Power grid anomaly identification method and device based on intelligent edge computing gateway

Abstract

The application discloses a power grid anomaly identification method and device based on an intelligent edge computing gateway. The method comprises the following steps: acquiring a current image of a power grid collected in a monitoring process of the power grid; comparing the current image with a historical image; updating an image collection time point of the historical image when there is no difference between the current image and the historical image; comparing the current image with a standard image when there is a difference between the current image and the historical image, obtaining a coincident image and a non-coincident image between the current image and the standard image; removing the coincident image; calculating a coincidence degree of the non-coincident image, and marking a risk according to the coincidence degree to obtain a target image; and transmitting the target image to a server to identify an anomaly in the power grid. The application solves the technical problems in the related art that data redundancy in the gateway is excessive, the data is not screened, the data processing efficiency is low, and it is difficult to quickly and accurately find problems existing in the power grid.

Description

Technical Field

[0001] This invention relates to the field of power grid monitoring technology, and more specifically, to a method and apparatus for identifying power grid anomalies based on an intelligent edge computing gateway. Background Technology

[0002] Currently, the main method involves video monitoring at locations such as substations, distribution substations / transformer areas / towers, and grid connection points of emerging market players such as distributed renewable energy. The data collected from each location is then directly transmitted to a server via a corresponding gateway. The server processes and analyzes the data, and then makes judgments based on the analysis results to monitor the power grid. However, this method has the following problems: 1) It easily leads to excessive data redundancy within the gateway, reducing equipment reliability and affecting the long-term stable operation of the edge gateway; 2) The lack of effective data screening and processing significantly reduces the gateway's data processing efficiency. Simultaneously, the low information transmission efficiency prevents the server from quickly and accurately identifying key issues, hindering the rapid identification of problems requiring resolution.

[0003] There is currently no effective solution to the problems of excessive data redundancy in the gateway and lack of data screening in the aforementioned technologies, which leads to low data processing efficiency and difficulty in quickly and accurately identifying problems in the power grid. Summary of the Invention

[0004] This invention provides a method and apparatus for identifying power grid anomalies based on an intelligent edge computing gateway, which at least solves the technical problems in related technologies, such as excessive data redundancy within the gateway and lack of data screening, resulting in low data processing efficiency and difficulty in quickly and accurately identifying problems in the power grid.

[0005] According to one aspect of the present invention, a power grid anomaly identification method based on an intelligent edge computing gateway is provided, comprising: acquiring a current image of the power grid collected during power grid monitoring; comparing the current image with historical images to obtain a first comparison result, wherein the historical image is an image collected at the previous collection time point of the current collection time point, and the current collection time point is the collection time point of the current image; updating the image collection time point of the historical image if the first comparison result indicates that there is no difference between the current image and the historical image; and updating the image collection time point of the historical image if the first comparison result indicates that there is a difference between the current image and the historical image. The current image is compared with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image. The standard image is a reference image used for comparative analysis of the current image. The overlapping images are the repeated portions between the current image and the standard image, and the non-overlapping images are the non-repeating portions between the current image and the standard image. The overlapping images in the current image are removed. The overlap degree of the non-overlapping images is calculated, and risk marking is performed according to the overlap degree to obtain a target image. The target image is transmitted to a server so that the server can identify anomalies in the power grid based on the target image.

[0006] Optionally, comparing the current image with historical images to obtain a first comparison result includes: decomposing the current image into pixels to obtain first pixel data, wherein the first pixel data is a set of multiple first pixels arranged in a matrix to form the current image; decomposing the historical image into pixels to obtain second pixel data, wherein the second pixel data is a set of multiple second pixels arranged in a matrix to form the historical image; and comparing each of the multiple first pixels in the first pixel data with each of the multiple second pixels in the second pixel data to obtain the first comparison result.

[0007] Optionally, the first comparison result is obtained by comparing multiple first pixels in the first pixel data with multiple second pixels in the second pixel data one by one, including: when all the first pixels and the second pixels correspond to the same, the first comparison result is determined to be that there is no difference between the current image and the historical image; when at least one pixel is different from the second pixel, the first comparison result is determined to be that there is a difference between the current image and the historical image.

[0008] Optionally, if the first comparison result indicates a difference between the current image and the historical image, the current image is compared with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image. This includes: dividing the current image and the standard image into modules to obtain multiple current module images corresponding to the current image and multiple standard module images corresponding to the standard image; performing pixel decomposition on the multiple current module images to obtain first module pixel data for each current module image, wherein the first module pixel data is a set of multiple first module pixels, and the multiple first module pixels are arranged in a matrix to form the current module image; and decomposing the multiple standard module images to obtain second module pixel data for each standard module image, wherein the second module pixel data is a set of multiple second modules. A set of pixel points, with multiple second module pixel points arranged in a matrix to form the standard module image; comparing each set of first module pixel point data with the corresponding set of second module pixel point data one by one to obtain a second comparison result, wherein the first module pixel point data and the second module pixel data are correlated by the position of the current module image in the current image and the position of the standard module image in the standard image; based on the second comparison result, the portion composed of first module pixel points that are the same as the second module pixel points in multiple sets of first module pixel point data is the overlapping image; based on the second comparison result, the portion composed of first module pixel points that are different from the second module pixel points in multiple sets of first module pixel point data is the non-overlapping image.

[0009] Optionally, calculating the overlap degree of the non-overlapping images and performing risk labeling according to the overlap degree to obtain the target image includes: calculating the overlap degree of each current module image based on a second comparison result, wherein the second comparison result is a comparison result obtained by comparing the current image with the standard image, and the current module image is an image obtained by dividing the current image into modules; comparing the overlap degree with an overlap degree threshold to obtain the risk level corresponding to the overlap degree; and performing risk labeling on each current module image according to the risk level to obtain the target image.

[0010] Optionally, calculating the overlap degree of each current module image based on the second comparison result includes: generating a comparison matrix corresponding to each current module image based on the second comparison result, wherein the matrix elements of the comparison matrix correspond one-to-one with the first module pixels in the current module image, and the first module pixels are pixels obtained by pixel decomposition of the current module image; assigning values ​​to the matrix elements of each comparison matrix, wherein the first matrix element corresponding to each first module pixel in the overlapping image is 0, and the second matrix element corresponding to each first module pixel in the non-overlapping image is 1; calculating the overlap degree of each current module image according to the values ​​of the matrix elements using a first formula, wherein the first formula is: Wherein, G represents the overlap degree, n represents the number of row matrices in the alignment matrix, m represents the number of column matrices in the alignment matrix, and H represents the sum of the values ​​of all the first matrix elements and the second matrix elements in the alignment matrix.

