Power quality analysis system and method based on edge computing

Abstract

The present application provides a power quality analysis system and method based on edge computing. Based on the edge computing device, the detection results of each power quality detection device are directly analyzed for abnormalities, the target detection results with abnormalities are screened out and uploaded to the central server for judgment and detection content switching. For most of the points to be detected in the power grid that are in a normal state, only less content detection and processing are required. Only a small number of points to be detected that have abnormalities and a certain abnormality level need to be switched for detection content to achieve associated detection, so as to ensure the comprehensiveness and reliability of the detection of the points to be detected with abnormalities. Through the ingenious design and combination of this solution, all aspects of transmission, processing, and detection are optimized, thereby ensuring the efficiency and reliability of power quality analysis, and then achieving effective analysis of power quality, meeting actual needs, and suitable for large-scale promotion and application.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and specifically to a power quality analysis system and method based on edge computing. Background Art

[0002] Power quality refers to the quality of electrical energy in a power system. Ideally, electrical energy should be a perfectly symmetrical sine wave. However, certain factors can cause the waveform to deviate from this symmetrical sine wave, leading to power quality issues. Key indicators for measuring power quality include voltage, frequency, and waveform. Generally speaking, it refers to high-quality power supply, encompassing voltage quality, current quality, power supply quality, and power consumption quality.

[0003] Power quality problems can be defined as deviations in voltage, current or frequency that cause electrical equipment to malfunction or malfunction. These deviations include frequency deviation, voltage deviation, voltage fluctuation and flicker, three-phase imbalance, instantaneous or transient overvoltage, waveform distortion, voltage sag, interruption, swell and power supply continuity.

[0004] With the widespread application of electric energy, power supply reliability has become a top priority in the industry, and effective analysis of power quality is an important factor in ensuring power supply reliability. Summary of the Invention

[0005] The objectives of this application include, for example, providing a power quality analysis system and method based on edge computing, which can improve the efficiency and reliability of power quality analysis.

[0006] The embodiments of the present application can be implemented as follows:

[0007] In a first aspect, the present application provides a power quality analysis system based on edge computing, the system comprising an edge computing device, a central server and a plurality of power quality detection devices respectively connected to the edge computing device for communication, wherein each of the power quality detection devices is respectively installed at each point to be detected in the power grid;

[0008] The edge computing device stores a plurality of detection contents, and is configured to send at least one detection content to each of the power quality detection devices, analyze whether the detection results obtained by each of the power quality detection devices are abnormal, upload target detection results with abnormalities to the central server, and, upon receiving detection contents to be switched for a certain target detection result sent by the central server, send the detection contents to be switched to the power quality detection device that feeds back the target detection result;

[0009] The power quality detection device is configured to receive the detection content sent by the edge computing device, perform detection of corresponding content on the point to be detected according to the detection content, and, upon receiving the detection content to be switched sent by the edge computing device, perform detection of the latest detection content on the point to be detected according to the detection content to be switched;

[0010] The central server stores the association relationship between each detection content. The central server is used to receive the target detection results uploaded by the edge computing device. When it is determined based on the target detection results that the preset conditions are met, the central server obtains the detection content to be switched based on the target detection results and sends the detection content to be switched to the edge computing device.

[0011] In an optional embodiment, the central server is used to:

[0012] Determine the abnormality level based on the target detection result, determine whether the target detection result meets the switching condition based on the abnormality level, and if the switching condition is met, determine whether the target detection result is associated with other detection content. If other detection content is associated with it, use at least one associated detection content as the detection content to be switched, and send the detection content to be switched to the edge computing device.

[0013] In an optional embodiment, each of the detection contents corresponds to multiple abnormality levels;

[0014] The central server is further configured to count the number of target detection results existing at each to-be-detected point within a set time period, and for a to-be-detected point whose target detection result exceeds a set value, calculate the overall abnormality level of the to-be-detected point based on the abnormality level of each target detection result at the to-be-detected point, and when the overall abnormality level exceeds a preset level threshold, call a pre-stored detection strategy and send it to the edge computing device;

[0015] The edge computing device is also used to receive the detection strategy sent by the central server, and send the detection strategy to the power quality detection device located at the point to be detected and / or the power quality detection devices at other points to be detected associated with the point to be detected, so that the power quality detection device can detect the point to be detected according to the detection strategy.

