Abnormal data feedback method and device for power system

Abstract

The invention discloses a power system abnormal data feedback method and device. Comprising the following steps: acquiring a plurality of event data of a plurality of electrical devices in a power system in a plurality of periods; calculating the conversion rate of converting the plurality of event data of the plurality of electrical devices in the power system into normal event data in each period, so as to construct a conversion matrix; determining the system state of the power system in each period based on the conversion matrix; when the power system is in an abnormal state in the target period, determining a fluctuation state of each electrical device according to the plurality of event data of each electrical device in the target period, and determining a feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, and feeding back the plurality of event data of each abnormal electrical device to the target object in sequence according to the feedback priority. According to the invention, the technical problem that the event data of a plurality of abnormal electrical devices in a power system cannot be reasonably fed back in the prior art, so that the power failure cannot be checked in time is solved.

Description

Technical Field

[0001] The present application relates to the technical field of power system management, and in particular to a method and device for abnormal data feedback of a power system. Background Art

[0002] Traditional circuit anomaly detection is mostly done manually, but with the continuous development of technology, circuit faults or electrical equipment problems can be determined by monitoring the real-time operating status of the power system.

[0003] At present, the measurement point data of the integrated monitoring system of the relevant power industry are usually mainly measurement point information and measurement point value, among which the measurement point information refers to the location information of the current electrical equipment being monitored, and the measurement point value is the detailed operation data of the electrical equipment. Although this monitoring method can solve the data anomalies or failures in the entire power system in a timely manner, it is difficult to query the data due to the large amount of measured data and the data volume is messy, and it is also difficult to find when the data is abnormal. If the system fails before repair, it will cause serious economic losses and safety hazards.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method and device for feedback of abnormal data of an electric power system, so as to at least solve the technical problem that the related technology fails to reasonably feedback event data of multiple abnormal electrical devices in the electric power system, resulting in the inability to timely troubleshoot power failures.

[0006] According to one aspect of an embodiment of the present application, a method for identifying anomalies in an electric power system is provided, comprising: obtaining multiple event data of multiple electrical devices in the electric power system in multiple cycles, wherein the event data is used to characterize the operating status data corresponding to the events occurring at any time in the target cycle of the electrical devices, and the types of the event data include: normal event data and abnormal event data; calculating the conversion rate of multiple event data of multiple electrical devices in each cycle into normal event data in the electric power system, and constructing a conversion matrix based on the conversion rate; determining the system state of the electric power system in each cycle based on the conversion matrix, wherein the types of the system state include: normal state and abnormal state; when the electric power system is in an abnormal state in the target cycle, determining the fluctuation state of each electrical device according to the multiple event data of each electrical device in the target cycle, determining the feedback priority of at least one abnormal electrical device in the electric power system based on the fluctuation state, and feeding back the multiple event data of each abnormal electrical device to the target object in sequence according to the feedback priority, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at the current moment and the previous moment.

[0007] Optionally, obtaining multiple event data of multiple electrical devices in the power system within multiple cycles includes: obtaining multiple event data of each electrical device in the power system within multiple cycles from a cloud database, wherein the cloud database stores normal event data and / or abnormal event data of each electrical device in the power system, and the types of abnormal event data include: fault event data or abnormal event data.

[0008] Optionally, before obtaining multiple event data of each electrical equipment in the power system in multiple cycles from the cloud database, the method also includes: obtaining the operating status data and corresponding occurrence events of each electrical equipment in the power system in multiple cycles; judging whether the operating status data of each electrical equipment in each cycle meets a preset operating status threshold; when the operating status data meets the status threshold, determining that the operating status data corresponding to the occurrence event of the electrical equipment is normal event data; when the operating status data does not meet the status threshold, judging whether the operating status data is within a preset abnormal deviation range; when the operating status data is within the abnormal deviation range, determining that the operating status data corresponding to the occurrence event of the electrical equipment is abnormal event data; when the operating status data is not within the abnormal deviation range, determining that the operating status data corresponding to the occurrence event of the electrical equipment is fault event data.

[0009] Optionally, the conversion rate includes: a fault conversion rate and / or an abnormal conversion rate, wherein the conversion rate of multiple event data of multiple electrical devices in the power system into normal event data in each cycle is calculated, and a conversion matrix is ​​constructed based on the conversion rate, including: in each cycle, based on multiple event data of multiple electrical devices in the power system in the current cycle, determining the abnormal conversion value for converting abnormal event data into normal event data and the fault conversion value for converting each fault event data into normal event data; constructing a fault conversion value set based on the fault conversion value of the power system in the current cycle, and determining the maximum fault conversion value and the average fault conversion value of the fault conversion value set, and calculating the fault conversion rate of each fault event data into normal event data based on each fault conversion value, the maximum fault conversion value and the average fault conversion value in the fault conversion value set; constructing an abnormal conversion value set based on the abnormal conversion value of the power system in the current cycle, and determining the maximum abnormal conversion value and the average abnormal conversion value of the abnormal conversion value set, and calculating the abnormal conversion rate of each abnormal event data into normal event data based on each abnormal conversion value, the maximum abnormal conversion value and the average abnormal conversion value in the abnormal conversion value set; and constructing the conversion matrix of the power system based on the abnormal conversion rate and the fault conversion rate in each cycle of the power system.

