Power grid anomaly detection method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a power grid anomaly detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring real-time power data of a target power system; the target power system comprises a plurality of power areas; according to the real-time electric power data, calculating an abnormal probability value of the target electric power system and an abnormal weight of each electric power region; when the abnormal probability value is greater than a preset threshold value, calculating a failure risk value of each power region in combination with the abnormal probability value and the abnormal weight of each power region; and determining the influence of the power region on the target power system according to the failure risk value. By adopting the method, the abnormal state can be accurately detected.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a power grid anomaly detection method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the continuous development of society and the continuous growth of electricity demand, the operational stability and safety of the power grid are particularly important. As a key link in power system management, power grid status monitoring technology can monitor the operating status of power grid equipment in real time, evaluate its performance indicators, and ensure the safe and stable operation of the power grid. At present, power grid status monitoring usually relies on big data analysis and Internet of Things technology to identify and warn potential abnormal situations by collecting equipment operation data.

[0003] However, there are still some problems in the application of related power grid anomaly monitoring technologies. First, some technologies are difficult to achieve comprehensive coverage of large-scale power grid systems, resulting in insufficient integrity and accuracy of monitoring data, which affects the recognition of abnormal conditions. Secondly, most existing abnormality monitoring methods are based on static threshold settings, which have poor adaptability to complex and changeable power grid operating environments and are difficult to accurately evaluate the abnormal state of equipment in real time. Therefore, there is a lack of a method that can accurately detect abnormal power grid conditions. Summary of the invention

[0004] Based on this, it is necessary to provide a power grid anomaly detection method, device, computer equipment, computer-readable storage medium and computer program product that can accurately detect abnormal conditions in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting anomalies in a power grid, the method comprising:

[0006] Acquiring real-time power data of a target power system; the target power system includes multiple power areas;

[0007] Calculating the abnormal probability value of the target power system and the abnormal weight of each of the power areas according to the real-time power data;

[0008] When the abnormal probability value is greater than a preset threshold, the failure risk value of each of the power areas is calculated by combining the abnormal probability value and the abnormal weight of each of the power areas;

[0009] An influence of the power area on the target power system is determined according to the failure risk value.

[0010] In one embodiment, the real-time power data includes operating parameters and status information of each of the power areas; and calculating the abnormal probability value of the target power system and the abnormal weight of each of the power areas according to the real-time power data includes:

[0011] Calculating the number of fluctuation items of each power area according to each operating parameter, and calculating the abnormal probability value according to the number of fluctuation items and the proportion coefficient of each power area;

[0012] The device retention probability of each of the power areas is calculated according to each of the state information, and the abnormal weight of each of the power areas is determined according to the device retention probability.

[0013] In one embodiment, the operating parameters include real-time voltage data, real-time current data, grid frequency fluctuation data, and load fluctuation data; the power area includes a power transmission system, a substation system, and a power distribution system;

[0014] The calculating the number of fluctuation items of each power area according to each operating parameter includes:

[0015] Calculating the number of voltage fluctuation items and the number of current fluctuation items of the power transmission system respectively according to the real-time voltage data and the real-time current data collected from the power transmission system;

[0016] Calculating the number of power grid frequency fluctuation items of the substation system according to the power grid frequency fluctuation data collected from the substation system;

[0017] The number of electric load fluctuation items of the power distribution system is calculated based on the load fluctuation data collected from the power distribution system.

[0018] In one embodiment, the calculating the abnormal probability value according to the number of fluctuation items and the proportion coefficient of each power area includes:

[0019] Obtaining a first abnormality probability value according to the number of voltage fluctuation items, the number of current fluctuation items, and a first proportion coefficient;

[0020] Obtaining a second abnormal probability value according to the number of power grid frequency fluctuation items and the second proportion coefficient;

[0021] Obtaining a third abnormal probability value according to the number of electric load fluctuation items and the third proportion coefficient;

[0022] The first abnormal probability value, the second abnormal probability value, and the third abnormal probability value are weighted to obtain the abnormal probability value.

[0023] In one embodiment, the state information includes a plurality of state information parameters; calculating the device retention probability of each power area according to each state information, and determining the abnormal weight of each power area according to the device retention probability, including:

[0024] Calculate the device retention probability of each state information parameter according to each state information parameter in each state information;

[0025] Calculate the Manhattan difference distance between the device retention probability of each state information parameter in each state information and the target state probability;

[0026] The abnormal weight of each power area is determined according to the number of target state information parameters in each state information; the target state information parameter is the state information whose Manhattan difference distance is greater than a preset distance.

[0027] In one embodiment, determining the abnormal weight of each power area according to the number of target state information parameters in each state information includes:

[0028] When the number is less than or equal to a first preset threshold number, determining that the abnormal weight is a first abnormal weight;

[0029] When the number is greater than or equal to the first preset threshold number and less than the second preset threshold number, determining that the abnormal weight is the second abnormal weight;

[0030] When the number is greater than or equal to the second preset threshold number and less than the third preset threshold number, determining that the abnormal weight is the third abnormal weight;

[0031] When the number is greater than or equal to the third preset threshold number and less than a fourth preset threshold number, it is determined that the abnormal weight is a fourth abnormal weight.

[0032] In one embodiment, determining the influence of the power area on the target power system according to the failure risk value includes:

[0033] When the risk failure value is less than a first judgment threshold, it is determined that the power area has no impact on the power system;

[0034] When the risk failure value is greater than or equal to the first judgment threshold and less than the second judgment threshold, it is determined that the power area has an intermittent impact on the target power system;

[0035] When the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold, it is determined that the power area has a continuous impact on the target power system.

