Edge calculation control method and equipment for power transmission line image acquisition device

Abstract

The invention discloses an edge calculation control method and equipment for a power transmission line image acquisition device, and the method comprises the steps: deploying a plurality of edge calculation nodes at a preset position node of a power transmission line, and enabling all edge calculation nodes to be connected with a management system of a cloud server; the control method comprises the following steps: preferentially processing tasks with high priorities and high security levels by adopting a dynamic resource allocation strategy according to the priorities and the security levels of image acquisition tasks; the tasks can be distributed to adjacent idle nodes through the centralized management system; or uploading the data corresponding to the processing task of the edge computing node to a cloud server for collaborative analysis; and an analysis result can be sent to a monitoring center and maintenance personnel in real time. According to the method, edge computing resources are reasonably optimized, so that edge computing nodes can perform data processing locally; edge-edge and edge-cloud cooperative processing can be realized through control; the system can cope with complex and changeable field environments, and provides powerful guarantee for safe and stable operation of a power transmission line.

Description

Technical Field

[0001] The present invention relates to the field of image acquisition technology, and more specifically to an edge computing control method and device for a power transmission line image acquisition device. Background Art

[0002] Overhead transmission lines are important national infrastructure. In order to prevent and eliminate the occurrence of transmission line failures, the power grid operation and maintenance department will regularly organize a large amount of manpower and material resources to invest in the operation, maintenance and management of transmission lines.

[0003] At present, with the development of power systems and the continuous expansion of transmission lines, the safe and stable operation of transmission lines is particularly important. Traditional transmission line image acquisition methods usually rely on manual inspections and fixed camera monitoring, which have the following main defects:

[0004] High labor costs: Manual inspections require a lot of manpower and time, which is costly and inefficient.

[0005] Poor real-time performance: Fixed camera monitoring is limited by its installation location and coverage, making it difficult to detect faults on transmission lines in a timely manner.

[0006] Data processing delay: After traditional image data is collected, it needs to be transmitted to a centralized server for processing, resulting in data processing delays and the inability to conduct real-time analysis and early warning.

[0007] In order to solve the above problems, edge computing technology has been introduced into the power transmission line image acquisition system. Edge computing can process and analyze data close to the data source, greatly improving the real-time performance and response speed of the system. However, the existing edge computing system still has some shortcomings when applied to power transmission line image acquisition, such as limited computing resources and limited data transmission bandwidth. Summary of the invention

[0008] In view of this, the present invention provides an edge computing control method and device for a transmission line image acquisition device, which realizes efficient image acquisition and processing by optimizing the deployment and resource management of edge computing nodes.

[0009] In order to achieve the above object, the present invention adopts the following technical solution:

[0010] In a first aspect, an embodiment of the present invention provides an edge computing control method for a power transmission line image acquisition device, wherein a plurality of edge computing nodes are deployed at a preset position node of the power transmission line, each edge computing node is equipped with a corresponding image acquisition device and a computing module; all edge computing nodes are connected to a management system of a cloud server;

[0011] The control method comprises the following steps:

[0012] According to the priority and security level of the image acquisition task, a dynamic resource allocation strategy is adopted to control the corresponding edge computing nodes to give priority to high-priority and high-security level tasks;

[0013] When any edge computing node has no computing resources, its tasks are assigned to nearby idle nodes through the centralized management system; or when edge node resources are insufficient or in-depth analysis is required, the edge-cloud collaborative processing mechanism is triggered to upload the data corresponding to the processing tasks of the edge computing node to the cloud server for collaborative analysis;

[0014] When the edge computing node is processing tasks or the cloud server is processing tasks, the collected images are pre-processed, intelligently analyzed and fault detected, and early warning information is sent to the monitoring center and maintenance personnel in real time.

