Power grid operation risk assessment method and system considering time period coupling characteristics

Abstract

The application discloses a power grid operation risk assessment method and system considering period coupling characteristics, and relates to the technical field of power grid operation risk assessment, and comprises the following steps: obtaining operation data of a target power grid in a plurality of continuous periods, and constructing a time-space state tensor based on the operation data; introducing a period memory kernel function to obtain a cross-period evolution memory curve of a node state; based on the evolution memory curve and a power grid power flow equation, a risk diffusion path graph is constructed; based on the risk diffusion path graph, a critical energy accumulation function is established, and a node risk source marker is triggered when the accumulation exceeds a preset threshold; based on the risk source marker, a space-time risk evolution spectrum is generated, and the risk trajectory and threshold breakthrough point of each node in the continuous period are output. The application realizes early identification of high-risk nodes of tail events in continuous periods by constructing a cross-period evolution memory curve and a dynamic risk diffusion path graph, so as to solve the problem of lacking quantitative accumulation of cross-period risks.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid operation risk assessment, and more particularly to a power grid operation risk assessment method and system considering time period coupling characteristics. BACKGROUND

[0002] With the large-scale access of new energy and the intensification of load fluctuation, the power grid operation risk presents obvious time period coupling characteristics. In the case of continuous low output of new energy or continuous load peak, the risk of the power grid system not only appears in a single time period, but also is superimposed in multiple consecutive time periods, forming potential cumulative risk, which may eventually lead to "threshold breakthrough" of key nodes or lines, affecting the safe and stable operation of the system.

[0003] The existing power grid risk assessment method mainly relies on single time period analysis, and usually quantifies the risk for instantaneous extreme events or short-term disturbances, such as voltage drop analysis, frequency stability evaluation or short-term load overrun judgment. These methods often ignore the cumulative effect of risk in consecutive time periods, lack conditional risk measurement across time periods, and are difficult to accurately identify high-risk nodes that gradually accumulate in the scenario of continuous load or low output of new energy.

[0004] In addition, the existing method lacks consideration of the space-time propagation characteristics, and is usually based on single-node indicators or global system indicators, which cannot depict the dynamic transmission and superposition effect of risk among nodes and in consecutive time periods. Therefore, the existing technology has problems such as untimely risk identification, insufficient warning window, and inaccurate node priority ranking when facing the cumulative risk of events at the end of consecutive time periods, and is difficult to meet the demand of modern smart grid for cross-time period operation risk assessment.

[0005] The above disclosed technical solutions have at least the following technical problems: in the case of continuous low output of new energy or continuous load peak, the risk is superimposed in multiple time periods, which may eventually lead to "threshold breakthrough", and the existing method focuses on single time period extreme scenarios, but lacks cross-time period cumulative risk indicators.

[0006] In view of the above problems, the present application provides a solution. SUMMARY

[0007] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a power grid operation risk assessment method and system considering time period coupling characteristics, which realizes cumulative risk analysis and early identification of high-risk nodes for events at the end of consecutive time periods by constructing a cross-time period evolution memory curve and a dynamic risk diffusion path diagram, and establishing a critical energy accumulation function to generate a space-time risk evolution spectrum, thereby solving the problems in the prior art that only focus on single time period extreme events, lack of cross-time period cumulative risk quantification and space-time coupling analysis.

[0008] To achieve the above object, the present application provides the following technical solutions:

[0009] In one aspect, the power grid operation risk assessment method considering time period coupling characteristics comprises the following steps: obtaining operation data of a target power grid in a plurality of continuous time periods, and constructing a time-space state tensor based on the operation data; introducing a time period memory kernel function to obtain a cross-time period evolution memory curve of a node state; based on the evolution memory curve and a power grid power flow equation, constructing a risk diffusion path graph; based on the risk diffusion path graph, establishing a critical energy accumulation function, gradually superimposing tail events of the continuous time periods, and triggering a node risk source marker when the accumulation exceeds a preset threshold; based on the risk source marker, generating a space-time risk evolution spectrum, and outputting a risk trajectory and a threshold breakthrough point of each node in the continuous time periods.

[0010] In one preferred embodiment, the operation data of the target power grid in the plurality of continuous time periods is obtained, and a time-space state tensor is constructed based on the operation data, specifically: obtaining operation data of each node of the power grid in the continuous time periods; organizing the node operation parameters in the continuous time periods in time sequence and space topology information to form a basic time-space state tensor; introducing an uncertainty disturbance component of the operation data in the basic time-space state tensor, and generating a multi-instance tensor set through Monte Carlo sampling.

