicating a fault in the target distribution network at that moment. Conversely, if the monitored values ​​of all nodes are above the preset normal threshold, no early warning signal is issued, indicating that there is no fault in the target distribution network at that moment. Early warning signals can be obtained in the following ways: ,in, Indicates a warning signal. This indicates an indicator function used to indicate whether a corresponding node is faulty. Less than or equal to the preset normal threshold hour, An output of 1 indicates that the node has failed; when Greater than the preset normal threshold hour, An output of 0 indicates that the node is normal. This step uses deep reinforcement learning to achieve adaptive identification of complex nonlinear faults, changing the dependence of threshold methods on a single parameter in related technologies. This can significantly improve the fault detection accuracy and response speed under multi-source disturbances in extreme mountainous environments.

[0025] Step S104: If the fault detection result indicates that there is a fault in the target distribution network at the current time, determine the faulty node among multiple nodes, and divide the target distribution network into a first region and a second region. The first region is the region associated with the faulty node, and the second region is the region in the target distribution network other than the first region.

[0026] Optionally, if the fault detection results indicate that the target distribution network is faulty at the current moment, firstly, based on the monitoring values ​​of multiple nodes and combined with the topology of the target distribution network and the connection relationship between nodes, all nodes with monitoring values ​​lower than the preset normal threshold are accurately located and identified as faulty nodes. Subsequently, with the faulty node as the core, the area associated with the faulty node is delineated as the first area (i.e., the fault area), and the connection between the fault area and the target distribution network is cut off, switching to island mode to prevent the fault from spreading to other areas and maintain the stability of the mountain distribution network. The area consisting of the remaining nodes that are not affected by the fault and are still in normal operation is divided into the second area (i.e., the non-fault area). Through this division method, the spread of fault current to the second area can be blocked in time, avoiding cascading trips and large-scale power outages. At the same time, it provides a clear decision boundary for the first area to start autonomous operation of the grid-type energy storage island and for the second area to maintain normal power supply from the main grid, thus building a reliable zonal control foundation for stable operation during disasters and rapid recovery after disasters.

[0027] Step S106: During the process of supplying power to the first region based on the target energy storage configuration power, the operating status of the first region is detected. The target energy storage configuration power is used to indicate the power that the energy storage device will allocate to the first region within a predicted time period. The predicted time period is a period of a first predetermined duration after the current time.

[0028] Optionally, in the event of a fault in the target distribution network at the current moment, the first region will perform an islanding switch, activating the energy storage devices configured in that region to provide power support. During the process of supplying power to the first region based on the target energy storage configuration, the operational status within the first region is continuously monitored, and the adequacy of the target energy storage configuration's capacity to support the stable operation of the region is dynamically verified. The target energy storage configuration is the predicted energy storage power and capacity that should be allocated to each node in the target distribution network before the disaster occurs. This step, by monitoring the operational status of the first region in real time during energy storage power supply, can optimize power utilization efficiency and maximize power supply reliability during islanding operation.

[0029] In one optional embodiment, obtaining the target energy storage configuration power includes: determining the predicted energy storage power, predicted energy storage capacity, predicted load importance, predicted new energy power, predicted load power, and predicted grid power for each of the multiple nodes in the predicted time period, based on the historical operating data of each of the multiple nodes in the historical time period, wherein the historical time period is a time period of a second predetermined duration prior to the current moment; determining the natural disaster operation scenario of the target distribution network based on the historical environmental information of the target distribution network in the historical time period, wherein the historical environmental information includes at least: historical meteorological information and historical geographical information of the area where the target distribution network is located; and determining the predicted energy storage power, predicted energy storage capacity, predicted load importance, predicted new energy power, predicted load power, and predicted grid power for each of the multiple nodes in the predicted time period based on the historical operating data of each of the multiple nodes in the historical time period. The objective function of the target distribution network is determined by predicting energy storage power, energy storage capacity, and load importance. Constraints on the target distribution network are determined based on the predicted energy storage power, predicted renewable energy power, predicted load power, and predicted grid power for each node during the prediction period. Based on these constraints and natural disaster scenarios, the initial energy storage configuration strategy is optimized with the objective function's maximum value as the optimization goal, resulting in the target energy storage configuration strategy. This initial strategy indicates the amount of electricity allocated to multiple regions by the energy storage devices during the prediction period, with each region corresponding to a specific node. Finally, the target energy storage configuration quantity is determined based on the target energy storage configuration strategy.

