Pressure testing method, device and equipment of industrial edge cloud and storage medium

Abstract

The application discloses a pressure test method, device and equipment of an industrial edge cloud and a storage medium. The method comprises the following steps: acquiring time-labeled resource data sets of edge node resources in each working procedure; performing cluster analysis on the resource data sets based on the working procedures to obtain basic data sets corresponding to the working procedures; filtering test data sets with a correlation intensity greater than a preset threshold from the basic data sets; and inputting the test data sets into a preset test container and controlling the test container to perform pressure test on the edge nodes. In the application, the resource data of the edge nodes in different working procedures is filtered twice to obtain test data sets, and the edge nodes are tested through the test data sets, so that the pressure test is closely combined with the working procedures, the performance of each edge node is tested in a real industrial pressure load scene, and the confidence of the edge cloud performance test is improved.

Description

Technical Field

[0001] This application relates to the field of stress testing technology, and in particular to a stress testing method, apparatus, equipment and storage medium for industrial edge clouds. Background Technology

[0002] With the rise of the Industrial Internet, industrial edge clouds, which directly connect to edge cloud intelligent control devices near the industrial site for localized computing and control, reduce network overhead for communication between the industrial site and the central cloud, thereby improving production efficiency.

[0003] Because industrial edge clouds are affected by industrial scenarios, stress testing is required after the edge cloud is connected at the industrial site to ensure high utilization of edge cloud resources during industrial production. Currently, stress testing of edge clouds only uses a large number of ideal industrial loads to determine performance bottlenecks, without combining actual production conditions. This makes it impossible to achieve edge cloud performance testing under real industrial stress load scenarios, resulting in low credibility of edge cloud performance testing. Summary of the Invention

[0004] The main purpose of this application is to provide a stress testing method, apparatus, equipment and storage medium for industrial edge clouds, aiming to solve the technical problem that the existing technology cannot realize edge cloud performance testing under real industrial stress load scenarios, resulting in low reliability of edge cloud performance testing.

[0005] To achieve the above objectives, this application provides a stress testing method for industrial edge clouds, the stress testing method for industrial edge clouds comprising:

[0006] Obtain the resource dataset with time stamps for edge node resources during each process;

[0007] Based on the aforementioned process, cluster analysis is performed on the resource dataset to obtain the basic dataset corresponding to the aforementioned process;

[0008] From the basic dataset, the edge node resources and the test datasets whose correlation strength with the corresponding process is greater than a preset threshold are selected;

[0009] The test dataset is input into a preset test container, and the test container is controlled to perform stress tests on the edge nodes.

[0010] Optionally, before the step of filtering the edge node resources from the basic dataset and the test dataset whose correlation strength with the corresponding process is greater than a preset threshold, the method includes:

[0011] The access frequency of the basic dataset is calculated to obtain the access density of the edge node resources when performing the same process.

[0012] Based on the access density, the edge node resources are simulated under the same process in different scenarios to determine the correlation strength between the edge node resources and the process under different scenarios.

[0013] Optionally, the step of calculating the access frequency of the basic dataset to obtain the access density of the edge node resources during the same process includes:

[0014] The number of accesses to the basic dataset is calculated to obtain the number of times each edge node resource is accessed by the same process.

[0015] By performing time-series analysis on the number of times, the access density of the edge node resources is obtained when the same process is performed.

[0016] Optionally, the step of performing time-series analysis on the number of times to obtain the access density of the edge node resources during the same process includes:

[0017] By performing time-series analysis on the number of accesses, the access probability of each edge node resource being accessed by the same process is obtained;

[0018] Based on the preset time interval, a density analysis is performed on the access probability to obtain the access density of the edge node resources when the same process is performed in each time interval.

[0019] Optionally, the step of filtering the edge node resources and the test dataset whose correlation strength with the corresponding process is greater than a preset threshold from the basic dataset includes:

[0020] Based on a preset intensity range, the basic dataset is divided to obtain an intensity dataset;

[0021] The minimum correlation intensity in each intensity dataset is compared with the preset threshold, and test datasets with a minimum correlation intensity greater than the preset threshold are selected from the intensity datasets.

[0022] Optionally, the step of performing cluster analysis on the resource dataset based on the process to obtain the basic dataset corresponding to the process includes:

[0023] Based on the aforementioned process, the resource dataset is analyzed to obtain the utilization dataset of the edge nodes used in the process.

