Power system risk prediction method, device and equipment

Abstract

The invention is suitable for the technical field of power systems, and particularly relates to a power system risk prediction method, device and equipment, and the method comprises the steps: obtaining first historical data, real-time environment data and real-time operation data of a power system; determining a plurality of initial fault groups and a plurality of second historical data based on the first historical data and the real-time environment data; respectively calculating each second historical data and the real-time operation data to obtain a first matching degree; obtaining a real-time prediction fault group based on each first matching degree and the corresponding initial fault group; and determining risk information based on the real-time predicted fault group and the first historical data. According to the power system risk prediction method provided by the embodiment of the invention, the problem of low risk prediction efficiency caused by insufficient fault prediction capability can be solved.

Description

Technical Field

[0001] The present application belongs to the technical field of power systems, and in particular, relates to a method, device and equipment for predicting risks in power systems. Background Art

[0002] The power system is a unified whole of electric energy production, transmission, distribution and use, which is composed of power generation, transmission, transformation, distribution, power consumption equipment and corresponding auxiliary systems. The power system is a complex and important system that realizes the production, transmission, distribution and consumption of electric energy.

[0003] With the rapid advancement of science and technology and the increasing complexity of power systems, higher requirements are placed on the stability and security of power supply, that is, the power system needs to have stronger fault prevention and response capabilities. However, existing technologies are often limited to the analysis and summary of historical fault data, making it difficult to accurately identify possible future faults in the power system, and thus appear to be powerless in risk prediction. The traditional troubleshooting method based on experience judgment is not only inefficient, but also unable to proactively foresee potential risks, and is far from meeting the high standards for fault prevention in modern power systems. Therefore, there is currently a problem of insufficient ability to predict faults in the power system, resulting in low risk prediction efficiency. Summary of the invention

[0004] The embodiments of the present application provide a method, device and equipment for predicting risks in an electric power system, which can solve the problem of low risk prediction efficiency caused by insufficient fault prediction capability.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting power system risks, comprising: Acquire first historical data, real-time environmental data and real-time operation data of the power system; wherein the first historical data includes voltage data, current data, frequency data, time, weather, location and type of fault when a fault occurs in the power system, the real-time environmental data includes time and weather, and the real-time operation data includes voltage data, current data and frequency data; Determine multiple initial fault groups and multiple second historical data based on the first historical data and the real-time environmental data; wherein the initial fault group includes the location and type of each fault that occurs successively or concurrently in the power system, and the second historical data includes voltage data, current data and frequency data of the power system corresponding to the initial fault group; Calculate each of the second historical data and the real-time operation data to obtain a first matching degree; wherein the first matching degree is used to reflect the similarity between the second historical data and the real-time operation data; Based on each of the first matching degrees and the corresponding initial fault groups, a real-time predicted fault group is obtained; wherein the real-time predicted fault group includes the location and type of each fault that will occur successively or concurrently in the future power system; The risk information is determined based on the real-time predicted fault group and the first historical data; wherein the risk information is used to reflect the severity of each fault that may occur in the power system in the future.

[0006] The above technical solutions in the embodiments of the present application have at least the following technical effects: The power system risk prediction method provided in the embodiment of the present application obtains the first historical data, real-time environmental data and real-time operation data of the power system; determines multiple initial fault groups and multiple second historical data based on the first historical data and the real-time environmental data; calculates each second historical data and the real-time operation data to obtain a first matching degree; obtains a real-time predicted fault group based on each first matching degree and the corresponding initial fault group; and determines risk information based on the real-time predicted fault group and the first historical data. Therefore, the power system risk prediction method provided in the embodiment of the present application realizes the prediction of future power system faults by collecting and analyzing the first historical data, real-time environmental data and real-time operation data of the power system, which is not only conducive to improving the accuracy and reliability of the prediction, but also can provide risk information before the fault occurs, which helps to take timely measures to prevent or reduce the impact of the fault on the power system.

[0007] In a possible implementation manner of the first aspect, determining a plurality of initial fault groups and a plurality of second historical data based on the first historical data and the real-time environment data includes: According to the real-time environment data, third historical data is obtained by filtering from the first historical data; wherein the third historical data includes the time, location and type of each fault occurring in the power system corresponding to the real-time environment data; Obtain multiple first fault groups according to the third historical data; wherein the first fault groups include the locations and types of each fault that occurs successively or concurrently in the power system; Determine whether there is an inclusion relationship between every two of the first fault groups; If there is an inclusion relationship between the first fault groups, merging the corresponding first fault groups to obtain the initial fault group; The corresponding second historical data is obtained according to the first historical data and each of the initial fault groups.

[0008] In a possible implementation manner of the first aspect, the filtering, according to the real-time environment data, from the first historical data to obtain third historical data includes: Obtaining a real-time feature sequence according to the real-time environmental data; wherein the real-time feature sequence is used to reflect the environment in which the current power system is located; Obtaining a plurality of historical feature sequences according to the first historical data; wherein the historical feature sequences are used to reflect the environment in which the power system is located during the time period when the fault occurs; A plurality of first matrices are obtained according to the real-time feature sequence and each of the historical feature sequences; wherein the first matrix is ​​used to reflect the similarity between the real-time feature sequence and the historical feature sequence; Obtaining a corresponding first distance according to each of the first matrices; wherein the first distance is used to reflect the overall similarity between the real-time feature sequence and each of the historical feature sequences; The third historical data is obtained according to the first distances and the first historical data.

