Monitoring and warning method and device for power distribution network, storage medium and product

Abstract

The invention discloses a power distribution network monitoring alarm method and device, a storage medium and a product, and the method comprises the steps: constructing a line topological graph according to power equipment of a power distribution network, dividing the line topological graph into a plurality of region blocks, and receiving first operation data uploaded by the intelligent terminal in each region block, collecting second operation data of a non-intelligent terminal in each region block, identifying abnormal data from the first operation data and the second operation data according to the region block, and performing alarm operation on the power distribution network according to the abnormal data. By constructing the line topological graph of the power distribution network and dividing the line topological graph into a plurality of area blocks, data of the intelligent terminal and data of the non-intelligent terminal are processed separately, and the operation condition of power equipment of each area block can be comprehensively known. The operation data uploaded by the intelligent terminal and the non-intelligent terminal are analyzed, abnormal data are recognized, and the accuracy and efficiency of analysis of the operation state of the power distribution network are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of distribution network monitoring, and in particular to a distribution network monitoring and alarming method, device, storage medium and product. Background Art

[0002] With the continuous development of smart grid and Internet of Things technologies, the automation and intelligence level of distribution networks are constantly improving. There are a large number of power equipment in the distribution network, and the types of equipment are various, and the types of monitoring data and collection methods are also different. In such a complex distribution network environment, comprehensive collection of power equipment operation data and effective analysis have become one of the factors for monitoring the operation status of the distribution network. A good distribution network operation status can reduce power loss, improve energy efficiency, and reduce the risk of power equipment failure.

[0003] Traditional distribution network monitoring and management mainly rely on centralized data collection and analysis methods, usually with the entire distribution network as the monitoring object. Various types of power equipment in the distribution network, including intelligent terminals and non-intelligent terminals, will generate a large amount of real-time operation data. However, traditional methods often ignore the structural complexity of the distribution network and the diversity of the distribution of power equipment. In the process of data collection and processing, the regional division of the distribution network and the analysis of local data are less involved, resulting in low accuracy and efficiency in the analysis of the distribution network operation status. Summary of the invention

[0004] The present invention provides a distribution network monitoring and alarm method, equipment, storage medium and product, which are used to improve the accuracy and efficiency of the distribution network operation status analysis.

[0005] In a first aspect, an embodiment of the present invention provides a monitoring and alarm method for a distribution network, comprising:

[0006] Constructing a line topology diagram based on power equipment of the distribution network; the types of power equipment include intelligent terminals and non-intelligent terminals;

[0007] Dividing the line topology map into a plurality of area blocks;

[0008] receiving, in each of the area blocks, first operation data uploaded by the smart terminal;

[0009] Collecting the second operation data of the non-intelligent terminal in each of the area blocks;

[0010] identifying abnormal data from the first operation data and the second operation data according to the region block;

[0011] An alarm operation is performed on the distribution network according to the abnormal data.

[0012] In a second aspect, an embodiment of the present invention further provides a monitoring and alarm device for a distribution network, comprising:

[0013] A line topology map construction module is used to construct a line topology map based on the power equipment of the distribution network; the types of the power equipment include intelligent terminals and non-intelligent terminals;

[0014] A region block division module, used for dividing the line topology map into a plurality of region blocks;

[0015] A first operation data receiving module, configured to receive, in each of the area blocks, first operation data uploaded by the smart terminal;

[0016] A second operation data collection module, used for collecting the second operation data of the non-intelligent terminal in each of the area blocks;

[0017] an abnormal data identification module, configured to identify abnormal data from the first operation data and the second operation data according to the region block;

[0018] The distribution network alarm module is used to perform an alarm operation on the distribution network according to the abnormal data.

[0019] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0020] one or more processors;

[0021] A storage device for storing one or more programs;

[0022] When the one or more programs are executed by the one or more processors, the one or more processors implement the monitoring and alarm method for the distribution network provided in the first aspect of the present invention.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the monitoring and alarm method for a distribution network as provided in the first aspect of the present invention.

[0024] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the monitoring and alarm method for the distribution network provided in the first aspect of the present invention.