[0010] Optionally, determining the system state of the power system in each cycle based on the conversion matrix includes: judging the relationship between the conversion rate of the power system in each cycle and the average conversion rate of each conversion rate in the conversion matrix; when the conversion rate of the power system in the target cycle is not greater than the average conversion rate, determining that the power system is in a normal state in the target cycle; when the conversion rate of the power system in the target cycle is greater than the average conversion rate, determining that the power system is in an abnormal state in the target cycle.

[0011] Optionally, determining the fluctuation state of each electrical device according to multiple event data of each electrical device within a target period, and determining the feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, includes: determining the operating state fluctuation value of the electrical device based on the multiple event data of each electrical device within the target period; determining the Mahalanobis distance corresponding to the operating state fluctuation value of each electrical device, and determining the maximum Mahalanobis distance from multiple Mahalanobis distances; calculating the difference between each Mahalanobis distance and the maximum Mahalanobis distance to obtain the corresponding distance difference, arranging each distance difference in order from large to small, and obtaining a difference sequence, wherein the difference sequence includes at least multiple distance differences and each distance difference. abnormal electrical equipment corresponding to the distance difference; obtaining the position coordinates of each abnormal electrical equipment in the difference sequence in the power system, and determining the density of each abnormal electrical equipment based on the position coordinates, wherein the density is used to reflect the density of other abnormal electrical equipment distributed around the abnormal electrical equipment; determining the distribution type of each abnormal electrical equipment in the difference sequence according to the density, wherein the distribution types include: proximal distribution and distal distribution; for each type of distribution type, determining the number of abnormal electrical equipment corresponding to the distribution type, and determining the type weight value based on the number and the distance difference of each abnormal electrical equipment; determining the feedback priority of the abnormal electrical equipment corresponding to each type of distribution based on the type weight value.

[0012] Optionally, the density of each abnormal electrical device is determined based on the position coordinates, including: determining the abnormal area corresponding to the abnormal electrical device sequence based on the position coordinates of each abnormal electrical device in the difference sequence; for each abnormal electrical device in the abnormal area, calculating the coordinate variance between the position coordinates of the abnormal electrical device and the position coordinates of other abnormal electrical devices in the abnormal area, and using the coordinate variance as the discreteness of the abnormal electrical device; determining the density of the abnormal electrical equipment based on the position coordinates and discreteness of the abnormal electrical equipment.

[0013] According to another aspect of an embodiment of the present application, there is also provided an abnormal data feedback device for an electric power system, comprising: an acquisition module, for acquiring multiple event data of multiple electrical devices in the electric power system within a target cycle, wherein the event data is used to characterize the operating status data corresponding to the event occurring at any time of the electric device within the target cycle, and the types of the event data include: normal event data and abnormal event data; a construction module, for calculating the conversion rate of multiple event data of multiple electrical devices in each cycle into normal event data, and constructing a conversion matrix based on the conversion rate; a determination module, for determining the system state of the electric power system in each cycle based on the conversion matrix, wherein the types of the system state include: normal state and abnormal state; a feedback module, for determining the fluctuation state of each electrical device according to the multiple event data of each electrical device within the target cycle when the electric power system is in an abnormal state within the target cycle, determining the feedback priority of at least one abnormal electrical device in the electric power system based on the fluctuation state, and feeding back the multiple event data of each abnormal electrical device to the target object in sequence according to the feedback priority, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at the current moment and the previous moment.

[0014] According to another aspect of an embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned power system abnormal data feedback method by running the computer program.

[0015] According to another aspect of an embodiment of the present application, a computer program product is further provided. The computer program product includes a stored computer program, wherein when the computer program is executed by a processor, the above-mentioned power system abnormal data feedback method is implemented.

[0016] In an embodiment of the present application, multiple event data of multiple electrical devices in a power system in multiple cycles are obtained, wherein the event data is used to characterize the operating status data corresponding to the events occurring at any time in the target cycle of the electrical devices, and the types of event data include: normal event data and abnormal event data; the conversion rate of multiple event data of multiple electrical devices in each cycle into normal event data is calculated, and a conversion matrix is ​​constructed based on the conversion rate; the system state of the power system in each cycle is determined based on the conversion matrix, wherein the types of system states include: normal state and abnormal state; when the power system is in an abnormal state in the target cycle, the fluctuation state of each electrical device is determined according to the multiple event data of each electrical device in the target cycle, the feedback priority of at least one abnormal electrical device in the power system is determined based on the fluctuation state, and the multiple event data of each abnormal electrical device is fed back to the target object in sequence according to the feedback priority, so that the target object can perform fault troubleshooting on each electrical device in the power system in sequence according to the order of receiving the event data, thereby effectively improving the efficiency of fault troubleshooting, and thus solving the technical problem that the related technology does not reasonably feed back the event data of multiple abnormal electrical devices in the power system, resulting in the inability to timely troubleshoot power faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 It is a hardware structure block diagram of an optional computer terminal (mobile device) for implementing a method for identifying abnormalities in a power system according to an embodiment of the present application;

[0019] Figure 2 is a flow chart of an optional method for identifying anomalies in a power system according to an embodiment of the present application;

[0020] Figure 3 is a schematic structural diagram of an optional power system anomaly identification device according to an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] In addition, the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0025] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0026] Variance: A statistic that measures the degree of dispersion of data distribution. It is used to measure the variability of a set of values. Variance can be expressed as the average of the squares of the differences between each value and the mean value. The calculation formula is:

[0027] LSTM-FCN (Long Short-Term Memory Fully Convolution Network): A deep learning model that combines a long short-term memory network (LSTM) and a fully convolutional neural network (FNN). It is often used to process sequence data, especially in the fields of time series prediction, natural language processing, and video processing. It uses the long short-term memory characteristics of LSTM to capture long-term dependencies in time series, and uses a fully convolutional network to process spatial features, thereby achieving efficient processing and prediction of data.