[0024] The dataset is then subjected to cluster analysis to obtain the basic dataset corresponding to the process.

[0025] Optionally, before the step of filtering the edge node resources from the basic dataset and the test dataset whose correlation strength with the corresponding process is greater than a preset threshold, the method includes:

[0026] The number of times the resource dataset was retrieved is determined.

[0027] If the number of acquisitions exceeds the preset number, the basic dataset will be filtered.

[0028] This application also provides a stress testing device for industrial edge clouds, the stress testing device for industrial edge clouds comprising:

[0029] The acquisition module is used to acquire resource datasets with time stamps for edge node resources during each process.

[0030] The clustering module is used to perform clustering analysis on the resource dataset based on the process to obtain the basic dataset corresponding to the process.

[0031] The filtering module is used to filter out the edge node resources and the test datasets whose correlation strength with the corresponding process is greater than a preset threshold from the basic dataset.

[0032] The testing module is used to input the test dataset into a preset test container and control the test container to perform stress tests on the edge nodes.

[0033] This application also provides a stress testing device for industrial edge cloud, which is a physical node device. The stress testing device for industrial edge cloud includes: a memory, a processor, and a program for the stress testing method of industrial edge cloud stored in the memory and executable on the processor. When the program for the stress testing method of industrial edge cloud is executed by the processor, it can implement the steps of the stress testing method of industrial edge cloud as described above.

[0034] This application also provides a storage medium storing a program that implements the above-described stress testing method for industrial edge clouds. When the program for the stress testing method for industrial edge clouds is executed by a processor, it implements the steps of the stress testing method for industrial edge clouds as described above.

[0035] This application provides a stress testing method, apparatus, equipment, and storage medium for industrial edge cloud. Compared with existing technologies that cannot achieve edge cloud performance testing under true industrial stress load scenarios, resulting in low reliability of edge cloud performance testing, this application obtains a resource dataset with time stamps for edge node resources during each process; based on the process, the resource dataset is clustered to obtain a basic dataset corresponding to the process; from the basic dataset, the edge node resources and test datasets with a correlation strength greater than a preset threshold corresponding to the process are selected; the test datasets are input into a preset test container, and the test container is controlled to perform stress testing on the edge nodes. In this application, the acquired edge node resource dataset is clustered according to different processes to obtain the basic dataset corresponding to each process. From the basic dataset, test datasets with a correlation strength between edge node resources and processes greater than a preset threshold are selected. The test datasets are then input into a preset test container to perform stress tests on the edge nodes. In other words, in this application, the acquired edge node resource data under different processes are filtered twice to select test datasets with a correlation strength between edge nodes and processes greater than a preset threshold. The edge nodes are then subjected to stress tests using the test datasets, thus closely integrating stress testing with the processes. This enables performance testing of each edge node under real industrial stress load scenarios, which is also equivalent to performance testing of the edge cloud, thereby improving the credibility of edge cloud performance testing. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating the first embodiment of the stress testing method for industrial edge cloud in this application;

[0039] Figure 2 This is a schematic diagram of the test process for the first embodiment of the stress testing method for industrial edge cloud in this application.

[0040] Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application;

[0041] Figure 4This is a flowchart illustrating the second embodiment of the stress testing method for industrial edge clouds in this application.

[0042] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0043] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0044] This application provides a stress testing method for industrial edge clouds. In the first embodiment of this application's stress testing method for industrial edge clouds, refer to... Figure 1 The stress testing method for the industrial edge cloud includes:

[0045] Step S10: Obtain the resource dataset with time stamps for edge node resources during each process.

[0046] Step S20: Based on the process, perform cluster analysis on the resource dataset to obtain the basic dataset corresponding to the process;

[0047] Step S30: From the basic dataset, filter out the edge node resources and the test dataset whose correlation strength with the corresponding process is greater than a preset threshold;

[0048] Step S40: Input the test dataset into a preset test container and control the test container to perform stress tests on the edge nodes.

[0049] This embodiment aims to address the issue that edge cloud performance testing cannot be performed under real industrial pressure load scenarios, resulting in low reliability of edge cloud performance testing.