[0016] In an optional embodiment, the edge computing device stores an anomaly detection model, and the edge computing device analyzes whether each of the detection results is abnormal through the anomaly detection model, and the anomaly detection model is trained based on each detection content and detection result in the training data set;

[0017] The central server stores an anomaly classification model, and the central server determines the anomaly level of the target detection result through the anomaly classification model, wherein the anomaly classification model is trained based on the target detection results and the level division in the training data set.

[0018] In an optional embodiment, each abnormality level of each detection content corresponds to a different weight value;

[0019] The central server is used to obtain, for a point to be detected whose target detection result exceeds a set value, a weight value corresponding to each target detection result at the point to be detected according to the abnormality level and the detection content of each target detection result at the point to be detected, calculate the total abnormality weight value of the point to be detected according to the weight value corresponding to each target detection result at the point to be detected, and determine the overall abnormality level of the point to be detected according to the total abnormality weight value.

[0020] In an optional embodiment, the detection strategy includes performing simultaneous or sequential detection on two or more detection contents, and / or performing associated detection on other points to be detected that are associated with the point to be detected.

[0021] In an optional embodiment, the points to be detected are divided into multiple groups, the multiple groups including a set of points to be detected located on the power supply side of the power grid, a set of points to be detected located on the load side of the power grid, and a set of points to be detected located on the distribution side of the power grid;

[0022] There are multiple edge computing devices, and each power quality detection device installed at the same group of detection points is connected to at least one edge computing device. The central server stores the association relationship between each edge computing device and the connected power quality detection devices, as well as the association relationship between each power quality detection device and the detection point.

[0023] In an optional embodiment, the central server further stores an abnormal situation analysis model;

[0024] The central server is also used to find out the group to which the to-be-detected point belongs, and other to-be-detected points in the group that are associated with the to-be-detected point, when there is a to-be-detected point whose overall abnormality level exceeds a preset level threshold, determine whether there are target detection results for other to-be-detected points, input all target detection results of the to-be-detected point and other to-be-detected points associated with the to-be-detected point into the abnormal situation analysis model, and analyze and obtain abnormal lines in the power grid.

[0025] In an optional embodiment, each of the power quality detection devices is integrated with a monitoring module;

[0026] The central server is further configured to issue detection content adjustment instructions and status detection instructions to the edge computing device, wherein the detection content adjustment instructions include adding, deleting, and modifying detection content;

[0027] The edge computing device is also used to make corresponding adjustments to the detection content in the power quality detection device when receiving a detection content adjustment instruction issued by the central server, and to detect the working status and version of the power quality detection device based on the monitoring module when receiving a status detection instruction issued by the central server, and to analyze whether there is a target power quality detection device with an abnormal status or requiring a version update. If the target power quality detection device exists, the target power quality detection device is fed back to the central server.

[0028] In a second aspect, the present application provides a power quality analysis method based on edge computing, which is applied to the power quality analysis system described in any one of the aforementioned embodiments, and the method includes:

[0029] The edge computing device sends at least one detection content to each power quality detection device;

[0030] The power quality detection device is used to receive the detection content sent by the edge computing device, and perform corresponding content detection on the point to be detected according to the detection content;

[0031] The edge computing device analyzes whether there are any abnormalities in the detection results obtained by the power quality detection devices, and uploads the target detection results with abnormalities to the central server;

[0032] The central server is configured to receive the target detection result uploaded by the edge computing device, and when it is determined based on the target detection result that a preset condition is met, obtain the detection content to be switched according to the target detection result, and send the detection content to be switched to the edge computing device;

[0033] The edge computing device receives the detection content to be switched sent by the central server for a certain target detection result, and sends the detection content to be switched to the power quality detection device that feeds back the target detection result;

[0034] The power quality detection device receives the detection content to be switched sent by the edge computing device, and detects the latest detection content of the point to be detected based on the detection content to be switched.

