CN114297255B - Network quality work order fault early warning method based on log analysis - Google Patents
Network quality work order fault early warning method based on log analysis Download PDFInfo
- Publication number
- CN114297255B CN114297255B CN202111554152.2A CN202111554152A CN114297255B CN 114297255 B CN114297255 B CN 114297255B CN 202111554152 A CN202111554152 A CN 202111554152A CN 114297255 B CN114297255 B CN 114297255B
- Authority
- CN
- China
- Prior art keywords
- work order
- period
- index
- network
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 238000013179 statistical model Methods 0.000 claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000011084 recovery Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Abstract
The invention provides a network quality work order fault early warning method based on log analysis, which comprises the following steps: constructing a log server and receiving index monitoring values of all network devices; setting an index threshold value for each network device; respectively counting the index anomaly times of each network device in each period of each region, and recording whether a fault work order is generated in the corresponding period of the corresponding region; constructing a statistical database and storing statistical information; calculating the generation probability of the work order faults in each time period of each region on the n+1 day according to the statistical information of the n th day in the statistical database by calculating the statistical model parameters of the work order faults; and dividing the early warning grades by setting different early warning thresholds according to the generation probability of the work order faults. The invention establishes the statistical model by using the historical index monitoring value and the historical work order fault information of each network device, can early warn the network quality fault work orders of different time periods of each region, is beneficial to improving the operation and maintenance efficiency of the network system, and further improves the overall service efficiency of the network system.
Description
Technical Field
The invention belongs to the technical field of computer networks, and particularly relates to a network quality work order fault early warning method based on log analysis.
Background
With the rapid development of information industry, the variety and traffic of services carried on wide area networks are continuously increasing, the scale is also continuously expanding, and a large number of terminal access devices are widely used. Meanwhile, network systems are becoming larger and more complex, and they generally comprise thousands or even tens of thousands of network devices deployed in different urban areas, and in order to ensure smooth performance of related network services of the network system in each urban area, it is necessary to monitor network quality of each network device and process the network device in time when a network failure occurs. However, the operation and maintenance of the network device is a passive operation and maintenance at present, that is, after the failure occurs, the failure is reflected to the related departments through the work order, and then the related departments assign technicians to perform the troubleshooting and recovery, so that a long time is required from the failure generation to the recovery. If the work order faults of the network system in different time periods of different urban areas can be pre-warned, related personnel can improve the monitoring strength before the work order faults occur, so that problems can be quickly found to solve the possible faults, and the service efficiency of the network system can be obviously improved greatly.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a network quality work order fault early warning method based on log analysis, which adopts the following technical scheme:
A network quality work order fault early warning method based on log analysis comprises the following steps:
step 1: constructing a log server for receiving network quality index monitoring values of a plurality of network devices in each area;
Step 2: setting an index threshold for each network device, and if the network quality index monitoring value of each network device is greater than the index threshold, calling the network quality index monitoring value as an index abnormal value;
Step 3: analyzing network quality index monitoring values in a log server in a regional and time-division mode, respectively counting the occurrence times of index abnormal values of each network device in each time period in each region every day, and recording whether a fault work order is generated in the corresponding time period of the corresponding region;
Step 4: constructing a statistical database for storing the statistical information in the step 3; the statistical database contains the occurrence times of index abnormal values of each network device in each period of each region and whether fault work orders are generated or not;
step 5: according to the statistical information in the statistical database, calculating the statistical model parameters of the work order fault, including the work order fault generation probability of each time period in each region, the average value of the occurrence times of index abnormal values of each network device when the work order fault is generated in each time period in each region, and the fault contribution rate of each network device in each time period in each region;
Step 6: combining the statistical model parameters obtained in the step 5, and calculating the generation probability of work order faults in each time period in each region on the n+1 day according to the statistical information on the n day in the statistical database;
step 7: and dividing the early warning level by setting different early warning thresholds according to the generation probability of the work order faults in each time period of each region on the n+1th day.
