CN119652934B - Smart grid data communication optimization method based on edge calculation - Google Patents
Smart grid data communication optimization method based on edge calculation Download PDFInfo
- Publication number
- CN119652934B CN119652934B CN202510150729.5A CN202510150729A CN119652934B CN 119652934 B CN119652934 B CN 119652934B CN 202510150729 A CN202510150729 A CN 202510150729A CN 119652934 B CN119652934 B CN 119652934B
- Authority
- CN
- China
- Prior art keywords
- inspection
- communication
- edge
- power transmission
- sets
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
本发明提供了一种基于边缘计算的智能电网数据通信优化方法，涉及智能电网技术领域，包括：获取目标电网的巡检拓扑网络；进行多角度通信分析，获得K个输电设备通信特征元组集合和L个巡检站点通信特征元组；进行边缘跃阶识别，获得M个边缘拓扑子网络；进行子网络服务资源均衡配置，获得M个边缘计算服务器；利用巡检无人机和巡检机器人进行巡检，获得L个站点巡检视频数据；分发至M个边缘计算服务器进行数据预处理，上传至云计算中心进行巡检数据分析，获得巡检分析结果。本发明解决了现有技术的电网监控通常依赖于集中式数据处理，导致数据传输延迟和网络负载过重，进而导致数据处理效率较低的技术问题。
The present invention provides a smart grid data communication optimization method based on edge computing, which relates to the field of smart grid technology, including: obtaining the inspection topology network of the target power grid; performing multi-angle communication analysis to obtain K sets of transmission equipment communication feature tuples and L inspection site communication feature tuples; performing edge jump identification to obtain M edge topology sub-networks; performing sub-network service resource balancing configuration to obtain M edge computing servers; using inspection drones and inspection robots to perform inspections to obtain L site inspection video data; distributing to M edge computing servers for data preprocessing, uploading to a cloud computing center for inspection data analysis, and obtaining inspection analysis results. The present invention solves the technical problem that the prior art power grid monitoring usually relies on centralized data processing, resulting in data transmission delays and excessive network load, which in turn leads to low data processing efficiency.
Description
Technical Field
The invention relates to the technical field of smart grids, in particular to a smart grid data communication optimization method based on edge calculation.
Background
In a conventional smart grid, data is generally required to be transmitted from an edge device to a central cloud computing center for centralized processing, this method may cause high transmission delay, especially in a scene with high real-time monitoring and response requirements, for example, state monitoring and fault diagnosis of a power transmission line need quick feedback, while high delay in the conventional method may affect safety and stability of the grid, such centralized processing mode may often cause excessive use of network bandwidth and increase of network load, in the smart grid, especially when large-scale data acquisition and processing is performed, data transmission requirement is greatly increased, which may cause reduction of transmission efficiency, and limitation of bandwidth may affect data transmission speed and reliability, thereby affecting real-time monitoring and decision capability of the grid.
Disclosure of Invention
The application provides an intelligent power grid data communication optimization method based on edge calculation, and aims to solve the technical problems that in the prior art, power grid monitoring generally depends on centralized data processing, so that data transmission delay and network load are excessive, and further the data processing efficiency is low.
The application discloses a smart grid data communication optimization method based on edge calculation, which comprises the steps of obtaining a routing inspection topological network of a target grid, wherein the routing inspection topological network comprises K power transmission lines, L routing inspection stations and a cloud computing center, the K power transmission lines comprise K power transmission equipment sets and K power transmission paths, carrying out multi-angle communication analysis on the K power transmission equipment sets and the L routing inspection stations to obtain K power transmission equipment communication characteristic meta-sets and L routing inspection station communication characteristic meta-sets, carrying out edge jump recognition on the routing inspection topological network based on the K power transmission equipment communication characteristic meta-sets and the L routing inspection station communication characteristic meta-sets to obtain M edge topology sub-networks, wherein the M edge topology sub-networks comprise M edge communication coefficients, carrying out sub-network service resource balanced configuration on the M edge topology sub-networks based on the M edge topology sub-networks to obtain M edge computing servers after being configured, respectively carrying out routing inspection on the K power transmission equipment sets and the L routing inspection station communication characteristic meta-sets by using K routing inspection machines to obtain the K routing inspection stations and the L routing inspection station communication data according to a preset data protocol, carrying out routing inspection on the L routing inspection station communication protocol to obtain the L routing inspection station communication protocol, and obtaining a patrol analysis result of the target power grid.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The method provides comprehensive understanding of a power grid structure, lays a foundation for subsequent communication analysis and edge calculation optimization, ensures accuracy of data acquisition and processing, performs multi-angle communication analysis on power transmission equipment and the inspection site to obtain a communication characteristic tuple set, enables multi-dimensional data analysis to identify communication characteristics of the equipment and the site, establishes comprehensive communication characteristics, facilitates optimization of data flow and network load, performs edge jump identification on the inspection topology network based on the communication characteristic tuple set, can divide the power grid into a plurality of edge topology sub-networks, calculates edge communication coefficients, can effectively identify key edge nodes and communication paths in the network, optimizes path selection of data transmission, improves data processing efficiency and transmission stability, performs balanced configuration of sub-network service resources based on the edge communication coefficients, optimizes resource allocation of an edge calculation server, ensures balanced use of the computing resources, improves processing capacity and response speed of the server, enables the inspection machine to perform data transmission and the inspection to be processed by the aid of an unmanned aerial vehicle, enables the inspection machine to obtain a detailed data transmission line, and the data transmission state to be processed in real-time, and the data is processed by the automatic inspection machine, and the data inspection machine is enabled to be fully and the data inspection machine is enabled to be processed in real-time, the cloud computing center analyzes the uploaded preprocessed data to generate a patrol analysis result of a target power grid, and the centralized analysis can integrate data from different sources, provide comprehensive power grid running state and potential problem assessment and promote the scientificity and effectiveness of power grid management.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Fig. 1 is a schematic flow chart of a smart grid data communication optimization method based on edge calculation according to an embodiment of the present application;
Fig. 2 is a schematic flow chart of constructing K communication characteristic tuple sets of power transmission equipment and L communication characteristic tuples of patrol stations in the smart grid data communication optimization method based on edge calculation according to the embodiment of the application.
