Grid Edge Cluster Monitoring Method Based on Cloud-Edge Fusion Intelligent Scheduling and Operation Platform

Abstract

This application relates to a power grid edge cluster monitoring method based on a cloud-edge fusion intelligent scheduling operation platform. The method includes: obtaining edge cluster monitoring data corresponding to the power grid edge cluster according to the data monitoring rule data of the power grid edge cluster; performing abnormal data inspection on the edge cluster monitoring data to obtain data inspection information corresponding to the power grid edge cluster; extracting edge cluster abnormal data from the edge cluster monitoring data when the data inspection information indicates that there is abnormal data in the edge cluster monitoring data; inputting the edge cluster abnormal data into an abnormal data analysis model of the power grid edge cluster to obtain abnormal data analysis information; and generating cluster monitoring policy information corresponding to the power grid edge cluster according to the abnormal data analysis information. By using this method, the state of "detecting when it should be detected" can be achieved, and the efficiency of discovering abnormal situations in the power grid edge cluster is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technologies, and in particular, to a method, apparatus, computer device, storage medium, and computer program product for monitoring a power grid edge cluster based on a cloud-edge fusion intelligent scheduling operation platform. Background Art

[0002] With the development of computer technologies, an intelligent power grid monitoring platform has emerged. This monitoring platform is based on an integrated, high-speed two-way communication network, and through the application of advanced sensing and measurement technologies, advanced equipment technologies, advanced control methods, and advanced decision support system technologies, it realizes a fully digital information transmission and management system based on the intelligent power grid. On the basis of the construction of the intelligent power grid monitoring platform, a power grid edge cluster has emerged as an intermediate medium between the intelligent power grid monitoring platform and power grid equipment.

[0003] However, during the use of the power grid edge cluster, abnormal situations are inevitable. Therefore, the monitoring of the power grid edge cluster is particularly important. In traditional technologies, the operation mode of "periodic monitoring" is adopted to monitor the power grid edge cluster. However, since this mode not only consumes time and effort in the monitoring process and has a long cycle, but also the reliability and real-time performance of the monitoring results are poor, resulting in low efficiency in discovering abnormal situations of the power grid edge cluster. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for monitoring a power grid edge cluster based on a cloud-edge fusion intelligent scheduling operation platform, which can improve the efficiency of discovering abnormal situations of the power grid edge cluster.

[0005] In a first aspect, the present application provides a method for monitoring a power grid edge cluster based on a cloud-edge fusion intelligent scheduling operation platform. The method includes: obtaining edge cluster monitoring data corresponding to the power grid edge cluster according to data monitoring rule data of the power grid edge cluster; performing abnormal data inspection on the edge cluster monitoring data to obtain data inspection information corresponding to the power grid edge cluster; in the case where the data inspection information indicates that there is abnormal data in the edge cluster monitoring data, extracting edge cluster abnormal data from the edge cluster monitoring data; inputting the edge cluster abnormal data into an abnormal data analysis model of the power grid edge cluster to obtain abnormal data analysis information; and generating cluster monitoring policy information corresponding to the power grid edge cluster according to the abnormal data analysis information.

[0006] In a second aspect, the present application further provides a power grid edge cluster monitoring device based on a cloud-edge fusion intelligent scheduling operation platform. The device includes: a monitoring data acquisition module, configured to acquire edge cluster monitoring data corresponding to the power grid edge cluster according to data monitoring rule data for the power grid edge cluster; an abnormal data inspection module, configured to perform abnormal data inspection on the edge cluster monitoring data to obtain data inspection information corresponding to the power grid edge cluster; an abnormal data extraction module, configured to extract edge cluster abnormal data from the edge cluster monitoring data when the data inspection information indicates that there is abnormal data in the edge cluster monitoring data; an abnormal data analysis module, configured to input the edge cluster abnormal data into an abnormal data analysis model of the power grid edge cluster to obtain abnormal data analysis information; and a monitoring policy generation module, configured to generate cluster monitoring policy information corresponding to the power grid edge cluster according to the abnormal data analysis information.

[0007] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: acquiring edge cluster monitoring data corresponding to the power grid edge cluster according to data monitoring rule data for the power grid edge cluster; performing abnormal data inspection on the edge cluster monitoring data to obtain data inspection information corresponding to the power grid edge cluster; extracting edge cluster abnormal data from the edge cluster monitoring data when the data inspection information indicates that there is abnormal data in the edge cluster monitoring data; inputting the edge cluster abnormal data into an abnormal data analysis model of the power grid edge cluster to obtain abnormal data analysis information; and generating cluster monitoring policy information corresponding to the power grid edge cluster according to the abnormal data analysis information.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the following steps are implemented: acquiring edge cluster monitoring data corresponding to the power grid edge cluster according to data monitoring rule data for the power grid edge cluster; performing abnormal data inspection on the edge cluster monitoring data to obtain data inspection information corresponding to the power grid edge cluster; extracting edge cluster abnormal data from the edge cluster monitoring data when the data inspection information indicates that there is abnormal data in the edge cluster monitoring data; inputting the edge cluster abnormal data into an abnormal data analysis model of the power grid edge cluster to obtain abnormal data analysis information; and generating cluster monitoring policy information corresponding to the power grid edge cluster according to the abnormal data analysis information.

