Angle-based risk anomaly identification and quantitative characterization method for satellite-ground integrated distribution system and related devices

Abstract

The present invention discloses a method for identifying and quantifying the risk anomalies of a satellite-ground integrated power distribution system based on an angle and a related device. The method comprises: obtaining operating parameters of each node in the satellite-ground integrated power distribution system, preprocessing the operating parameters, obtaining multidimensional feature data of each node, and constructing a risk feature data set based on the multidimensional feature data, the multidimensional feature data comprising power feature data and communication feature data, constructing an angle spectrum of each node based on the risk feature data set, the angle spectrum comprising angle parameters between each node and other nodes in the satellite-ground integrated power distribution system; identifying abnormal nodes in the nodes based on the angle spectrum; generating a risk heat map of the satellite-ground integrated power distribution system according to the angle spectrum and the abnormal nodes, accurately detecting abnormal nodes based on power and communication heterogeneous data, realizing quantitative characterization of system risks, and ensuring the safe operation of the satellite-ground integrated power distribution system.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution systems, and in particular to an angle-based method for identifying and quantifying risk anomalies in a satellite-ground integrated power distribution system and related devices. Background Art

[0002] With the rapid development of distributed renewable energy, the distribution system has undergone new changes compared with the traditional distribution system, forming new features of active distribution side, diversified power supply mode and informationization of power network. The access of high proportion of new energy generation and high proportion of power electronic devices has led to a decrease in the overall inertia of the distribution system, which has further reduced its safe and stable operation capability. At the same time, as a typical information-physical system, after combining with network communication, due to the complexity and openness of network communication, the distribution system will face information security challenges such as blurred and weakened network security boundaries, and the access of massive digital devices leading to complex and widespread types of network attacks. Therefore, the distribution system faces more complex physical information risk threats. These risk threats include not only risk threats in the traditional electrical field, but also risks in the information field such as cyber attacks and signal interference, which will cause the distribution system to deviate from normal operation and affect the safe operation of the distribution system. Traditional anomaly detection methods cannot cope with the massive power and non-power heterogeneous data in the satellite-ground integrated distribution system, and cannot accurately identify system anomalies. Therefore, they cannot effectively quantify and characterize system risks, resulting in huge safety hazards in the distribution system. Summary of the invention

[0003] The main purpose of the present invention is to provide an angle-based method for identifying and quantitatively characterizing risk anomalies in a satellite-ground integrated distribution system and related devices, aiming to solve the technical problem that the existing technology is unable to cope with the massive power and non-power heterogeneous data in the satellite-ground integrated distribution system, and is unable to accurately identify system anomalies, and therefore is unable to effectively quantify and characterize system risks, resulting in huge safety hazards in the distribution system.

[0004] To achieve the above object, the present invention provides an angle-based method for identifying and quantifying risk anomalies in a satellite-ground integrated power distribution system, the method comprising the following steps:

[0005] Acquire operating parameters of each node in the satellite-ground integrated power distribution system, wherein the operating parameters include power operating parameters and communication operating parameters;

[0006] Preprocessing the operating parameters to obtain multidimensional feature data of each node, and constructing a risk feature data set based on the multidimensional feature data, wherein the multidimensional feature data includes power feature data and communication feature data, and the risk feature data set includes a state point corresponding to each node, and the state point is a feature state corresponding to the node;

[0007] Constructing an angle spectrum of each node based on the risk characteristic data set, wherein the angle spectrum includes angle parameters between each node and other nodes in the satellite-ground integrated power distribution system;

[0008] identifying abnormal nodes among the nodes based on the angle spectrum;

[0009] A risk heat map of the satellite-ground integrated power distribution system is generated according to the angle spectrum and the abnormal nodes.

[0010] Optionally, constructing the angle spectrum of each node based on the risk feature data set includes:

[0011] Generate a point vector corresponding to each node based on the risk feature data set;

[0012] Determine the difference vector between each node according to the point vector:

[0013] ;

[0014] in, are the state points in the risk feature dataset respectively. The corresponding point vector, Status points and Difference vector of a pair of points;

[0015] Calculate the angle parameters between the nodes based on the difference vector:

[0016] ;

[0017] in, is the angle parameter, For vector The Euclidean norm of is the dot product of the vectors;

[0018] The angle spectrum of each node is constructed according to the angle parameters between each node.

[0019] Optionally, the identifying abnormal nodes among the nodes based on the angle spectrum includes:

[0020] Perform discrete analysis on the angle spectrum of each node to obtain the angle discrete distribution information of the angle spectrum of each node;

[0021] Determine the degree of angle change of the angle spectrum of each node according to the angle discrete distribution information;

[0022] Acquire an angle anomaly identification condition, wherein the angle anomaly identification condition includes that an angle change degree of the angle spectrum of the node is less than an angle change degree of the angle spectrum of the boundary point;

[0023] Abnormal nodes among the nodes are identified according to the angle anomaly identification condition and the degree of angle change of the angle spectrum of each node.

[0024] Optionally, generating a risk heat map of the satellite-ground integrated power distribution system according to the angle spectrum and the abnormal node includes:

[0025] Calculate the outlier factor value corresponding to each node based on the angle spectrum:

[0026] ;

[0027] in, are the state points in the risk feature dataset respectively. The corresponding point vector, Represents the risk feature data set except for the state point All point pairs of all state points except Status points and The difference vector of the point pair, is the state point in the risk feature dataset The outlier factor value of represents variance;

[0028] Generate an abnormal quantification result of the satellite-ground integrated power distribution system according to the outlier factor value corresponding to each node and the abnormal node;

[0029] A risk heat map of the satellite-ground integrated power distribution system is generated based on the abnormal quantification result.

