Performance detection method and device of wireless network and computer readable storage medium

Abstract

The invention provides a wireless network performance detection method and device and a computer readable storage medium. The method comprises the steps of obtaining a value of a to-be-measured parameter to obtain a first value; a value of a first environment parameter is obtained, a second value is obtained, and the correlation between the first environment parameter and the to-be-tested parameter is higher than a threshold value; whether the first value is abnormal or not is detected according to the value range of the to-be-detected parameter corresponding to the second value in the first time period, and selection of the first time period is determined according to the time when the first value is detected. The problem of poor anomaly detection accuracy of the network performance index in the prior art is at least solved.

Description

Technical Field

[0001] The present application relates to the field of network communications, and in particular to a method, device, computer-readable storage medium and electronic device for detecting performance of a wireless network. Background Art

[0002] For the existing network topology, users usually use a network manager (hereinafter referred to as the manager) to collect data on network performance indicators. The manager can be in the form of hardware or software, and users use it to configure and manage network devices. Currently, fixed thresholds are commonly used to detect wireless network performance indicators. This method does not take into account the performance differences of the indicators in different environments and configurations, so it will cause serious false positives and false negatives. To solve the fixed threshold method, there are currently dynamic baseline solutions based on machine learning or deep learning. However, this solution generally only considers the characteristics of the data itself, and trains historical data through regression or aggregation to predict the next trend of the data. This method first has high requirements on the time series of data. Current wireless network performance indicators are generally not periodic in a short time interval, so this method cannot predict some indicators. And because it involves machine learning and deep learning, the complexity of the algorithm is high, resulting in excessive resource consumption of the training model. Or in order to reduce resource consumption, reduce the frequency of model updates. This leads to the situation where the environment is updated but the model is still the old model. Summary of the invention

[0003] The main purpose of the present application is to provide a performance detection method, device, computer-readable storage medium and electronic device for a wireless network, so as to at least solve the problem of poor accuracy of abnormal detection of network performance indicators in the prior art.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a performance detection method for a wireless network is provided, including: obtaining a value of a parameter to be measured to obtain a first value; obtaining a value of a first environmental parameter to obtain a second value, and the correlation between the first environmental parameter and the parameter to be measured is higher than a threshold value; based on a value range of the parameter to be measured corresponding to the second value within a first time period, detecting whether the first value has an abnormality, and the selection of the first time period is determined according to the timing of detecting the first value.

[0005] Optionally, before detecting whether the first value is abnormal based on the value range of the parameter to be measured corresponding to the second value within the first time period, the method also includes: obtaining a first value set of the parameter to be measured and a second value set of the first environmental parameter within the first time period; determining the value of the parameter to be measured corresponding to the value of the first environmental parameter from the first value set, the value of the first environmental parameter and the acquisition time of the corresponding value of the parameter to be measured being the same; dividing the values ​​of the parameter to be measured corresponding to the same value of the first environmental parameter into the same value set to obtain a third value set corresponding to each value of the first environmental parameter; and processing each of the third value sets using a statistical algorithm to determine the upper limit and lower limit of each of the third value sets to obtain the value ranges corresponding to multiple values ​​of the first environmental parameters.

[0006] Optionally, based on the value range of the parameter to be measured corresponding to the second value within the first time period, detecting whether the first value has an abnormality includes one of the following: when the first value is not within the value range corresponding to the second value, determining that the parameter to be measured has an abnormality; when a predetermined number of consecutive first values ​​are not within the value range corresponding to the second value, determining that the parameter to be measured has an abnormality.

[0007] Optionally, after determining that there is an abnormality in the parameter to be measured, the method further includes: when the interval between the current abnormal moment and the historical abnormal moment of the parameter to be measured is greater than a preset range, issuing a first alarm message carrying the current abnormal information of the parameter to be measured; when the interval is less than or equal to the preset range, issuing a second alarm message carrying the current abnormal information and historical abnormal information, wherein the historical abnormal information is the abnormal information corresponding to the historical abnormal moment.

[0008] Optionally, before obtaining the value of the first environmental parameter, the method also includes: obtaining a fourth value set of the parameter to be measured and a fifth value set of multiple environmental parameters; determining the correlation between each of the environmental parameters and the parameter to be measured based on the fourth value set and multiple fifth value sets to obtain multiple first correlation coefficients; and determining the first environmental parameter from the multiple environmental parameters based on the multiple first correlation coefficients.

[0009] Optionally, the first environmental parameter is determined from the multiple environmental parameters based on the multiple first correlation coefficients, including: when the maximum of the multiple first correlation coefficients is greater than a first predetermined value, determining the environmental parameter corresponding to the maximum of the multiple first correlation coefficients as the first environmental parameter, the method also includes: when the maximum of the multiple first correlation coefficients is less than or equal to the first predetermined value, and the data volume of the fourth value set and / or the fifth value set is less than or equal to a second predetermined value, determining the trend correlation between each of the environmental parameters and the parameter to be measured based on the fourth value set and multiple fifth value sets to obtain multiple second correlation coefficients; determining the first environmental parameter from the multiple environmental parameters based on the multiple second correlation coefficients.

[0010] Optionally, according to the fourth value set and multiple fifth value sets, the correlation between each of the environmental parameters and the parameter to be measured is determined to obtain multiple first correlation coefficients, including: determining the covariance of the fourth value set and the fifth value set according to the fourth value set and the fifth value set; determining the standard deviation of the fourth value set and the standard deviation of the fifth value set, and calculating the product of the standard deviation of the fourth value set and the standard deviation of the fifth value set; determining the correlation between the environmental parameter and the parameter to be measured as the ratio of the covariance to the product, and obtaining the first correlation coefficient.

[0011] Optionally, the method also includes: when the maximum of the multiple first correlation coefficients is less than or equal to the first predetermined value, and the data volume of the fourth value set and / or the fifth value set is greater than the second predetermined value, determining that the value range of the parameter to be measured is a preset range; based on the preset range, detecting whether there is an abnormality in the first value.

[0012] Optionally, obtaining a first value set of the parameter to be measured and a second value set of the first environmental parameter within the first time period includes: obtaining an initial value of the parameter to be measured and an initial value of the first environmental parameter within the first time period; eliminating abnormal data in the initial value of the parameter to be measured and the initial value of the first environmental parameter, and the remaining initial values ​​of the parameter to be measured constitute the first value set, and the remaining initial values ​​of the first environmental parameter constitute the second value set.

[0013] According to another aspect of the present application, a performance detection device for a wireless network is provided, including: a first acquisition unit, used to acquire a value of a parameter to be measured to obtain a first value; a second acquisition unit, used to acquire a value of a first environmental parameter to obtain a second value, wherein the correlation between the first environmental parameter and the parameter to be measured is higher than a threshold value; a first detection unit, used to detect whether there is an abnormality in the first value based on a value range of the parameter to be measured corresponding to the second value within a first time period, wherein the selection of the first time period is determined based on the timing of detecting the first value.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0015] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0016] Applying the technical solution of the present application, first obtain the value of the parameter to be measured; then obtain the value of the first environmental parameter whose correlation with the parameter to be measured is higher than the threshold; finally, determine whether the value of the parameter to be measured is abnormal according to the value range of the parameter to be measured corresponding to the value of the first environmental parameter. The present application fully considers the connection between the parameter to be measured and other environmental indicators in the wireless network, and takes the environmental parameter whose correlation with the parameter to be measured is higher than the threshold as the first environmental parameter. In addition, the present application maps the value range of the parameter to be measured to different values ​​of the first environmental parameter, and performs abnormal detection on the value of the parameter to be measured according to the corresponding relationship between the value range of the parameter to be measured and the value of the first environmental parameter, realizing the automatic determination of the value range of the parameter to be measured, without manually setting the upper and lower limits of the performance parameters of the wireless network, and ensuring the high accuracy of abnormal detection. In addition, the process does not involve machine learning, which ensures that the performance detection process has low computational complexity and low computational complexity, and avoids the resource consumption problem caused by the training model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for executing a performance detection method for a wireless network provided in an embodiment of the present application is shown;

