Risk monitoring methods, devices, equipment, media and program products for source-load-storage networks

Abstract

The present invention discloses a risk monitoring method, device, equipment, medium and program product for a source-load-storage network. The method comprises: acquiring accident monitoring data of a sky-ground system, and preprocessing the accident monitoring data to obtain target risk data, constructing a risk knowledge graph of the source-load-storage network based on the target risk data, acquiring fault factors of the source-load-storage network, and analyzing the correlation information between the fault factors and the risk knowledge graph, constructing a defect propagation model based on the correlation information and the environmental characteristic information and seasonal characteristic information of each risk entity, inputting the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and performing risk monitoring on the source-load-storage network based on the risk analysis results, realizing spatiotemporal analysis of multidimensional data of the sky-ground system, and fully mining the relationship between faults in combination with the knowledge graph, thereby effectively improving the accuracy of risk disaster prediction and ensuring the stable operation of the power system.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a risk monitoring method, device, equipment, medium and program product for a source-load-storage network. Background Art

[0002] With the progress of society and the development of science and technology, the proportion of new energy sources such as wind, light, and water in actual power supply has increased significantly. With the widespread implementation of new clean energy projects, the disaster accidents that may occur in the supporting new power system source-load-storage network cannot be ignored. Wind turbines and photovoltaic panels, power load ends, transmission and distribution lines, and energy storage batteries have different application methods and operating mechanisms: wind power and photovoltaic production operations have significant time periods and randomness and are greatly affected by weather; the power load end has strong volatility and periodicity due to factors such as seasonal changes and population mobility; overhead transmission lines are susceptible to strong winds, rain, snow, and thunderstorms. Limited by the current material level, the energy storage capacity of energy storage equipment is greatly reduced or even fails due to factors such as the age of the equipment, carrying intensity, and improper operation of personnel; therefore, it is particularly important to purposefully identify and analyze the causes of power accidents and disasters that have occurred and establish a risk situation awareness mechanism for sources, loads, storage networks. In this demand context, low-orbit satellites and Internet technologies with a wide monitoring range, low action delay, and excellent perception quality have become important tools for establishing a risk situation awareness mechanism.

[0003] At present, it is difficult to jointly process the multi-dimensional data among various modules in the sky-ground system in the risk situation awareness of source-load-storage-grid. The information transmission and monitoring effect are poor during risk perception. The risk influencing factors of different dimensions are not considered, and the multi-dimensional data of the sky-ground system cannot be effectively analyzed, resulting in low risk monitoring accuracy and poor monitoring efficiency. Summary of the invention

[0004] The main purpose of the present invention is to provide a risk monitoring method, device, equipment, medium and program product for a source-load-storage network, aiming to solve the technical problem that the existing technology cannot effectively process and analyze the multi-dimensional data of the sky-ground system, resulting in low risk monitoring accuracy and poor monitoring efficiency.

[0005] To achieve the above object, the present invention provides a risk monitoring method for a source-load-storage network, the risk monitoring method for a source-load-storage network is applied to a terminal device, the terminal device is communicatively connected to a sky-ground system, the sky-ground system includes a space-based module, an air-based module and a ground-based module, the method includes:

[0006] Acquiring accident monitoring data of the air-ground system, and preprocessing the accident monitoring data to obtain target risk data;

[0007] Constructing a risk knowledge graph of the source-load-storage network based on the target risk data, wherein the risk knowledge graph includes risk entities and risk relationships of each risk entity, wherein the risk entity is a fault type of the source-load-storage network, and the risk relationship is a risk weight corresponding to each fault type;

[0008] Obtaining the failure factors of the source-load-storage network, and analyzing the association information between the failure factors and the risk knowledge graph;

[0009] Building a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity;

[0010] The real-time monitoring data of the source-load-storage network collected by the sky-ground system is input into the defect propagation model for risk analysis, and risk monitoring of the source-load-storage network is performed based on the risk analysis results.

[0011] Optionally, the step of constructing a risk knowledge graph of a source-load-storage network based on the target risk data includes:

[0012] Obtain fault record information of source, load and storage network;

[0013] Acquire common fault types and rare fault types based on the fault record information;

[0014] Determining a mode value and a minimum value in the target risk data;

[0015] Setting a first initial threshold value for the common fault type based on the mode value, and setting a second initial threshold value for the rare fault type based on the minimum value;

[0016] Optimizing the first initial threshold and the second initial threshold according to historical risk prediction information to obtain a target threshold;

[0017] Determine a risk weight based on the target threshold and the occurrence frequency of each fault type in the fault record information;

[0018] A risk knowledge graph of the source-load-storage network is constructed based on the risk weights, the common fault types and the rare fault types.

[0019] Optionally, the constructing a risk knowledge graph of the source-load-storage network based on the risk weight, the common fault type and the rare fault type includes:

[0020] Performing feature analysis on the target risk data to obtain discrete feature information and continuous feature information;

[0021] Determine a state fuzzy score based on the discrete feature information and the continuous feature information;

[0022] mining high-risk rare types from the common fault types and the rare fault types according to the state fuzzy scores;

[0023] Performing correlation analysis on the common fault type, the rare fault type and the high-risk rare type to obtain a correlation amplitude;

[0024] Correcting the risk weight based on the correlation magnitude;

[0025] A risk knowledge graph of the source-load-storage network is constructed based on the corrected risk weights, the common fault types, the rare fault types and the high-risk rare types.

[0026] Optionally, the constructing of a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity includes:

[0027] Determine the disaster severity coefficient of each risk entity based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity;

[0028] A defect propagation model is constructed according to the severity coefficient and the risk knowledge graph, and the defect propagation model is:

[0029]

[0030] in, is the input database containing m fault records, Indicates input database The Fault records, Represents the fault record index, Represents an environmental feature , represent The cardinality of all fault records in Indicates The first environmental feature A value.