[0009] Fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program which, when executed by a processor, implements the following steps: obtaining edge cluster monitoring data corresponding to the grid edge cluster according to data monitoring rule data of the grid edge cluster; performing abnormal data inspection on the edge cluster monitoring data to obtain data inspection information corresponding to the grid edge cluster; extracting edge cluster abnormal data from the edge cluster monitoring data when the data inspection information indicates that there is abnormal data in the edge cluster monitoring data; inputting the edge cluster abnormal data into an abnormal data analysis model of the grid edge cluster to obtain abnormal data analysis information; and generating cluster monitoring policy information corresponding to the grid edge cluster according to the abnormal data analysis information.

[0010] The above-mentioned grid edge cluster monitoring method, device, computer device, storage medium and computer program product based on a cloud-edge fusion intelligent scheduling operation platform obtain edge cluster monitoring data corresponding to the grid edge cluster according to data monitoring rule data of the grid edge cluster; perform abnormal data inspection on the edge cluster monitoring data to obtain data inspection information corresponding to the grid edge cluster; extract edge cluster abnormal data from the edge cluster monitoring data when the data inspection information indicates that there is abnormal data in the edge cluster monitoring data; input the edge cluster abnormal data into an abnormal data analysis model of the grid edge cluster to obtain abnormal data analysis information; and generate cluster monitoring policy information corresponding to the grid edge cluster according to the abnormal data analysis information.

[0011] By performing abnormal data inspection on the edge cluster monitoring data, if abnormal data is found, inferential analysis and status evaluation are performed on the abnormal data to obtain abnormal data analysis information of the grid edge cluster and generate cluster monitoring policy information. It can give full play to the big data normal monitoring of the cloud-edge fusion intelligent scheduling operation platform for the vertical disturbance discrimination and horizontal comparison and investigation of the grid edge cluster, lock the faults of the grid edge cluster, achieve the state of "inspecting when it should be inspected", and improve the discovery efficiency of abnormal situations of the grid edge cluster. Description of the Drawings

[0012] Figure 1 It is an application environment diagram of a grid edge cluster monitoring method based on a cloud-edge fusion intelligent scheduling operation platform in an embodiment;

[0013] Figure 2 It is a flowchart of a grid edge cluster monitoring method based on a cloud-edge fusion intelligent scheduling operation platform in an embodiment;

[0014] Figure 3 It is a flowchart of a method for obtaining data inspection information in an embodiment;

[0015] Figure 4 It is a schematic flowchart of a method for extracting abnormal data of an edge cluster in an embodiment;

[0016] Figure 5 It is a schematic flowchart of a method for obtaining abnormal data analysis information in an embodiment;

[0017] Figure 6 It is a schematic flowchart of a method for obtaining data for analyzing the continuous operation state of a cluster in an embodiment;

[0018] Figure 7 It is a schematic flowchart of a method for obtaining cluster monitoring policy information in an embodiment;

[0019] Figure 8 It is a schematic flowchart of a method for generating device rejection strategy information in an embodiment;

[0020] Figure 9 It is a schematic diagram of a monitoring interface of a power grid edge cluster in an embodiment;

[0021] Figure 10 It is a structural block diagram of a power grid edge cluster monitoring device based on a cloud-edge fusion intelligent scheduling operation platform in an embodiment;

[0022] Figure 11 It is an internal structure diagram of a computer device in an embodiment. Specific embodiments

[0023] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0024] A power grid edge cluster monitoring method provided by an embodiment of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the grid edge cluster 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 obtains the edge cluster monitoring data corresponding to the grid edge cluster according to the data monitoring rule data for the grid edge cluster; performs abnormal data inspection on the edge cluster monitoring data to obtain the data inspection information corresponding to the grid edge cluster; in the case where the data inspection information indicates that there is abnormal data in the edge cluster monitoring data, extracts the edge cluster abnormal data from the edge cluster monitoring data; inputs the edge cluster abnormal data into the abnormal data analysis model of the grid edge cluster to obtain the abnormal data analysis information; and generates the cluster monitoring policy information corresponding to the grid edge cluster according to the abnormal data analysis information. Among them, the grid edge cluster 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0025] In one embodiment, as Figure 2 shown, a method for monitoring a grid edge cluster based on a cloud-edge fusion intelligent scheduling operation platform is provided. Taking the server in Figure 1 as an example, the method includes the following steps:

[0026] Step 202, obtain the edge cluster monitoring data corresponding to the grid edge cluster according to the data monitoring rule data for the grid edge cluster.

[0027] Among them, the grid edge cluster can be a set of computing nodes located at the edge of the computing architecture or close to the power grid data source. These computing nodes are usually located at distributed positions in power grid devices, such as power generation stations, substations, transmission lines, etc., rather than concentrated in the cloud-edge fusion intelligent scheduling operation platform.

[0028] Among them, the data monitoring rule data can be the rules for the cloud-edge fusion intelligent scheduling operation platform to monitor the grid edge cluster. Among them, the cloud-edge fusion intelligent scheduling operation platform can be a resource scheduling platform with two-level collaborative operation of "cloud brain + edge nodes".

[0029] Among them, the edge cluster monitoring data can be the monitoring data collected by the cloud-edge fusion intelligent scheduling operation platform during the operation of the grid edge cluster.