[0019] Figure 2 A schematic diagram of a flow chart of a performance detection method for a wireless network provided according to an embodiment of the present application is shown;

[0020] Figure 3 A schematic diagram of a performance detection process of a wireless network according to an embodiment of the present application is shown;

[0021] Figure 4 A schematic diagram of another wireless network performance detection process according to an embodiment of the present application is shown;

[0022] Figure 5 A schematic diagram of a performance detection process of another wireless network according to an embodiment of the present application is shown;

[0023] Figure 6 A schematic diagram showing the corresponding relationship between the negotiation rate and the RSSI according to an embodiment of the present application is shown;

[0024] Figure 7 The figure shows a correspondence between different RSSI data and the value range of the negotiation rate according to an embodiment of the present application;

[0025] Figure 8 A schematic diagram of a performance detection process of another wireless network according to an embodiment of the present application is shown;

[0026] Fig. 9 A schematic diagram of another wireless network performance detection process according to an embodiment of the present application is shown;

[0027] Fig.10 The figure shows another correspondence between different RSSI data and the value range of the negotiation rate according to an embodiment of the present application;

[0028] Fig.11 A structural block diagram of a performance detection device for a wireless network provided according to an embodiment of the present application is shown.

[0029] The drawings include the following reference numerals:

[0030] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0031] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the accompanying drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] As introduced in the background technology, the accuracy of anomaly detection of network performance indicators in the prior art is poor. To solve the above technical problems, the embodiments of the present application provide a performance detection method, device, computer-readable storage medium and electronic device for a wireless network.

[0035] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0036] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a wireless network performance detection method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0037] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the performance detection method of the wireless network in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the method described is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0038] In this embodiment, a performance detection method for a wireless network running on a network manager is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] Figure 2 FIG. 1 is a flow chart of a method for detecting performance of a wireless network according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0040] Step S201, obtaining a value of a parameter to be measured to obtain a first value;

[0041] Specifically, the parameter to be measured is a performance parameter of the wireless network to be detected. The first value is a specific parameter value of the parameter to be measured. The performance parameter of the wireless network is a parameter that displays the performance of the wireless network from different dimensions, also known as a network performance index. The performance parameters are not limited to: access failure when the client enters the AP (Access Point), access time, the number of clients currently mounted on the AP during the communication process between the AP and the client, the CPU utilization of the AP, the negotiation rate between the AP and the client, the signal strength, the packet loss rate, the packet error rate, the retransmission rate in different frequency bands, and the channel utilization of different channels.

[0042] Step S202, obtaining a value of a first environmental parameter to obtain a second value, wherein the correlation between the first environmental parameter and the parameter to be measured is higher than a threshold;

[0043] Specifically, the first environmental parameter is determined from a plurality of performance parameters of the wireless network. A person skilled in the art may select any feasible method to determine a performance parameter having a correlation with the parameter to be measured higher than a threshold value from the plurality of performance parameters as the first environmental parameter, and the present application does not limit the specific method for determining the correlation between the parameter to be measured and each performance parameter. The second value is a specific parameter value of the first environmental parameter.

[0044] Step S203, detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within a first time period, wherein the selection of the first time period is determined according to the timing of detecting the first value.

[0045] Specifically, the value range includes at least one of an upper limit and a lower limit. The first time period can be selected from one day, one week or any other time length. The selection of the first time period can be constant, such as setting one week as the first time period to perform the detection process; the selection of the first time period can also change dynamically with the environment time, for example, first set one week as the first time period, and detect the value of the parameter to be measured one week later as the first value; after detecting for a period of time in the manner described, set one day as the first time period, and detect the value of the parameter to be measured one day later as the first value. In order to ensure the accuracy of the detection result, the interval between the detection time of the first value and the first time period should not be too large.

[0046] Through the embodiment, first obtain the value of the parameter to be measured; then, obtain the value of the first environmental parameter whose correlation with the parameter to be measured is higher than the threshold; finally, determine whether the value of the parameter to be measured is abnormal according to the value range of the parameter to be measured corresponding to the value of the first environmental parameter. The present application fully considers the connection between the parameter to be measured and other environmental indicators in the wireless network, and takes the environmental parameter whose correlation with the parameter to be measured is higher than the threshold as the first environmental parameter. In addition, the present application maps the value range of the parameter to be measured to different values ​​of the first environmental parameter, and performs abnormal detection on the value of the parameter to be measured according to the corresponding relationship between the value range of the parameter to be measured and the value of the first environmental parameter, thereby realizing the automatic determination of the value range of the parameter to be measured, without manually setting the upper and lower limits of the performance parameters of the wireless network, and ensuring the high accuracy of abnormal detection. In addition, the process does not involve machine learning, which ensures that the performance detection process has low computational complexity and low computational complexity, and avoids the resource consumption problem caused by the training model.

[0047] Of course, in addition to the network manager, the method can also be applied to a mobile terminal, a computer terminal or a similar computing device.

[0048] In actual application, at least one may be selected from the plurality of performance parameters as the parameter to be measured according to user needs. That is, there may be one or more parameters to be measured. Before obtaining the value of the parameter to be measured and obtaining the first value, the method further includes: receiving designated information, wherein the designated information is information characterizing that the client specifies one or more performance parameters of the wireless network as the parameter to be measured.

[0049] In an optional solution, before step S203: detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value in the first time period, the method further includes:

[0050] Step S204: obtaining a first value set of the parameter to be measured and a second value set of the first environmental parameter within the first time period;

[0051] Specifically, the first time period includes multiple moments, and the value of the parameter to be measured and the value of the first environmental parameter are obtained once at each moment in the first time period to obtain the values ​​of the parameter to be measured corresponding to multiple moments and the values ​​of the first environmental parameter corresponding to multiple moments.

[0052] Step S205: determining a value of the parameter to be measured corresponding to the value of the first environmental parameter from the first value set, wherein the value of the first environmental parameter and the corresponding value of the parameter to be measured are acquired at the same time;

[0053] Specifically, this condition is obtained at the same time as the corresponding condition between the value of the first environmental parameter and the value of the parameter to be measured, so as to obtain the value of the parameter to be measured corresponding to the value of the first environmental parameter.

[0054] Step S206: Divide the values ​​of the parameter to be measured corresponding to the same value of the first environmental parameter into the same value set, and obtain a third value set corresponding to each value of the first environmental parameter;

[0055] Specifically, each value of the parameter to be measured in the first value set corresponds to a value of the first environment parameter in the second value set. Since there are some identical values ​​of the first environment parameter in the second value set, the values ​​of the parameter to be measured corresponding to the identical values ​​of the first environment parameter are divided into the same value set, and a value set of the parameter to be measured corresponding to each different value of the first environment parameter is obtained, that is, the third value set. After the division, the values ​​of the first environment parameter corresponding to any two of the third value sets are different.

[0056] Step S207: using a statistical algorithm to process each of the third value sets, determining an upper limit value and a lower limit value of each of the third value sets, and obtaining the value ranges corresponding to the values ​​of the plurality of first environmental parameters.

[0057] Specifically, by processing the values ​​of each parameter to be measured in the same third value set using a statistical algorithm, the value range of the values ​​in each third value set, i.e., the upper limit value and the lower limit value, can be obtained, thereby obtaining the corresponding relationship between different values ​​of the first environmental parameter and the value range of the parameter to be measured. The statistical algorithm includes but is not limited to algorithms such as 3-sigma, Z-score, and Box-plot.