[0025] In an embodiment of the present invention, a line topology map is constructed based on the power equipment of the distribution network, and the types of power equipment include intelligent terminals and non-intelligent terminals. The line topology map is divided into multiple regional blocks, and the first operating data uploaded by the intelligent terminal is received in each regional block. The second operating data of the non-intelligent terminal is collected in each regional block. Abnormal data is identified from the first operating data and the second operating data according to the regional block, and an alarm operation is performed on the distribution network according to the abnormal data. By constructing a line topology map of the distribution network and dividing it into multiple regional blocks, the operating status of the distribution network can be effectively monitored and managed. The data of the intelligent terminal and the non-intelligent terminal are processed separately, and through the combination of these two types of operating data, the operating conditions of the power equipment in each regional block can be fully understood. In each regional block, the operating data uploaded by smart terminals and non-intelligent terminals are intelligently analyzed to identify possible abnormal data. Through regional management, the equipment and data in each regional block in the distribution network are relatively concentrated, so that the source of abnormal data can be more accurately located in the specific area, and potential distribution network fault points can be quickly located, thereby providing timely warnings and alarm information to operation and maintenance personnel, helping them to take quick measures to handle or maintain the fault, avoiding larger-scale power outages caused by the spread of faults, and improving the accuracy and efficiency of distribution network operation status analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A flow chart of a distribution network monitoring and alarming method provided in Embodiment 1 of the present invention;

[0027] Figure 2 A structural block diagram of a monitoring and alarm device for a distribution network provided in Embodiment 2 of the present invention;

[0028] Figure 3 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device 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 units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] See also Figure 1 , shows a flow chart of a distribution network monitoring and alarming method provided by the first embodiment of the present invention, the method can be executed by a distribution network monitoring and alarming device, the distribution network monitoring and alarming device can be implemented in the form of hardware and / or software, and the distribution network monitoring and alarming device can be configured in a computer device. Figure 1 As shown, the method includes:

[0033] Step 101: construct a line topology diagram based on the power equipment of the distribution network.

[0034] In this embodiment, the distribution network is composed of multiple power equipment, and the types of these power equipment can be divided into intelligent terminals and non-intelligent terminals. In the distribution network, intelligent terminals have the capabilities of automatic control, data acquisition and processing, communication functions and fault self-diagnosis, and realize remote monitoring and optimization; while non-intelligent terminals lack these functions and rely on manual operation and inspection. When constructing the line topology diagram, these power equipment are reasonably arranged according to their actual connection relationships to form a structured line topology diagram, which provides effective space division and data sources for subsequent monitoring, data analysis and anomaly detection, thereby realizing accurate alarm operations and improving the operation safety and management efficiency of the distribution network.

[0035] Step 102: Divide the line topology map into multiple area blocks.

[0036] In this embodiment, the line topology diagram is divided into multiple area blocks according to the effective communication distance of each power device in the line. In order to ensure that the power devices in each area block can exchange and monitor data within the effective communication range. By dividing the area blocks, the reliability and efficiency of data transmission can be improved, and data delay or loss caused by the long communication distance can be avoided. At the same time, after dividing the area blocks, more accurate status monitoring and abnormality detection can be performed for the power devices in each area block, achieving more fine-grained management and maintenance, optimizing the real-time monitoring and fault diagnosis of the distribution network, and improving the response speed and accuracy of the alarm.

[0037] In one embodiment of the present invention, step 102 may include the following steps:

[0038] Step 1021: Set multiple groups of equipment parameters for the power equipment.

[0039] In this embodiment, multiple sets of device parameters are set for each power device in the distribution network. These device parameters include at least the type of power device, which is the basis for classifying and analyzing the power device. The definition of the device type can cover aspects such as the working characteristics, performance indicators, and communication capabilities of the device. By setting these device parameters, the power devices can be preliminarily distinguished to ensure that all power devices can be reasonably classified according to their characteristics, so as to better manage and monitor the entire distribution network.

[0040] Step 1022: Convert the line topology graph into a graph neural network.

[0041] In this embodiment, the line topology of the distribution network is converted into a graph neural network (GNN), the power equipment and their connection relationships in the line topology are converted into a graph structure, and the GNN can be used to extract features in the line topology. The graph structure learning ability of the GNN is used to capture the interactions and interdependencies between power equipment in the distribution network, thereby providing support for subsequent steps such as power equipment classification and anomaly detection.