[0050] In this embodiment, it should be noted that the stress testing method for industrial edge clouds can be applied to a stress testing device for industrial edge clouds, which is subordinate to the stress testing equipment for industrial edge clouds, and the stress testing equipment for industrial edge clouds is subordinate to the stress testing system for industrial edge clouds.

[0051] Among them, stress testing simulates the system load of the hardware and software environment and user usage process in actual applications. The test software is run under long-term or extremely heavy load to test the performance, reliability, and stability of the system under test.

[0052] Among them, edge cloud can be a distributed cloud composed of scattered edge nodes working together.

[0053] Edge nodes can possess common capabilities such as real-time data analysis at the edge, local data storage, and real-time network connectivity; specifically, edge nodes can be processors, storage devices, disks, transmission interfaces, etc.

[0054] The resource dataset can include data such as processor utilization, storage utilization, disk read / write speed, and upload / download bandwidth of the transmission interface.

[0055] The basic dataset can be a collection of resource data required during the production process, that is, a collection of resource utilization rates involved in the production process.

[0056] In this embodiment, the application scenarios of the industrial edge cloud stress testing method can be industrial zinc smelting volatilization kiln scenarios, food refining scenarios, porcelain or glass firing processes, etc., without being limited to any specific scenarios. In this embodiment, the industrial zinc smelting volatilization kiln scenario is used as an example for illustration.

[0057] In this embodiment, refer to Figure 2 , Figure 2 This is a schematic diagram of the test process for the first embodiment of the stress testing method for industrial edge cloud in this application.

[0058] The specific steps are as follows:

[0059] Step S10: Obtain the resource dataset with time stamps for edge node resources during each process.

[0060] Each edge node includes at least one edge node resource. For example, a disk may include write resources and read resources, etc., without any specific limitation.

[0061] In this embodiment, before acquiring the resource dataset, the production process is decomposed according to the industrial production process, and then the utilization time series data of edge node resources during each process is acquired, that is, the resource dataset with time stamps, so as to facilitate the analysis of the utilization rate of edge node resources during each production process.

[0062] It should be noted that the resource dataset can include data with a value of zero, that is, the utilization rate of edge node resources can be zero. For example, in a process, no storage area is used and no data is written to the disk, that is, the utilization rate of storage is zero and the utilization rate of disk write resources is also zero. In this case, the resource dataset can include storage utilization data and disk write resource utilization data.

[0063] Specifically, the production process can be broken down into steps based on the industrial example production process. For instance, the industrial zinc volatilization kiln production process can be broken down into steps such as zinc leaching residue, limestone, coke feeding, and material mixing.

[0064] In this embodiment, by adding a time stamp to the resource dataset, the utilization of edge node resources under different production scenarios during the process can be obtained. It should be noted that, due to the random and dynamic changes in industrial production factors during actual production, multiple application scenarios may arise for the same process. For example, the coke feeding process requires real-time speed feedback to ensure the feeding speed. During the production process, the volatilization kiln may be affected by voltage, causing unstable speed during the coke feeding process, or the volatilization kiln may experience certain wear and tear over time. Different wear and tear will have different impacts on the speed of the volatilization kiln.

[0065] Step S20: Based on the process, perform cluster analysis on the resource dataset to obtain the basic dataset corresponding to the process.

[0066] In this embodiment, the data of edge node resources participating in the process are clustered and classified according to the process. That is, according to different processes, the resource dataset is clustered and analyzed to gather the resource data of edge node resources used in the process to obtain the basic dataset corresponding to the process. For example, in the resource dataset corresponding to a process, the utilization rate of storage is zero, the utilization rate of disk write resources is also zero, the utilization rate of processor is 15%, and the utilization rate of network resources (i.e., transmission interface) is 1%. That is, after the clustering analysis, the basic dataset includes the utilization data of processor and network resources, i.e., the utilization rate of processor and network resources, but does not include the utilization data of storage and disk write resources with zero utilization.

[0067] In this embodiment, the data of edge node resources that are not used during the process are filtered out to obtain a set of edge node resource data used during the process, that is, the basic dataset. The access count of each edge node resource during the process can be obtained through the basic dataset.