[0058] In the embodiment, the value range of the parameter to be measured is mapped to different values ​​of the first environmental parameter through a statistical algorithm, and the correspondence between the value of the first environmental parameter and the value range of the parameter to be measured is obtained. Subsequently, the value range of the parameter to be measured can be determined according to the value of the first environmental parameter and the correspondence, thereby further realizing automatic and accurate determination of the value range of the parameter to be measured, thereby further ensuring that the accuracy of abnormal detection of the parameter to be measured based on the value range is high, and further solving the problem of poor accuracy of detection results caused by using a fixed threshold method to detect whether the network performance indicators of the wireless network are abnormal.

[0059] The value range of the parameter to be measured corresponding to the second value in the first time period refers to the value range corresponding to the value of the first environmental parameter that is the same as the second value in the correspondence between the values ​​of the first environmental parameters and the value ranges. The value range can be obtained by traversing the correspondence according to the second value.

[0060] It should be noted that the value range corresponding to the values ​​of the multiple first environmental parameters is dynamically updated, that is, the process of determining the value range corresponding to the values ​​of the multiple first environmental parameters is performed once every period of time to update the value range.

[0061] In order to further ensure the accuracy of anomaly detection, in some optional embodiments of the present application, step S203: detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within the first time period, includes one of the following:

[0062] Step S2031: when the first value is not within the value range corresponding to the second value, determining that the parameter to be measured is abnormal;

[0063] In the embodiment, when a value of the parameter to be measured is not within the value range, it is determined that the value of the parameter to be measured is abnormal. This can simply and efficiently determine whether the value of the parameter to be measured is abnormal, avoiding abnormal omissions.

[0064] Step S2032: when a predetermined number of consecutive first values ​​are not within the value range corresponding to the second value, it is determined that an abnormality exists in the parameter to be measured.

[0065] In the embodiment, since the value range of the parameter to be measured corresponding to the second value is obtained by statistical methods, there is basically no problem of missed abnormal reports. This embodiment determines that the parameter to be measured is abnormal only when the value of the parameter to be measured is abnormal for multiple consecutive times, thus avoiding the problem of false abnormal reports. That is, this embodiment avoids both the problem of missed abnormal reports and the problem of false abnormal reports.

[0066] Specifically, the continuous predetermined number of the first values ​​refers to the continuous values ​​of the parameter to be measured at the acquisition moment. Those skilled in the art can flexibly set the specific numerical value of the predetermined number according to actual needs, such as setting it to 3, 5, 6, etc. It should be noted that the value ranges corresponding to the values ​​of the parameter to be measured at different moments may be the same or different, depending on whether the values ​​of the first environmental parameters at these moments are the same. When the values ​​of the first environmental parameters at two moments are the same, the value ranges corresponding to the values ​​of the parameter to be measured at these two moments are also the same; and when the values ​​of the first environmental parameters at two moments are different, the value ranges corresponding to the values ​​of the parameter to be measured at these two moments are also different.

[0067] Further, when a predetermined number of consecutive first values ​​are not within the value range corresponding to the second value, it is determined that the parameter to be measured has an abnormality, including: when the value of the parameter to be measured is not within the value range, triggering an abnormality pre-event, and recording the abnormality pre-event at the collection time of the value of the parameter to be measured; determining whether the abnormality pre-event is recorded at the predetermined number of consecutive collection times, and when the abnormality pre-event is recorded at the predetermined number of consecutive collection times, determining that the parameter to be measured has an abnormality.

[0068] In some other optional schemes, after determining that the parameter to be measured has an abnormality, the method further includes: when the interval between the current abnormal moment and the historical abnormal moment of the parameter to be measured is greater than a preset range, issuing a first alarm message carrying the current abnormal information of the parameter to be measured; when the interval is less than or equal to the preset range, issuing a second alarm message carrying the current abnormal information and the historical abnormal information, the historical abnormal information being the abnormal information corresponding to the historical abnormal moment. In this embodiment, when the interval between the current abnormal moment and the historical abnormal moment is long, the problem causing the current abnormality is basically unrelated to the problem causing the historical abnormality, so only the alarm message carrying the current abnormal information is sent out, which is convenient for operation and maintenance personnel to analyze, investigate and repair; and when the interval between the current abnormal moment and the historical abnormal moment is short, the problems causing these abnormalities may be the same or related, so the alarm message carrying the current abnormal information and the historical abnormal information is sent out, which is convenient for operation and maintenance personnel to perform root cause analysis and fault repair based on these abnormal information.

[0069] Specifically, the historical abnormal moment may be the moment when an abnormality occurred last time before the current abnormal moment. The preset range may be any appropriate time range, such as 3, 4, 5 or 6 time slots. The current abnormal information is the abnormal information corresponding to the current abnormal moment; the abnormal information includes the abnormal moment, the name of the parameter to be measured, the value of the parameter to be measured at the abnormal moment, and the values ​​of other performance parameters of the wireless network at the abnormal moment.

[0070] In actual application, the first alarm information and the second alarm information are sent to the terminal device of the operation and maintenance personnel, so that the operation and maintenance personnel can be aware of the abnormality in time and handle the abnormality.

[0071] In order to obtain the first environmental parameter that is highly correlated with the parameter to be measured, according to some other exemplary embodiments of the present application, before step S201: obtaining the value of the first environmental parameter, the method further includes:

[0072] Step S208: obtaining a fourth value set of the parameter to be measured and a fifth value set of multiple environmental parameters;

[0073] Specifically, the plurality of environmental parameters are performance parameters other than the parameter to be measured in the wireless network. The fourth value set and the fifth value set are obtained in the same second time period, the second time period includes a plurality of moments, and a value of the parameter to be measured and a value of each environmental parameter are obtained at each moment in the second time period. The second time period may be the same as or different from the first time period.

[0074] Step S209: determining the correlation between each of the environmental parameters and the parameter to be measured according to the fourth value set and the plurality of fifth value sets, and obtaining a plurality of first correlation coefficients;

[0075] Specifically, by performing correlation analysis on the fourth value set and each fifth value set, the correlation between the parameter to be measured and each environmental parameter is determined, and a first correlation coefficient characterizing the correlation between the parameter to be measured and the environmental parameter is obtained, wherein the first correlation coefficient corresponds one-to-one to the environmental parameter.

[0076] Step S210: determining the first environmental parameter from the plurality of environmental parameters according to the plurality of the first correlation coefficients.

[0077] In the embodiment, a correlation analysis is performed on multiple environmental parameters and the parameters to be measured to obtain multiple first correlation coefficients. The first environmental parameter is determined from multiple environmental parameters based on the multiple first correlation coefficients, thereby further achieving accurate determination of the first environmental parameter, thereby further ensuring that the value range of the parameter to be measured subsequently obtained based on the value of the first environmental parameter is relatively accurate.

[0078] In order to further ensure that multiple first correlation coefficients can be obtained more accurately and quickly, further, according to the fourth value set and multiple fifth value sets, the correlation between each of the environmental parameters and the parameter to be measured is determined to obtain multiple first correlation coefficients, including: according to the fourth value set and the fifth value set, the covariance of the fourth value set and the fifth value set is determined to obtain cov(X,Y); the standard deviation of the fourth value set is determined to obtain δx, and the standard deviation of the fifth value set is determined to obtain δy, and the product of the standard deviation of the fourth value set and the standard deviation of the fifth value set is calculated to obtain δxδy; the correlation between the environmental parameter and the parameter to be measured is determined as the ratio of the covariance to the product, and the first correlation coefficient is obtained as

[0079] In a specific application process, the environmental parameter corresponding to the largest first correlation coefficient may be determined as the first environmental parameter; or other methods may be selected to determine the first environmental parameter from multiple environmental parameters according to multiple first correlation coefficients.

