CN115484188A - TAP device monitoring method and system, electronic device and readable storage medium - Google Patents

Abstract

The invention provides a TAP device monitoring method and system, an electronic device and a readable storage medium, wherein the method comprises the following steps: acquiring state information data and link state data of TAP equipment in real time; storing the state information data and the link state data of the TAP equipment into a network management monitoring platform database; and performing statistical analysis on the state information data and the link state data of the TAP equipment to determine abnormal state information of the equipment and/or abnormal state information of the link. The invention can determine the abnormal state information of the equipment and/or the abnormal state information of the link by collecting and storing the state information data of the TAP equipment and the link state data and analyzing the state information of the TAP equipment and the link state data by adopting an automatic intelligent analysis method, thereby realizing the automatic monitoring of the TAP equipment and the unified monitoring management of the TAP equipment and the link state.

Description

TAP device monitoring method and system, electronic device and readable storage medium

technical field

The invention relates to the technical field of a network management monitoring platform, in particular to a TAP device monitoring method and system, electronic equipment and a readable storage medium.

Background technique

In the prior art, the TAP device has been widely used. The TAP device can display all network data, and realize full wire speed 100% data capture (including error packets) in any duplex state, which is convenient for troubleshooting.

The existing TAP device solution is usually serially connected in the CS domain or PS domain network in the operator's signaling network to realize the replication and aggregation of signaling stream data. For the supervision of TAP equipment, operation and maintenance personnel need to go to the equipment site to check and analyze, which consumes a lot of manpower and is inefficient. At the same time, in the case of a large number of TAP equipment, manual monitoring of TAP equipment still has periodic problems. Monitoring history records such as link interruption, link receiving data error, high link usage, and link overflow cannot be controlled.

Contents of the invention

The invention provides a TAP equipment monitoring method and system, electronic equipment and a readable storage medium to solve the technical defects in the prior art.

The present invention provides a TAP equipment monitoring method, comprising:

Real-time collection of status information data and link status data of TAP equipment;

Store the state information data and link state data of the TAP device in the network management monitoring platform database;

Statistical analysis is performed on the state information data and link state data of the TAP device to determine device abnormal state information and/or link abnormal state information.

According to the TAP device monitoring method of the present invention, the real-time collection of state information data and link state data of the TAP device includes:

Configuring monitoring items for the TAP device, the monitoring items including the status of the TAP device and the link status;

Communicate with the TAP device to realize monitoring item data collection and network status monitoring of the TAP device; the monitoring item data includes status information data and link status data.

According to the TAP device monitoring method of the present invention, storing the state information data and link state data of the TAP device in the network management monitoring platform database includes:

The state information data and link state data of the TAP device are stored in the database of the network management monitoring platform in a round-robin manner, and the storage data space of a preset time length is set in the network management monitoring platform database.

According to the TAP device monitoring method of the present invention, the statistical analysis of the state information data and link state data of the TAP device includes:

Verifying the data compliance of the state information data of the TAP device and the link state data;

For the missing values in the verified data, use the mean value, linear function or prediction algorithm to predict the missing value interpolation to obtain continuous data in time series;

Analyzing and predicting the continuous data in time series.

According to the TAP device monitoring method of the present invention, the statistical analysis of the state information data and link state data of the TAP device is performed to determine the abnormal state information of the device and/or the abnormal state information of the link, including:

Constructing a continuous data set of time and business flow size value and/or the number of traffic packets based on the business flow data in the time series continuous data;

Use the Prophet algorithm, use the Prophet.fit method to perform model fitting on the continuous data set, use the auxiliary method Prophet.make future dataframe to expand the future date by the specified number of data, and use the Prophet.predict method to predict, Obtain the forecast object, which contains a list of predicted values, as well as the analysis and confidence interval of the components;

Calculate the data points where the traffic size and/or the number of traffic packets deviate from the confidence interval, analyze the severity of the deviation, and determine the abnormal state information of the link.

According to the TAP device monitoring method of the present invention, after performing statistical analysis on the state information data and link state data of the TAP device, after determining the abnormal state information of the device and/or the abnormal state information of the link, it includes:

Alarming and displaying based on the abnormal state information of the link;

When the link returns to normal, clear the alarm.

