Automatic monitoring method and system for low-voltage power distribution fault based on Internet of Things

Abstract

The present invention discloses an automatic monitoring method and system for low-voltage power distribution faults based on the Internet of Things, and relates to the relevant fields of smart grids. The method includes: collecting power consumption information and meter information of low-voltage users, constructing a power grid user topology, setting a topology level, and setting a multi-level power grid user topology network; performing abnormal monitoring and positioning of user power grids; clustering abnormal power consumption information of users; collecting the supply relationship of low-voltage power distribution, and integrating it with a multi-level power grid user topology network to obtain a fused power distribution topology; tracing the source of low-voltage power distribution according to abnormal distribution, locating supply control parameters, and performing abnormal feedback of low-voltage distribution network. The method solves the technical problems of the existing low-voltage power distribution fault monitoring, such as the difficulty in realizing comprehensive real-time monitoring and fault monitoring of distribution networks, and the low fault handling efficiency and accuracy, and achieves the technical effect of realizing comprehensive real-time monitoring and fault monitoring of low-voltage distribution networks, and improving fault handling efficiency and accuracy.

Description

Technical Field

[0001] The present application relates to the field of smart grid, and in particular to a method and system for automatically monitoring low-voltage power distribution faults based on the Internet of Things. Background Art

[0002] With the acceleration of urbanization and the growing demand for electricity, the low-voltage distribution network, as the "last mile" of power supply, has become increasingly complex and covers a wide range. The traditional distribution network management model often relies on manual inspections and manual records. During the transformation of the distribution network, the change information of the topological relationship is prone to omissions, false alarms, and failure to enter the system. This method is not only time-consuming and labor-intensive, but also difficult to achieve comprehensive real-time monitoring of the distribution network. In addition, due to the lack of in-depth analysis of user power consumption, existing methods often find it difficult to accurately locate the source of the fault, resulting in untimely fault handling and affecting the normal power consumption of users.

[0003] In the current related technologies, low-voltage distribution fault monitoring has the technical problems of difficulty in achieving comprehensive real-time monitoring and fault monitoring of the distribution network, and low efficiency and accuracy of fault handling. Summary of the invention

[0004] The present application provides an automatic monitoring method and system for low-voltage power distribution faults based on the Internet of Things, adopts the Internet of Things technology to collect the power consumption information and meter information of low-voltage users in real time, constructs a power grid user topology structure, and sets the topology structure level according to the collection scope to form a multi-level power grid user topology structure network. The multi-level power grid user topology structure network is used to monitor and locate user power grid anomalies, and low-voltage distribution is traced based on the integrated distribution topology structure, and supply control parameters are located for abnormal feedback. Technical means such as these achieve the technical effect of realizing comprehensive real-time monitoring and automatic fault monitoring of the low-voltage distribution network, and improving the efficiency and accuracy of fault handling.

[0005] The present application provides a method for automatic monitoring of low-voltage power distribution faults based on the Internet of Things, including:

[0006] Based on the Internet of Things, the electricity consumption information and meter information of low-voltage users are collected to build the topological structure of power grid users, and the topological structure level is set according to the collection scope, and a multi-level power grid user topological structure network is set;

[0007] Utilizing the multi-level power grid user topology structure network, abnormal monitoring and positioning of user power grids are performed to obtain abnormal power consumption information of users;

[0008] Clustering the abnormal power consumption information of the user according to the occurrence time period or the occurrence area range to obtain abnormal distribution;

[0009] Collecting the supply relationship of low-voltage power distribution, integrating the multi-level power grid user topology network with the supply relationship to obtain a fused distribution topology structure;

[0010] According to the abnormal distribution, the low-voltage distribution source is traced through the integrated distribution topology, and the supply control parameters are located to provide abnormal feedback of the low-voltage distribution network.

[0011] In a possible implementation, the Internet of Things is used to collect electricity consumption information and meter information of low-voltage users, build a topological structure of power grid users, and perform the following processing:

[0012] Based on the Internet of Things, the electric meter is located according to the electric meter information to determine the location information of the electric meter;

[0013] Collecting user electricity consumption information according to the electric meter information to obtain user voltage data;

[0014] Based on the electricity meter location information, the power grid user topology structure is constructed, and the mapping relationship between the user voltage data and the electricity meter information is used to establish a relationship connection between the user voltage data and the power grid user topology structure.

[0015] In a possible implementation, the topology level is set according to the acquisition scope, a multi-level power grid user topology network is set, and the following processing is performed:

[0016] Preset the quantity threshold of multi-level classification;

[0017] Perform location clustering according to the meter location information to obtain user clustering circles;

[0018] Reclassify the user clustering circles based on the preset multi-level classification quantity threshold, and sequentially obtain a base user topology structure, a second-layer user topology structure, and so on until an N-layer user topology structure, where N is a positive integer, wherein the quantity threshold of the base user topology structure is greater than the quantity threshold of the second-layer user topology structure, and so on, the quantity threshold of the N-layer user topology structure is the smallest;

[0019] The base user topology structure, the second-layer user topology structure, ..., and the N-layer user topology structure are sequentially established to construct the multi-level power grid user topology structure network.

[0020] In a possible implementation, the multi-level power grid user topology network is used to monitor and locate user power grid anomalies, obtain user power consumption anomaly information, and perform the following processing:

[0021] According to the multi-level power grid user topology network, hierarchical monitoring periods are set respectively according to hierarchical relationships, wherein the base monitoring period is greater than the second layer monitoring period, and the N layer monitoring period is the smallest;

[0022] Building a distributed computing network, including a multi-level analysis operator, the multi-level analysis operator corresponds to a multi-level power grid user topology network, the multi-level analysis operator has a computing cycle according to the hierarchical relationship, and the computing cycle matches the hierarchical monitoring cycle;

[0023] Based on the grassroots monitoring cycle, the grassroots analysis operator is activated to perform power consumption analysis of users in the grassroots user topology structure, and anomaly comparison or status monitoring is performed according to the historical data characteristics of the user voltage data to determine the abnormal power consumption information of the user, wherein the abnormal power consumption information of the user includes power consumption feature matching abnormality or offline abnormality;

[0024] When the abnormal power consumption information of the user reaches the warning requirement, a warning reminder is issued;

[0025] When the warning requirement is not met, the level monitoring cycle continues to be executed to complete the monitoring and analysis of the subsequent levels.