[0080] In an embodiment of the present application, the first environmental parameter is determined from the plurality of environmental parameters according to the plurality of the first correlation coefficients, including: when the maximum of the plurality of the first correlation coefficients is greater than a first predetermined value, determining the environmental parameter corresponding to the maximum of the plurality of the first correlation coefficients as the first environmental parameter. In this embodiment, the maximum of the plurality of first correlation coefficients is compared with the first predetermined value, and when the maximum is greater than the first predetermined value, determining the environmental parameter corresponding to the maximum is the first environmental parameter most correlated with the parameter to be measured, further ensuring that the correlation between the determined first environmental parameter and the parameter to be measured is strong.

[0081] Specifically, the first predetermined value is a preset correlation coefficient threshold, such as 0.7, 0.8, etc., and those skilled in the art can flexibly set the value according to actual needs.

[0082] Based on the embodiment, the method also includes: when the maximum of the multiple first correlation coefficients is less than or equal to the first predetermined value, and the data volume of the fourth value set and / or the fifth value set is less than or equal to the second predetermined value, determining the trend correlation between each of the environmental parameters and the parameter to be measured according to the fourth value set and multiple fifth value sets to obtain multiple second correlation coefficients; determining the first environmental parameter from the multiple environmental parameters according to the multiple second correlation coefficients.

[0083] In the embodiment, taking into account that the amount of data in the network system will affect the accuracy of the correlation analysis, when the maximum of multiple first correlation coefficients is not greater than the first predetermined value and the amount of data analyzed is small, a trend correlation analysis is performed on the environmental parameters and the parameters to be measured, thereby further ensuring that the first environmental parameters that are more relevant to the parameters to be measured can be accurately found when the amount of data in the network system is small, thereby further ensuring that the value range of the parameters to be measured obtained subsequently based on the value of the first environmental parameter is more accurate.

[0084] A person skilled in the art may adopt any suitable method to determine the trend correlation between each of the environmental parameters and the parameter to be measured. According to another optional embodiment of the present application, the trend correlation between each of the environmental parameters and the parameter to be measured is determined according to the fourth value set and multiple fifth value sets to obtain multiple second correlation coefficients, including: processing the fourth value set and the fifth value set in a multiple-up method to determine the trend correlation between the environmental parameter corresponding to the fifth value set and the parameter to be measured, and obtain one of the second correlation coefficients.

[0085] Specifically, multiple surge is a general term for a class of data anomaly detection algorithms. Common multiple surge detection methods include simple thresholds based on the mean, moving average and standard deviation, interquartile range method, distribution-based methods, clustering and other methods. For example, a simple threshold based on the mean can be used, such as setting the threshold to 3 times the mean of the data in a fixed time window. When the real-time data exceeds 3 times the mean, it is judged as a multiple surge; for another example, a distribution-based method uses statistical distributions (such as normal distribution, exponential distribution, etc.) to model the data and calculate the probability of a data point under the distribution. If the probability is lower than a certain threshold (such as 0.01 or 0.001), the data point is considered to be a multiple surge.

[0086] Optionally, the method further includes: when the maximum of the plurality of first correlation coefficients is less than or equal to the first predetermined value, and the data volume of the fourth value set and / or the fifth value set is greater than the second predetermined value, determining that the value range of the parameter to be measured is a preset range; and detecting whether the first value is abnormal based on the preset range. In this embodiment, when the data volume of the network system is large and there is no first correlation coefficient that meets the threshold requirement, in order to achieve normal monitoring of the parameter to be measured, a preset range is used as the value range of the parameter to be measured, and by comparing the value of the parameter to be measured with the range, it is determined whether the value of the parameter to be measured is abnormal, thereby achieving monitoring of the parameter to be measured.

[0087] Optionally, obtaining the first value set of the parameter to be measured and the second value set of the first environmental parameter within the first time period includes: obtaining the initial value of the parameter to be measured and the initial value of the first environmental parameter within the first time period; removing abnormal data from the initial value of the parameter to be measured and the initial value of the first environmental parameter, and the remaining initial values ​​of the parameter to be measured constitute the first value set, and the remaining initial values ​​of the first environmental parameter constitute the second value set. By removing abnormal data from the collected values, it is ensured that the final first value set and the second value set are relatively accurate, providing accurate data support for subsequent abnormality detection.

[0088] Similarly, the fourth value set and multiple fifth value sets are collected by eliminating abnormal data.

[0089] In order to ensure that the latest data can be used for subsequent performance testing, in the actual application process, for a network system with a large amount of data, such as a cloud network, obtaining the first value set of the parameter to be tested in the first time period and the second value set of the first environmental parameter includes: obtaining the first value set and the second value set once every first predetermined time period. For a network system with a small amount of data, such as a local network, obtaining the first value set of the parameter to be tested in the first time period and the second value set of the first environmental parameter includes: obtaining the first value set and the second value set once every second predetermined time period, the first predetermined time period is greater than the second predetermined time period, for example, the first predetermined time period is one month, and the second predetermined time period is one day or one week, etc.

[0090] Similarly, the fourth value set and the plurality of fifth value sets can also be obtained in the manner described. The first environmental parameter can be fixed, that is, it is determined and fixed by the fourth value set and the plurality of fifth value sets; the first environmental parameter can also be dynamically changing, that is, it is determined once every period of time by the fourth value set and the plurality of fifth value sets.

[0091] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the performance detection method of the wireless network of the present application will be described in detail below in combination with specific embodiments.

[0092] This embodiment relates to a specific wireless network performance detection method, such as Figure 3 As shown, the following steps are included:

[0093] Step S1: Select all performance indicators of the current wireless network that need to be tested as parameters to be tested;

[0094] Step S2: Automatically analyze the environmental influencing factors most relevant to the measured parameters, take them as the first environmental parameters, establish a correspondence between different values ​​of the first environmental parameters and the value range of the measured parameters, and regularly update the correspondence. Considering the real-time and efficiency issues of data processing, this application provides two solutions:

[0095] For network systems with large amounts of data, taking cloud networks as an example, you can follow Figure 4 The specific operations are as follows:

[0096] Step S2a1: Obtain all performance indicator data of all users in the current cloud;

[0097] Step S2a2: Perform a preliminary screening of the data, and screen out the data that has not been reported or is obviously misreported. And update the data regularly, such as re-collecting the performance indicator data of all user networks on a monthly basis to ensure that the subsequent anomaly detection model uses the latest data. Since the cloud data contains the network topology performance of different users and the data volume is very large, the sample examples included in the statistical algorithm calculation model are more comprehensive, and the relevant environmental factors obtained by the correlation algorithm will not change;

[0098] Step S2a3: Determine whether the performance indicator already has the most relevant environmental factor, if yes, jump to step S2a5, otherwise jump to step S2a4;

[0099] Step S2a4: Follow Figure 5 The process shown in the figure performs correlation analysis between the measured parameter and the environmental parameter to obtain the first correlation coefficient Among them, cov(X,Y) is the covariance of the two parameter sets, and δx and δy are standard deviations. When the first correlation coefficient reaches the threshold value p, it proves that there is a strong correlation between the two parameters, so it can be used as the environmental influencing factor of the parameter to be tested under the current wireless network, that is, as the first environmental parameter. If no relevant parameter is found, use the preset value range and wait for the data to be updated for re-testing; taking the client's negotiation rate as the parameter to be tested as an example, the specific steps are as follows:

[0100] Assuming that the threshold of the first correlation coefficient is 0.7, the correlation analysis between the negotiation rate data and the environmental parameter data is performed, and the following is obtained: Figure 6 The environmental parameter with the highest correlation with the negotiation rate is the RSSI (Received Signal Strength Indication) between the client and the AP, and the first correlation coefficient between the two reaches 0.9, exceeding 0.7. Therefore, RSSI will be used as the first environmental parameter reflecting the client negotiation rate.