[0030] Specifically, data monitoring rule data of the grid edge cluster is input into the server 104 through a terminal. Among them, the data monitoring rule data is determined according to the requirement of "inspecting when it should be inspected" for the grid edge cluster. Therefore, the data monitoring rule data can be dynamic monitoring rule data or static monitoring rule data. Among them, the dynamic monitoring rule data can be a monitoring rule that changes in real time along with the operation data collected in real time from the grid edge cluster, and the static monitoring rule data can be a monitoring rule determined according to the operation data of the grid edge cluster in the recent three months. On the premise that the data monitoring rule data of the grid edge cluster is used as a constraint condition, the server 104 obtains the edge cluster monitoring data corresponding to the grid edge cluster from the grid edge cluster 102 through data interaction with the grid edge cluster 102, and stores the obtained edge cluster monitoring data in the storage unit. When the server needs to process the edge cluster monitoring data, it is retrieved from the storage unit to the volatile storage resource for the central processing unit to perform calculations. Among them, the edge cluster monitoring data can be a single data input into the central processing unit, or multiple data can be input into the central processing unit simultaneously.

[0031] Step 204: Check the abnormal data in the edge cluster monitoring data to obtain the data check information corresponding to the grid edge cluster.

[0032] Among them, the data check information can be the check data generated by checking the abnormal data in the edge cluster monitoring data. Among them, the data check information includes the check information of the normal data, the check information of the abnormal data, and the check information of the suspicious data in the edge cluster monitoring data, etc.

[0033] Specifically, expand the edge cluster monitoring data to obtain cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data. Among them, the cluster base monitoring data can be the detection data collected during the operation of the base of the power grid edge cluster; the cluster artifact monitoring data can be the detection data collected during the operation of the power grid artifacts of the power grid edge cluster; the cluster application monitoring data can be the detection data collected during the interaction of the application programs of the power grid edge cluster; the cluster resource monitoring data can be the detection data of the resource changes during the operation of the power grid edge cluster. First: When the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data are all static, combine the data monitoring rule data and the artifact characteristic parameter information of the power grid edge cluster, and perform random permutations and combinations according to at least one of the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data to determine the abnormal data check sequence for the edge cluster monitoring data. At this time, the abnormal data check sequence is static (that is, the abnormal data check sequence does not change within a period of time). For example: Combine the data monitoring rule data and the artifact characteristic parameter information of the power grid edge cluster, and generate the abnormal data check sequence in the order of 1. cluster base monitoring data, 2. cluster artifact monitoring data, 3. cluster application monitoring data, 4. cluster resource monitoring data; or: Generate the abnormal data check sequence in the order of 1. cluster artifact monitoring data, 2. cluster resource monitoring data, 3. cluster application monitoring data, 4. cluster base monitoring data. Second: When at least one of the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data is dynamic, combine the data monitoring rule data and the artifact characteristic parameter information of the power grid edge cluster, and perform random permutations and combinations according to at least one of the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data to determine the abnormal data check sequence for the edge cluster monitoring data. At this time, the abnormal data check sequence is dynamic (that is, the abnormal data check sequence changes with the dynamic changes of the monitoring data). Among them, the artifact characteristic parameter information can be the parameters that can reflect the characteristic information of the power grid artifacts, and can be divided into professional parameter information and general parameter information. Among them, the professional parameter information can be voltage, current, frequency, power factor, system inertia, capacity factor, etc., and the general parameter information can be function introduction, version, change log, technical operation manual, etc.

[0034] Since the abnormal data check sequence includes the order of checks and the monitoring data for which abnormal data checks need to be performed, according to the abnormal data check sequence, the monitoring data to be checked is selected from the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data, and the abnormal data check is performed in the order of checks to obtain data check information.

[0035] Step 206, in the case where the data check information indicates that there is abnormal data in the edge cluster monitoring data, extract the edge cluster abnormal data from the edge cluster monitoring data.

[0036] Among them, the edge cluster abnormal data can be the data with abnormalities in the edge cluster monitoring data.

[0037] Specifically, if the data check information indicates that there is abnormal data in the edge cluster monitoring data, traverse the edge cluster monitoring data according to the data check information to obtain a cluster monitoring data traversal result, where the cluster monitoring data traversal result includes the mapping relationship between the data check information and the edge cluster monitoring data. According to the cluster monitoring data traversal result, locate at least one of the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data in the edge cluster monitoring data as the cluster abnormal monitoring data. Further, separate the abnormal data from the cluster abnormal monitoring data, and take out the separated abnormal data as the edge cluster abnormal data.

[0038] Step 208, input the edge cluster abnormal data into the abnormal data analysis model of the power grid edge cluster to obtain abnormal data analysis information.

[0039] Among them, the abnormal data analysis model can be a neural network for inferential analysis and status evaluation of edge cluster abnormal data, or a professional simulation model for inferential analysis and status evaluation of edge cluster abnormal data.

[0040] Among them, the abnormal data analysis information can be the data obtained by inferential analysis and status evaluation of the edge cluster abnormal data.

[0041] Specifically, analyze the current operating state of the power grid edge cluster according to the edge cluster abnormal data. Among them, the items of the operating state analysis include the performance data, errors, warnings, abnormal conditions, operating conditions, stability, response time, security status, etc. of the power grid cluster base, power grid artifacts, application programs, and resource usage at each node at the current time, to obtain the current operating state analysis data of the cluster.