[0011] In one preferred embodiment, the time period memory kernel function is introduced to obtain the cross-time period evolution memory curve of the node state, specifically: inputting the multi-instance time-space state tensor of the continuous time periods into the memory kernel function; the memory kernel function includes an exponential decay type, a long tail type or an event weighting type, which is used to respectively depict short-term disturbance decay, tail event continuation and differentiated influence of different event categories; based on the weighted results of the memory kernel function, the cross-time period evolution memory value of the node in the current time period is calculated; the cross-time period evolution memory value is calculated one by one on the multi-instance tensor set to generate a multi-instance cross-time period evolution memory curve set of the node state.

[0012] In one preferred embodiment, the risk diffusion path graph is constructed based on the evolution memory curve and the power grid power flow equation, specifically: defining a propagation weight function based on the cross-time period evolution memory curve of the node and the power flow sensitivity matrix; using a gradient differentiable update method to dynamically correct the propagation weight function, wherein the correction process takes the system operation risk function as the target, iteratively updates the correction process combining the memory curve modulation factor and the power flow sensitivity partial derivative; introducing a state-related diffusion adjustment factor in the correction process, which automatically expands the propagation range when the power grid operation stress increases, and automatically shrinks the propagation range when the operation risk weakens; generating a dynamic risk diffusion path graph based on the corrected propagation weight function.

[0013] In a preferred embodiment, the dynamic risk diffusion path diagram is generated based on the modified propagation weight function, specifically: the modified propagation weight function is assembled into a space-time propagation weight matrix according to the power grid topology relationship; taking the node marked as a risk source as the starting point, the risk diffusion probability of the node on adjacent nodes is calculated based on the propagation weight matrix to generate an initial risk diffusion probability distribution; based on the initial risk diffusion probability distribution, an initial risk diffusion path set is screened; the propagation weight matrix is iterated on consecutive time periods, and the diffusion amplitude and direction of the risk at different time steps are calculated based on the initial risk diffusion path set as the starting point to obtain a risk propagation trajectory across time periods; in the iteration process, a risk threshold monitoring mechanism is introduced, and the risk propagation trajectories after iteration of each time period are merged in the path set to generate a unified space-time risk diffusion path diagram.

[0014] In a preferred embodiment, based on the risk diffusion path diagram, a critical energy accumulation function is established, and the tail events of consecutive time periods are gradually superimposed, specifically: the risk propagation intensity of each node in the risk diffusion path diagram is mapped into an equivalent energy component, which reflects the risk contribution of the node at the end of the time period; the equivalent energy components are gradually superimposed on consecutive time periods to construct a critical energy accumulation function, which is used to represent the cumulative effect of the risk across time periods; in the accumulation process, a dynamic threshold judgment mechanism is introduced, and the node risk source is marked when the critical energy accumulation value exceeds a preset threshold.

[0015] In a preferred embodiment, based on the risk source marking, a space-time risk evolution spectrum is generated, and the risk trajectory and threshold breakthrough point of each node within consecutive time periods are output, specifically: according to the existing node risk trajectory in the dynamic risk diffusion path diagram, a risk trajectory subset corresponding to the node that has been marked as a risk source is screened; the screened node risk trajectory is subjected to critical energy accumulation threshold monitoring, and the time point at which each node risk trajectory first exceeds the threshold is recorded and marked as a cross-time period threshold breakthrough point; the node risk trajectory and the corresponding cross-time period threshold breakthrough point are integrated to generate a space-time risk evolution spectrum; the evolution spectrum includes: a node risk intensity curve, a cross-time period threshold breakthrough point; based on the space-time risk evolution spectrum, a time window and a spatial range of risk warning are extracted.

[0016] In a preferred embodiment, the risk trajectory of each node in the continuous period and the threshold breakthrough point further comprise: based on the node risk intensity curve and the cross-period threshold breakthrough point in the space-time risk evolution spectrum, identifying nodes with high risk levels or threshold breakthroughs in the continuous period; according to the risk intensity, threshold breakthrough time and risk accumulation trend of the node, the identified high-risk nodes are prioritized to form a node risk level sequence; based on the node risk level sequence, combined with the node position in the power grid topology, operation and maintenance resource constraints and historical maintenance records, maintenance optimization suggestions for high-risk nodes are generated; the maintenance optimization suggestions are output, including maintenance priority, expected risk mitigation effect and recommended time window.