According to the TAP device monitoring method of the present invention, the statistical analysis of the state information data and link state data of the TAP device is performed to determine the abnormal state information of the device and/or the abnormal state information of the link, including:

Configuring an alarm trigger condition for the state of the TAP device and monitoring items associated with the TAP device;

The exponential weighted moving algorithm is used to configure the dynamic threshold for triggering an alarm. The model formula of the exponentially weighted moving algorithm is as follows:

v _t =βv _t-1 +(1-β)θ _t

Among them, the value of β is between 0 and 1, and the value of β is selected according to the changing characteristics of the time series; the historical data is used as the training set of the exponential weighted moving algorithm, and multiple trainings are performed to obtain the β with the smallest prediction error, and the index is saved Weighted moving algorithm model; v _t-1 represents the exponential moving average at time t-1, θ _t represents the actual temperature at time t, and v _t represents the exponential moving average at time t as the alarm dynamic threshold.

The present invention also provides a TAP equipment monitoring system, comprising:

The real-time acquisition module is used for real-time acquisition of the state information data and link state data of the TAP device;

A data storage module, configured to store the state information data and link state data of the TAP device in the network management monitoring platform database;

The statistical analysis module is used to perform statistical analysis on the state information data and link state data of the TAP device, and determine the abnormal state information of the device and/or the abnormal state information of the link.

The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, it realizes monitoring of the TAP device as described above. method steps.

The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the TAP device monitoring methods described above are realized.

The present invention collects and stores the state information data and link state data of the TAP device, and analyzes the TAP device state information and link state data by an automatic intelligent analysis method, so as to determine the abnormal state information and/or link state information of the device. Abnormal status information can realize automatic monitoring of TAP equipment, and realize unified monitoring and management of TAP equipment and link status.

Description of drawings

In order to more clearly illustrate the present invention or the technical solutions in the prior art, the accompanying drawings that need to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are the present invention. For some embodiments of the invention, those skilled in the art can also obtain other drawings based on these drawings without creative effort.

Fig. 1 is a schematic flow chart of the TAP device monitoring method provided by the present invention;

Fig. 2 is the structural representation of the TAP equipment monitoring system provided by the present invention;

Fig. 3 is a schematic structural diagram of an electronic device provided by the present invention.

detailed description

In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention , but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

A kind of TAP equipment monitoring method of the present invention is described below in conjunction with Fig. 1, and execution subject such as this method is network management monitoring platform, and this method comprises:

S1. Real-time collection of state information data and link state data of the TAP device;

The network management monitoring platform is connected to the switch network to realize the access of the TAP device. Its status information is used to judge whether the following abnormalities occur: received data error, high port usage, power supply, memory usage, CPU usage, etc., link The link status data is used to judge whether the following abnormalities occur: monitor link interruption, link overflow, etc.

S2, storing the state information data and link state data of the TAP device in the database of the network management monitoring platform;

The storage is carried out in a round-robin manner, with a fixed size of storage data space. When the storage is full, the new data will overwrite the oldest data, and the cycle continues, so that only the collected data of a fixed length of time can be saved.

S3. Statistically analyze the state information data and link state data of the TAP device, and determine device abnormal state information and/or link abnormal state information.

Configure the TAP device alarm trigger condition on the network management monitoring platform, associate with the TAP device monitoring item, and configure the trigger alarm threshold. If the status information data reaches the trigger alarm threshold, it indicates that the device status is abnormal. Link abnormal status can be based on traffic size, traffic packet Statistical analysis is performed on data such as the number of links to determine link abnormal state information.

The present invention collects and stores the state information data and link state data of the TAP device, and analyzes the TAP device state information and link state data by an automatic intelligent analysis method, so as to determine the abnormal state information and/or link state information of the device. Abnormal status information can realize automatic monitoring of TAP equipment, and realize unified monitoring and management of TAP equipment and link status.

