User side power failure fault analysis method and system

Abstract

The invention discloses a user side power failure fault analysis method and system. The method comprises the following steps: acquiring and sorting power grid state data of a target area and a power utilization data sequence of each user terminal according to a time sequence; through a threshold strategy based on environment temperature dynamic correction, whether a power grid abnormal event exists is intelligently judged from a power grid state data sequence. And if the event time node exists, intercepting an associated sub-sequence from the power consumption data sequence of each user according to the event time node, and extracting the power consumption change rate and the power loss duration as key features. And then, inputting the features into a pre-trained power failure fault classification model to identify a power failure type. And finally, in combination with the spatial distribution information of the user terminal, automatically generating a visual power failure influence area by adopting a density clustering algorithm, and pushing the visual power failure influence area to the user terminal. Power grid and user side multi-source data are effectively fused, and rapid and accurate identification of power failure faults and visual positioning of influence ranges are realized.

Description

Technical Field

[0001] This invention belongs to the field of power outage fault analysis technology, and particularly relates to a user-side power outage fault analysis method and system. Background Technology

[0002] With the rapid development of smart grids and advanced metering systems (AMIs), the dimensions and scale of data available to power systems are exploding, especially the massive amounts of real-time electricity consumption data provided by smart meters on the user side, which offers new opportunities for refined management and fault diagnosis of the power grid. Accurate and rapid analysis of user-side power outage faults is a key aspect of improving power supply reliability and enhancing user experience.

[0003] Traditional power outage fault analysis methods mainly rely on substation alarm signals, reports from distribution automation terminals (FTU / DTU), or user-reported repairs via telephone. These methods have significant limitations and lag: hardware alarms cannot cover the periphery of the distribution network, and signal transmission itself may be interrupted by faults; while user-reported repairs are limited by user willingness and communication channels, resulting in ambiguous information and difficulty in location, making it impossible for maintenance personnel to accurately determine the nature and scope of the fault in a timely manner, thus prolonging the time for fault investigation and power restoration.

[0004] In recent years, although some studies have attempted to use user electricity consumption data (such as voltage, current, and electricity consumption) for power outage analysis, existing methods generally have the following shortcomings: First, they fail to perform time-series correlation and collaborative analysis between grid-side status data and user-side electricity consumption data, lack cross-validation of fault events, and have a high false alarm rate; second, the extraction of power outage features is relatively singular, failing to comprehensively consider multi-dimensional features such as electricity consumption change rate and power outage duration, making it difficult to accurately distinguish between different types of events such as planned power outages, fault power outages, and instantaneous voltage dips; finally, when determining the scope of power outage impact, they are mostly limited to list-based user ledgers, lacking clustering visualization methods based on spatial geographic information, and cannot intuitively and automatically generate power outage impact areas, thus providing limited support for dispatching and emergency repair decisions.

[0005] Therefore, there is an urgent need for a new analysis method that can integrate multi-source data from the power grid and the user side, automatically and accurately identify fault types, and intelligently generate visualized power outage areas, in order to overcome the shortcomings of existing technologies and comprehensively improve the intelligence level and response efficiency of power outage management. Summary of the Invention

[0006] This invention provides a user-side power outage fault analysis method and system to solve the technical problems of traditional power outage fault analysis methods, which mainly rely on substation alarm signals and reports from distribution automation terminals, resulting in significant lag and limitations.

[0007] In a first aspect, the present invention provides a user-side power outage fault analysis method, comprising: The power grid status data of the target area and the electricity consumption data of each user terminal in the target area are acquired within a preset time period. The power grid status data and the electricity consumption data are sorted according to the time sequence to obtain the power grid status data sequence and the electricity consumption data sequence. Each electricity consumption data sequence corresponds to one electricity terminal. Based on the power grid status data sequence, a preset power grid anomaly analysis strategy is used to determine whether there are any power grid anomaly events within the preset time period; If there is at least one power grid abnormal event, then according to the time node corresponding to the at least one power grid abnormal event, a preset data selection strategy is used to extract at least one power consumption data subsequence associated with the at least one power grid abnormal event from each power consumption data sequence. Based on a certain electricity consumption data subsequence, a certain electricity consumption feature corresponding to a certain power grid abnormal event is determined, and the certain electricity consumption feature is input into a pre-trained power outage fault classification model. The power outage fault classification model corresponds to the power outage type of the certain power grid abnormal event. The certain electricity consumption feature includes the electricity consumption change rate and the power outage duration. Based on the power outage type and the spatial distribution information of each user terminal, a preset clustering strategy is used to generate the power outage impact area, and the power outage impact area is sent to the user terminal.