[0017] In another aspect, the power grid operation risk assessment system considering period coupling characteristics comprises the following modules: a state tensor construction module for obtaining operation data of a target power grid in a plurality of continuous periods and constructing a time-space state tensor based on the operation data; an evolution memory extraction module for introducing a period memory kernel function to obtain a cross-period evolution memory curve of a node state; a risk diffusion path generation module for constructing a risk diffusion path graph based on the evolution memory curve and a power grid flow equation; a risk source marking module for establishing a critical energy accumulation function based on the risk diffusion path graph, gradually superimposing events at the tail of the continuous period, and triggering node risk source marking when the accumulation exceeds a preset threshold; a space-time risk evolution spectrum generation module for generating a space-time risk evolution spectrum based on the risk source marking, and outputting the risk trajectory of each node in the continuous period and the threshold breakthrough point.

[0018] The technical effects and advantages of the power grid operation risk assessment method and system considering period coupling characteristics are as follows:

[0019] 1. The present application forms a dynamic risk diffusion path graph by constructing a cross-period evolution memory curve and combining a power grid flow sensitivity matrix, realizes time-space coupling analysis of power grid node risk, and can accumulate modeling of node state evolution in continuous periods, consider the flow constraint and topological relationship between nodes, realize dynamic transmission and adaptive adjustment of risk in space and time, and identify key nodes that may become risk sources, especially in the risk accumulation scenario of continuous load peak or continuous low output of new energy.

[0020] 2. The present application realizes the quantification of the cumulative effect of cross-period tail events and the marking of node risk by establishing a critical energy accumulation function and generating a space-time risk evolution spectrum. The method can monitor whether the risk accumulation in the continuous period exceeds the preset threshold, and mark high-risk nodes when the threshold is broken, while providing risk intensity curves and cross-period threshold breakthrough points, providing a basis for maintenance optimization and operation and maintenance strategy priority sorting of high-risk nodes, thereby supporting early warning and risk prevention and control measures. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 Flowchart of the power grid operation risk assessment method considering period coupling characteristics for the present application;

[0022] Figure 2 Structural diagram of the power grid operation risk assessment system considering period coupling characteristics for the present application;

[0023] Figure 3 Schematic diagram of the node risk cross-period evolution memory curve;

[0024] Figure 4 Risk intensity curve for each node;

[0025] Figure 5 Risk evolution thermodynamic diagram. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0027] Embodiment 1, Figure 1 The power grid operation risk assessment method considering period coupling characteristics for the present application is given, including the following steps:

[0028] S1, obtaining operation data of a target power grid in a plurality of continuous periods, and constructing a time-space state tensor based on the operation data;

[0029] The time-space state tensor is a multi-dimensional data structure for describing the operation state of each node of the target power grid in the continuous periods, which can represent the continuous evolution characteristics of the node state in the time dimension and the mutual correlation of the nodes in the power grid topology in the space dimension.

[0030] Specifically, the time-space state tensor includes the following features:

[0031] Time dimension: one dimension of the tensor corresponds to a plurality of continuous periods (such as minute level, hour level or scheduling period), which is used to record the voltage amplitude, power flow, energy storage state and new energy output of each node at different time points, and can reflect the evolution trend of the node state with time.

[0032] Space dimension: another dimension of the tensor corresponds to the nodes of the power grid and their topological relationship, which is used to reflect the power transmission, power flow constraints and risk propagation channels between nodes, and realize the spatial description of the overall structure of the power grid.

[0033] Multi-instance feature: When considering uncertainties (such as new energy fluctuations and load forecasting errors), a multi-instance tensor set can be formed by introducing a disturbance component into the tensor and performing multiple samplings. This set can be used to describe the possible evolution of node states under different disturbance scenarios.

[0034] In this embodiment, the step of acquiring the operating data of the target power grid over several consecutive time periods and constructing a time-space state tensor based on the operating data specifically involves:

[0035] The operation data of each node of the power grid is acquired over a continuous period of time. The operation data includes node voltage, branch power flow, new energy output and energy storage status.

[0036] The node operation parameters within a continuous time period are organized according to the time sequence and spatial topology information to form a basic time-space state tensor;

[0037] Uncertainty perturbation components of the running data are introduced into the basic time-space state tensor, and a multi-instance tensor set is generated through Monte Carlo sampling.