[0042] Graph Neural Network (GNN) is a type of deep learning model for graph structured data. Graph Neural Network can process the relationship information of nodes, edges and graphs. GNN learns the representation of nodes in the graph by transferring information between the nodes in the graph, and uses the topological structure and adjacency relationship of the graph for effective feature learning. The representation of each node depends not only on its own features, but also on the information of its neighboring nodes.

[0043] Step 1023: For each group of equipment parameters, the power equipment is classified according to the equipment parameters based on the graph neural network to obtain multiple categories.

[0044] In this embodiment, the graph neural network uses the set device parameters to classify the power equipment. Based on the classification ability of the graph neural network, the graph neural network can group the power equipment according to the equipment parameters (such as equipment type, performance indicators, etc.) to form multiple categories. Each category represents a group of power equipment with similar characteristics. The purpose of classifying power equipment is to better understand the operating characteristics and behavior patterns of different categories of equipment, so as to facilitate subsequent fault diagnosis and alarm management.

[0045] The training process of graph neural network includes three main steps: data preparation, model construction and parameter optimization. Specifically, the equipment parameters of power equipment, such as equipment type, performance indicators, etc., are collected and organized, and represented as a graph structure, where nodes represent power equipment and edges represent the relationship between equipment. A graph neural network model is constructed, node features and graph convolution layers are defined, and the correlation between devices is captured through multi-layer information propagation and node representation updates. Supervised learning is performed using labeled equipment category data, and network parameters are optimized through the back propagation algorithm, so that the graph neural network model can effectively classify power equipment. During the training process, the graph neural network model continuously adjusts the weights and optimizes the classification accuracy, thereby achieving accurate identification of different groups of power equipment in fault diagnosis and alarm management.

[0046] Step 1024: for each group of equipment parameters, perform unsupervised clustering on the power equipment according to the equipment parameters to obtain multiple clusters.

[0047] In this embodiment, unsupervised clustering is a process of automatically grouping according to device parameters, without relying on predefined category labels. Clustering is performed according to the device parameters of the power equipment to generate multiple clusters. Each cluster represents a class of similar power equipment. Unsupervised clustering algorithms (such as K-means clustering (K-means) or density clustering algorithm (DBSCAN)) group the power equipment together based on their similarities without explicit labels, further refining the management structure of the power equipment.

[0048] The K-means algorithm is a partition-based clustering algorithm that aims to divide a data set into K pre-specified clusters. The basic idea is to randomly select K initial center points in an iterative manner, and assign each data point to the closest cluster based on its distance from the center point. The center point of each cluster is recalculated until the cluster division no longer changes.

[0049] The DBSCAN algorithm is a density-based clustering algorithm that clusters data points by finding data points with similar density. The basic idea is that for a data point, if there are enough other points in its neighborhood (with high enough density), these points belong to the same cluster; otherwise, the data point is marked as noise. DBSCAN does not require a preset number of clusters and can effectively identify clusters of different shapes, making it particularly suitable for processing noisy data sets.

[0050] Step 1025: For each set of device parameters, calculate the degree of overlap between multiple categories and multiple clusters.

[0051] In this embodiment, the power equipment in the distribution network is divided into different categories and clusters through unsupervised clustering and equipment classification. These categories and clusters represent different types and operating states of power equipment. A single power equipment classification or clustering method may not accurately reflect the correlation or spatial distribution between power equipment. By calculating the degree of overlap between categories and clusters, it is determined which categories have a higher degree of overlap with which clusters, so that the power equipment can be reasonably divided into different area blocks. By maximizing the overlap between categories and clusters, it can be ensured that the power equipment in each area block is relatively consistent in nature and function, making subsequent abnormal data detection more efficient and accurate.

[0052] In one embodiment of the present invention, step 1025 may include the following steps:

[0053] Step 10251: For each group of device parameters, count the first number of identical power devices between each category and each cluster.

[0054] In this embodiment, the number of overlapping power devices (i.e., the first number) between each category obtained by graph neural network classification and each cluster obtained by unsupervised clustering is counted by the device parameters of the power devices. Each power device may belong to a category and a cluster at the same time, and the number of these intersection power devices is counted as the first number. The similarity between categories and clusters is clarified, and the belonging of each power device under different division methods is evaluated.

[0055] Step 10252: align each category with each cluster with the goal of maximizing the sum of the first quantities.