[0068] Specifically, the step of performing cluster analysis on the resource dataset based on the process to obtain the basic dataset corresponding to the process includes:

[0069] Step S21: Based on the process, perform utilization analysis on the resource dataset to obtain the utilization dataset of the edge nodes used in the process;

[0070] In this embodiment, since the resource dataset contains resource data of edge node resources that are not used during the process, the resource dataset is used for utilization analysis. That is, the utilization dataset with a non-zero utilization rate is selected from the resource dataset. By deleting the data with a zero utilization rate, the amount of data to be processed during cluster analysis can be reduced, thereby avoiding the lag during data processing and improving the speed of cluster analysis.

[0071] Step S22: Perform cluster analysis on the dataset to obtain the basic dataset corresponding to the process.

[0072] In this embodiment, since the edge node resources required during each process are basically the same, regardless of changes in the production environment, the utilization rate of edge node resources during the same process is also roughly the same. By performing cluster analysis on the utilization data in the dataset, distorted and duplicate data are filtered out, and the set of utilization data with similar utilization rates is used to obtain the basic dataset. This can reduce the impact of distorted data on the stress test of edge nodes and make the stress test of edge nodes distorted.

[0073] In this embodiment, firstly, based on the utilization rate of edge node resources in the process, a utilization dataset with a non-zero utilization rate is selected from the resource dataset. Then, distorted and duplicate data are deleted from the utilization dataset to obtain the basic dataset. This avoids lag during quantity processing, improves the speed of re-selecting the resource dataset, and avoids stress test distortion of edge nodes caused by distorted data.

[0074] Step S30: From the basic dataset, filter out the edge node resources and the test dataset whose correlation strength with the corresponding process is greater than a preset threshold.

[0075] In this embodiment, the correlation between edge node resources and processes is first calculated to obtain the correlation strength between edge node resources and processes. Then, test datasets with correlation strength greater than a preset threshold are selected from the basic dataset. That is, test datasets of edge node resources that are strongly correlated with processes are selected from the basic dataset in order to restore the real process as much as possible and improve the authenticity of edge node stress testing.

[0076] The preset threshold can be adjusted by the user according to their needs.

[0077] In this embodiment, the correlation strength between edge node resources and processes can be determined by probability distribution. That is, the correlation strength between edge node resources and processes is determined based on the distribution of edge node resources accessed by the same process. Densely distributed edge node resources and processes have a strong correlation, that is, a high correlation strength. For example, if the distribution of disk read resources being accessed is dense during a process, the correlation strength between the process and the disk read resources is high after calculation.

[0078] In this embodiment, the basic dataset is filtered a second time to select data with high relevance to form the test dataset, thereby improving the connection between edge node resources and processes during stress testing and thus enhancing the realism of stress testing.

[0079] Specifically, the step of filtering the edge node resources from the basic dataset and the test dataset whose correlation strength with the corresponding process is greater than a preset threshold includes:

[0080] Step S31: Based on the preset intensity range, the basic dataset is divided to obtain the intensity dataset;

[0081] Step S32: Compare the minimum correlation intensity corresponding to each intensity dataset with the preset threshold, and select test datasets from the intensity datasets whose minimum correlation intensity is greater than the preset threshold.

[0082] In this embodiment, an intensity range is preset, that is, a utilization range is preset. The basic data is divided according to the intensity range to obtain intensity datasets with different related intensities. For example, the intensity range is set as [1,10], [11,20], [21,30], ..., [81,90], [91,100]. The basic dataset is divided according to the intensity range. Then, the minimum related intensity in the intensity dataset is compared with a preset threshold to obtain a test dataset that is greater than the preset threshold.

[0083] The larger the preset threshold, the stronger the correlation between the edge node resources and the process corresponding to the obtained test dataset, and the closer the stress test of the edge node is to reality.

[0084] Step S40: Input the test dataset into a preset test container and control the test container to perform stress tests on the edge nodes.

[0085] It should be noted that the preset test container can be a lightweight container edge cloud environment built on an embedded development board, which uses an edge cloud framework to quickly deploy dynamic computing and storage resource stress load test containers.

[0086] In this embodiment, the test dataset is used as the input set to generate corresponding load pressure on the test container, thereby performing stress testing on the edge nodes, that is, performance testing on the edge nodes. Since the test dataset is an access probability density with strong correlation between edge node resources and processes, it can realistically reflect the relationship between edge node resources and processes, closely integrating the stress testing of edge node resources with the processes, thus improving the realism of the edge node resource stress testing.