[0038] S2, introduce the time period memory kernel function to obtain the cross-time period evolution memory curve of the node state;

[0039] A time-period memory kernel function is a function structure used to characterize the decay-cumulative effect of the state of a power grid node across different time periods. It superimposes the state information of past time periods onto the current time period after decaying or amplifying it according to a certain rule.

[0040] In this embodiment, the introduction of a time-period memory kernel function to obtain the cross-time-period evolution memory curve of the node state is specifically as follows:

[0041] The multi-instance time-space state tensor of continuous time periods is input into the memory kernel function, which is used to attenuate or amplify the node state of historical time periods, and is used to simulate the temporal attenuation effect or cumulative amplification effect of risk energy respectively.

[0042] The memory kernel functions include exponential decay type, long tail type and event weighted type, which are used to characterize the decay of short-term disturbances, the continuation of tail events and the differentiated effects of different event categories, respectively.

[0043] Based on the weighted results of the memory kernel function, the cross-time evolution memory value of the node in the current time period is calculated;

[0044] The cross-time period evolution memory value is calculated one by one on the multi-instance tensor set to generate a set of multi-instance cross-time period evolution memory curves of node states.

[0045] Figure 3A node risk cross-period evolution memory curve is given to intuitively present the decay / cumulative effect of the node risk state in different periods. Through three typical "memory kernel function effect schematic curves", the influence of different types of memory mechanisms on risk energy and the evolution law of node state over time are shown.

[0046] Exponential decay type (blue curve): reflects the characteristic that risk memory decays exponentially. As the time step (horizontal axis) advances, the cross-period evolution memory value (vertical axis) rises rapidly and then falls gradually, and tends to be stable in the later period. It shows that the risk energy decays rapidly with time, only short-term memory effect is retained, and the long-term influence of past risk on the current node state is weak.

[0047] Long tail type (orange curve): the overall curve shows a continuous upward or high fluctuation trend, which shows that the risk energy gradually accumulates with time and decays slowly, the long-term influence of past risk on the current node state is significant, and the risk is easy to form a "long tail" type of continuous memory.

[0048] Event weighted type (green curve): it shows that the risk memory is weighted and accumulated by key events / periods. The curve grows slowly in the early stage and accelerates in the later stage, reflecting that due to the "weighting effect" of specific events or stages, the risk energy is continuously superimposed, and the memory effect is gradually strengthened with time. The cumulative effect is particularly prominent in the later period.

[0049] The cross-period evolution memory value is specifically:

[0050]

[0051] Wherein, is the cross-period evolution memory value of node i at time t, is the total number of continuous periods, is the memory kernel function, is the state vector of node i in the historical period .

[0052] S3, based on the evolution memory curve and the power grid flow equation, a risk diffusion path diagram is constructed;

[0053] In this embodiment, the risk diffusion path diagram is constructed based on the evolution memory curve and the power grid flow equation, which is specifically:

[0054] Based on the cross-period evolution memory curve of the node and the power flow sensitivity matrix, a propagation weight function is defined;

[0055] The propagation weight function is dynamically corrected by using a gradient differentiable update method, wherein the correction process is performed by taking the system operation risk function as the target, and combining the memory curve modulation factor and the power flow sensitivity partial derivative to perform iterative update;

[0056] Introducing a state-dependent diffusion adjustment factor in the correction process, automatically expanding the propagation range when the grid operating stress increases, and automatically shrinking the propagation range when the operating risk weakens;

[0057] Based on the corrected propagation weight function, a dynamic risk diffusion path graph is generated to depict the spatio-temporal transmission relationship of risk in the power grid topology.

[0058] The propagation weight function is dynamically corrected, specifically:

[0059]

[0060]

[0061]

[0062] Among them, is the corrected propagation weight, is the propagation weight of node i to node j at time t, is the gradient update step, is a preset spatio-temporal loss function based on risk energy distribution, is the corresponding element of the power flow sensitivity matrix, is a diffusion adjustment factor, is a time modulation function derived from a memory curve, is a preset weight adjustment factor, is a node time sequence dependence, , are the cross-period evolution memory curves of nodes i and j, respectively.

