Integrated operation and maintenance resource allocation method and system for power information network

By calculating the feature degree of images collected by the drone and the remaining capacity of the computing terminal, and using the matching algorithm to allocate image processing tasks, the problem of low allocation efficiency of data processing resources during drone inspection is solved, and the optimization use and calculation of resources is realized Improved efficiency.

CN118740838BActive Publication Date: 2024-11-19HUBEI CENT CHINA TECH DEV OF ELECTRIC POWER
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411219892.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2024-11-19
Estimated Expiration
2044-09-02

AI Technical Summary

Technical Problem

The large amount of videos or pictures taken during the drone inspection leads to a high demand for computing power for data processing. How to globally optimal resource allocation of images collected by drone and computing terminal is an urgent solution. question.

Method used

By processing the acquired acquired images, the characteristic degree and confidence of the edge map are calculated, and these characteristics and the remaining capacity of the computing terminal are used as edge weight coefficients. The image and the computing terminal are matched using a matching algorithm (such as the KM matching algorithm). Ensure that images of different levels of clarity are uploaded to different server terminals, and optimize resource usage and computing efficiency.

Benefits of technology

The optimal resource allocation for images and computing terminals is realized, computing efficiency is improved, task waiting time is reduced, response speed is improved, and the computing terminal is avoided. By filtering images with obvious fault characteristics is retained, missing detection and Misconduct.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118740838B_ABST
    Figure CN118740838B_ABST
Patent Text Reader

Abstract

The present application relates to the field of resource allocation, and in particular to a method and system for allocating integrated operation and maintenance resources of an electric power information network, the method comprising the steps of: processing the acquired acquisition image to obtain an edge map; calculating the characteristic degree and confidence of each edge map; taking the cumulative sum of the characteristic degree, confidence of each edge map and the remaining capacity of each acquired operation terminal as the edge weight coefficient; matching the image with the operation terminal using a matching algorithm according to the edge weight coefficient. The present application has the effect of optimal resource allocation for global images and operation terminals.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of resource allocation, and in particular to a method and system for allocating integrated operation and maintenance resources of an electric power information network. Background Art

[0002] The Integrated Operations and Maintenance Resource Allocation Method is a systematic method for efficiently and reasonably allocating and utilizing various resources in operation and maintenance management. The Integrated Operations and Maintenance Resource Allocation Method for Power Information Network is a resource management strategy specifically for power industry information systems to ensure stable operation and efficient maintenance of power information systems.

[0003] In the integrated operation and maintenance resource allocation method of the power information network, wiring detection is a key link to ensure the stable operation of the power system. The operation and maintenance team of the power information network can ensure that the health of the line is effectively monitored, and potential problems are discovered and solved in a timely manner, thereby ensuring the reliability and safety of power supply. Common methods of wiring detection include: visual inspection, regular visual inspection of power lines to identify visible damage, wear or abnormalities. Drone inspection, using drones for aerial inspections to cover areas that are difficult to reach manually.

[0004] During the drone inspection process, the collected video information and image information need to be sent to the terminal for defect identification. For example, the application document with publication number CN117765375A discloses a power grid inspection data management method, including: receiving the inspection results of the drone; matching the inspection results with the transmission line information, and determining the corresponding transmission line tower number and position when the inspection picture was taken; preprocessing the inspection picture; renaming the preprocessed inspection picture; identifying defects in the renamed picture; and marking defects in the renamed picture with defects.

[0005] However, the amount of videos or pictures taken during the inspection process is large, so the amount of data processing at the terminal is large, and the computing power requirements are high. How to make the global optimal resource allocation for the images collected by the drone and the computing terminal is an urgent problem that needs to be solved. Summary of the invention

[0006] In order to solve the technical problem of how to optimally allocate resources to global image and computing terminals, the present application provides an integrated operation and maintenance resource allocation method and system for an electric power information network.

[0007] In a first aspect, the present application provides an integrated operation and maintenance resource allocation method for a power information network, which adopts the following technical solution:

[0008] A method for allocating integrated operation and maintenance resources for an electric power information network comprises the following steps: processing acquired collected images to obtain edge maps; calculating the characteristic degree and confidence of each edge map; taking the cumulative sum of the characteristic degree, confidence of each edge map and the acquired remaining capacity of each operation terminal as an edge weight coefficient; matching the image with the operation terminal using a matching algorithm according to the edge weight coefficient; wherein the characteristic degree is calculated by: setting the statistical angle of the grayscale run matrix in the edge map, calculating the texture complexity of each statistical angle, calculating the normalized result of the mean of the cumulative sum of the ratios of the pixel value of each pixel point to the pixel value of all pixels, and taking the product of the normalized result and the mean of the texture complexity as the characteristic degree of the edge map.