[0031] Optionally, the acquiring the accident monitoring data of the air-to-ground system and preprocessing the accident monitoring data to obtain target risk data includes:

[0032] Obtain risk history data and risk experience data;

[0033] Based on the risk history data and the risk experience data, the accident monitoring data is divided into risk stages to obtain risk level data of each power terminal in the source-load-storage network;

[0034] Perform risk superposition assessment according to the risk level data to obtain candidate risk data of the source-load-storage-grid;

[0035] Identify abnormal data in the candidate risk data:

[0036]

[0037] in, is the value of the data point to be detected in the candidate risk data, is the average value of the candidate risk data, is the standard deviation of the candidate risk data, is the number of standard deviations of the value of the data point to be detected in the candidate risk data from the mean value, and the data points in the candidate risk data whose standard deviation exceeds the preset range are determined to be abnormal data;

[0038] The abnormal data is cleaned, and the missing data in the cleaned candidate risk data is filled to obtain the target risk data:

[0039]

[0040] in, represents the target risk data obtained after filling in the missing data, is the time node, and Indicates the load weighting coefficient of two time nodes two days before and after. Indicates the monitoring data recorded in the last hour. Indicates the monitoring data recorded in the previous hour. Indicates the monitoring data recorded in the last 12 hours. Indicates the monitoring data recorded in the previous 12 hours. Indicates the monitoring data recorded in the last 24 hours. Indicates the monitoring data recorded in the previous 24 hours.

[0041] Optionally, the real-time monitoring data includes multi-dimensional heterogeneous image data of the sky-ground system; before inputting the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, it also includes:

[0042] Acquire monitoring data collected by each module in the sky-ground system, wherein the monitoring data includes sensor monitoring data collected by the ground-based module, image monitoring data collected by the air-based module, and remote sensing monitoring data collected by the space-based module;

[0043] Preprocessing the monitoring data, wherein the preprocessing includes data synchronization processing and data standardization processing;

[0044] Perform weight analysis on the pre-processed monitoring data to determine the data weight of each monitoring data;

[0045] Data fusion is performed based on the data weights and the pixel information of each preprocessed monitoring data to obtain multi-dimensional heterogeneous image data of the sky-ground system.

[0046] In addition, to achieve the above-mentioned purpose, the present invention further proposes a risk monitoring device for a source-load-storage network, wherein the device is communicatively connected with a sky-ground system, wherein the sky-ground system includes a space-based module, an air-based module and a ground-based module, and the risk monitoring device for a source-load-storage network includes:

[0047] A data processing module, used to obtain the accident monitoring data of the air-ground system, and pre-process the accident monitoring data to obtain target risk data;

[0048] A graph construction module, for constructing a risk knowledge graph of the source-load-storage network based on the target risk data, wherein the risk knowledge graph includes risk entities and risk relationships of each risk entity, wherein the risk entity is a fault type of the source-load-storage network, and the risk relationship is a risk weight corresponding to each fault type;

[0049] An association analysis module, used to obtain the fault factors of the source-load-storage network and analyze the association information between the fault factors and the risk knowledge graph;

[0050] A model building module, used to build a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity;

[0051] The risk analysis module is used to input the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and to perform risk monitoring on the source-load-storage network based on the risk analysis results.

[0052] In addition, to achieve the above-mentioned purpose, the present application also proposes a risk monitoring device for a source-load-storage network, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the risk monitoring method for a source-load-storage network as described above.

[0053] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the risk monitoring method of the source-load-storage network as described above are implemented.

[0054] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the risk monitoring method of the source-load-storage network as described above.

[0055] The present invention obtains target risk data by acquiring accident monitoring data of the sky-ground system and preprocessing the accident monitoring data; constructs a risk knowledge graph of the source-load-storage network based on the target risk data, the risk knowledge graph includes risk entities and risk relationships of each risk entity, the risk entity is the fault type of the source-load-storage network, and the risk relationship is the risk weight corresponding to each fault type; obtains the fault factor of the source-load-storage network, and analyzes the association information between the fault factor and the risk knowledge graph; constructs a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity; inputs the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and performs risk monitoring on the source-load-storage network based on the risk analysis result, realizes effective analysis of the multidimensional data of the sky-ground system in the time dimension and the space dimension, realizes efficient use of the multidimensional data of the sky-ground system, fully mines the relationship between faults in combination with the knowledge graph, and performs risk analysis on the source-load-storage network through the trap propagation model, effectively improves the accuracy and efficiency of risk disaster prediction, ensures timely discovery of power risks and power disasters, and ensures stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] 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.

[0057] 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.

[0058] Figure 1 It is a schematic diagram of the structure of a risk monitoring device for a source-load-storage network in a hardware operating environment involved in an embodiment of the present invention;

[0059] Figure 2 It is a schematic flow chart of the first embodiment of the risk monitoring method of the source-load-storage network of the present invention;

[0060] Figure 3 It is a schematic diagram of a risk knowledge graph in an embodiment of a risk monitoring method for a source-load-storage network of the present invention;

[0061] Figure 4 It is a flow chart of the second embodiment of the risk monitoring method of the source-load-storage network of the present invention;

[0062] Figure 5 This is a structural block diagram of the first embodiment of the risk monitoring device for the source-load-storage network of the present invention.

[0063] 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

[0064] 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.

[0065] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a risk monitoring device for a source-load-storage network in the hardware operating environment involved in an embodiment of the present invention.

[0066] like Figure 1 As shown, the risk monitoring device of the source-load-storage network 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.

[0067] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the risk monitoring device for the source-load-storage network, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0068] 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 risk monitoring program for a source-load-storage network.

[0069] exist Figure 1In the risk monitoring device of the source-load-storage network shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the risk monitoring device of the source-load-storage network of the present invention can be set in the risk monitoring device of the source-load-storage network, and the risk monitoring device of the source-load-storage network calls the risk monitoring program of the source-load-storage network stored in the memory 1005 through the processor 1001, and executes the risk monitoring method of the source-load-storage network provided by the embodiment of the present invention.

[0070] The embodiment of the present invention provides a risk monitoring method for a source-load-storage network, referring to Figure 2 , Figure 2 It is a flow chart of the first embodiment of the risk monitoring method of the source-load-storage network of the present invention.

[0071] In this embodiment, the risk monitoring method of the source-load-storage network includes the following steps:

[0072] Step S10: Acquire the accident monitoring data of the air-ground system, and pre-process the accident monitoring data to obtain target risk data.