[0011] Optionally, the overlap threshold includes: a first overlap threshold, a second overlap threshold, and a third overlap threshold. Comparing the overlap degree with the overlap threshold to obtain the risk level corresponding to the overlap degree includes: if the overlap degree is greater than the first overlap threshold but not greater than the second overlap threshold, determining the risk level corresponding to the overlap degree as a low-risk level, wherein the first overlap threshold is less than the second overlap threshold; if the overlap degree is greater than the second overlap threshold but not greater than the third overlap threshold, determining the risk level corresponding to the overlap degree as a medium-risk level, wherein the second overlap threshold is less than the third overlap threshold; and if the overlap threshold is greater than the third overlap threshold, determining the risk level corresponding to the overlap degree as a high-risk level.

[0012] According to another aspect of the present invention, a power grid anomaly identification device based on an intelligent edge computing gateway is also provided, comprising: a first acquisition unit, configured to acquire a current image of the power grid collected during power grid monitoring; a second acquisition unit, configured to compare the current image with historical images to obtain a first comparison result, wherein the historical image is an image collected at the previous acquisition time point of the current acquisition time point, and the current acquisition time point is the acquisition time point of the current image; an update unit, configured to update the image acquisition time point of the historical image when the first comparison result indicates that there is no difference between the current image and the historical image; and a third acquisition unit, configured to update the image acquisition time point of the historical image when the first comparison result indicates that there is a difference between the current image and the historical image. In other cases, the current image is compared with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image. The standard image is a reference image used for comparative analysis of the current image. The overlapping images are the images of the repeated portions between the current image and the standard image, and the non-overlapping images are the images of the non-repeating portions between the current image and the standard image. A removal unit is used to remove the overlapping images from the current image. A fourth acquisition unit is used to calculate the overlap degree of the non-overlapping images and perform risk marking according to the overlap degree to obtain a target image. A transmission unit is used to transmit the target image to a server so that the server can identify anomalies in the power grid based on the target image.

[0013] Optionally, the second acquisition unit includes: a first acquisition module, configured to perform pixel decomposition on the current image to obtain first pixel data, wherein the first pixel data is a set of multiple first pixels, and the multiple first pixels are arranged in a matrix to form the current image; a second acquisition module, configured to perform pixel decomposition on the historical image to obtain second pixel data, wherein the second pixel data is a set of multiple second pixels, and the multiple second pixels are arranged in a matrix to form the historical image; and a third acquisition module, configured to compare the multiple first pixels in the first pixel data with the multiple second pixels in the second pixel data one by one to obtain the first comparison result.

[0014] Optionally, the third acquisition module includes: a first determining submodule, configured to determine that there is no difference between the current image and the historical image when all the first pixel points and the second pixel points correspond to the same value; and a second determining submodule, configured to determine that there is a difference between the current image and the historical image when at least one of the first pixel points is different from the second pixel point.

[0015] Optionally, the third acquisition unit includes: a fourth acquisition module, configured to divide the current image and the standard image into modules respectively, to obtain multiple current module images corresponding to the current image and multiple standard module images corresponding to the standard image; a first decomposition module, configured to decompose the multiple current module images into pixels, to obtain first module pixel data for each current module image, wherein the first module pixel data is a set of multiple first module pixels, and the multiple first module pixels are arranged in a matrix to form the current module image; and a second decomposition module, configured to decompose the multiple standard module images, to obtain second module pixel data for each standard module image, wherein the second module pixel data is a set of multiple second module pixels, and the multiple second module pixels are arranged in a matrix to form the standard module image. A block image; a fifth acquisition module, used to compare multiple first module pixels in each group of first module pixel data with multiple second module pixels in the corresponding second module pixel data one by one to obtain a second comparison result, wherein the first module pixel data and the second module pixel data are correlated by the position of the current module image in the current image and the position of the standard module image in the standard image; a first determination module, used to determine, based on the second comparison result, the portion composed of first module pixels that are the same as the second module pixels in multiple groups of first module pixel data as the overlapping image; a second determination module, used to determine, based on the second comparison result, the portion composed of first module pixels that are not the same as the second module pixels in multiple groups of first module pixel data as the non-overlapping image.

[0016] Optionally, the fourth acquisition unit includes: a calculation module, used to calculate the overlap degree of each current module image based on the second comparison result, wherein the second comparison result is a comparison result obtained by comparing the current image with the standard image, and the current module image is an image obtained by dividing the current image into modules; a sixth acquisition module, used to compare the overlap degree with an overlap degree threshold to obtain the risk level corresponding to the overlap degree; and a seventh acquisition module, used to perform risk marking on each of the current module images according to the risk level to obtain the target image.

[0017] Optionally, the calculation module includes: a generation submodule, configured to generate a comparison matrix corresponding to each current module image based on the second comparison result, wherein the matrix elements of the comparison matrix correspond one-to-one with the first module pixels in the current module image, and the first module pixels are pixels obtained by pixel decomposition of the current module image; an assignment submodule, configured to assign values ​​to the matrix elements of each comparison matrix, wherein the first matrix element corresponding to each first module pixel in the overlapping image is 0, and the second matrix element corresponding to each first module pixel in the non-overlapping image is 1; and a calculation submodule, configured to calculate the overlap degree of each current module image according to the values ​​of the matrix elements using a first formula, wherein the first formula is: Wherein, G represents the overlap degree, n represents the number of row matrices in the alignment matrix, m represents the number of column matrices in the alignment matrix, and H represents the sum of the values ​​of all the first matrix elements and the second matrix elements in the alignment matrix.

[0018] Optionally, the overlap threshold includes: a first overlap threshold, a second overlap threshold, and a third overlap threshold. The sixth acquisition module includes: a third determining submodule, configured to determine the risk level corresponding to the overlap as a low-risk level when the overlap is greater than the first overlap threshold and not greater than the second overlap threshold, wherein the first overlap threshold is less than the second overlap threshold; a fourth determining submodule, configured to determine the risk level corresponding to the overlap as a medium-risk level when the overlap is greater than the second overlap threshold and not greater than the third overlap threshold, wherein the second overlap threshold is less than the third overlap threshold; and a fifth determining submodule, configured to determine the risk level corresponding to the overlap as a high-risk level when the overlap threshold is greater than the third overlap threshold.

[0019] According to another aspect of the present invention, a power grid anomaly identification system based on an intelligent edge computing gateway is also provided, wherein the power grid anomaly identification system based on an intelligent edge computing gateway uses any of the above-described power grid anomaly identification methods based on an intelligent edge computing gateway.

[0020] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes any of the above-described methods for identifying power grid anomalies based on a smart edge computing gateway.

[0021] According to another aspect of the present invention, a processor is also provided, the processor being used to run a program, wherein the program, when running, executes any of the above-described methods for identifying power grid anomalies based on a smart edge computing gateway.

[0022] According to another aspect of the present invention, a computer program product is also provided, including computer instructions, which, when executed by a processor, perform any of the above-described methods for identifying power grid anomalies based on a smart edge computing gateway.