[0015] Furthermore, according to the priority and security level of the image acquisition task, a dynamic resource allocation strategy is adopted to control the corresponding edge computing nodes to give priority to tasks with high priority and high security level; including:

[0016] According to the timeliness of task processing, set the task priority and configure the corresponding weight, including: high priority task weight is 3, medium priority task weight is 2 and low priority task weight is 1;

[0017] According to the importance of the task, set the task security level and configure the corresponding coefficient, including: high security level coefficient is 1.5, medium security level coefficient is 1.2 and low security level coefficient is 1;

[0018] When they belong to the same task priority or task security level, the corresponding edge computing node is controlled to process the tasks with high weight or large coefficient first;

[0019] When there are both task priority weights and task safety level coefficients, the product of the two is used as the total task execution score. According to the total task execution score, the corresponding edge computing nodes are controlled to give priority to tasks with larger total task execution scores.

[0020] Furthermore, task priorities are set based on task processing timeliness, including:

[0021] When a real-time failure is detected, its task priority is adjusted to a high-priority task;

[0022] Set regular inspection tasks as medium priority tasks;

[0023] Set historical data analysis tasks or tasks that need to be processed when the system is idle as low-priority tasks.

[0024] Furthermore, according to the importance of the task, the task safety level is set; including:

[0025] Set the monitoring task of important equipment on the transmission line that has a significant impact on safety to a high safety level;

[0026] The monitoring tasks of general equipment on the transmission line with less impact on safety are set to medium safety level;

[0027] The monitoring task of non-critical areas on the transmission line is set to a low safety level.

[0028] Furthermore, when any edge computing node has no computing resources, its tasks are allocated to adjacent idle nodes through a centralized management system; including:

[0029] Each edge computing node monitors its own computing resource usage in real time, and uses a heartbeat mechanism to report the node's resource status to the centralized management system at preset intervals;

[0030] The centralized management system draws a dynamic resource table according to the collected resource status;

[0031] When one of the edge computing nodes has no computing resources or the resource usage exceeds the threshold, a resource shortage request is sent to the centralized management system;

[0032] The centralized management system uses the neighboring node selection algorithm according to the resource status table, based on the geographical location and network topology, to select the node with the smallest communication delay and the lowest resource utilization rate among the neighboring nodes of the node;

[0033] According to the preset task splitting algorithm, the task is split into multiple subtasks and assigned to the selected adjacent nodes.

[0034] Furthermore, the resource status includes information about the node ID, resource usage rate and current task queue length.

[0035] Furthermore, when edge node resources are insufficient or in-depth analysis is required, the edge-cloud collaborative processing mechanism is triggered to upload the data corresponding to the processing task of the edge computing node to the cloud server for collaborative analysis, including:

[0036] The centralized management system uses the data compression algorithm to compress the task data and upload it to the cloud server when it determines that the resource usage of all edge computing nodes exceeds the threshold, or the task queue time exceeds the set time, or when it determines that the task processing requires complex calculations or large-scale data processing.

[0037] After receiving the task data, the cloud server decomposes the task into multiple subtasks that can be processed in parallel; it processes the tasks by itself, or distributes the subtasks to multiple idle edge computing nodes through task scheduling and allocation.

[0038] In a second aspect, an embodiment of the present invention further provides an edge computing control system for a power transmission line image acquisition device, comprising: a cloud server and a plurality of edge computing nodes deployed at preset position nodes of the power transmission line; each edge computing node is equipped with a corresponding image acquisition device and a computing module; all edge computing nodes are connected to a management system of the cloud server;

[0039] The control system includes the following functional modules:

[0040] The control dynamic allocation module is used to adopt a dynamic resource allocation strategy according to the priority and security level of the image acquisition task, and control the corresponding edge computing nodes to give priority to tasks with high priority and high security level;

[0041] The control collaborative analysis module is used to distribute the tasks of any edge computing node to the adjacent idle nodes through the centralized management system when there are no computing resources at any edge computing node; or to trigger the edge-cloud collaborative processing mechanism when the edge node resources are insufficient or in-depth analysis is required, and upload the data corresponding to the processing tasks of the edge computing node to the cloud server for collaborative analysis;

[0042] The control processing feedback module is used to pre-process, intelligently analyze and detect faults on the collected images when the edge computing node is processing tasks or the cloud server is processing tasks, and send early warning information to the monitoring center and maintenance personnel in real time.