[0087] This application provides a stress testing method, apparatus, equipment, and storage medium for industrial edge cloud. Compared with existing technologies that cannot achieve edge cloud performance testing under true industrial stress load scenarios, resulting in low reliability of edge cloud performance testing, this application obtains a resource dataset with time stamps for edge node resources during each process; based on the process, the resource dataset is clustered to obtain a basic dataset corresponding to the process; from the basic dataset, the edge node resources and test datasets with a correlation strength greater than a preset threshold corresponding to the process are selected; the test datasets are input into a preset test container, and the test container is controlled to perform stress testing on the edge nodes. In this application, the acquired edge node resource dataset is clustered according to different processes to obtain the basic dataset corresponding to each process. From the basic dataset, test datasets with a correlation strength between edge node resources and processes greater than a preset threshold are selected. The test datasets are then input into a preset test container to perform stress tests on the edge nodes. In other words, in this application, the acquired edge node resource data under different processes are filtered twice to select test datasets with a correlation strength between edge nodes and processes greater than a preset threshold. The edge nodes are then subjected to stress tests using the test datasets, thus closely integrating stress testing with the processes. This enables performance testing of each edge node under real industrial stress load scenarios, i.e., performance testing of the edge cloud, to improve the credibility of edge cloud performance testing.

[0088] Furthermore, based on the above embodiments of this application, another embodiment of this application is provided, in which reference is made to... Figure 4 Specifically, before the step of filtering the edge node resources from the basic dataset and the test dataset whose correlation strength with the corresponding process is greater than a preset threshold, the method includes:

[0089] Step S100: Calculate the number of accesses to the basic dataset to obtain the access density of the edge node resources when performing the same process.

[0090] In this embodiment, the access frequency of the basic dataset is calculated to obtain the access probability of edge node resources during the process. The access density is determined by the access probability. Edge node resources with high access density have a strong correlation with the process, that is, a strong correlation.

[0091] Step S200: Based on the access density, simulate the same process for the edge node resources under different scenarios to determine the correlation strength between the edge node resources and the process under different scenarios.

[0092] In this embodiment, based on access density, different scenarios of the same process are simulated to determine the correlation strength between edge node resources and the process in each scenario. The correlation strengths obtained from different scenarios of the same process are then averaged to determine a representative correlation strength between edge node resources and the process under different scenarios, thus adapting to scenario changes and restoring the impact of scenarios on stress testing. The correlation strength between edge node resources and the process can be calculated using the probability density function of a Beta distribution.

[0093] Specifically, the mathematical expression for the probability density function of the Beta distribution is:

[0094]

[0095] Where x (0≤x≤1) is a statistical random variable; α and β (α>0, β>0) are the shape parameters of the Beta distribution, B(α,β) is the Beta function with parameters α and β, and f(x; α,β) is the probability density, that is, the correlation strength.

[0096] The expression for the function B(α,β) is:

[0097]

[0098] The shape parameters α and β of the Beta distribution are calculated from the mean and variance of the set, that is, from the mean and variance of the underlying dataset.

[0099] The formula for calculating α is:

[0100]

[0101] Where μ is the mean of the basic dataset, and σ is the variance of the basic dataset.

[0102] The formula for calculating β is:

[0103]

[0104] In this embodiment, the distribution of edge node resources accessed by the same process can be obtained by using the mean and variance of the basic dataset. That is, the distribution of the basic dataset with respect to the process. The access density is determined based on the access distribution.

[0105] It should be noted that the shape parameters α and β of the Beta distribution affect the probability function. The shape parameters α and β of the Beta distribution are determined by the mean and variance of the underlying dataset, that is, α and β are determined by the number of visits.

[0106] In this embodiment, based on the access density, the access situation of the process to the edge node resources under different scenarios is simulated, and distorted data in the access distribution is filtered out. Based on the access density, the correlation between the edge node resources and the process under different scenarios is determined, and the correlation strength is determined.

[0107] Specifically, the step of calculating the access frequency of the basic dataset to obtain the access density of the edge node resources during the same process includes:

[0108] Step S110: Calculate the number of accesses to the basic dataset to obtain the number of times each edge node resource is accessed by the same process.

[0109] Step S120: Perform time-series analysis on the number of times to obtain the access density of the edge node resources when performing the same process.