[0036] In a second aspect, the present application provides a power grid anomaly detection device, the device comprising:

[0037] An acquisition module, used to acquire real-time power data of a target power system; the target power system includes multiple power areas;

[0038] A first calculation module, used for calculating an abnormal probability value of the target power system and an abnormal weight of each of the power areas according to the real-time power data;

[0039] A second calculation module, configured to calculate a failure risk value of each of the power areas by combining the abnormal probability value and an abnormal weight of each of the power areas when the abnormal probability value is greater than a preset threshold;

[0040] An anomaly detection module is used to determine the impact of the power area on the target power system according to the failure risk value.

[0041] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0043] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0044] The above-mentioned power grid anomaly detection method, device, computer equipment, computer-readable storage medium and computer program product can accurately calculate the abnormal probability value of the target power system and the failure risk value of each power area by real-time monitoring of the real-time power data of the power system. Then, combined with the abnormal probability and regional weight, the failure risk value of each area can be effectively evaluated. Finally, according to the risk failure value, the impact of the power area on the target power system is determined to accurately locate the abnormal position of the target power. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions 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 related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A schematic diagram of a flow chart of a power grid anomaly detection method in one embodiment;

[0047] Figure 2 is a structural block diagram of a power grid anomaly detection device in one embodiment;

[0048] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] In one embodiment, Figure 1 As shown, a method for detecting abnormalities in a power grid is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0051] Step S102, acquiring real-time power data of a target power system; the target power system includes multiple power areas.

[0052] The target power system is the system that needs to be tested currently, which can be power systems in different regions or power infrastructure with specific functions.

[0053] Furthermore, the target power system includes multiple power areas. Optionally, each power area can perform different functions. Exemplarily, the power area can be a power transmission system, a substation system, and a power distribution system.

[0054] Optionally, the real-time power system data of the target power system can be collected in real time through power sensors, monitoring equipment, etc.

[0055] Among them, real-time power data refers to the real-time monitoring data related to power transmission, distribution, and usage generated during the operation of the target power system.

[0056] Optionally, the real-time power data may include voltage data, current data, power data, load data, etc.

[0057] Step S104, calculating the abnormal probability value of the target power system and the abnormal weight of each power area according to the real-time power data.

[0058] In this embodiment, key indicators in real-time power data, such as voltage, current, and frequency, are analyzed to identify possible abnormalities. The identified abnormalities are converted into probability values, which represent the possibility of abnormalities occurring in the target power system.

[0059] Optionally, the abnormal probability value can be determined by calculating the number of fluctuation items of real-time power data, because the number of fluctuation items reflects the instability and frequency of change of the target power system during operation. Furthermore, the number of fluctuation items represents the number of times the operating parameters of the target power system exceed the normal range or change significantly within a certain time range, so the abnormal probability value can be effectively calculated by calculating the number of fluctuation items.

[0060] Since the target power system includes multiple power areas, the operating status of each area has different effects on the target power system. Therefore, weights are assigned to each area based on the real-time power data of each power area.

[0061] Optionally, the abnormal weight of each power area may be determined by calculating the equipment retention probability of each power area.

[0062] Among them, the equipment retention probability reflects the possibility that the equipment will work normally within the range of its status information. Therefore, by calculating the retention probability of equipment in each power area, the health status of the equipment in the area can be more accurately assessed, and the abnormal weight of the area can be determined accordingly. This method can identify areas with potential risks and improve the accuracy of overall risk assessment.

[0063] Optionally, devices in different power zones may have different workloads and environmental conditions, and their retention probabilities may be different. By calculating the retention probabilities of devices one by one, different abnormal weights can be assigned according to the specific conditions of each power zone.

[0064] Step S106: when the abnormal probability value is greater than a preset threshold, the failure risk value of each power area is calculated by combining the abnormal probability value and the abnormal weight of each power area.

[0065] When the abnormal probability value of the power system exceeds the preset threshold, it is necessary to further evaluate the potential failure risk of each power area.

[0066] The preset threshold is a pre-set indicator used to measure whether the failure risk value needs to be calculated, and the preset threshold can be set according to the actual application scenario. Exemplarily, the preset threshold is obtained after analyzing a large amount of historical data.

[0067] Optionally, when the abnormal probability value is greater than a preset threshold, the abnormal probability value is multiplied by the abnormal weight of each power area to obtain a failure risk value of each power area.

[0068] For example, the failure risk value can be calculated by combining formula (1):

[0069] Formula (1)

[0070] in, is the abnormal weight of the power area, and gl is the abnormal probability value.

[0071] In this way, by combining the abnormal probability value and the abnormal weight, the failure risk value can be calculated more accurately.

[0072] Step S108: determining the impact of the power area on the target power system according to the failure risk value.

[0073] Optionally, the failure risk value may be compared with a plurality of judgment thresholds to classify the failure risk values ​​corresponding to the power areas, and the impact of the power areas on the target power system may be determined based on the classification results.

[0074] Exemplarily, when the failure risk value is lower than the first judgment threshold, the power area is classified as a low-risk area, indicating that the operating condition of the area is stable.

[0075] When the failure risk value is between the first judgment threshold and the second judgment threshold, the power area is divided into a medium risk area.

[0076] When the failure risk value is higher than the second judgment threshold, the power area is divided into a high-risk area.

[0077] In the above-mentioned power grid anomaly detection method, by real-time monitoring of the real-time power data of the power system, the abnormal probability value of the target power system and the failure risk value of each power area can be accurately calculated. Then, by combining the abnormal probability and the regional weight, the failure risk value of each area can be effectively evaluated. Finally, according to the risk failure value, the impact of the power area on the target power system is determined to accurately locate the abnormal position of the target power.