[0028] Mahalanobis distance: A metric used to measure the similarity or difference between two sample points in multidimensional space. It takes into account the correlation between various dimensions and can effectively compare the distance between sample points when the data has different variance and covariance structures. The calculation formula is: Where x represents the vector of data points, μ represents the mean vector of the data set, ∑ -1 Represents the inverse of the covariance matrix. Generally speaking, the larger the value of the Mahalanobis distance, the farther the data point is from the center of the data set, and the greater the difference; the smaller the value, the closer the data point is to the center of the data set, and the greater the similarity.

[0029] Example 1

[0030] According to an embodiment of the present application, a method embodiment of a method for feedback of abnormal data of an electric power system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing the power system abnormal data feedback method is shown. Figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0032] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0033] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the power system abnormal data feedback method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the power system abnormal data feedback method of the above-mentioned application is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0034] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0035] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0036] In the above operating environment, Figure 2 is a flow chart of an optional method for feedback of abnormal data of a power system according to an embodiment of the present application, such as Figure 2 As shown, the method at least includes steps S202-S208, wherein:

[0037] Step S202, obtaining a plurality of event data of a plurality of electrical devices in the power system in a plurality of cycles.

[0038] In the technical solution provided in step S202, the above-mentioned event data refers to the operating status data (such as current, voltage, electric energy, etc.) corresponding to the event of the electrical equipment at any time during the collection period, wherein the event refers to whether the electrical equipment has a fault or whether the data is abnormal at the current moment, and therefore, the types of event data can be divided into: normal event data and abnormal event data. The above-mentioned electrical equipment includes but is not limited to: substations, power stations, transmission lines, etc. For example, during the collection period, due to weather reasons, the electrical equipment has a circuit short circuit or overload, etc. At this time, the operating status data of the electrical equipment during the collection period is the abnormal event data of the electrical equipment.

[0039] Step S204 , calculating the conversion rate of multiple event data of multiple electrical devices in the power system into normal event data in each cycle, and constructing a conversion matrix based on the conversion rate.

[0040] In the technical solution provided in step S204, since the types of the above-mentioned event data include normal event data and abnormal event data, the above-mentioned conversion rate can be understood as the conversion rate of converting multiple abnormal event data of multiple electrical equipment in the power system in each cycle into normal event data, and constructing a conversion matrix according to the conversion rates corresponding to each cycle.

[0041] Step S206: determining the system state of the power system in each cycle based on the conversion matrix.

[0042] In the technical solution provided in step S206, the conversion matrix can be used to determine the conversion status of each abnormal event data of the power system into normal event data in each cycle, and the system state of the power system in each cycle can be determined based on the conversion status, and the type of system state includes: normal state or abnormal state.

[0043] Step S208, when the power system is in an abnormal state within the target cycle, the fluctuation state of each electrical device is determined according to multiple event data of each electrical device within the target cycle, and the feedback priority of at least one abnormal electrical device in the power system is determined based on the fluctuation state, and the multiple event data of each abnormal electrical device are fed back to the target object in sequence according to the feedback priority.

[0044] In the technical solution provided in step S208, when it is determined that the power system is in an abnormal state within the target cycle, in order to determine the fault fluctuation range of the abnormal electrical equipment in the power system, the fluctuation state of each electrical equipment is determined based on multiple event data of each electrical equipment within the target cycle, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical equipment at the current moment and the previous moment; the feedback priority of the abnormal electrical equipment is determined according to the fluctuation state of each electrical equipment, wherein the greater the fluctuation, the greater the scope of its impact on the surrounding electrical equipment, and the higher the feedback priority of the abnormal electrical equipment is determined, so that the multiple event data of each abnormal electrical equipment can be fed back to the target object (i.e., the technician) in sequence according to the feedback priority, so that the target object can give priority to troubleshooting the abnormal electrical equipment with a large fluctuation range, thereby reducing the impact range of the abnormal electrical equipment in the power system and shrinking the abnormal area.

[0045] The above-mentioned power system abnormality identification method of this embodiment will be further introduced below.

[0046] As an optional implementation, in the technical solution provided in the above step S202, the method may include: acquiring multiple event data of each electrical device in the power system in multiple cycles from a cloud database.

[0047] Specifically, the cloud database can first obtain text data of multiple electrical devices in the power system, wherein the text data is used to describe the equipment information of the electrical equipment; then, normal event data and / or abnormal event data of each electrical device is periodically collected according to the text data, and the types of abnormal event data include: fault event data or abnormal event data; and the event data is classified and stored in the cloud database according to the electrical equipment (i.e., text data) and the collection period.

[0048] Among them, the embodiment of the present application can divide the event data of the electrical equipment by the following method:

[0049] First, the operating status data of each electrical device in the power system in multiple cycles and the corresponding events are obtained.

[0050] Then, it is determined whether the operating status data of each electrical device in each cycle meets a preset operating status threshold.