[0110] In this embodiment, the access count of the basic dataset is calculated to determine the number of times each edge node resource is requested, i.e., the number of times it is accessed, during a process. The access count is analyzed by time series to obtain the access probability of the edge node resource when the same process is performed. The access density is determined based on the access probability, which facilitates secondary screening of the basic dataset to identify edge node resources with high access density. The access density can also better reflect the utilization of edge node resources required by the process.

[0111] Specifically, the step of performing time-series analysis on the number of times to obtain the access density of the edge node resources when performing the same process includes:

[0112] Step S121: Perform time-series analysis on the number of times to obtain the access probability of each edge node resource being accessed by the same process.

[0113] Step S122: Based on the preset time interval, perform density analysis on the access probability to obtain the access density of the edge node resources when the same process is performed in each time interval.

[0114] In this embodiment, the access frequency of edge node resources during the process is divided according to a preset time interval. A probability analysis is performed on the access frequency in each time period to estimate the correlation between the process and the edge node resources. The probability analysis of the access frequency can be represented by a chart or a table, and the average access frequency can be marked in the chart or table. If it is a chart, the access frequency can be represented by dots in the chart, that is, a dot is marked at the corresponding position in the chart for each access. Since the production scenario is affected by production factors such as equipment connection, process design, material balance, and equipment damage, the access to edge node resources may have certain deviations. Therefore, it is necessary to clear the abnormal data in the access frequency distribution chart or access frequency distribution table. That is, the abnormal data in the basic dataset is cleared. For example, the difference between the basic dataset and the mean of the basic dataset is taken to obtain the absolute value of the difference. Data whose absolute value exceeds the preset error is deleted. The remaining basic dataset after clearing is subjected to density analysis to obtain the access density.

[0115] In this embodiment, distorted data resulting from changes in the production scenario are removed from the access counts, resulting in a high-reliability basic dataset. Access count analysis is then performed on this basic dataset to obtain the access density. Using the probability density function of the Beta distribution, the access density of edge node resources is calculated to obtain the probability density of the edge node resources corresponding to the process, i.e., the correlation strength between the process and the edge node. This embodiment enables the association of the same process with edge node resources under different scenarios, allowing stress testing of edge nodes to simulate test results under varying scenarios.

[0116] Furthermore, based on the above embodiments of this application, another embodiment of this application is provided. In this embodiment, before the step of filtering the edge node resources and the test dataset whose correlation strength with the corresponding process is greater than a preset threshold from the basic dataset, the method includes:

[0117] Step B10: Determine the number of times the resource dataset has been retrieved;

[0118] Step B20: If the number of acquisitions is greater than the preset number, then the basic dataset is filtered.

[0119] In this embodiment, in order to ensure the credibility of the edge node stress test and avoid randomness in the testing process, it is necessary to obtain the resource dataset multiple times to ensure the credibility and authenticity of the edge node stress test.

[0120] It should be noted that resource datasets can be obtained from historical data or collected in real time.

[0121] The number of times the edge node resources are accessed can be the number of times they are accessed. In this embodiment, the number of times the edge node resources are accessed can be used for judgment, or the amount of data can be used for judgment. Since the number of times each process accesses the edge node resources is easier to record, the number of times the edge node resources are accessed is used for judgment in this embodiment.

[0122] In this embodiment, the number of data points in the test dataset is increased by judging the number of acquisitions, thereby increasing the number of tests and improving the credibility and authenticity of the edge node stress test.

[0123] Reference Figure 3 , Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.

[0124] like Figure 3 As shown, the stress testing equipment for this industrial edge cloud may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to establish communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0125] Optionally, the industrial edge cloud stress testing equipment may also include a rectangular user interface, a network interface, a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, etc. The rectangular user interface may include a display screen and an input submodule such as a keyboard; optionally, the rectangular user interface may also include standard wired or wireless interfaces. The network interface may optionally include standard wired or wireless interfaces (such as a Wi-Fi interface).