[0043] In a third aspect, an embodiment of the present invention further provides a computer device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0044] Memory, used to store computer programs;

[0045] The processor, when used to execute the program stored in the memory, can implement an edge computing control method for a power transmission line image acquisition device as described in any one of the first aspects.

[0046] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes an edge computing control method for a transmission line image acquisition device as described in any one of the first aspects.

[0047] The descriptions of the second to fourth aspects of the present invention can refer to the detailed description of the first aspect; and the beneficial effects of the descriptions of the second to fourth aspects can refer to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0048] It can be seen from the above technical solution that compared with the prior art, the present invention has the following advantages:

[0049] Improve real-time performance: Rationally optimize edge computing resources so that edge computing nodes can process data locally, reduce data transmission delays, and achieve real-time detection and early warning of faults.

[0050] Reduce costs: Through automated image acquisition and intelligent analysis, the frequency and cost of manual inspections are reduced.

[0051] Enhanced system reliability: Dynamic resource management and edge-cloud collaboration mechanisms improve the system's reliability and processing capabilities, enabling it to cope with complex and changing on-site environments, and providing strong guarantees for the safe and stable operation of transmission lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a scene for collecting images of power transmission lines provided by the present invention.

[0054] Figure 2 This is a flow chart of the edge computing control method of the power transmission line image acquisition device provided by the present invention.

[0055] Figure 3 This is a block diagram of the edge computing control system of the power transmission line image acquisition device provided by the present invention.

[0056] Figure 4 A structural block diagram of the computer device provided by the present invention is provided for the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0058] Embodiment 1:

[0059] The present invention deploys multiple edge computing nodes at key nodes of the transmission line. Figure 1As shown, each node is equipped with a high-performance image acquisition device and computing module. All edge computing nodes are connected to the management system of the cloud server;

[0060] Among them, based on the geographical environment of the transmission line and the high-prone areas of faults, it is necessary to select appropriate deployment locations to ensure full coverage of key areas. Each edge computing node is equipped with a high-resolution camera, image processing unit (GPU / FPGA) and network module (5G / satellite communication) to ensure high-quality image acquisition and high-speed data transmission.

[0061] Reference Figure 2 As shown, an embodiment of the present invention discloses an edge computing control method for a power transmission line image acquisition device, and the control method includes the following steps:

[0062] S10. According to the priority and security level of the image acquisition task, a dynamic resource allocation strategy is adopted to control the corresponding edge computing nodes to give priority to tasks with high priority and high security level;

[0063] S20. When any edge computing node has no computing resources, its tasks are assigned to adjacent idle nodes through the centralized management system; or when edge node resources are insufficient or in-depth analysis is required, the edge-cloud collaborative processing mechanism is triggered to upload the data corresponding to the processing tasks of the edge computing node to the cloud server for collaborative analysis;

[0064] S30. When the edge computing node processes a task or the cloud server processes a task, the collected images are pre-processed, intelligently analyzed, and faults are detected, and early warning information is sent to the monitoring center and maintenance personnel in real time.

[0065] The present invention realizes efficient utilization of edge computing nodes through intelligent resource management and scheduling algorithms, dynamically allocates computing resources of edge computing nodes according to the real-time and importance of image acquisition tasks, and ensures that key tasks are processed first. In addition, when the computing resources of a certain node are insufficient, some computing tasks can be allocated to neighboring nodes by task splitting and collaborative processing to achieve load balancing. Furthermore, when the processing capacity of the edge node reaches a bottleneck, some data can be uploaded to the cloud for in-depth analysis, and the edge and cloud work together to improve the processing capacity of the overall system. Finally, whether the edge computing node processes tasks or the cloud server processes tasks, the collected images can be denoised, enhanced and feature extracted to improve image quality and recognition accuracy. In addition, deep learning and machine vision technology can be used to establish a transmission line fault detection model, which can quickly identify problems such as broken wires, foreign objects and aging on the transmission line. When a fault is detected, early warning information can be sent to the monitoring center and maintenance personnel in real time, and countermeasures can be taken in time.