[0009] The beneficial effects are as follows: the clarity of the image can be determined according to the characteristic degree of the edge image. Since the real-time idle capacity of different server terminals is also different, images of different clarity are uploaded to different server terminals to ensure sufficient computing capacity, optimize resource usage, and improve computing efficiency. Through fast matching, task waiting time is reduced, response speed is improved, and through reasonable allocation of image processing tasks, load balancing is achieved to avoid overloading of certain computing terminals.

[0010] Optionally, the characteristic degree is calculated as:

[0011] ,in, Indicates The characteristic degree of the frame edge map, , , , For the The statistical angle of the grayscale run-length matrix in the frame edge map, Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on represents the positive correlation normalization function, Indicates The pixel value in the frame edge map is The number of pixels, Indicates The number of all pixels in the frame edge map, Indicates The number of non-zero pixels in the frame edge map.

[0012] The beneficial effects are as follows: by calculating the texture complexity at the above four angles, the texture features of the image can be fully captured. Averaging the texture complexity values ​​at different angles helps to balance the texture information in all directions and obtain a comprehensive feature degree index. By considering the distribution of pixel points corresponding to each pixel value, the grayscale contrast and distribution uniformity of the image are reflected.

[0013] Optionally, the characteristic degree is calculated as:

[0014] ,in, Indicates The characteristic degree of the frame edge map, , , , For the The statistical angle of the grayscale run-length matrix in the frame edge map, Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on represents the negative correlation normalization function, Indicates The pixel value in the frame edge map is The number of pixels, Indicates The number of all pixels in the frame edge map, Indicates The number of non-zero pixels in the frame edge map.

[0015] The beneficial effect is: providing another method for calculating a comprehensive feature degree index, which reflects the grayscale contrast and distribution uniformity of the image by considering the distribution of pixel points corresponding to each pixel value.

[0016] Optionally, the texture complexity is calculated as:

[0017] , Indicates The statistical angle of the grayscale run-length matrix in the frame edge map, For the Frame edge graph at angle The complexity of the texture on Indicates The length of the grayscale run length matrix in the frame edge image is The proportion of an element to the whole.

[0018] The beneficial effects are: by calculating the length distribution of grayscale runs in the edge map to evaluate the complexity of the texture, the texture features are quantified, and by calculating the texture complexity at different angles θ, the texture features of the image can be comprehensively analyzed.

[0019] Optionally, the confidence is calculated as:

[0020] ,in, For the The confidence of the frame edge map, For the The characteristic degree of the frame edge map, is the total number of frames.

[0021] Optionally, the method further includes the step of deleting edge images whose feature degree is greater than a preset threshold.

[0022] The beneficial effect is: since the drone will be affected by factors such as airflow, human operation, and defocus during flight, the captured image will be unclear and the fault location may be blurred. The fault detection effect using this image is poor, and may even result in missed detection and false detection. Therefore, it is necessary to screen the blurred images and retain images with obvious fault characteristics.

[0023] Optionally, the matching algorithm is set to the KM matching algorithm.

[0024] In a second aspect, the present application provides an integrated operation and maintenance resource allocation system for a power information network, which adopts the following technical solutions:

[0025] An integrated operation and maintenance resource allocation system for an electric power information network comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the integrated operation and maintenance resource allocation method for the electric power information network is implemented.

[0026] The beneficial effect is: the above-mentioned integrated operation and maintenance resource allocation method of the power information network is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a system based on the memory and the processor for easy use.

[0027] This application has the following technical effects:

[0028] 1. Optimize resource allocation for global images and computing terminals, upload images of different clarity to different server terminals to ensure sufficient computing capacity, improve computing efficiency, and optimize resource usage. Through fast matching, reduce task waiting time, improve response speed, and achieve load balancing through reasonable allocation of image processing tasks to avoid overloading of certain computing terminals.

[0029] 2. During the flight, the drone will be affected by factors such as airflow, human operation, and defocusing, resulting in unclear images. The fault location may be blurred, and the fault detection effect using this image is poor, or even missed detection or false detection may occur. Therefore, it is necessary to screen the blurred images and retain images with obvious fault features. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-restrictive manner, and the same or corresponding numbers represent the same or corresponding parts.