[0030] Optionally, before a disaster occurs, a target energy storage configuration strategy based on historical data is obtained to determine the energy storage resource allocation strategy for each node during the forecast period. Specifically, firstly, by analyzing the historical operating data of multiple nodes in the target distribution network for each historical period, and simultaneously integrating historical environmental information of the target distribution network area, including but not limited to: historical meteorological data (such as heavy rain, heavy snow, wind speed, temperature and humidity), geological disaster records (such as areas prone to landslides and debris flows), and topographic information, a natural disaster operating scenario is simulated to characterize the extreme event patterns that may occur during the forecast period. Next, for the forecast period, the corresponding predicted load power, predicted renewable energy power, predicted grid power, and predicted load importance are predicted for each node, and the appropriate predicted energy storage power and predicted energy storage capacity for each node are deduced based on historical energy storage data. Furthermore, by constructing an objective function and setting constraints, with maximizing the objective function as the optimization goal, under the constraints of a natural disaster scenario, intelligent optimization algorithms (including but not limited to genetic algorithms, particle swarm optimization, and mixed integer programming) are used to optimize the initial energy storage configuration strategy of each node during the prediction period, iteratively obtaining the target energy storage configuration strategy. This target energy storage configuration strategy explicitly specifies the energy storage capacity and spatial deployment location that each node should configure during the prediction period. Therefore, based on this target energy storage configuration strategy, the final determined target energy storage capacity is the energy storage resource required by each node under the disaster scenario.

[0031] In an optional embodiment, the objective function of the target distribution network is determined based on the predicted energy storage power, predicted energy storage capacity, and predicted load importance of each node during the prediction period. This includes determining the objective function based on the predicted energy storage power, predicted energy storage capacity, and predicted load importance of each node during the prediction period, using the following method:

[0032] ;

[0033] Where Z represents the value of the objective function. This represents the number of nodes, where i represents the index of any node. This represents the prediction period, where t represents the index of any prediction time within that period. This represents the predicted energy storage power of any node at any prediction time. This represents the predicted energy storage capacity of any node. This indicates the importance of the predicted load for any given node. This represents the weighting coefficient corresponding to the predicted energy storage power. This represents the weighting coefficient corresponding to the predicted energy storage capacity. This represents the weighting coefficient corresponding to the importance of the predicted load.

[0034] Optionally, the objective function incorporates weighting coefficients for predicted energy storage power, predicted energy storage capacity, and predicted load importance to adjust their relative contributions to optimization. Predicted energy storage power represents the power support capacity that the energy storage devices at the corresponding node can provide to the load during the prediction period; predicted energy storage capacity represents the electrical energy that the energy storage devices configured at the corresponding node can release during the prediction period; and predicted load importance represents the priority of the load at the corresponding node during the prediction period. By constructing a weighted objective function with predicted energy storage power, predicted energy storage capacity, and predicted load importance as objectives, the optimal configuration strategy for the target distribution network during the disaster prediction period is guided.

[0035] In one optional embodiment, constraints on the target distribution network are determined based on the predicted energy storage power, predicted renewable energy power, predicted load power, and predicted grid power corresponding to each of the multiple nodes during the prediction period. This includes determining the constraints as follows:

[0036] ;

[0037] ;

[0038] in, This represents the predicted load power of any node at any prediction time within the prediction period. This represents the predicted renewable energy power at any node at any prediction time. This represents the predicted energy storage power of any node at any prediction time. This represents the predicted grid power at any node at any prediction time. This represents the preset operating power of any node's load at any predicted time in a natural disaster operation scenario.

[0039] Optionally, to ensure the optimized energy storage configuration strategy is operationally safe under extreme natural disaster scenarios, energy balance constraints and critical load guarantee constraints are constructed as boundary conditions for solving the objective function. Energy balance constraints are used to prevent voltage collapse or equipment tripping in the target distribution network due to power shortages. Critical load guarantee constraints are used to ensure that, within the forecast period, the sum of the predicted energy storage power and the predicted renewable energy power at each node of the energy storage device is not less than the preset operating power.