[0023] In this embodiment of the invention, a current image of the power grid is acquired during the monitoring of the power grid; the current image is compared with historical images to obtain a first comparison result, wherein the historical image is the image acquired at the previous acquisition time point, and the current acquisition time point is the acquisition time point of the current image; if the first comparison result indicates that there is no difference between the current image and the historical image, the image acquisition time point of the historical image is updated; if the first comparison result indicates that there is a difference between the current image and the historical image, the current image is compared with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image, wherein the standard image is a reference image used for comparison and analysis of the current image, the overlapping image is the image of the repeated part between the current image and the standard image, and the non-overlapping image is the image of the non-repeating part between the current image and the standard image; overlapping images in the current image are removed; the overlap degree of the non-overlapping images is calculated, and risk marking is performed according to the overlap degree to obtain a target image; the target image is transmitted to a server so that the server can identify anomalies in the power grid based on the target image. The above technical solution achieves the goal of comparing newly acquired images with the previous frame, storing new images only when there are differences, marking risk only on the parts of the new image that do not overlap with the standard image, and transmitting the obtained target image to the server. The server then uses this target image to identify anomalies in the power grid. This achieves the technical effect of screening and processing newly acquired images, enabling the server to quickly and accurately identify problems in the power grid. It reduces the redundancy of data within the gateway, improves data processing efficiency, and solves the technical problems in related technologies where excessive data redundancy within the gateway and lack of data screening lead to low data processing efficiency and difficulty in quickly and accurately identifying problems in the power grid. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0025] Figure 1This is a hardware structure block diagram of a mobile terminal for a power grid anomaly identification method based on an intelligent edge computing gateway according to an embodiment of the present invention.

[0026] Figure 2 This is a flowchart of a power grid anomaly identification method based on an intelligent edge computing gateway according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of a power grid anomaly identification system based on an intelligent edge computing gateway according to an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram of an intelligent edge computing gateway according to an embodiment of the present invention;

[0029] Figure 5 This is a schematic diagram of a preprocessing module according to an embodiment of the present invention;

[0030] Figure 6 This is a flowchart of an optional power grid anomaly identification method based on a smart edge computing gateway according to an embodiment of the present invention;

[0031] Figure 7 This is a schematic diagram of a data processing and analysis module according to an embodiment of the present invention;

[0032] Figure 8 This is a schematic diagram of a power grid anomaly identification device based on an intelligent edge computing gateway according to an embodiment of the present invention. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] As described in the background section, related technologies suffer from excessive data redundancy within gateways and a lack of data screening, resulting in low data processing efficiency and difficulty in quickly and accurately identifying problems in the power grid. To address these shortcomings, embodiments of the present invention provide a method and apparatus for power grid anomaly identification based on an intelligent edge computing gateway.

[0036] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0037] The methods and embodiments provided in this invention can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a power grid anomaly identification method based on an intelligent edge computing gateway, according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0038] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the power grid anomaly identification method based on a smart edge computing gateway in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] According to an embodiment of the present invention, a method embodiment for identifying power grid anomalies based on a smart edge computing gateway is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0040] Figure 2 This is a flowchart of a power grid anomaly identification method based on an intelligent edge computing gateway according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0041] Step S202: Obtain the current image of the power grid collected during the monitoring of the power grid.

[0042] In this embodiment, the image acquisition device of the terminal device can be used to acquire the current image of the power grid during the monitoring of the power grid, and the intelligent edge computing gateway can be used to receive the image acquired by the terminal device for processing.

[0043] The image acquisition devices here may include, but are not limited to, cameras, scanners, sensors, and other devices capable of acquiring images.

[0044] The following is combined Figure 3 The embodiments of the present invention will be described in detail below. Figure 3 This is a schematic diagram of a power grid anomaly identification system based on an intelligent edge computing gateway according to an embodiment of the present invention; as shown. Figure 3 As shown, the intelligent edge computing gateway has communication connections with both the terminal device and the server. The intelligent edge computing gateway can receive images collected by the terminal device when it detects the power grid, process them, and then transmit the processed images to the server so that the server can identify abnormal problems in the power grid.

[0045] In the above embodiments of the present invention, an intelligent edge computing gateway is mainly used to process images. The following describes the process in conjunction with... Figure 4 The embodiments of the present invention will be described in detail below. Figure 4 This is a schematic diagram of an intelligent edge computing gateway according to an embodiment of the present invention, as shown below. Figure 4 As shown, the intelligent edge computing gateway includes: a preprocessing module, a second signal input module, a second signal output module, a storage module, and a data processing and analysis module. The intelligent edge computing gateway can perform the following functions: the preprocessing module receives and processes images collected by terminal devices, and then transmits the processed images to the data processing and analysis module through the first signal input module for further processing. After processing the images, the data processing and analysis module transmits the processed images to the storage module for storage, and transmits the processed images to the server through the second signal output module, so that the server can quickly and accurately identify abnormal problems in the power grid based on the processed images.

[0046] Step S204: Compare the current image with the historical images to obtain the first comparison result, wherein the historical image is the image acquired at the previous acquisition time point of the current acquisition time point, and the current acquisition time point is the acquisition time point of the current image.

[0047] The following is combined Figure 5 and Figure 6 The embodiments of the present invention will be described in detail below. Figure 5 This is a schematic diagram of a preprocessing module according to an embodiment of the present invention. Figure 6 This is a flowchart of an optional power grid anomaly identification method based on a smart edge computing gateway according to an embodiment of the present invention.

[0048] like Figure 5As shown, the preprocessing module in the intelligent edge computing gateway includes a first signal output module for signal output, a data preprocessing module for data comparison and analysis, and a first signal input module for signal output. The data preprocessing module is connected to the first signal input module and the first signal output module. The first signal input module is connected to the acquisition device of the terminal device through the network. The first signal output module is connected to the second signal input module.

[0049] like Figure 6 As shown, the acquisition device of the terminal device transmits the newly acquired image to the data preprocessing module of the preprocessing module through the network and the first signal input module. The data preprocessing module compares the newly added image (i.e., the current image) with the previous frame image (i.e., the historical image) to determine whether there is a difference.

[0050] According to the above embodiments of the present invention, in step S204, comparing the current image with a historical image to obtain a first comparison result includes: decomposing the current image into pixels to obtain first pixel data, wherein the first pixel data is a set of multiple first pixels arranged in a matrix to form the current image; decomposing the historical image into pixels to obtain second pixel data, wherein the second pixel data is a set of multiple second pixels arranged in a matrix to form the historical image; and comparing the multiple first pixels in the first pixel data with the multiple second pixels in the second pixel data one by one to obtain the first comparison result.

[0051] In this embodiment, the data preprocessing module can be used to decompose both the current image and the historical image into pixels, so as to decompose them into multiple pixels arranged in matrix form. Then, the pixels of the current image and the historical image are compared one by one to determine whether there is any difference.