[0042] Analyze the data traversing the edge cluster monitoring data according to the current running state of the cluster to obtain the traversal result of the current running state analysis data, where the traversal result of the current running state analysis data includes the mapping relationship between the current running state analysis data of the cluster and the edge cluster monitoring data. According to the traversal result of the cluster monitoring data, locate the abnormal feature information in the current situation from the edge cluster monitoring data. Use a Transformer to extract the feature information of the device information from the abnormal feature information, and extract the abnormal operation feature information of the devices in the grid edge cluster from the extraction result through the self-attention mechanism. Finally, input the current running state analysis data of the cluster and the abnormal operation feature information of the devices into the continuous running state prediction layer in the abnormal data analysis model, and perform prediction through one or more of linear regression, decision trees, random forests, Bayesian models, support vector machines (SVMs), pre-trained language models, etc. of the continuous running state prediction layer to obtain the continuous running state analysis data of the cluster.

[0043] Since there are static and dynamic ways in the current running state analysis data of the cluster and the continuous running state analysis data of the cluster, time is introduced as a parameter to fuse the current running state analysis data of the cluster and the continuous running state analysis data of the cluster to obtain the abnormal data analysis information.

[0044] Step 210, generate the cluster monitoring policy information corresponding to the grid edge cluster according to the abnormal data analysis information.

[0045] Among them, the cluster monitoring policy information can be the way for the cloud-edge fusion intelligent scheduling operation platform to monitor the grid edge cluster.

[0046] Specifically, according to the current running state analysis data of the cluster, adjust the way of using the cloud-edge fusion intelligent scheduling operation platform to monitor the grid edge cluster to obtain the current cluster monitoring policy information; and, according to the continuous running state analysis data of the cluster, adjust the way of using the cloud-edge fusion intelligent scheduling operation platform to monitor the grid edge cluster to obtain the continuous cluster monitoring policy information. Since there are static and dynamic ways in the current cluster monitoring policy information and the continuous cluster monitoring policy information, time is introduced as a parameter to fuse the current cluster monitoring policy information and the continuous cluster monitoring policy information to obtain the cluster monitoring policy information. As Figure 9 shown, it is a schematic diagram of the grid edge cluster monitoring interface in the cloud-edge fusion intelligent scheduling operation platform.

[0047] In the above grid edge cluster monitoring method based on the cloud-edge integrated intelligent scheduling operation platform, edge cluster monitoring data corresponding to the grid edge cluster is obtained according to the data monitoring rule data of the grid edge cluster; the edge cluster monitoring data is checked for abnormal data to obtain data check information corresponding to the grid edge cluster; in the case where the data check information indicates that there is abnormal data in the edge cluster monitoring data, the edge cluster abnormal data is extracted from the edge cluster monitoring data; the edge cluster abnormal data is input into the abnormal data analysis model of the grid edge cluster to obtain abnormal data analysis information; and according to the abnormal data analysis information, cluster monitoring policy information corresponding to the grid edge cluster is generated.

[0048] By checking the edge cluster monitoring data for abnormal data, if abnormal data is found, the abnormal data is analyzed and its status is evaluated to obtain abnormal data analysis information of the grid edge cluster and generate cluster monitoring policy information. It can give full play to the big data normalization monitoring of the cloud-edge integrated intelligent scheduling operation platform for the vertical disturbance discrimination and horizontal comparison and investigation of the grid edge cluster, lock the faults of the grid edge cluster, achieve the state of "check when it should be checked", and improve the efficiency of discovering abnormal situations of the grid edge cluster.

[0049] In one embodiment, as Figure 3 shown, checking the edge cluster monitoring data for abnormal data to obtain data check information corresponding to the grid edge cluster includes:

[0050] Step 302, determining an abnormal data check sequence according to the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data.

[0051] Among them, the abnormal data check sequence can be the order of checking and the index of the monitoring data for which abnormal data needs to be checked.

[0052] Specifically, expand the edge cluster monitoring data to obtain cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data. First: when the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data are all static, combine the data monitoring rule data and the artifact characteristic parameter information of the grid edge cluster, and perform random permutations and combinations based on at least one of the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data to determine the abnormal data check sequence for the edge cluster monitoring data. At this time, the abnormal data check sequence is static (i.e., the abnormal data check sequence does not change within a period of time). Second: when at least one of the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data is dynamic, combine the data monitoring rule data and the artifact characteristic parameter information of the grid edge cluster, and perform random permutations and combinations based on at least one of the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data to determine the abnormal data check sequence for the edge cluster monitoring data. At this time, the abnormal data check sequence is dynamic (i.e., the abnormal data check sequence changes with the dynamic changes of the monitoring data).

[0053] Step 304, according to the abnormal data check sequence, perform abnormal data checks on the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data to obtain data check information.

[0054] Specifically, since the abnormal data check sequence includes the order of checks and the monitoring data indexes for which abnormal data checks need to be performed, according to the abnormal data check sequence, select the monitoring data to be checked from the cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data, and perform abnormal data checks in the order of checks to obtain data check information.

[0055] In this embodiment, by determining the abnormal data check sequence according to different monitoring data and further using the abnormal data check sequence to check each monitoring data, different check methods can be implemented for the monitoring data at different times, improving the efficiency and accuracy of data checks.

[0056] In one embodiment, as Figure 4 shown, extracting edge cluster abnormal data from the edge cluster monitoring data includes:

[0057] Step 402, locate the cluster abnormal monitoring data according to the edge cluster monitoring data and the data check information.