Detailed Description
The embodiment of the application solves the technical problems of low data processing efficiency caused by data transmission delay and overweight network load due to the fact that the power grid monitoring in the prior art generally depends on centralized data processing by providing the intelligent power grid data communication optimization method based on edge calculation.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present application provides a smart grid data communication optimization method based on edge calculation, where the method includes:
the method comprises the steps of obtaining a patrol topology network of a target power grid, wherein the patrol topology network comprises K power transmission lines, L patrol stations and a cloud computing center, and the K power transmission lines comprise K power transmission equipment sets and K power transmission paths.
Firstly, the physical range and equipment distribution of a target power grid are defined, wherein the target power grid comprises all power transmission lines, power transmission equipment and patrol stations, and can be a regional power grid or a sub-part of a large-scale power system.
The method comprises the steps of determining K power transmission lines of a target power grid, L inspection stations and a cloud computing center, wherein K, L are positive integers, the K power transmission lines are all power transmission lines needing to be inspected in the target power grid, the lines comprise actual physical lines and all related power transmission equipment such as transformers, power transmission towers and switching equipment, the L inspection stations are stations needing to be inspected periodically or irregularly in the power grid, the stations generally comprise key nodes such as transformer substations, power distribution stations and control centers, the cloud computing center is connected with the power grid and is responsible for processing and storing data obtained from the power grid inspection, and computing resources are provided for data analysis.
For the K power transmission lines, all power transmission equipment comprising cables, transformers, switching equipment and the like, which play a key role in the operation of a power grid, are determined, wherein the K power transmission lines comprise K power transmission equipment sets, meanwhile, the specific path of each power transmission line is determined, the specific path comprises information such as physical layout, path length and passing terrain environment of the line, the detailed information of the path is very important for subsequent inspection planning, and the K power transmission lines comprise K power transmission paths.
The information of the K power transmission lines, the L inspection stations and the cloud computing center is integrated into a complete inspection topological network, and the topological network can display all key components and interrelations thereof in the power grid and is used for planning and executing the inspection tasks of the power grid.
And carrying out multi-angle communication analysis on the K power transmission equipment sets and the L inspection stations to obtain K power transmission equipment communication characteristic tuple sets and L inspection station communication characteristic tuples.
For K power transmission equipment sets, respectively analyzing the environmental characteristics, position coordinates and channel power loss of the nearby power transmission equipment sets to obtain K power transmission equipment environmental characteristic sets, K power transmission equipment position coordinate sets and K power transmission equipment channel power loss amounts, integrating to obtain K power transmission equipment communication characteristic tuple sets, wherein each tuple comprises three-dimensional communication characteristics which cannot be changed by each power transmission equipment and cannot be changed in practical application, and for each inspection station, analyzing the nearby environmental characteristics, position coordinates and channel power loss of each inspection station to obtain L inspection station communication characteristic tuples.
And carrying out edge jump recognition on the inspection topological network based on the K transmission equipment communication characteristic tuple sets and the L inspection site communication characteristic tuples to obtain M edge topological sub-networks, wherein the M edge topological sub-networks comprise M edge communication coefficients.
And using the obtained K transmission equipment communication characteristic tuple sets and L patrol station communication characteristic tuples as basic data for analyzing the patrol topology network. In graph theory, the step recognition involves detecting key turning points or edge positions between nodes in the network, the edge step recognition is used herein to locate points of significant changes in communication characteristics in the patrol topology network, these changes mark the division of different areas or sub-networks, the patrol topology network is divided into M edge topology sub-networks according to the result of the edge step recognition, M is a positive integer, and each sub-network represents an independent part of the patrol topology network. The M edge topology subnetworks include M edge communication coefficients that represent communication efficiency, stability, and other related communication performance metrics within the subnetwork and between the subnetwork and the external network.
And carrying out sub-network service resource balance configuration on the M edge topology sub-networks based on the M edge communication coefficients to obtain M edge computing servers with complete configuration.
And evaluating the computing resource requirement of each edge topology sub-network by using the M edge communication coefficients obtained by calculation, wherein the computing resource requirement comprises computing capacity, storage space, network bandwidth, response time and the like. The equalization configuration target is determined, for example, to avoid over-allocation or under-allocation of resources while ensuring that each sub-network is able to meet its service requirements.
Based on the balanced configuration target, according to the edge communication coefficient, computing resources are reasonably distributed, so that the load of each sub-network is uniformly distributed, for example, for the sub-network with higher service requirement, more computing resources are preferentially distributed to ensure the communication quality and service performance, and according to the edge communication coefficient and the requirement evaluation result, the M edge topology sub-networks are distributed with resources, wherein the resources distributed by each sub-network comprise computing capacity, storage, network bandwidth and the like. According to the resource allocation result, corresponding edge computing servers are deployed for each edge topology sub-network to obtain M edge computing servers with complete configuration, and the edge computing servers are responsible for processing computing tasks and data processing in the sub-network and provide low-delay and high-efficiency computing services.
By means of balanced configuration of service resources of the sub-network, calculation efficiency and stability of the routing inspection topological network can be effectively improved, stable operation of the edge calculation server under the condition of high load is ensured, and reliable calculation support is provided for power grid routing inspection and maintenance.
And carrying out inspection on the K power transmission lines by using the K inspection unmanned aerial vehicles according to the K power transmission paths respectively to obtain K line inspection video data sets, and carrying out inspection on the L inspection sites by using the L inspection robots according to the inspection routes in the preset stations to obtain L site inspection video data.
Each power transmission line is allocated with a patrol unmanned aerial vehicle, the patrol unmanned aerial vehicle is flight equipment for power transmission line patrol, and the patrol unmanned aerial vehicle is provided with a high-definition camera and can automatically fly according to a preset path to acquire video data of the running condition and the safety condition of the power transmission line. The unmanned aerial vehicle automatically patrols and examines according to the transmission path, and the unmanned aerial vehicle records the running condition and the security condition of transmission line and equipment thereof in real time through the high definition camera that its carried, acquires the detailed video data of circuit to real-time transmission to ground control center obtains K circuit and patrols and examines the video data set.
Each inspection station is provided with an inspection robot, the inspection robot is ground mobile equipment for inspection in the station, the inspection robot is provided with a high-definition camera, the inspection can be automatically performed in a preset route, and video data of the running state and the safety condition of equipment in the station are collected. According to the structural layout of each inspection station, an in-station inspection route is preset, and the inspection route should cover all key equipment and areas in the station, so that the comprehensiveness and accuracy of inspection are ensured. The inspection robot automatically inspects in the inspection station according to a preset inspection route, acquires the running state and the safety condition of equipment in the station in real time through a camera of the inspection robot, acquires station inspection video data, and uploads the station inspection video data to a control center in real time to acquire L station inspection video data.