[0008] Secondly, the present invention provides a user-side power outage fault analysis system, comprising: The acquisition module is configured to acquire power grid status data of a target area and electricity consumption data of each user terminal in the target area within a preset time period, and sort the power grid status data and electricity consumption data according to the time sequence to obtain a power grid status data sequence and an electricity consumption data sequence, wherein one electricity consumption data sequence corresponds to one electricity terminal. The judgment module is configured to determine whether there are any abnormal power grid events within the preset time period based on the power grid status data sequence and a preset power grid anomaly analysis strategy. The interception module is configured to, if there is at least one abnormal power grid event, use a preset data selection strategy to intercept at least one subsequence of electricity consumption data associated with the at least one abnormal power grid event from each electricity consumption data sequence according to the time node corresponding to the at least one abnormal power grid event. The output module is configured to determine a certain electricity consumption feature corresponding to a certain power grid abnormal event based on a certain electricity consumption data subsequence, and input the certain electricity consumption feature into a pre-trained power outage fault classification model. The power outage fault classification model corresponds to the power outage type of the certain power grid abnormal event. The certain electricity consumption feature includes the electricity consumption change rate and the power outage duration. The generation module is configured to generate the power outage impact area based on the power outage type and the spatial distribution information of each user terminal using a preset clustering strategy, and send the power outage impact area to the user terminal.

[0009] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the user-side power outage fault analysis method according to any embodiment of the present invention.

[0010] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the user-side power outage fault analysis method according to any embodiment of the present invention.

[0011] This application presents a user-side power outage fault analysis method and system that achieves accurate detection and classification of power outage faults through time-series correlation analysis of power grid status data and user terminal electricity consumption data. The system first identifies abnormal power grid events based on thresholds corrected for dynamic ambient temperature, significantly improving the adaptability and accuracy of abnormal state judgment and effectively avoiding misjudgments caused by environmental factors. By extracting user electricity consumption data subsequences associated with abnormal events and focusing on key features such as electricity consumption change rate and power outage duration, a pre-trained classification model is used to accurately identify outage types (such as planned outages and fault outages). Furthermore, by combining user spatial distribution information, a density clustering algorithm is used to automatically generate a geographical description of the outage impact area, achieving rapid spatial visualization and location of the outage impact. This method comprehensively improves the automation and response speed of power outage analysis, providing accurate decision support for power grid operation and maintenance personnel, while facilitating the delivery of accurate outage impact range information to users, enhancing the transparency and satisfaction of user services. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating a user-side power outage fault analysis method according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a user-side power outage fault analysis system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Please see Figure 1 The diagram shows a flowchart of a user-side power outage fault analysis method according to this application.

[0016] like Figure 1 As shown, the user-side power outage fault analysis method specifically includes the following steps: Step S101: Obtain the power grid status data of the target area and the electricity consumption data of each user terminal in the target area within a preset time period, and sort the power grid status data and the electricity consumption data according to the time sequence to obtain the power grid status data sequence and the electricity consumption data sequence, wherein one electricity consumption data sequence corresponds to one electricity terminal.

[0017] Step S102: Based on the power grid status data sequence, a preset power grid anomaly analysis strategy is used to determine whether there are any power grid anomaly events within the preset time period.

[0018] In this step, normal power grid status data of the target area within a historical time period is obtained, and the average of each normal power grid status data is calculated to obtain normal average power grid status data. Based on the historical ambient temperature of the historical time period and the real-time ambient temperature of each preset time period, the normal average power grid state data is corrected to obtain each target normal average power grid state data, and each target normal average power grid state data is defined as a dynamic state threshold. The degree of state deviation between each power grid state data in the power grid state data sequence and the dynamic state threshold is obtained, and the degree of state deviation is sorted according to time sequence to obtain the state deviation degree sequence. Sequentially determine whether the degree of each state deviation in the state deviation degree sequence is greater than a preset threshold; If at least two state deviations are greater than a preset threshold, then it is determined whether the time interval between the first state deviation and the second state deviation is greater than a preset time threshold. Here, the first state deviation and the second state deviation are the two state deviations with the shortest time interval among the at least two state deviations, and the power grid state data collection time corresponding to the first state deviation is earlier than the power grid state data collection time corresponding to the second state deviation. Specifically, if only one state deviation is greater than the preset threshold, or if all state deviations are not greater than the preset threshold, then it is directly determined that there are no abnormal power grid events in the target area within the preset time period. If it is not greater than a preset time threshold, it is determined that there is a power grid abnormal event in the target area within the preset time period, and the occurrence time of the power grid abnormal event is the time of collection of power grid state data corresponding to the first state deviation degree. If the time exceeds a preset time threshold, it is determined that there are no abnormal power grid events in the target area within the preset time period.