[0030] Optionally, generating a risk heat map of the satellite-ground integrated power distribution system based on the abnormal quantification result includes:

[0031] quantifying the abnormal degree of the abnormal node based on the outlier factor value, and obtaining an abnormal state parameter of the abnormal node;

[0032] Acquiring spatiotemporal characteristic information of each node according to the risk characteristic data set;

[0033] Match the spatiotemporal characteristic information of each node with the outlier factor value corresponding to each node to obtain the risk status parameter of each node;

[0034] A risk heat map of the satellite-ground integrated power distribution system is generated based on the abnormal state parameters of the abnormal nodes and the risk state parameters of each node.

[0035] Optionally, preprocessing the operating parameters to obtain multidimensional feature data of each node, and constructing a risk feature data set based on the multidimensional feature data includes:

[0036] Performing characteristic analysis on the operating parameters to obtain original power characteristic data and original communication operating characteristic data;

[0037] Acquire status data of each node in the satellite-ground integrated power distribution system, wherein the status data includes time status information and space status information;

[0038] Based on the state data, the original power characteristic data and the original communication operation characteristic data are synchronously processed to obtain multi-dimensional characteristic data of each node, wherein the synchronization processing includes time synchronization processing and space synchronization processing;

[0039] The multidimensional feature data is normalized, and a risk feature data set is constructed based on the normalized multidimensional feature data.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also proposes an angle-based risk anomaly identification and quantitative characterization device for a satellite-ground integrated power distribution system, and the angle-based risk anomaly identification and quantitative characterization device for a satellite-ground integrated power distribution system comprises:

[0041] A data acquisition module is used to acquire the operating parameters of each node in the satellite-ground integrated power distribution system, wherein the operating parameters include power operating parameters and communication operating parameters;

[0042] a data processing module, configured to pre-process the operating parameters, obtain multi-dimensional feature data of each node, and construct a risk feature data set based on the multi-dimensional feature data, wherein the multi-dimensional feature data includes power feature data and communication feature data, and the risk feature data set includes a state point corresponding to each node, wherein the state point is a feature state corresponding to the node;

[0043] An angle calculation module, used to construct an angle spectrum of each node based on the risk characteristic data set, wherein the angle spectrum includes angle parameters between each node and other nodes in the satellite-ground integrated power distribution system;

[0044] An abnormality identification module, used for identifying abnormal nodes among the nodes based on the angle spectrum;

[0045] An abnormal characterization module is used to generate a risk heat map of the satellite-ground integrated power distribution system according to the angle spectrum and the abnormal nodes.

[0046] In addition, to achieve the above-mentioned objectives, the present application also proposes an angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization device, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization method as described above.

[0047] 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 angle-based satellite-ground integrated distribution system risk anomaly identification and quantitative characterization method are implemented as described above.

[0048] 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 angle-based satellite-ground integrated distribution system risk anomaly identification and quantitative characterization method as described above.

[0049] The present invention obtains the operating parameters of each node in the satellite-ground fusion distribution system, wherein the operating parameters include power operating parameters and communication operating parameters, pre-processes the operating parameters, obtains multidimensional feature data of each node, and constructs a risk feature data set based on the multidimensional feature data, wherein the multidimensional feature data includes power feature data and communication feature data, and the risk feature data set includes a state point corresponding to each node, wherein the state point is a feature state corresponding to the node, and constructs an angle spectrum of each node based on the risk feature data set, wherein the angle spectrum includes angle parameters between each node and other nodes in the satellite-ground fusion distribution system, identifies abnormal nodes in the nodes based on the angle spectrum, and generates a risk heat map of the satellite-ground fusion distribution system according to the angle spectrum and the abnormal nodes, thereby effectively analyzing the power operating parameters and communication operating parameters of each node in the system, accurately detecting abnormal nodes based on power and communication heterogeneous data, significantly improving the efficiency of risk anomaly identification in the satellite-ground fusion distribution system, realizing quantitative characterization of system risks, and ensuring the safe operation of the satellite-ground fusion distribution system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] 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.

[0051] 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.

[0052] Figure 1 It is a structural schematic diagram of an angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization device in a hardware operating environment involved in an embodiment of the present invention;

[0053] Figure 2It is a flow chart of the first embodiment of the angle-based risk anomaly identification and quantitative characterization method for satellite-ground integrated power distribution system of the present invention;

[0054] Figure 3 It is a schematic diagram of a scenario of a satellite-ground integrated power distribution system in an embodiment of a method for identifying and quantifying risk anomalies of a satellite-ground integrated power distribution system based on angles of the present invention;

[0055] Figure 4 It is a schematic diagram of the data processing flow in an embodiment of the method for identifying and quantifying risk anomalies of a satellite-ground integrated power distribution system based on angles of the present invention;

[0056] Figure 5 It is a schematic diagram of the process of constructing an angle spectrum in an embodiment of the angle-based method for identifying and quantifying risk anomalies in a satellite-ground integrated power distribution system of the present invention;

[0057] Figure 6 It is a schematic diagram of a process of identifying abnormal nodes in an embodiment of a method for identifying and quantifying risk anomalies in a satellite-ground integrated power distribution system based on angles of the present invention;

[0058] Figure 7 It is a schematic diagram of the abnormality quantification characterization process in an embodiment of the method for identifying and quantifying the risk abnormality of a satellite-ground integrated power distribution system based on angles of the present invention;

[0059] Figure 8 It is a structural block diagram of the first embodiment of the angle-based risk anomaly identification and quantitative characterization device for the satellite-ground integrated power distribution system of the present invention.