[0040] In one optional embodiment, when there are multiple fault nodes, multiple energy storage devices, and multiple new energy sources, during the process of supplying power to the first region based on the target energy storage configuration, the operating status of the first region is detected, including: dividing the first region into multiple network groups based on preset division rules, wherein each network group includes at least one energy storage device and one new energy source (including but not limited to photovoltaic power generation equipment and wind turbine generators) in the target distribution network; determining the total power supply of the first region based on the predicted energy storage power and predicted new energy power corresponding to each of the multiple fault nodes during the prediction period; allocating the total power supply to the multiple network groups based on the target energy storage configuration, and determining the power supply corresponding to each of the multiple network groups; and determining the operating status detection result of the first region based on the power supply corresponding to each of the multiple network groups.

[0041] Optionally, firstly, based on preset partitioning rules (including but not limited to spatial proximity rules and power coupling rules), the first region is divided into several independently operating network clusters. Each network cluster contains at least one grid-type energy storage device and one operable distributed renewable energy source. Based on the physical electrical topology, it is ensured that each network cluster forms a closed-loop power supply circuit, possessing the voltage and frequency regulation capabilities for islanded operation. Next, after completing the network cluster partitioning, based on the predicted energy storage power and predicted renewable energy power corresponding to multiple fault nodes during the prediction period, the total power supply of the first region can be obtained in the following way: ,in, This represents the total power supply of the first region at any prediction time within the prediction period. Let represent the set of faulty nodes in the first region, and t represent the index at any prediction time. This represents the predicted renewable energy power at any node at any prediction time. This represents the predicted energy storage power of any node at any predicted time. Further, based on the target energy storage configuration capacity, the total power supply is proportionally allocated to each grid group to determine the power supply received by each grid group. Finally, by analyzing the operating status of each grid group, the operating status detection results of the first region are obtained. In this step, by decomposing the first region into multiple grid groups with self-regulating capabilities, fault isolation, regional autonomy, and parallel operation can be achieved, thereby ensuring the continuity and reliability of the target distribution network's power supply during disasters and significantly reducing outage time.

[0042] In one optional embodiment, the operation status detection result of the first region is determined based on the power supply of each of the multiple network groups, including: if the power supply of each network group is within the preset safe power supply range, the operation status detection result is determined to be that the first region is in normal operation; if the power supply of any network group is not within the preset safe power supply range, the operation status detection result is determined to be that the first region is in abnormal operation.

[0043] Optionally, the preset safe power supply range refers to a pre-defined power allowable range based on the load demand, energy storage capacity, renewable energy fluctuation characteristics, and equipment safety thresholds of each grid group. The first region is considered to be in normal operation only when all grid groups meet the preset safe power supply range; conversely, if any grid group exceeds the preset safe power supply range, regardless of its importance, the first region is considered to be in abnormal operation. Furthermore, when the first region is determined to be in abnormal operation, a preset abnormal state recovery strategy can be adopted to restore the abnormal grid group to normal operation. For example, if the power supply of the abnormal grid group is lower than the lower limit of the preset safe power supply range, strategies such as prioritizing the disconnection of non-critical loads, releasing reserve capacity, or cross-grid power support can be used to restore the abnormal grid group to normal operation; if the power supply of the abnormal grid group is higher than the upper limit of the preset safe power supply range, strategies such as absorbing excess renewable energy, activating flexible loads (such as controllable loads like electric water heaters and charging piles), or reducing renewable energy output can be used to restore the abnormal grid group to normal operation. This step involves monitoring each network cluster to identify which specific clusters are at risk of insufficient power supply or overload, and immediately locating the source of the fault, which can greatly shorten the fault diagnosis time.

[0044] Step S108: Under normal operating conditions, the initial fault recovery strategy of the target distribution network is optimized based on the corresponding operating data of the first and second regions to obtain the target fault recovery strategy of the target distribution network.

[0045] Optionally, if the first region is in normal operation, the initial fault recovery strategy is optimized based on the corresponding operation data of the first and second regions to generate a target fault recovery strategy with high reliability and optimal recovery efficiency, so as to gradually restore the connection between multiple network groups in the first region and the second region, thereby enabling the target distribution network to be restored to normal operation smoothly, safely and efficiently.

[0046] In an optional embodiment, when the first region includes multiple network clusters, and the operating status is normal, the initial fault recovery strategy of the target distribution network is optimized based on the operating data corresponding to the first region and the second region respectively to obtain the target fault recovery strategy of the target distribution network. This includes: determining the optimization objective of the target distribution network based on the operating data corresponding to the multiple network clusters and the operating data of the second region, wherein the optimization objective is: minimizing the fault recovery time of the target distribution network and maximizing the total fault recovery load of the target distribution network; and optimizing the initial fault recovery strategy based on the optimization objective to obtain the target fault recovery strategy.