[0101] Step S2a5: Use a statistical algorithm to correspond the upper and lower limits of the parameter to be measured to the data of the first environmental parameter, and regularly use the latest network performance data to update the correspondence to avoid a decrease in the accuracy of abnormal judgment due to changes in network topology and configuration.

[0102] Finally, by performing statistical algorithm analysis on the negotiation rate data under each RSSI, the upper and lower limits of the negotiation rate are obtained, such as Figure 7 As shown. Among them, Figure 7 The corresponding relationship between different RSSI data and the upper and lower limits of the negotiated rate is shown. Since it is the rate, the abnormality only focuses on the lower limit.

[0103] For a network system with a small amount of data, taking the local network as an example, you can follow Figure 8 The specific operations are as follows:

[0104] Step S2b1: Obtain all local performance indicator data of the current user;

[0105] Step S2b2: Perform a preliminary screening of the data, screening out the data that has not been reported or is obviously misreported. The data is updated regularly. Unlike network systems with large data volumes, the corresponding data update cycle is shorter when the data volume is small, generally one day or one week, to re-collect the performance indicator data in all user networks.

[0106] Step S2b3: Follow Fig. 9The process shown performs a correlation analysis between the parameter to be measured and the environmental parameter to obtain a first correlation coefficient. When the first correlation coefficient reaches a threshold value p, it proves that there is a strong correlation between the two parameters. Therefore, it can be used as an environmental influencing factor of the parameter to be measured under the current wireless network, that is, as the first environmental parameter. If a parameter with correlation cannot be found, the trend correlation is used to detect the parameter to be measured and each environmental parameter. The environmental parameter with the highest trend correlation will be determined as the first environmental parameter of the parameter to be measured.

[0107] Step S2b4: By using a statistical algorithm, the upper and lower limits of the parameter to be measured are mapped to the data of the first environmental parameter, and the corresponding relationship is regularly updated using the latest network performance data to avoid a decrease in the accuracy of abnormal judgment due to changes in network topology and configuration;

[0108] Step S3: Collecting real-time data of current wireless network performance indicators;

[0109] Step S4: Find the corresponding upper and lower limits of the parameter to be measured according to the data of the current first environmental parameter, and test the data of the current parameter to be measured. If all are normal, repeat steps S3 and S4;

[0110] Step S5: Since the upper and lower limits are obtained by statistical methods, the underreporting rate is very low and the false alarm rate is high, so it is necessary to make further judgments on abnormal events. Therefore, if an abnormality is detected, the data of the current parameter to be measured will continue to be monitored, and the monitoring data will be recorded, waiting for the subsequent final abnormality judgment;

[0111] Step S6: Starting from the beginning of the abnormal event triggering, when the abnormal event is triggered m times continuously, it is determined that an abnormality exists and is continuously recorded. When the time interval between the time of the next abnormal event and the previous abnormal event is less than n time slots, the abnormal event is merged with the previous one to facilitate subsequent root cause analysis. For example: Assume m = 3, n = 6, such as Fig.10 As shown, at time 13:31:54, an event of exceeding the lower limit occurs, but because it does not occur m times in succession, the final result is not determined as an abnormal event. At time 14:13, the situation of exceeding the lower limit begins to occur 6 times in succession. If it exceeds m times, it is determined to be an abnormality, and then after 5 time intervals (14:16-14:19, less than n), the situation of exceeding the lower limit begins to occur again, so they are classified as the same abnormal event. And so on, until there is no event exceeding the baseline in the subsequent n time slots, then stop recording this abnormal event, issue an alarm, and jump back to step S5.

[0112] The scheme effectively reduces the rate of false positives and false negatives of network performance anomalies caused by fixed thresholds, simplifies the complexity of network performance indicator anomaly detection, and provides a set of standardized processes for network performance indicator anomaly detection and alarm. By associating network environment parameters, the dependence of the correspondence between different first environment parameter data and the value range of the parameter to be measured on the periodicity, timing and other characteristics of the performance indicator data itself during anomaly detection is reduced. And the correspondence effectively takes into account the situation where the indicator data undergoes large changes caused by factors such as network configuration.

[0113] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0114] The embodiment of the present application also provides a performance detection device for a wireless network. It should be noted that the performance detection device for a wireless network in the embodiment of the present application can be used to execute the performance detection method for a wireless network provided in the embodiment of the present application. The device is used to implement the embodiments and preferred implementations, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0115] The following is an introduction to the performance detection device of a wireless network running on a network manager provided in an embodiment of the present application.

[0116] Fig.11 Schematic diagram of a performance detection device for a wireless network according to an embodiment of the present application. Fig.11 As shown, the device comprises:

[0117] A first acquisition unit 10 is used to acquire a value of a parameter to be measured to obtain a first value;

[0118] Specifically, the parameter to be measured is a performance parameter of the wireless network to be detected. The first value is a specific parameter value of the parameter to be measured. The performance parameter of the wireless network is a parameter that displays the performance of the wireless network from different dimensions, also known as a network performance index. The performance parameters are not limited to: access failure when the client enters the AP (Access Point), access time, the number of clients currently mounted on the AP during the communication process between the AP and the client, the CPU utilization of the AP, the negotiation rate between the AP and the client, the signal strength, the packet loss rate, the packet error rate, the retransmission rate in different frequency bands, and the channel utilization of different channels.

[0119] A second acquisition unit 20 is used to acquire a value of a first environmental parameter to obtain a second value, wherein the correlation between the first environmental parameter and the parameter to be measured is higher than a threshold;

[0120] Specifically, the first environmental parameter is determined from a plurality of performance parameters of the wireless network. A person skilled in the art may select any feasible method to determine a performance parameter having a correlation with the parameter to be measured higher than a threshold value from the plurality of performance parameters as the first environmental parameter, and the present application does not limit the specific method for determining the correlation between the parameter to be measured and each performance parameter. The second value is a specific parameter value of the first environmental parameter.

[0121] The first detection unit 30 is used to detect whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within a first time period, and the selection of the first time period is determined according to the timing of detecting the first value.

[0122] Specifically, the value range includes at least one of an upper limit and a lower limit. The first time period can be selected from one day, one week or any other time length. The selection of the first time period can be constant, such as setting one week as the first time period to perform the detection process; the selection of the first time period can also change dynamically with the environment time, for example, first set one week as the first time period, and detect the value of the parameter to be measured one week later as the first value; after detecting for a period of time in the manner described, set one day as the first time period, and detect the value of the parameter to be measured one day later as the first value. In order to ensure the accuracy of the detection result, the interval between the detection time of the first value and the first time period should not be too large.

[0123] Through the embodiment, the value of the parameter to be measured is obtained by the first acquisition unit; the value of the first environmental parameter whose correlation with the parameter to be measured is higher than the threshold value is obtained by the second acquisition unit; and the first detection unit determines whether the value of the parameter to be measured is abnormal according to the value range of the parameter to be measured corresponding to the value of the first environmental parameter. The present application fully considers the connection between the parameter to be measured and other environmental indicators in the wireless network, and takes the environmental parameter whose correlation with the parameter to be measured is higher than the threshold value as the first environmental parameter. In addition, the present application maps the value range of the parameter to be measured to different values ​​of the first environmental parameter, and performs abnormal detection on the value of the parameter to be measured according to the corresponding relationship between the value range of the parameter to be measured and the value of the first environmental parameter, so as to realize the automatic determination of the value range of the parameter to be measured, without manually setting the upper and lower limits of the performance parameters of the wireless network, and ensures that the accuracy of abnormal detection is high. In addition, the process does not involve machine learning, which ensures that the performance detection process has low computational complexity and low computational complexity, and avoids the resource consumption problem caused by the training model.

