A method, apparatus, equipment and storage medium for quantifying relay protection risks

Abstract

This invention relates to the field of power grid assessment technology and discloses a method, device, equipment, and storage medium for quantifying relay protection risks. The method first integrates the status data of the relay protection system with the power grid status data to construct a digital twin, mapping the relay protection system's settings, soft circuit boards, and self-test information with the power grid topology and measurement data. Then, based on new energy sources and load forecasts, a set of power grid operation scenarios is generated, enabling risk assessment to cover future changes in operating modes. Next, simulations are performed using the digital twin for each power grid operation scenario to pre-simulate protection actions and power grid consequences, proactively quantifying potential risks. Finally, a risk entropy quantification method is used to comprehensively assess the mismatch probability and the severity of consequences, generating a heat map. The final risk identification results are presented in a visual form, improving the decision-making efficiency for risk assessment after the current power grid integrates a high proportion of new energy sources.

Description

Technical Field

[0001] This invention relates to the field of power grid assessment technology, specifically to a method, apparatus, equipment, and storage medium for quantifying relay protection risks. Background Technology

[0002] The relay protection system is the first line of defense in a power system. When primary equipment on the grid side (such as lines, transformers, busbars, generators, etc.) fails or exhibits abnormal operating conditions, it selectively issues tripping commands or alarm signals to isolate the faulty equipment and ensure the continued safe operation of the fault-free parts. The performance of the relay protection system directly affects the safe and stable operation of the power system. With the high proportion of new energy integration and increasingly flexible and diverse grid operation modes, higher requirements are placed on the dynamic risk assessment of relay protection systems.

[0003] The risk assessment methods for relay protection systems disclosed in related technologies include physical model-driven setting verification methods. These methods check the correctness of protection configuration through fault simulation and setting comparison, and then perform online sequential verification of settings by ranking protection importance. An assessment model is constructed by comprehensively considering the criticality of the relay protection system's network location and the severity of protection fault consequences. The reliability of the relay protection system is then evaluated using the constructed assessment model.

[0004] However, the risk assessment methods for relay protection systems disclosed in related technologies are still limited to the stage of lagging analysis and partial quantification based on historical data, which is difficult to meet the current risk quantification assessment needs of the power grid after a high proportion of new energy sources are connected. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for quantifying relay protection risks, in order to address the problem that the risk assessment methods for relay protection systems disclosed in related technologies are insufficient to meet the current risk quantification assessment needs of the power grid after the integration of a high proportion of new energy sources.

[0006] In a first aspect, the present invention provides a method for quantifying relay protection risks, the method comprising: Based on the status data of the target relay protection system and the power grid status data, and combined with the pre-constructed software logic image of the target relay protection system, a fused digital twin is obtained using a data mapping method; the status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information; the power grid status data includes the power grid topology, parameters, and real-time measurement data. Based on access-based new energy power prediction, load prediction, and network topology prediction, various power grid operation scenarios are obtained using scenario construction methods, and a power grid operation scenario set is constructed. For each power grid operation scenario in the power grid operation scenario set, and in conjunction with the current power grid status data, simulations are performed using data twins to obtain predictions of protection action behaviors and consequences under the corresponding power grid operation scenario. For each protection configuration of the target relay protection system, the protection action behavior prediction and consequence prediction under multiple power grid operation scenarios are combined, and the risk entropy quantitative assessment method is used to evaluate them respectively, so as to obtain multiple risk identification results and generate a risk heat map.

[0007] Through the above implementation method, firstly, a digital twin is constructed by integrating the status data of the relay protection system and the status data of the power grid. The settings, soft circuit boards, and self-test information of the relay protection system are uniformly mapped with the power grid topology and measurement data to achieve deep coupling between the protection logic and the power grid model. Then, a set of power grid operation scenarios is generated based on new energy sources and load forecasts, so that the risk assessment can cover future changes in operation mode. Next, simulations are performed on each power grid operation scenario using the digital twin to pre-simulate protection actions and power grid consequences, thereby achieving forward-looking quantification of potential risks. Finally, the risk entropy quantification method is used to comprehensively assess the mismatch probability and the severity of the consequences, and a heat map is generated to present the final risk identification results in a visual form, improving the decision-making efficiency for risk assessment after the current power grid is connected to a high proportion of new energy sources.

[0008] In one optional implementation, the step of performing simulations using a data twin for each power grid operation scenario in the power grid operation scenario set, combined with current power grid status data, to obtain predictions of protection action behaviors and consequences under the corresponding power grid operation scenario, includes: Based on each power grid operation scenario in the power grid operation scenario set, multiple anticipated faults are generated using the anticipated fault construction method; the anticipated faults include: single faults, complex faults, or protection-related faults. Based on each anticipated fault, combined with the current power grid status data, the digital twin is used to perform fault simulation to obtain the protection action parameters and power grid response parameters under the corresponding fault. By combining the protection action parameters corresponding to multiple faults, and using the action correctness judgment method, the behavior prediction result of each protection action is obtained; By combining the power grid response parameters corresponding to multiple faults and using the power grid consequence quantification method, the line load rate, node voltage and stability margin after fault clearance are calculated to obtain the power grid consequence prediction results.

[0009] Through the above implementation method, firstly, a set of anticipated faults covering single, complex, and protection-related faults is generated for each operating scenario to ensure that subsequent risk assessments cover multiple fault modes and avoid overlooking key hidden dangers. Then, a digital twin is used to simulate each anticipated fault to obtain protection action parameters and grid response parameters respectively. Next, the protection action parameters under multiple faults are combined, and the behavior prediction results are obtained through action correctness judgment to quantify the statistical characteristics of protection failure to operate or maloperation. Finally, the grid response parameters under multiple faults are combined to calculate the load rate, voltage, and stability margin after fault clearance, quantifying the consequences of protection actions into comparable grid physical indicators, providing reliable data support for subsequent risk entropy quantification.

[0010] In one optional implementation, the step of performing fault simulation using the digital twin based on each anticipated fault and combined with current power grid state data to obtain protection action parameters and power grid response parameters under the corresponding fault includes: Based on each anticipated fault, and combined with the current power grid status data, the fault injection method is used to simulate the electrical quantity mutation at the moment of fault occurrence in the digital twin, thereby obtaining the transient electrical quantity sequence after the fault. Based on the transient electrical quantity sequence after the fault, the digital twin is driven to perform fault detection, logic judgment and output action, and the start time, action time and final action status of the corresponding target relay protection system are recorded to obtain protection action parameters. Based on the protection action parameters, the power redistribution process after fault clearance is simulated using the digital twin, and the line load rate, node voltage amplitude and power angle stability margin are calculated to obtain the power grid response parameters.

[0011] Through the above implementation method, firstly, a fault injection method is used to simulate sudden changes in electrical quantities to obtain a transient electrical quantity sequence, which can accurately reflect the transient characteristics when a fault occurs. Secondly, based on the transient electrical quantity sequence, a digital twin is driven to perform fault detection, logic judgment, and output actions, recording the start time, action time, and final action state of the relay protection system to obtain protection action parameters, which facilitates the quantification of the response behavior and action correctness of the relay protection system. Finally, based on the protection action parameters, the power redistribution process after fault clearance is simulated to calculate the line load rate, node voltage amplitude, and power angle stability margin, obtaining grid response parameters, which facilitates the provision of quantitative basis for evaluating the operating status of the grid after a fault.