And distributing the K line inspection video data sets and the L site inspection video data to M edge computing servers based on the M edge topology sub-networks to perform data preprocessing, uploading the preprocessed data to the cloud computing center according to a preset communication protocol to perform inspection data analysis, and obtaining inspection analysis results of the target power grid.
And distributing the K line inspection video data sets and the L site inspection video data to M edge computing servers according to the M edge topology subnetworks, wherein each edge computing server corresponds to one edge topology subnetwork and is responsible for processing the distributed video data.
After the edge computing server receives the distributed data, the data is preprocessed by utilizing computing resources of the edge computing server, and the steps of video compression, denoising, image enhancement, data format conversion, preliminary fault detection and the like are included, wherein the preliminary fault detection can be used for carrying out preliminary analysis on inspection video data by utilizing a preset detection algorithm, equipment faults, line anomalies or potential safety hazards which possibly exist are identified, the preprocessing aims at reducing data transmission quantity, improving data quality and preliminarily identifying the potential safety hazards or faults which possibly exist.
Uploading the preprocessed data to a cloud computing center according to a preset communication protocol, and after the cloud computing center receives the preprocessed data from the M edge computing servers, performing deep analysis on all inspection data by using a high-level analysis algorithm and a big data processing tool, wherein the analysis process comprises comprehensive inspection of equipment operation states, identification of potential safety hazards, trend prediction and the like, and generating inspection analysis results of a target power grid, and the analysis results comprise information of equipment health states, risk assessment, fault prediction and the like and are used for supporting operation and maintenance decisions of the power grid.
Further, as shown in fig. 2, performing multi-angle communication analysis on the K power transmission device sets and the L inspection sites to obtain K power transmission device communication feature tuple sets and L inspection site communication feature tuples, including:
The method comprises the steps of carrying out near environment feature recognition on K power transmission equipment sets and L inspection sites by using a local scene sensor to obtain K power transmission equipment environment feature sets and L inspection site features, obtaining K power transmission equipment position coordinate sets, L inspection site position coordinates and cloud computing center position coordinates of the K power transmission equipment sets, L inspection sites and the cloud computing center by combining the inspection topology network, carrying out channel power loss analysis on the K power transmission equipment position coordinate sets, the L inspection site position coordinates and the cloud computing center position coordinates based on a channel power loss function to obtain K power transmission equipment channel power loss amounts and L site channel power loss amounts, and constructing K power transmission equipment communication feature tuple sets and L inspection site communication feature tuple based on the K power transmission equipment environment feature sets, the L inspection site features, the K power transmission equipment position coordinate sets, the L inspection site position coordinates, the K power transmission equipment channel power loss amounts and the L site channel power loss amounts.
The local scene sensor is equipment for sensing environmental information in a specific area, such as a high-definition camera, a laser radar, a temperature and humidity sensor and the like, and is arranged at key positions of K power transmission equipment sets and L inspection sites, so that the environment around the equipment can be covered.
The local scene sensor collects environmental data around the power transmission equipment and the inspection site, the data comprise visual images, temperature distribution, humidity level, obstacle positions and the like, key environmental features are extracted from the collected data by utilizing a computer vision and sensor data processing algorithm, for example, the image processing algorithm is adopted to identify physical features such as surrounding trees, buildings and topography changes, the temperature sensor is adopted to record the temperature changes nearby the equipment, and the laser radar is adopted to draw a three-dimensional environmental model around the equipment. And (3) extracting environmental characteristics to form K power transmission equipment environmental characteristic sets and L patrol station characteristics.
And acquiring accurate geographic coordinates of each power transmission device and the patrol station by using a GPS or Beidou navigation system, and acquiring geographic position coordinates of a cloud computing center. The method comprises the steps of combining geographical coordinate data of K power transmission equipment sets into a set, representing specific positions of the equipment in a patrol topology network to obtain K power transmission equipment position coordinate sets, combining geographical coordinate data of L patrol stations into a set to obtain L patrol station position coordinates, and similarly obtaining cloud computing center position coordinates. Integrating the position coordinates with the inspection topological network, determining the relative position and distance relation of each device and the station in the network, and laying a foundation for subsequent inspection tasks and data processing.
Setting a channel power loss function, carrying out channel power loss calculation on the K power transmission equipment position coordinate sets and the cloud computing center position coordinates through the channel power loss function to obtain K power transmission equipment channel power loss amounts, and carrying out channel power loss calculation on the L inspection station position coordinates and the cloud computing center position coordinates through the channel power loss function to obtain L station channel power loss amounts.
The method comprises the steps of integrating the obtained K power transmission equipment environment feature sets, the K power transmission equipment position coordinate sets and the K power transmission equipment channel power loss amounts to obtain K power transmission equipment communication feature tuple sets, and integrating the obtained L patrol station features, the L patrol station position coordinates and the L station channel power loss amounts to obtain L patrol station communication feature tuples. The communication characteristic tuple comprises three-dimensional communication characteristics which cannot be changed by the power transmission equipment or the inspection station, including environmental characteristics, position coordinates and channel power loss, and is used for the communication characteristics of the power transmission equipment or the inspection station.
Further, performing channel power loss analysis on the K power transmission equipment position coordinate sets, the L patrol station position coordinates and the cloud computing center position coordinates based on a channel power loss function to obtain K power transmission equipment channel power loss amounts and L station channel power loss amounts, including:
constructing the channel power loss function, wherein the channel power loss function is as follows:
;
Wherein, As the amount of channel power loss,In order to inspect the power transmission equipment or inspection sites, the height of the signal transmission device of the inspection unmanned plane or inspection robot from the horizontal plane,For the position coordinates of the power transmission equipment or the position coordinates of the inspection station,The center position coordinates are calculated for the cloud,,For reference distanceThe transmission power is the reception power of 1w,In order to carry out the inspection of the transmission equipment or the inspection station, the transmission loss of the signal transmission device of the inspection unmanned plane or the inspection robot,For the reception loss of the cloud computing center,The method comprises the steps of representing signal transmission wavelength, respectively inputting the K power transmission equipment position coordinate sets and the cloud computing center position coordinates into the channel power loss function to obtain the K power transmission equipment channel power loss, respectively inputting the L patrol station position coordinates and the cloud computing center position coordinates into the channel power loss function to obtain the L station channel power loss.