[0051] In the case where the operating status data meets the status threshold, determining that the operating status data corresponding to the occurrence event of the electrical equipment is normal event data;

[0052] When the running status data does not meet the status threshold, determining whether the running status data is within a preset abnormal deviation range;

[0053] When the operating status data is within the abnormal deviation range, determining the operating status data corresponding to the occurrence event of the electrical equipment as abnormal event data;

[0054] When the operating status data is not within the abnormal deviation range, it is determined that the operating status data corresponding to the occurrence event of the electrical equipment is fault event data.

[0055] The state threshold can be determined at least according to the equipment specifications, industry standards or specific safety requirements of the electrical equipment. The abnormal deviation range is set according to the historical fault data and historical abnormal data to determine the critical value or critical range of the electrical equipment in abnormal or faulty state. Therefore, the state threshold and abnormal deviation range corresponding to each electrical equipment or the same type or different models of electrical equipment are different.

[0056] It should be noted that when the cloud database stores the event data of each electrical device, it can use the LSTM-FCN classification model to directly classify the acquired event data, and store the event data according to the classification results, thereby realizing rapid classification of the event data of the electrical equipment.

[0057] As an optional implementation, in the technical solution provided in the above step S204, according to the type of abnormal event data, the conversion rate of abnormal event data into normal event data can be divided into an abnormal conversion rate of abnormal event data into normal event data and a fault conversion rate of fault event data into normal event data. Therefore, the embodiment of the present application can determine the conversion matrix of the power system by the following method, including:

[0058] Step S2041, based on multiple event data of multiple electrical devices in the power system in the current cycle, determine an abnormal conversion value for converting abnormal event data into normal event data and a fault conversion value for converting each fault event data into normal event data.

[0059] Specifically, the number of normal event data, fault event data and abnormal event data in each time period in the current cycle is recorded as D1, D2, and D3 respectively. Then, the fault conversion value and abnormal conversion value in each cycle can be calculated by the following formula: i =(D2-D1) / t i 、inb i =(D3-D1) / t i , where t i Indicates the i-th time period in the current cycle, ina i 、inb i It represents the fault conversion value and abnormal conversion value of the power system in the i-th time period in the current cycle.

[0060] Step S2042, construct a fault conversion value set based on the fault conversion values ​​of the power system in the current cycle, and determine the maximum fault conversion value and the average fault conversion value of the fault conversion value set, and calculate the fault conversion rate of each fault event data into normal event data based on each fault conversion value, the maximum fault conversion value and the average fault conversion value in the fault conversion value set.

[0061] That is to say, the fault conversion value of the power system in the current cycle is used to construct a fault conversion value set [a] = [ina i ], i = 1, 2, 3 ... n, n represents the total number of elements in the set [a]. Then, the average fault conversion value mean (a) of each fault conversion value in the fault conversion value set is calculated, and the maximum fault conversion value max (a) in the fault conversion value set is counted. Therefore, the fault conversion rate of each fault event data converted into normal event data can be calculated by the following formula through each fault conversion value, the maximum fault conversion value max (a) and the average fault conversion value mean (a) of the fault conversion value set [a]:

[0062]

[0063] Among them, the above conversion rate DPA i It represents the conversion rate of all fault event data in the i-th time period of the current cycle of the power system into normal event data after adjustment.

[0064] Step S2043, construct an abnormal conversion value set based on the abnormal conversion values ​​of the power system in the current cycle, and determine the maximum abnormal conversion value and the average abnormal conversion value of the abnormal conversion value set, and calculate the abnormal conversion rate of each abnormal event data into normal event data based on each abnormal conversion value, the maximum abnormal conversion value and the average abnormal conversion value in the abnormal conversion value set.

[0065] Similarly, the abnormal conversion values ​​of the power system in each cycle are used to construct an abnormal conversion value set [b] = [inb i ], i = 1, 2, 3 ... n, n represents the total number of elements in the set [b]. Then, the average abnormal conversion value mean(b) of each abnormal conversion value in the abnormal conversion value set is calculated, and the maximum abnormal conversion value max(b) in the abnormal conversion value set is counted. Therefore, the abnormal conversion rate of each abnormal event data into normal event data can be calculated by the following formula through each abnormal conversion value, the maximum abnormal conversion value max(b) and the average abnormal conversion value mean(b) of the abnormal conversion value set [b]:

[0066]

[0067] Among them, the above conversion rate DPB i It represents the conversion rate of all abnormal event data in the i-th time period of the current cycle of the power system into normal event data after adjustment.

[0068] Step S2044: construct a conversion matrix of the power system based on the abnormal conversion rate and the fault conversion rate of the power system in each cycle.

[0069] Among them, the power system conversion matrix (DPA, DPB) is constructed with the fault conversion rate of the power system in each cycle as the horizontal rank and the abnormal conversion rate as the column rank. In other words, each matrix element in the conversion matrix (DPA, DPB) represents the fault conversion rate and abnormal conversion rate of the power system in any cycle.

[0070] As an optional implementation, in the technical solution provided in step S206 above, the system state of the power system in each cycle can be determined by the following method, including:

[0071] First, determine the relationship between the conversion rate of the power system in each cycle and the average conversion rate of each conversion rate in the conversion matrix.

[0072] Specifically, the conversion matrix constructed in the above step S204 is first read, and then the mean of each conversion rate in the conversion matrix is ​​calculated to obtain the conversion rate mean, and the calculated conversion rate mean includes: abnormal conversion rate mean and normal conversion rate mean. Then, the relationship between the conversion rate of the power system recorded in the conversion matrix in each cycle and the conversion rate mean of the conversion matrix is ​​determined.

[0073] In the case where the conversion rate of the power system in the target period is not greater than the average conversion rate, determining that the power system is in a normal state in the target period;

[0074] When the conversion rate of the power system in the target period is greater than the conversion rate average, it is determined that the power system is in an abnormal state in the target period.

[0075] As an optional implementation, in the technical solution provided in the above step S208, the method may include:

[0076] Step S2081: determining the operating status fluctuation value of the electrical equipment based on the event data of each electrical equipment within the target period.

[0077] That is to say, the operating status fluctuation value of each electrical equipment in different time periods within the target cycle is first determined based on multiple event data of each electrical equipment in the power system within the target cycle, wherein the operating status fluctuation value is used to reflect the difference between the operating status data of the electrical equipment at the current moment and the previous moment.

[0078] Step S2082, determining the Mahalanobis distance corresponding to the operating state fluctuation value of each electrical device, and determining the maximum Mahalanobis distance from multiple Mahalanobis distances.

[0079] Considering the analysis of abnormal data in the power system, since the power system contains more electrical equipment and the collection cycle is longer, the event data that needs to be analyzed is more complicated and the amount of data will increase accordingly. In order to quickly find abnormal electrical equipment in a power system containing a large number of electrical equipment, the embodiment of the present application introduces the concept of Mahalanobis distance, where the Mahalanobis distance is a method of measuring the distance of a point to other points in a multidimensional space. The central tendency (such as the mean vector). In the analysis of the power system, the use of Mahalanobis distance can help us identify abnormal electrical equipment in the system.

[0080] Specifically, the embodiment of the present application first standardizes the operation state fluctuation data, and then calculates the Mahalanobis distance of the operation state fluctuation value of each electrical device within the target period through the Mahalanobis distance formula, wherein the Mahalanobis distance is used to reflect the distance between the different operation state fluctuation values ​​of each electrical device within the target period and the operation state fluctuation distribution center (i.e., the reasonable operation fluctuation range of the electrical device during operation, such as operation fluctuations caused by load changes, power quality problems, equipment aging, etc.), so as to reflect whether the operation fluctuation of the electrical device is large, and the corresponding electrical device has abnormal operation or failure. Finally, the maximum Mahalanobis distance is determined from the multiple Mahalanobis distances calculated, wherein each Mahalanobis distance corresponds to the operation state data of an electrical device.

[0081] Step S2083, calculating the difference between each Mahalanobis distance and the maximum Mahalanobis distance to obtain a corresponding distance difference, and arranging the distance differences in order from large to small to obtain a difference sequence.

[0082] That is to say, the distance difference between each Mahalanobis distance and the maximum Mahalanobis distance is calculated to obtain the corresponding distance difference, and the distance differences are reordered according to the size to obtain a difference sequence, and at the same time, the abnormal electrical equipment corresponding to each distance difference in the updated difference sequence is obtained.

[0083] Step S2084, obtaining the position coordinates of each abnormal electrical device in the difference sequence in the power system, and determining the density of each abnormal electrical device based on the position coordinates.

[0084] The abnormal area is determined by obtaining the position coordinates of each abnormal electrical device in the power system in the difference sequence, and the density of each abnormal electrical device in the abnormal area is determined according to the position coordinates of each abnormal electrical device by the following method, including:

[0085] Step 1: Calculate the coordinate variance between the location coordinates of the abnormal electrical equipment and the location coordinates of other abnormal electrical equipment in the abnormal area using the following formula, and use the coordinate variance as the discreteness of the abnormal electrical equipment:

[0086]

[0087] Among them, P represents the horizontal range of the abnormal area, Q represents the vertical range of the abnormal area, z represents the number of abnormal electrical equipment points in the abnormal area, and x represents the number of abnormal electrical equipment points in the abnormal area. j represents the horizontal coordinate of the ith abnormal electrical equipment, y j Represents the vertical coordinate of the i-th abnormal electrical equipment.

[0088] Step 2: Based on the location coordinates and dispersion of abnormal electrical equipment, the density of initial abnormal electrical equipment is determined by the following formula:

[0089]

[0090] Among them, Var(x,y)dw represents the derivative value of discreteness, G(x,y)=dx(dm j (x j ,y j ))+dy(dm j (x j ,y j )) represents the gradient matrix of the electrical equipment, dx(dm j (x j ,y j )) represents the derivative of the position coordinate of the abnormal electrical equipment in the x-axis direction, dy(dm j (x j ,y j )) represents the derivative of the position coordinates of the abnormal electrical equipment in the y-axis direction.

[0091] Step S2085, determining the distribution type of each abnormal electrical device in the difference sequence according to the density.

[0092] Specifically, after determining the density of each abnormal electrical device through the above step S2084, all abnormal electrical devices in the abnormal area are divided into proximal abnormal electrical devices distributed proximal to the abnormal center area and distal abnormal electrical devices distributed far away from the abnormal center area according to the density, wherein the device set consisting of proximal abnormal electrical devices is denoted as [dn], and the device set consisting of distal abnormal electrical devices is denoted as [pn].

[0093] Step S2086: for each distribution type, determine the number of abnormal electrical devices corresponding to the distribution type, and determine the type weight value based on the number and the distance difference between each abnormal electrical device.

