A network operation and maintenance management system and method based on big data

Abstract

The present invention discloses a network operation and maintenance management system and method based on big data, which belongs to the field of network operation and maintenance management technology, including a monitoring module, which monitors the relevant parameter information of the router during operation; an operation and maintenance management platform, which analyzes and processes the acquired relevant parameter information to determine whether there is an abnormal risk in the operation of the router; a real-time alarm module, which issues a corresponding alarm when it is determined that the operation of the router has an abnormal risk; and an early warning judgment module, which performs an early warning analysis on the potential abnormal risk of the router when it is determined that the operation of the router is normal. When the operation of the router is normal, the present invention performs a comprehensive analysis based on the abnormal value fluctuations generated within a fixed period, the accumulation of abnormal value differences, and the abnormal frequency of the log, to perform an early warning analysis on the potential abnormal risk of the router, so that the potential risk of the router can be discovered, hidden risks can be solved early, and the occurrence of subsequent failures can be reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of network operation and maintenance management, and specifically relates to a network operation and maintenance management system and method based on big data. Background Art

[0002] Network operation and maintenance management refers to the management of daily network operations by relevant departments, including real-time monitoring of network equipment and systems, troubleshooting, performance optimization, security reinforcement, resource allocation, and daily maintenance to ensure stable, secure, and efficient operation of the network.

[0003] Since routers are important devices in network equipment, they can connect to external networks, allowing multiple devices to connect to the Internet through the same network to achieve data transmission and information sharing. Existing router inspections are generally manual inspections, which are mostly single-item independent inspections. Since single-item inspections are prone to accidental errors, they can easily lead to inaccurate inspection results. In addition, existing router inspections can only be carried out after a router network failure occurs, and potential failure risks cannot be predicted. When a failure occurs, it will affect the normal transmission of network data. Summary of the invention

[0004] The purpose of the present invention is to provide a network operation and maintenance management system and method based on big data to solve the problems faced by the above-mentioned background technology.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A network operation and maintenance management system based on big data, the management system comprising:

[0007] A monitoring module, which is used to monitor the relevant parameter information of the router during operation and send it to the operation and maintenance management platform;

[0008] An operation and maintenance management platform, which is used to analyze and process the acquired relevant parameter information, thereby generating an abnormal value to determine whether there is an abnormal risk in the operation status of the router;

[0009] A real-time alarm module, which generates a corresponding alarm when it is determined that the router operation status has an abnormal risk;

[0010] The early warning judgment module performs early warning analysis on the potential abnormal risks of the router when judging that the router is operating normally, thereby issuing corresponding early warnings.

[0011] Furthermore, the relevant parameter information includes the signal strength generated by the router, the network speed generated by the router, the CPU utilization of the router, the memory utilization of the router, the temperature of the router, and abnormal conditions in the log of the router.

[0012] Furthermore, the method for generating an abnormal value by the operation and maintenance management platform is:

[0013] Get the signal strength RSS generated by the router, the network speed V generated by the router, and the CPU utilization U of the router CPU 、Router memory usage U RAM , the temperature of the router T;

[0014] By formula The outlier value R is obtained;

[0015] Among them, RSS st is the standard signal strength generated by the router, V st is the standard network speed generated by the router, U CPUst is the standard CPU utilization of the router, U RAMst is the standard memory usage of the router, T st is the standard temperature of the router, ΔU CPU is the preset CPU utilization reference value, ΔU RAM is the preset memory usage reference value, and ΔT is the preset temperature reference value.

[0016] Furthermore, the operation and maintenance management platform determines whether there is an abnormal risk in the operation status of the router by:

[0017] The obtained outlier value R is compared with the outlier threshold R preset in the system. th1 To compare:

[0018] When R>R th1 When the router is running abnormally, it is judged that there is a risk of abnormality;

[0019] Otherwise, the router is judged to be operating normally.

[0020] Furthermore, the method for the real-time alarm module to make an alarm is:

[0021] It includes level 1 alarm and level 2 alarm. Level 2 alarm is more serious than level 1 alarm. The abnormal value R obtained is compared with another abnormal value threshold R preset in the system. th2 Compare, R th1 <R th2 ;

[0022] Level 1 alarm: When R th1 <R≤R th2When a fault occurs, a level 1 alarm is generated to remind the operation and maintenance personnel to check the status of the router;

[0023] Second level alarm: when R>R th2 When the router is disconnected, a secondary alarm is generated, the router connection is disconnected, and the operation and maintenance personnel are reminded to repair or replace the router.

[0024] Furthermore, the method by which the early warning judgment module performs early warning analysis on the potential abnormal risk of the router is:

[0025] When the router is operating normally, obtain the time variation curve R(t) of the abnormal value R every fixed period ΔT, and the number of abnormalities k in the router log within the fixed period;

[0026] By formula Obtain the warning value W;

[0027] The obtained warning value W is compared with the warning value threshold W set by the system th To compare:

[0028] When W>W th If the router is abnormal, it means that there is a potential abnormal risk.

[0029] Among them, ρ is the abnormal fluctuation coefficient within a fixed period, R 0 (t) is the time-varying curve of the standard abnormal value preset in the system, t 1 is the start time of the fixed cycle, t 2 The end time of the fixed period.

[0030] Furthermore, the method for obtaining the abnormal fluctuation coefficient ρ within the fixed period is:

[0031] Collect the size of abnormal values ​​n times in a fixed period, and record the size R of the abnormal value collected each time i , i∈[1,n];

[0032] So through the formula The abnormal fluctuation coefficient ρ within a fixed period is obtained.

[0033] A network operation and maintenance management method based on big data, the management method is executed and managed by the above-mentioned network operation and maintenance management system based on big data, and the management method includes the following steps:

[0034] Step 1: Real-time monitoring of the relevant parameter information of the router during operation, including the signal strength generated by the router, the network speed generated by the router, the CPU utilization rate of the router, the memory utilization rate of the router, the temperature of the router, and any abnormalities in the router log;

[0035] Step 2: Analyze and process the acquired relevant parameter information to generate abnormal values, and judge whether there is abnormal risk in the operation of the router according to the abnormal values;

[0036] Step 3: When there is an abnormal risk in the operation of the router, a corresponding real-time alarm is issued to the router according to the magnitude of the abnormal value;

[0037] Step 4: When there is no abnormal risk in the operation of the router, an early warning analysis of the potential abnormal risk of the router is performed based on the abnormal value situation and the log abnormal situation.

[0038] Beneficial effects of the present invention:

[0039] The present invention monitors in real time the signal strength generated by the router during operation, the network speed generated by the router, the CPU utilization rate of the router, the memory utilization rate of the router, the temperature of the router, and the abnormality of the log of the router and other related parameter information, and sends it to the operation and maintenance management platform for analysis and processing, thereby generating an abnormal value, and judging whether the operation status of the router has an abnormal risk according to the size of the abnormal value, without the need for manual inspection, thus saving human resources and improving the monitoring accuracy, and during the analysis and processing, combining a variety of parameters of the router during operation for comprehensive analysis to judge whether the router has an abnormal risk, thus reducing the error caused by accidental factors and making the monitoring result more accurate, and when judging that the operation status of the router has an abnormal risk, timely giving an alarm of a corresponding degree to remind the operation and maintenance management personnel to carry out corresponding processing on the router.

[0040] When the router is operating normally, the present invention can conduct a comprehensive analysis on the abnormal value fluctuations, abnormal value difference accumulation and log abnormality frequency generated within a fixed period to conduct early warning analysis on the potential abnormal risks of the router. In this way, the potential risks of the router can be discovered to solve the hidden risks early and reduce the occurrence of subsequent failures, thereby ensuring the normal data transmission.

[0041] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0043] Figure 1 is a system block diagram of the present invention;

[0044] Figure 2 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] In one embodiment, a network operation and maintenance management system based on big data is disclosed. Figure 1 As shown, the management system mainly includes:

[0047] Monitoring module: The monitoring module is used to monitor the relevant parameter information of the router during operation and send it to the operation and maintenance management platform. The relevant parameter information includes the signal strength generated by the router, the network speed generated by the router, the CPU utilization rate of the router, the memory utilization rate of the router, the temperature of the router, and any abnormalities in the router log;

[0048] The operation and maintenance management platform is used to analyze and process the acquired relevant parameter information, thereby generating abnormal values ​​to determine whether there is an abnormal risk in the operation of the router;

[0049] Real-time alarm module: The real-time alarm module will issue corresponding alarms when it determines that the router operation status has abnormal risks;

[0050] The early warning judgment module, when judging that the router is operating normally, performs early warning analysis on the potential abnormal risks of the router, and thus issues corresponding early warnings.

[0051] Through the above technical solution, the present application monitors the relevant parameter information of the router in real time during operation, including the signal strength generated by the router, the network speed generated by the router, the CPU utilization rate of the router, the memory utilization rate of the router, the temperature of the router, and the abnormal situation of the log of the router, and sends it to the operation and maintenance management platform. The operation and maintenance management platform analyzes and processes the obtained relevant parameter information to generate abnormal values, and judges whether there is an abnormal risk in the operation of the router according to the size of the abnormal value. No manual inspection is required, which saves human resources and improves the monitoring accuracy. When analyzing and processing, a comprehensive analysis is performed in combination with various parameters of the router during operation to judge whether there is an abnormal risk in the router, which can reduce the error caused by accidental factors and make the monitoring result more accurate; at the same time, when it is judged that there is an abnormal risk in the operation of the router, an alarm of a corresponding degree can be made in time to remind the operation and maintenance management personnel to deal with the router accordingly; and when it is judged that the operation of the router is normal, the potential abnormal risk of the router can be analyzed according to the abnormal value within a fixed period, so that the potential risk of the router can be discovered to solve the hidden hidden dangers as early as possible and reduce the occurrence of subsequent failures, thereby ensuring the normal transmission of data.

[0052] As an implementation mode of the present invention, the method for the operation and maintenance management platform to generate an abnormal value is:

[0053] Get the signal strength RSS generated by the router, the network speed V generated by the router, and the CPU utilization U of the router CPU 、Router memory usage U RAM , the temperature of the router T;

[0054] By formula The outlier value R is obtained;

[0055] Among them, RSS st is the standard signal strength generated by the router, V st is the standard network speed generated by the router, U CPUst is the standard CPU utilization of the router, U RAMst is the standard memory usage of the router, T st is the standard temperature of the router, ΔU CPU is the preset CPU utilization reference value, ΔU RAM is the preset memory usage reference value, ΔT is the preset temperature reference value;

[0056] The operation and maintenance management platform determines whether there is an abnormal risk in the operation of the router by:

[0057] The obtained outlier value R is compared with the outlier threshold R preset in the system. th1To compare:

[0058] When R>R th1 When the router is running abnormally, it is judged that there is a risk of abnormality;

[0059] Otherwise, the router is judged to be operating normally.

[0060] Through the above technical scheme, the present invention provides a method for the operation and maintenance management platform to generate an abnormal value and a method for judging whether there is an abnormal risk in the operation status of the router according to the abnormal value. Generally speaking, the operation status of the router is related to the signal strength generated by the router, the network speed generated by the router, the CPU utilization rate of the router, the memory utilization rate of the router, the temperature of the router, etc. The better the signal strength and the faster the network speed, the better the operation status of the router. If the CPU utilization rate of the router, the memory utilization rate of the router, and the temperature change of the router are within a normal and reasonable range, it means that the operation status of the router is also good. Therefore, the present embodiment first obtains the signal strength RSS generated by the router, the network speed V generated by the router, and the CPU utilization rate U of the router. CPU 、Router memory usage U RAM , the temperature of the router T, and then through the formula The outlier value R is obtained; from the formula, it can be seen that when the ratio between the standard signal strength and the obtained signal strength is The larger the value, the ratio between the standard network speed and the obtained network speed The larger the value, the better the router is running. The difference between the CPU utilization of the router and the standard CPU utilization is The smaller the difference between the router's memory usage and the standard memory usage is, the smaller the difference between the router's memory usage and the standard memory usage is. The smaller the value, the greater the difference between the router temperature and the standard temperature. The smaller the value, the smaller the changes in CPU utilization, memory usage, temperature, etc. during the operation of the router, indicating that the router is in good condition. A comprehensive analysis is performed to obtain the outlier value R. It can be seen that the larger the outlier value R is, the more it indicates that there is an abnormal risk in the operation of the router. Therefore, the obtained outlier value R is compared with the outlier value threshold R preset in the system. th1 Compare: When R>R th1 If the router is running abnormally, it is judged that there is an abnormal risk; otherwise, it is judged that the router is running normally. In this way, a comprehensive analysis can be performed on various parameters of the router during operation to determine whether the router has an abnormal risk, which can reduce the error caused by accidental factors and make the monitoring results more accurate.

[0061] In the above technical solution, the standard signal strength RSS generated by the router st , the standard network speed V generated by the router st , the standard CPU utilization of the router U CPUst , the router's standard memory usage U RAMst , Standard temperature of the router T st It can be determined based on the historical operation data of the relevant routers in the large database, and the preset CPU utilization reference value ΔU CPU , the preset memory usage reference value ΔU RAM , the preset temperature reference value ΔT and the abnormal value threshold R preset in the system th1 All of these can be determined based on empirical data and will not be described in detail here.

[0062] As an implementation mode of the present invention, the method for the real-time alarm module to make an alarm is:

[0063] It includes level 1 alarm and level 2 alarm. Level 2 alarm is more serious than level 1 alarm. The abnormal value R obtained is compared with another abnormal value threshold R preset in the system. th2 Compare, R th1 <R th2 ;

[0064] Level 1 alarm: When R th1 <R≤R th2 When a fault occurs, a level 1 alarm is generated to remind the operation and maintenance personnel to check the status of the router;

[0065] Second level alarm: when R>R th2 When the router is disconnected, a secondary alarm is generated, the router connection is disconnected, and the operation and maintenance personnel are reminded to repair or replace the router.

[0066] Through the above technical solution, this embodiment provides a method for the real-time alarm module to alarm. First, the alarm is divided into a first-level alarm and a second-level alarm according to the severity of the alarm, wherein the severity of the second-level alarm is higher than that of the first-level alarm. Then, the obtained abnormal value R is compared with another abnormal value threshold R preset in the system. th2 For comparison, when R th1 <R≤R th2 When R>R th2When the router is at a high risk of abnormality, a secondary alarm is generated. In order to ensure the security of the entire network, the router connection is disconnected in time, and the operation and maintenance management personnel are reminded to repair and replace the router. In this way, the operation and maintenance management personnel can deal with the router accordingly according to the severity of the alarm, which is convenient for operation and maintenance management to implement.

[0067] As an implementation mode of the present invention, the method in which the early warning judgment module performs early warning analysis on the potential abnormal risk of the router is:

[0068] When the router is operating normally, obtain the time variation curve R(t) of the abnormal value R every fixed period ΔT, and the number of abnormalities k in the router log within the fixed period;

[0069] By formula Obtain the warning value W;

[0070] The obtained warning value W is compared with the warning value threshold W set by the system th To compare:

[0071] When W>W th If the router is abnormal, it means that there is a potential abnormal risk.

[0072] Among them, ρ is the abnormal fluctuation coefficient within a fixed period, R 0 (t) is the time-varying curve of the standard abnormal value preset in the system, t 1 is the start time of the fixed cycle, t 2 The end time of the fixed period;

[0073] The method for obtaining the abnormal fluctuation coefficient ρ within a fixed period is:

[0074] Collect the size of abnormal values ​​n times in a fixed period, and record the size R of the abnormal value collected each time i , i∈[1,n];

[0075] So through the formula The abnormal fluctuation coefficient ρ within a fixed period is obtained.

[0076] Through the above technical solution, this embodiment provides a method for the early warning judgment module to perform early warning analysis on the potential abnormal risk of the router. Since the set abnormal value threshold is a fixed value set manually, if the abnormal value in a certain period does not exceed the abnormal value threshold but is always near the threshold, although no alarm is triggered at this time, it can also indicate that there is an abnormal risk in the operation of the router; therefore, when the operation of the router is normal, this embodiment sets a fixed detection period, obtains the abnormal value R over time curve R(t) every fixed period ΔT, and the number of abnormalities k in the router log within the fixed period, and collects the size of the abnormal value n times within the fixed period, and records the size of the abnormal value R collected each time i , and then through the formula The warning value W is obtained, where formula It can represent the fluctuation of abnormal values ​​generated in a fixed period. If its value is larger, it means that the fluctuation of abnormal values ​​in the fixed period is larger, which means that it is more unstable. The formula It represents the cumulative difference between the abnormal value changes generated within a fixed period and the standard abnormal value changes. Obviously, the larger its value is, the greater the possibility of abnormal risk of the router. Similarly, if the frequency of abnormalities in the router log within a fixed period is higher, it can also indicate that the possibility of abnormal risk of the router is greater. Therefore, the larger the value of the warning value W is, the more it can indicate that the router has potential abnormal risk. Therefore, the obtained warning value W is compared with the warning value threshold W set by the system. th Compare, when W>W th , it indicates that there is a potential abnormal risk in the router. In this way, when the router is running normally, a comprehensive analysis can be performed based on the abnormal value fluctuations generated within a fixed period, the accumulation of abnormal value differences, and the log abnormality frequency to conduct an early warning analysis of the potential abnormal risk of the router. In this way, the potential risks of the router can be discovered to solve hidden risks early and reduce the occurrence of subsequent failures, thereby ensuring normal data transmission.

[0077] In the above technical solution, the standard abnormal value preset in the system changes with time curve R 0 (t), the warning value threshold W set by the system th Both can be determined based on relevant historical data in a large database combined with empirical data, while the start time and end time of the fixed period ΔT can be determined artificially based on actual conditions, which will not be described in detail here.

[0078] It should be noted that the calculation formulas and various parameters involved in the calculations in the present invention have been dimensionally processed in advance, and the process of dimensionless processing is well known in the industry and will not be described here.

[0079] In one embodiment, a network operation and maintenance management method based on big data is also disclosed. Figure 2 As shown, the management method includes the following steps:

[0080] Step 1: Real-time monitoring of the relevant parameter information of the router during operation, including the signal strength generated by the router, the network speed generated by the router, the CPU utilization rate of the router, the memory utilization rate of the router, the temperature of the router, and any abnormalities in the router log;

[0081] Step 2: Analyze and process the acquired relevant parameter information to generate abnormal values, and judge whether there is abnormal risk in the operation of the router according to the abnormal values;

[0082] Step 3: When there is an abnormal risk in the operation of the router, a corresponding real-time alarm is issued to the router according to the magnitude of the abnormal value;

[0083] Step 4: When there is no abnormal risk in the operation of the router, an early warning analysis of the potential abnormal risk of the router is performed based on the abnormal value situation and the log abnormal situation.

[0084] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A network operation and maintenance management system based on big data, characterized in that: The management system comprises: A monitoring module, which is used to monitor the relevant parameter information of the router during operation and send it to the operation and maintenance management platform. The relevant parameter information includes the signal strength generated by the router, the network speed generated by the router, the CPU utilization rate of the router, the memory utilization rate of the router, the temperature of the router, and abnormal conditions in the log of the router; An operation and maintenance management platform, which is used to analyze and process the acquired relevant parameter information, thereby generating an abnormal value to determine whether there is an abnormal risk in the operation status of the router; A real-time alarm module, which generates a corresponding alarm when it is determined that the router operation status has an abnormal risk; An early warning judgment module, when judging that the router is running normally, the early warning judgment module performs early warning analysis on the potential abnormal risks of the router, thereby issuing corresponding early warnings; The method for generating an abnormal value by the operation and maintenance management platform is: obtaining the signal strength RSS generated by the router, the network speed V generated by the router, and the CPU utilization U of the router CPU 、Router memory usage U RAM , the temperature of the router T; By formula The outlier value R is obtained; Among them, RSS st is the standard signal strength generated by the router, V st The standard network speed generated by the router. is the standard CPU utilization of the router, is the standard memory usage of the router, T st is the standard temperature of the router, ΔU CPU is the preset CPU utilization reference value, ΔU RAM is the preset memory usage reference value, ΔT is the preset temperature reference value; The method of the early warning judgment module for early warning analysis of the potential abnormal risk of the router is: when the router is operating normally, every fixed period ΔT, obtain the abnormal value R over time curve R(t), and the number of abnormalities k in the router log within the fixed period; By formula Obtain the warning value W; The obtained warning value W is compared with the warning value threshold W set by the system th To compare: When W>W th If the router is abnormal, it means that there is a potential abnormal risk. Among them, ρ is the abnormal fluctuation coefficient within the fixed period, R0(t) is the time-varying curve of the standard abnormal value preset in the system, t1 is the start time of the fixed period, and t2 is the end time of the fixed period; The method for obtaining the abnormal fluctuation coefficient ρ within the fixed period is: collect the abnormal value size n times within the fixed period, and record the abnormal value size R collected each time i , i∈[1,n]; So through the formula The abnormal fluctuation coefficient ρ within a fixed period is obtained.

2. According to the big data-based network operation and maintenance management system of claim 1, it is characterized in that: The method for the operation and maintenance management platform to determine whether there is an abnormal risk in the operation status of the router is: The obtained outlier value R is compared with the outlier threshold R preset in the system. th1 To compare: When R>R th1 When the router is running abnormally, it is judged that there is a risk of abnormality; Otherwise, the router is judged to be operating normally.

3. A network operation and maintenance management system based on big data according to claim 2, characterized in that: The method for the real-time alarm module to perform an alarm is: It includes level 1 alarm and level 2 alarm. Level 2 alarm is more serious than level 1 alarm. The abnormal value R obtained is compared with another abnormal value threshold R preset in the system. th2 Compare, R th1 <R th2 ; Level 1 alarm: When R th1 <R≤R th2 When a fault occurs, a level 1 alarm is generated to remind the operation and maintenance personnel to check the status of the router; Second level alarm: when R>R th2 When the router is disconnected, a secondary alarm is generated, the router connection is disconnected, and the operation and maintenance personnel are reminded to repair or replace the router.

4. A network operation and maintenance management method based on big data, characterized in that: The management method is executed and managed by the network operation and maintenance management system based on big data according to any one of claims 1 to 3, and the management method comprises the following steps: Step 1: Monitor the relevant parameter information of the router in real time during operation, including the signal strength generated by the router, the network speed generated by the router, the CPU utilization rate of the router, the memory utilization rate of the router, the temperature of the router, and any abnormalities in the router log; Step 2: Analyze and process the acquired relevant parameter information to generate abnormal values, and judge whether there is abnormal risk in the operation of the router according to the abnormal values; Step 3: When there is an abnormal risk in the operation of the router, a corresponding real-time alarm is issued to the router according to the magnitude of the abnormal value; Step 4: When there is no abnormal risk in the operation of the router, an early warning analysis of the potential abnormal risk of the router is performed based on the abnormal value situation and the log abnormal situation.

Images