[0047] Optionally, firstly, collect operational data from each grid cluster in the first region, including but not limited to the remaining energy storage capacity, new energy output prediction curves, and critical load priority weights of each grid cluster. Simultaneously, acquire operational data from the second region, including but not limited to bus voltage amplitude and phase, system short-circuit capacity, and adjustable output of backup power. Based on the operational data from both regions, construct optimization objectives, which are: minimizing fault recovery time and maximizing the total fault recovery load of the target distribution network, i.e., the total time from startup recovery to full regional grid connection completion, and maximizing the total fault recovery load, i.e., the total power of non-critical loads that can be recovered under safety constraints. These two are balanced collaboratively through a weighted summation function to avoid extreme strategies such as fast recovery but insufficient power supply or full recovery but excessively long time consumption. The optimization objective function can be obtained as follows: L = mT + nQ, where L represents the function value of the optimization objective function, T represents the minimum fault recovery time, Q represents the total fault recovery load of any maximum target distribution network, m represents the weight coefficient corresponding to the minimum fault recovery time, and n represents the weight coefficient corresponding to the total fault recovery load of the maximum target distribution network. An improved multi-objective genetic algorithm or model predictive control method can be used to jointly optimize the initial recovery strategy, dynamically prioritizing the recovery of each grid group to obtain the target fault recovery strategy. Furthermore, to achieve smooth, safe, and reliable grid connection between the first and second regions and avoid power system instability phenomena such as inrush currents caused by voltage amplitude, frequency, or phase differences, a pre-synchronization strategy is introduced. This pre-synchronization strategy uses a high-precision phase detection algorithm and a dynamic prediction model to calculate the voltage difference, frequency difference, and phase angle difference between each grid group in the first region and the second region at the grid connection point. It then adjusts the voltage amplitude, frequency, and phase of the energy storage devices in the first region, gradually bringing the grid groups in the first region and the second region closer to a synchronized state at the grid connection point. Figure 2 This is a schematic diagram illustrating an optional distribution network partitioning and fault recovery method according to an embodiment of the present invention. The diagram shows that a first region (fault region) forms an isolated autonomous area and is divided into multiple network clusters (i.e., Region 1, Region 2, and Region 3) equipped with energy storage devices and new energy power sources (including but not limited to photovoltaic power generation equipment and wind turbine generators). The entire process of safely reconnecting to the target distribution network after a disaster is then described. Each network cluster consists of energy storage devices and new energy power sources, achieving local power self-sufficiency and stable power supply, ensuring uninterrupted operation of critical loads. Once the normal operating status of each network cluster is confirmed, based on the target fault recovery strategy, each network cluster gradually and smoothly reconnects to the second region, ultimately restoring the normal operation of the target distribution network.

[0048] Through the above steps S102 to S108, the following objectives can be achieved: by acquiring the current operating data of multiple nodes in the target distribution network and the target energy storage configuration power, the target distribution network can be divided into fault areas and non-fault areas when a fault exists in the target distribution network, and the fault areas can be supplied with independent power. After the fault areas are operating normally, the target fault recovery strategy of the target distribution network can be determined. This achieves the technical effect of improving the resilience and fault recovery efficiency of mountain distribution networks, and solves the technical problem of insufficient resilience and fault recovery efficiency of mountain distribution networks in the face of extreme disasters.

[0049] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method. Figure 3 This is a flowchart of an optional method for determining a fault recovery strategy for a distribution network according to an embodiment of the present invention, such as... Figure 3 As shown, the method includes:

[0050] S1: Constructing an optimized configuration for grid-based energy storage based on intelligent optimization algorithms:

[0051] S11: By analyzing the historical operating data and historical environmental information of multiple nodes in the mountainous distribution network (target distribution network), the natural disaster operating scenario, objective function and constraints of the target distribution network are determined. The specific implementation process is the same as the aforementioned embodiment, and will not be repeated here.

[0052] S12: Based on constraints and natural disaster operation scenarios, an intelligent optimization algorithm is adopted to optimize the energy storage capacity configuration of the mountain power distribution network with the objective function value as the optimization objective. The target energy storage configuration power is obtained. The specific implementation process is the same as the previous embodiment, and will not be repeated here.