[0019] It should be noted that the normal average power grid state data is corrected based on the historical ambient temperature of the historical time period and the real-time ambient temperature of each preset time period to obtain the target normal average power grid state data, including: Calculate the ratio of the normal average power grid state data to the historical ambient temperature, and multiply the real-time ambient temperature at each time point within the preset time period with the historical ratio to obtain the normal average power grid state data for each target.

[0020] After determining whether there are any abnormal power grid events within the preset time period based on the power grid status data sequence and using a preset power grid anomaly analysis strategy, if there are no at least one abnormal power grid event, the user-side power outage fault analysis is stopped.

[0021] In one specific embodiment, the system first retrieves a sequence of power grid status data (such as voltage, frequency, load rate, etc.) of the target area from a historical database, showing that the area was in normal operating condition over a historical period (e.g., the past 30 days). The system then performs an arithmetic average calculation on these historical normal data to obtain the "normal average power grid status data" for the area, which serves as a static benchmark value for anomaly detection.

[0022] To adapt to the objective impact of environmental factors on the power grid's operating status (e.g., temperature changes can alter line impedance and load characteristics), the system introduces ambient temperature as a dynamic correction factor. Specifically, the ratio of historical normal average power grid state data to the average ambient temperature over the corresponding historical time period is calculated as a "unit temperature state coefficient." During the real-time monitoring phase, for each sampling time point within a preset time period, the real-time collected ambient temperature is multiplied by this coefficient to dynamically generate the "target normal average power grid state data" for that moment, which is then defined as the "dynamic state threshold" for that moment. This process allows the judgment threshold to adaptively adjust with temperature fluctuations, better reflecting the actual operating conditions of the power grid.

[0023] Subsequently, the system compares each data point in the real-time collected power grid state data sequence with the corresponding dynamic state threshold, calculates the absolute value or percentage of its relative deviation, and obtains the "state deviation degree" at each time point. The state deviation degrees at all times are arranged in chronological order to form a "state deviation degree sequence".

[0024] Next, the system employs a dual-criteria mechanism for anomaly detection. The first criterion is the amplitude criterion: it iterates through the sequence of state deviation levels, determining whether each value exceeds a preset fixed deviation threshold (e.g., 15%). If the state deviation level exceeds this threshold at least twice consecutively in the sequence, the second criterion—the time persistence criterion—is triggered. The system selects the pair with the shortest time interval between these two exceeding points and calculates the time difference between them. If this time difference is less than or equal to a preset time window threshold (e.g., 5 minutes), it is determined that a power grid anomaly event has occurred in the target area within a preset time period, and the data acquisition time corresponding to the earlier anomaly point is taken as the "occurrence time" of the anomaly event. Conversely, if the interval between exceeding points is too long, it is considered an occasional disturbance and determined as no power grid anomaly event.

[0025] It should be noted that if the entire judgment process ultimately determines that there is no abnormal power grid event, the system will terminate the current user-side power outage fault analysis process to save computing resources.

[0026] In summary, dynamic threshold compensation effectively mitigates normal fluctuations in grid status caused by factors such as temperature, thus avoiding false alarms due to changes in environmental conditions. Secondly, the dual-criteria mechanism (exceeding the limit and occurring consecutively within a short period) effectively distinguishes between genuine, persistent grid anomalies and instantaneous random interference or measurement noise, significantly reducing the system's false alarm rate and enhancing the reliability of the detection results. Finally, this method provides precise time anchors (occurrence times) for identified anomalies, laying a crucial foundation for accurately extracting data fragments associated with anomalies from massive user power consumption data in subsequent steps. This ensures the accuracy of time-series alignment throughout the analysis process and the effectiveness of subsequent feature extraction and fault classification, thereby comprehensively improving the intelligence level and judgment accuracy of the user-side power outage fault analysis system.