[0056] In this embodiment, by counting the number of identical power devices between each category and cluster (i.e., the first number), the goal is to maximize the sum of these first numbers. The division of categories and clusters is adjusted so that the power devices can overlap as much as possible between categories and clusters. This alignment process helps optimize the partitioning of power devices in the distribution network so that the classification and clustering of power devices are more consistent. An optimization algorithm such as a greedy algorithm or dynamic programming can be used to adjust the allocation of categories and clusters so that the sum of the first number is maximized.

[0057] Step 10253: If the alignment is completed, a union of the power equipment of the category and the power equipment of the cluster is obtained, and a second number of intersections is counted.

[0058] In this example, if the alignment of the categories and clusters is completed, a union operation can be performed on the power devices in each category and cluster, that is, all the power devices in the category and cluster are integrated into a new set. The number of intersections in the union (i.e., the second number) is calculated, that is, the overlapping part of the category and cluster. The second number represents the number of power devices shared between the category and the cluster, reflecting the consistency of these power devices in device allocation.

[0059] Step 10254: Calculate the ratio between the first quantity and the second quantity to obtain the overlap ratio.

[0060] In this embodiment, the ratio between the first number (the number of identical power devices between the categories and clusters) and the second number (the number of intersections in the union of the categories and clusters) is calculated. The overlap ratio reflects the degree of matching between the categories and clusters. The higher the overlap ratio, the more consistent the categories and clusters are, and the more reasonable the divided areas are.

[0061] Step 10255: Calculate the average value of the overlapping ratios to obtain the degree of overlap.

[0062] In this embodiment, the average value of the overlap ratios between all categories and clusters is calculated to obtain the overall overlap degree. The overlap degree is an indicator for evaluating the quality of the regional block division of the entire distribution network. The higher the average overlap ratio, the more consistent the classification and cluster division of the distribution network equipment, and the better the regional block division effect. The calculation of the overlap degree helps to further optimize the structure of the distribution network management and monitoring system.

[0063] Step 1026: Divide the line topology map into multiple area blocks according to the multiple categories with the highest degree of overlap.

[0064] In this embodiment, according to the calculated overlap between categories and clusters, the category with the highest overlap is selected for regional block division. Categories and clusters with high overlap can be considered to be functionally close, and the power equipment is within a reasonable communication range, so division into the same regional block helps improve the efficiency of monitoring and management. The regional blocks in the distribution network will more reasonably reflect the similarity and connectivity of power equipment, optimize the regional division of the distribution network, ensure that the monitoring and alarm system can respond to abnormal events more effectively, and reduce interference between regions.

[0065] Step 103: Receive the first operation data uploaded by the smart terminal in each area block.

[0066] In this embodiment, the first operation data uploaded by the smart terminal is received in order to monitor and obtain the operation status of the smart terminal in the distribution network in real time. The smart terminal can generally collect the status data of the power equipment in real time, such as current, voltage, power factor, frequency, temperature, etc., through embedded sensors, data acquisition modules, etc., to ensure that potential faults or abnormalities can be found at any time during the operation of the equipment. The smart terminal uploading the first operation data usually relies on wireless communication technology, such as Zigbee protocol, long-distance wireless technology (LoRa), narrowband Internet of Things (NB-IoT) or fifth-generation mobile communication technology (5G) and other wireless communication technologies to realize the remote transmission of the first operation data.

[0067] Step 104: Collect the second operation data of the non-intelligent terminal in each area block.

[0068] In this embodiment, non-intelligent terminals generally refer to traditional devices without built-in intelligent sensors or computing modules. These non-intelligent terminals themselves cannot actively generate digital operation data and usually rely on external means to collect data. Therefore, collecting the second operation data of these non-intelligent terminals helps to supplement the device information that cannot be covered by the intelligent terminals and fully understand the operation status of all power equipment in the distribution network.

[0069] In one embodiment of the present invention, step 104 may include the following steps:

[0070] Step 1041: When the non-intelligent terminals in each area block are running, video data is collected from the non-intelligent terminals.

[0071] In this embodiment, since non-intelligent terminals usually do not have the ability to output digital data, video data is collected from non-intelligent terminals. The video data provides an effective means to monitor the status of these non-intelligent terminals, and the video data includes multiple frames of original image data. By collecting multiple frames of original image data at the scene of the non-intelligent terminal, the specific operation of the non-intelligent terminal can be captured; the process of collecting video data from non-intelligent terminals relies on video monitoring technology, usually using high-definition cameras and real-time video streaming technology, generating video data through image acquisition hardware (such as high-definition cameras or surveillance cameras), and ensuring that these video data can accurately reflect the operating status of the non-intelligent terminal in each area block.