[0053] S2: Real-time detection of mountain power distribution network based on deep reinforcement learning to detect whether there is a fault in the mountain power distribution at the current moment: Based on deep reinforcement learning, the monitoring values ​​corresponding to multiple nodes in the mountain power distribution network are compared with the preset normal threshold to determine the fault detection result of the mountain power distribution network. The specific implementation process is the same as the above embodiment, and will not be repeated here.

[0054] S3: In the event of a power distribution fault in the mountainous area at the current moment, the first area (faulted area) will switch to islanded operation and activate the active defense mechanism:

[0055] S31: In the event of a power distribution fault in the mountainous area at the current moment, the target power distribution network is divided into a first area and a second area, switched to island mode, and the first area is divided into multiple network groups. Each network group is autonomously controlled. The specific implementation process is the same as the aforementioned embodiment, and will not be repeated here.

[0056] S32: Based on the target energy storage configuration power, the total power supply of the determined first area is allocated to multiple grid groups, and the power supply corresponding to each of the multiple grid groups is determined in order to determine the operation status detection result of the first area. The specific implementation process is the same as the aforementioned embodiment, and will not be repeated here.

[0057] S4: Post-disaster recovery path planning, gradually restoring the connection between isolated islands and the main network: If the operation status detection result of the first area is in normal operation, based on the operation data of each of the multiple network groups and the operation data of the second area, the optimization target is determined, the initial fault recovery strategy is optimized, and the target fault recovery strategy is obtained to gradually connect the network groups in the first area with the second area. The specific implementation process is the same as the aforementioned embodiment, and will not be repeated here.

[0058] Based on the above embodiments and optional embodiments, this invention proposes an optional power distribution network fault recovery strategy determination system. This system includes: a grid-connected energy storage system, which uses an intelligent optimization algorithm to configure the target energy storage capacity to ensure the short-term normal operation of critical equipment during disasters, providing the necessary emergency power support and thus improving the disaster resistance and resilience of the mountainous power distribution network; an information acquisition module, used to monitor various operating parameters of the mountainous power distribution network in real time, including voltage, current, and power, and uploads the data to the intelligent detection module in real time through the cooperation of sensors and a data acquisition system, ensuring the accuracy and real-time nature of the mountainous power distribution network status information and providing data support for subsequent decision-making; an intelligent detection module, based on a deep reinforcement learning model, to monitor and detect anomalies in the power distribution network in real time; and a central control system, responsible for coordinating the operation of the entire network, especially automatically controlling the switching to islanded mode during fault occurrences to ensure that the faulty area (first area) maintains operation and gradually recovers. Meanwhile, during the post-disaster recovery process, a power grid restoration path was planned and implemented to ensure a smooth transition during the recovery process. By optimizing control strategies, the grid connection between the first and second regions was gradually achieved to ensure the stable operation of the system.

[0059] This embodiment can achieve at least one of the following effects: (1) This embodiment provides a distributed energy storage configuration scheme based on intelligent optimization algorithm, which reasonably configures the distributed grid-type energy storage system, realizes the island autonomy of the mountain distribution network during disasters, and effectively ensures the short-term operation of key equipment. This scheme provides the basis for the global coordination control of this embodiment and lays the foundation for improving the resilience of the mountain distribution network. (2) This embodiment constructs a real-time monitoring and detection mechanism based on deep reinforcement learning, which can dynamically analyze the current, voltage, power and other parameters of the power grid, discover potential problems in a timely manner and issue early warnings. When an anomaly occurs, the system can respond quickly and trigger an early warning, which significantly improves the accuracy and real-time performance of fault detection in the mountain distribution network. (3) When a fault occurs, the fault area is switched to island mode through an active defense mechanism to avoid the fault from spreading to other areas. In island mode, each microgrid group maintains stable operation through autonomous control, and the energy storage system provides necessary power to local loads, ensuring the continuity and reliability of the power grid during disasters and significantly reducing power outage time. (4) This embodiment proposes a post-disaster recovery path planning and realizes the gradual recovery and grid connection of the island area. Through decisions made by the central control system, the isolated area smoothly transitions back to the main grid. During the recovery process, the system precisely regulates parameters such as voltage and current through a pre-synchronization control strategy to avoid fluctuations and instability during grid connection, ensuring the smooth operation of the restored grid and enhancing its recovery capabilities.