[0026] In a possible implementation, the abnormality comparison is performed according to the historical data characteristics of the user voltage data, and the following processing is performed:

[0027] Performing voltage curve fitting on the user voltage data to obtain a user voltage trend curve;

[0028] The user voltage trend curve is divided according to the curve trend range and the time period;

[0029] Based on the trend range segmentation results, determine the user's electricity consumption characteristics;

[0030] Establish a mapping relationship between the time period segmentation results and the trend range segmentation results to determine the user's periodic electricity consumption characteristics;

[0031] A feature tolerance range is set, and based on the user's power usage features, the user's periodic power usage features and the feature tolerance range, an abnormality comparison module is generated to perform abnormality comparison.

[0032] In a possible implementation, the user power consumption anomaly information is clustered according to the occurrence time period or occurrence area range to obtain anomaly distribution, and the following processing is performed:

[0033] When the abnormal power consumption information of the user does not meet the warning requirement, obtaining abnormal power consumption information of all users;

[0034] Clustering the user's power consumption anomaly information according to the occurrence time period and the occurrence area range to obtain period anomaly distribution and regional anomaly distribution;

[0035] The periodic anomaly distribution and the regional anomaly distribution are merged to obtain the anomaly distribution.

[0036] In a possible implementation, according to the abnormal distribution, through the integrated distribution topology, low-voltage distribution source tracing is performed, supply control parameters are located, and abnormal feedback of the low-voltage distribution network is performed, and the following processing is performed:

[0037] Perform abnormal distribution location according to the abnormal distribution to obtain abnormal distribution level features and abnormal distribution node features, wherein the abnormal distribution level features include same-level and same-partition abnormalities, same-level cross-partition abnormalities, and cross-level abnormalities;

[0038] Setting an abnormality feedback level according to the abnormality distribution level characteristics;

[0039] Determining power grid distribution equipment and supply control parameters according to the abnormal distribution node characteristics;

[0040] Based on the abnormal power consumption information and abnormal distribution of the user, an adjustment target value is obtained, and an optimization model is constructed based on the influence relationship between the adjustment target value and the supply control parameter of the power grid distribution equipment, and an iterative optimization is performed to obtain the power distribution optimization parameter;

[0041] According to the abnormal feedback level, it is converted into an adjustment constraint coefficient, the distribution optimization parameter and the abnormal feedback level adjustment constraint coefficient are used as abnormal feedback information, and feedback is performed according to the corresponding requirements of the abnormal feedback level.

[0042] This application also provides a low-voltage power distribution fault automatic monitoring system based on the Internet of Things, including:

[0043] A multi-level power grid user topology network setting module, which is used to collect power consumption information and meter information of low-voltage users based on the Internet of Things, build a power grid user topology structure, set the topology level according to the collection scope, and set the multi-level power grid user topology network;

[0044] A user power grid anomaly monitoring module, the user power grid anomaly monitoring module is used to use the multi-level power grid user topology network to perform user power grid anomaly monitoring and positioning, and obtain user power consumption anomaly information;

[0045] An abnormal information clustering module, the abnormal information clustering module is used to cluster the abnormal power consumption information of the user according to the occurrence time period or the occurrence area range to obtain abnormal distribution;

[0046] A fused distribution topology acquisition module, which is used to collect the supply relationship of low-voltage distribution, merge the multi-level power grid user topology network with the supply relationship, and obtain a fused distribution topology structure;

[0047] The abnormal feedback module is used to perform low-voltage distribution tracing based on the abnormal distribution and locate supply control parameters to perform abnormal feedback on the low-voltage distribution network through the integrated distribution topology.

[0048] The method and system for automatic monitoring of low-voltage power distribution faults based on the Internet of Things proposed in this application first collects power consumption information and meter information of low-voltage users based on the Internet of Things, constructs a power grid user topology structure, sets the topology level according to the collection scope, and sets a multi-level power grid user topology structure network. Then, the multi-level power grid user topology structure network is used to monitor and locate user power grid anomalies, obtain user power consumption anomaly information, and then cluster the user power consumption anomaly information according to the occurrence time period or the occurrence area to obtain the anomaly distribution. Then, the supply relationship of low-voltage distribution is collected, and the multi-level power grid user topology structure network is integrated with the supply relationship to obtain an integrated distribution topology structure. Finally, according to the anomaly distribution, the low-voltage distribution is traced through the integrated distribution topology structure, and the supply control parameters are located to perform abnormal feedback on the low-voltage distribution network, thereby achieving the technical effect of realizing comprehensive real-time monitoring and automatic fault monitoring of the low-voltage distribution network, and improving the efficiency and accuracy of fault handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0050] Figure 1 A schematic diagram of a flow chart of a method for automatic monitoring of low-voltage power distribution faults based on the Internet of Things provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the structure of an automatic monitoring system for low-voltage power distribution faults based on the Internet of Things provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0053] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0054] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0055] The present application embodiment provides a method for automatically monitoring low-voltage power distribution faults based on the Internet of Things, such as Figure 1 As shown, the method includes:

[0056] Step S100, based on the Internet of Things, electricity consumption information and meter information of low-voltage users are collected to construct a topological structure of power grid users, and the topological structure level is set according to the collection scope, and a multi-level topological structure network of power grid users is set. Specifically, the Internet of Things sensors and collectors are deployed on the meters and power-consuming devices of low-voltage users to obtain electricity consumption information and meter status in real time. Using the Internet of Things devices, the voltage, current, power and other electricity consumption information of low-voltage users are collected in real time, and the meter information, including power reading, meter status, communication status, etc., is collected at the same time. The collected raw data is cleaned, abnormal values, duplicate values ​​or erroneous data are removed, and the data is formatted and converted into a unified data format. According to the electricity consumption relationship, power supply relationship and geographical location relationship between users, a topological structure diagram of power grid users is constructed, and the topological structure diagram of power grid users is a connection relationship diagram between low-voltage users, in which nodes represent users or meters, and edges represent power supply lines or communication lines. According to different collection scopes, the topological structure of power grid users is divided into different levels, such as community level, street level, city level, etc., and topological structures of different levels contain user information of different scopes and granularities. The power grid user topology structures at different levels are connected according to a hierarchical relationship to form a multi-level power grid user topology structure network, which displays the hierarchical relationship and overall topology structure between users.