[0035] The beneficial effects of the embodiments of the present application include, for example:

[0036] The present application provides a power quality analysis system and method based on edge computing, which directly performs abnormal analysis on the detection results of each power quality detection device based on the edge computing device, filters out the target detection results with abnormalities and uploads them to the central server for judgment and detection content switching, thereby avoiding the network transmission pressure caused by the transmission and processing of a large number of detection results of each power quality detection device, and improving the transmission efficiency. For most of the points to be detected in the power grid that are in a normal state, only less content detection and processing are required, and only a small number of points to be detected that have abnormalities and have a certain abnormality level need to be switched to realize associated detection to ensure the comprehensiveness and reliability of the detection of the points to be detected that have abnormalities. Through the ingenious design and combination of this solution, all aspects of transmission, processing, and detection are optimized, thereby ensuring the efficiency and reliability of power quality analysis, and then realizing effective analysis of power quality, meeting actual needs, and suitable for large-scale promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 One of the structural block diagrams of power quality analysis based on edge computing provided in an embodiment of the present application;

[0039] Figure 2 The second structural block diagram of power quality analysis based on edge computing provided in an embodiment of the present application;

[0040] Figure 3 The third structural block diagram of power quality analysis based on edge computing provided in an embodiment of the present application;

[0041] Figure 4 A flowchart of a power quality analysis method based on edge computing provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0043] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0044] It should be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not preclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0045] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not require further definition or explanation in subsequent drawings.

[0046] It should be noted that, in the absence of conflict, the features in the embodiments of this application can be combined with each other.

[0047] See also Figure 1 , which is a block diagram of the structure of the edge computing-based power quality analysis system provided in an embodiment of the present application. The power quality analysis system includes an edge computing device, a central server in communication with the edge computing device, and multiple power quality detection devices, each of which is installed at a respective point to be detected in the power grid.

[0048] Among them, the edge computing device stores multiple detection contents, and the edge computing device can be used to send at least one detection content to each of the power quality detection devices, analyze whether there are abnormalities in the detection results obtained by each of the power quality detection devices, and upload the target detection results with abnormalities to the central server. When receiving the detection content to be switched sent by the central server for a certain target detection result, the detection content to be switched is sent to the power quality detection device that feeds back the target detection result.

[0049] The power quality detection device is used to receive the detection content sent by the edge computing device, perform corresponding content detection on the point to be detected according to the detection content, and when receiving the detection content to be switched sent by the edge computing device, perform the latest detection content detection on the point to be detected according to the detection content to be switched.

[0050] The central server stores the association relationship between each detection content. The central server is used to receive the target detection results uploaded by the edge computing device. When it is determined based on the target detection results that the preset conditions are met, the central server obtains the detection content to be switched based on the target detection results and sends the detection content to be switched to the edge computing device.

[0051] The power quality analysis system provided in this embodiment optimizes transmission, processing, and detection through the ingenious design and integration of power quality detection equipment, edge computing equipment, and central servers, thereby ensuring the efficiency and reliability of power quality analysis and achieving effective analysis of power quality.

[0052] In detail, in this embodiment, the central server can be used to determine the abnormality level based on the target detection result, determine whether the target detection result meets the switching condition based on the abnormality level, and if the switching condition is met, determine whether the target detection result is associated with other detection content. If other detection content is associated, at least one associated detection content is used as the detection content to be switched, and the detection content to be switched is sent to the edge computing device.

[0053] In the above example, each test point can be equipped with a power quality test device. The number and location of test points can be flexibly set based on the power quality analysis requirements in each scenario. The test points can be flexibly distributed in various areas of the power grid.