Specifically, the channel power loss function is:
;
the channel power loss is a power loss measurement from a source to a receiving end, namely the power lost by the signal in the process of transmitting the signal from the inspection equipment or the station to the cloud computing center, and the larger the power loss is, the worse the signal quality is. The formula calculates the power loss and numerator of the signal in the transmission process The denominator part combines the altitude factor and the actual transmission distance to adjust the reference value, thereby calculating the actual channel power loss, determining the propagation performance of the signal under different environments and conditions, and providing basis for optimizing the communication network and adjusting the equipment configuration.
The method comprises the steps of respectively inputting the position coordinates of the K power transmission equipment and the position coordinates of the cloud computing center into a channel power loss function, obtaining the channel power loss quantity of the K power transmission equipment through calculation, respectively inputting the position coordinates of the L inspection stations and the position coordinates of the cloud computing center into the channel power loss function, and obtaining the channel power loss quantity of the L stations through calculation.
Further, the local scene perceptron is used for identifying the environmental characteristics of the K power transmission equipment sets and the L inspection sites, and the K power transmission equipment environmental characteristic sets and the L inspection site characteristics are obtained, including:
The method comprises the steps of carrying out monitoring video acquisition on K power transmission equipment sets and L inspection sites by using video monitoring equipment to obtain K power transmission equipment monitoring picture sets and L inspection site monitoring pictures, calling an interesting identification unit in the local scene sensor to extract interesting targets of the K power transmission equipment monitoring picture sets and the L inspection site monitoring pictures to obtain K power transmission equipment monitoring target sets and L inspection site monitoring targets, taking the K power transmission equipment monitoring target sets and the L inspection site monitoring targets as dynamic semantic identification objects, and calling a semantic identification unit in the local scene sensor to carry out environment dynamic feature identification to obtain K power transmission equipment environment feature sets and L inspection site features.
And proper video monitoring equipment, such as a high-definition camera and the like, is arranged according to the geographical environment, equipment layout and monitoring requirements of the power transmission equipment and the inspection site, so that the key areas of the power transmission equipment and the inspection site can be covered. After the video monitoring equipment is started, carrying out uninterrupted monitoring on the K power transmission equipment sets and the L inspection stations to obtain the K power transmission equipment monitoring picture sets and the L inspection station monitoring pictures.
The interesting identification unit in the local scene sensor is mainly used for automatically analyzing the monitoring picture and identifying dynamic interference around the equipment, such as no person approaching the equipment, whether dangerous sources exist around the equipment and the like. The monitoring picture is analyzed by using the interesting identification unit, and the interesting target can be accurately extracted by using the technologies of an image processing algorithm, a deep learning model and the like, so that K monitoring target sets of power transmission equipment and L monitoring targets of inspection sites are obtained.
And taking the K monitoring target sets of the power transmission equipment and the L monitoring targets of the inspection sites as dynamic semantic identification objects, namely the basis of environment dynamic feature identification. Invoking a semantic recognition unit of the local scene perceptron, which is responsible for extracting dynamic features of the environment from the surveillance video, recognizing changes in the environment using deep learning or other advanced image processing techniques to identify dynamic features including movement of objects, personnel proximity, changes around the device, etc.
And (3) carrying out dynamic feature recognition on the monitoring target, for example, detecting whether a person approaches the power transmission equipment, whether dangerous sources (such as flames and smoke) exist around the equipment or not, processing recognition results into environment feature data, including the environment feature of each power transmission equipment and the environment feature of each inspection station, if so, whether dynamic interference exists, providing dynamic information of the equipment and the surrounding environment of the station, and corresponding one power transmission equipment environment feature to each power transmission equipment.
Further, performing edge jump recognition on the inspection topological network based on the K power transmission equipment communication feature tuple sets and the L inspection site communication feature tuples to obtain M edge topological sub-networks, including:
And randomly extracting N communication characteristic tuples from the K transmission equipment communication characteristic tuple sets and the L patrol site communication characteristic tuples to perform edge jump starting point authentication, obtaining N edge jump starting points when the authentication is passed, wherein N is an integer greater than or equal to 3, performing edge jump recognition in the patrol topology network based on the N edge jump starting points to obtain N first edge topology subnetworks, wherein the N first edge topology subnetworks comprise N first edge communication coefficients, obtaining N updated edge jump starting points again to perform edge jump recognition on the patrol topology network, and performing update recognition for a plurality of times until the K transmission equipment communication characteristic tuple sets and the L patrol site communication characteristic tuples are divided into the edge topology subnetworks to obtain N updated edge topology subnetwork sets, and obtaining the M edge topology subnetworks and the M edge communication coefficients according to the N first edge topology subnetworks and the N updated edge topology subnetworks.
From the communication characteristic tuple set of K power transmission equipment and the communication characteristic tuple of L patrol stations, extracting N communication characteristic tuples by adopting a random method, wherein N is an integer greater than or equal to 3, verifying whether the extracted N communication characteristic tuples can be used as effective edge jump starting points, wherein the edge jump starting points refer to initial nodes selected in an edge computing network, the nodes are used as starting points for data transmission and processing in the network, the verification standard can be based on factors such as stability of communication characteristics, acceptable range of channel power loss, safety of environmental characteristics and the like, and only the characteristic tuples meeting the standards can pass authentication, and N edge jump starting points are obtained after the authentication passes.
The edge jump recognition refers to determining an optimal path and structure of edge calculation by analyzing communication characteristics between each starting point and other nodes based on N selected edge jump starting points in a routing inspection topological network, specifically, analyzing communication paths with other nodes in the routing inspection topological network by utilizing the N edge jump starting points, mainly analyzing factors such as channel power loss, equipment position, environmental characteristics and the like in communication characteristic tuples to recognize stable and efficient communication paths, dividing the routing inspection topological network into a plurality of sub-networks according to the result of path analysis, wherein each sub-network takes one edge jump starting point as a center to form independent N first edge topological sub-networks, each first edge topological sub-network is a sub-network taking the edge jump starting point as a core node and comprises other nodes directly or indirectly connected with the core node, and the sub-networks are used for bearing data processing tasks in a local area. And analyzing the communication paths in each sub-network, calculating the communication efficiency of each path, and obtaining the communication coefficient of the sub-network for quantifying the communication performance of the first edge topology sub-network.