[0073] It should be understood that this embodiment is applied to the risk analysis of the source-load-storage-grid power system, which includes power sources, loads, energy storage equipment and transmission and distribution line networks. This embodiment obtains multi-dimensional data of the sky-ground system, constructs a risk knowledge graph and a defect propagation model based on the multi-dimensional data, and performs risk analysis from the time dimension and the space dimension respectively, thereby effectively improving the accuracy and efficiency of risk prediction 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 risk monitoring device of the source-load-storage network (hereinafter referred to as the monitoring device) as an example to illustrate this embodiment and the following embodiments.

[0075] It can be understood that the monitoring equipment of the present embodiment is communicatively connected with the sky-ground system, and the sky-ground system includes a space-based module, an air-based module and a ground-based module. The above-mentioned space-based module can be a space-based sensing module, for example, the space-based module can include low-orbit satellite equipment in the sky; the above-mentioned air-based module can be an air-based sensing module, for example, the air-based module can include drones, helicopter equipment in the air, etc.; the above-mentioned ground-based module can be a ground-based sensing module, for example, the ground-based module can include ground temperature sensors, current sensors, tension sensors and other sensor equipment.

[0076] It should be noted that the accident monitoring data can be the data of accident risk information of source, load and storage network collected by the sky-ground system. For example, the space-based module can collect meteorological conditions (cold waves, strong winds, wildfires, etc.) within the power system; the air-based module can collect images of transmission lines, equipment status images, and the swaying range of branches along the line during strong winds; the ground-based module can collect operating temperature of electrical equipment, line current, cable tension, SF6 gas concentration in transformers, etc.

[0077] In some embodiments, the monitoring equipment can build a multi-dimensional and comprehensive power information monitoring network through the sky-ground system. For example, in space, the infrared remote sensing function of low-orbit satellites and small-aperture radar positioning technology can be used to achieve large-scale system coverage, and quickly conduct wide-area monitoring and feature data collection of power equipment; in the air, robots, drones, and airborne acoustic wave damage detectors and other highly maneuverable and high-precision small equipment are used to conduct local in-depth monitoring of power distribution lines, pole tower equipment, and transformer taps to detect physical defects in the transmission and distribution network; on the ground, temperature, gas, current, tension and other sensors are used to perform high-resolution and continuous monitoring operations.

[0078] Furthermore, in order to improve data quality, thereby improving the accuracy of risk prediction and monitoring efficiency, the above step S10 may include:

[0079] Step S101: Acquire risk history data and risk experience data.

[0080] It should be noted that the risk historical data may be the historical data of the source, load and storage network collected by the air-ground system. The risk experience data may be the expert experience data of the source, load and storage network collected.

[0081] Step S102: dividing the accident monitoring data into risk stages based on the risk history data and the risk experience data, and obtaining risk level data of each power terminal in the source-load-storage network.

[0082] It should be understood that the monitoring equipment can implement risk stage division for the accident monitoring data collected by the sky-ground system based on risk history data and risk experience data, and divide the risk characteristic information in the accident monitoring data into low, medium and high stages. For example, the wind power and photovoltaic output in the source-load-storage network are divided into low, medium and high risk stages from small to large; similarly, the electricity load is also divided into low, medium and high risk stages from small to large; energy storage equipment is divided into low, medium and high risk stages from low to high according to the energy storage rate; transmission and distribution lines are divided into low, medium and high risk stages according to operating temperature and tension.

[0083] Step S103: Perform risk superposition assessment according to the risk level data to obtain candidate risk data of the source-load-storage network.

[0084] It is understandable that the monitoring equipment can refer to the risk level of the energy storage equipment and transmission and distribution lines monitored in real time based on the risk level data, and combine the risk level of the photovoltaic and wind power output period and the risk level of the load end during the power consumption period to perform a superimposed risk assessment. For example, the risk level of the power supply end is superimposed with the risk level of the load end to assess the source-load risk level, which is then superimposed with the risk level of the transmission and distribution lines to assess the source-load-network risk level, and then superimposed with the risk level of the energy storage equipment to assess the storage source-load-network risk level.

[0085] In some embodiments, the monitoring equipment can build a source-load-storage-network risk collaborative early warning mechanism based on the risk superposition assessment results. The source-load-storage-network risk collaborative early warning mechanism can be based on a collaborative assessment of the overall risk level of each part of the power system in a certain region during a certain period of time, so as to facilitate the reasonable allocation of limited operation and maintenance resources to the links that urgently need maintenance.

[0086] Step S104: Identify abnormal data in the candidate risk data.

[0087] It should be noted that the monitoring equipment can identify and remove abnormal data based on the standard deviation, referring to the following formula:

[0088]

[0089] in, is the value of the data point to be detected in the candidate risk data, is the average value of the candidate risk data, is the standard deviation of the candidate risk data, It is the standard deviation of the value of the data point to be detected in the candidate risk data from the mean value. The data points in the candidate risk data whose standard deviation exceeds the preset range are determined to be abnormal data.

[0090] Step S105: clean the abnormal data and fill in the missing data in the cleaned candidate risk data to obtain target risk data.

[0091] It should be noted that the monitoring equipment takes the weighted average of the data at the same time of the two days before and after the missing sample data, and fills the missing values ​​in combination with the data change rate, so that the candidate risk data after cleaning maintains structural integrity. The missing value filling formula is as follows:

[0092]

[0093] in, represents the target risk data obtained after filling in the missing data, is the time node, and Indicates the load weighting coefficient of two time nodes two days before and after. Indicates the monitoring data recorded in the last hour. Indicates the monitoring data recorded in the previous hour. Indicates the monitoring data recorded in the last 12 hours. Indicates the monitoring data recorded in the previous 12 hours. Indicates the monitoring data recorded in the last 24 hours. Indicates the monitoring data recorded in the previous 24 hours.

[0094] Step S20: Construct a risk knowledge graph of the source-load-storage network based on the target risk data.

[0095] It should be noted that the risk knowledge graph may include risk entities and risk relationships between risk entities. Risk entities may be fault types of the source-load-storage network. Fault types are abnormal situations that may be encountered during the operation of the source-load-storage network (for example, a small-scale wildfire will generally not cause a power outage for a line, but a large-scale wildfire will cause great damage to the line. The "wildfire" here refers to the abnormal situation encountered during the operation of the line). The risk relationship is the risk weight corresponding to each fault type.