[0054] Depending on the number and distribution range of power quality detection devices, the edge computing device can be set to one or more. For example, if the number of power quality detection devices is small, such as less than the set amount, only one edge computing device can be set. If the number of power quality detection devices is large, such as more than the set amount, more than two edge computing devices can be set to meet the processing efficiency, for example Figure 2 As shown in . For another example, if the power quality monitoring devices are concentrated, such as if they are all within a set distance range, only one edge computing device can be deployed. If the power quality monitoring devices are widely distributed, such as if they exceed the set distance range, multiple edge computing devices can be deployed, each located in a different area, and each edge computing device interacts with each power quality monitoring device in a specific area.

[0055] Exemplarily, the points to be detected can be divided into multiple groups, and the group division method can be flexibly selected. For example, the groups can be divided according to quantity, distance, customization, etc. In one implementation method, the multiple groups may include a set of points to be detected located on the power supply side of the power grid, a set of points to be detected located on the load side of the power grid, and a set of points to be detected located on the distribution side of the power grid. Accordingly, there can be multiple edge computing devices, and each power quality detection device installed at the point to be detected in the same group is connected to at least one of the edge computing devices. For example, an edge computing device can be set on the power supply side, the load side, and the distribution side, respectively, and each edge computing device performs data exchange processing with each power quality detection device in the area where it is located.

[0056] The central server can store the association between each edge computing device and each connected power quality detection device, as well as the association between each power quality detection device and the detection point. Based on the set association, the central server can determine the detection point to which each detection result belongs.

[0057] In this embodiment, the detection content can be flexibly selected, for example, it can include one or a combination of two or more of frequency deviation, voltage deviation, voltage fluctuation and flicker, three-phase imbalance, instantaneous or transient overvoltage, waveform distortion (harmonics), voltage sag, interruption, swell, and power supply continuity. For each detection content, the standard can be flexibly set according to the specific requirements of the power quality in the application scenario, for example, setting a standard threshold and a standard range, so that detection results exceeding the standard threshold or outside the standard range are regarded as target detection results with abnormalities.

[0058] Given that abnormal detection results may be short-lived and small in magnitude, with no significant impact on power quality, or they may be long-lasting and large in magnitude, potentially causing significant abnormalities in power quality, applying the same treatment to all abnormalities of varying severity would waste resources. To achieve refined handling of abnormalities, in this embodiment, each detection condition may correspond to multiple abnormality levels, with separate analyses performed for each abnormality level.

[0059] The central server is also used to count the number of target detection results at each point to be detected within a set time period. For the points to be detected whose target detection results exceed the set value, the overall abnormality level of the point to be detected is calculated based on the abnormality level of each target detection result at the point to be detected. When the overall abnormality level exceeds the preset level threshold, the pre-stored detection strategy is called and sent to the edge computing device.

[0060] The edge computing device is also used to receive the detection strategy sent by the central server, and send the detection strategy to the power quality detection device located at the point to be detected and / or the power quality detection devices at other points to be detected associated with the point to be detected, so that the power quality detection device can detect the point to be detected according to the detection strategy.

[0061] The central server can store the associations between various test items. These associations can be obtained through big data collection and statistical analysis of various power quality issues. For example, if a power quality issue exists, test items A, B, and C will have problems in sequence. In this case, test items A, B, and C can be associated in sequence. For another example, if a power quality issue exists, test items A and D will have problems at the same time. In this case, test items A and D can be associated simultaneously.

[0062] By setting the association between each detection content, in the initial state, each power quality detection device can be controlled to only perform a few items, such as the detection of one or two detection contents. For example, if no abnormality is detected, each power quality detection device installed at each detection point in the same group is controlled to detect a different detection content respectively, thereby reducing the amount of detection data under normal power supply status and alleviating the processing load of edge computing equipment.

[0063] When an abnormal target detection result is detected and the abnormality level exceeds the preset level threshold, the decision on whether to switch the detection content is made based on the association between the various detection contents. For example, the abnormality level of a certain detection content may be level five, and the detection content is associated with detection content B and detection content C. The central server can set the abnormality level to level one or level two, without any processing, and continue to detect according to the original detection content; when the abnormality level is level three, detection content B is used as the detection content to be switched; when the abnormality level is level four, detection content B and detection content C are used as the detection content to be switched; when the abnormality level is level five, the detection content, detection content B, and detection content C are all used as the detection content to be switched.