[0009] In a possible implementation manner of the first aspect, obtaining a plurality of first fault groups according to the third historical data includes: Calculating the support of each item set in the third historical data; wherein the item set includes a single item set and a multi-item set, the single item set includes the location and type of a single fault in the power system, the multi-item set includes the locations and types of multiple faults in the power system, and the support is used to reflect the frequency of occurrence of the item set in the third historical data; Determining whether each support exceeds a support threshold; If there is an item set whose support exceeds the support threshold, the corresponding item set is determined as the first fault group.

[0010] In a possible implementation manner of the first aspect, the method further includes: If there is no inclusion relationship between the first failure groups, each of the first failure groups is determined as the corresponding initial failure group.

[0011] In a possible implementation manner of the first aspect, the calculating each of the second historical data and the real-time operation data to obtain a first matching degree includes: Obtain a plurality of first state vectors according to the real-time operation data; Obtaining a corresponding second state vector according to each of the second historical data; Calculating the distance between each of the second state vectors and the corresponding first state vector; The corresponding first matching degree is obtained according to each of the distances.

[0012] In a possible implementation manner of the first aspect, obtaining a real-time predicted fault group based on each of the first matching degrees and the corresponding initial fault group includes: Determine whether the first matching degree exceeds a matching degree threshold; If there is a first matching degree exceeding the matching degree threshold, the real-time predicted fault group is determined according to the initial fault group corresponding to the largest first matching degree.

[0013] In a possible implementation manner of the first aspect, the method further includes: If the first matching degrees do not exceed the matching degree threshold, the faults in the initial fault groups are randomly combined to obtain a second abnormal combination; Obtaining a prediction model according to each of the initial fault groups and the corresponding second historical data; Input each of the second abnormal combinations into the prediction model to obtain corresponding first operation data; wherein the first operation data includes voltage data, current data and frequency data; Calculate the first operation data and the real-time operation data to obtain a corresponding second matching degree; wherein the second matching degree is used to reflect the similarity between the first operation data and the real-time operation data; Obtaining a plurality of third abnormal combinations according to each of the second abnormal combinations and the corresponding second matching degrees; The real-time predicted fault group is obtained by iteratively optimizing each of the third abnormal combinations.

[0014] In a possible implementation manner of the first aspect, determining risk information based on the real-time predicted fault group and the first historical data includes: Acquire fourth historical data of the power system; wherein the fourth historical data includes voltage data, current data and frequency data when the power system operates normally; Obtaining second operating data according to the real-time predicted fault group and the prediction model; wherein the second operating data includes voltage data, current data and frequency data; Obtaining the deviation corresponding to the real-time predicted fault group according to the second operating data and the fourth historical data; wherein the deviation is used to reflect the impact of each fault in the real-time predicted fault group on system stability, and the deviation includes voltage deviation, current deviation and frequency deviation; Obtaining a real-time fault range according to the real-time predicted fault group and the first historical data; wherein the real-time fault range is the impact range of each fault in the real-time predicted fault group; The risk information is obtained according to the real-time fault range and the deviation.

[0015] In a second aspect, an embodiment of the present application provides a power system risk prediction device, comprising: an acquisition module, configured to acquire first historical data, real-time environmental data, and real-time operation data of the power system; wherein the first historical data includes voltage data, current data, frequency data, time, weather, location, and type of fault when a fault occurs in the power system, the real-time environmental data includes time and weather, and the real-time operation data includes voltage data, current data, and frequency data; An initial module, configured to determine a plurality of initial fault groups and a plurality of second historical data based on the first historical data and the real-time environmental data; wherein the initial fault group includes the location and type of each fault that occurs successively or concurrently in the power system, and the second historical data includes voltage data, current data and frequency data of the power system corresponding to the initial fault group; A matching degree module, used to calculate the first matching degree for each of the second historical data and the real-time operation data; wherein the first matching degree is used to reflect the similarity between the second historical data and the real-time operation data; A real-time prediction module, configured to obtain a real-time predicted fault group based on each of the first matching degrees and the corresponding initial fault group; wherein the real-time predicted fault group includes the location and type of each fault that will occur successively or concurrently in the future power system; A risk module is used to determine risk information based on the real-time predicted fault group and the first historical data; wherein the risk information is used to reflect the severity of each fault that may occur in the power system in the future.

[0016] In a third aspect, an embodiment of the present application provides a power system risk prediction device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method as described in any one of the above-mentioned first aspects when executing the computer program.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a power system risk prediction device, enables the power system risk prediction device to execute any of the methods described in the first aspect above.

[0019] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flowchart of a power system risk prediction method provided by an embodiment of the present application; Figure 2 It is a schematic diagram of the implementation flow of steps S200, S210 and S220 in the power system risk prediction method provided in one embodiment of the present application; Figure 3 It is a schematic diagram of the implementation flow of steps S300 and S400 in the power system risk prediction method provided in one embodiment of the present application; Figure 4 It is a schematic diagram of the implementation flow of step S500 in the power system risk prediction method provided in one embodiment of the present application; Figure 5 is a schematic diagram of the structure of a power system risk prediction device provided in an embodiment of the present application; Figure 6 It is a structural diagram of the power system risk prediction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0024] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0026] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0028] In related technologies, with the rapid advancement of science and technology and the increasing complexity of power systems, higher requirements are placed on the stability and safety of power supply, that is, the power system needs to have stronger fault prevention and response capabilities. However, existing technologies are often limited to the analysis and summary of historical fault data, making it difficult to accurately identify future faults in the power system, and thus appear to be powerless in risk prediction. The traditional troubleshooting method based on experience judgment is not only inefficient, but also unable to proactively foresee potential risks, and is far from meeting the high standards for fault prevention in modern power systems. Therefore, there is currently a problem of insufficient ability to predict faults in the power system, resulting in low risk prediction efficiency.