According to the TAP device monitoring method of the present invention, the real-time collection of state information data and link state data of the TAP device includes:

Configure monitoring items for the TAP device, the monitoring items include the status of the TAP device and the link status; the monitoring items mainly monitor link interruption, received data error, high port usage, link overflow, power supply, Memory usage, CPU usage, etc.

Communicate with the TAP device to realize monitoring item data collection and network status monitoring of the TAP device; the monitoring item data includes status information data and link status data.

The network management monitoring platform communicates with the TAP device through SNMP, proxy, ping port and other methods to realize the data collection of the monitoring items of the TAP device and the monitoring of the network status.

According to the TAP device monitoring method of the present invention, storing the state information data and link state data of the TAP device in the network management monitoring platform database includes:

The state information data and link state data of the TAP device are stored in the database of the network management monitoring platform in a round-robin manner, and the storage data space of a preset time length is set in the network management monitoring platform database. The network management monitoring platform stores the data collection of key indicators of TAP equipment in a round-robin manner, and fixes a size of storage data space. When the storage is full, the new data will overwrite the oldest data and keep circulating, so that only the fixed data can be saved. The length of time to collect data.

According to the TAP device monitoring method of the present invention, the statistical analysis of the state information data and link state data of the TAP device includes:

Verifying the data compliance of the state information data of the TAP device and the link state data;

For the missing values in the verified data, use the mean value, linear function or prediction algorithm to predict the missing value interpolation to obtain continuous data in time series;

Analyzing and predicting the continuous data in time series.

First, verify the data compliance to ensure data integrity. For the missing values in the data, use the mean value, linear function or the predicted value of the prediction algorithm to interpolate the missing value. Ensure that the data has continuity in time series after preprocessing.

According to the TAP device monitoring method of the present invention, the statistical analysis of the state information data and link state data of the TAP device is performed to determine the abnormal state information of the device and/or the abnormal state information of the link, including:

Constructing a continuous data set of time and business flow size value and/or the number of traffic packets based on the business flow data in the time series continuous data;

The network management monitoring platform collects business traffic data, and performs statistical analysis on data such as traffic size and traffic packets.

Analyze and predict the flow size, count and measure the flow size every five minutes, construct a continuous data collection of time and flow size values. Use the Prophet algorithm, use the Prophet.fit method to perform model fitting on the continuous data set, use the auxiliary method Prophet.make future dataframe to expand the future date by the specified number of data, and use the Prophet.predict method to predict, Obtain the forecast object, which contains a list of predicted values, as well as the analysis and confidence interval of the components;

Calculate the data points where the traffic size and/or the number of traffic packets deviate from the confidence interval, analyze the severity of the deviation, and determine the abnormal state information of the link. Calculate the data points where the flow size deviates from the confidence interval, analyze the severity of the deviation, and give an alarm for the very serious and serious data points, so as to monitor the traffic with abnormal size. Use the same method to analyze and predict the number of traffic packets, so as to monitor abnormal traffic packets. And give an alarm for abnormal traffic.

According to the TAP device monitoring method of the present invention, after performing statistical analysis on the state information data and link state data of the TAP device, after determining the abnormal state information of the device and/or the abnormal state information of the link, it includes:

Alarming and displaying based on the abnormal state information of the link;

Through the TAP device model of the network management monitoring platform, the network topology of the TAP device can be added, and the specified TAP device can be found in the current view and other views, and the connection relationship between the TAP device and its switch, including the number of connections, and the monitoring indication of the TAP device, etc. Information, you can also view TAP device-related faults, performance information, and related alarm details and alarm history information. For the entry of TAP device model design query statistics, historical record query is provided;

Add automatic discovery (according to the configuration file), including automatic discovery of TAP devices according to network segments, discovery of single-point TAP devices and various automatic discovery methods;

The display of TAP devices configured on the network management monitoring platform is mainly presented in the form of points, lines, and planes. In order to highlight the problematic TAP devices or connection relationships, the topological connections are lightened under normal conditions (such as light green), and device alarms or When the performance warning value is reached, the relevant network elements are rendered with coloring. When the alarm is cleared or is lower than the performance warning value, the coloring returns to normal, and the automatic page refresh time is less than 60 seconds.

