Unified representation method of power system security risk situation based on integration of sky, ground, communication, guidance and sensing

Abstract

The present invention discloses a unified characterization method for the safety risk situation of an electric power system that integrates the sky, the ground, and the communication, the guidance, and the sensing. The method comprises: constructing a safety risk knowledge graph based on the safety risk structure information of the electric power system, obtaining risk coupling information between various safety risk characteristic factors according to the safety risk knowledge graph, constructing a spatiotemporal risk quantification model of the electric power system according to the risk coupling information, obtaining actual risk data of the electric power system, the actual risk data comprising actual risk label data and actual spatiotemporal risk characteristic data, optimizing the spatiotemporal risk quantification model based on the actual risk data, obtaining a target risk quantification model, and uniformly characterizing the safety risk situation of the electric power system according to the target risk quantification model, realizing accurate analysis of the coupling relationship of the electric power system, effectively improving the accuracy of risk situation characterization, thereby timely locating risks, and greatly improving the accuracy of risk prediction, thereby ensuring stable operation of the electric power system.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a unified characterization method for safety risk situation of an electric power system integrating sky, ground, communication, conduction and sensing. Background Art

[0002] In recent years, natural disasters such as typhoons, heavy rains and floods, as well as man-made attacks such as cyber attacks and electromagnetic attacks have occurred frequently, posing a serious threat to the safe operation of the power system. On the premise of extracting the key inducing factors of disasters, it is urgent to establish a unified characterization mechanism for the security risk situation of the power system, enhance the security risk early warning capability of the power system, and ensure the reliable supply of electricity and the safety of people’s lives and property.

[0003] Since the current power system is an organic whole formed by the close coupling of various fields of generation, transmission, transformation, distribution, and use, various links of source, grid, load, and storage, and technical systems, a large number of automation and information equipment have been integrated into the power grid, the scope of system failures has increased, and the equipment coupling relationship has become more complex. The characteristics of power disasters have differences in monitoring angles, which makes it impossible to effectively analyze the coupling between characteristics. Therefore, it is difficult to uniformly characterize the security risk situation of the new power system that integrates sky, ground, communication, and sensing, and cannot accurately characterize the security risk situation of the power system. Summary of the invention

[0004] The main purpose of the present invention is to provide a unified method for characterizing the safety risk situation of an electric power system that integrates the sky, the ground, and the communication, the conduction, and the sensing. The method aims to solve the technical problem that the existing technology cannot effectively analyze the coupling and correlation between the characteristics of power disasters, resulting in the inability to accurately characterize the safety risk situation of the power system.

[0005] To achieve the above-mentioned purpose, the present invention provides a unified characterization method for power system security risk situation integrating air, ground, communication, conduction and sensing, the method comprising the following steps:

[0006] Construct a safety risk knowledge graph based on the safety risk structure information of the power system;

[0007] Acquire risk coupling information between various safety risk characteristic factors of the power system according to the safety risk knowledge graph;

[0008] Constructing a spatiotemporal risk quantification model of the power system according to the risk coupling information, wherein the spatiotemporal risk quantification model includes a spatial risk quantification model and a temporal risk quantification model;

[0009] Acquire actual risk data of the power system, wherein the actual risk data is acquired based on sky-to-ground monitoring data collected by the sky-to-ground system, and the actual risk data includes actual risk label data and actual spatiotemporal risk feature data;

[0010] Optimizing the spatiotemporal risk quantification model based on the actual risk data to obtain a target risk quantification model;

[0011] The security risk situation of the power system is uniformly characterized according to the target risk quantification model.

[0012] Optionally, constructing a safety risk knowledge graph based on the safety risk structure information of the power system includes:

[0013] Acquiring security risk structure information of the power system based on an original structured knowledge base of the power system;

[0014] Constructing an initial risk ontology structure of the power system according to the security risk structure information;

[0015] Performing relationship identification on the initial risk ontology structure based on a pre-built relationship extraction model to obtain a relationship identification result;

[0016] Constructing a risk classification system based on the relationship identification results;

[0017] Aggregating the risk category system with the initial risk ontology structure to obtain a target risk ontology structure;

[0018] Performing knowledge data mining on the target risk ontology structure based on a pre-built data mining model to obtain risk map information of the power system, wherein the risk map information includes entity information and attribute information;

[0019] Construct a security risk knowledge graph based on the risk graph information.