[0029] To solve the above problems, the embodiments of the present application provide a method, device and equipment for predicting the risks of an electric power system. In the method, the first historical data, real-time environmental data and real-time operation data of the electric power system are obtained; multiple initial fault groups and multiple second historical data are determined based on the first historical data and the real-time environmental data; each second historical data and the real-time operation data are respectively calculated to obtain a first matching degree; a real-time predicted fault group is obtained based on each first matching degree and the corresponding initial fault group; and risk information is determined based on the real-time predicted fault group and the first historical data. Therefore, the electric power system risk prediction method provided by the embodiments of the present application realizes the prediction of future electric power system faults by collecting and analyzing the first historical data, real-time environmental data and real-time operation data of the electric power system, which is not only conducive to improving the accuracy and reliability of the prediction, but also can provide risk information before the fault occurs, which helps to take timely measures to prevent or reduce the impact of the fault on the electric power system.

[0030] The power system risk prediction method provided in the embodiment of the present application can be applied to the power system risk prediction device. At this time, the power system risk prediction device is the executor of the power system risk prediction method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the power system risk prediction device.

[0031] For example, the power system risk prediction device can be a station (STAION, ST) in a WLAN, and can be a cellular phone, a mobile phone, a tablet computer, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a smart screen, a smart TV, a computing device or other processing device connected to a wireless modem, a computer, a laptop computer, a handheld computing device, etc., but not limited to these.

[0032] In order to better understand the power system risk prediction method provided in the embodiment of the present application, the specific implementation process of the power system risk prediction method provided in the embodiment of the present application is exemplarily introduced below.

[0033] Figure 1 A schematic flow chart of a power system risk prediction method provided in an embodiment of the present application is shown, and the power system risk prediction method includes: S100, obtaining first historical data, real-time environmental data, and real-time operation data of the power system, wherein the first historical data includes voltage data, current data, frequency data, time, weather, location, and type of fault when a fault occurs in the power system, the real-time environmental data includes time and weather, and the real-time operation data includes voltage data, current data, and frequency data.

[0034] It can be understood that the location of the fault in the first historical data includes the area, equipment and geographical coordinates where the fault occurs in the power system.

[0035] For example, all fault records in the past year (i.e., first historical data) can be extracted from the database of the power system, and the current weather (including temperature and humidity) and time can be obtained in real time through the Internet, and the real-time operation data of the power system (including voltage data, current data, and frequency data) can be obtained through sensors (such as Hall voltage sensors, Hall current sensors, and digital frequency meters, etc.) or SCADA systems. For example, the first historical data is shown in Table 1 below, the real-time environmental data is shown in Table 2 below, and the real-time operation data is shown in Table 3 below.

[0036] Table 1 Table 2 Table 3 S200, determining a plurality of initial fault groups and a plurality of second historical data based on the first historical data and the real-time environmental data, wherein the initial fault group includes the location and type of each fault that occurs successively or concurrently in the power system, and the second historical data includes voltage data, current data and frequency data of the power system corresponding to the initial fault group.

[0037] It can be understood that the second historical data is the value range of the voltage, current and frequency of each fault in the initial fault group in the first historical data.

[0038] Exemplarily, based on the real-time environmental data, a clustering algorithm (such as K-means, DBSCAN, etc.) can be used to identify the fault combinations that occur successively or concurrently in the first historical data under environmental conditions similar to the real-time environmental data (such as the same weather, similar time period), and obtain initial fault groups. For example, the initial fault groups are shown in Table 4 below, and the second historical data corresponding to each initial fault group is obtained based on the first historical data.

[0039] Table 4 In one possible implementation, see Figure 2S200, determining a plurality of initial fault groups and a plurality of second historical data based on the first historical data and the real-time environment data, including: S210: Filter the first historical data to obtain third historical data according to the real-time environment data, wherein the third historical data includes the time, location and type of each fault occurring in the power system corresponding to the real-time environment data.

[0040] It can be understood that according to the real-time environmental data, the first historical data is traversed, and for each fault, the similarity between the real-time environmental data and the first historical data is compared according to the weather and time information when the fault occurred, and the third historical data that better matches the real-time environmental data is screened out.

[0041] Optionally, see Figure 2 S210, filtering the first historical data to obtain third historical data according to the real-time environment data, including: S211, obtaining a real-time feature sequence according to the real-time environment data, wherein the real-time feature sequence is used to reflect the environment in which the current power system is located.

[0042] Exemplarily, the real-time feature sequence may be [temperature (°C), humidity (%)]. For example, if the real-time environmental data is as shown in Table 2 above, the real-time feature sequence is [15, 60].

[0043] S212, obtaining a plurality of historical feature sequences according to the first historical data, wherein the historical feature sequences are used to reflect the environment of the power system during the time period when the fault occurs.

[0044] It can be understood that the historical feature sequence is the weather (including temperature and humidity) when the same fault occurs in the power system in the first historical data (ie, the location and type of the fault are the same). Multiple groups of historical feature sequences can be obtained based on the first historical data.

[0045] Exemplarily, the historical feature sequence may be [(temperature 1 (°C), humidity 1 (%)), (temperature 2 (°C), humidity 2 (%)), ...], for example, the first historical data is shown in Table 5 below, then the historical feature sequence is [(25, 60), (30, 65)].