[0064] Based on the above design, the data transmission and processing volume can be significantly reduced while taking into account the reliability of power quality analysis.

[0065] In order to further improve the efficiency of power quality analysis, model training can be performed in advance, and various analysis processes can be performed based on the trained model.

[0066] For example, an anomaly detection model may be stored in the edge computing device, and the edge computing device analyzes whether each of the detection results is abnormal using the anomaly detection model. The anomaly detection model is trained based on each detection content and detection result in the training data set.

[0067] For another example, the central server may store an anomaly classification model, and the central server determines the anomaly level of the target detection result using the anomaly classification model, wherein the anomaly classification model is trained based on the target detection results and the classification in the training data set.

[0068] For another example, the central server may store an abnormal situation analysis model, and the central server is also used to find out the group to which the detection point belongs and other detection points in the group that are associated with the detection point when there is a detection point whose overall abnormality level exceeds a preset level threshold, determine whether there are target detection results for other detection points, input all target detection results of the detection point and other detection points associated with the detection point into the abnormal situation analysis model, and analyze and obtain abnormal lines in the power grid.

[0069] In this embodiment, the anomaly detection model, anomaly classification model, and anomaly analysis model can be flexibly selected. For example, various network models such as convolutional network models, neural network models, and deep network models can be used for training. For example, they can be trained using corresponding content in the training and test datasets.

[0070] By setting up the model, edge computing devices and central servers can efficiently and reliably perform analysis and processing based on the stored model, further improving processing efficiency.

[0071] Since the power quality monitoring equipment can continuously detect abnormal target detection results at the detection point, the edge computing device will upload multiple target detection results for the detection point to the central server. When the edge computing device sends the detection content to be switched to the power quality monitoring equipment, the detection point may have more than two target detection results.

[0072] Based on this, in order to reliably analyze the overall abnormality of each point to be detected, each abnormality level of each detection content can be assigned a different weight value. The central server is also used to obtain the weight value corresponding to each target detection result at the point to be detected for which the target detection result exceeds the set value, based on the abnormality level and the detection content of each target detection result at the point to be detected, calculate the total abnormality weight value of the point to be detected based on the weight value corresponding to each target detection result at the point to be detected, and determine the overall abnormality level of the point to be detected based on the total abnormality weight value.

[0073] Determine whether the overall abnormality level exceeds a preset level threshold. If it exceeds the preset level threshold, call a pre-stored detection strategy and send it to the edge computing device.

[0074] In this embodiment, weight values ​​can be flexibly set. Based on the corresponding weight values, the total abnormality weight of the detected point is calculated, and the overall abnormality level of the detected point is determined based on the total abnormality weight. If the overall abnormality level exceeds the preset level threshold, the pre-stored detection strategy is further invoked. Based on this approach, a "multi-level" hierarchical and multi-dimensional processing is implemented based on the abnormal situation, thereby ensuring detection efficiency while maximizing the reliability of power quality analysis.

[0075] The detection strategy may include simultaneous or sequential detection of two or more detection items, and / or performing associated detection on other detection points associated with the detection point. By performing associated detection on other detection points associated with the detection point, the reliability of the detection and the comprehensiveness of the analysis are ensured.

[0076] See also Figure 3 To improve implementation convenience and flexibility, in one implementation, each power quality detection device integrates a monitoring module. The central server is further configured to issue detection content adjustment instructions and status detection instructions to the edge computing device; the detection content adjustment instructions include adding, deleting, and modifying detection content.

[0077] The edge computing device is also used to make corresponding adjustments to the detection content in the power quality detection device when it receives a detection content adjustment instruction issued by the central server; when it receives a status detection instruction issued by the central server, it detects the working status and version of the power quality detection device based on the monitoring module, analyzes whether there is a target power quality detection device with an abnormal status or that needs a version update, and if the target power quality detection device exists, feeds back the target power quality detection device to the central server.