According to the previous recognition result, selecting a new jump starting point based on the communication characteristic tuples of the uncovered area, and carrying out edge jump recognition on the inspection topological network again by utilizing the updated jump starting point, and continuously iterating the process until all the communication characteristic tuples of the whole inspection topological network are divided into edge topological sub-networks, so as to finally form N updated edge topological sub-network sets, wherein each sub-network in the sets covers a specific communication characteristic tuple.
And integrating the N first edge topology sub-networks and the N updated edge topology sub-networks to finally generate M edge topology sub-networks, wherein each edge topology sub-network is independent and has high-efficiency communication capability, can exert maximum efficiency in a patrol task, and corresponds to an edge communication coefficient which represents key parameters such as communication quality, channel stability and the like among network internal devices or stations.
Further, the method comprises the steps of:
Carrying out neighborhood recognition according to a preset recognition bandwidth in the routing inspection topological network according to the coordinate positions of the N edge jump starting points to obtain N edge jump starting point neighborhood, wherein each edge jump starting point neighborhood comprises a plurality of power transmission equipment communication characteristic tuples and a plurality of routing inspection site communication characteristic tuples, carrying out similarity recognition on the N edge jump starting points and the N corresponding edge jump starting point neighborhood by utilizing a cosine similarity calculation formula, cleaning the N edge jump starting point neighborhood according to a recognition result to obtain N cleaning edge jump starting point neighborhood, constructing N first edge topological sub-networks according to the N cleaning edge jump starting point neighborhood, wherein the N first edge topological sub-networks comprise N first power transmission equipment communication characteristic tuple sets and N routing inspection site communication characteristic tuple sets, and carrying out communication coefficient centralized analysis on the basis of the N first power transmission equipment communication characteristic tuple sets and the N inspection site communication characteristic tuple sets to obtain N first edge communication coefficients.
The preset identification bandwidth refers to the communication characteristic tuple range covered from an edge jump starting point in the routing inspection topological network, the size of the bandwidth is similar to the radius in a multidimensional space, the number of the power transmission equipment and routing inspection stations which can be included in the same neighborhood is determined, the preset identification bandwidth is determined according to the scale of the routing inspection topological network, the distribution density of the equipment and the similarity of communication characteristics, a larger bandwidth covers a wider area, more heterogeneous communication characteristic tuples can be introduced, and a smaller bandwidth focuses on more compact equipment and stations with similar communication characteristics.
And determining the specific position of each jump starting point in the routing inspection topological network by utilizing the coordinate positions of the N edge jump starting points obtained before, starting from each edge jump starting point, identifying a neighborhood range by taking a preset identification bandwidth as a radius, wherein in the range, a plurality of transmission equipment communication characteristic tuples close to the starting point positions and routing inspection station communication characteristic tuples are included, and N edge jump starting point neighborhoods are formed according to the identification result.
For each edge jump starting point, cosine similarity is calculated by using a cosine similarity calculation formula respectively with all communication characteristic tuples in the neighborhood of the edge jump starting point to obtain a group of similarity values, the closer the similarity value is to1, the higher the similarity of two vectors is, the closer the communication characteristics are, a similarity threshold value is set according to practical application requirements, communication characteristic tuples with similarity values lower than the threshold value are marked as low-similarity tuples, communication characteristic tuples with similarity values higher than the threshold value are marked as high-similarity tuples, cleaning is carried out according to marking results, specifically, communication characteristic tuples marked as low-similarity tuples are removed in each neighborhood, communication interference or instability can be introduced into the tuples, N cleaning edge jump starting point neighborhood is obtained according to cleaning results, the communication characteristic tuples which are most similar to the edge jump starting points are reserved in the cleaned edge jump starting point neighborhood, and communication among the tuples is more stable.
Based on N cleaning edge jump starting point neighborhoods, constructing communication links among nodes, wherein each link corresponds to a communication relation between a communication characteristic tuple of power transmission equipment and a communication characteristic tuple of a patrol station, constructing N first edge topology sub-networks according to the determined nodes and the determined communication links, the topology structure of each sub-network reflects a communication path and an association relation among nodes in the edge jump starting point neighborhoods, and generating corresponding communication characteristic sets in the constructed first edge topology sub-networks, wherein the communication characteristic sets comprise N first power transmission equipment communication characteristic tuple sets and N patrol station communication characteristic tuple sets, and the sets comprise communication characteristic information which is effective in the sub-networks and support subsequent data transmission and processing.
And constructing feature vectors based on the N first transmission equipment communication feature tuple sets and the N patrol station communication feature tuple sets, performing centralized analysis by using the extracted feature vectors, calculating the communication coefficient of each edge topology sub-network according to the analysis result, and obtaining N first edge communication coefficients, wherein the communication coefficients are key indexes reflecting factors such as communication efficiency, channel loss, interference degree and the like among nodes in the sub-network and are used for evaluating and optimizing network performance.
Further, performing communication coefficient centralized analysis based on the N first power transmission device communication feature tuple sets and the N patrol station communication feature tuple sets to obtain N first edge communication coefficients, including:
The method comprises the steps of respectively carrying out communication characteristic weighted calculation on N first transmission equipment communication characteristic tuple sets and N inspection site communication characteristic tuple sets according to preset weights to obtain N first transmission equipment communication coefficient sets and N first inspection site communication coefficient sets, randomly extracting N centralized analysis starting points from the N first transmission equipment communication coefficient sets, carrying out iteration on the N first transmission equipment communication coefficient sets according to preset iteration steps to obtain N iterative first transmission equipment communication coefficients, judging whether concentration degree difference values of the N iterative first transmission equipment communication coefficients and the N centralized analysis starting points meet preset concentration degree difference values, if not, updating the N iterative first transmission equipment communication coefficients to N iterative centralized analysis starting points, continuing iteration according to preset iteration steps, if yes, stopping iteration, taking the N iterative first transmission equipment communication coefficients as N first target transmission equipment communication coefficients, carrying out communication coefficient centralized analysis on the N first transmission equipment communication coefficient sets according to preset iteration steps, obtaining N first target inspection site communication coefficients, carrying out communication coefficient calculation on the N first target inspection site communication coefficients according to the N first target inspection site communication coefficients, and carrying out calculation on the N target inspection site communication coefficients according to the preset iteration steps.