[0063] In this embodiment, the dynamic risk diffusion path graph is generated based on the corrected propagation weight function, specifically:

[0064] The corrected propagation weight function is assembled into a spatio-temporal propagation weight matrix according to the power grid topology relationship, where the matrix elements reflect the risk transmission intensity between nodes;

[0065] Taking the node marked as the risk source as the starting point, the risk diffusion probability of the adjacent nodes is calculated based on the propagation weight matrix, and the initial risk diffusion probability distribution is generated;

[0066] Based on the initial risk diffusion probability distribution, the initial risk diffusion path set is screened;

[0067] Iterate the propagation weight matrix on consecutive time periods, take the initial risk diffusion path set as the starting point, calculate the diffusion amplitude and direction of risk at different time steps, and obtain the cross-period risk propagation trajectory;

[0068] A risk threshold monitoring mechanism is introduced in the iteration process, the path branches are expanded when the propagation intensity exceeds the set threshold, and the invalid paths are pruned when the propagation intensity is below the contraction threshold, so as to ensure that the path graph can be self-adaptively contracted or diffused;

[0069] The risk propagation trajectories after iteration of each period are merged in the path set, and a unified space-time risk diffusion path graph is finally generated.

[0070] The risk transmission intensity, specifically:

[0071]

[0072] The risk diffusion probability, specifically:

[0073]

[0074] Wherein, is the risk transmission intensity, is the corrected propagation weight, is the state offset (voltage deviation, power imbalance or risk energy residual) of node i at time t, is the risk diffusion probability.

[0075] S4, based on the risk diffusion path graph, a critical energy accumulation function is established, the tail events of continuous periods are gradually superimposed, and the node risk source mark is triggered when the accumulation exceeds the preset threshold;

[0076] In the embodiment, based on the risk diffusion path graph, the critical energy accumulation function is established, and the tail events of continuous periods are gradually superimposed, specifically:

[0077] The risk propagation intensity of each node in the risk diffusion path graph is mapped to an equivalent energy component, and the equivalent energy component reflects the risk contribution of the node at the end of the period;

[0078] The equivalent energy components are gradually superimposed on the continuous periods to construct a critical energy accumulation function, which is used to represent the accumulation effect of risk across periods;

[0079] A dynamic threshold judgment mechanism is introduced in the accumulation process, and the node risk source mark is triggered when the critical energy accumulation value exceeds the preset threshold, so as to realize the early warning of cross-period risk.

[0080] The critical energy accumulation function, specifically:

[0081]

[0082]

[0083] Wherein, is the state offset (voltage deviation, power imbalance or risk energy residual) of node i at time t, The critical energy accumulation value, The preset memory modulation coefficient, To accumulate window length, Let be the equivalent energy component of node i in time period t. The mapping coefficient from risk intensity to energy. The duration of the period. Let represent the risk transmission intensity of node i during time period t.

[0084] S5 generates a spatiotemporal risk evolution spectrum based on risk source marking, and outputs the risk trajectory and threshold breakthrough time of each node in a continuous period.

[0085] In this embodiment, the step of generating a spatiotemporal risk evolution spectrum based on risk source markers and outputting the risk trajectory and threshold breakthrough point of each node within a continuous time period specifically involves:

[0086] Based on the existing node risk trajectories in the dynamic risk diffusion path diagram, a subset of risk trajectories corresponding to nodes that have been marked as risk sources is selected.

[0087] The critical energy accumulation threshold of the screened node risk trajectory is monitored, and the time point when the risk trajectory of each node first exceeds the threshold is recorded and marked as the cross-time threshold breakthrough point.

[0088] By integrating the node risk trajectory and the corresponding cross-time threshold breakthrough point, a spatiotemporal risk evolution spectrum is generated;

[0089] The evolutionary spectrum includes:

[0090] Node risk intensity curve: depicts the change in risk level of each node over a continuous period of time; such as Figure 4 The diagram shows the risk intensity curves for each node. The horizontal axis represents time period, and the vertical axis represents risk intensity. Different curves correspond to different nodes and their respective memory mechanisms. Dashed lines represent the risk thresholds set for each node, and red-marked points indicate the moments when the risk intensity exceeds the threshold. This diagram can intuitively reflect the risk evolution trend and exceedance events at different nodes, providing a basis for the generation of subsequent risk warning and control strategies.

[0091] Cross-time threshold breach point: The moment when the risk of a node first exceeds the critical threshold.

[0092] Based on the spatiotemporal risk evolution spectrum, the time window and spatial range of risk warning are extracted to provide a reference for risk prevention and control across time periods and multiple nodes.