[0057] In a possible implementation, the electricity consumption information and meter information of low-voltage users are collected based on the Internet of Things to construct a power grid user topology structure. Step S100 further includes step S110, based on the Internet of Things, the meter is located according to the meter information to determine the meter location information. Specifically, the relevant information of the meter, including the meter ID, communication address, signal strength, etc., is collected through the Internet of Things device. According to the collected meter information, a positioning method is applied, including positioning based on signal strength, positioning based on a reference point of a known location, etc., to determine the specific location of the meter. The meter location information can be a longitude and latitude coordinate, an address, or a relative position relative to other known locations. Step S120, user electricity consumption information is collected according to the meter information to obtain user voltage data. Specifically, according to the meter location information and status, a collection instruction is sent to the meter through the Internet of Things system, and the meter responds to the collection instruction and returns real-time voltage data. The user voltage data can be an instantaneous value, an average value, or other statistical value of the voltage. Step S130, based on the meter location information, construct the power grid user topology structure, and use the mapping relationship between the user voltage data and the meter information to establish a relational connection between the user voltage data and the power grid user topology structure. Specifically, according to the meter location information and the power supply relationship between users, the power grid user topology structure is initialized. The power grid user topology structure is a collection of nodes and edges. The nodes represent users or meters, and the edges represent power supply lines. Using the mapping relationship between user voltage data and meter information, the user voltage data is associated with the corresponding nodes in the power grid user topology structure. In this way, each node not only represents a user or meter, but also contains voltage data related to the user or meter. This implementation method establishes a relational connection between the user voltage data and the power grid user topology structure, which can monitor the user's voltage situation in real time, and achieves the technical effect of providing basic support for power grid abnormality monitoring and traceability analysis.

[0058] In a possible implementation, the topology level is set according to the acquisition scope, and a multi-level power grid user topology network is set. Step S100 further includes step S140, presetting the number threshold of the multi-level classification. Specifically, according to the scale of the power grid and the needs of users, the number of levels of the power grid user topology structure is determined, and for each level of the power grid user topology structure, a number threshold is preset. The number threshold is set according to the needs of power grid management. For example, the grassroots user topology structure contains more users, so the number threshold is larger, and the high-level user topology structure contains fewer aggregation areas or nodes, so the number threshold is smaller. Step S150, according to the meter location information, location clustering is performed to obtain user clustering circles. Specifically, a clustering algorithm, such as K-means (K-means clustering), DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm, etc., is applied to cluster the meter location information (latitude and longitude coordinates, address, etc.) to form user clustering circles, and each user clustering circle represents a geographically close user set. Step S160, reclassify the user clustering circle based on the preset multi-level classification quantity threshold, and obtain the grassroots user topology structure, the second-layer user topology structure... until the N-layer user topology structure in turn, N is a positive integer, wherein the quantity threshold of the grassroots user topology structure is greater than the quantity threshold of the second-layer user topology structure, and so on, the quantity threshold of the N-layer user topology structure is the smallest. Specifically, the user clustering circle is used as the grassroots user topology structure, and according to the preset quantity threshold, according to the geographical proximity and the power supply relationship of the power grid, the grassroots user topology structure is merged to form a two-layer user topology structure, and the above process is repeated to form a three-layer, four-layer, and even N-layer user topology structure in turn, and the quantity threshold of each layer is reduced in turn until the preset level and quantity requirements are met. Step S170, establish the inclusive hierarchical relationship of the grassroots user topology structure, the second-layer user topology structure... until the N-layer user topology structure in turn, and construct the multi-level power grid user topology structure network. Specifically, the inclusion relationship between user topological structures at each level is defined, that is, the high-level user topological structure includes the low-level user topological structure. According to the defined relationship, the user topological structures at each level are connected to form a multi-level power grid user topological structure network containing hierarchical relationships. This implementation method aggregates and classifies a large amount of user information according to certain rules by presetting the number threshold of multi-level classification, thus realizing hierarchical monitoring and management of the power grid. When an abnormality occurs, it can be quickly located to a specific level and area, achieving the technical effect of realizing hierarchical and refined management of the power grid, improving management efficiency, and facilitating abnormal monitoring and tracing.

[0059] Step S200, using the multi-level power grid user topology network, perform user power grid anomaly monitoring and positioning, and obtain user power consumption anomaly information. Specifically, using the multi-level power grid user topology network, collect the power consumption data of each user in the power grid in real time, including key indicators such as voltage, current, and power. Clean the collected data, remove noise and outliers, ensure the accuracy and consistency of the data, and standardize the data so that data from different sources and formats can be uniformly compared and analyzed. According to the characteristics and actual needs of the power grid, determine the anomaly detection algorithm, such as a statistical method, a machine learning model, etc., and use historical data to train the anomaly detection algorithm so that the anomaly detection algorithm can identify normal power consumption patterns and abnormal power consumption patterns. Input the real-time collected user power consumption data into the trained anomaly detection model to perform real-time anomaly detection, and preliminarily locate the abnormal user or meter according to the results output by the anomaly detection model. Combined with the multi-level power grid user topology network, starting from the grassroots user topology, trace upward layer by layer until the specific abnormality area or level is located, analyze the power consumption data, equipment status and other information in the abnormality area, and determine the specific cause of the abnormality, such as equipment failure, power supply line problem, illegal power use, etc. The located abnormal information, cause analysis results, etc. are sorted out to form the user power consumption abnormality information.