[0126] Those skilled in the art will understand that Figure 3 The stress testing equipment structure of the industrial edge cloud shown does not constitute a limitation on the stress testing equipment of the industrial edge cloud. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0127] like Figure 3As shown, the memory 1005, serving as a storage medium, may include an operating system, a network communication module, and an industrial edge cloud stress testing program. The operating system is a program that manages and controls the hardware and software resources of the industrial edge cloud stress testing equipment, supporting the operation of the industrial edge cloud stress testing program and other software and / or programs. The network communication module is used to enable communication between the various components within the memory 1005, as well as communication with other hardware and software in the industrial edge cloud stress testing system.

[0128] exist Figure 3 In the stress testing device for industrial edge clouds shown, the processor 1001 is used to execute the stress testing program for industrial edge clouds stored in the memory 1005 to implement the steps of the stress testing method for industrial edge clouds described above.

[0129] The specific implementation of the stress testing equipment for industrial edge clouds in this application is basically the same as the various embodiments of the stress testing method for industrial edge clouds described above, and will not be repeated here.

[0130] This application also provides a stress testing device for industrial edge clouds, the stress testing device for industrial edge clouds comprising:

[0131] The acquisition module is used to acquire resource datasets with time stamps for edge node resources during each process.

[0132] The clustering module is used to perform clustering analysis on the resource dataset based on the process to obtain the basic dataset corresponding to the process.

[0133] The filtering module is used to filter out the edge node resources and the test datasets whose correlation strength with the corresponding process is greater than a preset threshold from the basic dataset.

[0134] The testing module is used to input the test dataset into a preset test container and control the test container to perform stress tests on the edge nodes.

[0135] Optionally, the stress testing device for the industrial edge cloud further includes:

[0136] The calculation module is used to calculate the number of accesses to the basic dataset to obtain the access density of the edge node resources when performing the same process.

[0137] The simulation module is used to simulate the same process for the edge node resources under different scenarios based on the access density, and to determine the correlation strength between the edge node resources and the process under different scenarios.

[0138] Optionally, the computing module includes:

[0139] The calculation submodule is used to calculate the number of accesses to the basic dataset to obtain the number of times each edge node resource is accessed by the same process.

[0140] The density sub-module is used to perform time-series analysis on the number of times to obtain the access density of the edge node resources when performing the same process.

[0141] Optionally, the density analysis module includes:

[0142] The timing analysis module is used to perform timing analysis on the number of times to obtain the access probability of each edge node resource being accessed by the same process.

[0143] The density analysis submodule is used to perform density analysis on the access probability based on the preset time interval, so as to obtain the access density of the edge node resources when the same process is performed in each time interval.

[0144] Optionally, the filtering module includes:

[0145] The partitioning module is used to partition the basic dataset based on a preset intensity range to obtain an intensity dataset;

[0146] The comparison module is used to compare the minimum correlation intensity corresponding to each intensity dataset with the preset threshold, and to filter out the test datasets from the intensity datasets where the minimum correlation intensity is greater than the preset threshold.

[0147] Optionally, the clustering module includes:

[0148] The analysis module is used to perform utilization analysis on the resource dataset based on the process, and to obtain the utilization dataset of the edge nodes used in the process;

[0149] Clustering units are used to perform clustering analysis on the dataset to obtain a basic dataset corresponding to the process.

[0150] Optionally, the stress testing device for the industrial edge cloud further includes:

[0151] The judgment module is used to judge the number of times the resource dataset is retrieved;

[0152] A filtering unit is used to filter the basic dataset if the number of acquisitions is greater than a preset number.

[0153] The specific implementation of the stress testing device for industrial edge clouds in this application is basically the same as the various embodiments of the stress testing method for industrial edge clouds described above, and will not be repeated here.

[0154] This application provides a storage medium that stores one or more programs, which can be executed by one or more processors to implement the steps of the stress testing method for industrial edge cloud described above.

[0155] The specific implementation of the storage medium in this application is basically the same as the various embodiments of the stress testing method for industrial edge cloud described above, and will not be repeated here.