[0093] The output of the risk trajectory and threshold breakthrough time points of each node within a continuous time period also includes:

[0094] A node risk intensity curve and a cross-period threshold breakthrough point in the spatiotemporal risk evolution spectrum are used to identify a node with a high risk level or a threshold breakthrough in a continuous period;

[0095] The identified high-risk node is prioritized according to the risk intensity of the node, the threshold breakthrough time, and the risk accumulation trend, and a node risk level sequence is formed;

[0096] Based on the node risk level sequence, the maintenance optimization suggestion for the high-risk node is generated in combination with the position of the node in the power grid topology, the operation and maintenance resource limit, and the historical maintenance record.

[0097] The maintenance optimization suggestion is output, including the maintenance priority order, the expected risk mitigation effect, and the recommended time window, for guiding the adjustment of the operation and maintenance strategy and the risk prevention and control.

[0098] Embodiment 2, Figure 2 The power grid operation risk assessment system considering the period coupling characteristic is given, which includes the following modules:

[0099] The state tensor construction module is used to obtain the operation data of the target power grid in a plurality of continuous periods, and construct a time-space state tensor based on the operation data.

[0100] The evolution memory extraction module is used to introduce a period memory kernel function to obtain a cross-period evolution memory curve of the node state.

[0101] The risk diffusion path generation module is used to construct a risk diffusion path graph based on the evolution memory curve and the power grid flow equation.

[0102] The risk source marking module is used to establish a critical energy accumulation function based on the risk diffusion path graph, to gradually superimpose the events at the tail of the continuous period, and to trigger the node risk source marking when the accumulation exceeds a preset threshold.

[0103] The spatiotemporal risk evolution spectrum generation module is used to generate a spatiotemporal risk evolution spectrum based on the risk source marking, and to output the risk trajectory and the threshold breakthrough point of each node in the continuous period.

[0104] The above formulas are all dimensionless numerical calculations, and the formulas are obtained by collecting a large amount of data to simulate the latest real situation, and the preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0105] The above embodiments can be realized by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized in the form of a computer program product.

[0106] Those skilled in the art can understand that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0107] In addition, each functional module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0108] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0109] Finally: the above is only the preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for power grid operation risk assessment considering period coupling characteristics, characterized in that, The method comprises the following steps: obtaining operation data of a target power grid in a plurality of continuous time periods, and constructing a time-space state tensor based on the operation data, specifically: obtaining operation data of each node of the power grid in the continuous time periods; organizing the node operation parameters in the continuous time periods in time sequence and space topology information to form a basic time-space state tensor; introducing an uncertainty disturbance component of the operation data into the basic time-space state tensor, and generating a multi-instance tensor set through Monte Carlo sampling; introducing a time period memory kernel function to obtain a cross-time period evolution memory curve of the node state, specifically: inputting the multi-instance time-space state tensor of the continuous time periods into the memory kernel function, calculating the cross-time period evolution memory value of the node in the current time period based on the weighted result of the memory kernel function; calculating the cross-time period evolution memory value on the multi-instance tensor set one by one to generate a multi-instance cross-time period evolution memory curve set of the node state; constructing a risk diffusion path diagram based on the evolution memory curve and the power grid power flow equation; based on the risk diffusion path diagram, establishing a critical energy accumulation function, gradually superimposing the tail events of the continuous time periods, and triggering the node risk source marking when the accumulation exceeds a preset threshold; generating a space-time risk evolution spectrum based on the risk source marking, and outputting the risk trajectory and threshold breakthrough point of each node in the continuous time periods.

2. The power grid operation risk assessment method considering period coupling characteristics according to claim 1, characterized in that, The memory kernel function includes an exponential decay type, a long tail type and an event weighting type, which are used to respectively depict short-term disturbance decay, tail event continuation and differentiated influence of different event categories.

3. The power grid operation risk assessment method considering period coupling characteristics according to claim 2, characterized in that, The risk diffusion path diagram is constructed based on the evolution memory curve and the power grid power flow equation, specifically: defining a propagation weight function based on the cross-time period evolution memory curve of the node and the power flow sensitivity matrix; dynamically correcting the propagation weight function in a gradient differentiable update mode, wherein the correction process is targeted at a system operation risk function, and iteratively updated by combining a memory curve modulation factor and a power flow sensitivity partial derivative; introducing a state-related diffusion adjustment factor in the correction process, which automatically expands the propagation range when the power grid operation stress increases, and automatically shrinks the propagation range when the operation risk weakens; generating a dynamic risk diffusion path diagram based on the corrected propagation weight function.