Further, in step 5, the calculation formula of the job ticket failure occurrence probability of each period in each area is:
Wherein, p Failure of (Ai,Tj) represents the work order fault generation probability of the A i area T j period, M represents the statistical days, statistics is carried out once per period each day, and M (A i,Tj) represents the number of times of work order faults generated in the A i area T j period.
Further, in step 5, the average value of the occurrence times of the abnormal index values of the network devices when the work order fault occurs in each period in each region is recorded as the average value of the abnormal index times, and the calculation formula is as follows:
wherein, Index anomaly frequency mean value of v-th network equipment when work order faults occur in T j period of A i area is represented, and index anomaly frequency mean value of v-th network equipment is represented by "/>And (3) indicating the index anomaly times of the v-th network equipment when the U-th work order fails, counted in the period T j of the A i area, and assuming that the U work order fails are counted in M days.
Further, in step 5, the calculation formula of the fault contribution rate of each network device in each period in each area is as follows:
where a (a i,Tj, v) represents the failure contribution rate of the v-th network device of the a i region T j period, The index anomaly number average value of the V-th network device in the period T j in the area a i is represented, and a total of V network devices in the area a i are assumed.
Further, in step 6, the calculation method of the generation probability of the work order fault in the n+1st day A i area T j period is as follows:
first, the failure probability of each network device in the a i area T j period is calculated separately:
Then, the generation probability p n+1(Ai,Tj of work order faults in the time period T j of the A i area on the n+1th day is calculated,
Wherein p (A i,Tj, v) represents the failure probability of the v-th network device in the period of T j in the A i area, and D n(Ai,Tj, v) represents the index anomaly number of the v-th network device in the period of T j in the A i area counted on the nth day.
Further, in step 7, if p n+1(Ai,Tj)＞β1 is detected, a light early warning is performed; if p n+1(Ai,Tj)＞β2 is detected, performing moderate early warning; if p n+1(Ai,Tj)＞β3 is detected, carrying out severe early warning; beta 1、β1、β1 is different pre-warning thresholds, and beta 1＜β2＜β3.
The beneficial effects of the invention are as follows: compared with the prior art, the invention establishes the statistical model by using the historical index monitoring values and the historical work order fault information of each network device in different regions and different time periods of the network system through log analysis, can early warn the network quality fault work orders in different time periods of each region, is beneficial to improving the operation and maintenance efficiency of the network system, and further improves the overall service efficiency of the network system.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
The invention will now be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, the present invention mainly includes the following steps:
(1) A log server is constructed for receiving daily network quality index monitoring values, such as network delay, of a plurality of network devices in each area.
(2) Setting an index threshold for each network device, and if the network quality index monitoring value of each network device is greater than the index threshold, then the network quality index monitoring value is called an index abnormal value.
(3) And carrying out regional and time-division analysis on the network quality index monitoring value in the log server, respectively counting the occurrence times of the index abnormal value of each network device in each time period in each region every day, and recording whether a fault work order is generated in the corresponding time period of the corresponding region.
(4) Constructing a statistical database for storing the statistical information in the step (3); the statistical database contains the occurrence times of index abnormal values of each network device in each period of each region and whether fault worksheets are generated or not.
(5) And calculating the statistic model parameters of the work order faults according to the statistic information in the statistic database.
Calculating the work order fault generation probability of each period in each region:
Wherein, p Failure of (Ai,Tj) represents the work order fault generation probability of the A i area T j period, M represents the statistical days, statistics is carried out once per period each day, and M (A i,Tj) represents the number of times of work order faults generated in the A i area T j period.
The average value of the index abnormal value occurrence times of each network device when each time period in each region generates work order faults is recorded as the average value of the index abnormal times, and the calculation formula is as follows:
wherein, Index anomaly frequency mean value of v-th network equipment when work order faults occur in T j period of A i area is represented, and index anomaly frequency mean value of v-th network equipment is represented by "/>And (3) indicating the index anomaly times of the v-th network equipment when the U-th work order fails, counted in the period T j of the A i area, and assuming that the U work order fails are counted in M days.