[0072] Step 1042: construct a blank image screening layer for non-intelligent devices.

[0073] In this embodiment, the video data usually contains a large amount of irrelevant background or irrelevant areas. In order to improve the processing efficiency of the video data, a blank image screening layer (mask layer) is constructed. The areas in the blank image screening layer that overlap with multiple interest areas in the original image data are transparent, and the areas that overlap with multiple non-interest areas in the original image data are of a specified color. The blank image screening layer is consistent in size with the original image data. The interest area represents the area of ​​the original image data where the second operating data of the non-intelligent terminal exists, thereby focusing on the operating status of the non-intelligent terminal.

[0074] Step 1043: Overlay the blank image screening layer on the original image data to obtain the target image data.

[0075] In this embodiment, a blank image screening layer is overlaid on the original image data, and the non-interest area of ​​the original image data is covered by the color specified by the blank image screening layer, and the original image data only has the area of ​​interest left to obtain the target image data; this overlay process enhances the visibility of the area of ​​interest in the original image data and removes irrelevant parts for subsequent analysis. This overlay process usually involves image overlay and image enhancement technology, and the blank image screening layer can be synthesized with the original image through matrix operations in computer vision.

[0076] Step 1044: perform optical character recognition on the target image data to obtain second operation data of the non-intelligent terminal.

[0077] In this embodiment, the target image data after blank image screening and enhancement is input into an optical character recognition (OCR) system for optical character recognition, and is used to extract the digital or text information contained therein to obtain the second operation data of the non-intelligent terminal. For the non-intelligent terminal in the distribution network, its second operation data may be presented on the display screen in the form of numbers or letters (such as the temperature, pressure, working status indication, etc. of the non-intelligent terminal), and the OCR technology can efficiently extract this information from the target image data.

[0078] In one embodiment of the present invention, step 1044 may include the following steps:

[0079] Step 10441: pre-process the target image data.

[0080] In this embodiment, the target image data acquisition process is usually affected by noise, light changes, image blur and other issues, which will affect the accuracy of subsequent processing. Therefore, the target image data is preprocessed to enhance the quality of the target image data, eliminate unnecessary interference, and ensure that the subsequent processing steps can better identify useful information in the image.

[0081] The preprocessing of target image data usually includes image denoising, image enhancement and binarization.

[0082] Image denoising: Use filters (such as Gaussian filtering, mean filtering, median filtering, etc.) to remove noise from the target image data.

[0083] Image enhancement: Enhance the contrast of the target image data through histogram equalization, making the details in the target image data more prominent.

[0084] Binarization: Convert the target image data into black and white, so that the characters or specific areas in the target image data can be more clearly identified.

[0085] Step 10442: If preprocessing is completed, detect edge image data for the target image data.

[0086] In this embodiment, by identifying the area with significant grayscale or color changes in the target image data, the outline or structure of the text in the target image data is highlighted. The target image data is subjected to edge detection (such as Canny edge detection, Sobel operator, Laplace operator and other edge detection algorithms). Through these edge detection algorithms, the outline in the image can be highlighted and the interference of background information can be reduced, which is helpful to extract the operation information of the non-intelligent terminal.

[0087] Canny edge detection: It can effectively detect the edges in the target image data by finding the area with the most dramatic change in grayscale value in the target image data through gradient operation.

[0088] Sobel operator: It identifies edges by calculating the change in pixel grayscale in the target image data. It is suitable for detecting horizontal and vertical edges of the target image data.

[0089] Laplace operator: uses second-order derivatives to detect fast-changing edges in target image data.

[0090] Step 10443: extract multiple contour data from the edge image data.

[0091] In this embodiment, the purpose of extracting contour data is to further extract more important information from the edge image data, especially specific areas related to non-intelligent terminals (such as numbers and control buttons in the display screen). Through contour extraction, different objects in the edge image data can be separated, and the shape, size and other features of each object can be identified, which is convenient for further identification and analysis.

[0092] Step 10444: perform optical character recognition on each contour data to extract the second operation data of the non-intelligent terminal.