4. The power grid operation risk assessment method considering period coupling characteristics according to claim 3, characterized in that, The dynamic risk diffusion path diagram is generated based on the corrected propagation weight function, specifically: assembling the corrected propagation weight function into a space-time propagation weight matrix according to the power grid topology relationship; taking the node marked as the risk source as the starting point, calculating the risk diffusion probability of the adjacent nodes based on the propagation weight matrix to generate an initial risk diffusion probability distribution; based on the initial risk diffusion probability distribution, screening an initial risk diffusion path set; iterating the propagation weight matrix on the continuous time periods, taking the initial risk diffusion path set as the starting point, calculating the diffusion amplitude and direction of the risk at different time steps to obtain a cross-time period risk propagation trajectory; introducing a risk threshold monitoring mechanism in the iteration process, merging the risk propagation trajectories of each time period after iteration in the path set to generate a unified space-time risk diffusion path diagram.

5. The power grid operation risk assessment method considering period coupling characteristics according to claim 4, characterized in that, The critical energy accumulation function is established based on the risk diffusion path diagram, and the tail events of the continuous time periods are gradually superimposed, specifically: mapping the risk propagation intensity of each node in the risk diffusion path diagram into an equivalent energy component reflecting the risk contribution of the node at the end of the time period; gradually superimposing the equivalent energy components over consecutive time periods to construct a critical energy accumulation function for characterizing the cumulative effect of risk across time periods; introducing a dynamic threshold judgment mechanism during the accumulation process, triggering node risk source labeling when the critical energy accumulation value exceeds a preset threshold.

6. The power grid operation risk assessment method considering period coupling characteristics according to claim 5, characterized in that, The time-space risk evolution spectrum is generated based on the risk source labeling, and the risk trajectory and threshold breakthrough point of each node within the consecutive time period are output, specifically: According to the existing node risk trajectory in the dynamic risk diffusion path diagram, a risk trajectory subset corresponding to the node labeled as a risk source is selected; monitoring the critical energy accumulation threshold of the screened node risk trajectory, recording the time point when each node risk trajectory first exceeds the threshold, and marking it as a cross-time period threshold breakthrough point; integrating the node risk trajectory and the corresponding cross-time period threshold breakthrough point to generate a time-space risk evolution spectrum; The evolution spectrum includes: node risk intensity curve, cross-time period threshold breakthrough point; Based on the time-space risk evolution spectrum, the time window and spatial range of risk warning are extracted.

7. The power grid operation risk assessment method considering period coupling characteristics according to claim 6, characterized in that, The output of the risk trajectory and the threshold breakthrough point of each node within the consecutive time period also includes: Based on the node risk intensity curve and the cross-time period threshold breakthrough point in the time-space risk evolution spectrum, identify the nodes with high risk level or threshold breakthrough within the consecutive time period; According to the risk intensity, threshold breakthrough time and risk accumulation trend of the node, the identified high-risk nodes are prioritized to form a node risk level sequence; Based on the node risk level sequence, combined with the node position in the power grid topology, operation and maintenance resource constraints and historical maintenance records, generate maintenance optimization suggestions for high-risk nodes; Output the maintenance optimization suggestions, including maintenance priority, expected risk mitigation effect and recommended time window.

8. A system for using the power grid operation risk assessment method taking into account period coupling characteristics according to any one of claims 1-7, characterized in that, The following modules are included: State tensor construction module: used to obtain the operation data of the target power grid in several consecutive time periods, and construct a time-space state tensor based on the operation data; Evolution memory extraction module: used to introduce a time period memory kernel function to obtain the cross-time period evolution memory curve of the node state; Risk diffusion path generation module: used to construct a risk diffusion path diagram based on the evolution memory curve and the power grid flow equation; Risk source labeling module: used to establish a critical energy accumulation function based on the risk diffusion path diagram, gradually superimpose the events at the end of the consecutive time period, and trigger node risk source labeling when the accumulation exceeds the preset threshold; Time-space risk evolution spectrum generation module: used to generate a time-space risk evolution spectrum based on the risk source labeling, and output the risk trajectory and threshold breakthrough point of each node within the consecutive time period.

Images