[0058] Among them, the cluster anomaly monitoring data can be at least one of the cluster base monitoring data, the cluster artifact monitoring data, the cluster application monitoring data, and the cluster resource monitoring data.

[0059] Specifically, if the data check information indicates that there is abnormal data in the edge cluster monitoring data, the edge cluster monitoring data is traversed according to the data check information to obtain a cluster monitoring data traversal result, where the cluster monitoring data traversal result includes the mapping relationship between the data check information and the edge cluster monitoring data. According to the cluster monitoring data traversal result, at least one of the cluster base monitoring data, the cluster artifact monitoring data, the cluster application monitoring data, and the cluster resource monitoring data in the edge cluster monitoring data is located as the cluster anomaly monitoring data.

[0060] Step 404, traverse the cluster anomaly monitoring data and extract the edge cluster abnormal data.

[0061] Specifically, the abnormal data is separated from the cluster anomaly monitoring data, and the separated abnormal data is used as the edge cluster abnormal data.

[0062] In this embodiment, by using the edge cluster monitoring data and the data check information to locate the cluster anomaly monitoring data with abnormal data, and extracting the edge cluster abnormal data from the cluster anomaly monitoring data, it is possible to perform in-depth search only on the monitoring data with abnormal data, reducing the computational amount of the cloud-edge fusion intelligent scheduling operation platform.

[0063] In one embodiment, as Figure 5 shown, the edge cluster abnormal data is input into the abnormal data analysis model of the power grid edge cluster to obtain abnormal data analysis information, including:

[0064] Step 502, analyze the current operating state of the power grid edge cluster according to the edge cluster abnormal data to obtain the cluster current operating state analysis data.

[0065] Among them, the cluster current operating state analysis data can be the data obtained by analyzing the current operating state of the power grid edge cluster.

[0066] Specifically, according to the edge cluster abnormal data, the current operating state of the power grid edge cluster is analyzed. Among them, the items of the operating state analysis include the performance data, errors, warnings, abnormal conditions, operating conditions, stability, response time, security status, etc. of the power grid cluster base, power grid artifacts, application programs, and resource usage at each node at the current time to obtain the cluster current operating state analysis data.

[0067] Step 504: Analyze the data based on the current operating status of the cluster, analyze the continuous operating status of the grid edge cluster, and obtain the analysis data of the continuous operating status of the cluster.

[0068] Among them, the analysis data of the continuous operating status of the cluster can be the data obtained by analyzing the continuous operating status of the grid edge cluster.

[0069] Specifically, traverse the edge cluster monitoring data according to the analysis data of the current operating status of the cluster to obtain the traversal result of the current operating status analysis data, where the traversal result of the current operating status analysis data includes the mapping relationship between the analysis data of the current operating status of the cluster and the edge cluster monitoring data. According to the traversal result of the cluster monitoring data, locate the abnormal feature information in the current situation from the edge cluster monitoring data. Use a Transformer to extract the feature information of the device from the abnormal feature information, and extract the abnormal operating feature information of the devices in the grid edge cluster from the extraction result through the self-attention mechanism. Finally, input the analysis data of the current operating status of the cluster and the abnormal operating feature information of the devices into the continuous operating status prediction layer in the abnormal data analysis model, and perform prediction through one or more of linear regression, decision trees, random forests, Bayesian models, support vector machines (SVMs), pre-trained language models, etc. in the continuous operating status prediction layer to obtain the analysis data of the continuous operating status of the cluster.

[0070] Step 506: Obtain the abnormal data analysis information based on the analysis data of the current operating status of the cluster and the analysis data of the continuous operating status of the cluster.

[0071] Specifically, since there are static and dynamic ways in the analysis data of the current operating status of the cluster and the analysis data of the continuous operating status of the cluster, time is introduced as a parameter to fuse the analysis data of the current operating status of the cluster and the analysis data of the continuous operating status of the cluster to obtain the abnormal data analysis information.

[0072] In this embodiment, by analyzing the current operating status and the continuous operating status of the grid edge cluster, and generating abnormal data analysis information based on the analysis results of the two, it is possible to pay attention to the current operating situation of the grid edge cluster while predicting the continuous operating situation of the grid edge cluster, make preparations in advance for possible situations of the grid edge cluster, and improve the security of the grid edge cluster.

[0073] In one embodiment, as Figure 6As shown, analyze the data according to the current running state of the cluster, analyze the continuous running state of the power grid edge cluster, and obtain the analysis data of the continuous running state of the cluster, including:

[0074] Step 602: Determine the abnormal feature information of the power grid edge cluster according to the analysis data of the current running state of the cluster.

[0075] Among them, the abnormal feature information can be the data information of the features that can represent abnormalities in the analysis data of the current running state of the cluster.

[0076] Specifically, traverse the edge cluster monitoring data according to the analysis data of the current running state of the cluster to obtain the traversal result of the analysis data of the current running state, where the traversal result of the analysis data of the current running state includes the mapping relationship between the analysis data of the current running state of the cluster and the edge cluster monitoring data. According to the traversal result of the cluster monitoring data, locate the abnormal feature information in the current situation from the edge cluster monitoring data.

[0077] Step 604: Determine the abnormal operation feature information of the devices in the power grid edge cluster according to the abnormal feature information.

[0078] Among them, the abnormal operation feature information of the devices can be the text feature information of the devices representing the abnormal operation of the power grid edge cluster in the abnormal feature information, such as: the model number, components, etc. of the abnormally operating devices.