[0066] The embodiments of the present invention optimize resource allocation and task scheduling by considering the priority and security level of image acquisition tasks, and combine edge-cloud collaborative processing to achieve efficient image processing, analysis and early warning.

[0067] The following is a detailed description of each of the above steps:

[0068] In step S10, the priority and security level of the image acquisition task are considered in resource allocation

[0069] 1.1 Setting of priorities and security levels

[0070] Each image acquisition task is assigned different priorities and security levels according to its importance and urgency: the task priority is set according to the timeliness of task processing; the task security level is set according to the importance of the task.

[0071] Priority: The urgency of the task, such as regular inspections, fault warnings, etc. Among them, urgent tasks: such as real-time fault monitoring, need to be processed immediately, and have the highest priority. Regular inspection tasks: such as regular line inspections, can be processed later, and have a medium priority. Low priority tasks: such as historical data analysis, can be processed when the system is idle, and have the lowest priority. For example, set: the weight of high priority tasks is 3, the weight of medium priority tasks is 2, and the weight of low priority tasks is 1.

[0072] Security level: the importance of the task, such as key equipment monitoring, general line monitoring, etc. High security level: such as key equipment monitoring, the task has a significant impact on system security. Medium security level: such as general equipment monitoring, the task has a certain impact on system security. Low security level: such as non-critical area monitoring, the task has a small impact on system security. For example, set: Security level coefficient: high security level is 1.5, medium security level is 1.2, and low security level is 1.

[0073] 1.2 Dynamic Resource Allocation

[0074] According to the priority and security level of the task, a dynamic resource allocation strategy is adopted: when the task priorities or security levels are the same, the corresponding edge computing nodes are controlled to process the tasks with high weight or large coefficients first;

[0075] High-priority tasks: Prioritize the allocation of computing resources to ensure timely processing of tasks. Low-priority tasks: Processed after high-priority tasks are completed, or when resources are idle. Tasks with high security levels: Even if the priority is not high, a certain amount of computing resources are guaranteed to ensure security.

[0076] When there are both task priority weight and task safety level coefficient, the product of the two is used as the total score of task execution, and the total priority score of the task is calculated: total task priority score = priority weight × safety level coefficient.

[0077] According to the total score of task execution, the corresponding edge computing node is controlled to give priority to processing tasks with larger total scores.

[0078] In this step, a multi-level feedback queue algorithm based on priority weights can be used to ensure that high-priority tasks can be processed quickly even when resources are tight. The dynamic time slice adjustment mechanism can be combined to dynamically adjust the time slice length according to the task execution time to improve the processing efficiency of medium-priority tasks. Finally, the dynamic priority boosting mechanism can also be used to prevent low-priority tasks from waiting for a long time and improve the overall fairness of tasks.

[0079] Through the above scheme, the present invention realizes dynamic resource allocation and optimization based on task priority and security level, ensures priority processing of high-priority and high-security level tasks, and improves the real-time performance, reliability and resource utilization of the system.