[0052] It should be noted that when comparing the pixels of the current image and the historical images one by one, the comparison is made only to pixels in the same position. Since the pixels of the two images are arranged in a matrix, the comparison can be made by comparing the position of each pixel with the corresponding pixel in the other image to determine if there is a difference.

[0053] In the above embodiments of the present invention, the first comparison result is obtained by comparing the multiple first pixels in the first pixel data with the multiple second pixels in the second pixel data one by one. This includes: when all the first pixels and the second pixels correspond to the same value, the first comparison result is determined to be that there is no difference between the current image and the historical image; when at least one pixel is different from the second pixel, the first comparison result is determined to be that there is a difference between the current image and the historical image.

[0054] Specifically, after comparing the pixel correspondences of the current image and the historical image one by one, if all the corresponding pixels of the current image and the historical image are the same, it means that there is no difference between the current image and the historical image; otherwise, it means that there is a difference between the current image and the historical image.

[0055] Step S206: If the first comparison result indicates that there is no difference between the current image and the historical image, update the image acquisition time point of the historical image.

[0056] As above Figure 6 As shown, when there is no difference between the current image and the historical images, the acquisition time of the current image is extracted by the data preprocessing module and transmitted through the first signal output module. Then, the acquisition time is transmitted to the data processing and analysis module through the second signal input module, so that the acquisition time of the historical images can be updated by the information update module in the data processing and analysis module.

[0057] It should be noted that updating the acquisition time of historical images here means adding the acquisition time of the extracted current image to the acquisition time of the historical images, rather than directly replacing them.

[0058] For example, if the current image was captured at 13:00 on December 25, 2023, the original captured time of the historical image can be updated from 12:00 on December 25, 2023 to 12:00 on December 25, 2023. This way, without any changes, only the storage time of the last image (historical image) needs to be modified, without adding new photo information or saving images captured at every time point. This greatly reduces the amount of data stored, which is beneficial to the reliability of the device and the long-term stable operation of the edge gateway.

[0059] Step S208: If the first comparison result indicates that there is a difference between the current image and the historical image, the current image is compared with the standard image to obtain overlapping and non-overlapping images between the current image and the standard image. The standard image is the reference image used for comparison and analysis of the current image, the overlapping image is the image of the repeated part between the current image and the standard image, and the non-overlapping image is the image of the non-repeating part between the current image and the standard image.

[0060] As above Figure 6 As shown in this embodiment, when there is a difference between the current image and the historical image, the current image can be transmitted to the storage module for storage, and the current image can be compared with the standard image stored in the storage module to analyze possible anomalies in the power grid based on the differences between the current image and the standard image.

[0061] The standard image here is an image stored in the storage module. This standard image serves as a benchmark for detecting and identifying changes or differences in new images; in some cases, the standard image may represent an ideal or desired state.

[0062] According to the above embodiments of the present invention, in step S208, when the first comparison result indicates that there is a difference between the current image and the historical image, the current image is compared with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image. This includes: dividing the current image and the standard image into modules to obtain multiple current module images corresponding to the current image and multiple standard module images corresponding to the standard image; performing pixel decomposition on the multiple current module images to obtain first module pixel data for each current module image, wherein the first module pixel data is a set of multiple first module pixels, and the multiple first module pixels are arranged in a matrix to form the current module image; and decomposing the multiple standard module images to obtain second module pixel data for each standard module image, wherein the second... The module pixel data is a collection of multiple second module pixels, which are arranged in a matrix to form a standard module image. Each set of first module pixels is compared one by one with the corresponding set of second module pixels to obtain a second comparison result. The first and second module pixel data are correlated by the position of the current module image in the current image and the position of the standard module image in the standard image. Based on the second comparison result, the portion of the first module pixels in multiple sets of first module pixel data that are identical to the second module pixels is considered an overlapping image. Based on the second comparison result, the portion of the first module pixels in multiple sets of first module pixel data that are not identical to the second module pixels is considered a non-overlapping image.

[0063] The following is combined Figure 7 The embodiments of the present invention will be described in detail below. Figure 7 This is a schematic diagram of the data processing and analysis module according to an embodiment of the present invention, such as... Figure 7 As shown, the data processing and analysis module includes: a comparison and judgment module, an extraction module, a grade determination module, a calibration module, a separation module, and an information update module. The comparison and judgment module is connected to the second signal input module, the extraction module, and the storage module. The extraction module is connected to the separation module. The separation module is connected to the storage module and the grade determination module. The grade determination module is connected to the calibration module. The calibration module is connected to the storage module and the second signal output module. The information update module is connected to the storage module and the second signal output module.

[0064] Specifically, the segmentation module in the data processing and analysis module can be used to divide the current image and the standard image stored in the storage system into modules, so that the current image is divided into multiple current module images and the standard image is divided into multiple standard module images. Then, the comparison and judgment module in the data processing and analysis module performs pixel decomposition and comparison analysis on each current module image and the corresponding standard module image to determine that the parts with the same pixels between the current image and the standard image are overlapping images and the parts with different pixels are non-overlapping images, and then they are calibrated respectively.

[0065] Here, dividing the current image and the standard image into multiple module images before comparing them separately speeds up the comparison process. Furthermore, calculating the overlap of non-overlapping images by module allows for a more refined understanding of the differences between the current and standard images. In other words, overlap calculation and risk labeling are performed on each module of the non-overlapping image, rather than calculating and labeling the entire non-overlapping image in a general way. Of course, in practice, the current image and the standard image can be compared first, and then the resulting non-overlapping images can be divided into modules to determine the overlap of each module and apply risk labeling; no specific restrictions are imposed here.

[0066] Step S210: Remove overlapping images from the current image.

[0067] As above Figure 6 As shown, the cropping module in the data processing and analysis module can be used to remove the parts of the current image that are marked as overlapping images. This reduces the workload of other modules in the data processing and analysis module in analyzing the parts of the current image that are marked as non-overlapping images. At the same time, removing overlapping images before transmitting them to the server can speed up the transmission.

[0068] Step S212: Calculate the overlap degree of the non-overlapping images and perform risk labeling according to the overlap degree to obtain the target image.

[0069] In this embodiment, the overlap between the current image (i.e., the non-overlapping image) after the cropping module removes overlapping images and the corresponding image in the standard image can be calculated. Risk marking is performed based on the calculated overlap to obtain the target image. The lower the overlap, the greater the change and the more serious the problem. The higher the overlap, the smaller the change and the less serious the problem. The greater the change, the more priority should be given to processing.