[0012] In one optional implementation, the process of obtaining a fused digital twin based on the state data of the target relay protection system and the power grid state data, combined with a pre-built software logic image of the target relay protection system, using a data mapping method, includes: Based on the grid-side topology and parameters in the grid state data, a primary system model of the power grid is obtained using the primary system modeling method. Based on the status data of the target relay protection system, a precise protection logic mirror that is consistent with the logic of the target relay protection system is obtained by using the protection logic mirroring construction method. Based on the primary system model of the power grid and the precise protection logic mirror, and combining the status data of the target relay protection system with the status data of the power grid, a weighted fusion is performed using a dynamic fusion method to obtain the fused digital twin.

[0013] Through the above implementation methods, a primary system model is constructed based on the grid-side topology and parameters to provide a physical benchmark for the digital twin; then, based on the protection status data, a precise protection logic mirror is constructed to ensure that the protection behavior of the precise protection logic mirror is consistent with the field device; finally, based on the primary system model and the protection logic mirror, dynamic weighted fusion is performed by combining the status data and grid data to achieve synchronization of virtual and real states, resulting in a high-fidelity digital twin.

[0014] In one optional implementation, the access-based new energy power prediction, load prediction, and network topology prediction utilize a scenario construction method to obtain multiple power grid operation scenarios and construct a power grid operation scenario set, including: Based on the access-based new energy power prediction, load prediction, and network topology prediction, the prediction data within the preset time window is obtained. Based on the predicted data within the preset time window, combined with the current real-time status data of the power grid, a combined sampling method is used to construct each power grid operation mode into a power grid operation scenario, resulting in multiple power grid operation scenarios; each power grid operation scenario includes power generation output, load level, and network topology configuration. By combining multiple power grid operation scenarios, a set of power grid operation scenarios is obtained using a set construction method.

[0015] Through the above implementation methods, based on new energy power prediction, load prediction, and network topology prediction, prediction data within a preset time window is obtained, providing time boundaries and data sources for scenario generation. Then, based on the prediction data and the current real-time state of the power grid, a combined sampling method is used to construct each power grid operation mode into a power grid operation scenario, resulting in multiple power grid operation scenarios, thereby covering possible future changes in operation modes. Finally, by integrating multiple power grid operation scenarios and using a set construction method, a set of power grid operation scenarios is obtained, providing diverse input conditions for subsequent parallel simulation.

[0016] In one optional implementation, for each protection configuration of the target relay protection system, the protection action behavior prediction and consequence prediction under multiple power grid operation scenarios are comprehensively integrated, and the risk entropy quantification assessment method is used to evaluate them respectively, obtaining multiple risk identification results, and generating a risk heat map, including: Based on the prediction results of protection action behavior under multiple power grid operation scenarios, for each protection configuration and each power grid operation scenario, the mismatch probability of each protection configuration under each power grid operation scenario is obtained by using the mismatch probability statistical method. Based on the mismatch probability of each protection configuration in each power grid operation scenario, the power grid consequences caused by protection mismatch are quantified into corresponding severity levels using a severity mapping rule base to obtain a consequence severity assessment value. Based on the mismatch probability and severity assessment value of each protection configuration in each power grid operation scenario, the comprehensive risk entropy of each protection configuration in each power grid operation scenario is determined using the risk entropy synthesis method, and the scenario-level risk quantification result of the corresponding protection configuration in each power grid operation scenario is constructed. Based on the scenario-level risk quantification results of each protection configuration under each power grid operation scenario, the overall risk level of each protection configuration is determined by using the risk aggregation method, and a risk heatmap of the corresponding protection configuration is generated.

[0017] Through the above implementation methods, based on the prediction results of protection action behavior under multiple power grid operation scenarios, the mismatch probability is statistically calculated for each protection configuration and each power grid operation scenario, quantifying the possibility of protection failure under a specific operating mode. Based on the mismatch probability, the power grid consequences are quantified into severity levels using a severity mapping rule base, converting physical consequences into comparable severity scores. Based on the mismatch probability and severity assessment value, the comprehensive risk entropy of each configuration under each scenario is obtained using a risk entropy synthesis method, realizing the fusion quantification of protection failure probability and system consequences. Based on the risk entropy under all power grid operation scenarios, the overall risk level of each protection configuration is determined using a risk aggregation method, and a risk heatmap is generated, converging into an intuitive visualization result to facilitate subsequent location of high-risk areas.

[0018] In one alternative implementation, it further includes: When a high risk is identified in the risk identification results, a candidate protection reconstruction strategy is generated using a digital twin, and the candidate strategy is verified in all scenarios to obtain the verified reconstruction strategy. Based on the verified reconstruction strategy, a two-factor verification method is used to output control commands for the target relay protection system to execute.

[0019] Through the above implementation method, when there is a high risk in the risk identification results, a candidate reconstruction strategy is generated using a digital twin and verified in all scenarios to ensure that the reconstruction strategy is effective and does not introduce new risks. Then, based on the verified reconstruction strategy, a two-factor confirmation method is used to output control commands to ensure the online safe adaptive adjustment of the control strategy of the target relay protection system.

[0020] Secondly, the present invention provides a relay protection risk quantification device, the device comprising: The twin construction module is used to obtain a fused digital twin based on the status data of the target relay protection system and the power grid status data, combined with the pre-built software logic image of the target relay protection system, using a data mapping method. The status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information. The power grid status data includes the power grid topology, parameters, and real-time measurement data. The scenario generation module is used for new energy power prediction, load prediction and network topology prediction based on access. It uses scenario construction methods to obtain a variety of power grid operation scenarios and constructs them into a power grid operation scenario set. The simulation module is used to perform simulations for each power grid operation scenario in the power grid operation scenario set, combined with the current power grid status data, using a data twin to obtain the protection action behavior prediction and consequence prediction under the corresponding power grid operation scenario. The risk assessment module is used to comprehensively predict the protection action behavior and consequences under multiple power grid operation scenarios for each protection configuration of the target relay protection system. It uses the risk entropy quantification assessment method to conduct assessments respectively, obtain multiple risk identification results, and generate a risk heat map.

[0021] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the relay protection risk quantification method of the first aspect or any corresponding embodiment described above.

[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the relay protection risk quantification method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the first process of the relay protection risk quantification method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the second process of the relay protection risk quantification method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the third process of the relay protection risk quantification method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the fourth process of the relay protection risk quantification method according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the fifth process of the relay protection risk quantification method according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the sixth process of the relay protection risk quantification method according to an embodiment of the present invention. Figure 7 This is a structural block diagram of a relay protection risk quantification device according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] The risk assessment methods for relay protection systems disclosed in related technologies include: a physical model-driven setting verification method, which checks the correctness of the protection configuration of the relay protection system through fault simulation and setting comparison, and then performs online sequential verification of the setting by ranking the importance of protection. An assessment model is constructed by comprehensively considering the criticality of the network location of the relay protection system and the severity of the consequences of protection faults, and the reliability of the relay protection system is evaluated using the constructed assessment model.