[0027] Step S103: If there is at least one power grid abnormal event, then according to the time node corresponding to the at least one power grid abnormal event, a preset data selection strategy is used to extract at least one power consumption data subsequence associated with the at least one power grid abnormal event from each power consumption data sequence.

[0028] In this step, if there is at least one power grid anomaly event, then based on the occurrence time of a certain power grid anomaly event, a first power consumption data subsequence of a first preset duration and a second power consumption data subsequence of a second preset duration are extracted from each power consumption data sequence; the first power consumption data subsequence and the second power consumption data subsequence are spliced ​​together based on time order to obtain a certain power consumption data subsequence associated with a certain power grid anomaly event.

[0029] Step S104: Determine a certain electricity consumption feature corresponding to a certain power grid abnormal event based on a certain electricity consumption data subsequence, and input the certain electricity consumption feature into a pre-trained power outage fault classification model. The power outage fault classification model corresponds to the power outage type of the certain power grid abnormal event. The certain electricity consumption feature includes the electricity consumption change rate and the power outage duration.

[0030] Step S105: Based on the power outage type and the spatial distribution information of each user terminal, a preset clustering strategy is used to generate the power outage impact area, and the power outage impact area is sent to the user terminal.

[0031] In this step, a spatial distribution matrix is ​​constructed based on the latitude and longitude coordinates of the user terminal. Based on the spatial distribution matrix, a density clustering algorithm is used to identify the power outage user clustering areas. The center coordinates and influence radius of each power outage user clustering area are calculated to generate the power outage impact area.

[0032] In summary, the method presented in this application achieves accurate detection and classification of power outage faults by analyzing power grid status data and user terminal electricity consumption data through time-series correlation analysis. The system first identifies abnormal power grid events based on thresholds corrected for dynamic ambient temperature, significantly improving the adaptability and accuracy of abnormal state judgment and effectively avoiding misjudgments caused by environmental factors. By extracting user electricity consumption data subsequences associated with abnormal events and focusing on key features such as electricity consumption change rate and power outage duration, a pre-trained classification model is used to accurately identify outage types (such as planned outages and fault outages). Furthermore, by combining user spatial distribution information, a density clustering algorithm is used to automatically generate a geographical description of the outage impact area, achieving rapid spatial visualization and location of the outage impact. This method comprehensively improves the automation and response speed of power outage analysis, providing accurate decision support for power grid operation and maintenance personnel, while facilitating the delivery of accurate outage impact range information to users, enhancing the transparency and satisfaction of user services.

[0033] Please see Figure 2 The diagram shows a structural block diagram of a user-side power outage fault analysis system according to this application.

[0034] like Figure 2 As shown, the user-side power outage fault analysis system 200 includes an acquisition module 210, a judgment module 220, an interception module 230, an output module 240, and a generation module 250.

[0035] The acquisition module 210 is configured to acquire power grid status data of a target area and electricity consumption data of each user terminal within the target area within a preset time period, and sort the power grid status data and electricity consumption data according to time sequence to obtain a power grid status data sequence and an electricity consumption data sequence, wherein one electricity consumption data sequence corresponds to one electricity terminal; the judgment module 220 is configured to determine whether there is a power grid abnormal event within the preset time period based on the power grid status data sequence and a preset power grid abnormality analysis strategy; the interception module 230 is configured to, if there is at least one power grid abnormal event, use a preset data interception strategy based on the time node corresponding to the at least one power grid abnormal event. A selection strategy is used to extract at least one subsequence of electricity consumption data associated with at least one power grid anomaly from each electricity consumption data sequence; the output module 240 is configured to determine a certain electricity consumption feature corresponding to a certain power grid anomaly based on a certain electricity consumption data subsequence, and input the certain electricity consumption feature into a pre-trained power outage fault classification model, wherein the power outage fault classification model corresponds to the power outage type of the certain power grid anomaly, and wherein the certain electricity consumption feature includes the rate of change of electricity consumption and the duration of power outage; the generation module 250 is configured to generate a power outage impact area based on the power outage type and the spatial distribution information of each user terminal using a preset clustering strategy, and send the power outage impact area to the user terminal.