[0070] According to the above embodiments of the present invention, in step S212, calculating the overlap degree of non-overlapping images and performing risk labeling according to the overlap degree to obtain the target image includes: calculating the overlap degree of each current module image based on the second comparison result, wherein the second comparison result is the comparison result obtained by comparing the current image with the standard image, and the current module image is the image obtained by dividing the current image into modules; comparing the overlap degree with the overlap degree threshold to obtain the risk level corresponding to the overlap degree; and performing risk labeling on each current module image according to the risk level to obtain the target image.

[0071] As above Figure 6 As shown, the overlap between each current module image and its corresponding standard module image can be calculated separately. Then, the risk level corresponding to the overlap of each current module image is determined by the level determination module in the data processing and analysis module. After that, the calibration module is used to calibrate each current module image of the non-overlapping image based on the risk level determined by the level determination module, so as to obtain the target image.

[0072] Specifically, in the above embodiments of the present invention, calculating the overlap degree of each current module image based on the second comparison result includes: generating a comparison matrix corresponding to each current module image based on the second comparison result, wherein the matrix elements of the comparison matrix correspond one-to-one with the first module pixels in the current module image, and the first module pixels are pixels obtained by decomposing the current module image into pixels; assigning values ​​to the matrix elements of each comparison matrix, wherein the first matrix element corresponding to each first module pixel in the overlapping image is 0, and the second matrix element corresponding to each first module pixel in the non-overlapping image is 1; calculating the overlap degree of each current module image according to the values ​​of the matrix elements using a first formula, wherein the first formula is: Where G represents the degree of overlap, n represents the number of row matrices in the alignment matrix, m represents the number of column matrices in the alignment matrix, and H represents the sum of the values ​​of all elements of the first and second matrices in the alignment matrix.

[0073] In this embodiment, each current module image and the standard module image can be decomposed into pixels, forming n rows * m columns of pixels. Then, each current module image is compared pixel by pixel with the corresponding standard module image to generate an n row * m column matrix. The value of the matrix element at the corresponding position is determined based on the pixel comparison result. When the corresponding pixel in the current module image and the standard module image is the same, the matrix element at that position is set to 0; otherwise, when the corresponding pixel in the current module image and the standard module image is different, the matrix element at that position is set to 1. Then, the formula is used: Calculate the overlap degree of each current module image, where G represents the overlap degree, n represents the number of row matrices in the alignment matrix, m represents the number of column matrices in the alignment matrix, and H represents the sum of the values ​​of all matrix elements (including the first and second matrix elements) in the alignment matrix. H can be calculated using the following formula: i represents the row number in the matrix, j represents the column number in the matrix, and a ij This represents the matrix element located in the i-th row and j-th column.

[0074] Specifically, in the above embodiments of the present invention, the overlap threshold includes: a first overlap threshold, a second overlap threshold, and a third overlap threshold. Comparing the overlap degree with the overlap threshold to obtain the risk level corresponding to the overlap degree includes: if the overlap degree is greater than the first overlap threshold but not greater than the second overlap threshold, determining the risk level corresponding to the overlap degree as low risk, wherein the first overlap threshold is less than the second overlap threshold; if the overlap degree is greater than the second overlap threshold but not greater than the third overlap threshold, determining the risk level corresponding to the overlap degree as medium risk, wherein the second overlap threshold is less than the third overlap threshold; and if the overlap threshold is greater than the third overlap threshold, determining the risk level corresponding to the overlap degree as high risk.

[0075] For example, the first overlap threshold can be set to 0%, the second overlap threshold to 8%, and the third overlap threshold to 15%. Of course, other values ​​can also be used as the corresponding overlap thresholds according to the actual situation, and no specific restrictions are imposed here. When 0 < G ≤ 8%, the risk level of the corresponding current module image can be judged as low risk level. When 8% < G ≤ 15%, the risk level of the corresponding current module image can be judged as medium risk level. When G > 15%, the risk level of the corresponding current module image can be judged as high risk level.

[0076] Step S214: The target image is transmitted to the server so that the server can identify anomalies in the power grid based on the target image.

[0077] As above Figure 6 As shown, after the intelligent edge computing gateway processes the new images collected by the terminal device, the processed target image can be transmitted to the server through the second signal output module and the network. This target image helps the server to quickly and accurately determine possible abnormal problems in the power grid and provides solutions quickly and accurately.

[0078] As described above, the technical solution provided by the above embodiments of the present invention obtains the current image of the power grid collected during the monitoring of the power grid; compares the current image with historical images to obtain a first comparison result, wherein the historical image is the image collected at the previous collection time point, and the current collection time point is the collection time point of the current image; if the first comparison result indicates that there is no difference between the current image and the historical image, the image collection time point of the historical image is updated; if the first comparison result indicates that there is a difference between the current image and the historical image, the current image is compared with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image, wherein the standard image is the reference image used for comparison and analysis of the current image, and the overlapping image is the image of the repeated part between the current image and the standard image. For example, a non-overlapping image is the portion of the current image that does not overlap with a standard image. Overlapping images in the current image are removed. The overlap degree of the non-overlapping images is calculated, and risk marking is performed according to the overlap degree to obtain the target image. The target image is then transmitted to the server, which uses the target image to identify anomalies in the power grid. This achieves the goal of comparing newly acquired images with the previous frame, storing new images only when there are differences, and only marking the non-overlapping portions of the new image with the standard image. The resulting target image is then transmitted to the server, which uses the target image to identify anomalies in the power grid. This process screens and processes newly acquired images, enabling the server to quickly and accurately identify problems in the power grid, reducing data redundancy within the gateway, and improving data processing efficiency.

[0079] Therefore, the technical solution provided by the above embodiments of the present invention solves the technical problems in the related art, such as excessive data redundancy in the gateway and lack of data screening, resulting in low data processing efficiency and difficulty in quickly and accurately identifying problems in the power grid.

[0080] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0081] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0082] According to embodiments of the present invention, a power grid anomaly identification device based on an intelligent edge computing gateway is also provided for implementing the above-described method for power grid anomaly identification based on an intelligent edge computing gateway. Figure 8 This is a schematic diagram of a power grid anomaly identification device based on a smart edge computing gateway according to an embodiment of the present invention, such as... Figure 8 As shown, the device includes: a first acquisition unit 801, a second acquisition unit 803, an update unit 805, a third acquisition unit 807, a removal unit 809, a fourth acquisition unit 811, and a transmission unit 813. The following is a detailed description of this power grid anomaly identification device based on a smart edge computing gateway.

[0083] The first acquisition unit 801 is used to acquire the current image of the power grid collected during the monitoring of the power grid.

[0084] The second acquisition unit 803 is used to compare the current image with the historical image to obtain a first comparison result, wherein the historical image is the image acquired at the previous acquisition time point of the current acquisition time point, and the current acquisition time point is the acquisition time point of the current image.

[0085] The update unit 805 is used to update the image acquisition time point of the historical image when the first comparison result indicates that there is no difference between the current image and the historical image.