[0124] Of course, in addition to the network manager, the device can also be applied to a mobile terminal, a computer terminal or a similar computing device.

[0125] In actual application, at least one can be selected from the multiple performance parameters as the parameter to be measured according to user needs. That is, there can be one or more parameters to be measured. The device also includes: a receiving unit, which is used to receive specified information before obtaining the value of the parameter to be measured and obtaining the first value, wherein the specified information is information that characterizes that the client specifies one or more performance parameters of the wireless network as the parameter to be measured.

[0126] In an optional solution, the device further includes:

[0127] A third acquisition unit is used to acquire a first value set of the parameter to be measured in the first time period and a second value set of the first environmental parameter before detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value in the first time period;

[0128] Specifically, the first time period includes multiple moments, and the value of the parameter to be measured and the value of the first environmental parameter are obtained once at each moment in the first time period to obtain the values ​​of the parameter to be measured corresponding to multiple moments and the values ​​of the first environmental parameter corresponding to multiple moments.

[0129] A first determining unit, configured to determine, from the first value set, a value of the parameter to be measured corresponding to the value of the first environmental parameter, wherein the value of the first environmental parameter and the corresponding value of the parameter to be measured are acquired at the same time;

[0130] Specifically, this condition is obtained at the same time as the corresponding condition between the value of the first environmental parameter and the value of the parameter to be measured, so as to obtain the value of the parameter to be measured corresponding to the value of the first environmental parameter.

[0131] A division unit, used for dividing the values ​​of the parameter to be measured corresponding to the same value of the first environmental parameter into the same value set, to obtain a third value set corresponding to each value of the first environmental parameter;

[0132] Specifically, each value of the parameter to be measured in the first value set corresponds to a value of the first environment parameter in the second value set. Since there are some identical values ​​of the first environment parameter in the second value set, the values ​​of the parameter to be measured corresponding to the identical values ​​of the first environment parameter are divided into the same value set, and a value set of the parameter to be measured corresponding to each different value of the first environment parameter is obtained, that is, the third value set. After the division, the values ​​of the first environment parameter corresponding to any two of the third value sets are different.

[0133] The processing unit is used to process each of the third value sets using a statistical algorithm, determine an upper limit value and a lower limit value of each of the third value sets, and obtain the value range corresponding to the values ​​of the plurality of first environmental parameters.

[0134] Specifically, by processing the values ​​of each parameter to be measured in the same third value set using a statistical algorithm, the value range of the values ​​in each third value set, i.e., the upper limit value and the lower limit value, can be obtained, thereby obtaining the corresponding relationship between different values ​​of the first environmental parameter and the value range of the parameter to be measured. The statistical algorithm includes but is not limited to algorithms such as 3-sigma, Z-score, and Box-plot.

[0135] In the embodiment, the value range of the parameter to be measured is mapped to different values ​​of the first environmental parameter through a statistical algorithm, and the correspondence between the value of the first environmental parameter and the value range of the parameter to be measured is obtained. Subsequently, the value range of the parameter to be measured can be determined according to the value of the first environmental parameter and the correspondence, thereby further realizing automatic and accurate determination of the value range of the parameter to be measured, thereby further ensuring that the accuracy of abnormal detection of the parameter to be measured based on the value range is high, and further solving the problem of poor accuracy of detection results caused by using a fixed threshold method to detect whether the network performance indicators of the wireless network are abnormal.

[0136] The value range of the parameter to be measured corresponding to the second value in the first time period refers to the value range corresponding to the value of the first environmental parameter that is the same as the second value in the correspondence between the values ​​of the first environmental parameters and the value ranges. The value range can be obtained by traversing the correspondence according to the second value.

[0137] It should be noted that the value range corresponding to the values ​​of the multiple first environmental parameters is dynamically updated, that is, the process of determining the value range corresponding to the values ​​of the multiple first environmental parameters is performed once every period of time to update the value range.

[0138] In order to further ensure the accuracy of anomaly detection, in some further optional embodiments of the present application, the first detection unit includes one of the following:

[0139] A first determination module, configured to determine that an abnormality exists in the parameter to be measured when the first value is not within the value range corresponding to the second value;

[0140] In the embodiment, when a value of the parameter to be measured is not within the value range, it is determined that the value of the parameter to be measured is abnormal. This can simply and efficiently determine whether the value of the parameter to be measured is abnormal, avoiding abnormal omissions.

[0141] The second determination module is used to determine that the parameter to be measured is abnormal when a predetermined number of consecutive first values ​​are not within the value range corresponding to the second value.

[0142] In the embodiment, since the value range of the parameter to be measured corresponding to the second value is obtained by statistical methods, there is basically no problem of missed abnormal reports. This embodiment determines that the parameter to be measured is abnormal only when the value of the parameter to be measured is abnormal for multiple consecutive times, thus avoiding the problem of false abnormal reports. That is, this embodiment avoids both the problem of missed abnormal reports and the problem of false abnormal reports.

[0143] Specifically, the continuous predetermined number of the first values ​​refers to the continuous values ​​of the parameter to be measured at the acquisition moment. Those skilled in the art can flexibly set the specific numerical value of the predetermined number according to actual needs, such as setting it to 3, 5, 6, etc. It should be noted that the value ranges corresponding to the values ​​of the parameter to be measured at different moments may be the same or different, depending on whether the values ​​of the first environmental parameters at these moments are the same. When the values ​​of the first environmental parameters at two moments are the same, the value ranges corresponding to the values ​​of the parameter to be measured at these two moments are also the same; and when the values ​​of the first environmental parameters at two moments are different, the value ranges corresponding to the values ​​of the parameter to be measured at these two moments are also different.

[0144] Further, the second determination module includes: a triggering submodule, used to trigger an abnormal pre-event when the value of the parameter to be measured is not within the value range, and record the abnormal pre-event at the collection time of the value of the parameter to be measured; a determination submodule, used to determine whether the abnormal pre-event is recorded at the predetermined number of collection times in a row, and determine that the parameter to be measured is abnormal when the abnormal pre-event is recorded at the predetermined number of collection times in a row.

[0145] In some other optional schemes, the device further includes: a first issuing unit, which is used to issue a first alarm message carrying the current abnormal information of the parameter to be measured after determining that the parameter to be measured is abnormal, when the interval between the current abnormal moment and the historical abnormal moment of the parameter to be measured is greater than a preset range; a second issuing unit, which is used to issue a second alarm message carrying the current abnormal information and the historical abnormal information when the interval is less than or equal to the preset range, and the historical abnormal information is the abnormal information corresponding to the historical abnormal moment. In this embodiment, when the interval between the current abnormal moment and the historical abnormal moment is long, the problem causing the current abnormality is basically unrelated to the problem causing the historical abnormality, so only the alarm message carrying the current abnormal information is sent out, which is convenient for the operation and maintenance personnel to analyze, investigate and repair; and when the interval between the current abnormal moment and the historical abnormal moment is short, the problems causing these abnormalities may be the same or related, so the alarm message carrying the current abnormal information and the historical abnormal information is sent out, which is convenient for the operation and maintenance personnel to perform root cause analysis and fault repair according to these abnormal information.

[0146] Specifically, the historical abnormal moment may be the moment when an abnormality occurred last time before the current abnormal moment. The preset range may be any appropriate time range, such as 3, 4, 5 or 6 time slots. The current abnormal information is the abnormal information corresponding to the current abnormal moment; the abnormal information includes the abnormal moment, the name of the parameter to be measured, the value of the parameter to be measured at the abnormal moment, and the values ​​of other performance parameters of the wireless network at the abnormal moment.