[0036] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0037] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the user-side power outage fault analysis method in any of the above method embodiments. In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows: The power grid status data of the target area and the electricity consumption data of each user terminal in the target area are acquired within a preset time period. The power grid status data and the electricity consumption data are sorted according to the time sequence to obtain the power grid status data sequence and the electricity consumption data sequence. Each electricity consumption data sequence corresponds to one electricity terminal. Based on the power grid status data sequence, a preset power grid anomaly analysis strategy is used to determine whether there are any power grid anomaly events within the preset time period; If there is at least one power grid abnormal event, then according to the time node corresponding to the at least one power grid abnormal event, a preset data selection strategy is used to extract at least one power consumption data subsequence associated with the at least one power grid abnormal event from each power consumption data sequence. Based on a certain electricity consumption data subsequence, a certain electricity consumption feature corresponding to a certain power grid abnormal event is determined, and the certain electricity consumption feature is input into a pre-trained power outage fault classification model. The power outage fault classification model corresponds to the power outage type of the certain power grid abnormal event. The certain electricity consumption feature includes the electricity consumption change rate and the power outage duration. Based on the power outage type and the spatial distribution information of each user terminal, a preset clustering strategy is used to generate the power outage impact area, and the power outage impact area is sent to the user terminal.

[0038] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of the user-side power outage fault analysis system, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely disposed relative to a processor, which can be connected to the user-side power outage fault analysis system via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0039] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3 Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby implementing the user-side power outage fault analysis method described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the user-side power outage fault analysis system. The output device 340 may include a display screen or other display device.

[0040] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0041] In one implementation, the above-described electronic device is applied to a user-side power outage fault analysis system for a client, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: The power grid status data of the target area and the electricity consumption data of each user terminal in the target area are acquired within a preset time period. The power grid status data and the electricity consumption data are sorted according to the time sequence to obtain the power grid status data sequence and the electricity consumption data sequence. Each electricity consumption data sequence corresponds to one electricity terminal. Based on the power grid status data sequence, a preset power grid anomaly analysis strategy is used to determine whether there are any power grid anomaly events within the preset time period; If there is at least one power grid abnormal event, then according to the time node corresponding to the at least one power grid abnormal event, a preset data selection strategy is used to extract at least one power consumption data subsequence associated with the at least one power grid abnormal event from each power consumption data sequence. Based on a certain electricity consumption data subsequence, a certain electricity consumption feature corresponding to a certain power grid abnormal event is determined, and the certain electricity consumption feature is input into a pre-trained power outage fault classification model. The power outage fault classification model corresponds to the power outage type of the certain power grid abnormal event. The certain electricity consumption feature includes the electricity consumption change rate and the power outage duration. Based on the power outage type and the spatial distribution information of each user terminal, a preset clustering strategy is used to generate the power outage impact area, and the power outage impact area is sent to the user terminal.

[0042] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A user-side power outage fault analysis method, characterized in that, include: The power grid status data of the target area and the electricity consumption data of each user terminal in the target area are acquired within a preset time period. The power grid status data and the electricity consumption data are sorted according to the time sequence to obtain the power grid status data sequence and the electricity consumption data sequence. Each electricity consumption data sequence corresponds to one electricity terminal. Based on the power grid status data sequence, a preset power grid anomaly analysis strategy is used to determine whether there are any power grid anomaly events within the preset time period; If there is at least one power grid abnormal event, then according to the time node corresponding to the at least one power grid abnormal event, a preset data selection strategy is used to extract at least one power consumption data subsequence associated with the at least one power grid abnormal event from each power consumption data sequence. Based on a certain electricity consumption data subsequence, a certain electricity consumption feature corresponding to a certain power grid abnormal event is determined, and the certain electricity consumption feature is input into a pre-trained power outage fault classification model. The power outage fault classification model corresponds to the power outage type of the certain power grid abnormal event. The certain electricity consumption feature includes the electricity consumption change rate and the power outage duration. Based on the power outage type and the spatial distribution information of each user terminal, a preset clustering strategy is used to generate the power outage impact area, and the power outage impact area is sent to the user terminal.