When the link returns to normal, clear the alarm.

Alarm type: including all alarm types, which can be filtered according to alarm type, alarm level, and alarm state; the network management monitoring platform monitors the TAP device alarm display page. When the link connection of the trigger alarm is disconnected, an alarm occurs, and when the link is restored, the alarm will be automatically released.

Configure the TAP device alarm trigger conditions on the network management monitoring platform, associate with the TAP device monitoring items, and configure the trigger alarm threshold. Different thresholds will generate different alarm levels; the threshold setting is no longer based on experience. Machine learning algorithms dynamically calculate settings. Therefore, according to the TAP device monitoring method of the present invention, the statistical analysis of the state information data and link state data of the TAP device is performed to determine the abnormal state information of the device and/or the abnormal state information of the link, including:

Configuring an alarm trigger condition for the state of the TAP device and monitoring items associated with the TAP device;

The exponential weighted moving algorithm is used to configure the dynamic threshold for triggering an alarm. The model formula of the exponentially weighted moving algorithm is as follows:

v _t =βv _t-1 +(1β)θ _t

Among them, the value of β is between 0 and 1, and the value of β is selected according to the changing characteristics of the time series; the historical data is used as the training set of the exponential weighted moving algorithm, and multiple trainings are performed to obtain the β with the smallest prediction error, and the index is saved Weighted moving algorithm model; v _t-1 represents the exponential moving average at time t-1, θ _t represents the actual temperature at time t, and v _t represents the exponential moving average at time t as the alarm dynamic threshold, which is EWMA Value, that is, the alarm dynamic threshold, also known as EXPMA indicator, it is also a trend indicator, the exponential moving average is an exponentially decreasing weighted moving average. The value of β is selected according to the changing characteristics of the time series. The coefficient β indicates the speed of weighted decline, and the smaller the value, the faster the weight decreases; if the fluctuation of the time series is not large and relatively stable, then β should be smaller, such as 0.1 to 0.3; if the time series has a rapid and obvious tendency to change , then β should be larger, such as 0.7~0.9. β is determined by trial calculation and comparison of multiple values, and whichever β value causes the smallest prediction error will be used.

The complex dynamic threshold is determined by the weighted moving average method (EWMA) learning algorithm. The characteristic of the EWMA algorithm is that the recent observation value has a greater impact on the threshold setting, and it can better reflect the recent change trend of the data. The historical data is used as the training set of the EWMA algorithm, multiple trainings are performed to obtain the β with the smallest prediction error, the EWMA model is saved, and then the future data is predicted, and the predicted value is used as the alarm threshold.

Referring to FIG. 2 , the TAP device monitoring system provided by the present invention will be described below. The TAP device monitoring system described below and the TAP device monitoring method described above can be referred to in correspondence.

The real-time collection module 10 is used for real-time collection of state information data and link state data of the TAP device;

The network management monitoring platform is connected to the switch network to realize the access of the TAP device. Its status information is used to judge whether the following abnormalities occur: received data error, high port usage, power supply, memory usage, CPU usage, etc., link The link status data is used to judge whether the following abnormalities occur: monitor link interruption, link overflow, etc.

Data storage module 20, for storing the state information data and link state data of the TAP equipment in the network management monitoring platform database;

The storage is carried out in a round-robin manner, with a fixed size of storage data space. When the storage is full, the new data will overwrite the oldest data, and the cycle continues, so that only the collected data of a fixed length of time can be saved.

The statistical analysis module 30 is configured to perform statistical analysis on the state information data and link state data of the TAP device, and determine device abnormal state information and/or link abnormal state information.

Configure the TAP device alarm trigger condition on the network management monitoring platform, associate with the TAP device monitoring item, and configure the trigger alarm threshold. If the status information data reaches the trigger alarm threshold, it indicates that the device status is abnormal. Link abnormal status can be based on traffic size, traffic packet Statistical analysis is performed on data such as the number of links to determine link abnormal state information.