[0020] Optionally, the spatial risk quantification model is constructed based on a spatial system risk coefficient calculation formula, and the spatial system risk coefficient calculation formula includes:

[0021]

[0022] in, represents the spatial risk quantification parameter, Indicates risk factors The increased risk level of the power system when it does not occur, Indicates the current risk level of the power system;

[0023]

[0024]

[0025] in, Indicates risk factors The reliability of the power system when the Indicates the current reliability of the power system;

[0026]

[0027]

[0028] in, Indicates risk factors When the power system does not appear The reliability of each component, Indicates the first The current reliability of each component;

[0029]

[0030]

[0031] in, Indicates that it contains The input database of risk data, Represents the input database Risk data in Represents the input database The cardinality of all fault data in .

[0032] Optionally, the time risk quantification model is constructed based on a time system risk coefficient calculation formula, and the time system risk coefficient calculation formula includes:

[0033]

[0034] in, represents the time risk quantification parameter, represents the probability of an event occurring, Indicates an event When the event occurs The conditional probability of occurrence, Indicates area In the event of a disaster, Indicates time period Disasters that occur within Indicates an event that causes losses when a disaster occurs in the power system;

[0035]

[0036]

[0037]

[0038]

[0039] in, represents a quarterly collection, Represents four quarters respectively. Indicates the consequences of loss, Indicates the consequences of loss The number of unit losses caused, Indicates the number of influencing features of power system security risk situation, Represents a collection of regions Sub-areas in .

[0040] Optionally, the spatiotemporal risk quantification model includes:

[0041]

[0042] in, is the risk prediction quantification result output by the spatiotemporal risk quantification model, is the spatial risk weight, is the time risk weight.

[0043] Optionally, constructing the spatiotemporal risk quantification model of the power system according to the risk coupling information includes:

[0044] Obtaining a risk dataset based on an input database;

[0045] Rating the disaster days corresponding to each risk data in the risk data set to determine the stability assessment level corresponding to each disaster day;

[0046] The stability assessment threshold corresponding to each stability assessment level is set based on the power outage duration parameter of each disaster day. The stability assessment threshold is calculated based on the following formula:

[0047]

[0048]

[0049] in, represents the stability assessment threshold, Indicates the stability assessment level, is the adjustment coefficient, which is used to reduce the statistical variation between different research cycles. for The average of the natural logarithms of for The standard deviation of the natural logarithm of Represents the power outage duration parameter, is the duration of the power outage, is the number of users affected by the disaster, is the total number of surveyed users;

[0050] Each disaster day is classified according to the stability assessment threshold and the risk coupling information, and a spatiotemporal risk quantification model is constructed based on the disaster day classification results.

[0051] Optionally, the optimizing the spatiotemporal risk quantification model based on the actual risk data to obtain a target risk quantification model includes:

[0052] Inputting the actual spatiotemporal risk characteristic data into the spatiotemporal risk quantification model to perform risk prediction to obtain a risk prediction quantification result;

[0053] Comparing the risk prediction quantification result with the actual risk label data to obtain a comparison result;

[0054] Based on the comparison result, the security risk knowledge graph is updated to obtain a target risk knowledge graph;

[0055] The spatiotemporal risk quantification model is optimized according to the target risk knowledge graph to obtain a target risk quantification model.

[0056] The present invention constructs a safety risk knowledge graph based on the safety risk structure information of the power system, obtains the risk coupling information between the safety risk characteristic factors of the power system according to the safety risk knowledge graph, constructs a spatiotemporal risk quantification model of the power system according to the risk coupling information, and the spatiotemporal risk quantification model includes a spatial risk quantification model and a temporal risk quantification model, obtains actual risk data of the power system, and the actual risk data is obtained based on the sky-ground monitoring data collected by the sky-ground system, and the actual risk data includes actual risk label data and actual spatiotemporal risk characteristic data. The spatiotemporal risk quantification model is optimized based on the actual risk data to obtain a target risk quantification model, and the safety risk situation of the power system is uniformly characterized according to the target risk quantification model, so as to achieve accurate analysis of the coupling relationship of the power system, and perform risk quantitative prediction from the time dimension and the space dimension respectively, so as to improve the disaster prediction accuracy of the new power system with sky-ground integration and communication, guidance and sensing integration, and give early warning of high-risk operation areas and chain failures, and provide decision-making information and reserve decision-making time for risk prevention and control and emergency plan formulation, so as to ensure the safe and stable operation of the new power system with sky-ground integration and communication, guidance and sensing integration. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0059] Figure 1 It is a structural schematic diagram of a unified characterization device for power system security risk situation with integrated sky-ground, communication-conducting-sensing integration in a hardware operating environment involved in an embodiment of the present invention;