[0029] However, the physical model-driven setting verification methods disclosed in related technologies rely on periodic offline verification based on typical operating modes. After a high proportion of new energy power generation is connected to the grid, the grid operating mode will change rapidly, such as network topology adjustment or fluctuations in new energy output. It is difficult to identify the risk of "hidden mismatch" of protection settings caused by changes in operating mode on a minute-level time scale.

[0030] To overcome the deficiencies disclosed in the aforementioned related technologies, this application provides a method for quantifying relay protection risks. First, it integrates the state data of the target relay protection system with the power grid state data to construct a digital twin. The settings, soft circuit boards, and self-test information of the relay protection system are uniformly mapped with the power grid topology and measurement data, achieving deep coupling between protection logic and the power grid model. Next, it generates a set of power grid operation scenarios based on new energy sources and load forecasts, enabling risk assessment to cover the future range of changes in power grid operation modes. Third, it uses the digital twin to simulate each power grid operation scenario, pre-simulating protection actions and power grid consequences, achieving forward-looking quantification of potential risks. Finally, it uses a risk entropy quantification method to comprehensively assess the mismatch probability and the severity of consequences, generating a heat map. The final risk identification results are presented in a visual form, improving the decision-making efficiency for risk assessment after the current power grid integrates a high proportion of new energy sources.

[0031] According to an embodiment of the present invention, a method for quantifying relay protection risks 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.

[0032] This embodiment provides a method for quantifying relay protection risks, which can be used in the aforementioned substation monitoring server. Figure 1 This is a flowchart of a relay protection risk quantification method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: S101, based on the status data of the target relay protection system and the power grid status data, combined with the pre-built software logic image of the target relay protection system, a fused digital twin is obtained using a data mapping method; the status data of the target relay protection system includes the current setting group, soft pressure plate status and internal self-test information; the power grid status data includes the power grid topology, parameters and real-time measurement data.

[0033] The target relay protection system is a collection of relay protection devices that currently require risk quantification assessment, such as line protection, transformer protection, bus protection, etc. The status data of each relay protection system includes configurable parameters such as settings, logic, and soft pressure plates.

[0034] The current setting group is the setpoint area currently active in the relay protection system and a list of all settings within that area, such as current, voltage, and time settings, which are used to determine the threshold values ​​for the protection actions of the relay protection system.

[0035] The soft switch status is a function switch controlled by software in the relay protection system, such as "differential protection enabled" or "distance protection enabled". The status is implemented as "enabled" or "disabled" to reflect whether the protection logic of the relay protection system is executed.

[0036] Internal self-test information is diagnostic data on the health status of the relay protection system itself, including device self-test alarms, key status words, hardware abnormality flags, etc., which are used to reflect whether there are internal faults in the relay protection system.

[0037] Power grid status data is a set of data describing the current operating status of the primary system of the power grid. The power grid topology refers to the connection relationship between nodes and branches of the power network. Parameters include line impedance, transformer turns ratio, generator inertia, etc. Real-time measurement data includes steady-state measurement data from Supervisory Control and Data Acquisition (SCADA) and synchronous phasor data from Phantom Measurement Unit (PMU). SCADA steady-state measurement data includes active power, reactive power, and voltage, while PMU synchronous phasor data includes voltage, current, and phase angle.

[0038] The software logic mirror is an exact software copy built based on the relay protection system. It contains protection principle algorithms, setting calculation logic, criterion equations and time-limit characteristics that are completely consistent with the field devices of the relay protection system. It is used to simulate the entire process of the relay protection system from fault detection to output action.

[0039] The data mapping method associates real-time collected power grid measurement data and protection status data with model nodes in the digital twin. By establishing a data mapping, the state variables of the constructed digital twin are synchronized with the actual physical system of the relay protection system.

[0040] A digital twin is a virtual-physical fusion body composed of a primary system model of the power grid and a software logical mirror of the relay protection system. It is used to accurately simulate the complete process of "power grid fault, protection response and power grid consequences" and evolves dynamically as real-time data is updated.

[0041] S102, based on the access-based new energy power prediction, load prediction and network topology prediction, uses scenario construction methods to obtain a variety of power grid operation scenarios and constructs them into a power grid operation scenario set.

[0042] New energy power forecasting is the prediction of the power output of new energy sources such as wind power and photovoltaic power in the short term. It is expressed in the form of time series or probability distribution to reflect the volatility of new energy power output and its impact on the operation mode of the power grid.

[0043] Load forecasting is the prediction data of active and reactive loads at each node of the power grid in the short term. It is obtained by ultra-short-term forecasting based on historical load curves, meteorological factors, etc., and is used to simulate the changes in power grid operation mode caused by load fluctuations.

[0044] Network topology prediction is information on expected changes in the topology of the power grid in the short term, including the status of power grid switches, the commissioning and decommissioning of lines, and the main wiring methods. It includes planned maintenance arrangements and switching operations, and is used to generate network connection relationships corresponding to future time windows.

[0045] The scenario construction method is based on new energy power prediction, load prediction, and network topology prediction, and uses methods such as combined sampling, Monte Carlo sampling, or typical scenario clustering to generate a set of scenarios to characterize the power grid operation mode, including power generation output, load level, and topology configuration combination.

[0046] A power grid operation scenario is a complete description of the future power grid operation state, including the power generation output, load levels of each node, and power grid topology in each scenario, which serve as input conditions for subsequent parallel fault simulation.

[0047] The power grid operation scenario set is a collection of multiple power grid operation scenarios used to cover the range of possible changes in operation modes in the near future.

[0048] S103, for each power grid operation scenario in the power grid operation scenario set, combined with the current power grid status data, simulation is performed using a data twin to obtain the prediction of protection action behavior and consequences under the corresponding power grid operation scenario.

[0049] Current power grid status data refers to the real-time operating data of the primary system of the power grid at the current moment, including SCADA steady-state measurement data and PMU synchronization phasor data, as well as information such as power grid topology and parameters, which are used as the initial conditions for subsequent simulation.

[0050] Simulation is a process that uses a digital twin to inject a pre-existing fault into a given power grid operation scenario and current power grid status data. This drives the protection logic mirror to perform joint calculations with the primary power grid model to reproduce the fault transient process and protection action sequence.

[0051] The protection action behavior prediction is obtained through simulation. It measures whether each part of the relay protection system operates, the operation time, and whether the sensitivity requirements are met under each anticipated fault. This result is used to determine the mismatch probability of the relay protection system in a specific scenario.

[0052] Consequence prediction is obtained through simulation, which measures the physical response of the power grid after protection action or failure to operate, including line load rate, node voltage amplitude and power angle stability margin, and is used to quantify the severity of protection mismatch caused by relay protection system.

[0053] S104, for each protection configuration of the target relay protection system, comprehensively predicts the protection action behavior and consequences under multiple power grid operation scenarios, and uses the risk entropy quantitative assessment method to evaluate them respectively, obtain multiple risk identification results, and generate a risk heat map.

[0054] Protection configuration refers to the specific parameter settings for a certain protection device in a relay protection system, including its activated setting area, setting list, soft pressure plate status, and logical coordination relationship. Different protection configurations correspond to different protection behaviors.

[0055] The risk entropy quantification assessment method is a composite risk index calculation method that integrates the probability of protection mismatch with the severity of system-level consequences. It calculates the comprehensive risk entropy through a comprehensive evaluation formula, thereby realizing the dynamic risk quantification of each protection configuration in the relay protection system.