[0096] It can be understood that the monitoring equipment can perform risk analysis and risk mining based on the target risk data, determine the various fault types of the source-load-storage network, and the frequency of occurrence of each fault type, set the risk weight of each fault type based on the frequency of occurrence, and construct a risk knowledge graph with the fault type as the graph entity and the risk weight as the graph relationship. Figure 3 , Figure 3 This is a schematic diagram of a risk knowledge graph in an embodiment, wherein the new energy power system includes various power equipment of the source, load, storage network, and each power equipment corresponds to multiple different fault types. For example, the energy storage equipment corresponds to fault types such as electrical shock and thermal runaway; the load equipment corresponds to fault types such as three-phase imbalance and frequency offset.

[0097] In some embodiments, reference Figure 3 , the risk weight of each risk entity can be based on V, C, I, S, and M in order of importance to minor, e.g. Figure 3 In the equation, the importance of the three-phase unbalanced fault corresponding to the load equipment is I, and the importance of the load demand overload fault is V.

[0098] In some embodiments, the grayscale value of each risk entity in the risk knowledge graph may represent the risk weight of each entity. The lower the grayscale value, the lower the risk weight. Conversely, the higher the grayscale value, the higher the risk weight.

[0099] In some embodiments, the risk entities in the risk knowledge graph can be situations that may be encountered during operation and may cause failures (for example, a wildfire for a line. A small-scale wildfire generally does not cause a power outage, but a large-scale wildfire can cause great damage to the line. The "wildfire" here refers to the situation encountered during line operation). The weight corresponding to each situation is determined by the frequency of occurrence and the degree of harm.

[0100] Step S30: Obtain the fault factors of the source-load-storage network, and analyze the correlation information between the fault factors and the risk knowledge graph.

[0101] It should be noted that the monitoring equipment can associate the fault types in the risk knowledge graph with the fault factors of the source, load and storage network and the data information collected by the sky-ground system.

[0102] In some embodiments, in the low-orbit satellite Internet risk situation awareness business, through the existing power system risk system, combined with the experience supplement of front-line construction personnel, and review and editing by business experts, data mining technology is used to associate the characteristic factors in the existing knowledge graph with the information data collected by the sky-ground monitoring system, so as to facilitate the subsequent focused collection and analysis of data.

[0103] Step S40: constructing a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity.

[0104] It should be noted that the monitoring equipment can perform disaster distribution analysis from the time dimension and space dimension respectively based on the correlation information, measure the severity of power disasters caused by different fault factors from the time dimension and space dimension, and thus construct a defect propagation model.

[0105] It should be noted that the environmental characteristic information may be the geographical environment in which each fault factor is distributed, and the above-mentioned seasonal characteristic information may be the season in which each fault factor is prone to occur.

[0106] In some embodiments, the monitoring device performs self-iteration and improvement on the spatiotemporal risk coefficient calculation model, specifically including: dynamically adjusting the stability threshold using the sliding scale adjustment theory for stability threshold setting, updating the weights of fault factors based on the results in each research cycle, and continuously improving the accuracy of the calculation model.

[0107] Furthermore, in order to effectively construct a model to improve the accuracy of risk prediction and analysis, the above step S40 may include:

[0108] Step S401: determining the disaster severity coefficient of each risk entity based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity;

[0109] Step S402: constructing a defect propagation model according to the severity coefficient and the risk knowledge graph.

[0110] It should be noted that the severity coefficient can refer to the intensity of the various fault factors (such as temperature, humidity, wind speed, current load, etc.) that affect the occurrence of power system disasters in the source-load-storage-network risk situation when the disaster occurs. The severity coefficient is mainly reflected in the propagation process of the disaster and is an indicator in the model to measure the strength of the relationship between the fault factor and the occurrence of the disaster.

[0111] It is understandable that this embodiment can be combined with the knowledge graph to fully explore the jointness between fault factors in the risk situation of the source, load and storage network. The correlation between each characteristic factor and the accident risk is evaluated by using a time-space binary risk coefficient calculation model, and the seasonality of the disaster distribution is referred to to design a defect propagation model to analyze different fault factors from the dual dimensions of time and space. For example, in summer, the focus is on analyzing lightning factors, in winter, the focus is on analyzing ice and strong wind factors, in coastal areas, the focus is on analyzing equipment corrosion, and in mountainous areas, the focus is on analyzing animal activities and trees along the line.

[0112] It should be noted that the above defect propagation model is:

[0113]

[0114] in, is the input database containing m fault records, Indicates input database The Fault records, Represents the fault record index, Represents an environmental feature , represent The cardinality of all fault records in Indicates The first environmental feature A value.

[0115] Step S50: input the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and perform risk monitoring on the source-load-storage network based on the risk analysis results.

[0116] It should be noted that the monitoring equipment can obtain the multi-dimensional monitoring data collected by the sky-ground system, pre-process the multi-dimensional monitoring data, obtain real-time monitoring data, input the real-time monitoring data into the defect propagation model for risk analysis, and conduct risk monitoring of the source-load-storage network based on the risk analysis results. For example, the monitoring data collected by the space-based module may include meteorological conditions within the power system (such as cold waves, strong winds, wildfires, etc.); the monitoring data collected by the air-based module may include: transmission line images, equipment status images, the swaying range of tree branches along the line during strong winds, etc.; the monitoring data collected by the ground-based module may include: electrical equipment operating temperature, line current, cable tension, SF6 gas concentration in the transformer, etc.

[0117] In some embodiments, the monitoring equipment can aggregate the multi-dimensional monitoring data collected from the sky and the ground to construct multi-dimensional heterogeneous image data. This is because in reality the sky-air-ground based perception module may not be able to function all the time. For example, the functions of air-based drone equipment are limited in extreme weather such as strong winds and sandstorms. At this time, the tension monitored by the tension sensor in the ground-based perception module can be used to estimate the degree of line dancing, and images with similar dancing degrees in the historical records of air-based equipment detection can be selected instead to ensure the integrity of multi-source data and facilitate data analysis and processing.