According to the requirements of practical application scenes and the importance of communication features, the weights of the features in each feature tuple are set, and the weights can be determined through historical data analysis or experimental results, for example, in the communication of power transmission equipment, the channel power loss is more important than the equipment position coordinates, so that the weights are higher, and the sum of the weights of the features is 1.
And multiplying each feature in each communication feature tuple by a corresponding weight value according to a preset weight, adding the weighted feature values to obtain a communication coefficient of a single feature tuple, and carrying out the weighted calculation on all tuples in the N first power transmission equipment communication feature tuple sets and the N patrol station communication feature tuple sets to obtain N first power transmission equipment communication coefficient sets and N first patrol station communication coefficient sets respectively.
And randomly extracting N starting points according to the N first power transmission equipment communication coefficient sets obtained through calculation to serve as initial positions for centralized analysis. According to the actual application requirements and the change rule of the equipment communication characteristics, a preset iteration step length is set, wherein the iteration step length refers to the adjustment amplitude of the communication coefficient in each iteration, when the step length is large, the iteration speed is high, but the accuracy may be insufficient, and when the step length is small, the iteration accuracy is high, but more iteration times may be needed.
Taking N centralized analysis starting points which are randomly extracted as initial points, adjusting the starting points according to a preset iteration step length in a first round of iteration, calculating new communication coefficients, adjusting the coefficients in N first transmission equipment communication coefficient sets for a plurality of times, in each iteration, the updated communication coefficients are used as the input of the next iteration, and the coefficients are gradually optimized until the preset convergence condition is met or the maximum iteration number is reached, so that the final N iteration first transmission equipment communication coefficients are obtained.
And calculating the concentration difference value between the communication coefficient of the N iterative first power transmission equipment and the N concentrated analysis starting points, wherein the concentration difference value is the difference between the communication coefficient updated each time in the iterative process and the initial concentrated analysis starting point, and can be obtained by calculating the difference value between each iterative communication coefficient and the corresponding starting point coefficient.
The preset concentration difference value is set to judge whether the iteration is converged or not, and can be set based on the requirements of the application scene and the characteristics of the algorithm. Comparing the calculated concentration difference value with a preset concentration difference value, if the calculated concentration difference value is larger than the preset concentration difference value, indicating that the current iteration result is not converged, updating the N iteration first power transmission equipment communication coefficients to N iteration concentrated analysis starting points, and continuing to iterate the next round according to the preset iteration step length.
If the difference value is smaller than or equal to the preset concentration difference value, the iteration process is converged, iteration can be stopped, and at the moment, the current N iteration first power transmission equipment communication coefficients are used as the final N first target power transmission equipment communication coefficients and are used as the basis for subsequent analysis and decision.
The same analysis method as the power transmission equipment is adopted to obtain N first target patrol station communication coefficients through analysis, and for the sake of simplicity of the description, details are omitted.
According to actual application requirements and a network optimization strategy, preset weights are set, the weights can reflect the influence degree of different communication coefficients on edge communication performance, and according to the preset weights, weighting calculation is carried out on N first target power transmission equipment communication coefficients and N first target patrol station communication coefficients, so that final N first edge communication coefficients are obtained.
Further, the method comprises the steps of:
and when the M operation coefficients are greater than or equal to preset operation coefficients, acquiring an early warning instruction, and sending the early warning instruction to the cloud computing center for warning.
The operation coefficients calculate the quantized values of the operation states and performance indexes of the server for each edge, specifically, indexes such as CPU utilization rate, memory use condition, disk read-write speed and the like are collected through a hardware monitoring tool and a sensor, standardized processing is carried out on the collected monitoring data so as to ensure that each index has comparability, weighting summation is carried out on each index data according to weights of different indexes, M operation coefficients are obtained, and the weights can be adjusted according to system requirements and performance importance.
Defining the maximum allowable performance index value of the edge computing servers in the normal operation state, setting preset operation coefficients, comparing the operation coefficient of each edge computing server with the preset operation coefficients, judging whether the operation coefficient exceeds a preset threshold, triggering early warning when the operation coefficient is larger than or equal to the preset operation coefficient, generating corresponding early warning instructions, and sending the early warning instructions to a cloud computing center for warning so as to ensure stable and efficient operation of the system.
In summary, the smart grid data communication optimization method based on edge calculation provided by the embodiment of the application has the following technical effects:
The method provides comprehensive understanding of a power grid structure, lays a foundation for subsequent communication analysis and edge calculation optimization, ensures accuracy of data acquisition and processing, performs multi-angle communication analysis on power transmission equipment and the inspection site to obtain a communication characteristic tuple set, enables multi-dimensional data analysis to identify communication characteristics of the equipment and the site, establishes comprehensive communication characteristics, facilitates optimization of data flow and network load, performs edge jump identification on the inspection topology network based on the communication characteristic tuple set, can divide the power grid into a plurality of edge topology sub-networks, calculates edge communication coefficients, can effectively identify key edge nodes and communication paths in the network, optimizes path selection of data transmission, improves data processing efficiency and transmission stability, performs balanced configuration of sub-network service resources based on the edge communication coefficients, optimizes resource allocation of an edge calculation server, ensures balanced use of the computing resources, improves processing capacity and response speed of the server, enables the inspection machine to perform data transmission and the inspection to be processed by the aid of an unmanned aerial vehicle, enables the inspection machine to obtain a detailed data transmission line, and the data transmission state to be processed in real-time, and the data is processed by the automatic inspection machine, and the data inspection machine is enabled to be fully and the data inspection machine is enabled to be processed in real-time, the cloud computing center analyzes the uploaded preprocessed data to generate a patrol analysis result of a target power grid, and the centralized analysis can integrate data from different sources, provide comprehensive power grid running state and potential problem assessment and promote the scientificity and effectiveness of power grid management.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. An intelligent power grid data communication optimization method based on edge calculation, which is characterized by comprising the following steps:
Acquiring a patrol topology network of a target power grid, wherein the patrol topology network comprises K power transmission lines, L patrol stations and a cloud computing center, and the K power transmission lines comprise K power transmission equipment sets and K power transmission paths;