[0060] 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

[0061] 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.

[0062] Reference Figure 1 , Figure 1 It is a schematic diagram of the structure of an angle-based device for identifying and quantitatively characterizing risk anomalies in a satellite-ground integrated power distribution system in the hardware operating environment involved in an embodiment of the present invention.

[0063] like Figure 1As shown, the angle-based satellite-ground integrated distribution system risk anomaly identification and quantitative characterization device 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.

[0064] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the angle-based satellite-ground integrated distribution system risk anomaly identification and quantitative characterization device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0065] 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 an angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization program.

[0066] exist Figure 1 In the angle-based satellite-ground fusion distribution system risk anomaly identification and quantitative characterization device 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 angle-based satellite-ground fusion distribution system risk anomaly identification and quantitative characterization device of the present invention can be set in the angle-based satellite-ground fusion distribution system risk anomaly identification and quantitative characterization device, and the angle-based satellite-ground fusion distribution system risk anomaly identification and quantitative characterization device calls the angle-based satellite-ground fusion distribution system risk anomaly identification and quantitative characterization program stored in the memory 1005 through the processor 1001, and executes the angle-based satellite-ground fusion distribution system risk anomaly identification and quantitative characterization method provided in the embodiment of the present invention.

[0067] The embodiment of the present invention provides a method for identifying and quantifying risk anomalies in a satellite-ground integrated power distribution system based on an angle, referring to Figure 2 , Figure 2 It is a flow chart of the first embodiment of the angle-based risk anomaly identification and quantitative characterization method for the satellite-ground integrated power distribution system of the present invention.

[0068] In this embodiment, the angle-based method for identifying and quantifying risk anomalies in a satellite-ground integrated power distribution system includes the following steps:

[0069] Step S10: Obtain the operating parameters of each node in the satellite-ground integrated power distribution system.

[0070] It should be noted that this embodiment can be applied to the satellite-ground fusion power distribution system. By combining the satellite module with the ground module in the satellite-ground fusion network, the risk feature perception of the information-physical unification and spatial-temporal coordination in the satellite-ground fusion power distribution system can be realized. Figure 3 , Figure 3 The schematic diagram of the satellite-ground integrated power distribution system scenario in one embodiment, in which the power distribution system realizes mutual communication between the satellite module and the ground module through satellite Internet. Among them, the satellite module is mainly composed of satellite communication nodes, satellite communication links and other parts, and the ground module includes electrical equipment such as smart sensors, smart meters, and side smart units in the power distribution system, as well as ground base stations in the satellite-ground integrated network, satellite ground terminals and other communication equipment. By combining the above modules, the mutual complementation of information-physical multi-dimensional data and the coordination of multi-source data at different time and space scales can be achieved, thereby constructing a risk feature perception system for the satellite-ground integrated power distribution system.

[0071] It should be noted that under the satellite-ground integrated distribution system, the existing overall risk anomaly identification and quantitative characterization is to identify and quantify the current system risk status in order to reduce the impact of comprehensive risks such as electrical equipment failure and network attacks on the distribution system, but there are still certain limitations: with the addition of the information layer, the data dimension of the distribution system operation increases, and the recognition effect of using distance to judge abnormal points gradually weakens, making it difficult to accurately identify abnormal data points; the quantification of abnormal states is not specific, the characterization method is not obvious, and it is difficult to intuitively represent the risk abnormal state of the system; the identification of coupling factors such as power and non-power is unclear, and it fails to comprehensively consider multi-level risk factors such as power and information.

[0072] It should be understood 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 computer, or a terminal electronic device capable of realizing the above functions. The following takes the angle-based satellite-ground integrated distribution system risk anomaly identification and quantitative characterization device (referred to as the terminal device) as an example to illustrate this embodiment and the following embodiments.

[0073] It should be noted that the satellite-ground fusion network can provide a comprehensive state perception method for the highly distributed, source-load bidirectional linkage, and multiple energy forms coexisting distribution system with its wide-area, all-time, high-reliability, and wide-coverage communication services. When the power system and the information system are deeply coupled, the risks come not only from traditional power equipment failures and line damage, but also from information risk sources such as network attacks, data anomalies, and communication delays. At this time, the system risk is induced by the interaction of the power-information integrated system, and has the characteristics of physical information risk coupling and chain, complex data types, and large dimensions.

[0074] In some embodiments, the terminal device can collect the operating parameters of each node through the satellite module and the ground module. The satellite module is mainly composed of satellite communication nodes, satellite communication links and other parts. The ground module includes electrical equipment such as smart sensors, smart meters, and side smart units in the distribution system, as well as ground base stations in the satellite-ground fusion network, satellite ground terminals and other communication equipment. By combining the above modules, the information-physical multi-dimensional data can be complemented with each other, and the multi-source data can be coordinated at different time and space scales, thereby building a risk feature perception system for the satellite-ground fusion distribution system.