[0094] Specifically, firstly, the total amount of event data of each proximal abnormal electrical device in the device set [dn] within the target period is counted, denoted as T, and at the same time, the total amount of event data of each distal abnormal electrical device in the device set [pn] within the target period is counted, denoted as L.

[0095] Then, according to the ratio of the Mahalanobis distance difference between adjacent devices in each device set:

[0096]

[0097] Among them, dn(Ek ′ ) r and dn(Ek ′ ) r+1 They represent the Mahalanobis distance difference Ek corresponding to the rth and r+1th proximal abnormal electrical devices in the device set [dn] respectively. ′ , pn(Ek ′ ) r and pn(Ek ′ ) r+1 They represent the distance difference Ek corresponding to the rth and r+1th remote abnormal electrical devices in the device set [pn] respectively. ′ .

[0098] Finally, based on the ratio of the Mahalanobis distance differences between adjacent devices in each device set, the weight value of each set is obtained according to the following formula:

[0099]

[0100] The above Q1 represents the weight value of the device set [dn], and Q2 represents the weight value of the device set [pn].

[0101] Step S2087: Determine the feedback priority of the abnormal electrical equipment corresponding to each distribution type based on the type weight value.

[0102] Specifically, firstly, according to the weight values ​​of each device set calculated above (i.e., the type weight values ​​of each distribution type), the weight values ​​of each abnormal electrical device are optimized and fitted according to the following formula:

[0103]

[0104] Among them, max(Ek ′ ) represents the maximum Mahalanobis distance difference Ek ′ , where Ek ′ The Mahalanobis distance difference represents an abnormal electrical device, where the abnormal electrical device may be an abnormal electrical device in any device set [pn], [dn].

[0105] According to the fitted weight value Q3 d , the weight values ​​Q1 and Q2 of each device set determine the feedback weight (i.e. feedback priority) of each electrical device:

[0106]

[0107] Then calculate the feedback weight z of each abnormal electrical device k Arrange them in order of size to get the comprehensive feedback weight matrix Z = (z1, z2, ..., z T+L ), the event data of abnormal electrical equipment are fed back in turn according to the feedback weight matrix, so that the power system can check the abnormal electrical equipment in turn.

[0108] Therefore, through the above-mentioned technical scheme of the embodiment of the present application, the conversion rate analysis is performed on the event data of each electrical equipment in the power system within multiple cycles to obtain the target period in which the power system is in an abnormal state; the fluctuation of the event data of the electrical equipment in the power system within the target period is analyzed to obtain the abnormal electrical equipment in the power system, and the density of these abnormal electrical equipment is analyzed to determine the feedback data priority of each electrical equipment in the abnormal area, and then, the event data of each electrical equipment is fed back to the relevant technical personnel in turn according to the feedback data priority of each electrical equipment, so that the relevant technical personnel can perform troubleshooting on each electrical equipment in the power system in turn according to the order of receiving the event data, thereby effectively improving the efficiency of troubleshooting, and further solving the technical problem that the related technology does not reasonably feedback the event data of multiple abnormal electrical equipment in the power system, resulting in the inability to troubleshoot power faults in a timely manner.

[0109] Example 2

[0110] Based on the first embodiment of the present application, an embodiment of a power system abnormal data feedback device is also provided, and the power system abnormal data feedback method of the above embodiment is executed when the device is running. Figure 3 is a schematic diagram of the structure of an optional power system abnormal data feedback device according to an embodiment of the present application, such as Figure 3 As shown, the power system abnormal data feedback device at least includes an acquisition module 32, a construction module 34, a determination module 36 and a feedback module 38, wherein:

[0111] The acquisition module 32 is used to acquire multiple event data of multiple electrical devices in the power system within the target period, wherein the event data is used to characterize the operating state data corresponding to the event occurring at any time of the electrical device within the target period, and the types of event data include: normal event data and abnormal event data;

[0112] A construction module 34 is used to calculate a conversion rate of a plurality of event data of a plurality of electrical devices in the power system into normal event data in each cycle, and to construct a conversion matrix based on the conversion rate;

[0113] A determination module 36 is used to determine the system state of the power system in each cycle based on the conversion matrix, wherein the types of the system state include: normal state and abnormal state;

[0114] The feedback module 38 is used to determine the fluctuation state of each electrical device based on multiple event data of each electrical device within the target cycle when the power system is in an abnormal state within the target cycle, determine the feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, and feed back the multiple event data of each abnormal electrical device to the target object in sequence according to the feedback priority, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at the current moment and the previous moment.

[0115] It should be noted that the various modules in the above-mentioned power system abnormal data feedback device can be program modules (for example, a set of program instructions to implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0116] Example 3

[0117] According to an embodiment of the present application, a non-volatile storage medium is further provided, in which a program is stored, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the power system abnormal data feedback method in Example 1.

[0118] Optionally, the device where the non-volatile storage medium is located implements the following steps by running the program: obtaining multiple event data of multiple electrical devices in the power system in multiple cycles, wherein the event data is used to characterize the operating status data corresponding to the events occurring at any time in the target cycle of the electrical devices, and the types of event data include: normal event data and abnormal event data; calculating the conversion rate of multiple event data of multiple electrical devices in each cycle in the power system into normal event data, and constructing a conversion matrix based on the conversion rate; determining the system state of the power system in each cycle based on the conversion matrix, wherein the types of system states include: normal state and abnormal state; when the power system is in an abnormal state in the target cycle, determining the fluctuation state of each electrical device according to the multiple event data of each electrical device in the target cycle, determining the feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, and feeding back the multiple event data of each abnormal electrical device to the target object in sequence according to the feedback priority, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at the current moment and the previous moment.