[0080] In step S20, case 1: task allocation when the current node has no computing resources

[0081] When any edge computing node has no computing resources, its tasks are distributed to nearby idle nodes through the centralized management system. The following are the detailed steps and details, including the implementation of load balancing and optimal allocation algorithms:

[0082] (1) Each edge computing node monitors its own computing resource usage in real time and uses a heartbeat mechanism to report the node's resource status to the centralized management system at preset intervals;

[0083] (2) The centralized management system draws a dynamic resource table based on the collected resource status;

[0084] (3) When one of the edge computing nodes has no computing resources or the resource usage exceeds the threshold, a resource shortage request is sent to the centralized management system;

[0085] (4) The centralized management system uses the neighboring node selection algorithm according to the resource status table, based on the geographical location and network topology, to select the node with the smallest communication delay and the lowest resource utilization rate among the neighboring nodes of the node;

[0086] (5) According to the preset task splitting algorithm, the task is split into multiple subtasks and assigned to the selected adjacent nodes.

[0087] Each edge computing node monitors its own computing resource usage in real time, including CPU, GPU, memory, etc. A heartbeat mechanism is used to report the resource status of the node to the centralized management system at regular intervals (such as 5 seconds). The status report includes information such as node ID, resource usage, and current task queue length. The centralized management system maintains a resource status table to record the latest resource status of all edge computing nodes.

[0088] When a certain edge computing node has insufficient resources (resource utilization exceeds a threshold, such as 80%), a resource shortage request is sent to the centralized management system.

[0089] The centralized management system selects the node with the lowest resource utilization rate among the neighboring nodes of the node according to the resource status table. It uses the Neighbor Node Selection Algorithm to select the node with the smallest communication delay based on the geographical location and network topology.

[0090] If the task is large, it can be split into multiple subtasks and split using the Task Splitting Algorithm. Use a distributed computing framework (such as MapReduce) to split the task into subtasks and assign them to multiple adjacent nodes for processing. Use the Load Balancing Algorithm to assign subtasks to the adjacent nodes with the lowest resource utilization to ensure load balancing.

[0091] In addition, in order to further optimize task allocation, a predictive load balancing algorithm can be used:

[0092] Based on historical data and current status, predict the future load of each node and pre-allocate tasks. Use machine learning models (such as LSTM, Long Short-Term Memory) to predict the future resource usage of each node. According to the prediction results, adjust the task allocation strategy to avoid assigning tasks to nodes that may be overloaded in the future. Dynamically adjust the allocation plan and continuously optimize it according to the actual execution situation.

[0093] For example, at a preset location node of a certain transmission line, Node A has received a large number of real-time fault monitoring tasks, and the resource utilization rate has reached 95%, with no available computing resources. Node A reports the resource status to the centralized management system through the heartbeat mechanism. Based on the resource status table, the centralized management system selects Node B, which is geographically adjacent, has the lowest network delay, and has a resource utilization rate of only 20%, as the task receiving node. Node A splits the task into multiple subtasks and assigns these subtasks to Node B.

[0094] Through the task allocation mechanism of adjacent idle nodes, the system can quickly find suitable nodes for task allocation when resources are insufficient, avoiding task backlogs and improving the system's resource utilization and task processing efficiency.

[0095] Case 2: When edge node resources are insufficient or in-depth analysis is required, the edge-cloud collaborative processing mechanism is triggered, and the data corresponding to the processing task of the edge computing node is uploaded to the cloud server for collaborative analysis:

[0096] 1) When the centralized management system determines that the resource utilization rate of all edge computing nodes exceeds the threshold, or the task queuing time exceeds the set time, or when it is determined that the task processing requires complex calculations or large-scale data processing, the data compression algorithm is used to compress the task data and upload it to the cloud server;

[0097] 2) After receiving the task data, the cloud server decomposes the task into multiple subtasks that can be processed in parallel; it processes the task by itself, or distributes the subtasks to multiple idle edge computing nodes through task scheduling and allocation.

[0098] Trigger condition detection:

[0099] It is triggered when the node resource utilization rate exceeds a threshold (such as 80%) or the task queue time exceeds a set threshold (such as 10 seconds), or when a deep analysis requirement is detected, edge-cloud collaboration is triggered. Data compression algorithms (such as Huffman coding) are used to reduce the amount of transmitted data, and data is uploaded through high-speed networks (such as 5G). After the cloud server receives the data, it uses a task decomposition algorithm (such as Divide and Conquer) to decompose the task into subtasks that can be processed in parallel; it can be processed by itself, or the task processing order and resource allocation can be optimized through the collaborative scheduling algorithm of the edge computing node and the cloud server (such as Heterogeneous Earliest Finish Time, HEFT).