[0086] The third acquisition unit 807 is used to compare the current image with a standard image when the first comparison result indicates that there is a difference between the current image and the historical image, and to obtain overlapping and non-overlapping images between the current image and the standard image. The standard image is a reference image used for comparison and analysis of the current image, the overlapping image is the image of the repeated part between the current image and the standard image, and the non-overlapping image is the image of the non-repeating part between the current image and the standard image.

[0087] Removal unit 809 is used to remove overlapping images in the current image.

[0088] The fourth acquisition unit 811 is used to calculate the overlap degree of non-overlapping images and perform risk marking according to the overlap degree to obtain the target image.

[0089] The transmission unit 813 is used to transmit the target image to the server so that the server can identify anomalies in the power grid based on the target image.

[0090] It should be noted that the first acquisition unit 801, the second acquisition unit 803, the update unit 805, the third acquisition unit 807, the removal unit 809, the fourth acquisition unit 811, and the transmission unit 813 mentioned above correspond to steps S202 to S214 in the above embodiments. The seven units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments.

[0091] As can be seen from the above, in the scheme described in the above embodiments of the present invention, the first acquisition unit can acquire the current image of the power grid collected during the monitoring of the power grid; then, the second acquisition unit can compare the current image with historical images to obtain a first comparison result, wherein the historical image is the image collected at the previous acquisition time point of the current acquisition time point, and the current acquisition time point is the acquisition time point of the current image; next, the update unit can update the image acquisition time point of the historical image if the first comparison result indicates that there is no difference between the current image and the historical image; then, the third acquisition unit can compare the current image with a standard image if the first comparison result indicates that there is a difference between the current image and the historical image, to obtain overlapping and non-overlapping images between the current image and the standard image, wherein the standard image is the reference image used for comparison and analysis of the current image, and the overlapping image is the image repeated between the current image and the standard image. The process involves several steps: first, a partial image is acquired, where non-overlapping images are the non-repeating portions between the current image and the standard image; then, a removal unit removes overlapping images from the current image; next, a fourth acquisition unit calculates the overlap degree of the non-overlapping images and marks them for risk based on the overlap degree, resulting in the target image; finally, a transmission unit transmits the target image to the server, allowing the server to identify anomalies in the power grid based on the target image. This process compares newly acquired images with the previous frame, stores new images only when there are differences, and marks only the non-overlapping portions of the new image with the standard image for risk. The resulting target image is then transmitted to the server, enabling the server to identify anomalies in the power grid based on the target image. This achieves the technical effect of screening and processing newly acquired images, allowing the server to quickly and accurately identify problems in the power grid, reducing data redundancy within the gateway, and improving data processing efficiency.

[0092] Therefore, the technical solution provided by the above embodiments of the present invention solves the technical problems in the related art, such as excessive data redundancy in the gateway and lack of data screening, resulting in low data processing efficiency and difficulty in quickly and accurately identifying problems in the power grid.

[0093] Optionally, the second acquisition unit includes: a first acquisition module, configured to decompose the current image into pixels to obtain first pixel data, wherein the first pixel data is a set of multiple first pixels arranged in a matrix to form the current image; a second acquisition module, configured to decompose a historical image into pixels to obtain second pixel data, wherein the second pixel data is a set of multiple second pixels arranged in a matrix to form the historical image; and a third acquisition module, configured to compare the multiple first pixels in the first pixel data with the multiple second pixels in the second pixel data one by one to obtain a first comparison result.

[0094] Optionally, the third acquisition module includes: a first determining submodule, configured to determine that there is no difference between the current image and the historical image when all the first pixel points and the second pixel points correspond to the same; and a second determining submodule, configured to determine that there is a difference between the current image and the historical image when at least one pixel point is different from the second pixel point.

[0095] Optionally, the third acquisition unit includes: a fourth acquisition module, used to divide the current image and the standard image into modules respectively, to obtain multiple current module images corresponding to the current image and multiple standard module images corresponding to the standard image; a first decomposition module, used to decompose the multiple current module images into pixels, to obtain first module pixel data for each current module image, wherein the first module pixel data is a set of multiple first module pixels, and the multiple first module pixels are arranged in a matrix to form the current module image; and a second decomposition module, used to decompose the multiple standard module images, to obtain second module pixel data for each standard module image, wherein the second module pixel data is a set of multiple second module pixels, and the multiple second module pixels are arranged in a matrix. The system comprises: a standard module image; a fifth acquisition module, used to compare multiple first module pixels in each group of first module pixel data with multiple second module pixels in the corresponding second module pixel data one by one to obtain a second comparison result, wherein the first module pixel data and the second module pixel data are correlated by the position of the current module image in the current image and the position of the standard module image in the standard image; a first determination module, used to determine, based on the second comparison result, that the portion composed of first module pixels that are the same as second module pixels in multiple groups of first module pixel data is an overlapping image; and a second determination module, used to determine, based on the second comparison result, that the portion composed of first module pixels that are different from second module pixels in multiple groups of first module pixel data is a non-overlapping image.

[0096] Optionally, the fourth acquisition unit includes: a calculation module, used to calculate the overlap degree of each current module image based on the second comparison result, wherein the second comparison result is the comparison result obtained by comparing the current image with a standard image, and the current module image is the image obtained by dividing the current image into modules; a sixth acquisition module, used to compare the overlap degree with an overlap degree threshold to obtain the risk level corresponding to the overlap degree; and a seventh acquisition module, used to perform risk marking on each current module image according to the risk level to obtain the target image.

[0097] Optionally, the calculation module includes: a generation submodule, used to generate a comparison matrix corresponding to each current module image based on the second comparison result, wherein the matrix elements of the comparison matrix correspond one-to-one with the first module pixels in the current module image, and the first module pixels are pixels obtained by pixel decomposition of the current module image; an assignment submodule, used to assign values ​​to the matrix elements of each comparison matrix, wherein the first matrix elements corresponding to each first module pixel in the overlapping image are 0, and the second matrix elements corresponding to each first module pixel in the non-overlapping image are 1; and a calculation submodule, used to calculate the overlap degree of each current module image according to the values ​​of the matrix elements and a first formula, wherein the first formula is: Where G represents the degree of overlap, n represents the number of row matrices in the alignment matrix, m represents the number of column matrices in the alignment matrix, and H represents the sum of the values ​​of all elements of the first and second matrices in the alignment matrix.

[0098] Optionally, the overlap thresholds include: a first overlap threshold, a second overlap threshold, and a third overlap threshold. The seventh acquisition module includes: a third determining submodule, used to determine the risk level corresponding to the overlap as low risk level when the overlap is greater than the first overlap threshold but not greater than the second overlap threshold, wherein the first overlap threshold is less than the second overlap threshold; a fourth determining submodule, used to determine the risk level corresponding to the overlap as medium risk level when the overlap is greater than the second overlap threshold but not greater than the third overlap threshold, wherein the second overlap threshold is less than the third overlap threshold; and a fifth determining submodule, used to determine the risk level corresponding to the overlap as high risk level when the overlap threshold is greater than the third overlap threshold.