Calculating fault contribution rates of network devices in each time period in each region:
where a (a i,Tj, v) represents the failure contribution rate of the v-th network device of the a i region T j period, The index anomaly number average value of the V-th network device in the period T j in the area a i is represented, and a total of V network devices in the area a i are assumed.
(6) Combining the probability model parameters obtained in the step 5, and calculating the generation probability of the work order faults in the A i area T j time period on the n+1th day according to the statistical information on the n th day in a statistical database:
first, the failure probability of each network device in the a i area T j period is calculated separately:
Then, the generation probability p n+1(Ai,Tj of work order faults in the time period T j of the A i area on the n+1th day is calculated,
Wherein p (A i,Tj, v) represents the failure probability of the v-th network device in the period of T j in the A i area, and D n(Ai,Tj, v) represents the index anomaly number of the v-th network device in the period of T j in the A i area counted on the nth day.
(7) According to the generation probability of work order faults in each time period of each region on the n+1th day, dividing the early warning grades by setting different early warning thresholds:
if p n+1(Ai,Tj)＞β1 is detected, carrying out light early warning;
if p n+1(Ai,Tj)＞β2 is detected, performing moderate early warning;
if p n+1(Ai,Tj)＞β3 is detected, carrying out severe early warning;
wherein, β 1、β1、β1 is different pre-warning thresholds, and β 1＜β2＜β3.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the invention without departing from the principles thereof are intended to be within the scope of the invention as set forth in the following claims.
Claims (6)
1. The network quality work order fault early warning method based on log analysis is characterized by comprising the following steps of:
step 1: constructing a log server for receiving network quality index monitoring values of a plurality of network devices in each area;
Step 2: setting an index threshold for each network device, and if the network quality index monitoring value of each network device is greater than the index threshold, calling the network quality index monitoring value as an index abnormal value;
Step 3: analyzing network quality index monitoring values in a log server in a regional and time-division mode, respectively counting the occurrence times of index abnormal values of each network device in each time period in each region every day, and recording whether a fault work order is generated in the corresponding time period of the corresponding region;
Step 4: constructing a statistical database for storing the statistical information in the step 3; the statistical database contains the occurrence times of index abnormal values of each network device in each period of each region and whether fault work orders are generated or not;
step 5: according to the statistical information in the statistical database, calculating the statistical model parameters of the work order fault, including the work order fault generation probability of each time period in each region, the average value of the occurrence times of index abnormal values of each network device when the work order fault is generated in each time period in each region, and the fault contribution rate of each network device in each time period in each region;
Step 6: combining the statistical model parameters obtained in the step 5, and calculating the generation probability of work order faults in each time period in each region on the n+1 day according to the statistical information on the n day in the statistical database;
step 7: and dividing the early warning level by setting different early warning thresholds according to the generation probability of the work order faults in each time period of each region on the n+1th day.
2. The network quality work order fault early warning method based on log analysis as claimed in claim 1, wherein in step 5, the calculation formula of the work order fault generation probability of each period in each region is:
Wherein, p Failure of (Ai,Tj) represents the work order fault generation probability of the A i area T j period, M represents the statistical days, statistics is carried out once per period each day, and M (A i,Tj) represents the number of times of work order faults generated in the A i area T j period.
3. The log analysis-based network quality work order fault early warning method as claimed in claim 2, wherein in step 5, the average value of the occurrence times of the index abnormal values of each network device when the work order fault is generated in each period in each region is recorded as the average value of the index abnormal times, and the calculation formula is as follows:
wherein, Index anomaly frequency mean value of v-th network equipment when work order faults occur in T j period of A i area is represented, and index anomaly frequency mean value of v-th network equipment is represented by "/>And (3) indicating the index anomaly times of the v-th network equipment when the U-th work order fails, counted in the period T j of the A i area, and assuming that the U work order fails are counted in M days.
4. The network quality work order fault early warning method based on log analysis as claimed in claim 3, wherein in step 5, the calculation formula of the fault contribution rate of each network device in each period of each region is:
where a (a i,Tj, v) represents the failure contribution rate of the v-th network device of the a i region T j period, The index anomaly number average value of the V-th network device in the period T j in the area a i is represented, and a total of V network devices in the area a i are assumed.