[0046] Table 5 S213, obtaining a plurality of first matrices according to the real-time feature sequence and each historical feature sequence, wherein the first matrix is ​​used to reflect the similarity between the real-time feature sequence and each historical feature sequence.

[0047] Exemplarily, a corresponding first matrix can be created according to the real-time feature sequence and each historical feature sequence. The size of the first matrix is ​​(m, n), where m is the length of the real-time feature sequence, and n is the length of the historical feature sequence. All elements of the first matrix are initialized to positive infinity (indicating uncalculated distances). For example, for the first matrix A, A[0, 0] is set to 0 (indicating that the distance between two empty sequences is 0). For i=1 to m, A[i, 0]=A[i-1, 0]+d(real-time feature sequence [i-1], historical feature sequence [0]); For j=1 to n, A[0, j]=A[0, j-1]+d(real-time feature sequence[0], historical feature sequence[j-1]); for i=1 to m, j=1 to n, A[i, j]=min(A[i-1, j], A[i, j-1], A[i-1, j-1])+d(real-time feature sequence[i-1], historical feature sequence[j-1]), where d(x, y) represents the distance between the eigenvalue x in the real-time feature sequence and the eigenvalue y in the historical feature sequence, which can be obtained using Euclidean distance, Manhattan distance or other methods.

[0048] S214, obtaining a corresponding first distance according to each first matrix, wherein the first distance is used to reflect the overall similarity between the real-time feature sequence and each historical feature sequence.

[0049] It can be understood that the lower right corner element A[m, n] of the first matrix is ​​the first distance between the real-time feature sequence and the historical feature sequence.

[0050] S215: Obtain third historical data according to the first distances and the first historical data.

[0051] Exemplarily, the weather of the corresponding historical feature sequence may be determined according to the historical feature sequence corresponding to the largest first distance, and the data under the same weather conditions in the first historical data may be determined as the third historical data.

[0052] Through the above steps S211 to S215, the association between faults and the environment in the power system is established, and the similarity between the real-time feature sequence and the historical feature sequence is quantified, which is conducive to screening out the third historical data that is highly relevant to the current environmental conditions, providing more accurate data support for subsequent fault mode matching and diagnosis, and helping to achieve in-depth analysis and accurate prediction of power system fault conditions, thereby improving the stability and reliability of the power system.

[0053] S220: Obtain a plurality of first fault groups according to the third historical data, wherein the first fault groups include locations and types of various faults that occur successively or concurrently in the power system.

[0054] Exemplarily, data mining techniques (such as association rule mining, frequent item set mining, etc.) can be used to identify the faults that occur successively or concurrently in the power system according to the third historical data to obtain the first fault group. For example, the first fault group is shown in Table 6 below.

[0055] Table 6 Optionally, see Figure 2 , S220, obtaining a plurality of first fault groups according to the third historical data, including: S221, calculate the support of each item set in the third historical data. The item set includes a single item set and a multi-item set, the single item set includes the location and type of a single fault in the power system, the multi-item set includes the locations and types of multiple faults in the power system, and the support is used to reflect the frequency of occurrence of the item set in the third historical data.

[0056] For example, all fault records can be extracted from the third historical data, each fault record includes the fault location and fault type, and all possible single item sets and multi-item sets are constructed according to the fault records. The third historical data is traversed, the number of occurrences of each item set is counted, and the corresponding support is obtained by dividing it by the total number of fault records.

[0057] S222, judging whether each support exceeds a support threshold.

[0058] It can be understood that the support threshold is a support value that does not exceed a preset specified value. The preset specified value can be set by ordinary technicians in the field according to actual needs and is not limited here.

[0059] For example, a reasonable support threshold may be determined based on historical data and industry standards, for example, the support threshold is 0.3.

[0060] S223: If there is an item set whose support exceeds the support threshold, determine the corresponding item set as the first fault group.

[0061] Exemplarily, the support of all item sets is traversed, and the item sets exceeding the support threshold are determined as the first fault group.

[0062] By calculating the support of each item set in the third historical data and setting the support threshold through the above steps S221 to S223, fault combinations that frequently appear in the third historical data can be identified, which is conducive to identifying potential fault risks, thereby improving the reliability of the entire power system.

[0063] S230: Determine whether there is an inclusion relationship between every two first fault groups.

[0064] It can be understood that, for any two first fault groups, if all faults of one first fault group are included in another first fault group, it is determined that there is an inclusion relationship between the two first fault groups.

[0065] S240: If there is an inclusion relationship between the first fault groups, the corresponding first fault groups are merged to obtain an initial fault group.

[0066] Exemplarily, the first fault groups with inclusion relationships may be merged to remove repeated faults to obtain an initial fault group. For example, the first fault group is shown in Table 6 above, and the initial fault group is shown in Table 7 below.

[0067] Table 7 S250: Obtain corresponding second historical data according to the first historical data and each initial fault group.

[0068] It can be understood that the second historical data includes the value ranges of voltage, current and frequency when each fault in the initial fault group occurs in the power system. The voltage data, current data and frequency data of each fault in the initial fault group can be filtered out from the first historical data to obtain the second historical data.

[0069] Through the above steps S210 to S250, common fault modes in the power system can be identified by mining frequent item sets in historical data. By merging the first fault groups with inclusion relationships, it is helpful to reduce redundant information and improve the accuracy of analysis. Reorganizing the first historical data according to the initial fault group can make subsequent analysis and decision-making more convenient.

[0070] In one possible implementation, see Figure 2 , S200, the method further includes: S201: If there is no inclusion relationship between the first fault groups, determine the first fault groups as corresponding initial fault groups.