[0060] Figure 2 It is a flow chart of an embodiment of a unified method for characterizing the security risk situation of a power system integrating air, ground, communication, conduction and sensing of the present invention;

[0061] Figure 3 It is a schematic diagram of the process of constructing a safety risk knowledge graph in an embodiment of a unified characterization method for safety risk situation of a power system integrating air, ground, communication, guidance and sensing of the present invention;

[0062] Figure 4 It is a schematic diagram of the process of constructing a spatiotemporal risk quantification model in an embodiment of a unified characterization method for power system security risk situation integrating sky, ground, communication, conduction and sensing of the present invention;

[0063] Figure 5 It is a schematic diagram of the model optimization process in an embodiment of the unified characterization method for the safety risk situation of an electric power system integrating air, ground, communication, conduction and sensing of the present invention.

[0064] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0066] Reference Figure 1 , Figure 1 It is a schematic diagram of the structure of a unified characterization device for the safety risk situation of an electric power system that integrates the sky, ground, communication, conduction and sensing in the hardware operating environment involved in an embodiment of the present invention.

[0067] like Figure 1As shown, the unified characterization device for power system security risk situation with integrated sky-ground, communication-conducting-sensing integration may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0068] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the unified characterization device for the security risk situation of the power system integrating the sky, the ground, the communication, the conduction and the sensing, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0069] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a unified characterization program for power system security risk situation that integrates air, ground, communication, guidance, and sensing.

[0070] exist Figure 1 In the unified characterization device for security risk situation of an electric power system integrating sky, ground, communication, conductor, and sense shown in the figure, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the unified characterization device for security risk situation of an electric power system integrating sky, ground, communication, conductor, and sense of the present invention can be arranged in the unified characterization device for security risk situation of an electric power system integrating sky, ground, communication, conductor, and sense of the present invention, and the unified characterization device for security risk situation of an electric power system integrating sky, ground, communication, conductor, and sense of the present invention calls the unified characterization program for security risk situation of an electric power system integrating sky, ground, communication, conductor, and sense of the present invention stored in the memory 1005 through the processor 1001, and executes the unified characterization method for security risk situation of an electric power system integrating sky, ground, communication, conductor, and sense of the present invention provided in an embodiment of the present invention.

[0071] The embodiment of the present invention provides a unified characterization method for power system security risk situation with integrated sky-ground and communication-conducting-sensing integration, referring to Figure 2 , Figure 2 It is a flow chart of an embodiment of a unified method for characterizing the safety risk situation of an electric power system integrating air, ground, communication, conduction and sensing of the present invention.

[0072] In this embodiment, the unified characterization method for power system security risk situation integrating air, ground, communication, conduction and sensing includes the following steps:

[0073] Step S10: Construct a safety risk knowledge graph based on the safety risk structure information of the power system.

[0074] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a terminal electronic device capable of realizing the above functions, etc. The following takes the unified characterization device for power system security risk situation with integrated sky-ground and communication-conducting-sensing integration (referred to as the characterization device) as an example to illustrate this embodiment and the following embodiments.

[0075] It should be noted that the power system can be a new type of power system that integrates the sky, the ground, and the communication, conduction, and sensing. The power system can be an organic whole formed by the close coupling of various fields of generation, transmission, transformation, distribution, and use, various links of source, grid, load, and storage, and various levels of technical system.

[0076] It can be understood that this embodiment constructs a new power system safety risk knowledge graph, which intuitively represents the complex coupling relationship between equipment, events and states in the power system through a graph structure, which helps to conduct in-depth analysis of key issues such as equipment failure, operating status and load scheduling.

[0077] It should be noted that the safety risk knowledge graph can be a graph structure containing entities and relationships. The entities of the safety risk knowledge graph may include power generation equipment, transmission equipment, substation equipment, distribution equipment, and power terminal equipment. The relationships of the safety risk knowledge graph may include "equipment-cause-failure event", "event-trigger-equipment risk escalation", etc.