[0118] Furthermore, in order to couple the multi-dimensional monitoring data of the sky-ground system and ensure the integrity of the data, the real-time monitoring data includes the multi-dimensional heterogeneous image data of the sky-ground system; before the above step S50, it also includes:

[0119] Step S51: Acquire monitoring data collected by each module in the sky-ground system.

[0120] It should be noted that the monitoring data includes sensor monitoring data collected by the ground-based module, image monitoring data collected by the air-based module and remote sensing monitoring data collected by the space-based module; for example, the space-based module can collect meteorological conditions (cold waves, strong winds, wildfires, etc.) within the power system; the air-based module can collect images of transmission lines, equipment status images, the swaying range of tree branches along the line during strong winds, etc.; the ground-based module can collect the operating temperature of electrical equipment, line current, cable tension, SF6 gas concentration in the transformer, etc.

[0121] In some embodiments, the monitoring equipment can build a multi-dimensional and comprehensive power information monitoring network through the sky-ground system. For example, in space, the infrared remote sensing function of low-orbit satellites and small-aperture radar positioning technology can be used to achieve large-scale system coverage, and quickly conduct wide-area monitoring and feature data collection of power equipment; in the air, robots, drones, and airborne acoustic wave damage detectors and other highly maneuverable and high-precision small equipment are used to conduct local in-depth monitoring of power distribution lines, pole tower equipment, and transformer taps to detect physical defects in the transmission and distribution network; on the ground, temperature, gas, current, tension and other sensors are used to perform high-resolution and continuous monitoring operations.

[0122] Step S52: pre-processing the monitoring data.

[0123] It should be noted that the above preprocessing includes data cleaning processing, missing data filling processing, data synchronization processing and data standardization processing.

[0124] Step S53: Perform weight analysis on the preprocessed monitoring data to determine the data weight of each monitoring data.

[0125] It can be understood that in the sky-ground system, the three-terminal devices collect independent image data respectively, and the monitoring equipment can set data weights based on the importance and clarity of the data collected by each terminal device.

[0126] Step S54: performing data fusion based on the data weights and the pre-processed pixel information of each monitoring data to obtain multi-dimensional heterogeneous image data of the sky-ground system.

[0127] It should be noted that in reality, the sky-air-ground based perception module does not always work. For example, the functions of air-based UAV equipment are limited in extreme weather such as strong winds and sandstorms. At this time, low-quality data or missing data can be filled based on multi-dimensional heterogeneous image data; for example, the tension monitored by the tension sensor in the ground-based perception module is used to estimate the degree of line jitter, and images with similar degree of jitter in the historical records of air-based equipment inspection are selected instead to ensure the integrity of multi-source data and facilitate the construction of mechanical energy risk maps, risk analysis and risk prediction.

[0128] In some embodiments, the monitoring device may adopt high-resolution fusion technology to achieve the reliability and correlation of data sources through weighted averaging at the pixel level, thereby constructing multi-dimensional heterogeneous image data.

[0129] This embodiment obtains target risk data by acquiring accident monitoring data of the sky-ground system and preprocessing the accident monitoring data; constructs a risk knowledge graph of the source-load-storage network based on the target risk data, the risk knowledge graph includes risk entities and risk relationships of each risk entity, the risk entity is the fault type of the source-load-storage network, and the risk relationship is the risk weight corresponding to each fault type; obtains the fault factor of the source-load-storage network, and analyzes the association information between the fault factor and the risk knowledge graph; constructs a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity; inputs the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and performs risk monitoring on the source-load-storage network based on the risk analysis results, realizes effective analysis of the multidimensional data of the sky-ground system in the time dimension and the space dimension, realizes efficient use of the multidimensional data of the sky-ground system, fully mines the relationship between faults in combination with the knowledge graph, and performs risk analysis on the source-load-storage network through the trap propagation model, effectively improves the accuracy and efficiency of risk disaster prediction, ensures timely discovery of power risks and power disasters, and ensures stable operation of the power system.

[0130] refer to Figure 4 , Figure 4 It is a flow chart of the second embodiment of the risk monitoring method of the source-load-storage network of the present invention.

[0131] Based on the above first embodiment, in this embodiment, step S20 further includes:

[0132] Step S201: Obtain fault record information of the source-load-storage network.

[0133] It should be noted that the fault record information can be obtained from the fault record log or data of the source-load-storage network according to the power department or other data sources.

[0134] Step S202: Acquire common fault types and rare fault types based on the fault record information.

[0135] It should be noted that the monitoring equipment can determine the number of accidents of each fault type based on the fault record information, and classify the faults based on the number of accidents. For example, faults with frequent accidents can be set as common fault types, and faults with a number of accidents not exceeding a preset threshold can be set as rare fault types.

[0136] It should be noted that the failure factors of common failure types and rare failure types vary due to different geographical environments. For example, in inland jungle and mountainous areas, common failure factors include animal activities, fallen trees, etc., and rare factors include hail, freezing rain, etc.; in coastal areas, common failure factors include rust, heavy rain, lightning strikes, etc., and rare factors include wildfires, etc.

[0137] Step S203: determining the mode value and the minimum value in the target risk data;

[0138] Step S204: setting a first initial threshold value of the common fault type based on the mode value, and setting a second initial threshold value of the rare fault type based on the minimum value.

[0139] It can be understood that, for common fault factors, the mode value in the historical fault data is selected and set as the initial threshold; for rare fault factors, the minimum value in the historical fault data is selected and set as the initial threshold.

[0140] Step S205: Optimize the first initial threshold and the second initial threshold according to historical risk prediction information to obtain a target threshold.

[0141] It should be noted that the historical predicted risk may be the prediction result of a historical risk prediction cycle (for example, it may be the prediction result of the previous cycle).

[0142] In some embodiments, the monitoring device may update and optimize the initial threshold in the current prediction process based on the state threshold algorithm fitting results and the prediction effect of the previous cycle in each research cycle, thereby adjusting the threshold range.

[0143] Step S206: Determine a risk weight based on the target threshold and the occurrence frequency of each fault type in the fault record information.

[0144] It should be noted that the risk weight can be the degree of importance of the fault type, and the monitoring equipment can set the risk weight based on the frequency of occurrence of the fault factor and the severity of the hazard.