[0093] In this embodiment, for non-intelligent terminal devices, many operating data (such as voltage, temperature, operating status, etc.) may be displayed on the screen of the non-intelligent terminal in the form of numbers or characters. By performing optical character recognition on the extracted contour area, the text information in the contour data can be converted into digital data, thereby providing data support for subsequent monitoring and alarm.

[0094] Step 105 : Identify abnormal data from the first operation data and the second operation data according to the region block.

[0095] In this embodiment, the first operating data and the second operating data collected by each regional block are identified and analyzed to identify abnormal data, and the regional blocks are divided to monitor the distribution network, thereby improving the efficiency of abnormal identification and ensuring the stable operation of the distribution network.

[0096] Exemplarily, the first operation data is stored in a preset report framework according to the type of the first operation data, and the second operation data is stored in a preset report framework according to the position of the second operation data in the original image data to obtain report data, and the data from different sources (intelligent terminals and non-intelligent terminals) are systematically integrated into a unified report to facilitate subsequent analysis and anomaly detection; in the report data, the query sets a data security threshold for each data information in the regional block; the data information is the first operation data and / or the second operation data; if the data information is greater than the data security threshold, the data information is marked as abnormal data. The marking process helps to quickly identify potential problems in the distribution network and ensure timely alarm response and maintenance. This process can automatically detect possible faults, overloads or other abnormal conditions, thereby improving the reliability and safety of the distribution network operation, reducing the need for human intervention, and improving the overall operation and maintenance efficiency and emergency response capabilities.

[0097] Step 106: Perform an alarm operation on the distribution network based on the abnormal data.

[0098] In this embodiment, when abnormal data appears during the operation of the distribution network, an alarm operation is performed in a timely manner, and information of the abnormal data is provided to the operation and maintenance personnel so that repair measures can be taken quickly to prevent the fault from spreading or causing more serious losses.

[0099] Exemplarily, the traceability information of abnormal data is extracted, and the traceability information includes the power equipment identification, data collection time identification and area block identification. These traceability information can help operation and maintenance personnel accurately locate the source of the abnormality, quickly determine the problem equipment and the specific location of the failure, so as to carry out targeted inspection, repair or replacement; based on the traceability information, an alarm task is generated to prompt the maintenance of the power equipment corresponding to the abnormal data, thereby improving the safety and stability of the distribution network, reducing the need for human intervention, and improving the speed and accuracy of emergency response.

[0100] In an embodiment of the present invention, a line topology map is constructed based on the power equipment of the distribution network, the power equipment includes intelligent terminals and non-intelligent terminals, the line topology map is divided into multiple regional blocks, the first operating data uploaded by the intelligent terminal is received in each regional block, the second operating data of the non-intelligent terminal is collected in each regional block, abnormal data is identified from the first operating data and the second operating data according to the regional block, and an alarm operation is performed on the distribution network according to the abnormal data. By constructing a line topology map of the distribution network and dividing it into multiple regional blocks, the operating status of the distribution network can be effectively monitored and managed. The data of the intelligent terminal and the non-intelligent terminal are processed separately, and through the combination of these two types of operating data, the operating conditions of the power equipment in each regional block can be fully understood. In each regional block, the operating data uploaded by smart terminals and non-intelligent terminals are intelligently analyzed to identify possible abnormal data. Through regional management, the equipment and data in each regional block in the distribution network are relatively concentrated, so that the source of abnormal data can be more accurately located in the specific area, and potential distribution network fault points can be quickly located, thereby providing timely warnings and alarm information to operation and maintenance personnel, helping them to take quick measures to handle or maintain the fault, avoiding larger-scale power outages caused by the spread of faults, and improving the accuracy and efficiency of distribution network operation status analysis.

[0101] Embodiment 2

[0102] Figure 2 A schematic diagram of the structure of a monitoring and alarm device for a distribution network provided in Embodiment 2 of the present invention is shown in FIG. Figure 2 As shown, the device comprises:

[0103] A line topology diagram construction module 201 is used to construct a line topology diagram based on power equipment in the distribution network; the types of power equipment include intelligent terminals and non-intelligent terminals;

[0104] A region block division module 202, used to divide the line topology map into a plurality of region blocks;

[0105] A first operation data receiving module 203, configured to receive, in each of the area blocks, first operation data uploaded by the smart terminal;

[0106] A second operation data collection module 204, used for collecting the second operation data of the non-intelligent terminal in each of the area blocks;

[0107] an abnormal data identification module 205, configured to identify abnormal data from the first operation data and the second operation data according to the region block;

[0108] The distribution network alarm module 206 is used to perform an alarm operation on the distribution network according to the abnormal data.