[0100] In step S30, the processing result is fed back:

[0101] The cloud server summarizes the subtask results processed by each computing node or summarizes the results of its own processing to generate the final processing result.

[0102] When the edge computing node is processing tasks or the cloud server is processing tasks, the collected images are pre-processed, intelligently analyzed and fault detected, and early warning information is sent to the monitoring center and maintenance personnel in real time. The following are the detailed steps:

[0103] 1. Image preprocessing

[0104] The purpose of image preprocessing is to improve image quality, reduce noise, and facilitate subsequent intelligent analysis and fault detection. Gaussian filtering can be used to remove noise from the image. Histogram equalization can be used to enhance image contrast. Otsu threshold segmentation method can be used to segment the image into foreground and background.

[0105] 2. Intelligent analysis

[0106] The purpose of intelligent analysis is to extract useful information from images, such as detecting fault points in power transmission lines. For example, a convolutional neural network (CNN) is used to extract image features. The pre-trained YOLO model can then be used for target detection. The purpose of fault detection is to identify and locate faults in power transmission lines, such as broken wires, tree branch contact, etc.

[0107] Among them, fault detection uses Support Vector Machine (SVM) classifier for fault identification. Fault location uses image processing technology such as edge detection and contour detection to locate the fault point.

[0108] 3. Real-time warning

[0109] According to the fault identification and location results, early warning information is generated, including fault type, fault location, time, etc. Early warning information is sent to the monitoring center and maintenance personnel in real time through message queues (such as Kafka) or push services (such as Pushbullet).

[0110] Through the above detailed steps of image preprocessing, intelligent analysis, fault detection and real-time early warning, the present invention realizes efficient processing and fault detection of transmission line images, ensures that the system can monitor and warn in real time, improves maintenance efficiency and reliability of transmission lines, improves the accuracy and response speed of fault detection, and ensures the safe operation of transmission lines.

[0111] Embodiment 2:

[0112] Based on the same inventive concept, Figure 1As shown, the present invention also provides an edge computing control system for a power transmission line image acquisition device, comprising: a cloud server and a plurality of edge computing nodes deployed at preset position nodes of the power transmission line; each edge computing node is equipped with a corresponding image acquisition device and a computing module; all edge computing nodes are connected to the management system of the cloud server;

[0113] Reference Figure 3 As shown, the control system includes the following functional modules:

[0114] The control dynamic allocation module is used to adopt a dynamic resource allocation strategy according to the priority and security level of the image acquisition task, and control the corresponding edge computing nodes to give priority to tasks with high priority and high security level;

[0115] The control collaborative analysis module is used to distribute the tasks of any edge computing node to the adjacent idle nodes through the centralized management system when there are no computing resources at any edge computing node; or to trigger the edge-cloud collaborative processing mechanism when the edge node resources are insufficient or in-depth analysis is required, and upload the data corresponding to the processing tasks of the edge computing node to the cloud server for collaborative analysis;

[0116] The control processing feedback module is used to pre-process, intelligently analyze and detect faults on the collected images when the edge computing node is processing tasks or the cloud server is processing tasks, and send early warning information to the monitoring center and maintenance personnel in real time.

[0117] In this embodiment, the system dynamically allocates computing resources according to task priority and security level, so that high-priority and high-security level tasks can obtain computing resources first, ensuring the timely processing of critical tasks. Among them, the centralized management system monitors the resource usage of each edge computing node in real time to ensure that tasks can be efficiently allocated to adjacent idle nodes when resources are insufficient, achieving load balancing and optimal resource utilization. In addition, when edge computing node resources are insufficient or complex calculations are required, the system can trigger the edge-cloud collaborative processing mechanism and upload tasks to the cloud server for collaborative analysis to ensure the smooth completion of tasks and improve the robustness and reliability of the system.