[0145] Step S207: construct a risk knowledge graph of the source-load-storage network based on the risk weights, the common fault types and the rare fault types.

[0146] It is understandable that the monitoring equipment can perform probabilistic fuzzy processing on the risk weights, assign correlation algorithms to the processed risk weights, and build a risk knowledge graph for the source-load-storage network in combination with common fault types and rare fault types.

[0147] Furthermore, in order to discover rare but serious faults to increase the attention paid to such faults, thereby effectively avoiding the situation where large-scale disasters are ignored, the above step S207 may include:

[0148] Step S2071: Perform feature analysis on the target risk data to obtain discrete feature information and continuous feature information.

[0149] It should be noted that discrete feature information may be feature information of a transient state, such as animal activities, etc. The above-mentioned continuous feature information may be feature information of a persistent and continuous state, such as continuous data such as wind speed and rainfall, which are continuous features.

[0150] Step S2072: Determine a state fuzzy score based on the discrete feature information and the continuous feature information.

[0151] It should be noted that in the source-load-storage-grid power system, the impact of multiple continuous characteristics needs to be considered. For example, in windy weather, tree branches fall on the line and cause phase-to-phase short circuits. In rainy periods, branches may burn and fall in a humid environment, making it difficult to continue burning. After the line is automatically reclosed, power can be supplied normally. However, if the ground is covered with a lot of dry humus in autumn, the burned branches may cause larger wildfires and cause large-scale faults. The state fuzzy score is to find the causes that will cause greater disasters when they occur at the same time.

[0152] In a specific implementation, the monitoring device may set a higher risk score for continuous features and a lower risk score for discrete features. For example, the higher the continuous features such as wind speed and rainfall, the higher the corresponding risk score.

[0153] Step S2073: mining high-risk rare types from the common fault types and the rare fault types according to the state fuzzy score;

[0154] Step S2074: performing correlation analysis on the common fault type, the rare fault type and the high-risk rare type to obtain a correlation amplitude;

[0155] Step S2075: Correcting the risk weight based on the correlation amplitude;

[0156] Step S2076: Construct a risk knowledge graph of the source-load-storage network based on the corrected risk weights, the common fault types, the rare fault types and the high-risk rare types.

[0157] It should be noted that high-risk and rare types can be fault types that occur infrequently but cause serious damage, such as volcanic eruptions and lightning wildfires. For the wildfire fault factor, it may be caused by the combination of strong winds and the distance between trees along the line. Compared with the previous understanding that lightning strikes the forest and causes wildfires, this situation is more likely and should be taken more seriously.

[0158] It is understandable that since high-risk and rare types of failures occur less frequently, the initially set weight may be smaller. In order to increase the importance of such failures, the risk weight of high-risk and rare types of failure factors may be corrected to increase the importance.

[0159] This embodiment obtains fault record information of the source-load-storage network, obtains common fault types and rare fault types based on the fault record information, determines the mode value and the minimum value in the target risk data, sets the first initial threshold value of the common fault type based on the mode value, and sets the second initial threshold value of the rare fault type based on the minimum value, optimizes the first initial threshold value and the second initial threshold value according to historical risk prediction information to obtain the target threshold value, determines the risk weight based on the target threshold value and the frequency of occurrence of each fault type in the fault record information, and constructs a risk knowledge graph of the source-load-storage network based on the risk weight, the common fault types and the rare fault types. This embodiment classifies the faults of the source-load-storage network and builds a risk knowledge graph based on sky-ground data, thereby realizing hierarchical diagnosis and treatment of the power system of the source-load-storage network, providing effective data support for risk prediction and risk monitoring of the power system, and improving the efficiency of risk monitoring.

[0160] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a risk monitoring program for a source-load-storage network is stored. When the risk monitoring program for the source-load-storage network is executed by a processor, the steps of the risk monitoring method for the source-load-storage network described above are implemented.

[0161] 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.

[0162] The computer-readable storage medium may be included in the risk monitoring device of the source-load-storage network; or may exist independently without being assembled into the risk monitoring device of the source-load-storage network.

[0163] In addition, an embodiment of the present invention further proposes a computer program product, including a risk monitoring program for a source-load-storage network, which implements the steps of the risk monitoring method for a source-load-storage network as described above when executed by a processor.

[0164] The specific implementation methods of the computer program product of the present invention are basically the same as the various embodiments of the risk monitoring method for the source-load-storage network described above, and will not be described in detail here.

[0165] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the risk monitoring device for the source-load-storage network of the present invention.

[0166] like Figure 5 As shown, the risk monitoring device of the source-load-storage network proposed in the embodiment of the present invention is connected to the sky-ground system in communication, and the sky-ground system includes a space-based module, an air-based module and a ground-based module. The risk monitoring device of the source-load-storage network includes:

[0167] A data processing module 10 is used to obtain the accident monitoring data of the air-ground system and pre-process the accident monitoring data to obtain target risk data;

[0168] A graph construction module 20, for constructing a risk knowledge graph of the source-load-storage network based on the target risk data, wherein the risk knowledge graph includes risk entities and risk relationships of each risk entity, wherein the risk entity is a fault type of the source-load-storage network, and the risk relationship is a risk weight corresponding to each fault type;

[0169] The association analysis module 30 is used to obtain the fault factors of the source-load-storage network and analyze the association information between the fault factors and the risk knowledge graph;

[0170] A model building module 40, for building a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity;

[0171] The risk analysis module 50 is used to input the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and to perform risk monitoring on the source-load-storage network based on the risk analysis results.

[0172] Furthermore, the graph construction module 20 is also used to obtain fault record information of the source-load-storage network; obtain common fault types and rare fault types based on the fault record information; determine the mode value and the minimum value in the target risk data; set the first initial threshold value of the common fault type based on the mode value, and set the second initial threshold value of the rare fault type based on the minimum value; optimize the first initial threshold value and the second initial threshold value according to historical risk prediction information to obtain a target threshold value; determine the risk weight based on the target threshold value and the frequency of occurrence of each fault type in the fault record information; and construct a risk knowledge graph of the source-load-storage network based on the risk weight, the common fault types and the rare fault types.