[0056] Risk identification results are the judgment conclusions obtained by aggregating the risk entropy of each protection configuration of the relay protection system under multiple scenarios, such as "high risk", "medium risk" and "low risk", and locating specific high-risk protection devices and risk causes.

[0057] A risk heatmap maps the risk level of each protection configuration onto a power grid geographic wiring diagram or topology diagram using color depth or grid format. This visually displays the hot spots in the distribution of protection risks across the entire network, helping maintenance personnel to quickly locate high-risk locations.

[0058] This embodiment provides a relay protection risk quantification method. First, it integrates the status data of the target relay protection system with the grid status data to construct a digital twin. The settings, soft circuit boards, and self-test information of the relay protection system are uniformly mapped with the grid topology and measurement data, achieving deep coupling between the protection logic and the grid model. Next, it generates a set of grid operation scenarios based on new energy sources and load forecasts, enabling risk assessment to cover the future range of grid operation changes. Then, it uses the digital twin to simulate each grid operation scenario, pre-simulating protection actions and grid consequences, achieving forward-looking quantification of potential risks. Finally, it uses a risk entropy quantification method to comprehensively assess the mismatch probability and the severity of consequences, generating a heat map. The final risk identification results are presented in a visual form, improving the decision-making efficiency for risk assessment after the grid has integrated a high proportion of new energy sources.

[0059] This embodiment provides a method for quantifying relay protection risks, which can be used in the aforementioned substation monitoring server. Figure 2 This is a flowchart of a relay protection risk quantification method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: S201, based on the status data of the target relay protection system and the power grid status data, combined with the pre-built software logic image of the target relay protection system, a fused digital twin is obtained using a data mapping method; the status data of the target relay protection system includes the current setting group, soft pressure plate status and internal self-test information; the power grid status data includes the power grid topology, parameters and real-time measurement data.

[0060] Specifically, S201 above includes: S2011, based on the grid-side topology and parameters in the grid state data, uses the primary system modeling method to obtain the grid primary system model.

[0061] The primary system modeling method is based on the topology data and parameters of the power grid, and uses node admittance matrix or power flow equation description method to construct a detailed mathematical model including lines, transformers, generators and loads.

[0062] A primary system model of a power grid is a digital model that describes the physical characteristics of primary equipment in a power grid. It is used to simulate the steady-state power flow, transient faults, and power redistribution process after protection actions.

[0063] S2012, based on the status data of the target relay protection system, a precise protection logic mirror that is consistent with the logic of the target relay protection system is obtained by using the protection logic mirror construction method.

[0064] The protection logic mirroring construction method reproduces the internal algorithms of the relay protection system in the form of software code or models, including the criterion equations and time-limited logic of staged current protection, distance protection, and longitudinal differential protection.

[0065] Precise protection logic mirror is a copy of the protection algorithm that is consistent with the logic of the field device, used to simulate the entire process from fault detection, electrical quantity transformation, logic judgment to output action.

[0066] The status data of the relay protection system and the status data of the power grid are obtained in real time and synchronously through a high-speed communication network.

[0067] Synchronize the status data of the relay protection system with the status data of the power grid in terms of time, for example, using the following expression:

[0068] in, express Time of the first Phase angle of a point; express Time of the first Voltage at a point; express Time of the first Current at a point; Indicates the angular velocity at power frequency; Indicates the current moment.

[0069] For example, S2012 above includes: Based on power grid CIM or topology data, a refined primary system model is constructed for the centralized control side, including detailed parameters of lines, transformers, generators, and loads.

[0070] At the same time, a corresponding software logic image is established for each relay protection device in the relay protection system, embedding protection principle algorithms, setting calculation logic, criterion equations and time-limit characteristics consistent with the field devices of the relay protection system, such as complete digital twin subsystems including staged current protection, distance protection, and longitudinal differential protection.

[0071] S2013, based on the primary system model of the power grid and the precise protection logic mirror, combines the status data of the target relay protection system with the status data of the power grid, and uses a dynamic fusion method to perform weighted fusion to obtain the fused digital twin.

[0072] The dynamic fusion method is a calculation method that synchronizes the state of real-time measurement data and simulation data according to dynamic weights.

[0073] Weighted fusion dynamically allocates weights based on data quality or system status during the fusion process, enabling the twins to maintain high-fidelity synchronization under both normal operation and fault transient conditions.

[0074] For example, S2013 above includes: The real-time acquired status data of the target relay protection system is fused with the power grid status data and the predicted data output from the primary system model simulation to drive the update of the constructed digital twin, satisfying the following expression:

[0075] in, In digital twins Time of the first The state of a point; Represents dynamic weights based on data quality and system state; This indicates that data is collected in real time. This represents the predicted data output from a single system model simulation.

[0076] For example, iterative power flow correction using node voltage updates can make the state of the digital twin consistent with the actual physical system.

[0077]

[0078] in, Represents a node The voltage phasor obtained after the current iteration; Represents a node Injected active power; Represents a node Injected reactive power; Represents the imaginary unit; Represents the nodes in the nodal admittance matrix and nodes Mutual admittance; Indicates adjacent nodes The current iteration voltage phasor; Represents a node The voltage phasor at the previous moment; ε represents the convergence accuracy threshold.

[0079] By constructing a primary system model based on the grid-side topology and parameters, a physical benchmark is provided for the digital twin. Then, based on the protection status data, an accurate protection logic mirror is constructed to ensure that the protection behavior of the accurate protection logic mirror is consistent with the field device. Finally, based on the primary system model and the protection logic mirror, dynamic weighted fusion is performed by combining the status data and grid data to achieve synchronization of virtual and real states, resulting in a high-fidelity digital twin.

[0080] S202, based on access-based renewable energy power forecasting, load forecasting, and network topology forecasting, utilizes scenario construction methods to obtain various power grid operation scenarios and constructs them into a power grid operation scenario set. For details, please refer to [link to relevant documentation]. Figure 1 S102 of the illustrated embodiment will not be described again here.

[0081] S203, for each power grid operation scenario in the set of power grid operation scenarios, combines current power grid status data and uses data twins to perform simulations to obtain predictions of protection action behavior and consequences under the corresponding power grid operation scenario. For details, please refer to... Figure 1 S103 of the illustrated embodiment will not be described again here.

[0082] S204, for each protection configuration of the target relay protection system, comprehensively predicts protection action behavior and consequences under multiple power grid operation scenarios, and uses a risk entropy quantification assessment method to evaluate them separately, obtaining multiple risk identification results and generating a risk heatmap. For details, please refer to [link to relevant documentation]. Figure 1 S104 of the illustrated embodiment will not be described again here.

[0083] This embodiment provides a method for quantifying relay protection risks, which can be used in the aforementioned substation monitoring server. Figure 3 This is a flowchart of a relay protection risk quantification method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: S301, based on the status data of the target relay protection system and the power grid status data, combined with the pre-built software logic image of the target relay protection system, uses a data mapping method to obtain a fused digital twin. The status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information; the power grid status data includes the power grid topology, parameters, and real-time measurement data. For details, please refer to [link to relevant documentation]. Figure 1 S101 of the illustrated embodiment will not be described again here.

[0084] S302, based on access-based new energy power prediction, load prediction and network topology prediction, uses scenario construction methods to obtain a variety of power grid operation scenarios and constructs them into a power grid operation scenario set.

[0085] Specifically, S302 above includes: S3021, based on the accessed new energy power prediction, load prediction and network topology prediction, obtain the prediction data within the preset time window; S3022, based on the predicted data within a preset time window and combined with the current real-time status data of the power grid, uses a combined sampling method to construct each power grid operation mode into a power grid operation scenario, resulting in multiple power grid operation scenarios; each power grid operation scenario includes power generation output, load level and network topology configuration. S3023 integrates multiple power grid operation scenarios and uses a set construction method to obtain a power grid operation scenario set.

[0086] For example, S302 above can be implemented as follows: Based on the access to future short-term renewable energy forecasts, load forecasts, and network topology plans, combined with the current real-time status, multiple scenarios are generated to characterize future power grid operation modes, and these scenarios are constructed into a scenario set, satisfying the following expression:

[0087] in, This represents the set of scenarios that have been constructed. This indicates a power grid operation mode; This indicates another mode of power grid operation; Indicates the first Each power grid operation mode.

[0088] By acquiring forecast data within a preset time window based on new energy power prediction, load prediction, and network topology prediction, the time boundary and data source are provided for scenario generation. Then, based on the forecast data and the current real-time state of the power grid, a combined sampling method is used to construct a power grid operation scenario for each power grid operation mode, resulting in multiple power grid operation scenarios to cover possible future changes in operation modes. Finally, by integrating multiple power grid operation scenarios and using an ensemble construction method, a set of power grid operation scenarios is obtained, providing diverse input conditions for subsequent parallel simulation.

[0089] S303, for each power grid operation scenario in the set of power grid operation scenarios, combines current power grid status data and uses data twins to perform simulations to obtain predictions of protection action behavior and consequences under the corresponding power grid operation scenario. For details, please refer to... Figure 1 S103 of the illustrated embodiment will not be described again here.

[0090] S304, for each protection configuration of the target relay protection system, comprehensively predicts protection action behavior and consequences under multiple power grid operation scenarios, and uses a risk entropy quantification assessment method to evaluate them separately, obtaining multiple risk identification results and generating a risk heatmap. For details, please refer to [link to relevant documentation]. Figure 1 S104 of the illustrated embodiment will not be described again here.

[0091] This embodiment provides a method for quantifying relay protection risks, which can be used in the aforementioned substation monitoring server. Figure 4 This is a flowchart of a relay protection risk quantification method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: S401, based on the status data of the target relay protection system and the power grid status data, combined with the pre-built software logic image of the target relay protection system, uses a data mapping method to obtain a fused digital twin. The status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information; the power grid status data includes the power grid topology, parameters, and real-time measurement data. For details, please refer to [link to relevant documentation]. Figure 1 S101 of the illustrated embodiment will not be described again here.

[0092] S402, based on access-based renewable energy power prediction, load prediction, and network topology prediction, utilizes scenario construction methods to obtain various power grid operation scenarios and constructs them into a power grid operation scenario set. For details, please refer to [link to relevant documentation]. Figure 1 S102 of the illustrated embodiment will not be described again here.

[0093] S403, for each power grid operation scenario in the power grid operation scenario set, combines the current power grid status data and uses data twins to perform simulations to obtain the prediction of protection action behavior and consequences under the corresponding power grid operation scenario.

[0094] Specifically, S403 includes: S4031, based on each power grid operation scenario in the power grid operation scenario set, uses the anticipated fault construction method to generate multiple anticipated faults; anticipated faults include: single faults, complex faults, or protection-related faults.

[0095] S4032, based on each anticipated fault and combined with the current power grid status data, uses a digital twin to perform fault simulation, and obtains the protection action parameters and power grid response parameters under the corresponding fault.

[0096] For example, S4032 above includes: a1. Based on each anticipated fault and combined with the current power grid status data, the fault injection method is used to simulate the electrical quantity mutation at the moment of fault occurrence in the digital twin, and obtain the transient electrical quantity sequence after the fault. a2, based on the transient electrical quantity sequence after the fault, drives the digital twin to perform fault detection, logic judgment and output action, records the start time, action time and final action status of the corresponding target relay protection system, and obtains the protection action parameters; a3. Based on the protection action parameters, a digital twin is used to simulate the power redistribution process after fault clearance, and the line load rate, node voltage amplitude and power angle stability margin are calculated to obtain the power grid response parameters.

[0097] For example, S4032 above can be implemented as follows: For each power grid operation scenario, a set of anticipated faults are injected in parallel into the digital twin, and multiple simulations are performed using a GPU cluster. The results of each simulation are recorded, including: the action behavior of each protection logic image, whether the action is correct, and the power grid status after the protection action.

[0098] First, a fault injection method is used to simulate sudden changes in electrical quantities, resulting in a transient electrical quantity sequence that accurately reflects the transient characteristics at the time of fault occurrence. Second, based on the transient electrical quantity sequence, a digital twin is driven to perform fault detection, logic judgment, and output actions, recording the start-up time, action time, and final action state of the relay protection system to obtain protection action parameters, facilitating the quantification of the response behavior and action correctness of the relay protection system. Finally, based on the protection action parameters, the power redistribution process after fault clearance is simulated, calculating the line load rate, node voltage amplitude, and power angle stability margin to obtain grid response parameters, providing a quantitative basis for assessing the operating status of the grid after a fault.

[0099] S4033 integrates the protection action parameters corresponding to multiple faults and uses the action correctness judgment method to obtain the behavior prediction result of each protection action; S4034 integrates the grid response parameters corresponding to multiple faults and uses the grid consequence quantification method to calculate the line load rate, node voltage and stability margin after fault clearance, and obtain the grid consequence prediction results.

[0100] For each operational scenario, a set of anticipated faults is generated, encompassing single, complex, and protection-related faults. This ensures that subsequent risk assessments cover multiple fault types, avoiding omissions of critical hidden dangers. A digital twin is then used to simulate each anticipated fault, obtaining protection action parameters and grid response parameters. By combining the protection action parameters under multiple faults, behavioral prediction results are obtained through action correctness judgment, quantifying the statistical characteristics of protection failure or maloperation. Finally, by combining the grid response parameters under multiple faults, the load rate, voltage, and stability margin after fault clearance are calculated, quantifying the consequences of protection actions into comparable grid physical indicators. This provides reliable data support for subsequent risk entropy quantification.

[0101] S404, for each protection configuration of the target relay protection system, comprehensively predicts protection action behavior and consequences under multiple power grid operation scenarios, and uses a risk entropy quantification assessment method to evaluate them separately, obtaining multiple risk identification results and generating a risk heatmap. For details, please refer to [link to relevant documentation]. Figure 1S104 of the illustrated embodiment will not be described again here.

[0102] This embodiment provides a method for quantifying relay protection risks, which can be used in the aforementioned substation monitoring server. Figure 5 This is a flowchart of a relay protection risk quantification method according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps: S501, based on the status data of the target relay protection system and the power grid status data, and combined with the pre-built software logic image of the target relay protection system, uses a data mapping method to obtain a fused digital twin. The status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information; the power grid status data includes the power grid topology, parameters, and real-time measurement data. For details, please refer to [link to relevant documentation]. Figure 1 S101 of the illustrated embodiment will not be described again here.