[0075] It should be noted that the operating parameters include power operating parameters and communication operating parameters. The power operating parameters may include power data such as node voltage, current phasor, frequency offset, power generation, load power, etc. The communication operating parameters may include satellite-ground fusion network information data such as node network traffic, communication bandwidth and latency, and satellite communication service quality QoS.

[0076] In some embodiments, the terminal device can collect the power operation parameters of each node in the distribution system through measurement tools such as phasor measurement units, smart sensors, voltage and current transformers in the distribution network, and obtain the communication operation parameters of each node through satellite platforms, satellite computer payloads, ground base stations, etc.

[0077] Step S20: pre-processing the operating parameters, acquiring multi-dimensional feature data of each node, and constructing a risk feature data set based on the multi-dimensional feature data.

[0078] It should be noted that the multi-dimensional feature data includes power feature data and communication feature data, and the risk feature data set includes a state point corresponding to each node, and the state point is a feature state corresponding to the node.

[0079] In a specific implementation, preprocessing may include data cleaning, abnormal data identification, abnormal data elimination, missing data filling, feature extraction and normalization processing, etc.

[0080] In some embodiments, after the terminal device obtains the operating parameters at the power and communication levels in the satellite-ground integrated power distribution system, the z-score method can be used to normalize the operating parameters to eliminate the influence of different dimensions on the recognition effect.

[0081] Furthermore, in order to improve data quality and data analysis efficiency, refer to Figure 4 , Figure 4 This is a schematic diagram of a data processing flow in an embodiment. The above step S20 may include:

[0082] Step S201: performing characteristic analysis on the operating parameters to obtain original power characteristic data and original communication operation characteristic data;

[0083] Step S202: Acquire status data of each node in the satellite-ground integrated power distribution system;

[0084] Step S203: Synchronously process the original power characteristic data and the original communication operation characteristic data based on the state data to obtain multi-dimensional characteristic data of each node;

[0085] Step S204: normalizing the multidimensional feature data, and constructing a risk feature data set based on the normalized multidimensional feature data.

[0086] It should be noted that the state data includes time state information and space state information. The synchronization process includes time synchronization process and space synchronization process.

[0087] In some embodiments, the terminal device may use a z-score method to normalize the multi-dimensional feature data to eliminate the influence of different dimensions on the recognition effect.

[0088] It should be noted that for a certain moment in the satellite-ground integrated power distribution system No. nodes, the terminal device can combine the electrical and non-electrical characteristic parameters corresponding to each node into one dimensional feature vector: ,in is the characteristic dimension.

[0089] At the same time, the status data of all nodes in the satellite-ground integrated power distribution system within a time series is collected to form feature data sets in different time and space dimensions in the satellite-ground integrated power distribution system:

[0090] ;

[0091] in, is the number of nodes, Based on this, a risk feature data set of the power and communication dimension (i.e., the power-information dimension) is formed, which is used in the subsequent angle-based anomaly identification to identify abnormal operation nodes in the satellite-ground integrated distribution system.

[0092] Step S30: constructing an angle spectrum of each node based on the risk feature data set.

[0093] It should be noted that the angle spectrum includes angle parameters between each node and other nodes in the satellite-ground integrated power distribution system.

[0094] It can be understood that this embodiment calculates the angle parameters between each node and other nodes in the power distribution system, and constructs the angle spectrum of the point based on the calculated angle set between each state point and all other point pairs in the characteristic data set.

[0095] Furthermore, in order to accurately construct the angle spectrum of each node, refer to Figure 5 , Figure 5 The flowchart of constructing an angle spectrum in one embodiment is shown in FIG. 1 . The step S30 may include:

[0096] Step S301: generating a point vector corresponding to each node based on the risk feature data set;

[0097] Step S302: determining the difference vector between each node according to the point vector;

[0098] Step S303: Calculating angle parameters between nodes based on the difference vector;

[0099] Step S304: constructing the angle spectrum of each node according to the angle parameters between each node.

[0100] It should be noted that this embodiment can construct the difference vector between all state points with all the data in the risk feature data set, and use the difference vector in the feature data set to expand the angle calculation between each point and all other point pairs. The cosine value of the angle formed by a point and other point pairs is calculated by the dot multiplication of the vector and the Euclidean norm of the vector itself, and then the angle between the point and all other point pairs is obtained. Based on the calculated angle set of each state point and all other point pairs in the risk feature data set, the angle spectrum of the point is constructed, and then the angle spectrum of all state points in the feature data set is constructed.

[0101] The difference vector is calculated according to the following formula:

[0102] ;

[0103] in, are the state points in the risk feature dataset respectively. The corresponding point vector, Status points and Difference vector of a pair of points.

[0104] It should be noted that the angle parameter calculation refers to the following formula:

[0105] ;

[0106] in, is the angle parameter, For vector The Euclidean norm of is the dot product of the vectors.

[0107] Step S40: identifying abnormal nodes among the nodes based on the angle spectrum.

[0108] It can be understood that this embodiment can identify data anomaly points in the risk feature data set based on the rules of angle anomaly identification. For example, the state points whose angle sizes in the angle spectrum tend to be basically consistent are determined as abnormal nodes.