[0079] Specifically, use a Transformer to extract the feature information of the device information from the abnormal feature information, and extract the abnormal operation feature information of the devices in the power grid edge cluster from the extraction result through a self-attention mechanism.

[0080] Step 606: Obtain the analysis data of the continuous running state of the cluster according to the analysis data of the current running state of the cluster and the abnormal operation feature information of the devices.

[0081] Specifically, input the analysis data of the current running state of the cluster and the abnormal operation feature information of the devices into the continuous running state prediction layer in the abnormal data analysis model, and perform prediction through one or more of linear regression, decision trees, random forests, Bayesian models, support vector machines (SVM), pre-trained language models, etc. in the continuous running state prediction layer to obtain the analysis data of the continuous running state of the cluster.

[0082] In this embodiment, by extracting the text information of the analysis data on the current running state of the cluster, the abnormal operation characteristic information of the devices in the power grid edge cluster is obtained, and further combined with the current running state analysis data to obtain the continuous running state analysis data of the cluster, which can combine the abnormal situation of the devices and the current running state to predict the possible situations that may be encountered in the continuous operation of the power grid edge cluster, and improve the emergency response ability of the cloud-edge fusion intelligent scheduling operation platform.

[0083] In one embodiment, as Figure 7 shown, according to the abnormal data analysis information, the cluster monitoring policy information corresponding to the power grid edge cluster is generated, including:

[0084] Step 702, generate the current cluster monitoring policy information of the power grid edge cluster according to the analysis data of the current running state of the cluster.

[0085] Among them, the current cluster monitoring policy information can be a monitoring method within a short period starting from the current time in the case of an abnormality in the power grid edge cluster.

[0086] Specifically, according to the continuous running state analysis data of the cluster, the monitoring method of the cloud-edge fusion intelligent scheduling operation platform for the power grid edge cluster is adjusted to obtain the current cluster monitoring policy information.

[0087] Step 704, generate the continuous cluster monitoring policy information of the power grid edge cluster according to the continuous running state analysis data of the cluster.

[0088] Among them, the continuous cluster monitoring policy information can be a monitoring method within a long period starting from the current time in the case of an abnormality in the power grid edge cluster.

[0089] Specifically, according to the continuous running state analysis data of the cluster, the monitoring method of the cloud-edge fusion intelligent scheduling operation platform for the power grid edge cluster is adjusted to obtain the continuous cluster monitoring policy information.

[0090] Step 706, optimize the current cluster monitoring policy information and the continuous cluster monitoring policy information according to the edge cluster abnormal data to obtain the cluster monitoring policy information.

[0091] Specifically, since the current cluster monitoring policy information and the continuous cluster monitoring policy information have both static and dynamic methods, therefore, time is introduced as a parameter to fuse the current cluster monitoring policy information and the continuous cluster monitoring policy information to obtain the cluster monitoring policy information. If there is no abnormal data in the data check information indicating the edge cluster monitoring data, then continue to monitor the power grid edge cluster according to the original monitoring method.

[0092] In this embodiment, by adopting new current cluster monitoring policy information for the current operating state and continuous cluster monitoring policy information for the continuous operating state, it is possible to monitor the operating information of the grid edge cluster at different scales, which is beneficial for the cloud-edge fusion intelligent scheduling operation platform to timely detect abnormal situations and ensure the safety of the power grid system.

[0093] In one embodiment, as Figure 8 shown, the method further includes:

[0094] Step 802, perform abnormal data inspection on the grid device operation monitoring data to obtain device inspection information corresponding to the grid device.

[0095] Among them, the grid device operation monitoring data can be the detection data collected during the operation of the grid device.

[0096] Among them, the device inspection information can be the inspection data generated by performing abnormal data inspection on the grid device operation monitoring data. Among them, the device inspection information includes the inspection information of normal data, abnormal data, and suspicious data in the grid device operation monitoring data, etc., which is used to reflect the operating conditions of the grid device.

[0097] Specifically, traverse the operation data information of each grid device in the grid device operation monitoring data. For each grid device, compare the operation data information in the grid device operation monitoring data with the normal operation data threshold in the grid device to obtain the device inspection information.

[0098] Step 804, when the device inspection information indicates that the grid device has an abnormality, analyze the grid device operation monitoring data to generate device abnormality analysis information corresponding to the grid device.

[0099] Among them, the device abnormality analysis information can be the data obtained by reasoning analysis and status evaluation of the grid device operation monitoring data.

[0100] Specifically, if the device inspection information indicates that the grid device has an abnormality, that is, the operation data information in the grid device operation monitoring data does not fall within the range of the normal operation data threshold in the grid device, then extract the operation data information in the grid device operation monitoring data that does not fall within the corresponding normal operation data threshold of the grid device to obtain the grid device operation abnormal data. According to the grid device operation abnormal data, analyze the abnormal situation of the grid device to obtain the device abnormality analysis information.

[0101] Step 806, generate device rejection strategy information according to the device abnormality analysis information.

[0102] Among them, the device rejection strategy information can be the way for the cloud-edge integrated intelligent scheduling operation platform to eliminate abnormalities of power grid devices.