[0099] According to another aspect of the present invention, a power grid anomaly identification system based on an intelligent edge computing gateway is also provided, wherein the power grid anomaly identification system based on an intelligent edge computing gateway uses any of the above-described power grid anomaly identification methods based on an intelligent edge computing gateway.

[0100] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes any of the above-described methods for identifying power grid anomalies based on a smart edge computing gateway.

[0101] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any communication device in a group of communication devices.

[0102] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: acquiring a current image of the power grid collected during power grid monitoring; comparing the current image with historical images to obtain a first comparison result, wherein the historical image is the image collected at the previous collection time point, and the current collection time point is the collection time point of the current image; if the first comparison result indicates that there is no difference between the current image and the historical image, updating the image collection time point of the historical image; if the first comparison result indicates that there is a difference between the current image and the historical image, comparing the current image with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image, wherein the standard image is a reference image used for comparative analysis of the current image, the overlapping image is the image of the repeated portion between the current image and the standard image, and the non-overlapping image is the image of the non-repeating portion between the current image and the standard image; removing overlapping images from the current image; calculating the overlap degree of the non-overlapping images and marking them for risk according to the overlap degree to obtain a target image; transmitting the target image to a server to use the server to identify anomalies in the power grid based on the target image.

[0103] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: decomposing the current image into pixels to obtain first pixel data, wherein the first pixel data is a set of multiple first pixels arranged in a matrix to form the current image; decomposing the historical image into pixels to obtain second pixel data, wherein the second pixel data is a set of multiple second pixels arranged in a matrix to form the historical image; comparing the multiple first pixels in the first pixel data with the multiple second pixels in the second pixel data one by one to obtain a first comparison result.

[0104] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: when all first pixels and second pixels correspond to the same value, determine that there is no difference between the current image and the historical image; when at least one pixel is different from the second pixel, determine that there is a difference between the current image and the historical image.

[0105] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: dividing the current image and the standard image into modules respectively to obtain multiple current module images corresponding to the current image and multiple standard module images corresponding to the standard image; decomposing the multiple current module images into pixels to obtain first module pixel data for each current module image, wherein the first module pixel data is a set of multiple first module pixels, and the multiple first module pixels are arranged in a matrix to form the current module image; decomposing the multiple standard module images to obtain second module pixel data for each standard module image, wherein the second module pixel data is a set of multiple second module pixels, and the multiple second module pixels are arranged in a matrix to form the current module image; decomposing the multiple standard module images to obtain second module pixel data for each standard module image, wherein the second module pixel data is a set of multiple second module pixels, and the multiple second module pixels are arranged in a matrix to form the current module image. Pixels are arranged in a matrix to form a standard module image. Multiple first module pixels in each group of first module pixel data are compared one by one with multiple second module pixels in the corresponding second module pixel data to obtain a second comparison result. The first and second module pixel data are correlated by the position of the current module image in the current image and the position of the standard module image in the standard image. Based on the second comparison result, the portion of first module pixels in multiple groups of first module pixel data that are identical to second module pixels is identified as an overlapping image. Based on the second comparison result, the portion of first module pixels in multiple groups of first module pixel data that are not identical to second module pixels is identified as a non-overlapping image.

[0106] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: calculating the overlap degree of each current module image based on the second comparison result, wherein the second comparison result is the comparison result obtained by comparing the current image with the standard image, and the current module image is the image obtained by dividing the current image into modules; comparing the overlap degree with the overlap degree threshold to obtain the risk level corresponding to the overlap degree; and marking each current module image with risk according to the risk level to obtain the target image.

[0107] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: generating a comparison matrix corresponding to each current module image based on the second comparison result, wherein the matrix elements of the comparison matrix correspond one-to-one with the first module pixels in the current module image, and the first module pixels are pixels obtained by pixel decomposition of the current module image; assigning values ​​to the matrix elements of each comparison matrix, wherein the first matrix elements corresponding to each first module pixel in the overlapping image are 0, and the second matrix elements corresponding to each first module pixel in the non-overlapping image are 1; calculating the overlap degree of each current module image according to the values ​​of the matrix elements using a first formula, wherein the first formula is: Where G represents the degree of overlap, n represents the number of row matrices in the alignment matrix, m represents the number of column matrices in the alignment matrix, and H represents the sum of the values ​​of all elements of the first and second matrices in the alignment matrix.

[0108] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: when the overlap degree is greater than a first overlap degree threshold and not greater than a second overlap degree threshold, determining the risk level corresponding to the overlap degree as a low-risk level, wherein the first overlap degree threshold is less than the second overlap degree threshold; when the overlap degree is greater than the second overlap degree threshold and not greater than a third overlap degree threshold, determining the risk level corresponding to the overlap degree as a medium-risk level, wherein the second overlap degree threshold is less than the third overlap degree threshold; when the overlap degree threshold is greater than the third overlap degree threshold, determining the risk level corresponding to the overlap degree as a high-risk level.

[0109] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes any of the above-described methods for identifying power grid anomalies based on a smart edge computing gateway.

[0110] According to another aspect of the present invention, a computer program product is also provided, including computer instructions, which, when executed by a processor, perform any of the above-described methods for identifying power grid anomalies based on a smart edge computing gateway.

[0111] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0117] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for identifying power grid anomalies based on an intelligent edge computing gateway, characterized in that, include: Acquire the current image of the power grid collected during the monitoring of the power grid; The current image is compared with the historical images to obtain a first comparison result, wherein the historical image is the image collected at the previous collection time point of the current collection time point, and the current collection time point is the collection time point of the current image; If the first comparison result indicates that there is no difference between the current image and the historical image, the image acquisition time point of the historical image is updated; If the first comparison result indicates that there is a difference between the current image and the historical image, the current image is compared with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image. The standard image is a reference image used for comparison and analysis of the current image. The overlapping image is the image of the repeated part between the current image and the standard image. The non-overlapping image is the image of the non-repeating part between the current image and the standard image. Remove the overlapping images from the current image; Calculate the overlap degree of the non-overlapping images, and perform risk labeling according to the overlap degree to obtain the target image; The target image is transmitted to a server so that the server can identify anomalies in the power grid based on the target image; If the first comparison result indicates a difference between the current image and the historical image, the current image is compared with a standard image to obtain overlapping and non-overlapping images between the current image and the standard image, including: The current image and the standard image are divided into modules respectively to obtain multiple current module images corresponding to the current image and multiple standard module images corresponding to the standard image; The pixels of the multiple current module images are decomposed to obtain the first module pixel data of each current module image, wherein the first module pixel data is a set of multiple first module pixels, and the multiple first module pixels are arranged in matrix form to form the current module image; The standard module images are decomposed to obtain the second module pixel data of each standard module image, wherein the second module pixel data is a set of multiple second module pixels, and the multiple second module pixels are arranged in a matrix to form the standard module image; Each set of first module pixel data is compared one by one with the corresponding second module pixel data to obtain a second comparison result. The first module pixel data and the second module pixel data are correlated by the position of the current module image in the current image and the position of the standard module image in the standard image. Based on the second comparison result, the part composed of first module pixels that are the same as the second module pixels in the multiple sets of first module pixel data is determined to be the overlapping image; Based on the second comparison result, the portion of the first module pixels that are different from the second module pixels in the multiple sets of first module pixel data is determined to be the non-overlapping image.