[0156] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0157] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0158] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0159] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A stress testing method for industrial edge clouds, characterized in that, The stress testing method for the industrial edge cloud includes: Obtain the resource dataset with time stamps for edge node resources during each process; Based on the aforementioned process, cluster analysis is performed on the resource dataset to obtain a basic dataset corresponding to the process; wherein, the cluster analysis includes aggregating the resource data of the edge node resources used during the process to obtain a basic dataset corresponding to the process. From the basic dataset, select test datasets from the edge node resources whose correlation strength with the corresponding process is greater than a preset threshold; The test dataset is input into a preset test container, and the test container is controlled to perform stress tests on the edge nodes. Before the step of filtering out test datasets from the basic dataset whose correlation strength with the corresponding process in the edge node resources is greater than a preset threshold, the method includes: The access frequency of the basic dataset is calculated to obtain the access density of the edge node resources when performing the same process. Based on the access density, simulations are performed on the edge node resources under different scenarios within the same process to determine the correlation strength between the edge node resources and the process under different scenarios.

2. The stress testing method for industrial edge clouds as described in claim 1, characterized in that, The step of calculating the access frequency of the basic dataset to obtain the access density of the edge node resources during the same process includes: The number of accesses to the basic dataset is calculated to obtain the number of times each edge node resource is accessed by the same process. By performing time-series analysis on the number of times, the access density of the edge node resources is obtained when the same process is performed.

3. The stress testing method for industrial edge clouds as described in claim 2, characterized in that, The step of performing time-series analysis on the number of times to obtain the access density of the edge node resources during the same process includes: By performing time-series analysis on the number of accesses, the access probability of each edge node resource being accessed by the same process is obtained; Based on a preset time interval, a density analysis is performed on the access probability to obtain the access density of the edge node resources when the same process is performed in each time interval.

4. The stress testing method for industrial edge clouds as described in claim 1, characterized in that, The step of filtering out test datasets from the basic dataset that have a correlation strength greater than a preset threshold with the corresponding process from the edge node resources includes: Based on a preset intensity range, the basic dataset is divided to obtain an intensity dataset; The minimum correlation intensity in each intensity dataset is compared with the preset threshold, and test datasets with a minimum correlation intensity greater than the preset threshold are selected from the intensity datasets.

5. The stress testing method for industrial edge clouds as described in claim 1, characterized in that, The step of performing cluster analysis on the resource dataset based on the process to obtain the basic dataset corresponding to the process includes: Based on the aforementioned process, a utilization analysis is performed on the resource dataset to obtain a utilization dataset of the edge nodes used in the process. The utilization analysis includes deleting data with a utilization rate of zero from the resource dataset and filtering to obtain a utilization dataset with a utilization rate of non-zero. The dataset is then subjected to cluster analysis to obtain the basic dataset corresponding to the process.

6. The stress testing method for industrial edge clouds as described in claim 1, characterized in that, Before the step of filtering out test datasets from the basic dataset whose correlation strength with the corresponding process in the edge node resources is greater than a preset threshold, the method includes: The number of times the resource dataset is accessed is determined; the number of times the resource is accessed on the edge node is included. If the number of acquisitions exceeds the preset number, the basic dataset will be filtered.

7. A pressure testing device for industrial edge clouds, characterized in that, The stress testing device for the industrial edge cloud includes: The acquisition module is used to acquire resource datasets with time stamps for edge node resources during each process. A clustering module is used to perform clustering analysis on the resource dataset based on the process to obtain a basic dataset corresponding to the process; wherein, the clustering analysis includes aggregating the resource data of the edge node resources used during the process to obtain a basic dataset corresponding to the process; The filtering module is used to filter out test datasets from the basic dataset that have a correlation strength greater than a preset threshold with the corresponding process in the edge node resources; The testing module is used to input the test dataset into a preset test container and control the test container to perform stress tests on the edge nodes; The stress testing device for the industrial edge cloud is used to achieve: The access frequency of the basic dataset is calculated to obtain the access density of the edge node resources when performing the same process. Based on the access density, simulations are performed on the edge node resources under different scenarios within the same process to determine the correlation strength between the edge node resources and the process under different scenarios.

8. A pressure testing device for industrial edge clouds, characterized in that, The stress testing equipment for the industrial edge cloud includes: a memory, a processor, and a program stored in the memory for implementing the stress testing method for the industrial edge cloud. The memory is used to store the program for implementing the stress testing method for industrial edge cloud; The processor is configured to execute a program that implements the stress testing method for the industrial edge cloud, thereby implementing the steps of the stress testing method for the industrial edge cloud as claimed in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a program for implementing a stress testing method for an industrial edge cloud, which is executed by a processor to implement the steps of the stress testing method for an industrial edge cloud as described in any one of claims 1 to 6.

Images