[0060] This embodiment also provides a fault recovery strategy determination device for a distribution network. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0061] According to an embodiment of the present invention, an apparatus embodiment for implementing the above-described method for determining fault recovery strategies for a power distribution network is also provided. Figure 4 This is a schematic diagram of a fault recovery strategy determination device for a distribution network according to an embodiment of the present invention, as shown below. Figure 4 As shown, the above-mentioned fault recovery strategy determination device for the power distribution network includes: a fault detection result determination module 400, a target power distribution network division module 402, a first area operation status detection module 404, and a target fault recovery strategy determination module 406, wherein:

[0062] The fault detection result determination module 400 is used to determine the fault detection result of the target distribution network based on the current operating data of multiple nodes in the target distribution network. The current operating data includes at least the current, voltage and power of the corresponding node at the current moment.

[0063] The target distribution network division module 402 is connected to the fault detection result determination module 400. It is used to determine the fault node among multiple nodes when the fault detection result indicates that there is a fault in the target distribution network at the current time, and divide the target distribution network into a first region and a second region. The first region is the region associated with the fault node, and the second region is the region in the target distribution network other than the first region.

[0064] The first area operation status detection module 404 is connected to the target distribution network division module 402. It is used to detect the operation status of the first area during the process of supplying power to the first area based on the target energy storage configuration power. The target energy storage configuration power is used to indicate the power that the energy storage device will allocate to the first area within the predicted time period. The predicted time period is the first predetermined time period after the current time.

[0065] The target fault recovery strategy determination module 406 is connected to the first area operation status detection module 404. It is used to optimize the initial fault recovery strategy of the target distribution network based on the corresponding operation data of the first area and the second area when the operation status is normal, so as to obtain the target fault recovery strategy of the target distribution network.

[0066] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0067] It should be noted that the fault detection result determination module 400, target distribution network division module 402, first area operation status detection module 404, and target fault recovery strategy determination module 406 mentioned above correspond to steps S102 to S108 in the embodiments. The instances and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a computer terminal.

[0068] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0069] The aforementioned fault recovery strategy determination device for the power distribution network may further include a processor and a memory. The aforementioned fault detection result determination module 400, target power distribution network division module 402, first area operation status detection module 404, target fault recovery strategy determination module 406, etc., are all stored in the memory as program modules, and the processor executes the aforementioned program modules stored in the memory to realize the corresponding functions.

[0070] The processor contains a core that retrieves the corresponding program modules from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0071] According to an embodiment of this application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein, when the program runs, it controls the device where the non-volatile storage medium is located to execute any of the above-mentioned power distribution network fault recovery strategy determination methods.

[0072] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals, and the non-volatile storage medium includes stored programs.

[0073] Optionally, during program execution, the device containing the non-volatile storage medium performs the following functions: Based on the current operating data corresponding to multiple nodes in the target distribution network, determine the fault detection result of the target distribution network, wherein the current operating data includes at least the current, voltage, and power of the corresponding node at the current moment; if the fault detection result indicates that a fault exists in the target distribution network at the current moment, identify the faulty node among the multiple nodes and divide the target distribution network into a first region and a second region, wherein the first region is the region associated with the faulty node, and the second region is the region in the target distribution network excluding the first region; during the process of supplying power to the first region based on the target energy storage configuration power, detect the operating status of the first region, wherein the target energy storage configuration power is used to indicate the power allocated to the first region by the energy storage device within a predicted period, the predicted period being a period of a first predetermined duration after the current moment; if the operating status is normal operation, optimize the initial fault recovery strategy of the target distribution network based on the operating data corresponding to the first region and the second region, to obtain the target fault recovery strategy of the target distribution network.

[0074] According to an embodiment of this application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein the program executes any of the above-described methods for determining fault recovery strategies for power distribution networks.

[0075] According to an embodiment of this application, an embodiment of a computer program product is also provided. Optionally, in this embodiment, the computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described method for determining a fault recovery strategy for a power distribution network.

[0076] Optionally, when the aforementioned computer program product is executed on a data processing device, it is suitable to execute an initialization program with the following method steps: determining the fault detection result of the target distribution network based on the current operating data corresponding to each of multiple nodes in the target distribution network, wherein the current operating data includes at least the current, voltage, and power of the corresponding node at the current moment; if the fault detection result indicates that there is a fault in the target distribution network at the current moment, identifying the faulty node among the multiple nodes, and dividing the target distribution network into a first region and a second region, wherein the first region is the region associated with the faulty node, and the second region is the region in the target distribution network other than the first region; during the process of supplying power to the first region based on the target energy storage configuration power, detecting the operating status of the first region, wherein the target energy storage configuration power is used to indicate the power allocated to the first region by the energy storage device within a predicted period, the predicted period being a period of a first predetermined duration after the current moment; if the operating status is normal operation, optimizing the initial fault recovery strategy of the target distribution network based on the operating data corresponding to the first region and the second region respectively, to obtain the target fault recovery strategy of the target distribution network.

[0077] This invention provides an electronic device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: determining the fault detection result of the target distribution network based on the current operating data corresponding to multiple nodes in the target distribution network, wherein the current operating data includes at least the current, voltage, and power of the corresponding node at the current moment; if the fault detection result indicates that a fault exists in the target distribution network at the current moment, identifying the faulty node among the multiple nodes and dividing the target distribution network into a first region and a second region, wherein the first region is the region associated with the faulty node, and the second region is the region in the target distribution network excluding the first region; during the process of supplying power to the first region based on the target energy storage configuration power, detecting the operating status of the first region, wherein the target energy storage configuration power is used to indicate the power allocated to the first region by the energy storage device within a predicted time period, the predicted time period being a period of a first predetermined duration after the current moment; if the operating status is normal operation, optimizing the initial fault recovery strategy of the target distribution network based on the operating data corresponding to the first region and the second region, to obtain the target fault recovery strategy of the target distribution network.

[0078] The order of the above embodiments of the present invention is merely for description and does not represent the superiority or inferiority of the embodiments.

[0079] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of modules described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between modules, and may be electrical or other forms.

[0081] The modules described above as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0082] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0083] If the aforementioned integrated modules are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0084] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining fault recovery strategies in a power distribution network, characterized in that, include: Based on the current operating data of multiple nodes in the target distribution network, the fault detection result of the target distribution network is determined, wherein the current operating data includes at least the current, voltage and power of the corresponding node at the current moment; If the fault detection result indicates that there is a fault in the target distribution network at the current time, the faulty node among the plurality of nodes is determined, and the target distribution network is divided into a first region and a second region, wherein the first region is the region associated with the faulty node, and the second region is the region in the target distribution network other than the first region; During the process of supplying power to the first region based on the target energy storage configuration power, the operating status of the first region is detected, wherein the target energy storage configuration power is used to indicate the power allocated to the first region by the energy storage device within a predicted period, and the predicted period is a period of a first predetermined duration after the current moment; When the operating state is normal, the initial fault recovery strategy of the target distribution network is optimized based on the operating data corresponding to the first region and the second region respectively, so as to obtain the target fault recovery strategy of the target distribution network.

2. The method according to claim 1, characterized in that, Obtaining the target energy storage configuration power includes: Based on the historical operating data of the multiple nodes in the historical time period, the predicted energy storage power, predicted energy storage capacity, predicted load importance, predicted new energy power, predicted load power, and predicted grid power of the multiple nodes in the predicted time period are determined, wherein the historical time period is a second predetermined time period before the current time. Based on the historical environmental information of the target power distribution network during the historical period, the natural disaster operation scenario of the target power distribution network is determined, wherein the historical environmental information includes at least: historical meteorological information and historical geographical information of the area where the target power distribution network is located; Based on the predicted energy storage power, predicted energy storage capacity, and predicted load importance of each of the multiple nodes during the prediction period, the objective function of the target distribution network is determined. Based on the predicted energy storage power, predicted new energy power, predicted load power, and predicted grid power corresponding to each of the multiple nodes during the prediction period, the constraints of the target distribution network are determined. Based on the constraints and the natural disaster operation scenario, the initial energy storage configuration strategy is optimized with the objective function value being maximized as the optimization objective, to obtain the target energy storage configuration strategy. The initial energy storage configuration strategy is used to indicate the amount of electricity allocated by the energy storage device to multiple regions during the prediction period, and the multiple regions correspond one-to-one with the multiple nodes. Based on the target energy storage configuration strategy, the target energy storage configuration capacity is determined.

3. The method according to claim 2, characterized in that, The objective function for determining the target distribution network based on the predicted energy storage power, predicted energy storage capacity, and predicted load importance of each of the multiple nodes during the prediction period includes: Based on the predicted energy storage power, predicted energy storage capacity, and predicted load importance of each of the multiple nodes during the prediction period, the objective function is determined in the following manner: ； Where Z represents the function value of the objective function. This represents the number of nodes, where i represents the index of any node. Let t represent the prediction period, and t represent the index of any prediction time within the prediction period. This represents the predicted energy storage power of any node at any predicted time. This represents the predicted energy storage capacity of any given node. This indicates the importance of the predicted load for any given node. This represents the weighting coefficient corresponding to the predicted energy storage power. This represents the weighting coefficient corresponding to the predicted energy storage capacity. The weighting coefficient represents the weighting coefficient corresponding to the importance of the predicted load.

4. The method according to claim 2, characterized in that, The constraint conditions for determining the target distribution network based on the predicted energy storage power, predicted renewable energy power, predicted load power, and predicted grid power corresponding to each of the multiple nodes during the prediction period include: Based on the predicted energy storage power, predicted new energy power, predicted load power, and predicted grid power corresponding to each of the multiple nodes during the prediction period, the constraint condition is determined as follows: ； ； in, This represents the predicted load power of any node at any predicted time within the predicted period. This represents the predicted renewable energy power of any given node at any given prediction time. This represents the predicted energy storage power of any node at any predicted time. This represents the predicted grid power of any node at any prediction time. This represents the preset operating power of the load of any node at any predicted time in the natural disaster operation scenario.

5. The method according to claim 1, characterized in that, The determination of the fault detection result of the target distribution network based on the current operating data of multiple nodes in the target distribution network includes: Based on the current running data corresponding to each of the multiple nodes, multiple monitoring values ​​are obtained, wherein each of the multiple monitoring values ​​corresponds one-to-one with the multiple nodes, and the monitoring values ​​are used to indicate whether the corresponding node is in a normal state; If any of the monitored values ​​does not exceed a preset normal threshold, the fault detection result is determined to be that the target distribution network has a fault at the current time. If all of the monitored values ​​exceed the preset normal threshold, the fault detection result is determined to be that there is no fault in the target distribution network at the current time.

6. The method according to claim 1, characterized in that, In the case that there are multiple fault nodes, multiple energy storage devices, and multiple new energy sources, the step of detecting the operating status of the first region during the process of supplying power to the first region based on the target energy storage configuration includes: Based on preset division rules, the first area is divided into multiple network groups, wherein each network group includes at least one energy storage device and one new energy power source in the target distribution network; Based on the predicted energy storage power and predicted new energy power corresponding to each of the multiple fault nodes during the prediction period, the total power supply of the first region is determined. Based on the target energy storage configuration power, the total power supply is allocated to the multiple grid groups, and the power supply corresponding to each of the multiple grid groups is determined; Based on the power supply corresponding to each of the multiple network groups, the operation status detection result of the first area is determined.

7. The method according to claim 6, characterized in that, The determination of the operational status detection result of the first region based on the power supply corresponding to each of the multiple network groups includes: If the power supply of each of the multiple network groups is within the preset safe power supply range, then the operation status detection result is determined to be that the first area is in normal operation. If the power supply of any of the multiple network groups is outside the preset safe power supply range, the operation status detection result is determined to be that the first area is in an abnormal operation state.

8. The method according to any one of claims 1 to 7, characterized in that, When the first region includes multiple network clusters, and the operating state is normal, the initial fault recovery strategy of the target distribution network is optimized based on the operating data corresponding to the first region and the second region, to obtain the target fault recovery strategy of the target distribution network, including: When the operating state is normal, based on the operating data corresponding to each of the multiple network groups and the operating data of the second region, the optimization objective of the target distribution network is determined, wherein the optimization objective is: to minimize the fault recovery time of the target distribution network and maximize the total fault recovery load of the target distribution network; Based on the optimization objective, the initial fault recovery strategy is optimized to obtain the target fault recovery strategy.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions, which are adapted to be loaded by a processor and executed by the method for determining the fault recovery strategy of the distribution network as described in any one of claims 1 to 8.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method for determining the fault recovery strategy of the distribution network as described in any one of claims 1 to 8.

Images