[0078] Furthermore, in order to accurately construct the security risk knowledge graph, refer to Figure 3 , Figure 3 The flowchart of constructing a security risk knowledge graph in one embodiment is shown in FIG. 1 . The above step S10 may include:

[0079] Step S101: acquiring security risk structure information of the power system based on an original structured knowledge base of the power system;

[0080] Step S102: constructing an initial risk ontology structure of the power system according to the security risk structure information;

[0081] Step S103: performing relationship identification on the initial risk ontology structure based on a pre-built relationship extraction model to obtain a relationship identification result;

[0082] Step S104: constructing a risk classification system according to the relationship identification result;

[0083] Step S105: Aggregate the risk category system with the initial risk ontology structure to obtain a target risk ontology structure;

[0084] Step S106: performing knowledge data mining on the target risk ontology structure based on a pre-built data mining model to obtain risk map information of the power system, wherein the risk map information includes entity information and attribute information;

[0085] Step S107: construct a security risk knowledge graph based on the risk graph information.

[0086] In some embodiments, the characterization device can, in the new power system safety risk perception business, obtain the structural information of the knowledge ontology in the field of new power system safety risk perception through business expert model compilation or by using an existing structured knowledge base, and then add the knowledge ontology to the knowledge base, build a basic ontology structure from top to bottom, and use concept extraction and relationship extraction models (such as the BERT model (Based Relation Extraction)) for automatic recognition. The recognition results are abstractly verified by business experts to form a bottom-up category system, which is integrated with the basic ontology architecture to construct a new power system safety risk knowledge ontology architecture.

[0087] It should be noted that the above-mentioned knowledge ontology may refer to core entities in the field, such as "equipment", "state", "event", etc. The above-mentioned structural information may refer to key concepts such as equipment, events, and states related to power system safety.

[0088] It should be noted that the above basic ontology structure refers to obtaining high-level concepts and relationship frameworks from existing domain knowledge bases and business models.

[0089] In some embodiments, the characterization device builds a basic ontology structure based on the structural information of the knowledge ontology, which may be to extract and define concepts and relationships through existing knowledge and data mining technology, and form a multi-level classification and association system.

[0090] In some embodiments, the characterization device can be based on the ontology architecture and use data mining models (such as decision trees and random forests) to realize the entity identification and attribute extraction of new power system safety risks. Based on multi-source heterogeneous data under satellite-ground fusion, with the support of the ontology library and rule library, the knowledge factors and their associations hidden in the data resources are obtained through knowledge extraction and transformation. After entity linking and knowledge completion, the construction of a new power system safety risk knowledge graph is realized.

[0091] Step S20: Obtain risk coupling information between various safety risk characteristic factors of the power system according to the safety risk knowledge graph.

[0092] It can be understood that this embodiment fully explores the coupling between the characteristic factors of safety risks of the new power system, constructs a spatial system risk coefficient calculation model and a spatial system risk coefficient calculation model for relative weight calculation, and constructs a structural function that affects the risk coefficient calculation model.

[0093] Step S30: constructing a spatiotemporal risk quantification model of the power system according to the risk coupling information.

[0094] It should be noted that the spatiotemporal risk quantification model includes a spatial risk quantification model and a temporal risk quantification model.

[0095] It can be understood that this embodiment constructs a new type of spatiotemporal risk quantification model for power systems, thereby quantifying power system risks from spatial and temporal dimensions respectively, and based on the spatiotemporal system risk coefficient calculation model, explores the coupling between features and measures feature risk weights.

[0096] In some embodiments, the characterization device constructs a spatiotemporal system risk coefficient calculation model based on the time system risk coefficient calculation model and the space system risk coefficient calculation model, so as to describe the correlation between different characteristic factors and disasters, measure the weight of satellite-ground fusion data, and consider the different disaster distributions in different time periods. The weights of characteristic factors are comprehensively measured from the time and space dimensions, thereby improving the accuracy of risk quantification.

[0097] Furthermore, in order to improve the accuracy of risk prediction in the spatial dimension, in some embodiments, the spatial risk quantification model is constructed based on a spatial system risk coefficient calculation formula, and the spatial system risk coefficient calculation formula includes:

[0098]

[0099] in, represents the spatial risk quantification parameter, Indicates risk factors The increased risk level of the power system when it does not occur, Indicates the current risk level of the power system;

[0100]

[0101]

[0102] in, Indicates risk factors The reliability of the power system when the Indicates the current reliability of the power system;

[0103]

[0104]

[0105] in, Indicates risk factors When the power system does not appear The reliability of each component, Indicates the first The current reliability of each component;

[0106]

[0107]

[0108] in, Indicates that it contains The input database of risk data, Represents the input database Risk data in Represents the input database The cardinality of all fault data in .

[0109] It should be noted that the above-mentioned spatial risk quantification model can be a spatial system risk coefficient calculation model (Spatial System Risk Coefficient, SSRC), and the spatial risk quantification model can be a risk growth degree (Risk Growth Degree, RGD) calculation model designed according to the power system stability theory to measure the extent of the risk increase caused by the emergence of a certain risk factor in the system on the existing overall risk level of a certain area, thereby quantifying the overall failure risk of the component to the system in the area.

[0110] Furthermore, in order to improve the accuracy of risk prediction in the time dimension, in some embodiments, the time risk quantification model is constructed based on a time system risk coefficient calculation formula, and the time system risk coefficient calculation formula includes:

[0111]

[0112] in, represents the time risk quantification parameter, is a set containing all disaster quarters, where Indicates the quarter in which a disaster occurs. represents the probability of an event occurring, Indicates in the event When the event occurs The conditional probability of occurrence, represents the probability of an event occurring, Indicates an event When the event occurs The conditional probability of occurrence, Indicates area In the event of a disaster, Indicates time period Disasters that occur within Indicates an event that causes losses when a disaster occurs in the power system;

[0113]

[0114]

[0115]

[0116]

[0117]

[0118] in, represents a quarterly collection, Represents four quarters respectively. Indicates the consequences of loss, Indicates the consequences of loss The number of unit losses caused, is the set of all sub-regions of the study area, Represents the number of influencing features of power system security risk situation, where Indicates the sub-region where a disaster is located. Represents a collection of regions Sub-areas in , It indicates the multiple of the unit loss number of Major Disaster Day (MDD) compared to Basic Disaster Day (BDD).

[0119] is a set of stability assessment levels on the disaster day for all disasters, where Indicates the stability assessment level of a fault on the disaster day. Indicates one of the three levels (MDD (Major Disaster Day), SDD, BDD). According to the data on losses caused by different accident levels stipulated in the Regulations on Emergency Response and Investigation of Power Safety Accidents, the number of disaster unit losses in SDD is estimated. is four times the BDD. Taking the number of disaster unit losses in the BDD as the benchmark, if it is set to "1", then Two stability assessment thresholds are set for MDD and SDD and Then MDD and SDD are the parameter scores based on the average power outage duration of the system on a single day. The disaster days that exceed the set threshold are BDD. and as well as The calculation formulas are:

[0120]

[0121]

[0122] in, represents the stability assessment threshold, Indicates the stability assessment level, is an adjustment factor used to reduce the statistical variation between different research cycles. As The coefficient of As The coefficient of for The average of the natural logarithms of for The standard deviation of the natural logarithm of Represents the power outage duration parameter, is the duration of the power outage, is the number of users affected by the disaster, is the total number of surveyed users.

[0123] It should be noted that the time risk quantification model can be a time system risk coefficient calculation model (TSRC). Considering the impact of seasonal load changes and climate in different seasons on the power system, the unit time period is set according to the quarter. Based on the power system stability assessment theory, the fault risk of all time periods is graded, and the time system risk coefficient calculation model is constructed in combination with the random process risk model to describe the overall disaster risk in the unit time period p within the region q.

[0124] Furthermore, in order to accurately predict the quantitative risk by combining the time dimension and the space dimension, the spatiotemporal risk quantification model includes:

[0125]

[0126] in, is the risk prediction quantification result output by the spatiotemporal risk quantification model, is the spatial risk weight, is the time risk weight. In some embodiments, the spatial risk weight and the time risk weight can be set to 1.

[0127] It should be noted that the spatiotemporal risk quantification model can be a time and spatial system risk coefficient (TSSRC) calculation model.

[0128] Furthermore, in order to accurately analyze the impact of the time dimension of disasters and thus improve the predictive performance of the spatiotemporal risk quantification model, refer to Figure 4 , Figure 4 This is a schematic diagram of a process for constructing a spatiotemporal risk quantification model in an embodiment. The above step S30 may include:

[0129] Step S301: Acquire a risk data set based on an input database;

[0130] Step S302: rating the disaster days corresponding to each risk data in the risk data set, and determining the stability assessment level corresponding to each disaster day;

[0131] Step S303: setting the stability assessment threshold corresponding to each stability assessment level based on the power outage duration parameter of each disaster day;

[0132] Step S304: classify each disaster day according to the stability assessment threshold and the risk coupling information, and construct a spatiotemporal risk quantification model based on the disaster day classification results.