[0118] Through the implementation of the above-mentioned technical solutions and functional modules, the edge computing control system of the transmission line image acquisition device has demonstrated significant technical advantages in task processing efficiency, resource utilization, system robustness, real-time fault warning and delay.

[0119] Embodiment 3:

[0120] Based on the same inventive concept, the present invention also provides a computer device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0121] Memory, used to store computer programs;

[0122] The processor, when used to execute the program stored in the memory, can implement an edge computing control method for a power transmission line image acquisition device as in Example 1.

[0123] like Figure 4 As shown, the electronic device may include: a processor 41, a communication interface 42, a memory 43 and a communication bus 44, wherein the processor 41, the communication interface 42 and the memory 43 communicate with each other through the communication bus 44. The processor 41 may call the logic instructions in the memory 43 to execute an edge computing control method for a power transmission line image acquisition device, the method comprising:

[0124] S10. According to the priority and security level of the image acquisition task, a dynamic resource allocation strategy is adopted to control the corresponding edge computing nodes to give priority to tasks with high priority and high security level;

[0125] S20. When any edge computing node has no computing resources, its tasks are assigned to adjacent idle nodes through the centralized management system; or when edge node resources are insufficient or in-depth analysis is required, the edge-cloud collaborative processing mechanism is triggered to upload the data corresponding to the processing tasks of the edge computing node to the cloud server for collaborative analysis;

[0126] S30. When the edge computing node processes a task or the cloud server processes a task, the collected images are pre-processed, intelligently analyzed, and faults are detected, and early warning information is sent to the monitoring center and maintenance personnel in real time.

[0127] In addition, the logic instructions in the above-mentioned memory 43 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0128] Through the detailed description of the above embodiments, the present invention can effectively solve the problems of unreasonable resource allocation, task processing delay, inaccurate fault detection, etc. in the edge computing control method of the transmission line image acquisition device in the prior art, and has significant technical effects and practical application value.

[0129] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0130] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An edge computing control method for a power transmission line image acquisition device, characterized in that: Multiple edge computing nodes are deployed at preset location nodes of the transmission line, and each edge computing node is equipped with a corresponding image acquisition device and a computing module; all edge computing nodes are connected to the management system of the cloud server; The control method comprises the following steps: According to the priority and security level of the image acquisition task, a dynamic resource allocation strategy is adopted to control the corresponding edge computing nodes to give priority to high-priority and high-security level tasks; When any edge computing node has no computing resources, its tasks are assigned to nearby idle nodes through the centralized management system; or when edge node resources are insufficient or in-depth analysis is required, the edge-cloud collaborative processing mechanism is triggered to upload the data corresponding to the processing tasks of the edge computing node to the cloud server for collaborative analysis; When the edge computing node is processing tasks or the cloud server is processing tasks, the collected images are pre-processed, intelligently analyzed and fault detected, and early warning information is sent to the monitoring center and maintenance personnel in real time.

2. The edge computing control method of a power transmission line image acquisition device according to claim 1, characterized in that: According to the priority and security level of the image acquisition task, a dynamic resource allocation strategy is adopted to control the corresponding edge computing nodes to give priority to high-priority and high-security level tasks; including: According to the timeliness of task processing, set the task priority and configure the corresponding weight, including: high priority task weight is 3, medium priority task weight is 2 and low priority task weight is 1; According to the importance of the task, set the task security level and configure the corresponding coefficient, including: high security level coefficient is 1.5, medium security level coefficient is 1.2 and low security level coefficient is 1; When they belong to the same task priority or task security level, the corresponding edge computing node is controlled to process the tasks with high weight or large coefficient first; When there are both task priority weights and task safety level coefficients, the product of the two is used as the total task execution score. According to the total task execution score, the corresponding edge computing nodes are controlled to give priority to tasks with larger total task execution scores.