[0031] Figure 1 It is a method flow chart of an integrated operation and maintenance resource allocation method for an electric power information network according to an embodiment of the present application.

[0032] Figure 2 It is a method flow chart of step S2 in a method for allocating integrated operation and maintenance resources of an electric power information network in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0034] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0035] The embodiment of the present application discloses an integrated operation and maintenance resource allocation method for a power information network, which is used to perform global optimal resource allocation for images collected by drones and computing terminals, referring to Figure 1 , including steps S1 to S4, which are specifically as follows:

[0036] S1: Process the acquired image to obtain an edge map.

[0037] A video containing wires or cables is shot by a drone, and frames are extracted from the video at a frame rate of 60 times per second, that is, 60 frames of images are extracted per second. Grayscale processing is performed on the image to obtain a grayscale image, and edge processing is performed on the grayscale image to obtain an edge image with a 0-1 distribution. The edge processing algorithm can be the Canny algorithm.

[0038] S2: Calculate the feature degree and confidence of each edge graph.

[0039] Reference Figure 2 The method for calculating the characteristic degree includes steps S20 to S22, which are specifically as follows:

[0040] S20: Setting the statistical angle of the grayscale run-length matrix in the edge map.

[0041] The angle of the grayscale run-length matrix refers to the direction in which pixel continuity is considered in the image. Common angles are 0° (horizontal), 45°, 90° (vertical), and 135°, which can cover all possible directions of the image, so 0°, 45°, 90°, and 135° are used as statistical angles.

[0042] S21: Calculate the texture complexity at each statistical angle.

[0043] The calculation formula for texture complexity is: , Indicates The statistical angle of the grayscale run-length matrix in the frame edge map, For the Frame edge graph at angle The complexity of the texture on Indicates The length of the grayscale run length matrix in the frame edge image is The proportion of an element to the whole.

[0044] angle The possible values ​​are: 0°, 45°, 90° and 135°.

[0045] S22: Calculate the normalized result of the average of the cumulative sum of the ratios of the pixel value of each pixel point to the pixel value of all pixels, and use the product of the normalized result and the average of the texture complexity as the feature degree of the edge map.

[0046] In one embodiment, the calculation formula of the characteristic degree is:

[0047] ,in, Indicates The characteristic degree of the frame edge map, , , , For the The statistical angle of the grayscale run-length matrix in the frame edge map, Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on.

[0048] represents the positive correlation normalization function, exemplarily, Set to , represents the hyperbolic tangent function.

[0049] Indicates The pixel value in the frame edge map is The number of pixels, Indicates The number of all pixels in the frame edge map, Indicates The number of non-zero pixels in the frame edge map.

[0050] In one embodiment, the calculation formula of the characteristic degree is:

[0051] ,in, Indicates The characteristic degree of the frame edge map, , , , For the The statistical angle of the grayscale run-length matrix in the frame edge map, Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture

[0052] represents the negative correlation normalization function; exemplarily, Set to , represents the natural exponential function.

[0053] Indicates The pixel value in the frame edge map is The number of pixels, Indicates The number of all pixels in the frame edge map, Indicates The number of non-zero pixels in the frame edge map.

[0054] The confidence level is calculated as: ,in, For the The confidence of the frame edge map, For the The characteristic degree of the frame edge map, is the total number of frames.

[0055] In one embodiment, The value of is 120, which means calculating the difference between the image two seconds before and the image two seconds after. Since abnormal fluctuations in the process of drone image shooting usually occur instantaneously, these changes can be captured by comparing the image differences in different time periods.

[0056] In one embodiment, the method further comprises the step of deleting edge images whose characteristic degree is greater than a preset threshold. The preset threshold may be 0.4, 0.5, 0.6 or 0.7, and the value of the preset threshold may be set by the user according to the actual application scenario.

[0057] During the flight, drones will be affected by factors such as airflow, human operation, and defocusing, which may cause the captured images to be unclear and the fault location may be blurred. The fault detection effect using such images is poor, and may even result in missed detections and false detections. Therefore, it is necessary to screen the blurred images and retain images that contain obvious fault features.

[0058] S3: The feature degree and confidence level of each edge graph and the accumulated sum of the remaining capacity of each computing terminal are used as the edge weight coefficient.