[0078] In one of the embodiments, the real-time power data includes operating parameters and status information of each power area; based on the real-time power data, calculating the abnormal probability value of the target power system includes: calculating the number of fluctuation items of each power area based on each operating parameter, and calculating the abnormal probability value based on the number of fluctuation items and the proportion coefficient of each power area.

[0079] Optionally, operating parameters are extracted from real-time power data, fluctuations of operating parameters are analyzed, and the number of fluctuations within a preset time period, i.e., the number of fluctuation items, is identified. The fluctuation can be determined by comparing the real-time index of the parameter with its set standard value or historical average. When the operating parameter exceeds the normal range, a fluctuation is recorded.

[0080] Optionally, for each power region, based on the calculated number of fluctuation items and the proportion coefficient of the region, the abnormal probability value of the region is calculated. The proportion coefficient can reflect the importance of each region in the entire power system or the degree of influence of its fluctuation on the overall stability of the system.

[0081] By comprehensively calculating the number of fluctuation items and the proportion coefficient of each power area, the abnormal probability value of the entire power system is obtained. This value reflects the possibility of abnormality in the power system under the current state.

[0082] In this embodiment, the fluctuation situation of each power area can be quantified into a specific abnormal probability value, thereby providing a scientific basis for risk assessment and decision-making of the power system.

[0083] Furthermore, in one of the embodiments, the above-mentioned operating parameters include real-time voltage data, real-time current data, grid frequency fluctuation data and load fluctuation data; the power area includes a power transmission system, a substation system and a power distribution system; the above-mentioned calculation of the number of fluctuation items of each power area according to each operating parameter includes: calculating the number of voltage fluctuation items and the number of current fluctuation items of the power transmission system according to the real-time voltage data and the real-time current data collected from the power transmission system; calculating the number of grid frequency fluctuation items of the substation system according to the grid frequency fluctuation data collected from the substation system; and calculating the number of electric load fluctuation items of the power distribution system according to the load fluctuation data collected from the power distribution system.

[0084] In this embodiment, the operating parameters include voltage data, real-time current data, grid frequency fluctuation data, and load fluctuation data; the power system is divided into three main power areas, including a power transmission system, a substation system, and a power distribution system.

[0085] Optionally, real-time voltage data and real-time current data are collected from the power transmission system to calculate the number of voltage fluctuation items and the number of current fluctuation items, respectively. The number of fluctuation items indicates the number of times the voltage or current fluctuates abnormally within a certain period of time.

[0086] For example, the voltage fluctuation term number can be calculated according to formula (2): ,

[0087] Formula (2)

[0088] in, It is the rated output voltage of the power supply company in the power transmission system; is the real-time voltage data on the nth power transmission line.

[0089] For example, the number of current fluctuation terms can be calculated according to formula (3): ,

[0090] Formula (3)

[0091] in, It is the rated output current of the power supply company in the power transmission system; It is the real-time current data on the nth power transmission line.

[0092] Optionally, the grid frequency fluctuation data collected from the substation system is used to calculate the number of grid frequency fluctuation items, which represents the number of times the grid frequency fluctuates beyond a normal range.

[0093] For example, the number of grid frequency fluctuation items can be calculated according to formula (4):

[0094] Formula (4)

[0095] in, is the number of fluctuations of the grid frequency of the substation system; are the grid input frequency and output frequency of the substation system respectively; express The average duration of the fluctuation of the grid frequency in the substation system; Respectively represent the substation system The grid frequency data and fluctuation duration when the grid frequency fluctuation occurs for the first time.

[0096] Optionally, load fluctuation data collected from the power distribution system is used to calculate the number of load fluctuation items, which represents the number of times the load fluctuates significantly.

[0097] For example, the number of load fluctuation items can be calculated according to formula (5):

[0098] Formula (5)

[0099] In this way, the stability of each key operating parameter in each power area can be evaluated separately, providing basic data for the subsequent calculation of abnormal probability values.

[0100] Furthermore, in one of the embodiments, the above-mentioned calculation of the abnormal probability value based on the number of fluctuation items and the proportion coefficient of each power area includes: obtaining a first abnormal probability value based on the number of voltage fluctuation items, the number of current fluctuation items and the first proportion coefficient; obtaining a second abnormal probability value based on the number of grid frequency fluctuation items and the second proportion coefficient; obtaining a third abnormal probability value based on the number of electric load fluctuation items and the third proportion coefficient; and weighting the first abnormal probability value, the second abnormal probability value and the third abnormal probability value to obtain the abnormal probability value.

[0101] In this embodiment, the number of fluctuation items corresponding to different power areas and their corresponding proportion coefficients are calculated to obtain an abnormal probability value.

[0102] Among them, the proportion coefficient is used to measure the influence weight of different types on the overall abnormal probability value. In this embodiment, the first proportion coefficient, the second proportion coefficient and the third proportion coefficient are used to distinguish the proportion coefficients of different power areas. Similarly, the first abnormal probability value, the second abnormal probability value and the third abnormal probability value are used to distinguish the abnormal probability values ​​of different power areas.

[0103] Optionally, a first abnormality probability value is calculated by the number of voltage fluctuation items, the number of current fluctuation items and the corresponding first proportion coefficient, and the first abnormality probability value reflects the degree of abnormality of the power transmission system.

[0104] Optionally, a second abnormality probability value is calculated based on the number of grid frequency fluctuation items and the corresponding second proportion coefficient, and the second abnormality probability value reflects the abnormality degree of the substation system.

[0105] Optionally, a third abnormality probability value is calculated by the number of electric load fluctuation items and the corresponding third proportion coefficient, and the third abnormality probability value reflects the degree of abnormality of the power distribution system.

[0106] Optionally, the first abnormal probability value, the second abnormal probability value, and the third abnormal probability value calculated above are weighted and combined according to certain weights to obtain a final overall abnormal probability value.

[0107] Exemplarily, the abnormal probability value is calculated according to formula (6).

[0108] Formula (6)

[0109] in is the coefficient of the number of fluctuation items in the power transmission system, is the coefficient of the number of fluctuation items in the substation system, is the coefficient of the number of fluctuation items in the power distribution system, and Both are greater than 0.

[0110] In the above embodiment, different power areas play different functions in the power grid, so the abnormal fluctuations of each power area have different effects on the overall system. By calculating the number of fluctuation items in each area and introducing the proportion coefficient, the impact of these fluctuations on the overall system can be more accurately reflected, thereby improving the accuracy of abnormality detection.

[0111] In one of the embodiments, the above-mentioned calculation of the abnormal weight of each power area based on the real-time power data includes: calculating the equipment retention probability of each power area according to each state information, and determining the abnormal weight of each power area according to the equipment retention probability.

[0112] Real-time power data includes status information, so in this embodiment, the equipment retention probability of each power area is calculated according to the status information of different power areas, and the abnormal weight of each power area is determined according to the equipment retention probability.

[0113] Exemplarily, the status information includes multiple status information parameters, such as voltage, current, temperature, vibration, etc. By analyzing the status information, it can be determined whether the device is operating within the normal range, thereby calculating the probability that the device continues to work normally under current conditions, that is, the device retention probability.

[0114] For example, abnormal status information of equipment is often a precursor to potential failure. For example, abnormal voltage fluctuation may indicate equipment overload or aging. By calculating the retention probability, this risk can be quantified and equipment or areas that may fail can be identified in advance.

[0115] Further, in one of the embodiments, the above-mentioned status information includes multiple status information parameters; the equipment retention probability of each power area is calculated according to each status information, and the abnormal weight of each power area is determined according to the equipment retention probability, including: according to each status information parameter in each status information, the equipment retention probability of each status information parameter is calculated; the Manhattan difference distance from the equipment retention probability of each status information parameter in each status information to the target status probability is calculated; according to the number of target status information parameters in each status information, the abnormal weight of each power area is determined; the target status information parameter is the status information whose Manhattan difference distance is greater than the preset distance.

[0116] Optionally, for each state information parameter, the probability of the device maintaining normal operation under the state information is calculated to obtain the device retention probability. The device retention probability reflects the possibility of the device maintaining normal operation under the current state.

[0117] Exemplarily, the calculation formula of the device retention probability is shown in formula (7):

[0118] Formula (7)

[0119] in, is the device sequence converted and output by the device sequence conversion layer at the i-th monitoring time point t The probability of retention in the M monitoring time points; for The mean of the normal distribution it follows; for The standard deviation of the normal distribution it follows; is the retention probability when the device sequence is a, where ; is the retention probability when the device sequence is b, where .

[0120] The conversion process of device serialization is shown in formula (8):

[0121] Formula (8)

[0122] in, The equipment sequence of each system equipment parameter and performance index at the monitoring time point t; is the equipment sequence at the monitoring time point t-1; is the equipment sequence at the monitoring time point t+1; is the equipment sequence with normal distribution at the monitoring time point ti; is the total number of monitoring time points; The upper limit value of the status information parameter monitored by the device; It is the lower limit value of the status information parameter monitored by the equipment; is the equipment sequence at the i-th monitoring time point t The device sequence converted and output by the device sequence conversion layer; is the equipment sequence at the i-1th monitoring time point t-1 The device sequence converted and output by the device sequence conversion layer; is the conversion rate of the device sequence conversion layer at the monitoring time point t;

[0123] Optionally, for each state information parameter, the Manhattan difference distance between its device retention probability and the target state probability is calculated. This distance represents the deviation between the current state and the ideal state. The larger the deviation, the more abnormal the state information parameter may be.

[0124] Optionally, identify those state information parameters whose Manhattan difference distance exceeds a preset threshold, that is, the target state information parameters. According to the number of these target state information parameters, determine the abnormal weight of each power area. The abnormal weight reflects the degree of abnormality of the equipment in the power area. The more target state information parameters, the higher the possibility of abnormality in the area.

[0125] Further, in one of the embodiments, the above-mentioned determination of the abnormal weight of each power area based on the number of target state information parameters in each state information includes: when the number is less than or equal to the first preset threshold number, the abnormal weight is determined to be the first abnormal weight; when the number is greater than or equal to the first preset threshold number and less than the second preset threshold number, the abnormal weight is determined to be the second abnormal weight; when the number is greater than or equal to the second preset threshold number and less than the third preset threshold number, the abnormal weight is determined to be the third abnormal weight; when the number is greater than or equal to the third preset threshold number and less than the fourth preset threshold number, the abnormal weight is determined to be the fourth abnormal weight.

[0126] In this embodiment, the abnormal weights of each power area are divided into different levels by setting a plurality of preset thresholds.

[0127] First, the Manhattan difference distance of each state information parameter is calculated to determine whether it is greater than a preset threshold, and the number of target state information parameters that meet the conditions is counted.

[0128] Optionally, when the number of target state information parameters is less than or equal to a first preset threshold number, the abnormal weight of the power area is determined to be a first abnormal weight.

[0129] Optionally, when the number of target state information parameters is greater than or equal to a first preset threshold number and less than a second preset threshold number, the abnormal weight of the power area is determined to be a second abnormal weight.

[0130] Optionally, when the number of target state information parameters is greater than or equal to a second preset threshold number and less than a third preset threshold number, it is determined that the abnormal weight of the power area is a third abnormal weight.

[0131] Optionally, when the number of target state information parameters is greater than or equal to a third preset threshold number and less than a fourth preset threshold number, it is determined that the abnormal weight of the power area is a fourth abnormal weight.

[0132] One thing that needs to be explained is that in this embodiment, the first preset threshold number, the second preset threshold number, the third preset threshold number and the fourth preset threshold number, and their corresponding first abnormal weight, second abnormal weight, third abnormal weight and fourth abnormal weight are all set according to the actual usage scenario and are not specifically limited in this embodiment.

[0133] Optionally, in other embodiments, different weights may be visualized using different colors. For example, the first abnormal weight may be displayed in red, the second abnormal weight may be displayed in yellow, the third abnormal weight may be displayed in blue, and the fourth abnormal weight may be displayed in green. Among them, red is the most serious abnormal area, and the weight coefficient of the red abnormal area is the largest, and green is the mildest abnormal area, and the weight coefficient of the green abnormal area is the smallest.

[0134] For example, when there is a value greater than or equal to When the Manhattan difference distance of the v state information parameters is greater than D, the area is judged as a red abnormal area; when there is a difference greater than or equal to D among the v state information parameters, the area is judged as a red abnormal area. and less than When the Manhattan difference distance of the state information parameters is greater than D, the area is judged as a yellow abnormal area; when there is a difference greater than or equal to D among the v state information parameters and less than When the Manhattan difference distance of the state information parameters is greater than D, the area is judged as a blue abnormal area; when there is less than or equal to D among the v state information parameters When the Manhattan difference distance of the state information parameter is greater than D, the area is judged as a green abnormal area; wherein D is the distance threshold for area discrimination, that is, the preset distance mentioned in the above embodiment. In this embodiment, the first preset threshold is 0.15, the second preset threshold is 0.45, and the third preset threshold is 0.85. .

[0135] In other embodiments, the Manhattan distance may be calculated using the OPTICS (Ordering points to identify the clustering structure, a density-based clustering analysis algorithm). OPTICS does not rely on global variables to determine clustering, but rather arranges the closest points in space adjacent to each other to obtain a linear ordering of objects in a data set. The sequence generated after sorting stores the distances between adjacent points, and ultimately generates a clustering tree diagram.

[0136] In the above embodiment, the abnormal weight corresponding to each power area can be effectively calculated through this classification method.

[0137] In one of the embodiments, the above-mentioned determination of the impact of the power area on the target power system based on the failure risk value includes: when the risk failure value is less than the first judgment threshold, it is determined that the power area has no impact on the power system; when the risk failure value is greater than or equal to the first judgment threshold and less than the second judgment threshold, it is determined that the power area has an intermittent impact on the target power system; when the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold, it is determined that the power area has a continuous impact on the target power system.

[0138] Optionally, when the risk failure value is less than the first judgment threshold, it is judged that the power area is within a controllable range, the target power system can operate normally, and it is judged that the power area has no impact on the power system.

[0139] Optionally, when the risk failure value is greater than or equal to a first judgment threshold and less than a second judgment threshold, it is determined that the regional discontinuity of the power grid affects the performance of the target power system.

[0140] Optionally, when the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold, it is judged that the power area causes performance failure to the target power system and has a lasting impact on the target power system.

[0141] It should be noted that in this embodiment, the first judgment threshold, the second judgment threshold and the third judgment threshold are calculated based on historical data.

[0142] Furthermore, an emergency repair strategy may be specified according to the impact of the power area on the target power system.

[0143] Optionally, when the risk failure value is less than the first judgment threshold, there is no need to specify an emergency repair strategy.

[0144] Optionally, when the risk failure value is greater than or equal to the first judgment threshold and less than the second judgment threshold, a maintenance plan needs to be made for the power area.

[0145] Optionally, when the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold, it is necessary to designate power grid maintenance personnel to immediately perform maintenance on the abnormal area.

[0146] In the above embodiment, by comparing the risk failure value with the judgment threshold, it is determined that each power area has different impacts on the target power system, and an emergency repair strategy is executed, which can optimize maintenance management efficiency, reduce unexpected power outages and operating costs, and thus reduce overall operating risks.

[0147] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0148] Based on the same inventive concept, the embodiment of the present application also provides a power grid anomaly detection device for implementing the power grid anomaly detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power grid anomaly detection device embodiments provided below can refer to the limitations of the power grid anomaly detection method above, and will not be repeated here.

[0149] In an exemplary embodiment, Figure 2 As shown, a power grid anomaly detection device is provided, comprising: an acquisition module, a first calculation module, a second calculation module and an anomaly detection module, wherein:

[0150] The acquisition module 210 is used to acquire real-time power data of a target power system; the target power system includes multiple power areas.

[0151] The first calculation module 220 is used to calculate the abnormal probability value of the target power system and the abnormal weight of each power area according to the real-time power data.

[0152] The second calculation module 230 is used to calculate the failure risk value of each power area by combining the abnormal probability value and the abnormal weight of each power area when the abnormal probability value is greater than a preset threshold.

[0153] The anomaly detection module 240 is used to determine the impact of the power area on the target power system according to the failure risk value.

[0154] In one embodiment, the real-time power data includes operating parameters and status information of each power area; the first calculation module includes:

[0155] The probability calculation unit is used to calculate the number of fluctuation items in each power area according to each operating parameter, and calculate the abnormal probability value according to the number of fluctuation items and the proportion coefficient of each power area.

[0156] The weight calculation unit is used to calculate the equipment retention probability of each power area according to each state information, and determine the abnormal weight of each power area according to the equipment retention probability.

[0157] In one embodiment, the operating parameters include real-time voltage data, real-time current data, grid frequency fluctuation data, and load fluctuation data; the power area includes a power transmission system, a substation system, and a power distribution system; and the probability calculation unit includes:

[0158] The first item number calculation subunit is used to calculate the number of voltage fluctuation items and the number of current fluctuation items of the power transmission system according to the real-time voltage data and the real-time current data collected from the power transmission system.

[0159] The second item number calculation subunit is used to calculate the number of power grid frequency fluctuation items of the substation system according to the power grid frequency fluctuation data collected from the substation system.

[0160] The third item number calculation subunit is used to calculate the number of electric load fluctuation items of the power distribution system according to the load fluctuation data collected from the power distribution system.

[0161] In one embodiment, the probability calculation unit includes:

[0162] The first abnormality calculation subunit is used to obtain a first abnormality probability value according to the number of voltage fluctuation items, the number of current fluctuation items and the first proportion coefficient.

[0163] The second abnormality calculation subunit is used to obtain a second abnormality probability value according to the number of power grid frequency fluctuation items and the second proportion coefficient.

[0164] The third abnormality calculation subunit is used to obtain a third abnormality probability value according to the number of electric load fluctuation items and the third proportion coefficient.

[0165] The probability calculation subunit is used to weight the first abnormal probability value, the second abnormal probability value and the third abnormal probability value to obtain an abnormal probability value.

[0166] In one embodiment, the state information includes a plurality of state information parameters, and the weight calculation unit includes:

[0167] The retention probability calculation subunit is used to calculate the device retention probability of each state information parameter according to each state information parameter in each state information.

[0168] The distance calculation subunit is used to calculate the Manhattan difference distance between the device retention probability of each state information parameter in each state information and the target state probability.

[0169] The abnormal weight calculation subunit is used to determine the abnormal weight of each power area according to the number of target state information parameters in each state information; the target state information parameter is the state information whose Manhattan difference distance is greater than a preset threshold number.

[0170] In one embodiment, the above-mentioned abnormal weight calculation subunit includes:

[0171] The first weight calculation subunit is used to determine that the abnormal weight is a first abnormal weight when the number is less than or equal to a first preset threshold number.

[0172] The second weight calculation subunit is used to determine that the abnormal weight is a second abnormal weight when the number is greater than or equal to the first preset threshold number and less than the second preset threshold number.

[0173] The third weight calculation grandchild unit is used to determine that the abnormal weight is a third abnormal weight when the number is greater than or equal to the second preset threshold number and less than the third preset threshold number.

[0174] The fourth weight calculation grandchild unit is used to determine that the abnormal weight is a fourth abnormal weight when the number is greater than or equal to the third preset threshold number and less than the fourth preset threshold number.

[0175] In one embodiment, the anomaly detection module includes:

[0176] The first judgment unit is used to judge that the power area has no impact on the power system when the risk failure value is less than a first judgment threshold.

[0177] The second judgment unit is used to judge whether the power area has an intermittent impact on the target power system when the risk failure value is greater than or equal to the first judgment threshold and less than the second judgment threshold.

[0178] The third judgment unit is used to judge whether the power area has a continuous impact on the target power system when the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold.

[0179] Each module in the above-mentioned power grid anomaly detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0180] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store real-time power data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a power grid anomaly detection method is implemented.

[0181] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0182] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: acquiring real-time power data of a target power system; the target power system includes multiple power areas; based on the real-time power data, calculating an abnormal probability value of the target power system and an abnormal weight of each power area; when the abnormal probability value is greater than a preset threshold, calculating a failure risk value of each power area in combination with the abnormal probability value and the abnormal weight of each power area; and determining the impact of the power area on the target power system based on the failure risk value.

[0183] In one embodiment, when the processor executes the computer program, the following steps are further implemented: the number of fluctuation items of each power area is calculated according to each operating parameter, and the abnormal probability value is calculated according to the number of fluctuation items and the proportion coefficient of each power area; the equipment retention probability of each power area is calculated according to each state information, and the abnormal weight of each power area is determined according to the equipment retention probability. The real-time power data includes the operating parameters and state information of each power area.

[0184] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the number of fluctuation items of each power area is calculated according to each operating parameter, including: according to the real-time voltage data and real-time current data collected from the power transmission system, the number of voltage fluctuation items and the number of current fluctuation items of the power transmission system are calculated respectively; according to the power grid frequency fluctuation data collected from the substation system, the number of power grid frequency fluctuation items of the substation system is calculated; according to the load fluctuation data collected from the power distribution system, the number of electric load fluctuation items of the power distribution system is calculated. Among them, the operating parameters include real-time voltage data, real-time current data, power grid frequency fluctuation data and load fluctuation data; the power area includes the power transmission system, the substation system and the power distribution system.

[0185] In one embodiment, when the processor executes the computer program, the following steps are also implemented: a first abnormal probability value is obtained based on the number of voltage fluctuation items, the number of current fluctuation items and the first accounting coefficient; a second abnormal probability value is obtained based on the number of grid frequency fluctuation items and the second accounting coefficient; a third abnormal probability value is obtained based on the number of electric load fluctuation items and the third accounting coefficient; and the first abnormal probability value, the second abnormal probability value and the third abnormal probability value are weighted to obtain an abnormal probability value.

[0186] In one embodiment, when the processor executes the computer program, the following steps are also implemented: according to each state information parameter in each state information, the device retention probability of each state information parameter is calculated; the Manhattan difference distance from the device retention probability of each state information parameter in each state information to the target state probability is calculated; according to the number of target state information parameters in each state information, the abnormal weight of each power area is determined; the target state information parameter is the state information whose Manhattan difference distance is greater than the preset threshold number. Wherein, the state information includes multiple state information parameters.

[0187] In one embodiment, when the processor executes the computer program, the following steps are also implemented: when the number is less than or equal to the first preset threshold number, the abnormality weight is determined to be the first abnormality weight; when the number is greater than or equal to the first preset threshold number and less than the second preset threshold number, the abnormality weight is determined to be the second abnormality weight; when the number is greater than or equal to the second preset threshold number and less than the third preset threshold number, the abnormality weight is determined to be the third abnormality weight; when the number is greater than or equal to the third preset threshold number and less than the fourth preset threshold number, the abnormality weight is determined to be the fourth abnormality weight.

[0188] In one embodiment, when the processor executes the computer program, the following steps are also implemented: when the risk failure value is less than the first judgment threshold, it is determined that the power area has no impact on the power system; when the risk failure value is greater than or equal to the first judgment threshold and less than the second judgment threshold, it is determined that the power area has an intermittent impact on the target power system; when the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold, it is determined that the power area has a continuous impact on the target power system.

[0189] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: the number of fluctuation items of each power area is calculated according to each operating parameter, and the abnormal probability value is calculated according to the number of fluctuation items and the proportion coefficient of each power area; the equipment retention probability of each power area is calculated according to each state information, and the abnormal weight of each power area is determined according to the equipment retention probability. The real-time power data includes the operating parameters and state information of each power area.

[0190] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: the number of fluctuation items of each power area is calculated according to each operating parameter, and the abnormal probability value is calculated according to the number of fluctuation items and the proportion coefficient of each power area; the equipment retention probability of each power area is calculated according to each state information, and the abnormal weight of each power area is determined according to the equipment retention probability. The real-time power data includes the operating parameters and state information of each power area.

[0191] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the number of fluctuation items of each power area is calculated according to each operating parameter, including: according to the real-time voltage data and real-time current data collected from the power transmission system, the number of voltage fluctuation items and the number of current fluctuation items of the power transmission system are calculated respectively; according to the power grid frequency fluctuation data collected from the substation system, the number of power grid frequency fluctuation items of the substation system is calculated; according to the load fluctuation data collected from the power distribution system, the number of electric load fluctuation items of the power distribution system is calculated. Among them, the operating parameters include real-time voltage data, real-time current data, power grid frequency fluctuation data and load fluctuation data; the power area includes the power transmission system, the substation system and the power distribution system.

[0192] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a first abnormal probability value is obtained based on the number of voltage fluctuation items, the number of current fluctuation items and the first accounting coefficient; a second abnormal probability value is obtained based on the number of grid frequency fluctuation items and the second accounting coefficient; a third abnormal probability value is obtained based on the number of electric load fluctuation items and the third accounting coefficient; and the first abnormal probability value, the second abnormal probability value and the third abnormal probability value are weighted to obtain an abnormal probability value.

[0193] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to each state information parameter in each state information, the device retention probability of each state information parameter is calculated; the Manhattan difference distance from the device retention probability of each state information parameter in each state information to the target state probability is calculated; according to the number of target state information parameters in each state information, the abnormal weight of each power area is determined; the target state information parameter is the state information whose Manhattan difference distance is greater than the preset threshold number. Wherein, the state information includes multiple state information parameters.

[0194] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the number is less than or equal to the first preset threshold number, the abnormality weight is determined to be the first abnormality weight; when the number is greater than or equal to the first preset threshold number and less than the second preset threshold number, the abnormality weight is determined to be the second abnormality weight; when the number is greater than or equal to the second preset threshold number and less than the third preset threshold number, the abnormality weight is determined to be the third abnormality weight; when the number is greater than or equal to the third preset threshold number and less than the fourth preset threshold number, the abnormality weight is determined to be the fourth abnormality weight.

[0195] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the risk failure value is less than the first judgment threshold, it is determined that the power area has no impact on the power system; when the risk failure value is greater than or equal to the first judgment threshold and less than the second judgment threshold, it is determined that the power area has an intermittent impact on the target power system; when the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold, it is determined that the power area has a continuous impact on the target power system.

[0196] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps: acquiring real-time power data of a target power system; the target power system comprises a plurality of power areas; calculating an abnormal probability value of the target power system and an abnormal weight of each power area based on the real-time power data; when the abnormal probability value is greater than a preset threshold, calculating a failure risk value of each power area in combination with the abnormal probability value and the abnormal weight of each power area; and determining the impact of the power area on the target power system based on the failure risk value.

[0197] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: the number of fluctuation items of each power area is calculated according to each operating parameter, and the abnormal probability value is calculated according to the number of fluctuation items and the proportion coefficient of each power area; the equipment retention probability of each power area is calculated according to each state information, and the abnormal weight of each power area is determined according to the equipment retention probability. The real-time power data includes the operating parameters and state information of each power area.

[0198] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the number of fluctuation items of each power area is calculated according to each operating parameter, including: according to the real-time voltage data and real-time current data collected from the power transmission system, the number of voltage fluctuation items and the number of current fluctuation items of the power transmission system are calculated respectively; according to the power grid frequency fluctuation data collected from the substation system, the number of power grid frequency fluctuation items of the substation system is calculated; according to the load fluctuation data collected from the power distribution system, the number of electric load fluctuation items of the power distribution system is calculated. Among them, the operating parameters include real-time voltage data, real-time current data, power grid frequency fluctuation data and load fluctuation data; the power area includes the power transmission system, the substation system and the power distribution system.

[0199] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a first abnormal probability value is obtained based on the number of voltage fluctuation items, the number of current fluctuation items and the first accounting coefficient; a second abnormal probability value is obtained based on the number of grid frequency fluctuation items and the second accounting coefficient; a third abnormal probability value is obtained based on the number of electric load fluctuation items and the third accounting coefficient; and the first abnormal probability value, the second abnormal probability value and the third abnormal probability value are weighted to obtain an abnormal probability value.

[0200] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to each state information parameter in each state information, the device retention probability of each state information parameter is calculated; the Manhattan difference distance from the device retention probability of each state information parameter in each state information to the target state probability is calculated; according to the number of target state information parameters in each state information, the abnormal weight of each power area is determined; the target state information parameter is the state information whose Manhattan difference distance is greater than the preset threshold number. Wherein, the state information includes multiple state information parameters.

[0201] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the number is less than or equal to the first preset threshold number, the abnormality weight is determined to be the first abnormality weight; when the number is greater than or equal to the first preset threshold number and less than the second preset threshold number, the abnormality weight is determined to be the second abnormality weight; when the number is greater than or equal to the second preset threshold number and less than the third preset threshold number, the abnormality weight is determined to be the third abnormality weight; when the number is greater than or equal to the third preset threshold number and less than the fourth preset threshold number, the abnormality weight is determined to be the fourth abnormality weight.

[0202] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the risk failure value is less than the first judgment threshold, it is determined that the power area has no impact on the power system; when the risk failure value is greater than or equal to the first judgment threshold and less than the second judgment threshold, it is determined that the power area has an intermittent impact on the target power system; when the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold, it is determined that the power area has a continuous impact on the target power system.

[0203] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0204] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0205] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting anomalies in a power grid, characterized in that: The method comprises: Acquiring real-time power data of a target power system; the target power system includes multiple power areas; Calculating the abnormal probability value of the target power system and the abnormal weight of each of the power areas according to the real-time power data; When the abnormal probability value is greater than a preset threshold, the failure risk value of each of the power areas is calculated by combining the abnormal probability value and the abnormal weight of each of the power areas; An influence of the power area on the target power system is determined according to the failure risk value.

2. The power grid anomaly detection method according to claim 1, characterized in that: The real-time power data includes operating parameters and status information of each of the power areas; and calculating the abnormal probability value of the target power system and the abnormal weight of each of the power areas according to the real-time power data includes: Calculating the number of fluctuation items of each power area according to each operating parameter, and calculating the abnormal probability value according to the number of fluctuation items and the proportion coefficient of each power area; The device retention probability of each of the power areas is calculated according to each of the state information, and the abnormal weight of each of the power areas is determined according to the device retention probability.

3. The power grid anomaly detection method according to claim 2, characterized in that: The operating parameters include real-time voltage data, real-time current data, grid frequency fluctuation data and load fluctuation data; the power area includes a power transmission system, a substation system and a power distribution system; The calculating the number of fluctuation items of each power area according to each operating parameter includes: Calculating the number of voltage fluctuation items and the number of current fluctuation items of the power transmission system respectively according to the real-time voltage data and the real-time current data collected from the power transmission system; Calculating the number of power grid frequency fluctuation items of the substation system according to the power grid frequency fluctuation data collected from the substation system; The number of electric load fluctuation items of the power distribution system is calculated based on the load fluctuation data collected from the power distribution system.

4. The power grid anomaly detection method according to claim 3, characterized in that: The calculating the abnormal probability value according to the number of fluctuation items and the proportion coefficient of each power area includes: Obtaining a first abnormality probability value according to the number of voltage fluctuation items, the number of current fluctuation items, and a first proportion coefficient; Obtaining a second abnormal probability value according to the number of power grid frequency fluctuation items and the second proportion coefficient; Obtaining a third abnormal probability value according to the number of electric load fluctuation items and the third proportion coefficient; The first abnormal probability value, the second abnormal probability value, and the third abnormal probability value are weighted to obtain the abnormal probability value.

5. The power grid anomaly detection method according to claim 2, characterized in that: The state information includes a plurality of state information parameters; calculating the equipment retention probability of each power area according to each state information, and determining the abnormal weight of each power area according to the equipment retention probability, including: Calculate the device retention probability of each state information parameter according to each state information parameter in each state information; Calculate the Manhattan difference distance between the device retention probability of each state information parameter in each state information and the target state probability; The abnormal weight of each power area is determined according to the number of target state information parameters in each state information; the target state information parameter is the state information whose Manhattan difference distance is greater than a preset distance.

6. The power grid anomaly detection method according to claim 5, characterized in that: The determining the abnormal weight of each of the power areas according to the number of target state information parameters in each of the state information includes: When the number is less than or equal to a first preset threshold number, determining that the abnormal weight is a first abnormal weight; When the number is greater than or equal to the first preset threshold number and less than the second preset threshold number, determining that the abnormal weight is the second abnormal weight; When the number is greater than or equal to the second preset threshold number and less than the third preset threshold number, determining that the abnormal weight is the third abnormal weight; When the number is greater than or equal to the third preset threshold number and less than a fourth preset threshold number, it is determined that the abnormal weight is a fourth abnormal weight.

7. The power grid anomaly detection method according to claim 1, characterized in that: The determining, according to the failure risk value, the influence of the power area on the target power system includes: When the risk failure value is less than a first judgment threshold, it is determined that the power area has no impact on the power system; When the risk failure value is greater than or equal to the first judgment threshold and less than the second judgment threshold, it is determined that the power area has an intermittent impact on the target power system; When the risk failure value is greater than or equal to the second judgment threshold and less than the third judgment threshold, it is determined that the power area has a continuous impact on the target power system.

8. A power grid anomaly detection device, characterized in that: The device comprises: An acquisition module, used to acquire real-time power data of a target power system; the target power system includes multiple power areas; A first calculation module, used for calculating an abnormal probability value of the target power system and an abnormal weight of each of the power areas according to the real-time power data; A second calculation module, configured to calculate a failure risk value of each of the power areas by combining the abnormal probability value and an abnormal weight of each of the power areas when the abnormal probability value is greater than a preset threshold; An anomaly detection module is used to determine the impact of the power area on the target power system according to the failure risk value.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images