According to the TAP equipment monitoring system of the present invention, the real-time acquisition module 10 is used for:

Configure monitoring items for the TAP device, the monitoring items include the status of the TAP device and the link status; the monitoring items mainly monitor link interruption, received data error, high port usage, link overflow, power supply, Memory usage, CPU usage, etc.

Communicate with the TAP device to realize monitoring item data collection and network status monitoring of the TAP device; the monitoring item data includes status information data and link status data.

The network management monitoring platform communicates with the TAP device through SNMP, proxy, ping port and other methods to realize the data collection of the monitoring items of the TAP device and the monitoring of the network status.

According to the TAP equipment monitoring system of the present invention, the data storage module 20 is used for:

The state information data and link state data of the TAP device are stored in the database of the network management monitoring platform in a round-robin manner, and the storage data space of a preset time length is set in the network management monitoring platform database. The network management monitoring platform stores the data collection of key indicators of TAP equipment in a round-robin manner, and fixes a size of storage data space. When the storage is full, the new data will overwrite the oldest data and keep circulating, so that only the fixed data can be saved. The length of time to collect data.

According to the TAP equipment monitoring system of the present invention, the statistical analysis module 30 is used for:

Verifying the data compliance of the state information data of the TAP device and the link state data;

For the missing values in the verified data, use the mean value, linear function or prediction algorithm to predict the missing value interpolation to obtain continuous data in time series;

Analyzing and predicting the continuous data in time series.

First, verify the data compliance to ensure data integrity. For the missing values in the data, use the mean value, linear function or the predicted value of the prediction algorithm to interpolate the missing value. Ensure that the data has continuity in time series after preprocessing.

According to the TAP equipment monitoring system of the present invention, the statistical analysis module 30 is used for:

Constructing a continuous data set of time and business flow size value and/or the number of traffic packets based on the business flow data in the time series continuous data;

The network management monitoring platform collects business traffic data, and performs statistical analysis on data such as traffic size and traffic packets.

Analyze and predict the flow size, count and measure the flow size every five minutes, construct a continuous data collection of time and flow size values. Use the Prophet algorithm, use the Prophet.fit method to perform model fitting on the continuous data set, use the auxiliary method Prophet.make future dataframe to expand the future date by the specified number of data, and use the Prophet.predict method to predict, Obtain the forecast object, which contains a list of predicted values, as well as the analysis and confidence interval of the components;

Calculate the data points where the traffic size and/or the number of traffic packets deviate from the confidence interval, analyze the severity of the deviation, and determine the abnormal state information of the link. Calculate the data points where the flow size deviates from the confidence interval, analyze the severity of the deviation, and give an alarm for the very serious and serious data points, so as to monitor the traffic with abnormal size. Use the same method to analyze and predict the number of traffic packets, so as to monitor abnormal traffic packets. And give an alarm for abnormal traffic.

According to the TAP equipment monitoring system of the present invention, the system also includes an alarm module, and the alarm module is used for:

Alarming and displaying based on the abnormal state information of the link;

Through the TAP device model of the network management monitoring platform, the network topology of the TAP device can be added, and the specified TAP device can be found in the current view and other views, and the connection relationship between the TAP device and its switch, including the number of connections, and the monitoring indication of the TAP device, etc. Information, you can also view TAP device-related faults, performance information, and related alarm details and alarm history information. For the entry of TAP device model design query statistics, historical record query is provided;

Add automatic discovery (according to the configuration file), including automatic discovery of TAP devices according to network segments, discovery of single-point TAP devices and various automatic discovery methods;

The display of TAP devices configured on the network management monitoring platform is mainly presented in the form of points, lines, and planes. In order to highlight the problematic TAP devices or connection relationships, the topological connections are lightened under normal conditions (such as light green), and device alarms or When the performance warning value is reached, the relevant network elements are rendered with coloring. When the alarm is cleared or is lower than the performance warning value, the coloring returns to normal, and the automatic page refresh time is less than 60 seconds.

When the link returns to normal, clear the alarm.

Alarm type: including all alarm types, which can be filtered according to alarm type, alarm level, and alarm state; the network management monitoring platform monitors the TAP device alarm display page. When the link connection of the trigger alarm is disconnected, an alarm occurs, and when the link is restored, the alarm will be automatically released.