5. The method for early warning of network quality work order faults based on log analysis as claimed in claim 4, wherein in the step 6, the calculation method of the generation probability of work order faults in the (n+1) th day A i area T j period is as follows:
first, the failure probability of each network device in the a i area T j period is calculated separately:
Then, the generation probability p n+1(Ai,Tj of work order faults in the time period T j of the A i area on the n+1th day is calculated,
Wherein p (A i,Tj, v) represents the failure probability of the v-th network device in the period of T j in the A i area, and D n(Ai,Tj, v) represents the index anomaly number of the v-th network device in the period of T j in the A i area counted on the nth day.
6. The network quality work order fault early warning method based on log analysis as claimed in claim 5, wherein in step 7, if p n+1(Ai,Tj)＞β1, a light early warning is performed; if p n+1(Ai,Tj)＞β2 is detected, performing moderate early warning; if p n+1(Ai,Tj)＞β3 is detected, carrying out severe early warning; beta 1、β1、β1 is different pre-warning thresholds, and beta 1＜β2＜β3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111554152.2A CN114297255B (en) | 2021-12-17 | 2021-12-17 | Network quality work order fault early warning method based on log analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111554152.2A CN114297255B (en) | 2021-12-17 | 2021-12-17 | Network quality work order fault early warning method based on log analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114297255A CN114297255A (en) | 2022-04-08 |
| CN114297255B true CN114297255B (en) | 2024-04-19 |
Family
ID=80967208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111554152.2A Active CN114297255B (en) | 2021-12-17 | 2021-12-17 | Network quality work order fault early warning method based on log analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114297255B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013024613A1 (en) * | 2011-08-17 | 2013-02-21 | 株式会社日立製作所 | Malfunction detection/diagnostic method, and malfunction detection/diagnostic system |
| CN103487682A (en) * | 2013-09-13 | 2014-01-01 | 深圳供电局有限公司 | Method for early warning of sensitive client electric energy experience quality under voltage dip disturbance |
| CN106209432A (en) * | 2016-06-30 | 2016-12-07 | 中国人民解放军国防科学技术大学 | Network equipment subhealth state method for early warning based on dynamic threshold and device |
| CN106815647A (en) * | 2016-12-28 | 2017-06-09 | 国家电网公司 | A kind of high efficiency distribution network failure repairing system and method based on data analysis |
| CN107991870A (en) * | 2017-12-05 | 2018-05-04 | 暨南大学 | A kind of fault pre-alarming and life-span prediction method of Escalator equipment |
| CN109005556A (en) * | 2018-07-24 | 2018-12-14 | 武汉虹信技术服务有限责任公司 | A kind of 4G network quality optimization method and system based on user bill |
| CN109508745A (en) * | 2018-11-14 | 2019-03-22 | 上海交通大学 | The detection method of gas turbine gascircuit fault based on Bayesian network model |
| CN109523276A (en) * | 2018-11-19 | 2019-03-26 | 国网河北省电力有限公司电力科学研究院 | The pre-warning monitoring method and device of customer complaint |
| CN109905269A (en) * | 2018-01-17 | 2019-06-18 | 华为技术有限公司 | The method and apparatus for determining network failure |
| CN109981328A (en) * | 2017-12-28 | 2019-07-05 | 中国移动通信集团陕西有限公司 | A kind of fault early warning method and device |
| CN111552609A (en) * | 2020-04-12 | 2020-08-18 | 西安电子科技大学 | Abnormal state detection method, system, storage medium, program and server |
| CN112731159A (en) * | 2020-12-23 | 2021-04-30 | 江苏省电力试验研究院有限公司 | Method for pre-judging and positioning battery fault of battery compartment of energy storage power station |
-
2021
- 2021-12-17 CN CN202111554152.2A patent/CN114297255B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013024613A1 (en) * | 2011-08-17 | 2013-02-21 | 株式会社日立製作所 | Malfunction detection/diagnostic method, and malfunction detection/diagnostic system |
| CN103487682A (en) * | 2013-09-13 | 2014-01-01 | 深圳供电局有限公司 | Method for early warning of sensitive client electric energy experience quality under voltage dip disturbance |