[0103] Specifically, input the device anomaly analysis information into the cloud-edge integrated intelligent scheduling operation platform, and find a solution for the device anomaly analysis information through the cloud-edge integrated intelligent scheduling operation platform to generate the device rejection strategy information. Among them, the solutions for the device anomaly analysis information are pre-stored in the storage space of the cloud-edge integrated intelligent scheduling operation platform, and are selected from each solution by analyzing the principle of data matching with the solution data.

[0104] In this embodiment, by using the operation monitoring data of power grid devices and taking the power grid edge cluster as an intermediate medium, the cloud-edge integrated intelligent scheduling operation platform can monitor the power grid devices. Under the overall planning of the cloud-edge integrated intelligent scheduling operation platform, integrated monitoring can be realized, which is beneficial to timely propose solutions in case of problems in the power grid system.

[0105] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0106] Based on the same inventive concept, the embodiment of the present application also provides a device for monitoring the power grid edge cluster based on the cloud-edge integrated intelligent scheduling operation platform for implementing the above-mentioned method for monitoring the power grid edge cluster based on the cloud-edge integrated intelligent scheduling operation platform. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the device for monitoring the power grid edge cluster based on the cloud-edge integrated intelligent scheduling operation platform provided below can refer to the limitations for the method for monitoring the power grid edge cluster based on the cloud-edge integrated intelligent scheduling operation platform in the above text, and will not be repeated here.

[0107] In one embodiment, as Figure 10As shown, a grid edge cluster monitoring device based on a cloud-edge fusion intelligent scheduling operation platform is provided, including: a monitoring data acquisition module 1002, an abnormal data inspection module 1004, an abnormal data extraction module 1006, an abnormal data analysis module 1008, and a monitoring policy generation module 1010, where:

[0108] The monitoring data acquisition module 1002 is used to obtain the edge cluster monitoring data corresponding to the grid edge cluster according to the data monitoring rule data for the grid edge cluster;

[0109] The abnormal data inspection module 1004 is used to perform abnormal data inspection on the edge cluster monitoring data to obtain the data inspection information corresponding to the grid edge cluster;

[0110] The abnormal data extraction module 1006 is used to extract the edge cluster abnormal data from the edge cluster monitoring data when the data inspection information indicates that there is abnormal data in the edge cluster monitoring data;

[0111] The abnormal data analysis module 1008 is used to input the edge cluster abnormal data into the abnormal data analysis model of the grid edge cluster to obtain the abnormal data analysis information;

[0112] The monitoring policy generation module 1010 is used to generate the cluster monitoring policy information corresponding to the grid edge cluster according to the abnormal data analysis information.

[0113] In one embodiment, the abnormal data inspection module 1004 is further used to determine the abnormal data inspection sequence according to the cluster base monitoring data, the cluster artifact monitoring data, the cluster application monitoring data, and the cluster resource monitoring data; according to the abnormal data inspection sequence, perform abnormal data inspection on the cluster base monitoring data, the cluster artifact monitoring data, the cluster application monitoring data, and the cluster resource monitoring data to obtain the data inspection information.

[0114] In one embodiment, the abnormal data extraction module 1006 is further used to locate the cluster abnormal monitoring data according to the edge cluster monitoring data and the data inspection information; the cluster abnormal monitoring data is at least one of the cluster base monitoring data, the cluster artifact monitoring data, the cluster application monitoring data, and the cluster resource monitoring data; traverse the cluster abnormal monitoring data to extract the edge cluster abnormal data.

[0115] In one embodiment, the abnormal data analysis module 1008 is further configured to analyze the current operating state of the power grid edge cluster based on the edge cluster abnormal data to obtain the analysis data of the current operating state of the cluster; analyze the continuous operating state of the power grid edge cluster based on the analysis data of the current operating state of the cluster to obtain the analysis data of the continuous operating state of the cluster; and obtain the abnormal data analysis information based on the analysis data of the current operating state of the cluster and the analysis data of the continuous operating state of the cluster.

[0116] In one embodiment, the abnormal data analysis module 1008 is further configured to determine the abnormal feature information of the power grid edge cluster based on the analysis data of the current operating state of the cluster; determine the abnormal operating feature information of the devices in the power grid edge cluster based on the abnormal feature information; and obtain the analysis data of the continuous operating state of the cluster based on the analysis data of the current operating state of the cluster and the abnormal operating feature information of the devices.

[0117] In one embodiment, the abnormal data analysis module 1008 is further configured to generate the current cluster monitoring policy information of the power grid edge cluster based on the analysis data of the current operating state of the cluster; generate the continuous cluster monitoring policy information of the power grid edge cluster based on the analysis data of the continuous operating state of the cluster; and optimize the current cluster monitoring policy information and the continuous cluster monitoring policy information based on the edge cluster abnormal data to obtain the cluster monitoring policy information.

[0118] In one embodiment, the monitoring policy generation module 1010 is further configured to check for abnormal data in the power grid device operation monitoring data to obtain the device check information corresponding to the power grid device; analyze the power grid device operation monitoring data in the case where the device check information indicates that the power grid device is abnormal to generate the device abnormal analysis information corresponding to the power grid device; generate the device exclusion policy information based on the device abnormal analysis information, and send the device exclusion policy information to the power grid edge cluster; and the power grid edge cluster is configured to send the device exclusion policy information to the power grid maintenance unit.

[0119] Each module in the above-mentioned power grid edge cluster monitoring device based on the cloud-edge fusion intelligent scheduling operation platform can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor in the computer device in the form of hardware or be independent of the processor, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0120] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 11As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for monitoring a power grid edge cluster based on a cloud-edge fusion intelligent scheduling operation platform.