[0071] It can be understood that if there is no inclusion relationship between all first fault groups, then each first fault group is directly determined as the corresponding initial fault group.

[0072] Through the above step S201, when there is no inclusion relationship between the first fault groups, the first fault group is directly determined as the initial fault group, which can simplify the fault analysis process, help to quickly identify the main fault mode in the power system, and improve the accuracy of fault prediction.

[0073] S300: Calculate the second historical data and the real-time operation data to obtain a first matching degree, wherein the first matching degree is used to reflect the similarity between the second historical data and the real-time operation data.

[0074] Exemplarily, the real-time operation data of the power system and each second historical data can be converted into state vectors respectively, and the distance between each first state vector (i.e., the state vector of the real-time operation data) and the corresponding second state vector (i.e., the state vector of the second historical data) can be calculated by a distance measurement method (such as Euclidean distance, Manhattan distance, cosine similarity, etc.), and based on the calculated distance, a function (such as the inverse of the distance, an exponential decay function, etc.) is used to convert the distance into a first matching degree.

[0075] In one possible implementation, see Figure 3 , S300, respectively calculating each second historical data and the real-time operation data to obtain a first matching degree, including: S310, obtaining a plurality of first state vectors according to real-time operation data.

[0076] It can be understood that the real-time operation data includes voltage data V, current data I and frequency data f, and the first state vector can be expressed as (V, I, f). For example, the real-time operation data is shown in Table 8 below, and the first state vector is (220, 100, 50).

[0077] Table 8 S320: Obtain a corresponding second state vector according to each second historical data.

[0078] Exemplarily, the second state vector may be determined according to the midpoint of the value range of the voltage, current and frequency when the fault occurs in the second historical data. For example, the second historical data is shown in Table 9 below, and the second state vector is [207.5, 165, 50].

[0079] Table 9 S330: Calculate the distance between each second state vector and the corresponding first state vector.

[0080] Exemplarily, the distance between each first state vector and the corresponding second state vector may be calculated using the Euclidean distance formula. For example, the real-time operation data is shown in Table 8 above, and the corresponding second historical data is shown in Table 9 above. , where (x1, y1, z1) is the first state vector, (x2, y2, z2) is the second state vector, and Distance is the distance between the first state vector and the corresponding second state vector. The second state vector is (207.5, 165, 50), and the corresponding first state vector is (220, 100, 50). Substituting this into the formula, we get Distance≈66.19.

[0081] S340: Obtain a corresponding first matching degree according to each distance.

[0082] Exemplarily, the first matching degree may be calculated by an inverse proportional function or an exponential decay function, for example, (where ϵ is a small positive number used to avoid division by zero errors and adjust the sensitivity of the matching degree), distance ≈ 66.19, ϵ = 1, then the matching degree = ≈0.0149.

[0083] Through the above steps S310 to S340, the similarity between the real-time operating data and the second historical data can be effectively evaluated, which is helpful to identify abnormal conditions in the power system. By comparing the real-time data with the historical data, potential faults or abnormal conditions can be quickly discovered, which is beneficial to improving the reliability and safety of the power system.

[0084] S400: Based on each first matching degree and the corresponding initial fault group, a real-time predicted fault group is obtained, wherein the real-time predicted fault group includes the location and type of each fault that will occur successively or concurrently in the future power system.

[0085] It can be understood that if there is at least one first matching degree that exceeds the preset threshold (i.e., the matching degree threshold), then the initial fault group corresponding to the largest first matching degree is selected as the real-time predicted fault group; if each first matching degree does not exceed the preset threshold (i.e., the matching degree threshold), then the faults in each initial fault group are randomly combined to obtain a second abnormal combination, and each second abnormal combination is input into a prediction model (such as a decision tree, random forest, neural network, etc.) to obtain the corresponding first operating data, and each first operating data and real-time operating data are respectively calculated to obtain the corresponding second matching degree, and the corresponding third abnormal combination is obtained according to each second matching degree, and iterative optimization is performed according to the third abnormal combination to obtain the real-time predicted fault group.

[0086] In one possible implementation, see Figure 3 , S400, obtaining a real-time predicted fault group based on each first matching degree and the corresponding initial fault group, including: S410: Determine whether there is a first matching degree exceeding a matching degree threshold.

[0087] It can be understood that the matching degree threshold is that the first matching degree does not exceed a preset specified value, and the preset specified value can be set by ordinary technicians in the field according to actual needs, and is not limited here.

[0088] For example, a reasonable matching threshold may be determined based on historical data and industry standards, for example, the matching threshold is 0.2.

[0089] S420: If there is a first matching degree exceeding the matching degree threshold, determine the real-time predicted fault group according to the initial fault group corresponding to the largest first matching degree.

[0090] It can be understood that all first matching degrees are traversed to find the largest first matching degree that exceeds the matching degree threshold, and the initial fault group corresponding to the first matching degree is used as the real-time predicted fault group.

[0091] Through the above steps S410 to S420, the initial fault group that best matches the real-time data can be found quickly and accurately, so as to perform fault prediction.

[0092] In one possible implementation, see Figure 3 , S400, the method further includes: S401: If each first matching degree does not exceed the matching degree threshold, the faults in each initial fault group are randomly combined to obtain a second abnormal combination.

[0093] It can be understood that the second abnormal combination includes the type and location of each fault.

[0094] Exemplarily, a random algorithm (such as a shuffling algorithm, a random permutation algorithm, etc.) may be used to randomly combine the faults in each initial fault group to generate a plurality of second abnormal combinations.

[0095] S402: Obtain a prediction model according to each initial fault group and the corresponding second historical data.