Configure the TAP device alarm trigger conditions on the network management monitoring platform, associate with the TAP device monitoring items, and configure the trigger alarm threshold. Different thresholds will generate different alarm levels; the threshold setting is no longer based on experience. Machine learning algorithms dynamically calculate settings. Therefore, according to the TAP equipment monitoring system of the present invention, the statistical analysis module 30 is used for:

Configuring an alarm trigger condition for the state of the TAP device and monitoring items associated with the TAP device;

The exponential weighted moving algorithm is used to configure the dynamic threshold for triggering an alarm. The model formula of the exponentially weighted moving algorithm is as follows:

v _t =βv _t-1 +(1-β)θ _t

Among them, the value of β is between 0 and 1, and the value of β is selected according to the changing characteristics of the time series; the historical data is used as the training set of the exponential weighted moving algorithm, and multiple trainings are performed to obtain the β with the smallest prediction error, and the index is saved Weighted moving algorithm model; v _t-1 represents the exponential moving average at time t-1, θ _t represents the actual temperature at time t, and v _t represents the exponential moving average at time t as the alarm dynamic threshold, which is EWMA Value, that is, the alarm dynamic threshold, also known as EXPMA indicator, it is also a trend indicator, the exponential moving average is an exponentially decreasing weighted moving average. The value of β is selected according to the changing characteristics of the time series. The coefficient β indicates the speed of weighted decline, and the smaller the value, the faster the weight decreases; if the fluctuation of the time series is not large and relatively stable, then β should be smaller, such as 0.1 to 0.3; if the time series has a rapid and obvious tendency to change , then β should be larger, such as 0.7~0.9. β is determined by trial calculation and comparison of multiple values, and whichever β value causes the smallest prediction error will be used.

The complex dynamic threshold is determined by the weighted moving average method (EWMA) learning algorithm. The characteristic of the EWMA algorithm is that the recent observation value has a greater impact on the threshold setting, and it can better reflect the recent change trend of the data. The historical data is used as the training set of the EWMA algorithm, multiple trainings are performed to obtain the β with the smallest prediction error, the EWMA model is saved, and then the future data is predicted, and the predicted value is used as the alarm threshold.

FIG. 3 illustrates a schematic diagram of the physical structure of an electronic device, which may include: a processor (processor) 310, a communication interface (Communications Interface) 320, a memory (memory) 330, and a communication bus 340, wherein the processor 310, The communication interface 320 and the memory 330 communicate with each other through the communication bus 340 . The processor 310 can call the logic instructions in the memory 330 to execute the TAP device monitoring method, and the method includes:

S1. Real-time collection of state information data and link state data of the TAP device;

S2, storing the state information data and link state data of the TAP device in the database of the network management monitoring platform;

S3. Statistically analyze the state information data and link state data of the TAP device, and determine device abnormal state information and/or link abnormal state information.

In addition, the above logic instructions in the memory 430 may be implemented in the form of software function units and be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. .

On the other hand, the present invention also provides a computer program product, the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer During execution, the computer can perform the TAP device monitoring method provided by each of the above methods, the method comprising:

S1. Real-time collection of state information data and link state data of the TAP device;

S2, storing the state information data and link state data of the TAP device in the database of the network management monitoring platform;

S3. Statistically analyze the state information data and link state data of the TAP device, and determine device abnormal state information and/or link abnormal state information.

In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it is implemented to perform the TAP device monitoring methods provided above, the method comprising:

S1. Real-time collection of state information data and link state data of the TAP device;

S2, storing the state information data and link state data of the TAP device in the database of the network management monitoring platform;

S3. Statistically analyze the state information data and link state data of the TAP device, and determine device abnormal state information and/or link abnormal state information.

The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative effort.

Through the above description of the implementations, those skilled in the art can clearly understand that each implementation can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims (10)

1. A TAP device monitoring method, comprising:

acquiring state information data and link state data of TAP equipment in real time;

storing the state information data and the link state data of the TAP equipment into a network management monitoring platform database;

and performing statistical analysis on the state information data of the TAP equipment and the link state data to determine equipment abnormal state information and/or link abnormal state information.

2. The TAP device monitoring method of claim 1, wherein the collecting of the state information data and the link state data of the TAP device in real time comprises:

configuring a monitoring item for the TAP device, wherein the monitoring item comprises the state of the TAP device and the link state;

the monitoring system is communicated with TAP equipment to realize data acquisition of monitoring items of the TAP equipment and monitoring of network states; the monitoring item data includes status information data and link status data.

3. The TAP device monitoring method of claim 1, wherein the storing the state information data and the link state data of the TAP device into a network management monitoring platform database comprises:

and storing the state information data and the link state data of the TAP equipment into a network management monitoring platform database in a round-robin manner, wherein the network management monitoring platform database is provided with a storage data space with a preset time length.

4. The TAP device monitoring method of any one of claims 1 through 3, wherein said statistically analyzing the state information data and the link state data of the TAP device comprises:

verifying the data compliance of the state information data and the link state data of the TAP equipment;

performing missing value interpolation on the checked missing values in the data in a prediction mode by adopting a mean value, a linear function or a prediction algorithm to obtain data with continuity in time sequence;

and analyzing and predicting the data with continuity in time sequence.

5. The TAP device monitoring method according to claim 4, wherein the determining of device abnormal state information and/or link abnormal state information by performing statistical analysis on the state information data and the link state data of the TAP device comprises:

constructing a continuous data set of time, a service flow size value and/or a flow packet number based on service flow data in the data with continuity in time sequence;

performing model fitting on the continuous data set by a Prophet algorithm and a Prophet.fit method, expanding the future date by a specified data number by using an auxiliary method, namely a Prophet.make future dataframe, and predicting by a Prophet.predict method to obtain a forecast object, wherein the forecast object comprises a column of predicted values, and analysis and confidence intervals of components;

and calculating the data point of the deviation of the flow size and/or the flow packet number from the confidence interval, analyzing the deviation degree and severity to determine the abnormal state information of the link.

6. The TAP device monitoring method according to claim 2, wherein after performing statistical analysis on the state information data and the link state data of the TAP device to determine device abnormal state information and/or link abnormal state information, the method comprises:

based on the link abnormal state information, alarming and displaying;

and when the link is recovered to be normal, the alarm is released.

7. The TAP device monitoring method according to claim 4, wherein the determining of device abnormal state information and/or link abnormal state information by performing statistical analysis on the state information data and the link state data of the TAP device comprises:

configuring an alarm triggering condition, a monitoring item associated to the TAP device, for a state of the TAP device;

an exponential weighting mobile algorithm is adopted to configure a dynamic threshold value for triggering alarm, and the model formula of the exponential weighting mobile algorithm is as follows:

ν _t ＝βν _t-1 +(1-β)θ _t

wherein, the value of beta is between 0 and 1, and the value of beta is selected according to the variation characteristic of the time sequence; taking historical data as a training set of the exponential weighted moving algorithm, carrying out multiple times of training to obtain beta with the minimum prediction error, and storing an exponential weighted moving algorithm model; v is _t-1 Denotes the exponential moving average, theta, at time t-1 _t Representing the actual temperature at time t, v _t Represents an exponential moving average at time t as the dynamic threshold for the alarm.

8. A TAP device monitoring system, comprising:

the real-time acquisition module is used for acquiring the state information data and the link state data of the TAP equipment in real time;

the data storage module is used for storing the state information data and the link state data of the TAP equipment into a network management monitoring platform database;

and the statistical analysis module is used for performing statistical analysis on the state information data and the link state data of the TAP equipment to determine the abnormal state information of the equipment and/or the abnormal state information of the link.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the TAP device monitoring method of any one of claims 1 to 7 are implemented when the program is executed by the processor.

10. A non-transitory computer-readable storage medium, having stored thereon a computer program, which, when being executed by a processor, carries out the steps of the TAP device monitoring method according to any one of claims 1 to 7.

Images