[0121] Those skilled in the art can understand that Figure 11 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0122] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0123] In one embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0124] In one embodiment, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in the above method embodiments.

[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties.

[0126] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0127] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0128] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A power grid edge cluster monitoring method based on a cloud-edge fusion intelligent scheduling operation platform, characterized in that, The method includes: Obtaining the edge cluster monitoring data corresponding to the grid edge cluster according to the data monitoring rule data of the grid edge cluster; Performing abnormal data inspection on the edge cluster monitoring data to obtain the data inspection information corresponding to the grid edge cluster; When the data inspection information indicates that there is abnormal data in the edge cluster monitoring data, extracting the edge cluster abnormal data from the edge cluster monitoring data; Inputting the edge cluster abnormal data into the abnormal data analysis model of the grid edge cluster to obtain abnormal data analysis information; Generating the current cluster monitoring policy information of the grid edge cluster according to the current operating state analysis data of the cluster; Generating the continuous cluster monitoring policy information of the grid edge cluster according to the continuous operating state analysis data of the cluster; Optimizing the current cluster monitoring policy information and the continuous cluster monitoring policy information according to the edge cluster abnormal data to obtain the cluster monitoring policy information.

2. The method according to claim 1, wherein The edge cluster monitoring data includes cluster base monitoring data, cluster artifact monitoring data, cluster application monitoring data, and cluster resource monitoring data; The performing abnormal data inspection on the edge cluster monitoring data to obtain the data inspection information corresponding to the grid edge cluster includes: Determining an abnormal data inspection sequence according to the cluster base monitoring data, the cluster artifact monitoring data, the cluster application monitoring data, and the cluster resource monitoring data; Performing abnormal data inspection on the cluster base monitoring data, the cluster artifact monitoring data, the cluster application monitoring data, and the cluster resource monitoring data according to the abnormal data inspection sequence to obtain the data inspection information.

3. The method according to claim 2, characterized in that, The extracting the edge cluster abnormal data from the edge cluster monitoring data includes: Locating the cluster abnormal monitoring data according to the edge cluster monitoring data and the data inspection information; the cluster abnormal monitoring data is at least one of the cluster base monitoring data, the cluster artifact monitoring data, the cluster application monitoring data, and the cluster resource monitoring data; Traversing the cluster abnormal monitoring data to extract the edge cluster abnormal data.

4. The method according to claim 1, characterized in that, The inputting the edge cluster abnormal data into the abnormal data analysis model of the grid edge cluster to obtain abnormal data analysis information includes: Analyzing the current operating state of the grid edge cluster according to the edge cluster abnormal data to obtain the current operating state analysis data of the cluster; Analyzing the continuous operating state of the grid edge cluster according to the current operating state analysis data of the cluster to obtain the continuous operating state analysis data of the cluster; Obtaining the abnormal data analysis information according to the current operating state analysis data of the cluster and the continuous operating state analysis data of the cluster.

5. The method according to claim 4, wherein The analyzing the continuous operating state of the grid edge cluster according to the current operating state analysis data of the cluster to obtain the continuous operating state analysis data of the cluster includes: Determining the abnormal feature information of the grid edge cluster according to the current operating state analysis data of the cluster; Determine the abnormal operation characteristic information of the devices in the grid edge cluster according to the abnormal characteristic information; Obtain the analysis data of the continuous operation state of the cluster according to the analysis data of the current operation state of the cluster and the abnormal operation characteristic information of the devices.

6. The method according to claim 1, wherein The edge cluster monitoring data further includes the operation monitoring data of grid devices, and the method further includes: Perform abnormal data inspection on the operation monitoring data of the grid devices to obtain the device inspection information corresponding to the grid devices; When the device inspection information indicates that the grid devices are abnormal, analyze the operation monitoring data of the grid devices to generate the device abnormal analysis information corresponding to the grid devices; Generate the device exclusion strategy information according to the device abnormal analysis information, and send the device exclusion strategy information to the grid edge cluster; the grid edge cluster is used to send the device exclusion strategy information to the grid maintenance unit.

7. A power grid edge cluster monitoring device based on a cloud-edge fusion intelligent scheduling operation platform, characterized in that, The device includes: A monitoring data acquisition module, configured to acquire the edge cluster monitoring data corresponding to the grid edge cluster according to the data monitoring rule data for the grid edge cluster; An abnormal data inspection module, configured to perform abnormal data inspection on the edge cluster monitoring data to obtain the data inspection information corresponding to the grid edge cluster; An abnormal data extraction module, configured to extract the edge cluster abnormal data from the edge cluster monitoring data when the data inspection information indicates that there is abnormal data in the edge cluster monitoring data; An abnormal data analysis module, configured to input the edge cluster abnormal data into the abnormal data analysis model of the grid edge cluster to obtain the abnormal data analysis information; A monitoring strategy generation module, configured to generate the current cluster monitoring strategy information of the grid edge cluster according to the analysis data of the current operation state of the cluster; generate the continuous cluster monitoring strategy information of the grid edge cluster according to the analysis data of the continuous operation state of the cluster; optimize the current cluster monitoring strategy information and the continuous cluster monitoring strategy information according to the edge cluster abnormal data to obtain the cluster monitoring strategy information.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images