[0078] On the basis of the above, the embodiment of the present application also provides a power quality analysis method based on edge computing, which is applied to the power quality analysis system based on edge computing. Figure 4 , the method includes S110 to S160.

[0079] In step S110, the edge computing device sends at least one detection content to each power quality detection device.

[0080] In step S120, the power quality detection device is used to receive the detection content sent by the edge computing device, and perform corresponding content detection on the point to be detected based on the detection content.

[0081] In step S130, the edge computing device analyzes whether there is any abnormality in the detection results obtained by each of the power quality detection devices, and uploads the target detection results with abnormalities to the central server.

[0082] In step S140, the central server is used to receive the target detection result uploaded by the edge computing device. When it is determined based on the target detection result that a preset condition is met, the central server obtains the detection content to be switched based on the target detection result, and sends the detection content to be switched to the edge computing device.

[0083] In step S150 , the edge computing device receives the detection content to be switched sent by the central server for a certain target detection result, and sends the detection content to be switched to the power quality detection device that feeds back the target detection result.

[0084] In step S160, the power quality detection device receives the detection content to be switched sent by the edge computing device, and detects the latest detection content of the point to be detected based on the detection content to be switched.

[0085] In the above step S140, the central server determines the abnormality level based on the target detection result, and determines whether the target detection result meets the switching condition based on the abnormality level. If the switching condition is met, it determines whether the target detection result is associated with other detection content. If other detection content is associated, at least one associated detection content is used as the detection content to be switched, and the detection content to be switched is sent to the edge computing device.

[0086] Each of the detection contents corresponds to an abnormality level, and the method further includes:

[0087] The central server counts the number of target detection results at each to-be-detected point within a set time period, and for a to-be-detected point whose target detection result exceeds a set value, calculates the overall abnormality level of the to-be-detected point based on the abnormality level of each target detection result at the to-be-detected point, and calls a pre-stored detection strategy and sends it to the edge computing device when the overall abnormality level exceeds a preset level threshold;

[0088] The edge computing device receives the detection strategy sent by the central server, and sends the detection strategy to the power quality detection device located at the point to be detected and / or the power quality detection devices at other points to be detected associated with the point to be detected, so that the power quality detection device detects the point to be detected according to the detection strategy.

[0089] Among them, each abnormality level of each detection content corresponds to a different weight value. In the above step of determining the overall abnormality level, in detail, the central server obtains the weight value corresponding to each target detection result at the to-be-detected point for which the target detection result exceeds the set value, based on the abnormality level and the detection content of each target detection result at the to-be-detected point, calculates the total abnormality weight value of the to-be-detected point based on the weight value corresponding to each target detection result at the to-be-detected point, and determines the overall abnormality level of the to-be-detected point based on the said total abnormality weight value.

[0090] Furthermore, the points to be detected are divided into multiple groups, which include a set of points to be detected located on the power supply side of the power grid, a set of points to be detected located on the load side of the power grid, and a set of points to be detected located on the distribution side of the power grid.

[0091] There are multiple edge computing devices, and each power quality detection device installed at the same group of detection points is connected to at least one edge computing device. The central server stores the association between each edge computing device and each connected power quality detection device, as well as the association between each power quality detection device and the detection point. The central server stores an abnormal situation analysis model. The method further includes:

[0092] When there is a point to be detected whose overall abnormality level exceeds a preset level threshold, the central server finds out the group to which the point to be detected belongs, as well as other points to be detected in the group that are associated with the point to be detected, determines whether there are target detection results for other points to be detected, inputs all target detection results of the point to be detected and other points to be detected that are associated with the point to be detected into the abnormal situation analysis model, and analyzes to obtain abnormal lines in the power grid.

[0093] The power quality analysis solution in the embodiment of the present application can conveniently and efficiently achieve reliable analysis of power quality from multiple levels and dimensions.