[0133] It should be noted that is a set of stability assessment levels on the disaster day for all disasters, where Indicates the stability assessment level of a fault on the disaster day. Indicates one of the three levels (MDD (Major Disaster Day), SDD, BDD). According to the data on losses caused by different accident levels stipulated in the Regulations on Emergency Response and Investigation of Power Safety Accidents, the number of disaster unit losses in SDD is estimated. is four times the BDD. Taking the number of disaster unit losses in the BDD as the benchmark, if it is set to "1", then Two stability assessment thresholds are set for MDD and SDD and Then MDD and SDD are the parameter scores based on the average power outage duration of the system on a single day. The disaster days that exceed the set threshold are BDD. and as well as The calculation formulas are:

[0134]

[0135]

[0136] in, represents the stability assessment threshold, Indicates the stability assessment level, is an adjustment factor used to reduce the statistical variation between different research cycles. As The coefficient of As The coefficient of for The average of the natural logarithms of for The standard deviation of the natural logarithm of Represents the power outage duration parameter, is the duration of the power outage, is the number of users affected by the disaster, is the total number of surveyed users.

[0137] Step S40: Acquire actual risk data of the power system.

[0138] It should be noted that the actual risk data is obtained based on the sky-to-ground monitoring data collected by the sky-to-ground system, and the actual risk data includes actual risk label data and actual spatiotemporal risk characteristic data.

[0139] It is understandable that this embodiment constructs a parameter adaptive dynamic adjustment mechanism. Based on the comparison between the prediction results and the actual situation, the newly added entity types and newly added data are updated to the knowledge graph according to the originally set knowledge extraction rules, so as to update and improve the knowledge graph in the field of new power system safety risk perception, and then update the risk coefficient score of the spatiotemporal system.

[0140] Step S50: Optimizing the spatiotemporal risk quantification model based on the actual risk data to obtain a target risk quantification model.

[0141] In some embodiments, the characterization device constructs a parameter adaptive dynamic adjustment mechanism, and updates the knowledge graph and quantitative model of the safety risk of the new power system based on the comparison between the prediction results and the actual situation, ensuring that the operating parameters and risk characterization strategies are adjusted as needed in the highly coordinated source-grid-load-storage links, improving the accuracy of the unified characterization of the risk situation, and ensuring the coordinated and stable operation of the entire process of source-grid-load-storage of the new power system.

[0142] Furthermore, in order to update and optimize the model and thus improve the accuracy of risk prediction, refer to Figure 5 , Figure 5 This is a schematic diagram of a model optimization process in an embodiment. The above step S50 may include:

[0143] Step S501: inputting the actual spatiotemporal risk characteristic data into the spatiotemporal risk quantification model to perform risk prediction to obtain a risk prediction quantification result;

[0144] Step S502: Compare the risk prediction quantification result with the actual risk label data to obtain a comparison result;

[0145] Step S503: updating the security risk knowledge graph based on the comparison result to obtain a target risk knowledge graph;

[0146] Step S504: Optimize the spatiotemporal risk quantification model according to the target risk knowledge graph to obtain a target risk quantification model.

[0147] It can be understood that the characterization equipment can determine the actual loss degree of the power system based on the actual risk label data, classify the power system faults according to the loss degree, and adaptively and dynamically adjust the time system risk coefficient calculation model according to the difference between the assessed disaster day level and the actual level.

[0148] In some embodiments, the characterization device can adaptively and dynamically adjust the state parameters in the stability evaluation threshold. Based on the sliding scale theory, the two stability evaluation thresholds are realized. and In each research cycle, this application will update the disaster day rating, mainly in the stability assessment threshold. and Perform adaptive dynamic adjustments, including:

[0149] for , calculate the average natural logarithm of all disaster days selected from the input database B of risk data , and used as a unit sliding value interval. The total number of these selected disaster days will serve as the basis for adjusting the relevant parameters of B in the new cycle. When the total number of disaster days in the next year exceeds or falls below this benchmark, each increase or decrease in disaster day will increase the value of B in the next year. The value is adjusted up or down by one unit sliding value interval accordingly.

[0150] for : Calculate the difference between all disaster days in B and all disaster days selected in B The difference between the values ​​can be positive or negative. Then, based on the next year B solution Add this difference to the value.