[0103] S502, based on access-based renewable energy power prediction, load prediction, and network topology prediction, utilizes scenario construction methods to obtain various power grid operation scenarios and constructs them into a power grid operation scenario set. For details, please refer to [link to relevant documentation]. Figure 1 S102 of the illustrated embodiment will not be described again here.

[0104] S503, for each power grid operation scenario in the set of power grid operation scenarios, combines current power grid status data and uses data twins to perform simulations to obtain predictions of protection action behavior and consequences under the corresponding power grid operation scenario. For details, please refer to... Figure 1 S103 of the illustrated embodiment will not be described again here.

[0105] S504, for each protection configuration of the target relay protection system, comprehensively predicts the protection action behavior and consequences under multiple power grid operation scenarios, and uses the risk entropy quantitative assessment method to evaluate them respectively, obtain multiple risk identification results, and generate a risk heat map.

[0106] Specifically, the aforementioned S504 includes: S5041, based on the prediction results of protection action behavior under multiple power grid operation scenarios, uses the mismatch probability statistical method to obtain the mismatch probability of each protection configuration under each power grid operation scenario for each protection configuration and each power grid operation scenario.

[0107] For example, the above S5041 satisfies the following:

[0108] in, This indicates the condition for the first [unit / item] under power grid operation scenario s. The probability of mismatch in a protection configuration-related fault; This indicates the condition for the first [unit / item] under power grid operation scenario s. The total number of simulations for each protection configuration-related fault; To perform the first under power grid operation scenario s The number of times a protection configuration-related fault occurs that the system fails to operate or operates erroneously.

[0109] S5042, based on the mismatch probability of each protection configuration in each power grid operation scenario, uses a severity mapping rule base to quantify the power grid consequences caused by protection mismatch into corresponding severity levels, and obtains the consequence severity assessment value.

[0110] For example, the severity mapping rule base in S5042 above satisfies the following: S=1 corresponds to a slight mismatch, indicating that only non-critical loads are lost and no equipment exceeds limits; S=3 corresponds to a moderate mismatch probability, which is used to indicate the loss of critical loads or the occurrence of short-term equipment overload; S=10 corresponds to the probability of severe mismatch, which is used to indicate that the adjacent equipment overload trips, or causes local voltage collapse, or significantly reduces the system stability margin.

[0111] The severity rating is based on specific physical quantities from the simulation output, such as overload ratio, voltage amplitude, and power angle difference, which are determined by the rule engine.

[0112] S5043, based on the mismatch probability and severity assessment value of each protection configuration in each power grid operation scenario, uses the risk entropy synthesis method to determine the comprehensive risk entropy of each protection configuration in each power grid operation scenario, and constructs the scenario-level risk quantification result of the corresponding protection configuration in each power grid operation scenario.

[0113] For example, the risk entropy synthesis method in S5043 above satisfies the following:

[0114] in, This indicates the condition for the first [unit / item] under power grid operation scenario s. The overall risk entropy of each protection configuration; This represents the mismatch probability weight determined using the entropy weight method; This indicates the condition for the first [unit / item] under power grid operation scenario s. The probability of mismatch in a protection configuration-related fault; This represents the weight of the consequence severity assessment value determined using the entropy weight method; This indicates the condition for the first [unit / item] under power grid operation scenario s. The normalized severity of each protection configuration.

[0115] S5044, based on the scenario-level risk quantification results of each protection configuration under each power grid operation scenario, uses the risk aggregation method to determine the overall risk level of each protection configuration and generates a risk heatmap of the corresponding protection configuration.

[0116] For example, S5044 above includes: The maximum comprehensive risk entropy of each protection configuration in all power grid operation scenarios is selected to generate a dynamic risk heat map of the entire network, which can conveniently and intuitively display high-risk areas.

[0117] Based on the prediction results of protection action behavior under multiple power grid operation scenarios, the mismatch probability is calculated for each protection configuration and each power grid operation scenario, quantifying the possibility of protection failure under a specific operating mode. Based on the mismatch probability, the power grid consequences are quantified into severity levels using a severity mapping rule base, converting physical consequences into comparable severity scores. Based on the mismatch probability and severity assessment value, the comprehensive risk entropy of each configuration under each scenario is obtained using a risk entropy synthesis method, realizing the fusion quantification of protection failure probability and system consequences. Based on the risk entropy under all power grid operation scenarios, the overall risk level of each protection configuration is determined using a risk aggregation method, and a risk heatmap is generated, which is aggregated into an intuitive visualization result, facilitating the subsequent location of high-risk areas.

[0118] This embodiment provides a method for quantifying relay protection risks, which can be used in the aforementioned substation monitoring server. Figure 6 This is a flowchart of a relay protection risk quantification method according to an embodiment of the present invention, such as... Figure 6 As shown, the process includes the following steps: S601, based on the status data of the target relay protection system and the power grid status data, and combined with the pre-built software logic image of the target relay protection system, uses a data mapping method to obtain a fused digital twin. The status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information; the power grid status data includes the power grid-side topology, parameters, and real-time measurement data. For details, please refer to [link to relevant documentation]. Figure 1 S101 of the illustrated embodiment will not be described again here.

[0119] S602, based on access-based renewable energy power prediction, load prediction, and network topology prediction, utilizes scenario construction methods to obtain various power grid operation scenarios and constructs them into a power grid operation scenario set. For details, please refer to [link to relevant documentation]. Figure 1 S102 of the illustrated embodiment will not be described again here.

[0120] S603, for each power grid operation scenario in the set of power grid operation scenarios, combines current power grid status data and uses data twins to perform simulations to obtain predictions of protection action behavior and consequences under the corresponding power grid operation scenario. For details, please refer to... Figure 1 S103 of the illustrated embodiment will not be described again here.

[0121] S604, for each protection configuration of the target relay protection system, comprehensively predicts protection action behavior and consequences under multiple power grid operation scenarios, and uses a risk entropy quantification assessment method to evaluate them separately, obtaining multiple risk identification results and generating a risk heatmap. For details, please refer to [link to relevant documentation]. Figure 1 S104 of the illustrated embodiment will not be described again here.

[0122] S605: When a high risk is identified in the risk identification results, a candidate protection reconfiguration strategy is generated using a digital twin, and the candidate strategy is verified in all scenarios to obtain the verified reconfiguration strategy. Based on the verified reconfiguration strategy, a two-factor confirmation method is used to output control commands for the target relay protection system to execute.

[0123] For example, S605 above includes: S6051 When a high risk is identified in the risk identification results, the cause of the high risk is analyzed and a set of candidate reconstruction strategies is generated. The candidate reconstruction strategies include: adjusting specific protection settings, switching setting areas, enabling or disabling a certain protection function soft switch, and modifying the time coordination settings between protections.

[0124] S6052 creates an independent sandbox environment and clones the current digital twin, while applying candidate strategies to the protection logic mirror in the sandbox environment to obtain a new relay protection configuration.

[0125] S6053 repeats tens of thousands of parallel simulations and risk entropy calculations based on the same future scenario set and fault set for the new relay protection configuration, and obtains a strategy that significantly reduces the risk entropy R' of high-risk points to below the safety threshold, while not introducing new high-risk points in other parts of the power grid.