[0173] Furthermore, the graph construction module 20 is also used to perform feature analysis on the target risk data to obtain discrete feature information and continuous feature information; determine a state fuzzy score based on the discrete feature information and the continuous feature information; mine high-risk rare types from the common fault types and the rare fault types according to the state fuzzy score; perform correlation analysis on the common fault types, the rare fault types and the high-risk rare types to obtain correlation amplitudes; correct the risk weights based on the correlation amplitudes; and construct a risk knowledge graph of the source-load-storage network based on the corrected risk weights, the common fault types, the rare fault types and the high-risk rare types.

[0174] Furthermore, the model building module 40 is also used to determine the disaster severity coefficient of each risk entity based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity; and to build a defect propagation model according to the severity coefficient and the risk knowledge graph, wherein the defect propagation model is:

[0175]

[0176] in, is the input database containing m fault records, Indicates input database The Fault records, Represents the fault record index, Represents an environmental feature , represent The cardinality of all fault records in Indicates The first environmental feature A value.

[0177] Furthermore, the data processing module 10 is also used to obtain risk history data and risk experience data; divide the accident monitoring data into risk stages based on the risk history data and the risk experience data to obtain risk level data of each power terminal in the source-load-storage network; perform risk superposition assessment based on the risk level data to obtain candidate risk data of the source-load-storage network; and identify abnormal data in the candidate risk data:

[0178]

[0179] in, is the value of the data point to be detected in the candidate risk data, is the average value of the candidate risk data, is the standard deviation of the candidate risk data, is the number of standard deviations of the value of the data point to be detected in the candidate risk data from the mean value, and the data points in the candidate risk data whose standard deviation exceeds the preset range are determined to be abnormal data;

[0180] The abnormal data is cleaned, and the missing data in the cleaned candidate risk data is filled to obtain the target risk data:

[0181]

[0182] in, represents the target risk data obtained after filling in the missing data, is the time node, and Indicates the load weighting coefficient of two time nodes two days before and after. Indicates the monitoring data recorded in the last hour. Indicates the monitoring data recorded in the previous hour. Indicates the monitoring data recorded in the last 12 hours. Indicates the monitoring data recorded in the previous 12 hours. Indicates the monitoring data recorded in the last 24 hours. Indicates the monitoring data recorded in the previous 24 hours.

[0183] Furthermore, the real-time monitoring data includes multi-dimensional heterogeneous image data of the sky-ground system; the data processing module 10 is also used to obtain the monitoring data collected by each module in the sky-ground system, and the monitoring data includes sensor monitoring data collected by the ground-based module, image monitoring data collected by the air-based module and remote sensing monitoring data collected by the space-based module; the monitoring data is preprocessed, and the preprocessing includes data synchronization processing and data standardization processing; weight analysis is performed on the preprocessed monitoring data to determine the data weight of each monitoring data; data fusion is performed based on the data weight and the pixel information of each preprocessed monitoring data to obtain the multi-dimensional heterogeneous image data of the sky-ground system.

[0184] This embodiment obtains target risk data by acquiring accident monitoring data of the sky-ground system and preprocessing the accident monitoring data; constructs a risk knowledge graph of the source-load-storage network based on the target risk data, the risk knowledge graph includes risk entities and risk relationships of each risk entity, the risk entity is the fault type of the source-load-storage network, and the risk relationship is the risk weight corresponding to each fault type; obtains the fault factor of the source-load-storage network, and analyzes the association information between the fault factor and the risk knowledge graph; constructs a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity; inputs the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and performs risk monitoring on the source-load-storage network based on the risk analysis results, realizes effective analysis of the multidimensional data of the sky-ground system in the time dimension and the space dimension, realizes efficient use of the multidimensional data of the sky-ground system, fully mines the relationship between faults in combination with the knowledge graph, and performs risk analysis on the source-load-storage network through the trap propagation model, effectively improves the accuracy and efficiency of risk disaster prediction, ensures timely discovery of power risks and power disasters, and ensures stable operation of the power system.

[0185] The risk monitoring device for the source-load-storage network provided by the present application adopts the risk monitoring method for the source-load-storage network in the above-mentioned embodiment, which can solve the technical problem of risk monitoring of the source-load-storage network. Compared with the prior art, the beneficial effects of the risk monitoring device for the source-load-storage network provided by the present application are the same as the beneficial effects of the risk monitoring method for the source-load-storage network provided by the above-mentioned embodiment, and the other technical features in the risk monitoring device for the source-load-storage network are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0186] 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.

[0187] 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.

[0188] In addition, for technical details not fully described in this embodiment, reference may be made to the risk monitoring method for the source-load-storage network provided in any embodiment of the present invention, and will not be repeated here.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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 risk monitoring method for a source-load-storage network, characterized in that: The risk monitoring method of the source-load-storage network is applied to a terminal device, the terminal device is communicatively connected with a sky-ground system, the sky-ground system includes a space-based module, an air-based module and a ground-based module, and the risk monitoring method of the source-load-storage network includes: Acquiring accident monitoring data of the air-ground system, and preprocessing the accident monitoring data to obtain target risk data; Constructing a risk knowledge graph of the source-load-storage network based on the target risk data, wherein the risk knowledge graph includes risk entities and risk relationships of each risk entity, wherein the risk entity is a fault type of the source-load-storage network, and the risk relationship is a risk weight corresponding to each fault type; Obtaining the failure factors of the source-load-storage network, and analyzing the association information between the failure factors and the risk knowledge graph; Building a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity; Inputting the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and performing risk monitoring on the source-load-storage network based on the risk analysis results; The step of constructing a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity includes: Determine the disaster severity coefficient of each risk entity based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity; A defect propagation model is constructed according to the severity coefficient and the risk knowledge graph, and the defect propagation model is: ； in, is the input database containing m fault records, Indicates input database The Fault records, Represents the fault record index, Represents an environmental feature , represent The cardinality of all fault records in Indicates The first environmental feature A value; The severity coefficient is used to indicate the intensity of the effects of various fault factors that affect the occurrence of power system disasters in the source-load-storage-grid risk situation when disasters occur; the severity coefficient is an indicator for measuring the intensity of the relationship between fault factors and disaster occurrence in the defect propagation model.