[0094] The power quality analysis method provided in this embodiment is implemented based on the above-mentioned power quality analysis system and has the same, similar or corresponding technical features as the above-mentioned power quality analysis system. Therefore, for the details not provided in this embodiment, please refer to the relevant description of the above-mentioned power quality analysis system, and this embodiment will not be repeated here.

[0095] To summarize, the edge computing-based power quality analysis system and method provided in the embodiments of the present application directly perform abnormality analysis on the detection results of each power quality detection device based on the edge computing device, screen out the target detection results with abnormalities and upload them to the central server for analysis and processing of the abnormality level, whether the switching conditions are met, and the detection content to be switched, thereby avoiding the network transmission pressure caused by the transmission and processing of a large number of detection results of each power quality detection device, thereby improving the transmission efficiency.

[0096] The edge computing device and the central server jointly perform hierarchical processing of the detection results, thereby reducing the processing pressure of each level of equipment and improving the overall processing efficiency. The central server subdivides the target detection results into abnormality levels, and determines whether the switching conditions are met based on the abnormality level. When the switching conditions are met and other detection contents are associated, the associated detection contents are used as the detection contents to be switched, so that the power quality detection equipment performs detection according to the latest detection content to be switched. Based on this design, for most of the points to be detected in the power grid that are in a normal state, only less content detection and processing is required. Only a small number of points to be detected that have abnormalities and a certain abnormality level need to be switched to detect content to achieve associated detection, so as to ensure the comprehensiveness and reliability of the detection of the points to be detected that have abnormalities. Through the ingenious design and combination of the above technical solutions, all aspects of transmission, processing, and detection are optimized, thereby ensuring the efficiency and reliability of power quality analysis, and then achieving effective analysis of power quality, which meets actual needs and is suitable for large-scale promotion and application.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0098] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0099] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0100] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A power quality analysis system based on edge computing, characterized in that: The system includes an edge computing device, a central server and a plurality of power quality detection devices respectively connected to the edge computing device for communication, wherein each of the power quality detection devices is respectively installed at each point to be detected in the power grid; The edge computing device stores a plurality of detection contents, and is configured to send at least one detection content to each of the power quality detection devices, analyze whether the detection results obtained by each of the power quality detection devices are abnormal, upload target detection results with abnormalities to the central server, and, upon receiving detection contents to be switched for a certain target detection result sent by the central server, send the detection contents to be switched to the power quality detection device that feeds back the target detection result; The power quality detection device is configured to receive the detection content sent by the edge computing device, perform detection of corresponding content on the point to be detected according to the detection content, and, upon receiving the detection content to be switched sent by the edge computing device, perform detection of the latest detection content on the point to be detected according to the detection content to be switched; The central server stores associations between various detection contents, and is configured to receive target detection results uploaded by the edge computing device, and when it is determined based on the target detection results that a preset condition is met, obtain the detection content to be switched based on the target detection results, and send the detection content to be switched to the edge computing device; The central server is used for: Determine the abnormality level based on the target detection result, determine whether the target detection result meets the switching condition based on the abnormality level, and if the switching condition is met, determine whether the target detection result is associated with other detection content. If other detection content is associated with it, use at least one associated detection content as the detection content to be switched, and send the detection content to be switched to the edge computing device.

2. The power quality analysis system based on edge computing according to claim 1, characterized in that: Each of the detection contents corresponds to multiple abnormality levels; The central server is further configured to count the number of target detection results existing at each to-be-detected point within a set time period, and for a to-be-detected point whose target detection result exceeds a set value, calculate the overall abnormality level of the to-be-detected point based on the abnormality level of each target detection result at the to-be-detected point, and when the overall abnormality level exceeds a preset level threshold, call a pre-stored detection strategy and send it to the edge computing device; The edge computing device is also used to receive the detection strategy sent by the central server, and send the detection strategy to the power quality detection device located at the point to be detected and / or the power quality detection devices at other points to be detected associated with the point to be detected, so that the power quality detection device can detect the point to be detected according to the detection strategy.