[0151] Step S60: uniformly characterizing the security risk situation of the power system according to the target risk quantification model.

[0152] It can be understood that this embodiment constructs a new power system safety risk knowledge graph, and intuitively represents the complex coupling relationship between equipment, events and states in the new power system that integrates sky, ground, communication, conduction and sensing through a graph structure; constructs a new power system safety risk quantification model to explore the coupling between sky, ground and collected features, and comprehensively measures the weights of the new power system risk characteristic factors from the time and space dimensions; constructs a parameter adaptive dynamic adjustment mechanism, and updates the new power system safety risk knowledge graph and quantification model based on the comparison between the prediction results and the actual situation, ensuring that the operating parameters and risk characterization strategies are adjusted as needed in the highly coordinated source-grid-load-storage links, so as to improve the accuracy of the unified characterization of the risk situation.

[0153] This embodiment constructs a safety risk knowledge graph based on the safety risk structure information of the power system, obtains risk coupling information between each safety risk characteristic factor of the power system according to the safety risk knowledge graph, constructs a spatiotemporal risk quantification model of the power system according to the risk coupling information, and the spatiotemporal risk quantification model includes a spatial risk quantification model and a temporal risk quantification model, obtains actual risk data of the power system, and the actual risk data is obtained based on the sky-ground monitoring data collected by the sky-ground system, and the actual risk data includes actual risk label data and actual spatiotemporal risk characteristic data, optimizes the spatiotemporal risk quantification model based on the actual risk data, obtains a target risk quantification model, and uniformly characterizes the safety risk situation of the power system according to the target risk quantification model, realizes accurate analysis of the coupling relationship of the power system, and performs risk quantitative prediction from the time dimension and the space dimension respectively, improves the disaster prediction accuracy of the new power system that integrates the sky-ground and the communication, guidance and sensing, and warns of high-risk operation areas and cascading failures in advance, provides decision-making information and reserves decision-making time for risk prevention and control and emergency plan formulation, and ensures safe and stable operation of the new power system that integrates the sky-ground and the communication, guidance and sensing.

[0154] In addition, an embodiment of the present invention further proposes a computer-readable storage medium, on which is stored a unified characterization program for the security risk situation of an electric power system that integrates the sky, the ground, and the communications, the conductors, and the senses. When the unified characterization program for the security risk situation of an electric power system that integrates the sky, the ground, and the communications, the conductors, and the senses is executed by a processor, the steps of the unified characterization method for the security risk situation of an electric power system that integrates the sky, the ground, and the communications, the conductors, and the senses are implemented as described above.

[0155] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0156] The above-mentioned computer-readable storage medium may be included in a unified characterization device for security risk situation of an electric power system that integrates sky, ground, communication, conduction and sensing; or it may exist independently and not be assembled into a unified characterization device for security risk situation of an electric power system that integrates sky, ground, communication, conduction and sensing.

[0157] In addition, an embodiment of the present invention also proposes a computer program product, including a unified characterization program for the security risk situation of an electric power system that integrates the sky, the ground, and the communications, the conductors, and the senses. When the unified characterization program for the security risk situation of an electric power system that integrates the sky, the ground, and the communications, the conductors, and the senses is executed by a processor, the steps of the unified characterization method for the security risk situation of an electric power system that integrates the sky, the ground, and the communications, the conductors, and the senses are implemented as described above.

[0158] The specific implementation methods of the computer program product of the present invention are basically the same as the embodiments of the above-mentioned unified characterization method for security risk situation of power system integrating sky, ground, communication, conduction and sensing, and will not be repeated here.

[0159] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0160] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0161] In addition, for technical details not described in detail in this embodiment, please refer to the unified characterization method for the security risk situation of the power system integrating air, ground, communication, conduction and sensing provided in any embodiment of the present invention, which will not be repeated here.