[0147] In actual application, the first alarm information and the second alarm information are sent to the terminal device of the operation and maintenance personnel, so that the operation and maintenance personnel can be aware of the abnormality in time and handle the abnormality.

[0148] In order to obtain the first environmental parameter that is highly correlated with the parameter to be measured, according to some other exemplary embodiments of the present application, the device further includes:

[0149] A fourth acquisition unit, used for acquiring a fourth value set of the parameter to be measured and a fifth value set of multiple environmental parameters before acquiring the value of the first environmental parameter;

[0150] Specifically, the plurality of environmental parameters are performance parameters other than the parameter to be measured in the wireless network. The fourth value set and the fifth value set are obtained in the same second time period, the second time period includes a plurality of moments, and a value of the parameter to be measured and a value of each environmental parameter are obtained at each moment in the second time period. The second time period may be the same as or different from the first time period.

[0151] A second determining unit, configured to determine the correlation between each of the environmental parameters and the parameter to be measured according to the fourth value set and the plurality of fifth value sets, to obtain a plurality of first correlation coefficients;

[0152] Specifically, by performing correlation analysis on the fourth value set and each fifth value set, the correlation between the parameter to be measured and each environmental parameter is determined, and a first correlation coefficient characterizing the correlation between the parameter to be measured and the environmental parameter is obtained, wherein the first correlation coefficient corresponds one-to-one to the environmental parameter.

[0153] The third determining unit is used to determine the first environmental parameter from a plurality of the environmental parameters according to a plurality of the first correlation coefficients.

[0154] In the embodiment, a correlation analysis is performed on multiple environmental parameters and the parameters to be measured to obtain multiple first correlation coefficients. The first environmental parameter is determined from multiple environmental parameters based on the multiple first correlation coefficients, thereby further achieving accurate determination of the first environmental parameter, thereby further ensuring that the value range of the parameter to be measured subsequently obtained based on the value of the first environmental parameter is relatively accurate.

[0155] In order to further ensure that multiple first correlation coefficients can be obtained more accurately and quickly, further, the second determination unit includes: a third determination module, used to determine the covariance of the fourth value set and the fifth value set according to the fourth value set and the fifth value set, to obtain cov(X,Y); a fourth determination module, used to determine the standard deviation of the fourth value set to obtain δx, and determine the standard deviation of the fifth value set to obtain δy, and calculate the product of the standard deviation of the fourth value set and the standard deviation of the fifth value set to obtain δxδy; a fifth determination module, used to determine that the correlation between the environmental parameter and the parameter to be measured is the ratio of the covariance to the product, and obtain the first correlation coefficient is

[0156] In a specific application process, the environmental parameter corresponding to the largest first correlation coefficient may be determined as the first environmental parameter; or other methods may be selected to determine the first environmental parameter from multiple environmental parameters according to multiple first correlation coefficients.

[0157] In an embodiment of the present application, the third determination unit includes: a sixth determination module, which is used to determine that the environmental parameter corresponding to the maximum of the plurality of first correlation coefficients is the first environmental parameter when the maximum of the plurality of first correlation coefficients is greater than the first predetermined value. In this embodiment, the maximum of the plurality of first correlation coefficients is compared with the first predetermined value, and when the maximum is greater than the first predetermined value, the environmental parameter corresponding to the maximum is determined to be the first environmental parameter most correlated with the parameter to be measured, further ensuring that the correlation between the determined first environmental parameter and the parameter to be measured is strong.

[0158] Specifically, the first predetermined value is a preset correlation coefficient threshold, such as 0.7, 0.8, etc., and those skilled in the art can flexibly set the value according to actual needs.

[0159] On the basis of the embodiment, the device also includes: a fourth determination unit, used to determine the trend correlation between each of the environmental parameters and the parameter to be measured according to the fourth value set and multiple fifth value sets to obtain multiple second correlation coefficients when the maximum of the multiple first correlation coefficients is less than or equal to the first predetermined value and the data volume of the fourth value set and / or the fifth value set is less than or equal to the second predetermined value; a fifth determination unit, used to determine the first environmental parameter from the multiple environmental parameters according to the multiple second correlation coefficients.

[0160] In the embodiment, taking into account that the amount of data in the network system will affect the accuracy of the correlation analysis, when the maximum of multiple first correlation coefficients is not greater than the first predetermined value and the amount of data analyzed is small, a trend correlation analysis is performed on the environmental parameters and the parameters to be measured, thereby further ensuring that the first environmental parameters that are more relevant to the parameters to be measured can be accurately found when the amount of data in the network system is small, thereby further ensuring that the value range of the parameters to be measured obtained subsequently based on the value of the first environmental parameter is more accurate.

[0161] A person skilled in the art may adopt any suitable method to determine the trend correlation between each of the environmental parameters and the parameter to be measured. According to another optional embodiment of the present application, the fourth determination unit includes: a processing module, used to process the fourth value set and the fifth value set by a multiple-raising method, determine the trend correlation between the environmental parameters corresponding to the fifth value set and the parameter to be measured, and obtain a second correlation coefficient.

[0162] Specifically, multiple surge is a general term for a class of data anomaly detection algorithms. Common multiple surge detection methods include simple thresholds based on the mean, moving average and standard deviation, interquartile range method, distribution-based methods, clustering and other methods. For example, a simple threshold based on the mean can be used, such as setting the threshold to 3 times the mean of the data in a fixed time window. When the real-time data exceeds 3 times the mean, it is judged as a multiple surge; for another example, a distribution-based method uses statistical distributions (such as normal distribution, exponential distribution, etc.) to model the data and calculate the probability of a data point under the distribution. If the probability is lower than a certain threshold (such as 0.01 or 0.001), the data point is considered to be a multiple surge.

[0163] Optionally, the device further includes: a sixth determination unit, configured to determine that the value range of the parameter to be measured is a preset range when the maximum of the plurality of first correlation coefficients is less than or equal to the first predetermined value, and the data volume of the fourth value set and / or the fifth value set is greater than the second predetermined value; and a second detection unit, configured to detect whether the first value is abnormal based on the preset range. In this embodiment, when the data volume of the network system is large and there is no first correlation coefficient that meets the threshold requirement, in order to achieve normal monitoring of the parameter to be measured, a preset range is used as the value range of the parameter to be measured, and by comparing the value of the parameter to be measured with the range, it is determined whether the value of the parameter to be measured is abnormal, thereby achieving monitoring of the parameter to be measured.

[0164] Optionally, the third acquisition unit includes: a first acquisition module, used to acquire the initial value of the parameter to be measured and the initial value of the first environmental parameter within the first time period; and a removal module, used to remove abnormal data from the initial value of the parameter to be measured and the initial value of the first environmental parameter, the remaining initial values ​​of the parameter to be measured constitute the first value set, and the remaining initial values ​​of the first environmental parameter constitute the second value set. By removing abnormal data from the collected values, it is ensured that the final first value set and the second value set are relatively accurate, providing accurate data support for subsequent abnormality detection.

[0165] Similarly, the fourth value set and multiple fifth value sets are collected by eliminating abnormal data.

[0166] In order to ensure that the latest data can be used for subsequent performance testing, in actual application, for a network system with a large amount of data, such as a cloud network, the third acquisition unit includes: a second acquisition module, which is used to acquire the first value set and the second value set once every first predetermined time period. For a network system with a small amount of data, such as a local network, the third acquisition unit includes: a third acquisition module, which is used to acquire the first value set and the second value set once every second predetermined time period, and the first predetermined time period is greater than the second predetermined time period, such as the first predetermined time period is one month, and the second predetermined time period is one day or one week, etc.