3. The power quality analysis system based on edge computing according to claim 2, characterized in that: The edge computing device stores an anomaly detection model, and the edge computing device analyzes whether each of the detection results has an anomaly through the anomaly detection model, wherein the anomaly detection model is trained based on each detection content and detection result in the training data set; The central server stores an anomaly classification model, and the central server determines the anomaly level of the target detection result through the anomaly classification model, wherein the anomaly classification model is trained based on the target detection results and the level division in the training data set.

4. The power quality analysis system based on edge computing according to claim 2, characterized in that: Each abnormality level of each detection content corresponds to a different weight value; The central server is used to obtain, for a point to be detected whose target detection result exceeds a set value, a weight value corresponding to each target detection result at the point to be detected according to the abnormality level and the detection content of each target detection result at the point to be detected, calculate the total abnormality weight value of the point to be detected according to the weight value corresponding to each target detection result at the point to be detected, and determine the overall abnormality level of the point to be detected according to the total abnormality weight value.

5. The power quality analysis system based on edge computing according to claim 2, characterized in that: The detection strategy includes performing simultaneous or sequential detection on two or more detection contents, and / or performing associated detection on other to-be-detected points associated with the to-be-detected point.

6. The power quality analysis system based on edge computing according to claim 2, characterized in that: The points to be detected are divided into a plurality of groups, wherein the plurality of groups include a set of points to be detected located on the power supply side of the power grid, a set of points to be detected located on the load side of the power grid, and a set of points to be detected located on the distribution side of the power grid; There are multiple edge computing devices, and each power quality detection device installed at the same group of detection points is connected to at least one edge computing device. The central server stores the association relationship between each edge computing device and the connected power quality detection devices, as well as the association relationship between each power quality detection device and the detection point.

7. The power quality analysis system based on edge computing according to claim 6, characterized in that: The central server also stores an abnormal situation analysis model; The central server is also used to find out the group to which the to-be-detected point belongs, and other to-be-detected points in the group that are associated with the to-be-detected point, when there is a to-be-detected point whose overall abnormality level exceeds a preset level threshold, determine whether there are target detection results for other to-be-detected points, input all target detection results of the to-be-detected point and other to-be-detected points associated with the to-be-detected point into the abnormal situation analysis model, and analyze and obtain abnormal lines in the power grid.

8. The power quality analysis system based on edge computing according to claim 1, characterized in that: Each of the power quality detection devices is integrated with a monitoring module; The central server is further configured to issue detection content adjustment instructions and status detection instructions to the edge computing device, wherein the detection content adjustment instructions include adding, deleting, and modifying detection content; The edge computing device is also used to make corresponding adjustments to the detection content in the power quality detection device when receiving a detection content adjustment instruction issued by the central server, and to detect the working status and version of the power quality detection device based on the monitoring module when receiving a status detection instruction issued by the central server, and to analyze whether there is a target power quality detection device with an abnormal status or requiring a version update. If the target power quality detection device exists, the target power quality detection device is fed back to the central server.

9. A power quality analysis method based on edge computing, characterized in that: Applied to the power quality analysis system according to any one of claims 1 to 8, the method comprising: The edge computing device sends at least one detection content to each power quality detection device; The power quality detection device is used to receive the detection content sent by the edge computing device, and perform corresponding content detection on the point to be detected according to the detection content; The edge computing device analyzes whether there are any abnormalities in the detection results obtained by the power quality detection devices, and uploads the target detection results with abnormalities to the central server; The central server is configured to receive the target detection result uploaded by the edge computing device, and when it is determined based on the target detection result that a preset condition is met, obtain the detection content to be switched according to the target detection result, and send the detection content to be switched to the edge computing device; The edge computing device receives the detection content to be switched sent by the central server for a certain target detection result, and sends the detection content to be switched to the power quality detection device that feeds back the target detection result; The power quality detection device receives the detection content to be switched sent by the edge computing device, and detects the latest detection content of the point to be detected based on the detection content to be switched.

Images