2. The risk monitoring method for source-load-storage network according to claim 1, characterized in that: The risk knowledge graph of the source-load-storage network is constructed based on the target risk data, including: Obtain fault record information of source, load and storage network; Acquire common fault types and rare fault types based on the fault record information; Determining a mode value and a minimum value in the target risk data; Setting a first initial threshold value for the common fault type based on the mode value, and setting a second initial threshold value for the rare fault type based on the minimum value; Optimizing the first initial threshold and the second initial threshold according to historical risk prediction information to obtain a target threshold; Determine a risk weight based on the target threshold and the occurrence frequency of each fault type in the fault record information; A risk knowledge graph of the source-load-storage network is constructed based on the risk weights, the common fault types and the rare fault types.

3. The risk monitoring method for source-load-storage network according to claim 2, characterized in that: The risk knowledge graph of the source-load-storage network is constructed based on the risk weight, the common fault types and the rare fault types, including: Performing feature analysis on the target risk data to obtain discrete feature information and continuous feature information; Determine a state fuzzy score based on the discrete feature information and the continuous feature information; mining high-risk rare types from the common fault types and the rare fault types according to the state fuzzy scores; Performing correlation analysis on the common fault type, the rare fault type and the high-risk rare type to obtain a correlation amplitude; Correcting the risk weight based on the correlation magnitude; A risk knowledge graph of the source-load-storage network is constructed based on the corrected risk weights, the common fault types, the rare fault types and the high-risk rare types.

4. The risk monitoring method for a source-load-storage network according to any one of claims 1 to 3, characterized in that: The acquiring the accident monitoring data of the air-ground system and preprocessing the accident monitoring data to obtain target risk data includes: Obtain risk history data and risk experience data; Based on the risk history data and the risk experience data, the accident monitoring data is divided into risk stages to obtain risk level data of each power terminal in the source-load-storage network; Perform risk superposition assessment according to the risk level data to obtain candidate risk data of the source-load-storage-grid; Identify abnormal data in the candidate risk data: ； in, is the value of the data point to be detected in the candidate risk data, is the average value of the candidate risk data, is the standard deviation of the candidate risk data, is the number of standard deviations of the value of the data point to be detected in the candidate risk data from the mean value, and the data points in the candidate risk data whose standard deviation exceeds the preset range are determined to be abnormal data; The abnormal data is cleaned, and the missing data in the cleaned candidate risk data is filled to obtain the target risk data: ； in, represents the target risk data obtained after filling in the missing data, is the time node, and Indicates the load weighting coefficient of two time nodes two days before and after. Indicates the monitoring data recorded in the last hour. Indicates the monitoring data recorded in the previous hour. Indicates the monitoring data recorded in the last 12 hours. Indicates the monitoring data recorded in the previous 12 hours. Indicates the monitoring data recorded in the last 24 hours. Indicates the monitoring data recorded in the previous 24 hours.

5. The risk monitoring method for a source-load-storage network according to any one of claims 1 to 3, characterized in that: The real-time monitoring data includes multi-dimensional heterogeneous image data of the sky-ground system; before the real-time monitoring data of the source-load-storage network collected by the sky-ground system is input into the defect propagation model for risk analysis, it also includes: Acquire monitoring data collected by each module in the sky-ground system, wherein the monitoring data includes sensor monitoring data collected by the ground-based module, image monitoring data collected by the air-based module, and remote sensing monitoring data collected by the space-based module; Preprocessing the monitoring data, wherein the preprocessing includes data synchronization processing and data standardization processing; Perform weight analysis on the pre-processed monitoring data to determine the data weight of each monitoring data; Data fusion is performed based on the data weights and the pixel information of each preprocessed monitoring data to obtain multi-dimensional heterogeneous image data of the sky-ground system.

6. A risk monitoring device for a source-load-storage network, characterized in that: The device is connected to the sky-ground system in communication, the sky-ground system includes a space-based module, an air-based module and a ground-based module, and the risk monitoring device of the source-load-storage network includes: A data processing module, used to obtain the accident monitoring data of the air-ground system, and pre-process the accident monitoring data to obtain target risk data; A graph construction module, for constructing a risk knowledge graph of the source-load-storage network based on the target risk data, wherein the risk knowledge graph includes risk entities and risk relationships of each risk entity, wherein the risk entity is a fault type of the source-load-storage network, and the risk relationship is a risk weight corresponding to each fault type; An association analysis module, used to obtain the fault factors of the source-load-storage network and analyze the association information between the fault factors and the risk knowledge graph; A model building module, used to build a defect propagation model based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity; A risk analysis module, used for inputting the real-time monitoring data of the source-load-storage network collected by the sky-ground system into the defect propagation model for risk analysis, and performing risk monitoring on the source-load-storage network based on the risk analysis results; The model building module is further used to determine the disaster severity coefficient of each risk entity based on the association information and the environmental characteristic information and seasonal characteristic information of each risk entity; A defect propagation model is constructed according to the severity coefficient and the risk knowledge graph, and the defect propagation model is: ； in, is the input database containing m fault records, Indicates input database The Fault records, Represents the fault record index, Represents an environmental feature , represent The cardinality of all fault records in Indicates The first environmental feature A value; The severity coefficient is used to indicate the intensity of the effects of various fault factors that affect the occurrence of power system disasters in the source-load-storage-grid risk situation when disasters occur; the severity coefficient is an indicator for measuring the intensity of the relationship between fault factors and disaster occurrence in the defect propagation model.

7. A risk monitoring device for a source-load-storage network, characterized in that: The risk monitoring device of the source-load-storage network includes: a memory, a processor, and a risk monitoring program of the source-load-storage network stored in the memory and executable on the processor. The risk monitoring program of the source-load-storage network is configured to implement the risk monitoring method of the source-load-storage network as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a risk monitoring program for a source-load-storage network. When the risk monitoring program for a source-load-storage network is executed by a processor, the risk monitoring method for a source-load-storage network as claimed in any one of claims 1 to 5 is implemented.

9. A computer program product, characterized in that The computer program product comprises a risk monitoring program for a source-load-storage network, and when the risk monitoring program for a source-load-storage network is executed by a processor, the steps of the risk monitoring method for a source-load-storage network as claimed in any one of claims 1 to 5 are implemented.

Images