[0126] S6054, based on the final strategy, generates a structured protection device reconfiguration instruction, including the operation object, modification content, reason, expected effect and rollback plan.

[0127] S6054, for protection device reconfiguration instructions, uses a rule-based automated program to conduct an initial review of logical compliance; then the person in charge conducts a second layer of confirmation using biometrics or dynamic passwords.

[0128] S6055, for protection device reconfiguration commands that have passed double confirmation, is sent to the field protection device via an encrypted signature channel. Upon receiving the command, the device verifies its integrity, executes the corresponding protection customization area switch, and sends back the confirmation result and new status information, forming a closed loop.

[0129] Finally, the deviation between the actual measurement data and the predicted scenario is continuously compared, as well as whether the actual state of the reconstructed device is consistent with the expected state. If the deviation exceeds the preset threshold, the simulation range is immediately narrowed, and a new adaptation strategy is regenerated and executed, starting from the latest real-time state, to achieve rolling optimization.

[0130] When a high risk is identified in the risk identification results, a candidate reconstruction strategy is generated using a digital twin and verified in all scenarios to ensure that the reconstruction strategy is effective and does not introduce new risks. Then, based on the verified reconstruction strategy, a two-factor confirmation method is used to output control commands to ensure the online safe adaptive adjustment of the control strategy of the target relay protection system.

[0131] This embodiment provides a relay protection risk quantification method. First, it integrates the status data of the target relay protection system with the grid status data to construct a digital twin. The settings, soft circuit boards, and self-test information of the relay protection system are uniformly mapped with the grid topology and measurement data, achieving deep coupling between the protection logic and the grid model. Next, it generates a set of grid operation scenarios based on new energy sources and load forecasts, enabling risk assessment to cover the future range of grid operation changes. Then, it uses the digital twin to simulate each grid operation scenario, pre-simulating protection actions and grid consequences, achieving forward-looking quantification of potential risks. Finally, it uses a risk entropy quantification method to comprehensively assess the mismatch probability and the severity of consequences, generating a heat map. The final risk identification results are presented in a visual form, improving the decision-making efficiency for risk assessment after the grid has integrated a high proportion of new energy sources.

[0132] This embodiment also provides a relay protection risk quantification device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs 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.

[0133] This embodiment provides a relay protection risk quantification device, such as... Figure 7 As shown, the device includes: The twin construction module 710 is used to obtain a fused digital twin based on the status data of the target relay protection system and the power grid status data, combined with the pre-built software logic image of the target relay protection system, using a data mapping method. The status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information; the power grid status data includes the power grid topology, parameters, and real-time measurement data. The scenario generation module 720 is used for new energy power prediction, load prediction and network topology prediction based on access. It uses scenario construction methods to obtain a variety of power grid operation scenarios and constructs them into a power grid operation scenario set. Simulation module 730 is used to simulate each power grid operation scenario in the power grid operation scenario set, combined with the current power grid status data, using data twins to obtain the protection action behavior prediction and consequence prediction under the corresponding power grid operation scenario. The risk assessment module 740 is used to comprehensively predict the protection action behavior and consequences under multiple power grid operation scenarios for each protection configuration of the target relay protection system, and to conduct assessments using the risk entropy quantification assessment method to obtain multiple risk identification results and generate a risk heat map.

[0134] In some alternative implementations, the twin building block 710 includes: The first model building unit is used to obtain the primary system model of the power grid based on the grid-side topology and parameters in the power grid state data and using the primary system modeling method. The second model construction unit is used to obtain an accurate protection logic image that is consistent with the logic of the target relay protection system based on the state data of the target relay protection system and using the protection logic image construction method. The data fusion unit is used to perform weighted fusion based on the primary system model of the power grid and the precise protection logic mirror, combined with the status data of the target relay protection system and the power grid status data, using a dynamic fusion method to obtain the fused digital twin.

[0135] In some alternative implementations, the scene generation module 720 includes: The data acquisition unit is used to acquire prediction data within a preset time window based on the access-based new energy power prediction, load prediction, and network topology prediction. The scenario construction unit is used to construct a grid operation scenario for each grid operation mode based on the predicted data within a preset time window and combined with the current real-time grid status data, using a combined sampling method to obtain multiple grid operation scenarios; each grid operation scenario includes power generation output, load level and network topology configuration. The set construction unit is used to integrate multiple power grid operation scenarios and obtain a set of power grid operation scenarios using the set construction method.

[0136] In some alternative implementations, simulation module 730 includes: The fault construction unit is used to generate multiple anticipated faults based on each power grid operation scenario in the power grid operation scenario set, using the anticipated fault construction method. The anticipated faults include: single faults, complex faults, or protection-related faults. The data simulation unit is used to simulate each anticipated fault using a digital twin, combined with the current power grid status data, to obtain the protection action parameters and power grid response parameters under the corresponding fault. The result prediction unit is used to integrate the protection action parameters corresponding to multiple faults and use the action correctness judgment method to obtain the behavior prediction result of each protection action. The result quantification unit is used to integrate the power grid response parameters corresponding to multiple faults, and to calculate the line load rate, node voltage and stability margin after fault clearance using the power grid consequence quantification method, so as to obtain the power grid consequence prediction results.

[0137] In some alternative implementations, the data simulation unit includes: The fault simulation subunit is used to simulate the electrical quantity mutation at the moment of fault occurrence in a digital twin based on each anticipated fault and combined with the current power grid status data, using the fault injection method, to obtain the transient electrical quantity sequence after the fault. The protection action simulation subunit is used to drive the digital twin to perform fault detection, logic judgment and output action based on the transient electrical quantity sequence after the fault, and record the start time, action time and final action status of the corresponding target relay protection system to obtain protection action parameters. The parameter simulation subunit is used to simulate the power redistribution process after fault clearance using a digital twin based on the protection action parameters, and to calculate the line load rate, node voltage amplitude and power angle stability margin to obtain the grid response parameters.

[0138] In some alternative implementations, the risk assessment module 740 includes: The mismatch behavior prediction unit is used to predict the protection action behavior based on the prediction results of multiple power grid operation scenarios. For each protection configuration and each power grid operation scenario, the mismatch probability is obtained by using the mismatch probability statistical method. The severity assessment unit is used to quantify the grid consequences caused by protection mismatch into the corresponding severity level based on the mismatch probability of each protection configuration in each power grid operation scenario, using the severity mapping rule base, and obtain the consequence severity assessment value. The comprehensive evaluation unit is used to determine the comprehensive risk entropy of each protection configuration in each power grid operation scenario based on the mismatch probability and severity of consequences assessment value of each protection configuration in each power grid operation scenario, and to construct the scenario-level risk quantification result of the corresponding protection configuration in each power grid operation scenario. The risk aggregation unit is used to determine the overall risk level of each protection configuration based on the scenario-level risk quantification results of each protection configuration under each power grid operation scenario, and to generate a risk heatmap of the corresponding protection configuration.

[0139] In some alternative implementations, it also includes: The iterative update module is used to generate candidate protection reconfiguration strategies using digital twins when there are high risks in the risk identification results, and to verify the candidate strategies in all scenarios to obtain the verified reconfiguration strategies. Based on the verified reconfiguration strategies, the two-factor confirmation method is used to output control commands for the target relay protection system to execute.