[0109] It should be noted that this embodiment uses an angle-based anomaly identification method to identify anomalies in the states of each node in the satellite-ground integrated power distribution system. For the multi-dimensional power and non-power characteristic parameters in the satellite-ground integrated power distribution system, the angle calculation of different state points in the dimensional space is carried out, and the angle spectrum of each point of the system state under different time and space states is constructed according to the calculation results. At the same time, the boundaries of the normal state clusters of the system are divided to achieve qualitative division of abnormal state points and identify the risk states of different nodes in the system.

[0110] Furthermore, in order to accurately identify abnormal nodes, refer to Figure 6 , Figure 6 This is a flow chart of identifying abnormal nodes in an embodiment. The above step S40 may include:

[0111] Step S401: performing discrete analysis on the angle spectrum of each node to obtain angle discrete distribution information of the angle spectrum of each node;

[0112] Step S402: determining the angle variation degree of the angle spectrum of each node according to the angle discrete distribution information;

[0113] Step S403: Acquire angle abnormality recognition conditions;

[0114] Step S404: identifying abnormal nodes among the nodes according to the angle anomaly identification condition and the degree of angle change of the angle spectrum of each node.

[0115] It should be noted that the angle anomaly identification condition includes that the angle variation degree of the angle spectrum of the node is less than the angle variation degree of the angle spectrum of the boundary point.

[0116] In some embodiments, the terminal device can determine the data anomaly points in the risk feature data set according to the rule based on angle anomaly identification, that is: if most of the other points are in similar directions, then the point is an outlier; if many other points are in different directions, then the point is not an outlier. The manifestation of this rule in the angle spectrum is that when a point is an abnormal point, the angle size on its angle spectrum tends to be basically consistent, and the frequency and degree of fluctuation of the angle change are small, while the angle change frequency and degree of the normal point on the angle spectrum are high and the angle change is complex, and the fluctuation of the angle change is frequent and the change amplitude is large.

[0117] In some embodiments, boundary points are determined through historical data, actual experience data, theoretical analysis data, and mathematical and statistical data, and then the angle spectrum of the boundary points is obtained, which is compared with the angle spectrum of other points. If the degree of change of the angle spectrum is less than the angle spectrum of the boundary point, angle-based anomaly recognition can be achieved, and abnormal data in the satellite-ground integrated power distribution system can be qualitatively identified, thereby identifying abnormal nodes.

[0118] Step S50: generating a risk heat map of the satellite-ground integrated power distribution system according to the angle spectrum and the abnormal nodes.

[0119] It can be understood that this embodiment can quantify each node based on the operating characteristics and risk level of the state point corresponding to each node, combine the abnormal nodes and the quantification results and visualize them using the spatiotemporal characteristic heat map to achieve quantitative characterization of the risks of the satellite-ground integrated distribution system.

[0120] Furthermore, in order to accurately quantify system anomalies, refer to Figure 7 , Figure 7 This is a schematic diagram of an abnormality quantitative characterization process in an embodiment. The above step S50 may include:

[0121] Step S501: Calculating the outlier factor value corresponding to each node based on the angle spectrum;

[0122] Step S502: generating an abnormal quantification result of the satellite-ground integrated power distribution system according to the outlier factor value corresponding to each node and the abnormal node;

[0123] Step S503: generating a risk heat map of the satellite-ground integrated power distribution system based on the abnormality quantification result.

[0124] It should be noted that the terminal device can calculate the weighted variance of the angle value between each state point and other state point pairs, and its weight factor has a certain correlation with the distance; the value of the angle-based outlier factor (ABOF) is assigned to each state point in the system, and a list of points sorted according to their ABOF is returned as a result, so as to quantify the risk level of the satellite-ground integrated distribution system, and visualize it using the spatiotemporal feature heat map to achieve quantitative characterization of the risk of the satellite-ground integrated distribution system.

[0125] The outlier factor value is calculated according to the following formula:

[0126] ;

[0127] in, are the state points in the risk feature dataset respectively. The corresponding point vector, Represents the risk feature data set except for the state point All point pairs of all state points except Status points and The difference vector of the point pair, is the state point in the risk feature dataset The outlier factor value of Represents variance.

[0128] It should be noted that this embodiment calculates the angle-based outlier factor ABOF based on the angle and the angle spectrum. The essence of ABOF is the variance of the angle between a state point and all point-pair difference vectors in the data set, and the variance is weighted by the distance of the point. The value of ABOF can describe the divergence of the objects in direction relative to each other. If the observation angle spectrum of a point is very wide, then this point will be surrounded by other points in all possible directions, which means that this point is located in a cluster. If the observation angle spectrum of a point is quite small, then other points will only be located in certain directions. This means that the point is outside certain point sets that are grouped together.

[0129] Further, in order to effectively characterize the abnormal state of each node in the system, the above step S503 may include:

[0130] Step S5031: quantifying the abnormality degree of the abnormal node based on the outlier factor value, and obtaining the abnormal state parameter of the abnormal node;

[0131] Step S5032: acquiring spatiotemporal characteristic information of each node according to the risk characteristic data set;

[0132] Step S5033: Match the spatiotemporal feature information of each node with the outlier factor value corresponding to each node to obtain the risk state parameter of each node;

[0133] Step S5034: Generate a risk heat map of the satellite-ground integrated power distribution system based on the abnormal state parameters of the abnormal nodes and the risk state parameters of each node.

[0134] It should be noted that the terminal device can use the calculated ABOF value as the abnormal quantification result of the risk of the satellite-ground integrated distribution system, and then assign the ABOF value to each state point in the feature data set, and return a list of points sorted according to its ABOF as the result. It can not only quantify the abnormal degree of the abnormal state point, but also allow different rankings for the boundary points and internal points of the cluster, thereby realizing the quantification of the abnormal degree of the operation risk of the satellite-ground integrated distribution system.

[0135] In some embodiments, the terminal device can combine the spatiotemporal characteristics of each state point in the risk feature data set, match the calculated ABOF value of each state point with its timestamp, spatial position and other key elements, thereby generating a risk heat map of the satellite-ground integrated distribution system with complete spatiotemporal characteristics, and realize the visualization of the risk level of the satellite-ground integrated distribution system, thereby providing a visual characterization method for the risks of the satellite-ground integrated distribution system.

[0136] In this embodiment, operating parameters of each node in the satellite-ground integrated power distribution system are obtained, and the operating parameters include power operating parameters and communication operating parameters. The operating parameters are preprocessed to obtain multidimensional feature data of each node, and a risk feature data set is constructed based on the multidimensional feature data. The multidimensional feature data include power feature data and communication feature data. The risk feature data set includes a state point corresponding to each node, and the state point is a feature state corresponding to the node. An angle spectrum of each node is constructed based on the risk feature data set, and the angle spectrum includes angle parameters between each node and other nodes in the satellite-ground integrated power distribution system. Abnormal nodes in the nodes are identified based on the angle spectrum, and a risk heat map of the satellite-ground integrated power distribution system is generated according to the angle spectrum and the abnormal nodes, so as to effectively analyze the power operating parameters and communication operating parameters of each node in the system, accurately detect abnormal nodes based on power and communication heterogeneous data, significantly improve the efficiency of risk anomaly identification in the satellite-ground integrated power distribution system, realize quantitative characterization of system risks, and ensure the safe operation of the satellite-ground integrated power distribution system.

[0137] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which is stored an angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization program. When the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization program is executed by a processor, the steps of the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization method as described above are implemented.

[0138] 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.

[0139] The above-mentioned computer-readable storage medium may be included in the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization device; or it may exist independently without being assembled into the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization device.

[0140] In addition, an embodiment of the present invention also proposes a computer program product, including an angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization program, which, when executed by a processor, implements the steps of the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization method as described above.

[0141] The specific implementation methods of the computer program product of the present invention are basically the same as the embodiments of the above-mentioned angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization method, and will not be repeated here.

[0142] Reference Figure 8 , Figure 8 It is a structural block diagram of the first embodiment of the angle-based risk anomaly identification and quantitative characterization device for the satellite-ground integrated power distribution system of the present invention.

[0143] like Figure 8 As shown, the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization device proposed in an embodiment of the present invention includes:

[0144] The data acquisition module 10 is used to acquire the operating parameters of each node in the satellite-ground integrated power distribution system, wherein the operating parameters include power operating parameters and communication operating parameters;

[0145] A data processing module 20 is used to pre-process the operating parameters, obtain multi-dimensional feature data of each node, and construct a risk feature data set based on the multi-dimensional feature data, wherein the multi-dimensional feature data includes power feature data and communication feature data, and the risk feature data set includes a state point corresponding to each node, and the state point is a feature state corresponding to the node;

[0146] An angle calculation module 30, used to construct an angle spectrum of each node based on the risk characteristic data set, wherein the angle spectrum includes angle parameters between each node and other nodes in the satellite-ground integrated power distribution system;

[0147] An abnormality identification module 40, used for identifying abnormal nodes among the nodes based on the angle spectrum;

[0148] The abnormal characterization module 50 is used to generate a risk heat map of the satellite-ground integrated power distribution system according to the angle spectrum and the abnormal nodes.

[0149] Furthermore, the angle calculation module 30 is also used to generate a point vector corresponding to each node based on the risk feature data set;

[0150] Determine the difference vector between each node according to the point vector:

[0151] ;

[0152] in, are the state points in the risk feature dataset respectively. The corresponding point vector, Status points and Difference vector of a pair of points;

[0153] Calculate the angle parameters between the nodes based on the difference vector:

[0154] ;

[0155] in, is the angle parameter, For vector The Euclidean norm of is the dot product of the vectors;

[0156] The angle spectrum of each node is constructed according to the angle parameters between each node.

[0157] Furthermore, the abnormality identification module 40 is also used to perform discrete analysis on the angle spectrum of each node to obtain the angle discrete distribution information of the angle spectrum of each node; determine the angle change degree of the angle spectrum of each node according to the angle discrete distribution information; obtain angle abnormality identification conditions, the angle abnormality identification conditions include that the angle change degree of the angle spectrum of the node is less than the angle change degree of the angle spectrum of the boundary point; identify abnormal nodes among the nodes according to the angle abnormality identification conditions and the angle change degree of the angle spectrum of each node.

[0158] Furthermore, the abnormal characterization module 50 is further configured to calculate the outlier factor value corresponding to each node based on the angle spectrum:

[0159] ;

[0160] in, are the state points in the risk feature dataset respectively. The corresponding point vector, Represents the risk feature data set except for the state point All point pairs of all state points except Status points and The difference vector of the point pair, is the state point in the risk feature dataset The outlier factor value of represents variance;

[0161] An abnormal quantification result of the satellite-ground integrated power distribution system is generated according to the outlier factor value corresponding to each node and the abnormal node; and a risk heat map of the satellite-ground integrated power distribution system is generated based on the abnormal quantification result.

[0162] Furthermore, the abnormal characterization module 50 is also used to quantify the abnormal degree of the abnormal node based on the outlier factor value to obtain the abnormal state parameters of the abnormal node; obtain the spatiotemporal characteristic information of each node according to the risk characteristic data set; match the spatiotemporal characteristic information of each node with the outlier factor value corresponding to each node to obtain the risk state parameters of each node; and generate the risk heat map of the satellite-ground integrated power distribution system based on the abnormal state parameters of the abnormal node and the risk state parameters of each node.

[0163] Furthermore, the data processing module 20 is also used to perform feature analysis on the operating parameters to obtain original power feature data and original communication operation feature data; obtain status data of each node in the satellite-ground integrated power distribution system, and the status data includes time status information and space status information; synchronize the original power feature data and the original communication operation feature data based on the status data to obtain multidimensional feature data of each node, and the synchronization processing includes time synchronization processing and space synchronization processing; normalize the multidimensional feature data, and construct a risk feature data set based on the normalized multidimensional feature data.

[0164] In this embodiment, operating parameters of each node in the satellite-ground integrated power distribution system are obtained, and the operating parameters include power operating parameters and communication operating parameters. The operating parameters are preprocessed to obtain multidimensional feature data of each node, and a risk feature data set is constructed based on the multidimensional feature data. The multidimensional feature data includes power feature data and communication feature data. The risk feature data set includes a state point corresponding to each node, and the state point is a feature state corresponding to the node. An angle spectrum of each node is constructed based on the risk feature data set. The angle spectrum includes angle parameters between each node and other nodes in the satellite-ground integrated power distribution system. Abnormal nodes in the nodes are identified based on the angle spectrum. A risk heat map of the satellite-ground integrated power distribution system is generated according to the angle spectrum and the abnormal nodes, so as to effectively analyze the power operating parameters and communication operating parameters of each node in the system, accurately detect abnormal nodes based on power and communication heterogeneous data, significantly improve the efficiency of risk anomaly identification in the satellite-ground integrated power distribution system, realize quantitative characterization of system risks, and ensure the safe operation of the satellite-ground integrated power distribution system.

[0165] The angle-based risk anomaly identification and quantitative characterization device for a satellite-ground fusion power distribution system provided in the present application adopts the angle-based risk anomaly identification and quantitative characterization method for a satellite-ground fusion power distribution system in the above-mentioned embodiment, which can solve the technical problem of angle-based risk anomaly identification and quantitative characterization for a satellite-ground fusion power distribution system. Compared with the prior art, the beneficial effects of the angle-based risk anomaly identification and quantitative characterization device for a satellite-ground fusion power distribution system provided in the present application are the same as the beneficial effects of the angle-based risk anomaly identification and quantitative characterization method for a satellite-ground fusion power distribution system provided in the above-mentioned embodiment, and the other technical features of the angle-based risk anomaly identification and quantitative characterization device for a satellite-ground fusion power distribution system are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0166] 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.

[0167] 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.

[0168] In addition, for technical details not described in detail in this embodiment, please refer to the angle-based risk anomaly identification and quantitative characterization method for the satellite-ground integrated power distribution system provided in any embodiment of the present invention, which will not be repeated here.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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 method for identifying and quantifying risk anomalies in a satellite-ground integrated power distribution system based on angles, characterized in that: The method comprises: Acquire operating parameters of each node in the satellite-ground integrated power distribution system, wherein the operating parameters include power operating parameters and communication operating parameters; Preprocessing the operating parameters to obtain multidimensional feature data of each node, and constructing a risk feature data set based on the multidimensional feature data, wherein the multidimensional feature data includes power feature data and communication feature data, and the risk feature data set includes a state point corresponding to each node, and the state point is a feature state corresponding to the node; Constructing an angle spectrum of each node based on the risk characteristic data set, wherein the angle spectrum includes angle parameters between each node and other nodes in the satellite-ground integrated power distribution system; identifying abnormal nodes among the nodes based on the angle spectrum; Generate a risk heat map of the satellite-ground integrated power distribution system according to the angle spectrum and the abnormal nodes; The step of constructing the angle spectrum of each node based on the risk feature data set includes: Generate a point vector corresponding to each node based on the risk feature data set; Determine the difference vector between each node according to the point vector: ； in, are the state points in the risk feature dataset respectively. The corresponding point vector, Status points and Difference vector of a pair of points; Calculate the angle parameters between the nodes based on the difference vector: ； in, is the angle parameter, For vector The Euclidean norm of is the dot product of the vectors; Construct the angle spectrum of each node according to the angle parameters between each node; The identifying abnormal nodes among the nodes based on the angle spectrum includes: Perform discrete analysis on the angle spectrum of each node to obtain the angle discrete distribution information of the angle spectrum of each node; Determine the degree of angle change of the angle spectrum of each node according to the angle discrete distribution information; Acquire an angle anomaly identification condition, wherein the angle anomaly identification condition includes that an angle change degree of the angle spectrum of the node is less than an angle change degree of the angle spectrum of the boundary point; Abnormal nodes among the nodes are identified according to the angle anomaly identification condition and the degree of angle change of the angle spectrum of each node.

2. The angle-based risk anomaly identification and quantitative characterization method for satellite-ground integrated power distribution system according to claim 1 is characterized in that: The generating a risk heat map of the satellite-ground integrated power distribution system according to the angle spectrum and the abnormal node includes: Calculate the outlier factor value corresponding to each node based on the angle spectrum: ； in, are the state points in the risk feature dataset respectively. The corresponding point vector, Represents the risk feature data set except for the state point All point pairs of all state points except Status points and The difference vector of the point pair, is the state point in the risk feature dataset The outlier factor value of represents variance; Generate an abnormal quantification result of the satellite-ground integrated power distribution system according to the outlier factor value corresponding to each node and the abnormal node; A risk heat map of the satellite-ground integrated power distribution system is generated based on the abnormal quantification result.

3. The angle-based risk anomaly identification and quantitative characterization method for satellite-ground integrated power distribution system according to claim 2 is characterized in that: The generating a risk heat map of the satellite-ground integrated power distribution system based on the abnormal quantification result includes: quantifying the abnormal degree of the abnormal node based on the outlier factor value, and obtaining an abnormal state parameter of the abnormal node; Acquiring spatiotemporal characteristic information of each node according to the risk characteristic data set; Match the spatiotemporal characteristic information of each node with the outlier factor value corresponding to each node to obtain the risk status parameter of each node; A risk heat map of the satellite-ground integrated power distribution system is generated based on the abnormal state parameters of the abnormal nodes and the risk state parameters of each node.

4. The angle-based risk anomaly identification and quantitative characterization method for satellite-ground integrated power distribution system according to any one of claims 1 to 3, characterized in that: The preprocessing of the operating parameters to obtain multidimensional feature data of each node and constructing a risk feature data set based on the multidimensional feature data includes: Performing characteristic analysis on the operating parameters to obtain original power characteristic data and original communication operating characteristic data; Acquire status data of each node in the satellite-ground integrated power distribution system, wherein the status data includes time status information and space status information; Based on the state data, the original power characteristic data and the original communication operation characteristic data are synchronously processed to obtain multi-dimensional characteristic data of each node, wherein the synchronization processing includes time synchronization processing and space synchronization processing; The multidimensional feature data is normalized, and a risk feature data set is constructed based on the normalized multidimensional feature data.

5. An angle-based device for identifying and quantifying risk anomalies in a satellite-ground fusion power distribution system, characterized in that: The angle-based satellite-ground fusion distribution system risk anomaly identification and quantitative characterization device includes: A data acquisition module is used to acquire the operating parameters of each node in the satellite-ground integrated power distribution system, wherein the operating parameters include power operating parameters and communication operating parameters; a data processing module, configured to pre-process the operating parameters, obtain multi-dimensional feature data of each node, and construct a risk feature data set based on the multi-dimensional feature data, wherein the multi-dimensional feature data includes power feature data and communication feature data, and the risk feature data set includes a state point corresponding to each node, wherein the state point is a feature state corresponding to the node; An angle calculation module, used to construct an angle spectrum of each node based on the risk characteristic data set, wherein the angle spectrum includes angle parameters between each node and other nodes in the satellite-ground integrated power distribution system; An abnormality identification module, used for identifying abnormal nodes among the nodes based on the angle spectrum; An abnormal characterization module, used for generating a risk heat map of the satellite-ground integrated power distribution system according to the angle spectrum and the abnormal nodes; The angle calculation module is further used to generate a point vector corresponding to each node based on the risk feature data set; Determine the difference vector between each node according to the point vector: ； in, are the state points in the risk feature dataset respectively. The corresponding point vector, Status points and Difference vector of a pair of points; Calculate the angle parameters between the nodes based on the difference vector: ； in, is the angle parameter, For vector The Euclidean norm of is the dot product of the vectors; Construct the angle spectrum of each node according to the angle parameters between each node; The abnormality identification module is also used to perform discrete analysis on the angle spectrum of each node to obtain the angle discrete distribution information of the angle spectrum of each node; determine the angle change degree of the angle spectrum of each node according to the angle discrete distribution information; obtain angle abnormality identification conditions, the angle abnormality identification conditions include that the angle change degree of the angle spectrum of the node is less than the angle change degree of the angle spectrum of the boundary point; identify abnormal nodes among the nodes according to the angle abnormality identification conditions and the angle change degree of the angle spectrum of each node.

6. An angle-based device for identifying and quantifying risk anomalies in a satellite-ground fusion power distribution system, characterized in that: The angle-based satellite-ground fusion power distribution system risk anomaly identification and quantitative characterization device includes: a memory, a processor, and an angle-based satellite-ground fusion power distribution system risk anomaly identification and quantitative characterization program stored in the memory and executable on the processor. The angle-based satellite-ground fusion power distribution system risk anomaly identification and quantitative characterization program is configured to implement the angle-based satellite-ground fusion power distribution system risk anomaly identification and quantitative characterization method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization program, and when the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization program is executed by the processor, the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization method as described in any one of claims 1 to 4 is implemented.

8. A computer program product, characterized in that The computer program product includes an angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization program, which, when executed by a processor, implements the steps of the angle-based satellite-ground integrated power distribution system risk anomaly identification and quantitative characterization method as described in any one of claims 1 to 4.

Images