[0167] Similarly, the fourth value set and the plurality of fifth value sets can also be obtained in the manner described. The first environmental parameter can be fixed, that is, it is determined and fixed by the fourth value set and the plurality of fifth value sets; the first environmental parameter can also be dynamically changing, that is, it is determined once every period of time by the fourth value set and the plurality of fifth value sets.

[0168] The performance detection device of the wireless network includes a processor and a memory, the first acquisition unit, the second acquisition unit and the first detection unit are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or the modules are located in different processors in any combination.

[0169] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be provided, and the problem of poor accuracy of abnormal detection of network performance indicators in the prior art can be at least solved by adjusting kernel parameters.

[0170] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0171] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the wireless network performance detection method.

[0172] Specifically, the performance detection method of the wireless network includes:

[0173] Step S201, obtaining a value of a parameter to be measured to obtain a first value;

[0174] Step S202, obtaining a value of a first environmental parameter to obtain a second value, wherein the correlation between the first environmental parameter and the parameter to be measured is higher than a threshold;

[0175] Step S203, detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within a first time period, wherein the selection of the first time period is determined according to the timing of detecting the first value.

[0176] An embodiment of the present invention provides a processor, which is used to run a program, wherein the performance detection method of the wireless network is executed when the program is running.

[0177] Specifically, the performance detection method of the wireless network includes:

[0178] Step S201, obtaining a value of a parameter to be measured to obtain a first value;

[0179] Step S202, obtaining a value of a first environmental parameter to obtain a second value, wherein the correlation between the first environmental parameter and the parameter to be measured is higher than a threshold;

[0180] Step S203, detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within a first time period, wherein the selection of the first time period is determined according to the timing of detecting the first value.

[0181] An embodiment of the present invention provides a device, the device including a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0182] Step S201, obtaining a value of a parameter to be measured to obtain a first value;

[0183] Step S202, obtaining a value of a first environmental parameter to obtain a second value, wherein the correlation between the first environmental parameter and the parameter to be measured is higher than a threshold;

[0184] Step S203, detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within a first time period, wherein the selection of the first time period is determined according to the timing of detecting the first value.

[0185] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0186] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0187] Step S201, obtaining a value of a parameter to be measured to obtain a first value;

[0188] Step S202, obtaining a value of a first environmental parameter to obtain a second value, wherein the correlation between the first environmental parameter and the parameter to be measured is higher than a threshold;

[0189] Step S203, detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within a first time period, wherein the selection of the first time period is determined according to the timing of detecting the first value.

[0190] Obviously, those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0191] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0192] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0193] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0194] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0195] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0196] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0197] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0198] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0199] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A performance detection method for a wireless network, characterized in that: include: Obtaining a value of a parameter to be measured to obtain a first value; Obtaining a value of a first environmental parameter to obtain a second value, wherein a correlation between the first environmental parameter and the parameter to be measured is higher than a threshold; According to the value range of the parameter to be measured corresponding to the second value within the first time period, it is detected whether the first value is abnormal, and the selection of the first time period is determined according to the timing of detecting the first value.

2. The method according to claim 1, characterized in that Before detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within the first time period, the method further includes: Acquire a first value set of the parameter to be measured and a second value set of the first environmental parameter within the first time period; Determine, from the first value set, a value of the parameter to be measured corresponding to the value of the first environmental parameter, wherein the value of the first environmental parameter and the corresponding value of the parameter to be measured are acquired at the same time; Dividing the values ​​of the parameter to be measured corresponding to the same value of the first environmental parameter into the same value set, to obtain a third value set corresponding to each value of the first environmental parameter; A statistical algorithm is used to process each of the third value sets, an upper limit value and a lower limit value of each of the third value sets are determined, and the value ranges corresponding to the values ​​of the plurality of first environmental parameters are obtained.

3. The method according to claim 1, characterized in that Detecting whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within the first time period includes one of the following: When the first value is not within the value range corresponding to the second value, determining that the parameter to be measured is abnormal; When a predetermined number of consecutive first values ​​are not within the value range corresponding to the second value, it is determined that the parameter to be measured is abnormal.

4. The method according to claim 3, characterized in that After determining that the parameter to be measured is abnormal, the method further includes: When the time interval between the current abnormal moment and the historical abnormal moment of the parameter to be measured is greater than a preset range, a first alarm message carrying the current abnormal information of the parameter to be measured is issued; When the interval duration is less than or equal to the preset range, a second alarm message carrying the current abnormality information and historical abnormality information is issued, and the historical abnormality information is the abnormality information corresponding to the historical abnormal time.

5. The method according to any one of claims 1 to 4, characterized in that Before obtaining the value of the first environmental parameter, the method further includes: Acquire a fourth value set of the parameter to be measured and a fifth value set of multiple environmental parameters; Determine the correlation between each of the environmental parameters and the parameter to be measured according to the fourth value set and the plurality of fifth value sets, and obtain a plurality of first correlation coefficients; The first environmental parameter is determined from a plurality of the environmental parameters according to the plurality of the first correlation coefficients.

6. The method according to claim 5, characterized in that Determining the first environmental parameter from the plurality of environmental parameters according to the plurality of first correlation coefficients includes: when a maximum of the plurality of first correlation coefficients is greater than a first predetermined value, determining the environmental parameter corresponding to the maximum of the plurality of first correlation coefficients as the first environmental parameter; The method also includes: when the maximum of the multiple first correlation coefficients is less than or equal to the first predetermined value, and the data volume of the fourth value set and / or the fifth value set is less than or equal to the second predetermined value, determining the trend correlation between each of the environmental parameters and the parameter to be measured according to the fourth value set and multiple fifth value sets to obtain multiple second correlation coefficients; and determining the first environmental parameter from the multiple environmental parameters according to the multiple second correlation coefficients.

7. The method according to claim 5, characterized in that Determining the correlation between each of the environmental parameters and the parameter to be measured according to the fourth value set and the plurality of fifth value sets, and obtaining a plurality of first correlation coefficients, including: Determine, according to the fourth value set and the fifth value set, a covariance between the fourth value set and the fifth value set; Determine a standard deviation of the fourth value set and a standard deviation of the fifth value set, and calculate a product of the standard deviation of the fourth value set and the standard deviation of the fifth value set; The correlation between the environmental parameter and the parameter to be measured is determined as a ratio of the covariance to the product, and the first correlation coefficient is obtained.

8. The method according to claim 6, characterized in that The method further comprises: When the maximum of the plurality of first correlation coefficients is less than or equal to the first predetermined value, and the amount of data of the fourth value set and / or the fifth value set is greater than the second predetermined value, determining that the value range of the parameter to be measured is a preset range; According to the preset range, it is detected whether the first value is abnormal.

9. The method according to any one of claims 1 to 4, characterized in that Acquiring a first value set of the parameter to be measured and a second value set of the first environmental parameter within the first time period, including: Obtaining an initial value of the parameter to be measured and an initial value of the first environmental parameter within the first time period; Abnormal data in the initial values ​​of the parameter to be measured and the initial values ​​of the first environmental parameter are eliminated, and the remaining initial values ​​of the parameter to be measured constitute the first value set, and the remaining initial values ​​of the first environmental parameter constitute the second value set.

10. A performance detection device for a wireless network, characterized in that: include: A first acquisition unit, used to acquire a value of the parameter to be measured to obtain a first value; A second acquisition unit, used for acquiring a value of a first environmental parameter to obtain a second value, wherein a correlation between the first environmental parameter and the parameter to be measured is higher than a threshold; The first detection unit is used to detect whether the first value is abnormal according to the value range of the parameter to be measured corresponding to the second value within a first time period, and the selection of the first time period is determined according to the timing of detecting the first value.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 9.

12. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 9.

Images