[0140] The relay protection risk quantification device provided in this embodiment of the invention can execute the relay protection risk quantification method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0141] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0142] The following is a detailed reference. Figure 8 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 801, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 802 or a program loaded from memory 808 into random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the electronic device. The processor 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0143] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 808 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0144] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a memory 808, or installed from a ROM 802. When the computer program is executed by the processor 801, it performs the functions defined in the relay protection risk quantification method of the embodiments of the present invention.

[0145] Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0146] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the relay protection risk quantification method shown in the above embodiments is implemented.

[0147] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0148] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for quantifying relay protection risks, characterized in that, The method includes: Based on the status data of the target relay protection system and the power grid status data, and combined with the pre-constructed software logic image of the target relay protection system, a fused digital twin is obtained using a data mapping method; the status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information; the power grid status data includes the power grid topology, parameters, and real-time measurement data. Based on access-based new energy power prediction, load prediction, and network topology prediction, various power grid operation scenarios are obtained using scenario construction methods, and a power grid operation scenario set is constructed. For each power grid operation scenario in the power grid operation scenario set, and in conjunction with the current power grid status data, simulations are performed using data twins to obtain predictions of protection action behaviors and consequences under the corresponding power grid operation scenario. For each protection configuration of the target relay protection system, the protection action behavior prediction and consequence prediction under multiple power grid operation scenarios are combined, and the risk entropy quantitative assessment method is used to evaluate them respectively, so as to obtain multiple risk identification results and generate a risk heat map.

2. The method according to claim 1, characterized in that, For each power grid operation scenario in the power grid operation scenario set, simulations are performed using data twins based on current power grid status data to obtain predictions of protection action behaviors and consequences under the corresponding power grid operation scenario, including: Based on each power grid operation scenario in the power grid operation scenario set, multiple anticipated faults are generated using the anticipated fault construction method; the anticipated faults include: single faults, complex faults, or protection-related faults. Based on each anticipated fault, combined with the current power grid status data, the digital twin is used to perform fault simulation to obtain the protection action parameters and power grid response parameters under the corresponding fault. By combining the protection action parameters corresponding to multiple faults, and using the action correctness judgment method, the behavior prediction result of each protection action is obtained; By combining the power grid response parameters corresponding to multiple faults and using the power grid consequence quantification method, the line load rate, node voltage and stability margin after fault clearance are calculated to obtain the power grid consequence prediction results.

3. The method according to claim 2, characterized in that, Based on each anticipated fault, and combined with current power grid status data, the digital twin is used to perform fault simulation, obtaining the corresponding protection action parameters and power grid response parameters under the fault, including: Based on each anticipated fault, and combined with the current power grid status data, the fault injection method is used to simulate the electrical quantity mutation at the moment of fault occurrence in the digital twin, thereby obtaining the transient electrical quantity sequence after the fault. Based on the transient electrical quantity sequence after the fault, the digital twin is driven to perform fault detection, logic judgment and output action, and the start time, action time and final action status of the corresponding target relay protection system are recorded to obtain protection action parameters. Based on the protection action parameters, the power redistribution process after fault clearance is simulated using the digital twin, and the line load rate, node voltage amplitude and power angle stability margin are calculated to obtain the power grid response parameters.

4. The method according to claim 1, characterized in that, The fused digital twin, based on the state data of the target relay protection system and the power grid state data, combined with the pre-constructed software logic image of the target relay protection system, is obtained using a data mapping method, including: Based on the grid-side topology and parameters in the grid state data, a primary system model of the power grid is obtained using the primary system modeling method. Based on the status data of the target relay protection system, a precise protection logic mirror that is consistent with the logic of the target relay protection system is obtained by using the protection logic mirroring construction method. Based on the primary system model of the power grid and the precise protection logic mirror, and combining the status data of the target relay protection system with the status data of the power grid, a weighted fusion is performed using a dynamic fusion method to obtain the fused digital twin.

5. The method according to claim 1, characterized in that, The access-based new energy power prediction, load prediction, and network topology prediction utilize scenario construction methods to obtain various power grid operation scenarios and construct a power grid operation scenario set, including: Based on the access-based new energy power prediction, load prediction, and network topology prediction, the prediction data within the preset time window is obtained. Based on the predicted data within the preset time window, combined with the current real-time status data of the power grid, a combined sampling method is used to construct each power grid operation mode into a power grid operation scenario, resulting in multiple power grid operation scenarios; each power grid operation scenario includes power generation output, load level, and network topology configuration. By combining multiple power grid operation scenarios, a set of power grid operation scenarios is obtained using a set construction method.

6. The method according to claim 1, characterized in that, For each protection configuration of the target relay protection system, the protection action behavior prediction and consequence prediction under multiple power grid operation scenarios are comprehensively integrated, and the risk entropy quantification assessment method is used to evaluate them respectively, resulting in multiple risk identification results and generating a risk heatmap, including: Based on the prediction results of protection action behavior under multiple power grid operation scenarios, for each protection configuration and each power grid operation scenario, the mismatch probability of each protection configuration under each power grid operation scenario is obtained by using the mismatch probability statistical method. Based on the mismatch probability of each protection configuration in each power grid operation scenario, the power grid consequences caused by protection mismatch are quantified into corresponding severity levels using a severity mapping rule base to obtain a consequence severity assessment value. Based on the mismatch probability and severity assessment value of each protection configuration in each power grid operation scenario, the comprehensive risk entropy of each protection configuration in each power grid operation scenario is determined using the risk entropy synthesis method, and the scenario-level risk quantification result of the corresponding protection configuration in each power grid operation scenario is constructed. Based on the scenario-level risk quantification results of each protection configuration under each power grid operation scenario, the overall risk level of each protection configuration is determined by using the risk aggregation method, and a risk heatmap of the corresponding protection configuration is generated.

7. The method according to any one of claims 1 to 6, characterized in that, Also includes: When a high risk is identified in the risk identification results, a candidate protection reconstruction strategy is generated using a digital twin, and the candidate strategy is verified in all scenarios to obtain the verified reconstruction strategy. Based on the verified reconstruction strategy, a two-factor verification method is used to output control commands for the target relay protection system to execute.

8. A relay protection risk quantification device, characterized in that, The device includes: The twin construction module is used to obtain a fused digital twin based on the status data of the target relay protection system and the power grid status data, combined with the pre-built software logic image of the target relay protection system, using a data mapping method. The status data of the target relay protection system includes the current setting group, soft pressure plate status, and internal self-test information. The power grid status data includes the power grid topology, parameters, and real-time measurement data. The scenario generation module is used for new energy power prediction, load prediction and network topology prediction based on access. It uses scenario construction methods to obtain a variety of power grid operation scenarios and constructs them into a power grid operation scenario set. The simulation module is used to perform simulations for each power grid operation scenario in the power grid operation scenario set, combined with the current power grid status data, using a data twin to obtain the protection action behavior prediction and consequence prediction under the corresponding power grid operation scenario. The risk assessment module is used to comprehensively predict the protection action behavior and consequences under multiple power grid operation scenarios for each protection configuration of the target relay protection system. It uses the risk entropy quantification assessment method to conduct assessments respectively, obtain multiple risk identification results, and generate a risk heat map.

9. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the relay protection risk quantification method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the relay protection risk quantification method according to any one of claims 1 to 7.

Images