[0162] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0163] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0164] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0165] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A unified characterization method for power system security risk situation integrating air, ground, communication, guidance and sensing, characterized in that: The method comprises: Construct a safety risk knowledge graph based on the safety risk structure information of the power system; Acquire risk coupling information between various safety risk characteristic factors of the power system according to the safety risk knowledge graph; Constructing a spatiotemporal risk quantification model of the power system according to the risk coupling information, wherein the spatiotemporal risk quantification model includes a spatial risk quantification model and a temporal risk quantification model; Acquire actual risk data of the power system, wherein the actual risk data is acquired based on sky-to-ground monitoring data collected by the sky-to-ground system, and the actual risk data includes actual risk label data and actual spatiotemporal risk feature data; Optimizing the spatiotemporal risk quantification model based on the actual risk data to obtain a target risk quantification model; Performing a unified characterization of the security risk situation of the power system according to the target risk quantification model; The step of constructing a spatiotemporal risk quantification model of the power system according to the risk coupling information includes: Obtaining a risk dataset based on an input database; Rating the disaster days corresponding to each risk data in the risk data set to determine the stability assessment level corresponding to each disaster day; The stability assessment threshold corresponding to each stability assessment level is set based on the power outage duration parameter of each disaster day. The stability assessment threshold is calculated based on the following formula: in, represents the stability assessment threshold, Indicates the stability assessment level, is the adjustment coefficient, which is used to reduce the statistical variation between different research cycles. for The average of the natural logarithms of for The standard deviation of the natural logarithm of Represents the power outage duration parameter, is the duration of the power outage, is the number of users affected by the disaster, is the total number of surveyed users; Each disaster day is classified according to the stability assessment threshold and the risk coupling information, and a spatiotemporal risk quantification model is constructed based on the disaster day classification results.

2. The unified characterization method for power system security risk situation integrating air, ground, communication, conduction and sensing as claimed in claim 1 is characterized in that: The construction of a safety risk knowledge graph based on the safety risk structure information of the power system includes: Acquiring security risk structure information of the power system based on an original structured knowledge base of the power system; Constructing an initial risk ontology structure of the power system according to the security risk structure information; Performing relationship identification on the initial risk ontology structure based on a pre-built relationship extraction model to obtain a relationship identification result; Constructing a risk classification system based on the relationship identification results; Aggregating the risk category system with the initial risk ontology structure to obtain a target risk ontology structure; Performing knowledge data mining on the target risk ontology structure based on a pre-built data mining model to obtain risk map information of the power system, wherein the risk map information includes entity information and attribute information; Construct a security risk knowledge graph based on the risk graph information.

3. The unified characterization method for power system security risk situation integrating air, ground, communication, conduction and sensing as claimed in claim 1 is characterized in that: The spatial risk quantification model is constructed based on the spatial system risk coefficient calculation formula, and the spatial system risk coefficient calculation formula includes: in, represents the spatial risk quantification parameter, Indicates risk factors The increased risk level of the power system when it does not occur, Indicates the current risk level of the power system; in, Indicates risk factors The reliability of the power system when the Indicates the current reliability of the power system; in, Indicates risk factors When the power system does not appear The reliability of each component, Indicates the first The current reliability of each component; in, Indicates that it contains The input database of risk data, Represents the input database Risk data in Represents the input database The cardinality of all fault data in .

4. The unified characterization method for power system security risk situation integrating air, ground, communication, conduction and sensing as claimed in claim 3 is characterized in that: The time risk quantification model is constructed based on the time system risk coefficient calculation formula, and the time system risk coefficient calculation formula includes: in, represents the time risk quantification parameter, represents the probability of an event occurring, Indicates an event When the event occurs The conditional probability of occurrence, Indicates area In the event of a disaster, Indicates time period Disasters that occur within Indicates an event that causes losses when a disaster occurs in the power system; in, represents a quarterly collection, Represents four quarters respectively. Indicates the consequences of loss, Indicates the consequences of loss The number of unit losses caused, Indicates the number of influencing features of power system security risk situation, Represents a collection of regions Sub-areas in .

5. The unified characterization method for power system security risk situation integrating air, ground, communication, conduction and sensing as claimed in claim 4 is characterized in that: The spatiotemporal risk quantification model includes: in, is the risk prediction quantification result output by the spatiotemporal risk quantification model, is the spatial risk weight, is the time risk weight.

6. The unified characterization method for power system security risk situation integrating air, ground, communication, conduction and sensing according to any one of claims 1 to 5, characterized in that: The step of optimizing the spatiotemporal risk quantification model based on the actual risk data to obtain a target risk quantification model includes: Inputting the actual spatiotemporal risk characteristic data into the spatiotemporal risk quantification model to perform risk prediction to obtain a risk prediction quantification result; Comparing the risk prediction quantification result with the actual risk label data to obtain a comparison result; Based on the comparison result, the security risk knowledge graph is updated to obtain a target risk knowledge graph; The spatiotemporal risk quantification model is optimized according to the target risk knowledge graph to obtain a target risk quantification model.

Images