Performing multi-angle communication analysis on the K power transmission equipment sets and the L inspection stations to obtain K power transmission equipment communication characteristic tuple sets and L inspection station communication characteristic tuples;
Performing edge jump recognition on the inspection topological network based on the K power transmission equipment communication characteristic tuple sets and the L inspection site communication characteristic tuples to obtain M edge topological sub-networks, wherein the M edge topological sub-networks comprise M edge communication coefficients;
Carrying out sub-network service resource balance configuration on the M edge topology sub-networks based on the M edge communication coefficients to obtain M edge computing servers with complete configuration;
The method comprises the steps that K inspection unmanned aerial vehicles are utilized to inspect K transmission lines according to the K transmission paths respectively, K line inspection video data sets are obtained, L inspection robots are utilized to inspect L inspection stations according to an inspection route in a preset station, and L station inspection video data are obtained;
Distributing the K line inspection video data sets and the L site inspection video data to M edge computing servers based on the M edge topology sub-networks to perform data preprocessing, uploading the preprocessed data to the cloud computing center according to a preset communication protocol to perform inspection data analysis, and obtaining inspection analysis results of the target power grid;
Performing edge step recognition on the inspection topological network based on the K power transmission equipment communication characteristic tuple sets and the L inspection site communication characteristic tuples to obtain M edge topological sub-networks, wherein the method comprises the following steps:
randomly extracting N communication characteristic tuples from the K transmission equipment communication characteristic tuple sets and the L patrol station communication characteristic tuples to perform edge jump starting point authentication, and obtaining N edge jump starting points when the authentication passes, wherein N is an integer greater than or equal to 3;
Performing edge jump recognition in the inspection topological network based on the N edge jump starting points to obtain N first edge topological sub-networks, wherein the N first edge topological sub-networks comprise N first edge communication coefficients;
acquiring N updated edge jump starting points again to carry out edge jump recognition on the inspection topological network, and carrying out repeated updating recognition until the K transmission equipment communication characteristic tuple sets and the L inspection site communication characteristic tuples are divided into edge topological sub-networks to obtain N updated edge topological sub-network sets;
Obtaining the M edge topology sub-networks and the M edge communication coefficients according to the N first edge topology sub-networks and N updated edge topology sub-network sets;
carrying out neighborhood recognition in the routing inspection topological network according to the coordinate positions of the N edge jump starting points and a preset recognition bandwidth to obtain N edge jump starting point neighborhood, wherein each edge jump starting point neighborhood comprises a plurality of transmission equipment communication characteristic tuples and a plurality of routing inspection station communication characteristic tuples;
Performing similarity recognition on N edge jump starting points and N corresponding edge jump starting point neighborhoods by using a cosine similarity calculation formula, and cleaning the N edge jump starting point neighborhoods according to recognition results to obtain N cleaning edge jump starting point neighborhoods;
constructing N first edge topology sub-networks according to the N cleaning edge jump starting point neighborhoods, wherein the N first edge topology sub-networks comprise N first power transmission equipment communication characteristic tuple sets and N inspection station communication characteristic tuple sets;
And carrying out communication coefficient centralized analysis based on the N first power transmission equipment communication characteristic tuple sets and the N patrol station communication characteristic tuple sets to obtain N first edge communication coefficients.
2. The smart grid data communication optimization method based on edge calculation according to claim 1, wherein performing multi-angle communication analysis on the K power transmission device sets and the L inspection sites to obtain K power transmission device communication feature tuple sets and L inspection site communication feature tuples, includes:
Carrying out nearby environment characteristic identification on the K power transmission equipment sets and the L inspection sites by using a local scene sensor to obtain K power transmission equipment environment characteristic sets and L inspection site characteristics;
combining the inspection topological network, and acquiring K power transmission equipment position coordinate sets, L inspection stations and cloud computing center position coordinates of the K power transmission equipment sets, L inspection stations and the cloud computing center;
carrying out channel power loss analysis on the K power transmission equipment position coordinate sets, the L patrol station position coordinates and the cloud computing center position coordinates based on a channel power loss function to obtain K power transmission equipment channel power loss amounts and L station channel power loss amounts;
And constructing the K power transmission equipment communication characteristic tuple sets and the L inspection site communication characteristic tuples based on the K power transmission equipment environment characteristic sets, the L inspection site characteristics, the K power transmission equipment position coordinate sets, the L inspection site position coordinates, the K power transmission equipment channel power loss amounts and the L site channel power loss amounts.
3. The smart grid data communication optimization method based on edge calculation according to claim 2, wherein performing channel power loss analysis on the K power transmission device position coordinate sets, the L patrol station position coordinates and the cloud computing center position coordinates based on a channel power loss function to obtain K power transmission device channel power loss amounts and L station channel power loss amounts comprises:
constructing the channel power loss function, wherein the channel power loss function is as follows: ;
Wherein, As the amount of channel power loss,In order to inspect the power transmission equipment or inspection sites, the height of the signal transmission device of the inspection unmanned plane or inspection robot from the horizontal plane,For the position coordinates of the power transmission equipment or the position coordinates of the inspection station,The center position coordinates are calculated for the cloud,,For reference distanceThe transmission power is the reception power of 1w,In order to carry out the inspection of the transmission equipment or the inspection station, the transmission loss of the signal transmission device of the inspection unmanned plane or the inspection robot,For the reception loss of the cloud computing center,Representing the signal transmission wavelength;
Respectively inputting the K power transmission equipment position coordinate sets and the cloud computing center position coordinates into the channel power loss function to obtain the K power transmission equipment channel power loss;
And respectively inputting the L patrol site position coordinates and the cloud computing center position coordinates into the channel power loss function to obtain the L site channel power loss.
4. The smart grid data communication optimization method based on edge calculation according to claim 2, wherein the performing, by using a local scene sensor, the near environmental feature recognition on the K power transmission device sets and the L patrol stations to obtain the K power transmission device environmental feature sets and the L patrol stations includes:
monitoring video collection is carried out on the K power transmission equipment sets and the L inspection sites by using video monitoring equipment, and K power transmission equipment monitoring picture sets and L inspection site monitoring pictures are obtained;
Invoking an interested identification unit in the local scene sensor to extract interested targets from the K power transmission equipment monitoring picture sets and the L patrol station monitoring pictures to obtain K power transmission equipment monitoring target sets and L patrol station monitoring targets;
and taking the K power transmission equipment monitoring target sets and the L inspection site monitoring targets as dynamic semantic identification objects, and calling a semantic identification unit in the local scene sensor to carry out environment dynamic feature identification to obtain the K power transmission equipment environment feature sets and the L inspection site features.