[0060] In a possible implementation, step S200 further includes step S210, according to the multi-level power grid user topology structure network, according to the hierarchical relationship, respectively set the hierarchical monitoring cycle, wherein the base monitoring cycle is greater than the second layer monitoring cycle, and the N layer monitoring cycle is the smallest. Specifically, analyze the characteristics of different levels in the multi-level power grid user topology structure network, such as the number of users, power supply range, importance, etc., and according to the analysis results, set a suitable monitoring cycle for each level, wherein the base monitoring cycle is set to be longer because the number of base users is large and the range is wide, but the probability of abnormal occurrence is relatively low, and the high-level monitoring cycle is set to be shorter because these levels represent important power supply nodes or areas and require more frequent monitoring. Step S220, build a distributed computing network, which includes a multi-level analysis operator, the multi-level analysis operator corresponds to the multi-level power grid user topology structure network, and the multi-level analysis operator has a calculation cycle according to the hierarchical relationship, and the calculation cycle matches the hierarchical monitoring cycle. Specifically, according to the hierarchical relationship of the multi-level power grid user topology network, a corresponding multi-level analysis operator is designed. The multi-level analysis operator is used to process and analyze the power consumption data of users at different levels. A calculation cycle is configured for each analysis operator. The calculation cycle matches the corresponding hierarchical monitoring cycle, and is used to start the corresponding analysis operator in time for calculation and analysis at the end of each monitoring cycle. Step S230, based on the grassroots monitoring cycle, the grassroots analysis operator is activated to perform power consumption analysis of users in the grassroots user topology structure, and abnormal comparison or status monitoring is performed according to the historical data characteristics of the user voltage data to determine the abnormal power consumption information of the user, and the abnormal power consumption information of the user includes power consumption feature matching abnormality or offline abnormality. Specifically, according to the grassroots monitoring cycle, when the cycle arrives, the grassroots analysis operator is activated, and the grassroots analysis operator is used to analyze the power consumption data of users in the grassroots user topology structure, including abnormal comparison or status monitoring according to the historical data characteristics of the user voltage data. According to the analysis results, the abnormal power consumption information of the user is determined, including power consumption feature matching abnormality (such as voltage fluctuation exceeding the normal range) or offline abnormality (such as no data upload of the meter for a long time). Step S240, when the abnormal power consumption information of the user meets the early warning requirements, an early warning reminder is issued; step S250, when the early warning requirements are not met, the hierarchical monitoring cycle is continued to be executed to complete the monitoring and analysis of the subsequent levels. Specifically, the determined abnormal power consumption information of the user is evaluated to determine whether it meets the early warning requirements. If the abnormal power consumption information of the user meets the early warning requirements, an early warning reminder is issued and the relevant personnel are notified to handle it. If the early warning requirements are not met, the monitoring cycle of the current level is continued to be executed, and the arrival of the next cycle is waited for. When the monitoring cycle of a higher level arrives, the analysis operator of the corresponding level is activated, and higher-level monitoring and analysis are performed, tracing upward layer by layer until the specific abnormality area or level is located.This implementation method utilizes distributed computing networks and multi-level analysis operators to improve processing efficiency and accuracy, achieving the technical effect of efficient and accurate abnormal monitoring and positioning of user power grids.

[0061] In another possible implementation, the abnormal comparison is performed according to the historical data characteristics of the user voltage data, and step S230 further includes step S231, performing voltage curve fitting on the user voltage data to obtain the user voltage trend curve. That is, a curve that can represent the user voltage trend is fitted by mathematical methods (such as least squares method, polynomial fitting, etc.), and the user voltage trend curve is used to reverse the voltage change trend over time. Step S232, the user voltage trend curve is divided according to the curve trend range and time period. Specifically, the user voltage trend curve obtained by fitting is divided, and there are two ways of segmentation, one is to segment according to the curve trend range, that is, according to the trend change of the curve, the curve is divided into different sections, each section represents a specific voltage change trend or range, and the other is to segment according to the time period, that is, the curve is segmented according to a fixed time period (such as hours, days, weeks, etc.) to reflect the voltage changes in different time periods. Step S233, based on the trend range segmentation result, determine the user's electricity consumption characteristics. That is, based on the segmentation results of the curve trend range, the user's electricity consumption characteristics are analyzed. For example, some sections represent the user's peak electricity consumption, and other sections represent the trough electricity consumption. The user's electricity consumption characteristics reflect the user's electricity consumption habits and needs. Step S234, establish a mapping relationship between the time period segmentation results and the trend range segmentation results, and determine the user's periodic electricity consumption characteristics. That is, combine the time period segmentation results with the trend range segmentation results to establish a mapping relationship between them. This mapping relationship can reflect the user's periodic electricity consumption characteristics. The user's periodic electricity consumption characteristics not only reflect the user's electricity consumption in a certain specific time period, but also characterize how this electricity consumption changes over time. Step S235, set a feature tolerance range, and generate an abnormal comparison module based on the user's electricity consumption characteristics, the user's periodic electricity consumption characteristics and the feature tolerance range to perform abnormal comparison. Specifically, a feature tolerance range is set based on historical data and experience. The feature tolerance range is used to determine whether the current power consumption characteristics are abnormal. Then, the abnormal comparison module is used to compare the current user power consumption characteristics with the user's historical power consumption characteristics. If it exceeds the set feature tolerance range, it is considered that there is an abnormality. This implementation method combines the time period with the voltage trend range to establish a bridge between the time period and the voltage trend range, so that the user's power consumption characteristics can be analyzed more comprehensively. By comparing the power consumption characteristics of the current time period with the power consumption characteristics of the same period in history, it can be more accurately determined whether there is abnormal power consumption, achieving the technical effect of effective abnormality detection and management.

[0062] Step S300, clustering the user power consumption anomaly information according to the time period or the area of ​​occurrence to obtain the anomaly distribution. Specifically, the user power consumption anomaly information includes the specific time, location, anomaly type and degree of the anomaly, and extracting key features from the user power consumption anomaly information for cluster analysis. For time period clustering, key features include the specific date and time (such as hour, day, week, month, etc.) of the anomaly and periodic patterns (such as seasonal changes). For regional range clustering, key features include geographical location information where the anomaly occurs, such as longitude and latitude, administrative region, etc. The extracted features are preprocessed, including processing missing values ​​and outliers, standardization, normalization, etc., to ensure the availability of data, eliminate dimensional differences between different features, and improve the accuracy of clustering. For time period clustering, a clustering algorithm based on time series is used, such as the K-means algorithm combined with the dynamic time warping (DTW) distance metric. For regional range clustering, a density-based clustering algorithm (such as DBSCAN) or a hierarchical clustering algorithm is used. The preprocessed feature data is input into a determined clustering algorithm for clustering analysis. For time period clustering, the algorithm divides the anomaly information into different clusters according to the time characteristics and periodic patterns of the anomaly occurrence, and each cluster represents a specific time period anomaly pattern; for regional range clustering, the algorithm divides the anomaly information into different clusters according to the similarity of geographic location information, and each cluster represents the anomaly distribution within a specific regional range. The anomaly distribution obtained by clustering can be displayed using charts (such as heat maps, scatter plots, etc.), which reflect the distribution of anomalies in different time periods or regional ranges, as well as the similarities and differences between different clusters.

[0063] In a possible implementation, step S300 further includes step S310, when the user power consumption abnormal information does not meet the warning requirements, all user power consumption abnormal information is obtained. Specifically, when the user power consumption abnormal information is detected but does not meet the set warning requirements, the system will collect all relevant user power consumption abnormal information, including the time, location, abnormal type, abnormal degree and other detailed data of the abnormality. By collecting all user power consumption abnormal information, it is ensured that all relevant information is taken into account. Step S320, the user power consumption abnormal information is clustered according to the occurrence time period and the occurrence area range, and the period abnormal distribution and regional abnormal distribution are obtained. Specifically, the system performs cluster analysis on the collected user power consumption abnormal information. The clustering is based on the similarity of the data, and the purpose is to classify similar abnormal information into one category. The system performs clustering according to the time period (such as hours, days, weeks, months, etc.) and regional range (such as cities, regions, streets, etc.) when the abnormality occurs. Through the clustering of the time period, the abnormal distribution in different time periods is identified. For example, abnormalities caused by peak power consumption may occur in certain time periods, while other time periods may be relatively stable. By clustering the region, the abnormal distribution in different geographical locations is revealed, and by comparing the number and type of abnormalities in different regions, it is identified which regions are more likely to have abnormal electricity consumption. Step S330, the periodic abnormal distribution and the regional abnormal distribution are merged to obtain the abnormal distribution. Specifically, after obtaining the periodic abnormal distribution and the regional abnormal distribution, the two abnormal distributions are merged based on certain weights or algorithms to obtain a comprehensive abnormal distribution. Through fusion, it is ensured that the information of the two abnormal distributions can be fully utilized, so that the distribution of abnormal electricity consumption of users can be more comprehensively reflected. This implementation method achieves the technical effect of more accurately revealing the abnormal distribution of electricity consumption of users by obtaining all abnormal electricity consumption information, clustering by time period and regional scope, and fusing the two distributions.

[0064] Step S400, collect the supply relationship of low-voltage power distribution, merge the multi-level power grid user topology network with the supply relationship, and obtain a fused distribution topology. Specifically, analyze the physical layout, electrical parameters and detailed records of the operating status of the power facilities, and collect the supply relationship data of the low-voltage distribution network through methods such as on-site investigation, equipment readings, sensor monitoring and data extraction from the power management system, including the connection relationship and power supply path between power supply points, substations, feeders, switches, branch lines and terminal users. Then, the collected low-voltage distribution supply relationship is merged with the multi-level power grid user topology network by means of graph theory, network analysis, etc., that is, the supply relationship data of low-voltage distribution is mapped to the corresponding position of the multi-level power grid user topology network, and ensure that the connection relationship and power supply path between them are accurately expressed in the fused distribution topology. After the above steps, a fused distribution topology is obtained, which fully reflects the power grid structure and power supply relationship, not only including the connection relationship between multi-level power grid users, but also describing the supply relationship and power supply path of the low-voltage distribution network.

[0065] Step S500, according to the abnormal distribution, through the fused distribution topology, low-voltage distribution is traced, and supply control parameters are located to perform abnormal feedback of the low-voltage distribution network. Specifically, by analyzing the periodic abnormal distribution and the regional abnormal distribution, the hot spots and time periods where the abnormalities occur, as well as the frequency and severity of the abnormalities, are identified. Next, the fused distribution topology obtained in step S400 is used to trace the low-voltage distribution. The fused distribution topology clearly shows the hierarchical structure of the power grid, the power supply path, and the connection relationship between the devices. Based on this information, the source of the abnormality is traced to determine which devices and paths caused the abnormality. In the tracing process, attention is paid to the supply control parameters related to the abnormal distribution, including voltage, current, power factor, etc. These supply control parameters directly reflect the operating status and power supply quality of the power grid. By analyzing the change trend and abnormal situation of these supply control parameters, specific supply control problems are located. Once the problem of the supply control parameters is located, the corresponding abnormal feedback is generated, including alarm information, fault report, optimization suggestions, etc. The abnormal feedback method includes interface display, SMS notification, email sending, etc., which is used to notify relevant personnel to handle the abnormality in time and take effective measures to repair and optimize. The embodiment of the present application adopts the Internet of Things technology to collect the electricity consumption information and meter information of low-voltage users in real time, constructs a power grid user topology structure, and sets the topology structure level according to the collection scope to form a multi-level power grid user topology structure network. The multi-level power grid user topology structure network is used to monitor and locate user power grid anomalies, and low-voltage distribution is traced based on the integrated distribution topology structure, and supply control parameters are located for abnormal feedback. Technical means such as abnormal feedback have achieved the technical effect of realizing comprehensive real-time monitoring and automatic fault monitoring of the low-voltage distribution network, and improving the efficiency and accuracy of fault handling.