[0109] In one embodiment of the present invention, the region block division module 202 includes:

[0110] A device parameter setting module, used to set multiple groups of device parameters for the power device; each group of the device parameters at least includes the type;

[0111] A graph neural network conversion module, used to convert the line topology graph into a graph neural network;

[0112] An electric equipment classification module, for classifying the electric equipment according to the equipment parameters of each group according to the graph neural network to obtain multiple categories;

[0113] An electric equipment clustering module, for performing unsupervised clustering of the electric equipment according to the equipment parameters for each group of equipment parameters to obtain a plurality of clusters;

[0114] An overlap degree calculation module, used for calculating the overlap degree between the plurality of the categories and the plurality of the clusters for each group of the device parameters;

[0115] The line topology diagram division module is used to divide the line topology diagram into multiple area blocks according to the multiple categories with the highest degree of overlap.

[0116] In one embodiment of the present invention, the overlap degree calculation module includes:

[0117] A first quantity statistics module, configured to count, for each group of the device parameters, a first quantity of the same power devices between each of the categories and each of the clusters;

[0118] an alignment operation module, configured to align each of the categories with each of the clusters with the goal of maximizing the sum of the first quantities;

[0119] A second quantity counting module, configured to take a union of the power devices of the category and the power devices of the cluster, and count a second quantity of the intersections if the alignment is completed;

[0120] An overlap ratio calculation module, used to calculate the ratio between the first number and the second number to obtain an overlap ratio;

[0121] The overlap degree acquisition module is used to calculate the average value between the overlap ratios to obtain the overlap degree.

[0122] In one embodiment of the present invention, the second operation data acquisition module 204 includes:

[0123] A video data acquisition module, used for collecting video data from the non-intelligent terminal when the non-intelligent terminal in each of the area blocks is running; the video data includes multiple frames of original image data;

[0124] A blank image screening layer construction module is used to construct a blank image screening layer for the non-intelligent device; the area in the blank image screening layer that overlaps with the multiple regions of interest in the original image data is transparent, and the area that overlaps with the multiple regions of non-interest in the original image data is a specified color;

[0125] A target image data acquisition module, used for overlaying the blank image screening layer on the original image data to obtain target image data;

[0126] The second operation data recognition module is used to perform optical character recognition on the target image data to obtain the second operation data of the non-intelligent terminal.

[0127] In one embodiment of the present invention, the second operation data identification module includes:

[0128] A preprocessing module, used for preprocessing the target image data;

[0129] An edge image data detection module, used for detecting edge image data of the target image data after the preprocessing is completed;

[0130] A contour data extraction module, used for extracting a plurality of contour data from the edge image data;

[0131] The outline data recognition module is used to perform optical character recognition on each of the outline data to extract the second operation data of the non-intelligent terminal.

[0132] In one embodiment of the present invention, the abnormal data identification module 205 includes:

[0133] a report data acquisition module, configured to store the first operation data into a preset report frame according to the type of the first operation data, and store the second operation data into a preset report frame according to the position of the second operation data in the original image data, so as to obtain report data;

[0134] A data security threshold query module, used for querying, in the report data, setting a data security threshold for each piece of data information in the area block; the data information is the first operating data and / or the second operating data;

[0135] The data information comparison module is used to mark the data information as abnormal data if the data information is greater than the data safety threshold.

[0136] In one embodiment of the present invention, the distribution network alarm module 206 includes:

[0137] A traceability information extraction module, used to extract the traceability information of the abnormal data; the traceability information includes the power equipment identification, data collection time identification and area block identification;

[0138] The alarm task generation module is used to generate an alarm task based on the traceability information to prompt maintenance of the power equipment corresponding to the abnormal data.

[0139] The distribution network monitoring and alarm device provided in the embodiment of the present invention can execute the distribution network monitoring and alarm method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the distribution network monitoring and alarm method.

[0140] Embodiment 3

[0141] See also Figure 3 , showing a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. The computer device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The computer device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0142] like Figure 3 As shown, the computer device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the computer device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0143] A number of components in the computer device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the computer device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0144] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the monitoring and alarm method of the distribution network.

[0145] In some embodiments, the monitoring and alarm method of the distribution network may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the computer device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the monitoring and alarm method of the distribution network described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the monitoring and alarm method of the distribution network by any other appropriate means (e.g., by means of firmware).

[0146] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0148] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0149] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0150] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0151] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0152] Embodiment 4

[0153] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the monitoring and alarm method for the distribution network provided in any embodiment of the present invention is implemented.

[0154] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0155] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0156] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A distribution network monitoring and alarm method, characterized in that: include: Construct line topology diagram based on power equipment of distribution network; The types of power equipment include intelligent terminals and non-intelligent terminals; Dividing the line topology map into a plurality of area blocks; receiving, in each of the area blocks, first operation data uploaded by the smart terminal; Collecting the second operation data of the non-intelligent terminal in each of the area blocks; identifying abnormal data from the first operation data and the second operation data according to the region block; An alarm operation is performed on the distribution network according to the abnormal data.

2. The method according to claim 1, characterized in that The dividing the line topology map into a plurality of area blocks comprises: Setting a plurality of groups of equipment parameters for the power equipment; each group of the equipment parameters at least includes the type; Converting the line topology graph into a graph neural network; For each group of the equipment parameters, classify the power equipment according to the equipment parameters based on the graph neural network to obtain multiple categories; For each group of the device parameters, performing unsupervised clustering on the power devices according to the device parameters to obtain a plurality of clusters; For each group of the device parameters, calculating the degree of overlap between the multiple categories and the multiple clusters; The line topology map is divided into a plurality of area blocks according to the plurality of categories with the highest degree of overlap.

3. The method according to claim 2, characterized in that The calculating, for each group of the device parameters, the degree of overlap between the multiple categories and the multiple clusters comprises: For each group of the device parameters, counting a first number of the same electrical devices between each of the categories and each of the clusters; With the goal of maximizing the sum of the first quantities, aligning each of the categories with each of the clusters; If the alignment is completed, taking a union of the power devices of the category and the power devices of the cluster, and counting a second number of intersections; calculating a ratio between the first number and the second number to obtain an overlap ratio; The average value of the overlap ratios is calculated to obtain the overlap degree.

4. The method according to claim 1, characterized in that: The collecting the second operation data of the non-intelligent terminal in each of the area blocks includes: When the non-intelligent terminal in each of the area blocks is running, video data is collected from the non-intelligent terminal; the video data includes multiple frames of original image data; Constructing a blank image screening layer for the non-intelligent device; in the blank image screening layer, the area overlapping with the multiple regions of interest in the original image data is transparent, and the area overlapping with the multiple regions of non-interest in the original image data is a specified color; Overlaying the blank image screening layer on the original image data to obtain target image data; Optical character recognition is performed on the target image data to obtain second operation data of the non-intelligent terminal.

5. The method according to claim 4, characterized in that The performing optical character recognition on the target image data to obtain the second operation data of the non-intelligent terminal includes: Preprocessing the target image data; If the preprocessing is completed, detecting edge image data of the target image data; extracting a plurality of contour data from the edge image data; Optical character recognition is performed on each of the outline data to extract the second operation data of the non-intelligent terminal.

6. The method according to claim 4, characterized in that The identifying abnormal data from the first operation data and the second operation data according to the region block includes: storing the first operating data into a preset report frame according to the type of the first operating data, and storing the second operating data into a preset report frame according to the position of the second operating data in the original image data, to obtain report data; In the report data, querying to set a data security threshold for each data information in the area block; the data information is the first operation data and / or the second operation data; If the data information is greater than the data safety threshold, the data information is marked as abnormal data.

7. The method according to any one of claims 1 to 6, characterized in that: The performing an alarm operation on the distribution network according to the abnormal data includes: Extracting the traceability information of the abnormal data; the traceability information includes the power equipment identification, data collection time identification and area block identification; An alarm task is generated based on the traceability information to prompt maintenance of the power equipment corresponding to the abnormal data.

8. A computer device, characterized in that: The computer device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the distribution network monitoring and alarm method as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the monitoring and alarm method for the distribution network as described in any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the monitoring and alarm method for a distribution network as described in any one of claims 1 to 7 is implemented.

Images