[0119] According to an embodiment of the present application, a computer program product is also provided, which includes a stored computer program, wherein when the computer program is executed by a processor, the power system abnormal data feedback method in Example 1 is implemented.

[0120] Optionally, the computer program executes the following steps: obtaining multiple event data of multiple electrical devices in the power system in multiple cycles, wherein the event data is used to characterize the operating status data corresponding to the events occurring at any time in the target cycle of the electrical devices, and the types of event data include: normal event data and abnormal event data; calculating the conversion rate of multiple event data of multiple electrical devices in each cycle into normal event data, and constructing a conversion matrix based on the conversion rate; determining the system state of the power system in each cycle based on the conversion matrix, wherein the types of system state include: normal state and abnormal state; when the power system is in an abnormal state in the target cycle, determining the fluctuation state of each electrical device according to the multiple event data of each electrical device in the target cycle, determining the feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, and feeding back the multiple event data of each abnormal electrical device to the target object in sequence according to the feedback priority, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at the current moment and the previous moment.

[0121] According to an embodiment of the present application, a processor is also provided, which is used to run a program, wherein the power system abnormal data feedback method in Example 1 is executed when the program is running.

[0122] Optionally, the following steps are executed when the program is running: obtaining multiple event data of multiple electrical devices in the power system in multiple cycles, wherein the event data is used to characterize the operating status data corresponding to the events occurring at any time in the target cycle of the electrical devices, and the types of event data include: normal event data and abnormal event data; calculating the conversion rate of multiple event data of multiple electrical devices in each cycle into normal event data, and constructing a conversion matrix based on the conversion rate; determining the system state of the power system in each cycle based on the conversion matrix, wherein the types of system state include: normal state and abnormal state; when the power system is in an abnormal state in the target cycle, determining the fluctuation state of each electrical device according to the multiple event data of each electrical device in the target cycle, determining the feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, and feeding back the multiple event data of each abnormal electrical device to the target object in sequence according to the feedback priority, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at the current moment and the previous moment.

[0123] According to an embodiment of the present application, an electronic device is also provided, wherein: Figure 4 is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application, such as Figure 4 As shown, the electronic device includes one or more processors; a memory for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are implemented to run the programs, wherein the programs are configured to execute the power system abnormal data feedback method in the above-mentioned embodiment 1 when running.

[0124] Optionally, the processor is configured to execute the following steps through a computer program: obtaining multiple event data of multiple electrical devices in the power system in multiple cycles, wherein the event data is used to characterize the operating status data corresponding to the events occurring at any time in the target cycle of the electrical devices, and the types of event data include: normal event data and abnormal event data; calculating the conversion rate of multiple event data of multiple electrical devices in each cycle in the power system into normal event data, and constructing a conversion matrix based on the conversion rate; determining the system state of the power system in each cycle based on the conversion matrix, wherein the types of system states include: normal state and abnormal state; when the power system is in an abnormal state in the target cycle, determining the fluctuation state of each electrical device according to the multiple event data of each electrical device in the target cycle, determining the feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, and feeding back the multiple event data of each abnormal electrical device to the target object in sequence according to the feedback priority, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at the current moment and the previous moment.

[0125] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0126] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be 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 through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0128] 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 over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0129] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0130] 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 technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0131] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for abnormal data feedback of a power system, characterized in that: include: Acquire multiple event data of multiple electrical devices in the power system in multiple cycles, wherein the event data is used to characterize the operating state data corresponding to the events occurring at any time in the target cycle of the electrical devices, and the types of event data include: normal event data and abnormal event data; Calculating the conversion rate of a plurality of the event data of a plurality of electrical devices in the power system into normal event data in each cycle, and constructing a conversion matrix based on the conversion rate; Determining the system state of the power system in each cycle based on the conversion matrix, wherein the types of the system state include: normal state and abnormal state; When the power system is in the abnormal state within the target cycle, the fluctuation state of each electrical device is determined according to a plurality of event data of each electrical device within the target cycle, the feedback priority of at least one abnormal electrical device in the power system is determined based on the fluctuation state, and the plurality of event data of each abnormal electrical device are fed back to the target object in sequence according to the feedback priority, wherein the fluctuation state includes a plurality of operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at a current moment and a previous moment.

2. The method according to claim 1, characterized in that Acquire multiple event data of multiple electrical devices in the power system in multiple cycles, including: Acquire multiple event data of each electrical device in the power system within multiple cycles from a cloud database, wherein the cloud database stores normal event data and / or abnormal event data of each electrical device in the power system, and the types of the abnormal event data include: fault event data or abnormal event data.

3. The method according to claim 2, characterized in that Before acquiring multiple event data of each electrical device in the power system in multiple cycles from the cloud database, the method further includes: Obtaining operating status data of each electrical device in the power system in multiple cycles and corresponding events; Determining whether the operating status data of each of the electrical devices in each cycle meets a preset operating status threshold; In the case where the operating status data meets the status threshold, determining that the operating status data corresponding to the occurrence event of the electrical device is normal event data; When the running status data does not meet the status threshold, determining whether the running status data is within a preset abnormal deviation range; In the case where the operating status data is within the abnormal deviation range, determining that the operating status data corresponding to the occurrence event of the electrical equipment is abnormal event data; When the operating status data is not within the abnormal deviation range, it is determined that the operating status data corresponding to the occurrence event of the electrical equipment is fault event data.