2. The power grid anomaly identification method based on intelligent edge computing gateway according to claim 1, characterized in that, The current image is compared with historical images to obtain a first comparison result, including: The current image is decomposed into pixels to obtain first pixel data, wherein the first pixel data is a set of multiple first pixels, and the multiple first pixels are arranged in a matrix to form the current image; The historical image is decomposed into pixels to obtain second pixel data, wherein the second pixel data is a set of multiple second pixels, and the multiple second pixels are arranged in a matrix to form the historical image; The first pixel in the first pixel data is compared one by one with the second pixel in the second pixel data to obtain the first comparison result.

3. The power grid anomaly identification method based on intelligent edge computing gateway according to claim 2, characterized in that, The first comparison result is obtained by comparing each of the first pixels in the first pixel data with each of the second pixels in the second pixel data one by one, including: When all the first pixel points and the second pixel points correspond to the same point, it is determined that the first comparison result is that there is no difference between the current image and the historical image. When at least one of the pixels differs from the second pixel, the first comparison result is determined to indicate a difference between the current image and the historical image.

4. The power grid anomaly identification method based on intelligent edge computing gateway according to claim 1, characterized in that, Calculate the overlap degree of the non-overlapping images, and perform risk labeling according to the overlap degree to obtain the target image, including: The overlap of each current module image is calculated based on the second comparison result, wherein the second comparison result is the comparison result obtained by comparing the current image with the standard image, and the current module image is the image obtained by dividing the current image into modules; The overlap degree is compared with the overlap threshold to obtain the risk level corresponding to the overlap degree; The target image is obtained by marking each current module image with a risk level according to the risk level.

5. The power grid anomaly identification method based on an intelligent edge computing gateway according to claim 4, characterized in that, The overlap of each current module image is calculated based on the second comparison result, including: Based on the second comparison result, a comparison matrix is ​​generated for each current module image, wherein the matrix elements of the comparison matrix correspond one-to-one with the first module pixels in the current module image, and the first module pixels are obtained by decomposing the current module image into pixels. The matrix elements of each of the comparison matrices are assigned values, wherein the first matrix element corresponding to each first module pixel in the overlapping image is 0, and the second matrix element corresponding to each first module pixel in the non-overlapping image is 1. The overlap degree of each current module image is calculated according to the values ​​of the matrix elements using a first formula, wherein the first formula is: Wherein, G represents the overlap degree, n represents the number of row matrices in the alignment matrix, m represents the number of column matrices in the alignment matrix, and H represents the sum of the values ​​of all the first matrix elements and the second matrix elements in the alignment matrix.

6. The power grid anomaly identification method based on an intelligent edge computing gateway according to claim 4, characterized in that, The overlap thresholds include: a first overlap threshold, a second overlap threshold, and a third overlap threshold. The overlap degree is compared with these overlap thresholds to obtain the risk level corresponding to the overlap degree, including: If the overlap degree is greater than the first overlap degree threshold and not greater than the second overlap degree threshold, the risk level corresponding to the overlap degree is determined to be a low risk level, wherein the first overlap degree threshold is less than the second overlap degree threshold. If the overlap degree is greater than the second overlap degree threshold and not greater than the third overlap degree threshold, the risk level corresponding to the overlap degree is determined to be a medium risk level, wherein the second overlap degree threshold is less than the third overlap degree threshold. If the overlap threshold is greater than the third overlap threshold, the risk level corresponding to the overlap is determined to be a high-risk level.

7. A power grid anomaly identification device based on an intelligent edge computing gateway, characterized in that, include: The first acquisition unit is used to acquire the current image of the power grid collected during the monitoring of the power grid; The second acquisition unit is used to compare the current image with the historical image to obtain a first comparison result, wherein the historical image is the image acquired at the previous acquisition time point of the current acquisition time point, and the current acquisition time point is the acquisition time point of the current image; An update unit is configured to update the image acquisition time point of the historical image when the first comparison result indicates that there is no difference between the current image and the historical image; The third acquisition unit is configured to compare the current image with a standard image when the first comparison result indicates that there is a difference between the current image and the historical image, and obtain overlapping and non-overlapping images between the current image and the standard image, wherein the standard image is a reference image used for comparison analysis of the current image, the overlapping image is the image of the repeated part between the current image and the standard image, and the non-overlapping image is the image of the non-repeating part between the current image and the standard image; The removal unit is used to remove the overlapping images in the current image; The fourth acquisition unit is used to calculate the overlap degree of the non-overlapping images and perform risk marking according to the overlap degree to obtain the target image; A transmission unit is configured to transmit the target image to a server, so that the server can identify anomalies in the power grid based on the target image; The third acquisition unit includes: a fourth acquisition module, used to divide the current image and the standard image into modules respectively, to obtain multiple current module images corresponding to the current image and multiple standard module images corresponding to the standard image; a first decomposition module, used to decompose the multiple current module images into pixels, to obtain first module pixel data for each current module image, wherein the first module pixel data is a set of multiple first module pixels, and the multiple first module pixels are arranged in a matrix to form the current module image; and a second decomposition module, used to decompose the multiple standard module images, to obtain second module pixel data for each standard module image, wherein the second module pixel data is a set of multiple second module pixels, and the multiple second module pixels are arranged in a matrix to form the current module image. The system generates a standard module image; a fifth acquisition module is used to compare multiple first module pixels in each group of first module pixel data with multiple second module pixels in the corresponding second module pixel data one by one to obtain a second comparison result, wherein the first module pixel data and the second module pixel data are correlated by the position of the current module image in the current image and the position of the standard module image in the standard image; a first determination module is used to determine, based on the second comparison result, that the part composed of first module pixels that are the same as the second module pixels in multiple groups of first module pixel data is an overlapping image; a second determination module is used to determine, based on the second comparison result, that the part composed of first module pixels that are different from the second module pixels in multiple groups of first module pixel data is a non-overlapping image.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program executes the power grid anomaly identification method based on a smart edge computing gateway as described in any one of claims 1 to 6.

9. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, the power grid anomaly identification method based on a smart edge computing gateway as described in any one of claims 1 to 6 is executed.

Images