3. The edge computing control method of a power transmission line image acquisition device according to claim 2, characterized in that: Set task priorities based on task processing timeliness; including: When a real-time failure is detected, its task priority is adjusted to a high-priority task; Set regular inspection tasks as medium priority tasks; Set historical data analysis tasks or tasks that need to be processed when the system is idle as low-priority tasks.

4. The edge computing control method of a power transmission line image acquisition device according to claim 2, characterized in that: According to the importance of the task, set the task security level; including: Set the monitoring task of important equipment on the transmission line that has a significant impact on safety to a high safety level; The monitoring tasks of general equipment on the transmission line with less impact on safety are set to medium safety level; The monitoring task of non-critical areas on the transmission line is set to a low safety level.

5. The edge computing control method of a power transmission line image acquisition device according to claim 1, characterized in that: When any edge computing node has no computing resources, its tasks are assigned to adjacent idle nodes through the centralized management system; include: Each edge computing node monitors its own computing resource usage in real time, and uses a heartbeat mechanism to report the node's resource status to the centralized management system at preset intervals; The centralized management system draws a dynamic resource table according to the collected resource status; When one of the edge computing nodes has no computing resources or the resource usage exceeds the threshold, a resource shortage request is sent to the centralized management system; The centralized management system uses the neighboring node selection algorithm according to the resource status table, based on the geographical location and network topology, to select the node with the smallest communication delay and the lowest resource utilization rate among the neighboring nodes of the node; According to the preset task splitting algorithm, the task is split into multiple subtasks and assigned to the selected adjacent nodes.

6. The edge computing control method of a power transmission line image acquisition device according to claim 5, characterized in that: The resource status includes information about the node ID, resource usage rate, and current task queue length.

7. The edge computing control method of a power transmission line image acquisition device according to claim 5, characterized in that: When edge node resources are insufficient or in-depth analysis is required, the edge-cloud collaborative processing mechanism is triggered to upload the data corresponding to the processing task of the edge computing node to the cloud server for collaborative analysis, including: The centralized management system uses the data compression algorithm to compress the task data and upload it to the cloud server when it determines that the resource usage of all edge computing nodes exceeds the threshold, or the task queue time exceeds the set time, or when it determines that the task processing requires complex calculations or large-scale data processing. After receiving the task data, the cloud server decomposes the task into multiple subtasks that can be processed in parallel; it processes the tasks by itself, or distributes the subtasks to multiple idle edge computing nodes through task scheduling and allocation.

8. An edge computing control system for a power transmission line image acquisition device, characterized in that: include: A cloud server and multiple edge computing nodes deployed at nodes at preset locations of the transmission line; Each edge computing node is equipped with a corresponding image acquisition device and computing module; All edge computing nodes are connected to the management system of the cloud server; The control system includes the following functional modules: The control dynamic allocation module is used to adopt a dynamic resource allocation strategy according to the priority and security level of the image acquisition task, and control the corresponding edge computing nodes to give priority to tasks with high priority and high security level; The control collaborative analysis module is used to distribute the tasks of any edge computing node to the adjacent idle nodes through the centralized management system when there are no computing resources at any edge computing node; or to trigger the edge-cloud collaborative processing mechanism when the edge node resources are insufficient or in-depth analysis is required, and upload the data corresponding to the processing tasks of the edge computing node to the cloud server for collaborative analysis; The control processing feedback module is used to pre-process, intelligently analyze and detect faults on the collected images when the edge computing node is processing tasks or the cloud server is processing tasks, and send early warning information to the monitoring center and maintenance personnel in real time.

9. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor, when used to execute the program stored in the memory, can implement the edge computing control method of the power transmission line image acquisition device as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed by a processor, enable the processor to execute an edge computing control method for a power transmission line image acquisition device according to any one of claims 1 to 7.

Images