4. The method according to claim 3, characterized in that The conversion rate includes: a fault conversion rate and / or an abnormal conversion rate, wherein the conversion rate of a plurality of event data of a plurality of electrical devices in the power system into normal event data in each cycle is calculated, and a conversion matrix is ​​constructed based on the conversion rate, including: In each cycle, based on multiple event data of multiple electrical devices in the power system in the current cycle, determine an abnormal conversion value for converting the abnormal event data into the normal event data and a fault conversion value for converting each of the fault event data into the normal event data; Constructing a fault conversion value set based on the fault conversion values ​​of the power system in the current cycle, determining a maximum fault conversion value and an average fault conversion value of the fault conversion value set, and calculating a fault conversion rate of each of the fault event data into normal event data based on each fault conversion value, the maximum fault conversion value and the average fault conversion value in the fault conversion value set; Constructing an abnormal conversion value set based on the abnormal conversion values ​​of the power system in the current cycle, and determining the maximum abnormal conversion value and the average abnormal conversion value of the abnormal conversion value set, and calculating the abnormal conversion rate of each abnormal event data into normal event data based on each abnormal conversion value, the maximum abnormal conversion value and the average abnormal conversion value in the abnormal conversion value set; A conversion matrix of the power system is constructed based on the abnormal conversion rate and the fault conversion rate of the power system in each cycle.

5. The method according to claim 1, characterized in that Determining a system state of the power system in each cycle based on the conversion matrix includes: Determining the relationship between the conversion rate of the power system in each cycle and the conversion rate average of each conversion rate in the conversion matrix; When the conversion rate of the power system in the target period is not greater than the conversion rate mean, determining that the power system is in a normal state in the target period; When the conversion rate of the power system in the target period is greater than the conversion rate average, it is determined that the power system is in an abnormal state in the target period.

6. The method according to claim 4, characterized in that Determining the fluctuation state of each of the electrical devices according to a plurality of event data of each of the electrical devices within a target period, and determining the feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, comprising: Determine the operating state fluctuation value of the electrical device based on a plurality of event data of each of the electrical devices within a target period; Determine the Mahalanobis distance corresponding to the operating state fluctuation value of each of the electrical devices, and determine the maximum Mahalanobis distance from the multiple Mahalanobis distances; Calculate the difference between each Mahalanobis distance and the maximum Mahalanobis distance to obtain a corresponding distance difference, and arrange each distance difference in order from large to small to obtain a difference sequence, wherein the difference sequence includes at least a plurality of distance differences and an abnormal electrical device corresponding to each distance difference; Obtaining the position coordinates of each abnormal electrical device in the difference sequence in the power system, and determining the density of each abnormal electrical device based on the position coordinates, wherein the density is used to reflect the density of other abnormal electrical devices distributed around the abnormal electrical device; Determining the distribution type of each abnormal electrical device in the difference sequence according to the density, wherein the distribution type includes: proximal distribution and distal distribution; For each type of the distribution, determine the number of abnormal electrical devices corresponding to the distribution type, and determine a type weight value based on the number and the distance difference between each abnormal electrical device; The feedback priority of the abnormal electrical equipment corresponding to each type of the distribution type is determined based on the type weight value.

7. The method according to claim 6, characterized in that Determining the density of each of the abnormal electrical devices based on the position coordinates includes: Determine the abnormal area corresponding to the abnormal electrical equipment sequence based on the position coordinates of each abnormal electrical equipment in the difference sequence; For each abnormal electrical device in the abnormal area, calculating the coordinate variance between the position coordinates of the abnormal electrical device and the position coordinates of other abnormal electrical devices in the abnormal area, and using the coordinate variance as the discreteness of the abnormal electrical device; The density of the abnormal electrical devices is determined based on the location coordinates and dispersion of the abnormal electrical devices.

8. A power system abnormal data feedback device, characterized in that: include: An acquisition module is used to acquire multiple event data of multiple electrical devices in the power system within a target period, wherein the event data is used to characterize the operating state data corresponding to the events occurring at any time of the electrical devices within the target period, and the types of event data include: normal event data and abnormal event data; A construction module, used for calculating the conversion rate of a plurality of the event data of a plurality of electrical devices in the power system into normal event data in each cycle, and constructing a conversion matrix based on the conversion rate; A determination module, configured to determine a system state of the power system in each cycle based on the conversion matrix, wherein the types of the system state include: a normal state and an abnormal state; A feedback module is used to determine the fluctuation state of each electrical device according to multiple event data of each electrical device within the target cycle when the power system is in the abnormal state within the target cycle, determine the feedback priority of at least one abnormal electrical device in the power system based on the fluctuation state, and feed back the multiple event data of each abnormal electrical device to the target object in sequence according to the feedback priority, wherein the fluctuation state includes multiple operating state fluctuation values ​​reflecting the difference between the operating state data of the electrical device at a current moment and a previous moment.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, wherein the device where the non-volatile storage medium is located executes the power system abnormal data feedback method according to any one of claims 1 to 7 by running the computer program.

10. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the power system abnormal data feedback method according to any one of claims 1 to 7 is implemented.

Images