| CN106209432A (en) * | 2016-06-30 | 2016-12-07 | 中国人民解放军国防科学技术大学 | Network equipment subhealth state method for early warning based on dynamic threshold and device |
| CN106815647A (en) * | 2016-12-28 | 2017-06-09 | 国家电网公司 | A kind of high efficiency distribution network failure repairing system and method based on data analysis |
| CN107991870A (en) * | 2017-12-05 | 2018-05-04 | 暨南大学 | A kind of fault pre-alarming and life-span prediction method of Escalator equipment |
| CN109981328A (en) * | 2017-12-28 | 2019-07-05 | 中国移动通信集团陕西有限公司 | A kind of fault early warning method and device |
| CN109905269A (en) * | 2018-01-17 | 2019-06-18 | 华为技术有限公司 | The method and apparatus for determining network failure |
| CN109005556A (en) * | 2018-07-24 | 2018-12-14 | 武汉虹信技术服务有限责任公司 | A kind of 4G network quality optimization method and system based on user bill |
| CN109508745A (en) * | 2018-11-14 | 2019-03-22 | 上海交通大学 | The detection method of gas turbine gascircuit fault based on Bayesian network model |
| CN109523276A (en) * | 2018-11-19 | 2019-03-26 | 国网河北省电力有限公司电力科学研究院 | The pre-warning monitoring method and device of customer complaint |
| CN111552609A (en) * | 2020-04-12 | 2020-08-18 | 西安电子科技大学 | Abnormal state detection method, system, storage medium, program and server |
| CN112731159A (en) * | 2020-12-23 | 2021-04-30 | 江苏省电力试验研究院有限公司 | Method for pre-judging and positioning battery fault of battery compartment of energy storage power station |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114297255A (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111176879A (en) | Fault repairing method and device for equipment | |
| CN113407507A (en) | Alarm log compression method, device and system and storage medium | |
| CN112491805B (en) | Network security equipment management system applied to cloud platform | |
| CN101632093A (en) | Be used to use statistical analysis to come the system and method for management of performance fault | |
| CN110502398B (en) | Switch fault prediction system and method based on artificial intelligence | |
| CN100356729C (en) | Method and system for monitoring network service performance | |
| CN110460454B (en) | Intelligent network equipment port fault prediction method based on deep learning | |
| CN110954782B (en) | Distribution network instantaneous fault identification method and system based on density peak clustering | |
| CN104574219A (en) | System and method for monitoring and early warning of operation conditions of power grid service information system | |
| CN109685399B (en) | Method and system for integrating and analyzing logs of power system | |
| WO2023071761A1 (en) | Anomaly positioning method and device | |
| CN116680113B (en) | Equipment detection implementation control system | |
| CN111666978B (en) | Intelligent fault early warning system for IT system operation and maintenance big data | |
| CN111241683A (en) | Equipment working condition fault prediction method and system based on dynamic time warping | |
| CN116628774A (en) | Data storage integrity supervision system based on cloud computing | |
| CN106951360B (en) | Data statistical integrity calculation method and system | |
| CN103490925A (en) | Electric power communication network performance state real-time assessment method and system | |
| CN114297255B (en) | Network quality work order fault early warning method based on log analysis | |
| CN116820014B (en) | Intelligent monitoring and early warning method and system for traffic electromechanical equipment | |
| CN110784352B (en) | Data synchronous monitoring and alarming method and device based on Oracle golden gate | |
| CN109936487A (en) | A kind of real-time analysis and monitoring method and system of Web broadcast packet | |
| CN116155581A (en) | Network intrusion detection method and device based on graph neural network | |
| CN116032526A (en) | Abnormal network flow detection method based on machine learning model optimization | |
| CN116522213A (en) | Service state level classification and classification model training method and electronic equipment | |
| CN112261009A (en) | Network intrusion detection method for railway dispatching centralized system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |