Power grid fault recovery capability evaluation method and device and electronic equipment
By constructing voltage manifolds and calculating resilience indices, the problem of lack of geometric representation in the assessment of power grid fault recovery capability is solved, and accurate assessment and automated diagnosis of power grid fault recovery capability are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID BEIJING ELECTRIC POWER CO
- Filing Date
- 2026-04-20
- Publication Date
- 2026-05-29
Smart Images
Figure CN122109729A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the fields of new energy and energy conservation technology, and more specifically, to a method, apparatus and electronic equipment for assessing power grid fault recovery capability. Background Technology
[0002] With the high proportion of new energy integration and the widespread deployment of power electronic equipment, power grid fault patterns are becoming increasingly complex, and fault recovery processes exhibit strong nonlinearity, multi-stage coupling, and dynamic evolution characteristics. The significant shortcomings of related technologies in assessing power grid fault recovery capabilities are mainly reflected in the following aspects:
[0003] The assessment dimensions are singular, focusing only on whether the voltage recovers to a acceptable range after a fault, ignoring the dynamic evolution characteristics of the entire fault process. The lack of geometric modeling capabilities for the voltage state space leads to assessment results relying on human experience, lacking quantifiable and reproducible geometric indicators, and thus failing to support automated diagnosis and strategy optimization. Although fault recovery capability assessment methods in related technologies can provide preliminary quantification of fault impact to a certain extent, when facing the complex multi-node, multi-stage recovery process of power grids, the lack of geometric representation of the entire power grid fault recovery process results in insufficient accuracy in power grid fault recovery capability assessment.
[0004] There is currently no effective solution to the above problems. Summary of the Invention
[0005] This invention provides a method, apparatus, and electronic device for assessing power grid fault recovery capability, in order to at least solve the technical problem of low accuracy in assessing power grid fault recovery capability due to the lack of geometric representation of the entire power grid fault recovery process.
[0006] According to one aspect of the present invention, a method for assessing the fault recovery capability of a power grid is provided, comprising: acquiring multiple sets of voltage data collected from multiple voltage monitoring points within a target power grid, wherein the multiple sets of voltage data correspond one-to-one with multiple predetermined time periods, the multiple predetermined time periods including a predetermined duration before the fault occurrence time, a time period between the fault occurrence time and the start time of protection action, a time period between the start time of protection action and the fault clearance time, and a time period between the fault clearance time and the time when the power grid is in stable operation; the multiple sets of voltage data respectively include the voltage of the three-phase point to the neutral point and the voltage of the neutral point connection point at each of the multiple voltage monitoring points within the predetermined time periods; determining the voltage manifold of the target power grid based on the multiple sets of voltage data, wherein the voltage manifold is used to indicate the voltage variation characteristics of the target power grid within the multiple predetermined time periods; determining characteristic parameters of the target power grid based on the fault clearance time, the fault occurrence time, and the voltage manifold, wherein the characteristic parameters represent the geometric characteristics of the voltage manifold within the multiple predetermined time periods; and obtaining a resilience index of the target power grid based on the characteristic parameters, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
[0007] According to another aspect of the present invention, a power grid fault recovery capability assessment device is also provided, comprising: a voltage data acquisition module, configured to acquire multiple sets of voltage data collected from multiple voltage monitoring points within a target power grid, wherein the multiple sets of voltage data correspond one-to-one with multiple predetermined time periods, the multiple predetermined time periods including a predetermined duration before the fault occurrence time, a time period between the fault occurrence time and the protection operation start time, a time period between the protection operation start time and the fault clearance time, and a time period between the fault clearance time and the power grid stable operation time; the multiple sets of voltage data respectively include the voltage of the three-phase point to the neutral point and the voltage of the neutral point connection point at each of the multiple voltage monitoring points within the predetermined time periods; a voltage manifold determination module, configured to determine the voltage manifold of the target power grid based on the multiple sets of voltage data, wherein the voltage manifold is used to indicate the voltage variation characteristics of the target power grid within the multiple predetermined time periods; a characteristic parameter determination module, configured to determine characteristic parameters of the target power grid based on the fault clearance time, the fault occurrence time, and the voltage manifold, wherein the characteristic parameters represent the geometric characteristics of the voltage manifold within the multiple predetermined time periods; and a resilience index determination module, configured to obtain a resilience index of the target power grid based on the characteristic parameters, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
[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 adapted for loading by a processor and executing any one of the power grid fault recovery capability assessment methods.
[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 any one of the power grid fault recovery capability assessment methods.
[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 power grid fault recovery capability assessment method described in any one of the present invention.
[0011] In this embodiment of the invention, multiple sets of voltage data collected from multiple voltage monitoring points within a target power grid are acquired. Each set of voltage data corresponds one-to-one with multiple predetermined time periods, including a predetermined duration before the fault occurrence, a period between the fault occurrence and the start of protection action, a period between the start of protection action and the fault clearance, and a period between the fault clearance and the stable operation of the power grid. The multiple sets of voltage data each include the voltage of the three-phase point relative to the neutral point and the voltage at the neutral point connection point of each voltage monitoring point within the predetermined time period. Based on the multiple sets of voltage data, the voltage manifold of the target power grid is determined, whereby the voltage manifold indicates the voltage variation characteristics of the target power grid within the multiple predetermined time periods. Based on the fault clearance... In addition to the time of fault occurrence, the time of fault occurrence, and the voltage manifold, characteristic parameters of the target power grid are determined. These characteristic parameters represent the geometric characteristics of the voltage manifold over multiple predetermined time periods. Based on these characteristic parameters, the resilience index of the target power grid is obtained. This resilience index indicates the fault recovery capability of the target power grid. By constructing the voltage manifold of the target power grid based on voltage data before, during, and after the fault, and determining the corresponding calculable characteristic parameters of the voltage manifold, the resilience index of the target power grid is accurately determined. This achieves the technical effect of improving the accuracy of power grid fault recovery capability assessment and solves the technical problem of low accuracy in power grid fault recovery capability assessment caused by the lack of geometric representation of the entire power grid fault recovery process. 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 power grid fault recovery capability assessment method according to an embodiment of the present invention;
[0014] Figure 2This is a flowchart of an optional toughness level determination method according to an embodiment of the present invention;
[0015] Figure 3 This is a flowchart of an optional power grid fault recovery capability assessment method according to an embodiment of the present invention;
[0016] Figure 4 This is a schematic diagram of a power grid fault recovery capability assessment device according to an embodiment of the present invention;
[0017] Figure 5 This is a schematic diagram of an electronic device for assessing power grid fault recovery capability according to an embodiment of the present invention. Detailed Implementation
[0018] 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.
[0019] 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.
[0020] First, to facilitate understanding of the embodiments of the present invention, some terms or nouns involved in the present invention will be explained below:
[0021] A voltage manifold is a geometric space that describes all possible voltage states, where the manifold can be locally approximated as a curved space of Euclidean space.
[0022] Latent space is a core concept in machine learning, especially deep learning and generative models. It refers to a low-dimensional, implicit feature space to which data is mapped after undergoing some nonlinear transformation, where each point represents some abstract representation or latent feature of the original data.
[0023] According to an embodiment of the present invention, a method embodiment for assessing the fault recovery capability of a power grid 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.
[0024] Figure 1 This is a flowchart of a power grid fault recovery capability assessment method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:
[0025] Step S102: Acquire multiple sets of voltage data collected from multiple voltage monitoring points within the target power grid. Each set of voltage data corresponds to a predetermined time period, which includes a predetermined duration before the fault occurs, a time period between the fault occurrence and the start of protection action, a time period between the start of protection action and the fault clearance, and a time period between the fault clearance and the stable operation of the power grid. The multiple sets of voltage data include the voltage of the three-phase point relative to the neutral point and the voltage at the neutral point connection point of each voltage monitoring point within the predetermined time period.
[0026] Optionally, by deploying high-precision distributed terminals at voltage monitoring points in the target power grid, voltage data corresponding to each of the entire fault recovery process (i.e., multiple predetermined time periods) can be collected synchronously. The acquired multiple sets of voltage data not only cover the four key time-series stages: the normal operation state before the fault occurs, the transient distortion period from the time of the fault occurrence to the time of the protection action, the continuous disturbance period from the time of the protection action to the time of the fault clearance, and the recovery and adjustment period from the time of the fault clearance to the time of the target power grid's transition to stable operation, but each set of voltage data also includes the three-phase point-to-neutral point voltage and the neutral point docking point voltage of each voltage monitoring point, which can comprehensively capture the spatiotemporal evolution characteristics of the three-phase voltage amplitude, phase change, and zero-sequence component. Among them, the fault occurrence time is the moment when a sudden electrical disturbance such as a short circuit or grounding occurs at a certain point in the target power grid, causing an abnormal voltage drop; the protection action start time is the moment when the relay protection device detects the fault and issues a trip command, starting to disconnect the faulty branch; the fault clearance time is the moment when the circuit breaker completes the opening, the fault current is completely isolated, and the target power grid enters a fault-free state but is still in a transient state; the power grid stable operation time is the moment when the target power grid, through the action of automatic adjustment or control devices, restores key parameters such as voltage and frequency to the safe allowable range and remains stable; the three-phase point-to-neutral point voltage reflects the symmetry and transient drop or rise behavior of the phase-to-phase voltage of the target power grid, while the neutral point-to-ground point voltage directly characterizes the neutral point offset and grounding point potential rise caused by grounding faults, unbalanced loads, or insulation abnormalities. The two together provide complete electrical information for identifying complex fault types such as single-phase grounding and two-phase short circuits. By strictly aligning multiple predetermined time periods with corresponding voltage data according to timestamps, a dynamic database representing the entire process of a target power grid fault in a unified manner across the three dimensions of time, voltage, and topology can be constructed. This overcomes the one-sidedness of related technologies that only focus on whether the steady-state voltage recovers after a fault, thus achieving a fundamental shift from fragmented results to a holistic view of the process. Through data acquisition, the subsequently constructed voltage manifold can realistically reconstruct the complete electrical memory trajectory of the target power grid from being disturbed in a healthy state, forced to deviate, actively recovering, until a new equilibrium is reached.
[0027] Step S104: Based on multiple sets of voltage data, determine the voltage manifold of the target power grid, wherein the voltage manifold is used to indicate the voltage variation characteristics of the target power grid over multiple predetermined time periods.
[0028] Optionally, based on multiple sets of voltage data collected synchronously at various predetermined time periods throughout the fault recovery process, the original, high-dimensional, multi-node voltage data is mapped to a low-dimensional, continuous latent space by jointly modeling the target power grid topology and the spatiotemporal evolution relationship of voltage. The voltage manifold is then reconstructed within this latent space. This voltage manifold is not a static statistical distribution, nor is it an isolated cluster of points. Instead, it is a smooth, continuous nonlinear surface composed of low-dimensional state sequences at all sampling times within the corresponding predetermined time period. This latent space fully carries the dynamic evolution trajectory of the target power grid voltage state within that predetermined time period.
[0029] In one optional embodiment, when there are multiple voltage manifolds, determining the voltage manifold of the target power grid based on multiple sets of voltage data includes: obtaining a topology graph of the target power grid, wherein multiple nodes in the topology graph correspond one-to-one with multiple voltage monitoring points, and multiple edges in the topology graph are obtained based on the topology connection relationship of the target power grid; and using a graph encoder based on multiple sets of voltage data and the topology graph to obtain multiple voltage manifolds, wherein multiple voltage manifolds correspond one-to-one with multiple sets of voltage data.
[0030] Optionally, when voltage manifolds need to model multiple predetermined time periods throughout the fault recovery process, to ensure that each voltage manifold not only reflects voltage time-series changes but also accurately carries the physical topology information of the target power grid, a topology graph of the target power grid needs to be constructed first. Each node in this graph strictly corresponds to an actual deployed voltage monitoring point, and each edge is established based on the actual physical connection relationships of the power grid (such as feeder impedance, switch on / off status, and transformer coupling relationships), thus forming a graph structure model completely consistent with the target power grid structure, providing structural prior knowledge for subsequent voltage data modeling. This topology graph construction process can solve the technical problem in related technologies where the topology relationships between nodes are ignored, and only each voltage monitoring point is processed independently, resulting in the inability to capture fault propagation paths and regional collaborative behavior. Based on this, multiple sets of voltage data (each set corresponding to a predetermined time period) are jointly input into a graph encoder along with the topology graph. Finally, for each predetermined time period, the graph encoder outputs a corresponding voltage manifold, and this manifold corresponds one-to-one with the voltage data for that predetermined time period. Through the conditional encoding mechanism, the graph encoder can clearly distinguish the operating states of different predetermined time periods, avoid manifold distortion caused by time period overlap, and ensure that each manifold only represents the dynamic characteristics of its corresponding stage.
[0031] In an optional embodiment, when multiple voltage manifolds include a ground-state manifold, a distorted manifold, a recovered manifold, and a steady-state manifold, multiple voltage manifolds are obtained based on multiple sets of voltage data and a topology graph using a graph encoder. This includes: obtaining low-dimensional state sequences corresponding to each set of voltage data using a graph encoder based on multiple sets of voltage data and a topology graph, wherein multiple low-dimensional vectors included in the low-dimensional state sequences correspond one-to-one with multiple sampling times within a predetermined time period, and the multiple low-dimensional vectors are used to indicate the voltage operating state of the target power grid at the corresponding sampling time; and performing probability density fitting on each of the low-dimensional state sequences corresponding to the multiple sets of voltage data to obtain multiple sets of... The voltage data corresponds to a probability distribution region in the latent space, where the latent space represents the variable space output by the graph encoder. For each corresponding probability distribution region, manifold fitting is performed to obtain the ground state manifold, distorted manifold, recovered manifold, and steady state manifold. The ground state manifold is used to indicate the voltage change characteristics of the target power grid before the fault occurs. The distorted manifold is used to indicate the voltage change characteristics of the target power grid from the fault occurrence time to the start of the protection action. The recovered manifold is used to indicate the voltage change characteristics of the target power grid from the start of the protection action to the fault clearance time. The steady state manifold is used to indicate the voltage change characteristics of the target power grid from the fault clearance time to the time when the power grid is in stable operation.
[0032] Optionally, a graph encoder can be used to jointly encode the power grid topology graph and multiple sets of voltage data, thereby extracting physically meaningful low-dimensional state sequences from high-dimensional, heterogeneous, and time-varying voltage observations. Specifically, the graph encoder takes the physical connection structure of the target power grid as a priori, inputs voltage data from each voltage monitoring point at each sampling time, aggregates the electrical responses of adjacent nodes through a graph neural network, and outputs low-dimensional vectors corresponding to each sampling time. These vectors are not simple compressions of the original voltage, but rather global voltage operating state codes that integrate topology propagation effects, inter-phase coupling relationships, and grounding anomaly responses. They can fully characterize the voltage state of the target power grid during a specific time period, such as stable fluctuations, violent oscillations, or local collapses. Based on this, for the low-dimensional state sequence corresponding to each predetermined time period, probability density fitting is performed on its distribution in the latent space to form multiple independent but continuous probability distribution regions with statistical significance. These probability distribution regions are not isolated point clouds, but smooth, embedded dynamic state clouds characterized by thousands of low-dimensional vectors. Multiple probability distribution regions represent sets of operating states of the target power grid under different operating phases. Subsequently, nonlinear manifold fitting is performed on each probability distribution region. A smooth, continuous, and low-dimensional embedding surface can be constructed using manifold learning algorithms (such as manifold regression, minimum curvature embedding, or Gaussian process regression), thereby obtaining multiple voltage manifolds with clear physical meanings. Among them, the ground-state manifold is used to capture the inherent natural fluctuation boundary of the voltage during normal operation of the target power grid; the distorted manifold is used to characterize the nonlinear surface formed by the sudden disturbance forcibly pulling the voltage away from the ground state after the fault occurs and before the protection action; the restored manifold accurately depicts the entire trajectory of the target power grid transitioning from the worst state to a new steady state after the protection action; and the steady-state manifold finally locks the stable operating state reached by the target power grid after the fault is cleared and adjusted.
[0033] Step S106: Based on the fault clearance time, the fault occurrence time, and the voltage manifold, determine the characteristic parameters of the target power grid, wherein the characteristic parameters represent the geometric characteristics of the voltage manifold over multiple predetermined time periods.
[0034] Optionally, within each predetermined time period, a series of characteristic parameters reflecting the inherent dynamic response characteristics of the target power grid are extracted by quantitatively analyzing the geometric structure of the voltage manifold in the latent space. These characteristic parameters are data-driven manifold topological properties that automatically capture the true movement trajectory of the target power grid in the multidimensional voltage space. Geometric characteristics refer to quantitative indicators obtained by performing geometric operations on the voltage manifold in the latent space. Table 1 shows a plurality of optional characteristic parameters according to an embodiment of the present invention. As can be seen from the table, the plurality of characteristic parameters are calculated based on the voltage manifold in the low-dimensional latent space. This calculation method can break through the qualitative evaluation method in related technologies that relies on a single voltage amplitude or human experience, and realize the whole-chain evaluation from whether the fault has been recovered to how it has been recovered and how stable the recovery is.
[0035] Table 1
[0036]
[0037] In an optional embodiment, given that the voltage manifold includes a ground-state manifold, a distorted manifold, a recovery manifold, and a steady-state manifold, and the characteristic parameters include deviation depth, fault duration, recovery margin, and recovery trajectory volatility, the characteristic parameters of the target power grid are determined based on the fault clearance time, the fault occurrence time, and the voltage manifold. This includes: obtaining the deviation depth based on the ground-state manifold and the distorted manifold, where the deviation depth is used to quantify the degree to which the target power grid deviates from its normal operating state after the fault occurs; obtaining the fault duration based on the fault clearance time and the fault occurrence time; obtaining the recovery margin based on the steady-state manifold and a preset voltage safety boundary, where the recovery margin is used to quantify the voltage regulation margin of the target power grid after stable operation; and obtaining the recovery trajectory volatility based on the distorted manifold and the steady-state manifold, where the recovery trajectory volatility is used to quantify the non-smoothness of the voltage recovery trajectory of the target power grid during the period from the fault occurrence time to the stable operation time of the power grid.
[0038] Optionally, the deviation depth is obtained by calculating the geodesic distance (such as Hausdorff distance or centroid distance) between the distorted manifold and the ground-state manifold, used to characterize the degree to which the target power grid deviates from its normal operating state under fault disturbance. This deviation depth can effectively identify voltage collapse caused by multi-node coordinated disturbances and circulating currents. The larger the deviation depth, the more severe the impact on the target power grid and the higher the difficulty of recovery. The fault duration is obtained by directly subtracting the fault occurrence time from the fault clearance time, used to assess whether the protection action is fast enough and whether it meets the requirements of rapid disconnection and loss reduction. The recovery margin is the shortest geodesic distance between the target power grid operating point and the preset voltage safety boundary manifold in the steady-state manifold. Its core significance lies in revealing the inherent safety redundancy space of the target power grid after recovery. If the recovery margin approaches zero, even if the apparent voltage meets the standard, the target power grid is highly susceptible to overshooting again due to secondary disturbances such as load fluctuations and sudden changes in renewable energy output. Sufficient recovery margin indicates that the target power grid not only achieves fault recovery but also reserves enough buffer space, effectively avoiding the risk of false stability and providing operators with a true safety margin for diagnosis. The recovery trajectory volatility is obtained by calculating the curvature of the recovery trajectory from the distorted manifold to the steady-state manifold, directly reflecting the smoothness of the voltage state evolution path and the intensity of control impacts during the recovery process. If the voltage recovery trajectory is sharply curved with significant curvature peaks, it indicates multiple power surges, control parameter mismatches, or multiple distributed resource coordination conflicts during the fault recovery process. Conversely, a smooth voltage recovery trajectory indicates a coordinated fault recovery process and strong self-healing capability of the target power grid. The characteristic parameter determination method in this embodiment overcomes the limitations of evaluation methods relying on single-point voltage, human experience, and static thresholds in related technologies, enabling a quantifiable analysis of the entire process of target power grid recovery quality.
[0039] In one optional embodiment, the recovery trajectory volatility is obtained based on the distorted manifold and the steady-state manifold, including: obtaining the voltage recovery trajectory curve of the target power grid based on the distorted manifold and the steady-state manifold, wherein the horizontal axis of the voltage recovery trajectory curve represents multiple target sampling times included in the target time period, the vertical axis of the voltage recovery trajectory curve represents the low-dimensional vector corresponding to each of the multiple target sampling times, and the target time period is the time period between the fault occurrence time and the stable operation time of the power grid; obtaining the curvature corresponding to each of the multiple target sampling times based on the voltage recovery trajectory curve; and determining that the curvature greater than a preset curvature among the curvatures corresponding to the multiple target sampling times is the recovery trajectory volatility.
[0040] Optionally, to accurately characterize the recovery smoothness and control impact of the target power grid during the transition from the worst-case state to the final steady state after a fault, curvature analysis is performed on the voltage recovery trajectory curve based on the recovery trajectory volatility. Specifically, firstly, during the entire recovery period from the fault occurrence to the point of stable grid operation, a graph encoder continuously outputs the distorted manifold and steady-state manifold in the latent space, forming a continuous and dynamically evolving voltage recovery trajectory curve. Further, based on this voltage recovery trajectory curve, the local path curvature corresponding to each target sampling time is calculated. Curvature indicates the degree of bending of the voltage recovery trajectory curve at a certain point; a larger curvature indicates that the trajectory experiences a sudden change, bend, or sharp turn near that point. By performing point-by-point curvature estimation on the entire voltage recovery trajectory curve (e.g., using third-order difference or moving window fitting methods), a series of discrete curvature values can be obtained. The curvature of any target sampling can be obtained using the third-order difference method. ,in, This represents the tangential velocity (i.e., the first derivative) of any target sample. Let represent the normal acceleration (i.e., the second derivative) of any target sample, and ...
[0041] Step S108: Based on the characteristic parameters, obtain the resilience index of the target power grid, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
[0042] Optionally, to characterize the overall recovery capability and shock resilience of the target power grid after being subjected to fault disturbances, instead of relying on a single indicator or empirical judgment, a resilience index is calculated based on characteristic parameters to achieve a synergistic quantification of the target power grid's ability to withstand shocks and its self-healing capabilities. This resilience index can enable the operation and maintenance of the target power grid to shift from experience-driven to data-driven approaches.
[0043] In an optional embodiment, when the characteristic parameters include deviation depth, fault duration, recovery margin, and recovery trajectory volatility, the resilience index of the target power grid is obtained based on the characteristic parameters, including: the resilience index is obtained based on deviation depth, fault duration, recovery margin, and recovery trajectory volatility in the following manner:
[0044] ;
[0045] in, Indicates the resilience index. Indicates recovery margin, Indicates deviation from depth. Indicates the duration of the fault. Indicates the degree of fluctuation in the recovery trajectory. This represents the preset normalization coefficient.
[0046] Optionally, the numerator of the formula represents the safety buffer space remaining after the target power grid is restored, while the three terms in the denominator represent the triple costs borne by the target power grid to achieve restoration: the degree of damage to the target power grid structure caused by the fault (deviation depth); the hysteresis of the target power grid's response to disturbances (fault duration); and the dynamic disturbances caused by improper control intervention during the restoration process (trajectory volatility). This embodiment deeply integrates voltage manifold analysis with dynamic trajectory modeling, giving each parameter a clear physical meaning, thereby calculating the resilience index of the target power grid.
[0047] In one alternative embodiment, Figure 2 This is a flowchart of an optional toughness level determination method according to an embodiment of the present invention, such as... Figure 2 As shown, after obtaining the resilience index of the target power grid based on the characteristic parameters, the method further includes:
[0048] Step S202: If the resilience index is greater than the first preset resilience index, the target power grid is determined to be at the first resilience level. The first resilience level is used to indicate that the target power grid does not need to implement a voltage control strategy to cope with at least one external disturbance after it has been operating stably.
[0049] Step S204: If the resilience index is less than or equal to the first preset resilience index and the resilience index is greater than or equal to the second preset resilience index, the target power grid is determined to be at the second resilience level. The second resilience level is used to indicate that a voltage control strategy needs to be implemented after stable operation to cope with an external disturbance.
[0050] Step S206: If the resilience index is less than the second preset resilience index and the resilience index is greater than or equal to the third preset resilience index, the target power grid is determined to be at the third resilience level. The third resilience level is used to indicate that there is a risk of voltage exceeding the limit after stable operation, and reactive power compensation operation needs to be performed to suppress voltage fluctuations.
[0051] Step S208: If the resilience index is less than the third preset resilience index and the resilience index is greater than or equal to the fourth preset resilience index, the target power grid is determined to be at the fourth resilience level. The fourth resilience level is used to indicate that there is a risk of voltage exceeding the limit after stable operation, and it is necessary to perform a power supply path switching operation to suppress voltage fluctuations.
[0052] Step S210: If the resilience index is less than the fourth preset resilience index, the target power grid is determined to be at the fifth resilience level. The fifth resilience level is used to indicate that maintenance operations are required on the target power grid after stable operation.
[0053] Optionally, based on the quantitative assessment of the target power grid's recovery capability using the resilience index, a five-level resilience level linkage response mechanism can be further constructed. This can realize a closed-loop operation and maintenance system from single-indicator evaluation to hierarchical intelligent decision-making: When the resilience index is higher than the first threshold, the target power grid is determined to have sufficient inherent stability margin and disturbance resistance capability, and can withstand at least one typical external disturbance (such as sudden changes in new energy output or load fluctuations) without any intervention, and is classified as excellent resilience (first resilience level), indicating that the target power grid's self-healing capability has reached an ideal state; when the resilience index is less than or equal to the first preset resilience index and greater than or equal to the second preset resilience index, it indicates that although the target power grid can recover to a steady state, its safety redundancy is limited, and it is necessary to actively activate voltage control strategies (such as energy storage pre-charge and discharge) before the disturbance occurs to cope with a single disturbance, and is classified as good resilience (second resilience level), reflecting the value of preventive control; when the resilience index is less than the second preset resilience index and greater than or equal to the second preset resilience index, the target power grid is classified as good resilience (second resilience level), indicating that the target power grid can recover to a steady state, but ... When the resilience index equals the third preset resilience index, it indicates that the voltage after recovery is close to the safety boundary and there is a risk of exceeding the limit. Reactive power compensation operations (such as switching capacitors and adjusting voltage regulating transformers) must be performed immediately to stabilize the voltage. This is classified as medium resilience (third resilience level) and triggers active reactive power dispatch. When the resilience index is further less than the third preset resilience index but greater than or equal to the fourth preset resilience index, it indicates that the target power grid structure is weak and reactive power regulation alone is insufficient to maintain voltage stability. Automatic recommendation of switching power supply paths (such as loop switching and tie switch operation) is needed to reconstruct the network topology to block voltage degradation links. This is classified as poor resilience (fourth resilience level) and enters network-level intervention. When the resilience index is lower than the fourth threshold, it is determined that the target power grid is on the verge of collapse. The recovery process has serious defects and deviates significantly from the healthy manifold. Equipment maintenance, protection verification, or grid structure transformation must be arranged immediately. This is classified as critical resilience (fifth resilience level) and requires triggering a mandatory maintenance work order. This grading system is based entirely on the geometric quantification results of the resilience index and is automatically mapped without manual judgment. It can achieve four-step linkage of assessment, grading, strategy and action, enabling the target power grid to shift from passively responding to faults to actively predicting risks, and significantly improving the operational safety, self-healing efficiency and operation and maintenance efficiency of the target power grid in the context of high proportion of new energy access.
[0054] Through the above steps S102 to S108, the voltage manifold of the target power grid can be constructed based on voltage data before, during, and after the fault, and the calculable characteristic parameters corresponding to the voltage manifold can be determined. Finally, the resilience index of the target power grid can be accurately determined, thereby achieving the technical effect of improving the accuracy of power grid fault recovery capability assessment. This solves the technical problem of low accuracy of power grid fault recovery capability assessment caused by the lack of geometric representation of the entire power grid fault recovery process.
[0055] 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 power grid fault recovery capability assessment method according to an embodiment of the present invention. Taking a 10kV power grid as an example, distributed terminals are deployed to collect voltage data throughout the entire power grid fault process. Figure 3 As shown, the method includes:
[0056] S1: During the entire process of power grid fault recovery, the voltage of the three-phase point to the neutral point and the voltage of the neutral point connection point are collected from multiple voltage monitoring points to obtain multiple sets of voltage data. Specifically, the distributed terminal collects the voltage of the neutral point and the voltage of the neutral point connection point before the target power grid fault occurs, during the fault, during the protection action intervention, and during the steady-state recovery process according to the preset sampling frequency.
[0057] S2: Input multiple sets of voltage data and the topology map of the target power grid into the graph encoder to obtain multiple voltage manifolds. Specifically, the graph encoder takes multiple sets of voltage data and the topology map of the target power grid as input, uses a graph neural network structure to model the electrical topology relationships between multiple voltage monitoring points, and compresses the high-dimensional voltage space into a low-dimensional latent space through a variational autoencoder mechanism. The model first learns the latent distribution of the normal operating state through the encoder and extracts the ground state manifold; then, after a fault occurs, it separates the distorted manifold before the protection action; after the protection action, it tracks the state evolution during the recovery process to generate the recovery manifold; finally, after the power grid stabilizes, it locks the final steady-state manifold. The specific implementation process is the same as in the previous embodiment and will not be repeated here.
[0058] S3: Based on multiple voltage manifolds, calculate multiple characteristic parameters, including at least deviation depth, fault duration, recovery margin, and recovery trajectory variability. For example, calculate the deviation depth of the power grid. Fault duration , restore margin , restore trajectory fluctuation The specific implementation process is the same as the aforementioned embodiments, and will not be repeated here.
[0059] S4: Based on characteristic parameters, calculate the resilience index of the power grid and determine the resilience level. For example, the resilience index of the power grid can be calculated based on deviation depth, fault duration, recovery margin, and recovery trajectory volatility. The resilience index is between the second preset resilience index (e.g., 5) and the third preset resilience index (e.g., 3), and is determined to be the third resilience level. This indicates that the power grid indicates that there is a risk of voltage exceeding the limit after stable operation, and reactive power compensation operation needs to be performed to suppress voltage fluctuations. The specific implementation process is the same as the aforementioned embodiment, and will not be repeated here.
[0060] This embodiment can achieve at least one of the following effects: (1) It constructs a quantifiable recovery trajectory geometric index system, transforming the fuzzy recovery quality into calculable indicators such as deviation depth, recovery path length, recovery trajectory fluctuation, recovery force, and damping coefficient, making the evaluation results objective and reproducible. (2) It designs a resilience index, which comprehensively reflects the target power grid's resistance to shocks and self-healing capabilities with a single value, facilitating horizontal comparisons between different events and providing a quantitative basis for protection setting verification, control strategy evaluation, and equipment aging early warning. (3) It outputs an automated evaluation report, i.e., the resilience level result, forming an intuitive diagnostic result similar to a physical examination report, making it easy for maintenance personnel to quickly understand the recovery status of the target power grid.
[0061] This embodiment also provides a power grid fault recovery capability assessment device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. 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 device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0062] According to an embodiment of the present invention, an apparatus embodiment for implementing the above-described power grid fault recovery capability assessment method is also provided. Figure 4 This is a schematic diagram of the structure of a power grid fault recovery capability assessment device according to an embodiment of the present invention, as shown below. Figure 4 As shown, the aforementioned power grid fault recovery capability assessment device includes: a voltage data acquisition module 400, a voltage manifold determination module 402, a characteristic parameter determination module 404, and a resilience index determination module 406, wherein:
[0063] The voltage data acquisition module 400 is used to acquire multiple sets of voltage data collected from multiple voltage monitoring points within the target power grid. The multiple sets of voltage data correspond one-to-one with multiple predetermined time periods, including a predetermined time period before the fault occurs, a time period between the fault occurs and the start of the protection action, a time period between the start of the protection action and the fault is cleared, and a time period between the fault is cleared and the power grid is in stable operation. The multiple sets of voltage data include the voltage of the three-phase point relative to the neutral point and the voltage at the neutral point connection point of each of the multiple voltage monitoring points within the predetermined time period.
[0064] The voltage manifold determination module 402 is connected to the voltage data acquisition module 400 and is used to determine the voltage manifold of the target power grid based on multiple sets of voltage data. The voltage manifold is used to indicate the voltage variation characteristics of the target power grid in multiple predetermined time periods.
[0065] The characteristic parameter determination module 404 is connected to the voltage manifold determination module 402 and is used to determine the characteristic parameters of the target power grid based on the fault clearance time, the fault occurrence time and the voltage manifold, wherein the characteristic parameters represent the geometric characteristics of the voltage manifold in multiple predetermined time periods;
[0066] The resilience index determination module 406 is connected to the characteristic parameter determination module 404 and is used to obtain the resilience index of the target power grid based on the characteristic parameters, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
[0067] 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.
[0068] It should be noted that the voltage data acquisition module 400, voltage manifold determination module 402, characteristic parameter determination module 404, and toughness index 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.
[0069] 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.
[0070] The aforementioned power grid fault recovery capability assessment device may also include a processor and a memory. The voltage data acquisition module 400, voltage manifold determination module 402, characteristic parameter determination module 404, resilience index 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.
[0071] 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.
[0072] 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 containing the non-volatile storage medium to execute any of the aforementioned power grid fault recovery capability assessment methods.
[0073] 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.
[0074] Optionally, during program execution, the device containing the non-volatile storage medium is controlled to perform the following functions: acquire multiple sets of voltage data collected from multiple voltage monitoring points within the target power grid, wherein each set of voltage data corresponds one-to-one with multiple predetermined time periods, including a predetermined duration before the fault occurrence time, a time period between the fault occurrence time and the start time of protection action, a time period between the start time of protection action and the fault clearance time, and a time period between the fault clearance time and the time when the power grid is in stable operation; the multiple sets of voltage data respectively include the voltage of the three-phase point to the neutral point and the voltage of the neutral point to the ground point at each of the multiple voltage monitoring points within the predetermined time periods; based on the multiple sets of voltage data, determine the voltage manifold of the target power grid, wherein the voltage manifold is used to indicate the voltage variation characteristics of the target power grid within the multiple predetermined time periods; based on the fault clearance time, the fault occurrence time, and the voltage manifold, determine the characteristic parameters of the target power grid, wherein the characteristic parameters represent the geometric characteristics of the voltage manifold within the multiple predetermined time periods; based on the characteristic parameters, obtain the resilience index of the target power grid, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
[0075] 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 power grid fault recovery capability assessment methods.
[0076] 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 any of the above-described power grid fault recovery capability assessment methods.
[0077] 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: acquiring multiple sets of voltage data collected from multiple voltage monitoring points within the target power grid, wherein the multiple sets of voltage data correspond one-to-one with multiple predetermined time periods, including a predetermined duration before the fault occurrence time, a time period between the fault occurrence time and the start time of protection action, a time period between the start time of protection action and the fault clearance time, and a time period between the fault clearance time and the time when the power grid is in stable operation; the multiple sets of voltage data respectively include the voltage of the three-phase point to the neutral point and the voltage of the neutral point to the neutral point connection point of each of the multiple voltage monitoring points in the predetermined time periods; determining the voltage manifold of the target power grid based on the multiple sets of voltage data, wherein the voltage manifold is used to indicate the voltage variation characteristics of the target power grid within the multiple predetermined time periods; determining the characteristic parameters of the target power grid based on the fault clearance time, the fault occurrence time, and the voltage manifold, wherein the characteristic parameters represent the geometric characteristics of the voltage manifold within the multiple predetermined time periods; and obtaining the resilience index of the target power grid based on the characteristic parameters, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
[0078] like Figure 5As shown, this embodiment of the invention provides an electronic device 10, which includes 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: acquiring multiple sets of voltage data collected from multiple voltage monitoring points within a target power grid, wherein the multiple sets of voltage data correspond one-to-one with multiple predetermined time periods, including a predetermined time period before the fault occurrence time, a time period between the fault occurrence time and the start time of protection action, a time period between the start time of protection action and the fault clearance time, and a time period between the fault clearance time and the time when the power grid is in stable operation; the multiple sets of voltage data respectively include the voltage of the three-phase point to the neutral point and the voltage of the neutral point to the neutral point connection point of each of the multiple voltage monitoring points in the predetermined time period; determining the voltage manifold of the target power grid based on the multiple sets of voltage data, wherein the voltage manifold is used to indicate the voltage variation characteristics of the target power grid within the multiple predetermined time periods; determining the characteristic parameters of the target power grid based on the fault clearance time, the fault occurrence time, and the voltage manifold, wherein the characteristic parameters represent the geometric characteristics of the voltage manifold within the multiple predetermined time periods; and obtaining the resilience index of the target power grid based on the characteristic parameters, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
[0079] 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.
[0080] 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.
[0081] 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.
[0082] 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.
[0083] 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.
[0084] 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.
[0085] 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 assessing power grid fault recovery capability, characterized in that, include: Multiple sets of voltage data collected from multiple voltage monitoring points within the target power grid are acquired. Each set of voltage data corresponds to a predetermined time period, which includes a predetermined duration before the fault occurs, a time period between the fault occurrence and the start of protection action, a time period between the start of protection action and the fault clearance, and a time period between the fault clearance and the stable operation of the power grid. Each set of voltage data includes the voltage of the three-phase point relative to the neutral point and the voltage at the neutral point connection point of each voltage monitoring point within the predetermined time period. Based on the multiple sets of voltage data, the voltage manifold of the target power grid is determined, wherein the voltage manifold is used to indicate the voltage variation characteristics of the target power grid within the multiple predetermined time periods; Based on the fault clearance time, the fault occurrence time, and the voltage manifold, characteristic parameters of the target power grid are determined, wherein the characteristic parameters represent the geometric characteristics of the voltage manifold within the multiple predetermined time periods; Based on the aforementioned characteristic parameters, a resilience index for the target power grid is obtained, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
2. The method according to claim 1, characterized in that, When there are multiple voltage manifolds, determining the voltage manifold of the target power grid based on the multiple sets of voltage data includes: Obtain the topology graph of the target power grid, wherein multiple nodes in the topology graph correspond one-to-one with multiple voltage monitoring points, and multiple edges in the topology graph are obtained based on the topological connection relationship of the target power grid; Based on the multiple sets of voltage data and the topology association graph, a graph encoder is used to obtain multiple voltage manifolds, wherein the multiple voltage manifolds correspond one-to-one with the multiple sets of voltage data.
3. The method according to claim 2, characterized in that, When the multiple voltage manifolds include a ground-state manifold, a distorted manifold, a recovered manifold, and a steady-state manifold, the multiple voltage manifolds are obtained by using a graph encoder based on the multiple sets of voltage data and the topological correlation graph, including: Based on the multiple sets of voltage data and the topology association graph, the graph encoder is used to obtain the low-dimensional state sequence corresponding to each of the multiple sets of voltage data. The multiple low-dimensional vectors included in the low-dimensional state sequence correspond one-to-one with multiple sampling times within a predetermined time period. The multiple low-dimensional vectors are used to indicate the voltage operation status of the target power grid at the corresponding sampling time. Based on the low-dimensional state sequences corresponding to each of the multiple sets of voltage data, probability density fitting is performed to obtain the probability distribution regions corresponding to each of the multiple sets of voltage data in the latent space, wherein the latent space represents the variable space output by the graph encoder; For each of the corresponding probability distribution regions, manifold fitting is performed to obtain the ground state manifold, the distorted manifold, the recovered manifold, and the steady-state manifold. The ground state manifold is used to indicate the voltage change characteristics of the target power grid before the fault occurs. The distorted manifold is used to indicate the voltage change characteristics of the target power grid from the fault occurrence time to the start time of the protection action. The recovered manifold is used to indicate the voltage change characteristics of the target power grid from the start time of the protection action to the fault clearance time. The steady-state manifold is used to indicate the voltage change characteristics of the target power grid from the fault clearance time to the time when the power grid is operating stably.
4. The method according to claim 1, characterized in that, When the voltage manifold includes a ground-state manifold, a distorted manifold, a recovering manifold, and a steady-state manifold, and the characteristic parameters include deviation depth, fault duration, recovery margin, and recovery trajectory volatility, determining the characteristic parameters of the target power grid based on the fault clearance time, the fault occurrence time, and the voltage manifold includes: Based on the ground state manifold and the distorted manifold, the deviation depth is obtained, wherein the deviation depth is used to quantify the degree to which the target power grid deviates from its normal operating state after a fault occurs; The duration of the fault is obtained based on the fault elimination time and the fault occurrence time. Based on the steady-state manifold and the preset voltage safety boundary, the recovery margin is obtained, wherein the recovery margin is used to quantify the voltage regulation margin of the target power grid after stable operation; Based on the distorted manifold and the steady-state manifold, the recovery trajectory volatility is obtained, wherein the recovery trajectory volatility is used to quantify the non-smoothness of the voltage recovery trajectory of the target power grid during the period from the time of the fault occurrence to the time of stable operation of the power grid.
5. The method according to claim 4, characterized in that, The process of obtaining the recovered trajectory volatility based on the distorted manifold and the steady-state manifold includes: Based on the distorted manifold and the steady-state manifold, the voltage recovery trajectory curve of the target power grid is obtained, wherein the horizontal axis of the voltage recovery trajectory curve is multiple target sampling times included in the target time period, the vertical axis of the voltage recovery trajectory curve is the low-dimensional vector corresponding to each of the multiple target sampling times, and the target time period is the time period between the time of the fault occurrence and the time of stable operation of the power grid; Based on the voltage recovery trajectory curve, the curvature corresponding to each of the multiple target sampling times is obtained; Among the curvatures corresponding to the multiple target sampling times, the curvatures greater than a preset curvature are determined to be the fluctuation of the recovered trajectory.
6. The method according to claim 1, characterized in that, When the characteristic parameters include deviation depth, fault duration, recovery margin, and recovery trajectory volatility, the process of obtaining the resilience index of the target power grid based on the characteristic parameters includes: Based on the deviation depth, the fault duration, the recovery margin, and the recovery trajectory volatility, the resilience index is obtained as follows: ； in, This represents the toughness index. This indicates the recovery margin. This indicates the deviation depth. This indicates the duration of the fault. This indicates the volatility of the recovery trajectory. This represents the preset normalization coefficient.
7. The method according to any one of claims 1 to 6, characterized in that, After obtaining the resilience index of the target power grid based on the characteristic parameters, the method further includes: If the resilience index is greater than the first preset resilience index, the target power grid is determined to be at the first resilience level, wherein the first resilience level is used to indicate that the target power grid does not need to implement a voltage control strategy to cope with at least one external disturbance after it has been operating stably. If the resilience index is less than or equal to the first preset resilience index and the resilience index is greater than or equal to the second preset resilience index, the target power grid is determined to be at a second resilience level, wherein the second resilience level is used to indicate that the voltage control strategy needs to be implemented after the stable operation to cope with an external disturbance. If the resilience index is less than the second preset resilience index and the resilience index is greater than or equal to the third preset resilience index, the target power grid is determined to be at the third resilience level. The third resilience level is used to indicate that there is a risk of voltage exceeding the limit after the stable operation, and reactive power compensation operation needs to be performed to suppress voltage fluctuations. If the resilience index is less than the third preset resilience index and the resilience index is greater than or equal to the fourth preset resilience index, the target power grid is determined to be at the fourth resilience level. The fourth resilience level is used to indicate that there is a risk of voltage exceeding the limit after the stable operation, and it is necessary to perform a power supply path switching operation to suppress the voltage fluctuation. If the resilience index is less than the fourth preset resilience index, the target power grid is determined to be at the fifth resilience level, wherein the fifth resilience level is used to indicate that maintenance operations are required on the target power grid after the stable operation is completed.
8. A power grid fault recovery capability assessment device, characterized in that, include: The voltage data acquisition module is used to acquire multiple sets of voltage data collected from multiple voltage monitoring points within the target power grid. These multiple sets of voltage data correspond one-to-one with multiple predetermined time periods, including a predetermined duration before the fault occurrence, a time period from the fault occurrence to the start of protection action, a time period from the start of protection action to the fault clearance, and a time period from the fault clearance to the stable operation of the power grid. Each set of voltage data includes the voltage of the three-phase point relative to the neutral point and the voltage at the neutral point connection point of each of the multiple voltage monitoring points within the predetermined time period. A voltage manifold determination module is used to determine the voltage manifold of the target power grid based on the multiple sets of voltage data, wherein the voltage manifold is used to indicate the voltage variation characteristics of the target power grid within the multiple predetermined time periods; The feature parameter determination module is used to determine the feature parameters of the target power grid based on the fault clearance time, the fault occurrence time, and the voltage manifold, wherein the feature parameters represent the geometric characteristics of the voltage manifold in the plurality of predetermined time periods; A resilience index determination module is used to obtain the resilience index of the target power grid based on the characteristic parameters, wherein the resilience index is used to indicate the fault recovery capability of the target power grid.
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 power grid fault recovery capability assessment method according to any one of claims 1 to 7.
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 power grid fault recovery capability assessment method of any one of claims 1 to 7.