[0066] In a possible implementation, step S500 further includes step S510, locating the abnormal distribution according to the abnormal distribution, obtaining the abnormal distribution hierarchical features and abnormal distribution node features, wherein the abnormal distribution hierarchical features include same-level and same-partition abnormalities, same-level cross-partition abnormalities, and cross-level abnormalities. Specifically, according to the abnormal distribution data, locate the specific location where the abnormality occurs, including a specific area, node or device. On the basis of positioning, further analyze the hierarchical features of the abnormal distribution, including same-level and same-partition abnormalities (i.e., abnormalities occurring in the same level and the same partition), same-level cross-partition abnormalities (abnormalities occurring at the same level but between different partitions), and cross-level abnormalities (abnormalities involving different levels). The abnormal distribution hierarchical features reflect the propagation and impact range of the abnormality. In addition to the hierarchical features, extract the node features related to the abnormal distribution, including the changes in the electrical parameters such as voltage, current, and power of the node, as well as information such as the operating status of the node. Step S520, set the abnormal feedback level according to the abnormal distribution hierarchical features. Specifically, according to the abnormal distribution level characteristics extracted in step S510, the corresponding abnormal feedback level is set. Since the degree of influence and urgency of abnormalities at different levels on the power grid are different, different feedback levels need to be set. For example, cross-level abnormalities usually involve multiple levels and devices, and have a wider impact range, so they are set to a higher feedback level. Step S530, according to the abnormal distribution node characteristics, determine the power grid distribution equipment and supply control parameters. Among them, the power grid distribution equipment includes direct equipment that causes the abnormality and key equipment affected by the abnormality. The supply control parameters reflect the operating status and performance of the power grid distribution equipment and are the key basis for power distribution optimization. Step S540, based on the user's power consumption abnormality information and abnormal distribution, obtain the adjustment target value, and construct an optimization model based on the influence relationship between the adjustment target value and the supply control parameters of the power grid distribution equipment, perform iterative optimization, and obtain the power distribution optimization parameters. Specifically, according to the user's power consumption abnormality information and abnormal distribution, determine the target value that needs to be adjusted, such as voltage range, power factor, etc. Based on the influence relationship between the adjustment target value and the supply control parameters of the power grid distribution equipment, an optimization model is constructed, and the optimization model is used to find the optimal distribution parameters to minimize the impact of abnormalities and improve the operating efficiency of the power grid. The optimization model is solved by an iterative optimization algorithm to obtain the distribution optimization parameters, and the distribution optimization parameters are used to guide the operation and management of the power grid and reduce the occurrence of abnormalities. Step S550, according to the abnormal feedback level, convert it into an adjustment constraint coefficient, use the distribution optimization parameter and the abnormal feedback level adjustment constraint coefficient as abnormal feedback information, and feedback according to the corresponding requirements of the abnormal feedback level. Specifically, according to the abnormal feedback level set in step S520, it is converted into a corresponding adjustment constraint coefficient, and the adjustment constraint coefficient reflects the adjustment requirements and restrictions on the distribution optimization parameters under different abnormal feedback levels.The distribution optimization parameters and the abnormal feedback level adjustment constraint coefficients are used as abnormal feedback information. These abnormal feedback information not only includes the optimized distribution parameters, but also considers the adjustment constraints under different abnormal feedback levels, providing comprehensive guidance and suggestions for relevant personnel. Finally, feedback is given according to the requirements corresponding to the abnormal feedback level. For example, for abnormalities with high feedback levels, more urgent and direct feedback methods are adopted to ensure that the problem is handled in a timely manner. For abnormalities with low feedback levels, more gentle or regular feedback methods are adopted. This implementation method accurately analyzes the abnormal distribution, sets the abnormal feedback level, and determines the power grid distribution equipment and supply control parameters based on this information. Finally, the distribution is optimized by constructing an optimization model, and the optimization results and feedback levels are used as abnormal feedback information for feedback according to specific requirements, achieving the technical effect of improving the operation efficiency and stability of the power grid and reducing the occurrence and impact of abnormalities.

[0067] In the above, refer to Figure 1 The present invention is described in detail based on the Internet of Things low-voltage distribution fault automatic monitoring method. Figure 2 The invention describes a low-voltage power distribution fault automatic monitoring system based on the Internet of Things according to an embodiment of the present invention.

[0068] The low-voltage power distribution fault automatic monitoring system based on the Internet of Things according to the embodiment of the present invention is used to solve the technical problems of the existing low-voltage power distribution fault monitoring, such as the difficulty in realizing comprehensive real-time monitoring and fault monitoring of the distribution network, and the low efficiency and accuracy of fault handling, so as to achieve the technical effect of realizing comprehensive real-time monitoring and automatic fault monitoring of the low-voltage distribution network, and improving the efficiency and accuracy of fault handling. The low-voltage power distribution fault automatic monitoring system based on the Internet of Things includes: a multi-level power grid user topology network setting module 10, a user power grid abnormality monitoring module 20, an abnormal information clustering module 30, a fusion distribution topology acquisition module 40, and an abnormal feedback module 50.

[0069] The multi-level power grid user topology network setting module 10 is used to collect power consumption information and meter information of low-voltage users based on the Internet of Things, build a power grid user topology structure, set the topology level according to the collection scope, and set the multi-level power grid user topology network;

[0070] The user power grid anomaly monitoring module 20 is used to utilize the multi-level power grid user topology network to perform user power grid anomaly monitoring and positioning, and obtain user power consumption anomaly information;

[0071] The abnormal information clustering module 30 is used to cluster the abnormal power consumption information of the user according to the occurrence time period or the occurrence area range to obtain the abnormal distribution;

[0072] The fused distribution topology structure acquisition module 40 is used to collect the supply relationship of low-voltage distribution, merge the multi-level power grid user topology structure network with the supply relationship, and obtain a fused distribution topology structure;

[0073] The abnormal feedback module 50 is used to perform low-voltage distribution tracing according to the abnormal distribution and through the integrated distribution topology structure, locate the supply control parameters and perform abnormal feedback of the low-voltage distribution network.

[0074] The specific configuration of the multi-level power grid user topology network setting module 10 will be described in detail below. As described above, based on the Internet of Things, the power consumption information and meter information of low-voltage users are collected to construct the power grid user topology structure. The multi-level power grid user topology network setting module 10 may further include: a meter positioning unit for locating the meter based on the Internet of Things and the meter information to determine the meter location information; a user power consumption information collection unit for collecting user power consumption information based on the meter information to obtain user voltage data; a relationship connection establishment unit for constructing the power grid user topology structure based on the meter location information, and establishing a relationship connection between the user voltage data and the power grid user topology structure by using the mapping relationship between the user voltage data and the meter information.

[0075] Among them, the topology level is set according to the collection scope, and the multi-level power grid user topology structure network is set. The multi-level power grid user topology structure network setting module 10 can further include: a multi-level classification quantity threshold preset unit is used to preset the quantity threshold of the multi-level classification; a location clustering unit is used to perform location clustering according to the meter location information to obtain user clustering circles; a user clustering circle reclassification unit is used to reclassify the user clustering circles based on the preset multi-level classification quantity threshold, and successively obtain the base user topology structure, the second-layer user topology structure... until the N-layer user topology structure, N is a positive integer, wherein the quantity threshold of the base user topology structure is greater than the quantity threshold of the second-layer user topology structure, and so on, the quantity threshold of the N-layer user topology structure is the smallest; a hierarchical relationship establishment unit is used to successively establish the base user topology structure, the second-layer user topology structure... until the N-layer user topology structure includes a hierarchical relationship to construct the multi-level power grid user topology structure network.

[0076] The specific configuration of the user power grid anomaly monitoring module 20 will be described in detail below. As described above, the multi-level power grid user topology structure network is used to perform user power grid anomaly monitoring and positioning to obtain user power consumption anomaly information. The user power grid anomaly monitoring module 20 may further include: a hierarchical monitoring period setting unit is used to set hierarchical monitoring periods according to the hierarchical relationship based on the multi-level power grid user topology structure network, wherein the base monitoring period is greater than the second-level monitoring period, and the N-level monitoring period is the smallest; a distributed computing network construction unit is used to construct a distributed computing network, which includes a multi-level analysis operator, and the multi-level analysis operator corresponds to the multi-level power grid user topology structure network, and the multi-level analysis operator has a hierarchical relationship. A calculation cycle, the calculation cycle matches the hierarchical monitoring cycle; the user power consumption analysis unit is used to activate the grassroots analysis operator based on the grassroots monitoring cycle, perform user power consumption analysis in the grassroots user topology structure, perform abnormality comparison or status monitoring according to the historical data characteristics of the user voltage data, and determine the user power consumption abnormality information, the user power consumption abnormality information includes power consumption feature matching abnormality or offline abnormality; the early warning unit is used to issue an early warning reminder when the user power consumption abnormality information meets the early warning requirements; the monitoring and analysis unit is used to continue to execute the hierarchical monitoring cycle when the early warning requirements are not met, and complete the monitoring and analysis of subsequent levels.

[0077] Among them, the abnormal comparison is performed according to the historical data characteristics of the user voltage data, and the user power consumption analysis unit may further include: a voltage curve fitting subunit is used to perform voltage curve fitting on the user voltage data to obtain a user voltage trend curve; a curve segmentation subunit is used to segment the user voltage trend curve according to the curve trend range and the time period; a user power consumption feature determination subunit is used to determine the user power consumption characteristics based on the trend range segmentation result; a mapping relationship establishment subunit is used to establish a mapping relationship between the time period segmentation result and the trend range segmentation result, and determine the user's periodic power consumption characteristics; the abnormal comparison subunit is used to set the characteristic tolerance range, and based on the user power consumption characteristics, the user's periodic power consumption characteristics and the characteristic tolerance range, generate an abnormal comparison module to perform abnormal comparison.

[0078] The specific configuration of the abnormal information clustering module 30 will be described in detail below. As described above, the abnormal power consumption information of the user is clustered according to the occurrence time period or the occurrence area range to obtain the abnormal distribution. The abnormal information clustering module 30 may further include: an all-user power consumption abnormal information acquisition unit for acquiring all user power consumption abnormal information when the user power consumption abnormal information does not meet the warning requirements; a power consumption abnormal information clustering unit for clustering the user power consumption abnormal information according to the occurrence time period and the occurrence area range to obtain the period abnormal distribution and the regional abnormal distribution; an abnormal distribution fusion unit for fusion of the period abnormal distribution and the regional abnormal distribution to obtain the abnormal distribution.

[0079] Next, the specific configuration of the abnormality feedback module 50 will be described in detail. As described above, according to the abnormal distribution, through the integrated distribution topology, low-voltage distribution traceability is performed, and the supply control parameters are located to perform abnormal feedback of the low-voltage distribution network. The abnormal feedback module 50 may further include: an abnormal distribution positioning unit is used to locate the abnormal distribution according to the abnormal distribution, and obtain abnormal distribution level characteristics and abnormal distribution node characteristics. The abnormal distribution level characteristics include same-level and same-partition abnormalities, same-level cross-partition abnormalities, and cross-level abnormalities; an abnormal feedback level setting unit is used to set the abnormal feedback level according to the abnormal distribution level characteristics; an equipment and parameter determination unit is used to determine the power grid distribution equipment and supply control parameters according to the abnormal distribution node characteristics; a distribution optimization parameter acquisition unit is used to obtain an adjustment target value based on the user's power consumption abnormality information and abnormal distribution, and to construct an optimization model based on the influence relationship between the adjustment target value and the supply control parameters of the power grid distribution equipment, perform iterative optimization, and obtain distribution optimization parameters; an abnormal feedback unit is used to convert the abnormal feedback level into an adjustment constraint coefficient, use the distribution optimization parameters and the abnormal feedback level adjustment constraint coefficient as abnormal feedback information, and provide feedback according to the requirements corresponding to the abnormal feedback level.

[0080] The automatic monitoring system for low-voltage power distribution faults based on the Internet of Things provided in the embodiment of the present invention can execute the automatic monitoring method for low-voltage power distribution faults based on the Internet of Things provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0081] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0082] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A low-voltage power distribution fault automatic monitoring method based on the Internet of Things, characterized in that: include: Based on the Internet of Things, the electricity consumption information and meter information of low-voltage users are collected to build the topological structure of power grid users, and the topological structure level is set according to the collection scope, and a multi-level power grid user topological structure network is set; Utilizing the multi-level power grid user topology structure network, abnormal monitoring and positioning of user power grids are performed to obtain abnormal power consumption information of users; Clustering the abnormal power consumption information of the user according to the occurrence time period or the occurrence area range to obtain abnormal distribution; Collecting the supply relationship of low-voltage power distribution, integrating the multi-level power grid user topology network with the supply relationship to obtain a fused distribution topology structure; According to the abnormal distribution, through the integrated distribution topology, low-voltage distribution source tracing is performed, and supply control parameters are located to perform abnormal feedback of the low-voltage distribution network; According to the abnormal distribution, through the integrated distribution topology, low-voltage distribution source tracing is performed, and supply control parameters are located to perform abnormal feedback of the low-voltage distribution network, including: Perform abnormal distribution location according to the abnormal distribution to obtain abnormal distribution level features and abnormal distribution node features, wherein the abnormal distribution level features include same-level and same-partition abnormalities, same-level cross-partition abnormalities, and cross-level abnormalities; Setting an abnormality feedback level according to the abnormality distribution level characteristics; Determining power grid distribution equipment and supply control parameters according to the abnormal distribution node characteristics; Based on the abnormal power consumption information and abnormal distribution of the user, an adjustment target value is obtained, and an optimization model is constructed based on the influence relationship between the adjustment target value and the supply control parameter of the power grid distribution equipment, and an iterative optimization is performed to obtain the power distribution optimization parameter; According to the abnormal feedback level, it is converted into an adjustment constraint coefficient, the distribution optimization parameter and the adjustment constraint coefficient corresponding to the abnormal feedback level are used as abnormal feedback information, and feedback is performed according to the corresponding requirements of the abnormal feedback level.

2. The method for automatic monitoring of low-voltage power distribution faults based on the Internet of Things according to claim 1, characterized in that: The method of collecting electricity consumption information and meter information of low-voltage users based on the Internet of Things and constructing a topological structure of power grid users includes: Based on the Internet of Things, the electric meter is located according to the electric meter information to determine the location information of the electric meter; Collecting user electricity consumption information according to the electric meter information to obtain user voltage data; Based on the electricity meter location information, the power grid user topology structure is constructed, and the mapping relationship between the user voltage data and the electricity meter information is used to establish a relationship connection between the user voltage data and the power grid user topology structure.

3. The method for automatic monitoring of low-voltage power distribution faults based on the Internet of Things as claimed in claim 2, characterized in that: The method of setting the topology level according to the acquisition scope and setting the multi-level power grid user topology network includes: Preset the quantity threshold of multi-level classification; Perform location clustering according to the meter location information to obtain user clustering circles; Reclassify the user clustering circles based on the preset multi-level classification quantity threshold, and sequentially obtain a base user topology structure, a second-layer user topology structure, and so on until an N-layer user topology structure, where N is a positive integer, wherein the quantity threshold of the base user topology structure is greater than the quantity threshold of the second-layer user topology structure, and so on, the quantity threshold of the N-layer user topology structure is the smallest; The base user topology structure, the second-layer user topology structure, ..., and the N-layer user topology structure are sequentially established to construct the multi-level power grid user topology structure network.

4. The method for automatic monitoring of low-voltage power distribution faults based on the Internet of Things as claimed in claim 3, characterized in that: The multi-level power grid user topology structure network is used to monitor and locate user power grid anomalies and obtain user power consumption anomaly information, including: According to the multi-level power grid user topology network, hierarchical monitoring periods are set respectively according to hierarchical relationships, wherein the base monitoring period is greater than the second layer monitoring period, and the N layer monitoring period is the smallest; Building a distributed computing network, including a multi-level analysis operator, the multi-level analysis operator corresponds to a multi-level power grid user topology network, the multi-level analysis operator has a computing cycle according to the hierarchical relationship, and the computing cycle matches the hierarchical monitoring cycle; Based on the grassroots monitoring cycle, the grassroots analysis operator is activated to perform power consumption analysis of users in the grassroots user topology structure, and anomaly comparison or status monitoring is performed according to the historical data characteristics of the user voltage data to determine the abnormal power consumption information of the user, wherein the abnormal power consumption information of the user includes power consumption feature matching abnormality or offline abnormality; When the abnormal power consumption information of the user reaches the warning requirement, a warning reminder is issued; When the warning requirement is not met, the level monitoring cycle continues to be executed to complete the monitoring and analysis of the subsequent levels.

5. The method for automatic monitoring of low-voltage power distribution faults based on the Internet of Things according to claim 4, characterized in that: The abnormality comparison based on the historical data characteristics of the user voltage data includes: Performing voltage curve fitting on the user voltage data to obtain a user voltage trend curve; The user voltage trend curve is divided according to the curve trend range and the time period; Based on the trend range segmentation results, determine the user's electricity consumption characteristics; Establish a mapping relationship between the time period segmentation results and the trend range segmentation results to determine the user's periodic electricity consumption characteristics; A feature tolerance range is set, and based on the user's power usage features, the user's periodic power usage features and the feature tolerance range, an abnormality comparison module is generated to perform abnormality comparison.

6. The method for automatic monitoring of low-voltage power distribution faults based on the Internet of Things according to claim 1, characterized in that: The clustering of the abnormal power consumption information of the users according to the occurrence time period or the occurrence area range to obtain abnormal distribution includes: When the abnormal power consumption information of the user does not meet the warning requirement, obtaining abnormal power consumption information of all users; Clustering the user's power consumption anomaly information according to the occurrence time period and the occurrence area range to obtain period anomaly distribution and regional anomaly distribution; The periodic anomaly distribution and the regional anomaly distribution are merged to obtain the anomaly distribution.

7. The low-voltage power distribution fault automatic monitoring system based on the Internet of Things is characterized by: The system is used to implement the method for automatic monitoring of low-voltage power distribution faults based on the Internet of Things according to any one of claims 1 to 6, and the system comprises: A multi-level power grid user topology network setting module, which is used to collect power consumption information and meter information of low-voltage users based on the Internet of Things, build a power grid user topology structure, set the topology level according to the collection scope, and set the multi-level power grid user topology network; A user power grid anomaly monitoring module, the user power grid anomaly monitoring module is used to use the multi-level power grid user topology network to perform user power grid anomaly monitoring and positioning, and obtain user power consumption anomaly information; An abnormal information clustering module, the abnormal information clustering module is used to cluster the abnormal power consumption information of the user according to the occurrence time period or the occurrence area range to obtain abnormal distribution; A fused distribution topology acquisition module, which is used to collect the supply relationship of low-voltage distribution, merge the multi-level power grid user topology network with the supply relationship, and obtain a fused distribution topology structure; The abnormal feedback module is used to perform low-voltage distribution tracing based on the abnormal distribution and locate supply control parameters to perform abnormal feedback on the low-voltage distribution network through the integrated distribution topology.

Images