[0059] Specifically, the expression of edge weight coefficient is: ,in, represents the edge weight coefficient, Indicates The confidence of the frame edge map, Indicates The characteristic degree of the frame edge map, Table The remaining capacity of the terminal.

[0060] S4: Match the image and the operation terminal using a matching algorithm according to the edge weight coefficient.

[0061] The matching algorithm adopts the KM algorithm. The edge weight coefficient is used as the edge weight of each edge graph and each operation terminal in the KM matching algorithm, and all edge graphs and operation terminals are matched to obtain the global matching result.

[0062] The KM (Kuhn-Munkres Algorithm) matching algorithm is an algorithm for solving the maximum matching problem of a bipartite graph. In a bipartite graph, there is usually a left set and a right set. The edge weight can be expressed as a certain cost or benefit generated by pairing elements in the two sets. In this application, the edge graph is the left set, the operation terminal is the right set, and the edge weight is expressed as the pairing of elements in the two sets with the highest matching degree, that is, every 2 seconds, 120 frames of edge graphs are paired with operation terminals one by one.

[0063] The clarity of the image can be determined based on the characteristic degree of the edge map. Since the real-time idle capacity of different server terminals is also different, images of different clarity are uploaded to different server terminals to ensure sufficient computing power.

[0064] An embodiment of the present application also discloses an integrated operation and maintenance resource allocation system for an electric power information network, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an integrated operation and maintenance resource allocation method for an electric power information network according to the present application is implemented.

[0065] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0066] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high bandwidth memory HBM (High Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0067] Although this specification has shown and described a plurality of embodiments of the present application, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein may be adopted.

[0068] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for allocating integrated operation and maintenance resources of a power information network, characterized in that: Includes steps: Processing the acquired collected image to obtain an edge map; calculating the feature degree and confidence of each edge map; taking the cumulative sum of the feature degree, confidence of each edge map and the acquired remaining capacity of each computing terminal as an edge weight coefficient; matching the image with the computing terminal using a matching algorithm according to the edge weight coefficient; The method for calculating the characteristic degree is as follows: setting the statistical angle of the grayscale run matrix in the edge image, calculating the texture complexity of each statistical angle, calculating the normalized result of the mean of the cumulative sum of the ratios of the pixel value of each pixel point to the pixel value of all pixels, and taking the product of the normalized result and the mean of the texture complexity as the characteristic degree of the edge image; The calculation formula for texture complexity is: , Indicates The statistical angle of the grayscale run-length matrix in the frame edge map, For the Frame edge graph at angle The complexity of the texture on Indicates The length of the grayscale run length matrix in the frame edge image is The proportion of an element to the whole.

2. The integrated operation and maintenance resource allocation method of the power information network according to claim 1 is characterized in that: The calculation formula of characteristic degree is: ,in, Indicates The characteristic degree of the frame edge map, , , , For the The statistical angle of the grayscale run-length matrix in the frame edge map, Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on represents the positive correlation normalization function, Indicates The pixel value in the frame edge map is The number of pixels, Indicates The number of all pixels in the frame edge map, Indicates The number of non-zero pixels in the frame edge map.

3. The integrated operation and maintenance resource allocation method of the power information network according to claim 1, characterized in that: The calculation formula of characteristic degree is: ,in, Indicates The characteristic degree of the frame edge map, , , , For the The statistical angle of the grayscale run-length matrix in the frame edge map, Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on Indicates angle The complexity of the texture on represents the negative correlation normalization function, Indicates The pixel value in the frame edge map is The number of pixels, Indicates The number of all pixels in the frame edge map, Indicates The number of non-zero pixels in the frame edge map.

4. The integrated operation and maintenance resource allocation method of the power information network according to claim 1, characterized in that: The confidence calculation formula is: ,in, For the The confidence of the frame edge map, For the The characteristic degree of the frame edge map, is the total number of frames.

5. The integrated operation and maintenance resource allocation method of the power information network according to claim 1, characterized in that: The step also includes: deleting edge images whose feature degree is greater than a preset threshold.

6. The integrated operation and maintenance resource allocation method of the power information network according to claim 1, characterized in that: The matching algorithm is set to KM matching algorithm.

7. An integrated operation and maintenance resource allocation system for a power information network, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the integrated operation and maintenance resource allocation method for the electric power information network according to any one of claims 1 to 6 is implemented.