[0096] Exemplarily, the prediction model may be a machine learning model, such as a decision tree, random forest, neural network, or other model.

[0097] Exemplarily, each initial fault group and the second historical data can be cleaned (identify and delete duplicate data, process missing values, correct outliers, and unify data formats); select features (fault type and location) according to the prediction target (voltage data, current data, and frequency data); divide each processed initial fault group and the second historical data into a training set and a test set (such as 70% training set, 30% test set), and ensure that the training set and the test set are continuous in time; use a machine learning algorithm (such as linear regression, random forest, etc.) to build a model, using the selected features as input and the corresponding voltage data, current data, and frequency data as output; use the training set to train the model, and iteratively optimize the algorithm parameters to minimize the model's prediction error; use the test set to verify the trained model and evaluate the model's performance (such as K-fold cross validation), and based on the verification results, adjust the model parameters or try different model structures to improve the model performance and obtain a prediction model.

[0098] S403, input each second abnormal combination into the prediction model to obtain corresponding first operation data, wherein the first operation data includes voltage data, current data and frequency data.

[0099] It can be understood that the first operating data is used to reflect the operating state of the power system under the simulated abnormal situation.

[0100] Exemplarily, each second abnormal combination can be used as an input feature and input into a prediction model, and the prediction model outputs the corresponding first operating data.

[0101] S404: Calculate the first operation data and the real-time operation data to obtain the corresponding second matching degree, wherein the second matching degree is used to reflect the similarity between the first operation data and the real-time operation data.

[0102] Exemplarily, a similarity calculation method (such as cosine similarity, Euclidean distance, etc.) may be used to calculate the similarity between the first operation data and the real-time operation data to obtain the second matching degree.

[0103] S405: Obtain a plurality of third abnormal combinations according to each second abnormal combination and the corresponding second matching degree.

[0104] Exemplarily, the second matching degrees are sorted, and corresponding second abnormal combinations are selected according to a preset ratio (such as the first 40%) to obtain respective third abnormal combinations.

[0105] S406, performing iterative optimization according to each third abnormal combination to obtain a real-time predicted fault group.

[0106] Exemplarily, the third abnormal combination can be used as the initial population, and new abnormal combinations can be obtained by iterative optimization through selection, crossover, mutation and other operations until the stopping condition is met (such as reaching the maximum number of iterations or exceeding the matching threshold), and the new abnormal combination exceeding the matching threshold is determined as the real-time predicted fault group.

[0107] Through the above steps S401 to S406, when each first matching degree does not exceed the matching degree threshold, the random combination of faults in each initial fault group and the prediction model can be used to obtain multiple possible fault combinations, and the optimal real-time predicted fault group can be obtained through iterative optimization, which is conducive to improving the accuracy and robustness of fault prediction.

[0108] S500, determining risk information based on the real-time predicted fault group, wherein the risk information is used to reflect the severity of each fault that may occur in the power system in the future.

[0109] Exemplarily, the fourth historical data of the power system can be obtained, the second operating data can be obtained based on each fault of the real-time predicted fault group and the prediction model, the deviation of each fault of the real-time predicted fault group can be obtained based on each second operating data and the fourth historical data, the real-time fault range can be obtained based on the real-time predicted fault group and the first historical data, and the risk information can be obtained based on the real-time fault range and the deviation corresponding to each fault of the real-time predicted fault group.

[0110] In one possible implementation, see Figure 4 , S500, determining risk information based on the real-time predicted fault group and the first historical data, including: S510, acquiring fourth historical data of the power system, wherein the fourth historical data includes voltage data, current data and frequency data when the power system operates normally.

[0111] Exemplarily, records of normal operation of the power system in the past year (ie, fourth historical data) may be extracted from a database of the power system.

[0112] S520, obtaining second operation data according to the real-time predicted fault group and the prediction model, wherein the second operation data includes voltage data, current data and frequency data.

[0113] It can be understood that the second operating data is used to reflect the operating state of the power system under the predicted fault condition.

[0114] Exemplarily, the type and location of each fault in the real-time predicted fault group may be used as input features and input into the prediction model, and the prediction model outputs the corresponding second operating data.

[0115] S530, obtaining the deviation corresponding to the real-time predicted fault group according to the second operation data and the fourth historical data, wherein the deviation is used to reflect the impact of each fault in the real-time predicted fault group on system stability, and the deviation includes voltage deviation, current deviation and frequency deviation.

[0116] Exemplarily, the fourth historical data can be preprocessed (including removing outliers, filling missing values, etc.), and for each item in the second operating data (voltage data, current data, and frequency data), the difference or ratio between it and the average value or normal range of the corresponding item in the fourth historical data is calculated.

[0117] S540: Obtain a real-time fault range according to the real-time predicted fault group and the first historical data, wherein the real-time fault range is the impact range of each fault in the real-time predicted fault group.

[0118] Exemplarily, a preset search radius can be obtained based on the location of each fault in the real-time predicted fault group, and each non-fault point of the power system within the search radius (i.e., a fault that has appeared in the first historical data but is not in the real-time predicted fault group) is determined based on the real-time predicted fault group and the first historical data. A spatial interpolation method (such as inverse distance weighted interpolation, Kriging interpolation, etc.) is used to predict the failure probability of non-fault points in the power system. If the failure probability of a non-fault point exceeds a preset threshold, then the non-fault point is within the real-time impact range, and the real-time fault range is obtained based on the location of all non-fault points whose failure probability exceeds the preset threshold. For example, for each non-fault point in the power system, the geographical distance between it and the corresponding fault point (i.e., the fault in the real-time predicted fault group) is calculated, and a weight is assigned to each non-fault point. , where w i is the weight of the ith non-faulty point, d i is the distance from the non-fault point to the fault point, p is the power parameter (p can be 2), and for each non-fault point within the search radius, its failure probability is: , where P(x,y) is the failure probability of the non-faulty point (x,y), P i is the failure probability of the ith fault point (i.e., the probability of appearing in the first historical data), and n is the number of fault points.

[0119] S550, obtain risk information according to the real-time fault range and deviation.

[0120] For example, risk information can be obtained based on the real-time fault range and deviation. For example, the risk information is: "In the XX area, due to the real-time prediction of the short circuit fault of line Y, the voltage in the area will drop by 8.5%, the current overload multiple will be 1.6, and the frequency will drop by 0.2%. The impact range is expected to spread outward by about 2 kilometers from the fault point. It is recommended to take immediate measures to isolate and repair the fault to avoid greater impact on surrounding areas." Through the above steps S510 to S550, the deviation between the second operating data and the fourth historical data is calculated, so as to quantitatively evaluate the impact of the fault on the stability of the power system; by using the spatial interpolation method, the propagation range and impact degree of the fault in the power system can be predicted, and the real-time fault range can be determined; combining the real-time fault range and the deviation is helpful to comprehensively evaluate the risk status of the power system, provide strong support for decision makers, and facilitate timely discovery and handling of potential faults, thereby improving the safety and stability of the power system.

[0121] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0122] Corresponding to the power system risk prediction method described in the above embodiment, the embodiment of the present application also provides a power system risk prediction device, and each module of the device can implement each step of the power system risk prediction method. Figure 5 A structural block diagram of a power system risk prediction device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0123] Reference Figure 5 , the device comprises: an acquisition module, configured to acquire first historical data, real-time environmental data, and real-time operation data of the power system; wherein the first historical data includes voltage data, current data, frequency data, time, weather, location, and type of fault when a fault occurs in the power system, the real-time environmental data includes time and weather, and the real-time operation data includes voltage data, current data, and frequency data; An initial module, configured to determine a plurality of initial fault groups and a plurality of second historical data based on the first historical data and the real-time environmental data; wherein the initial fault group includes the location and type of each fault that occurs successively or concurrently in the power system, and the second historical data includes voltage data, current data and frequency data of the power system corresponding to the initial fault group; A matching degree module, used to calculate the first matching degree for each of the second historical data and the real-time operation data; wherein the first matching degree is used to reflect the similarity between the second historical data and the real-time operation data; A real-time prediction module, configured to obtain a real-time predicted fault group based on each of the first matching degrees and the corresponding initial fault group; wherein the real-time predicted fault group includes the location and type of each fault that will occur successively or concurrently in the future power system; A risk module is used to determine risk information based on the real-time predicted fault group and the first historical data; wherein the risk information is used to reflect the severity of each fault that may occur in the power system in the future.

[0124] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0125] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0126] The present application also provides a power system risk prediction device, Figure 6 This is a schematic diagram of the structure of a power system risk prediction device / power system risk prediction equipment provided in one embodiment of the present application. Figure 6 As shown, the power system risk prediction device / power system risk prediction equipment 6 of this embodiment includes: at least one processor 60 ( Figure 6 Only one is shown), at least one memory 61 ( Figure 6 Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the power system risk prediction device / power system risk prediction equipment 6 implements the steps in any of the above-mentioned power system risk prediction method embodiments, or implements the functions of each module / unit in the above-mentioned device embodiments.

[0127] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the power system risk prediction device 6.

[0128] The power system risk prediction device / power system risk prediction equipment 6 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The power system risk prediction device / power system risk prediction equipment may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 6 It is merely an example of the power system risk prediction device / power system risk prediction equipment 6 and does not constitute a limitation of the power system risk prediction device / power system risk prediction equipment 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access equipment, buses, etc.

[0129] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0130] In some embodiments, the memory 61 may be an internal storage unit of the power system risk prediction device / power system risk prediction equipment 6, such as a hard disk or memory of the power system risk prediction device / power system risk prediction equipment 6. In other embodiments, the memory 61 may also be an external storage device of the power system risk prediction device / power system risk prediction equipment 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the power system risk prediction device / power system risk prediction equipment 6. Further, the memory 61 may also include both the internal storage unit of the power system risk prediction device / power system risk prediction equipment 6 and an external storage device. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0131] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0132] An embodiment of the present application provides a computer program product. When the computer program product runs on a power system risk prediction device, the power system risk prediction device implements the steps in any of the above-mentioned method embodiments.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the power system risk prediction device / power system risk prediction equipment, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0134] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0136] In the embodiments provided in the present application, it should be understood that the disclosed power system risk prediction device / power system risk prediction equipment and method can be implemented in other ways. For example, the power system risk prediction device / power system risk prediction device embodiment described above is only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for predicting power system risks, characterized in that: include: Acquire first historical data, real-time environmental data and real-time operation data of the power system; wherein the first historical data includes voltage data, current data, frequency data, time, weather, location and type of fault when a fault occurs in the power system, the real-time environmental data includes time and weather, and the real-time operation data includes voltage data, current data and frequency data; Determine multiple initial fault groups and multiple second historical data based on the first historical data and the real-time environmental data; wherein the initial fault group includes the location and type of each fault that occurs successively or concurrently in the power system, and the second historical data includes voltage data, current data and frequency data of the power system corresponding to the initial fault group; Calculate each of the second historical data and the real-time operation data to obtain a first matching degree; wherein the first matching degree is used to reflect the similarity between the second historical data and the real-time operation data; Based on each of the first matching degrees and the corresponding initial fault groups, a real-time predicted fault group is obtained; wherein the real-time predicted fault group includes the location and type of each fault that will occur successively or concurrently in the future power system; The risk information is determined based on the real-time predicted fault group and the first historical data; wherein the risk information is used to reflect the severity of each fault that may occur in the power system in the future.

2. The power system risk prediction method according to claim 1, characterized in that: The determining of a plurality of initial fault groups and a plurality of second historical data based on the first historical data and the real-time environment data comprises: According to the real-time environment data, third historical data is obtained by filtering from the first historical data; wherein the third historical data includes the time, location and type of each fault occurring in the power system corresponding to the real-time environment data; Obtain multiple first fault groups according to the third historical data; wherein the first fault groups include the locations and types of each fault that occurs successively or concurrently in the power system; Determine whether there is an inclusion relationship between every two of the first fault groups; If there is an inclusion relationship between the first fault groups, merging the corresponding first fault groups to obtain the initial fault group; The corresponding second historical data is obtained according to the first historical data and each of the initial fault groups.

3. The power system risk prediction method according to claim 2, characterized in that: The obtaining of a plurality of first fault groups according to the third historical data comprises: Calculating the support of each item set in the third historical data; wherein the item set includes a single item set and a multi-item set, the single item set includes the location and type of a single fault in the power system, the multi-item set includes the locations and types of multiple faults in the power system, and the support is used to reflect the frequency of occurrence of the item set in the third historical data; Determining whether each support exceeds a support threshold; If there is an item set whose support exceeds the support threshold, the corresponding item set is determined as the first fault group.

4. The power system risk prediction method according to claim 2, characterized in that: The method further comprises: If there is no inclusion relationship between the first failure groups, each of the first failure groups is determined as the corresponding initial failure group.

5. The power system risk prediction method according to claim 1, characterized in that: The calculating the first matching degree from each of the second historical data and the real-time operation data respectively includes: Obtain a plurality of first state vectors according to the real-time operation data; Obtaining a corresponding second state vector according to each of the second historical data; Calculating the distance between each of the second state vectors and the corresponding first state vector; The corresponding first matching degree is obtained according to each of the distances.

6. The power system risk prediction method according to claim 1, characterized in that: The obtaining of a real-time predicted fault group based on each of the first matching degrees and the corresponding initial fault group includes: Determine whether the first matching degree exceeds a matching degree threshold; If there is a first matching degree exceeding the matching degree threshold, the real-time predicted fault group is determined according to the initial fault group corresponding to the largest first matching degree.

7. The power system risk prediction method according to claim 6, characterized in that: The method further comprises: If the first matching degrees do not exceed the matching degree threshold, the faults in the initial fault groups are randomly combined to obtain a second abnormal combination; Obtaining a prediction model according to each of the initial fault groups and the corresponding second historical data; Input each of the second abnormal combinations into the prediction model to obtain corresponding first operation data; wherein the first operation data includes voltage data, current data and frequency data; Calculate the first operation data and the real-time operation data to obtain a corresponding second matching degree; wherein the second matching degree is used to reflect the similarity between the first operation data and the real-time operation data; Obtaining a plurality of third abnormal combinations according to each of the second abnormal combinations and the corresponding second matching degrees; The real-time predicted fault group is obtained by iteratively optimizing each of the third abnormal combinations.

8. The power system risk prediction method according to claim 7, characterized in that: The determining risk information based on the real-time predicted fault group and the first historical data includes: Acquire fourth historical data of the power system; wherein the fourth historical data includes voltage data, current data and frequency data when the power system operates normally; Obtaining second operating data according to the real-time predicted fault group and the prediction model; wherein the second operating data includes voltage data, current data and frequency data; Obtaining the deviation corresponding to the real-time predicted fault group according to the second operating data and the fourth historical data; wherein the deviation is used to reflect the impact of each fault in the real-time predicted fault group on system stability, and the deviation includes voltage deviation, current deviation and frequency deviation; Obtaining a real-time fault range according to the real-time predicted fault group and the first historical data; wherein the real-time fault range is the impact range of each fault in the real-time predicted fault group; The risk information is obtained according to the real-time fault range and the deviation.

9. A power system risk prediction device, characterized in that: include: an acquisition module, configured to acquire first historical data, real-time environmental data, and real-time operation data of the power system; wherein the first historical data includes voltage data, current data, frequency data, time, weather, location, and type of fault when a fault occurs in the power system, the real-time environmental data includes time and weather, and the real-time operation data includes voltage data, current data, and frequency data; An initial module, configured to determine a plurality of initial fault groups and a plurality of second historical data based on the first historical data and the real-time environmental data; wherein the initial fault group includes the location and type of each fault that occurs successively or concurrently in the power system, and the second historical data includes voltage data, current data and frequency data of the power system corresponding to the initial fault group; A matching degree module, used to calculate the first matching degree for each of the second historical data and the real-time operation data; wherein the first matching degree is used to reflect the similarity between the second historical data and the real-time operation data; A real-time prediction module, configured to obtain a real-time predicted fault group based on each of the first matching degrees and the corresponding initial fault group; wherein the real-time predicted fault group includes the location and type of each fault that will occur successively or concurrently in the future power system; A risk module is used to determine risk information based on the real-time predicted fault group and the first historical data; wherein the risk information is used to reflect the severity of each fault that may occur in the power system in the future.

10. A power system risk prediction device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images