2. The user-side power outage fault analysis method according to claim 1, characterized in that, The step of determining whether there are any abnormal power grid events within the preset time period based on the power grid status data sequence and using a preset power grid anomaly analysis strategy includes: Obtain normal power grid status data for the target area within a historical time period, and average the data for each normal power grid status to obtain the normal average power grid status data. Based on the historical ambient temperature of the historical time period and the real-time ambient temperature of each preset time period, the normal average power grid state data is corrected to obtain each target normal average power grid state data, and each target normal average power grid state data is defined as a dynamic state threshold. The degree of state deviation between each power grid state data in the power grid state data sequence and the dynamic state threshold is obtained, and the degree of state deviation is sorted according to time sequence to obtain the state deviation degree sequence. Sequentially determine whether the degree of each state deviation in the state deviation degree sequence is greater than a preset threshold; If at least two state deviations are greater than a preset threshold, then it is determined whether the time interval between the first state deviation and the second state deviation is greater than a preset time threshold. The first state deviation and the second state deviation are the two state deviations with the shortest time interval among the at least two state deviations, and the power grid state data collection time corresponding to the first state deviation is earlier than the power grid state data collection time corresponding to the second state deviation. If it is not greater than a preset time threshold, it is determined that there is a power grid abnormal event in the target area within the preset time period, and the occurrence time of the power grid abnormal event is the time of collection of power grid state data corresponding to the first state deviation degree. If the time exceeds a preset time threshold, it is determined that there are no abnormal power grid events in the target area within the preset time period.

3. The user-side power outage fault analysis method according to claim 2, characterized in that, The process of correcting the normal average power grid state data based on the historical ambient temperature of the historical time period and the real-time ambient temperature of each preset time period to obtain the target normal average power grid state data includes: Calculate the ratio of the normal average power grid state data to the historical ambient temperature, and multiply the real-time ambient temperature at each time point within the preset time period with the historical ratio to obtain the normal average power grid state data for each target.

4. The user-side power outage fault analysis method according to claim 1, characterized in that, After determining whether there are any abnormal power grid events within the preset time period based on the power grid state data sequence and using a preset power grid anomaly analysis strategy, the method further includes: If no power grid anomaly event exists, the user-side power outage fault analysis is stopped.

5. The user-side power outage fault analysis method according to claim 1, characterized in that, The step of extracting at least one subsequence of electricity consumption data associated with the at least one power grid anomaly event from each electricity consumption data sequence according to the time node corresponding to the at least one power grid anomaly event, using a preset data selection strategy, includes: Based on the occurrence time of a certain power grid abnormal event, a first power consumption data subsequence with a first preset time length is extracted from each power consumption data sequence, and a second power consumption data subsequence with a second preset time length is extracted from each sequence. The first and second electricity consumption data subsequences are concatenated in chronological order to obtain a certain electricity consumption data subsequence associated with the aforementioned power grid anomaly event.

6. The user-side power outage fault analysis method according to claim 1, characterized in that, The step of generating the power outage impact area based on the power outage type and the spatial distribution information of each user terminal using a preset clustering strategy includes: A spatial distribution matrix is ​​constructed based on the latitude and longitude coordinates of the user terminal, and a density clustering algorithm is used to identify the areas where power outage users gather based on the spatial distribution matrix. Calculate the center coordinates and influence radius of each power outage user cluster area to generate the power outage impact area.

7. A user-side power outage fault analysis system, characterized in that, include: The acquisition module is configured to acquire power grid status data of a target area and electricity consumption data of each user terminal in the target area within a preset time period, and sort the power grid status data and electricity consumption data according to the time sequence to obtain a power grid status data sequence and an electricity consumption data sequence, wherein one electricity consumption data sequence corresponds to one electricity terminal. The judgment module is configured to determine whether there are any abnormal power grid events within the preset time period based on the power grid status data sequence and a preset power grid anomaly analysis strategy. The interception module is configured to, if there is at least one abnormal power grid event, use a preset data selection strategy to intercept at least one subsequence of electricity consumption data associated with the at least one abnormal power grid event from each electricity consumption data sequence according to the time node corresponding to the at least one abnormal power grid event. The output module is configured to determine a certain electricity consumption feature corresponding to a certain power grid abnormal event based on a certain electricity consumption data subsequence, and input the certain electricity consumption feature into a pre-trained power outage fault classification model. The power outage fault classification model corresponds to the power outage type of the certain power grid abnormal event. The certain electricity consumption feature includes the electricity consumption change rate and the power outage duration. The generation module is configured to generate the power outage impact area based on the power outage type and the spatial distribution information of each user terminal using a preset clustering strategy, and send the power outage impact area to the user terminal.

8. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the method described in any one of claims 1 to 6.

Images