5. The smart grid data communication optimization method based on edge calculation according to claim 1, wherein the performing communication coefficient centralized analysis based on the N first power transmission device communication feature tuple sets and the N patrol site communication feature tuple sets to obtain N first edge communication coefficients includes:
respectively carrying out communication characteristic weighted calculation on the N first power transmission equipment communication characteristic tuple sets and the N inspection station communication characteristic tuple sets according to preset weights to obtain N first power transmission equipment communication coefficient sets and N first inspection station communication coefficient sets;
Randomly extracting N centralized analysis starting points from the N first power transmission equipment communication coefficient sets, and iterating in the N first power transmission equipment communication coefficient sets according to a preset iteration step length to obtain N iterated first power transmission equipment communication coefficients;
Judging whether the concentration difference value between the N iteration first power transmission equipment communication coefficients and the N concentrated analysis starting points meets a preset concentration difference value, if not, updating the N iteration first power transmission equipment communication coefficients into N iteration concentrated analysis starting points, and continuing to iterate according to a preset iteration step length;
If yes, stopping iteration, and taking the N iteration first power transmission equipment communication coefficients as N first target power transmission equipment communication coefficients;
Carrying out communication coefficient centralized analysis on the N first inspection site communication coefficient sets to obtain N first target inspection site communication coefficients;
And carrying out weighted calculation on the N first target power transmission equipment communication coefficients and the N first target patrol station communication coefficients according to preset weights to obtain the N first edge communication coefficients.
6. The smart grid data communication optimization method based on edge calculation as set forth in claim 1, comprising:
Performing operation situation monitoring on the M edge computing servers to obtain M operation coefficients;
And when the M operation coefficients are larger than or equal to the preset operation coefficients, acquiring an early warning instruction, and sending the early warning instruction to the cloud computing center for warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510150729.5A CN119652934B (en) | 2025-02-11 | 2025-02-11 | Smart grid data communication optimization method based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510150729.5A CN119652934B (en) | 2025-02-11 | 2025-02-11 | Smart grid data communication optimization method based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119652934A CN119652934A (en) | 2025-03-18 |
| CN119652934B true CN119652934B (en) | 2025-05-02 |
Family
ID=94947558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510150729.5A Active CN119652934B (en) | 2025-02-11 | 2025-02-11 | Smart grid data communication optimization method based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119652934B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120011604B (en) * | 2025-04-18 | 2025-07-25 | 福建亿榕信息技术有限公司 | An intelligent analysis method for multi-source unstructured data |
| CN120128697B (en) * | 2025-05-09 | 2025-07-25 | 东衢智慧交通基础设施科技(江苏)有限公司 | Intelligent terminal monitoring system and method based on edge calculation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739184A (en) * | 2020-06-28 | 2020-10-02 | 国网宁夏电力有限公司检修公司 | Transmission line inspection system based on transmission line tower |
| CN114448755A (en) * | 2022-03-03 | 2022-05-06 | 深圳供电局有限公司 | Data transmission method, apparatus, computer equipment, and computer-readable storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10149172B2 (en) * | 2015-03-10 | 2018-12-04 | Blinq Wireless Inc. | Method and system for network planning in fixed wireless backhaul networks |
| JP7035606B2 (en) * | 2018-02-21 | 2022-03-15 | 日本電気株式会社 | Edge computing systems, edge servers, system control methods, and programs |
-
2025
- 2025-02-11 CN CN202510150729.5A patent/CN119652934B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739184A (en) * | 2020-06-28 | 2020-10-02 | 国网宁夏电力有限公司检修公司 | Transmission line inspection system based on transmission line tower |
| CN114448755A (en) * | 2022-03-03 | 2022-05-06 | 深圳供电局有限公司 | Data transmission method, apparatus, computer equipment, and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119652934A (en) | 2025-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119652934B (en) | Smart grid data communication optimization method based on edge calculation | |
| CN116880555B (en) | Unmanned aerial vehicle crowd dispatch system based on edge calculation | |
| CN118731582A (en) | Transmission line fault location method, device and transmission line monitoring system | |
| US12007075B2 (en) | Methods and internet of things (IoT) systems for managing smart gas safety hazard items based on geographic information systems | |
| CN120178917B (en) | A distributed drone protection network dynamic generation optimization method and system | |
| CN114244691B (en) | Video service fault location method, device and electronic equipment | |
| CN117807558B (en) | A comprehensive fault detection method, system and storage medium for transmission line | |
| CN116707689B (en) | Method and system for distributing monitoring equipment of medium wave broadcast transmitter | |
| CN119478844B (en) | Transmission line hazard source distance measurement method and system based on point cloud spatial information fusion | |
| CN118763558B (en) | Power line inspection method of UAV swarm based on transmission line topology | |
| CN115664006A (en) | Increment distribution network intelligence management and control integration platform | |
| CN119597018A (en) | Multi-unmanned aerial vehicle cooperative power rechecking method and system based on communication technology | |
| CN118838392A (en) | Power transmission line unmanned aerial vehicle inspection method and system based on positioning communication | |
| CN121386841A (en) | Unmanned aerial vehicle formation inspection method, unmanned aerial vehicle formation inspection device, unmanned aerial vehicle formation inspection equipment and unmanned aerial vehicle formation inspection medium | |
| CN119518531B (en) | A method and device for power line inspection coordinated by unmanned aerial vehicle groups | |
| CN119342437B (en) | An intelligent collection system and method using Beidou communication technology | |
| CN118941986B (en) | Automatic inspection method for overhead transmission line and related products | |
| CN120850190A (en) | A method, system, device and medium for adaptive fusion of UWB and video stream | |
| CN120931097B (en) | Power transmission line fire risk assessment method and device, storage medium and electronic equipment | |
| CN113324998B (en) | Production quality inspection supervision system for titanium alloy bars | |
| CN120412660B (en) | Urban noise analysis methods, devices, equipment, and storage media based on edge AI | |
| CN120912649B (en) | An automatic registration method for power grid line point clouds | |
| CN121284611A (en) | Portable remote safe operation and maintenance system for power monitoring | |
| Gu et al. | Performance Optimization Strategy for Power Operation Safety Intelligent Monitoring System under Cloud Edge Fusion Architecture | |
| CN118730055A (en) | UAV mapping system based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |