CN107147526A - Intelligent network fault detection method and system - Google Patents
Intelligent network fault detection method and system Download PDFInfo
- Publication number
- CN107147526A CN107147526A CN201710335783.2A CN201710335783A CN107147526A CN 107147526 A CN107147526 A CN 107147526A CN 201710335783 A CN201710335783 A CN 201710335783A CN 107147526 A CN107147526 A CN 107147526A
- Authority
- CN
- China
- Prior art keywords
- network
- data
- tested
- primary standard
- current
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0681—Configuration of triggering conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a kind of intelligent network fault detection method and system, wherein method includes：The network data of network line is tested on S1, batch capture in a period, raw network data is obtained；S2, the raw network data is converted into primary standard data；S3, using the primary standard data set up Gauss model；The current network data are converted into Current standards data by S4, the current network data for gathering the tested network line in real time, and the Current standards data are substituted into the Gauss model, and calculating obtains rate value without exception；S5, judge whether the probable value meets the parameter probability valuing scope of small probability event, if, it is determined that the network state of the tested network line is abnormal；If not, it is determined that the network state of the tested network line is normal.Energy effective detection network failure of the invention, the unreliability for reducing the trouble for setting threshold value and setting threshold band improves the accuracy of network monitoring.
Description
Technical field
The present invention relates to technical field of the computer network, more particularly to a kind of intelligent network fault detection method and system.
Background technology
With continuing to develop for Internet technology, the stability and availability of network are particularly important.In continuous service
Network system in, when network index deviates original track suddenly, beyond normal fluctuation range, then may determine that the moment
Generation network failure.The performance of network is monitored, detection network failure is also into one of important work.Monitoring to network at present
All it is to be realized by way of static state setting threshold value, this method needs to set a fixed threshold value, when network index exceedes
Alarm is produced during the threshold value, much reports by mistake and fails to report so easily producing under this methodology so that the accuracy reduction of monitoring.
The content of the invention
The technical problem to be solved in the present invention be in order to overcome in the prior art use the fixed threshold of static state setting one side
Formula monitors network, and there is provided a kind of intelligent network fault detection method and system for the defect that easily generation is reported by mistake and failed to report.
The present invention is to solve above-mentioned technical problem by following technical proposals：
A kind of intelligent network fault detection method, the intelligent network fault detection method includes：
The network data of network line is tested on S1, batch capture in a period, raw network data is obtained；
S2, the raw network data is converted into primary standard data；
S3, using the primary standard data set up Gauss model；
S4, the current network data for gathering the tested network line in real time, the current network data are converted into and worked as
The Current standards data are substituted into the Gauss model by preceding normal data, and calculating obtains rate value without exception；
S5, judge whether the probable value meets the parameter probability valuing scope of small probability event, if, it is determined that it is described tested
The network state of network line is abnormal；If not, it is determined that the network state of the tested network line is normal.
It is preferred that the step of batch capture is tested the network data of network line in step S1 includes：
On described in a period, test data is persistently sent to multiple address tests by the tested network line
Bag, the address test is fed back by the tested network line, obtains the raw network data.
It is preferred that step S2 includes：Normal state processing is carried out to the raw network data, the primary standard number is obtained
According to；And/or, step S3 includes：Average and variance are asked for the primary standard data, the Gauss model is obtained；And/or,
Step S4 includes：Normal state processing is carried out to the current network data, the Current standards data are obtained.
It is preferred that the intelligent network fault detection method also includes：
In step s 5, if the network state of the tested network line is abnormal, step S6 is performed；
S6, to abnormal network status alert point out.
It is preferred that in step S5 when being judged as NO, the Current standards data are added into the primary standard data
In, and delete the earliest data of time in the primary standard data, return to step S3.
It is preferred that step S5 includes：
Network state abnormality mark variable is set, and the initial value of network state abnormality mark variable is set to zero；
When being judged as YES, then the value of the network state abnormality mark variable is added 1, judge that the network state is abnormal
Whether indexed variable is more than first threshold, if, it is determined that the network state of the tested network line is abnormal, return to step
S4；If it is not, then direct return to step S4；
When being judged as NO, then the network state abnormality mark variable is reset, the Current standards data are added to
In the primary standard data, and delete the earliest data of time in the primary standard data, return to step S3.
It is preferred that the raw network data and the current network data are included in network delay, packet loss, conditional code
At least one.
A kind of intelligent network fault detection system, including data acquisition module, data processing module, model building module and
Abnormal judge module；
The data acquisition module, the network data of network line is tested on batch capture, is obtained in a period
To raw network data；
The data processing module, for the raw network data to be converted into primary standard data；
The model building module, for setting up Gauss model using the primary standard data；
The data acquisition module, is additionally operable to gather the network data that network line is tested described in current time, is worked as
Preceding network data；
The data processing module, is additionally operable to the current network data being converted into Current standards data；
The abnormal judge module, for the Current standards data to be substituted into the Gauss model, obtains a probable value,
Judge whether the probable value meets the parameter probability valuing scope of small probability event, if, it is determined that the tested network line
Network state is abnormal；If not, it is determined that the network state of the tested network line is normal.
It is preferred that the data processing module is used to carry out normal state processing to the raw network data, obtain described
Primary standard data；And/or, the model building module is used to ask for average and variance to the primary standard data, obtains
The Gauss model；And/or, the data processing module is additionally operable to carry out normal state processing to the current network data, obtains
To the Current standards data.
It is preferred that the intelligent network fault detection system also includes alarm module, in the tested network line
Network state for it is abnormal when, abnormal network status alert is pointed out.
It is preferred that the Current standards data during for being judged as NO, are added to the original by the abnormal judge module
In beginning normal data, and the earliest data of time in the primary standard data are deleted, call the model building module.
It is preferred that the abnormal judge module is additionally operable to set network state abnormality mark variable, and network state is different
The initial value of normal indexed variable is set to zero；The abnormal judge module is additionally operable to when being judged as YES, by the network state
The value of abnormality mark variable adds 1, judges whether the network state abnormality mark variable is more than first threshold, if, it is determined that
The network state of the tested network line is abnormal, calls the data acquisition module, and collection subsequent time is tested grid line
The network data on road；If it is not, then directly invoking the data acquisition module, collection subsequent time is tested the network number of network line
According to；
It is preferred that the network state abnormality mark variable is reset, the Current standards data are added to the original
In beginning normal data, and the earliest data of time in the primary standard data are deleted, call the data acquisition module, gather
Subsequent time is tested the network data of network line.
The positive effect of the present invention is：
The present invention realizes indices and previous time on automatic decision current point in time by way of lasting modeling
Whether the index in section is compared to there is larger deviation, if there is big deviation, then illustrates that network state occurs abnormal, no
Then, illustrate that network state is normal.Energy effective detection network failure of the invention, reduces the trouble for setting threshold value and sets threshold value
The unreliability brought, improve the accuracy of network monitoring, it is to avoid when wrong report that network jitter is produced and network failure
Fail to report.
Brief description of the drawings
Fig. 1 is the flow chart of the intelligent network fault detection method of the embodiment of the present invention 1.
Fig. 2 is the flow chart of the intelligent network fault detection method of the embodiment of the present invention 2.
Fig. 3 is the module diagram of the intelligent network fault detection system of the embodiment of the present invention 3.
Embodiment
The present invention is further illustrated below by the mode of embodiment, but does not therefore limit the present invention to described reality
Apply among a scope.
Embodiment 1
As shown in figure 1, a kind of intelligent network fault detection method, the intelligent network fault detection method includes：
The network data of network line is tested in step 101, batch capture in a period, primitive network number is obtained
According to being realized especially by following steps：
On described in a period, test data is persistently sent to multiple address tests by the tested network line
Bag, the address test is fed back by the tested network line, obtains the raw network data.
In the present embodiment, 0.5 to 1 hours section is chosen, obtaining network by lasting ping each address test prolongs
When, packet loss and conditional code data, the result to ping counted and arranged, and obtains the raw network data.
Step 102, the raw network data is converted into primary standard data, realized especially by following steps：
Normal state processing is carried out to the raw network data, the primary standard data are obtained.
Step 103, using the primary standard data Gauss model is set up, realized especially by following steps：
Average and variance are asked for the primary standard data, the Gauss model is obtained.
Step 104, the current network data for gathering the tested network line in real time, the current network data are converted
For Current standards data, more specifically, normal state processing is carried out to the current network data, the Current standards number is obtained
According to then by the Current standards data substitution Gauss model, calculating obtains rate value without exception.
Step 105, judge whether the probable value meets the parameter probability valuing scope of small probability event, if, it is determined that institute
It is exception to state the network state of tested network line；If not, it is determined that the network state of the tested network line is normal.
In the present embodiment, the parameter probability valuing scope of small probability event is, less than 5%, to judge that the probable value is no and be less than 5%,
If so, then can be determined that as small probability event, therefore it can consider that the time point data of collection do not meet "current" model, i.e., currently
Moment network occurs abnormal；If it is not, then it is considered that the data fit "current" model of time point collection, i.e. current time network
Normally.
The present embodiment can realize network delay on automatic decision current point in time, three indexs of packet loss and conditional code and
Corresponding index in previous short time if there is big deviation, then illustrates network-like compared to whether there is larger deviation
There is exception in state, otherwise, illustrates that network state is normal.
Embodiment 2
The present embodiment provides a kind of intelligent network fault detection method, and the present embodiment is substantially the same manner as Example 1, such as Fig. 2
Shown, compared with Example 1, difference is that step 105 also includes to the present embodiment：
Network state abnormality mark variable is set, and the initial value of network state abnormality mark variable is set to zero.
Judge whether the probable value meets the parameter probability valuing scope of small probability event, if being judged as YES, by the net
The value of network abnormal state indexed variable adds 1, judges whether the network state abnormality mark variable is more than first threshold, if so,
It is abnormal, return to step 104 then to determine the network state of the tested network line；If it is not, then direct return to step 104；
If being judged as NO, the network state abnormality mark variable is reset, the Current standards data are added to
In the primary standard data, and delete the earliest data of time in the primary standard data, return to step 103.
In the present embodiment, first threshold is set to 3.
The present embodiment compared with Example 1, by setting network state abnormality mark denotation of variable contiguous network state different
Normal number of times, when judging whether the probable value meets the parameter probability valuing scope of small probability event, if being judged as NO, with the first threshold
Value 3 compares, if more than first threshold 3, representing continuous 3 exceptions, is defined as current network state abnormal.By setting the first threshold
It is worth this mode, compared with Example 1, by continuously judging, has reached 3 exceptions, that is, determines that network state is abnormal, so
The wrong report that network jitter can be avoided to produce, further improves the accuracy of network monitoring.If judging, the probable value is not inconsistent
The parameter probability valuing scope of small probability event is closed, then is reset network state abnormality mark variable, return to step 103, realizes and continues
New primary standard data are replaced, lasting modeling；Return to step 104, realization continuously acquires current network data, and two return to step
Suddenly, the network delay continued on automatic decision current point in time, three indexs of packet loss and conditional code and for the previous period are realized
Whether interior corresponding index is compared to there is larger deviation, if there is big deviation, then illustrates that network state occurs abnormal, no
Then, illustrate that network state is normal.This method energy effective detection network failure, reduces the trouble for setting threshold value and sets threshold value
The unreliability brought, improve the accuracy of network monitoring, it is to avoid when wrong report that network jitter is produced and network failure
Fail to report.
Preferably, step 105 judges whether network state abnormality mark variable is more than first threshold, if, it is determined that institute
It is abnormal, execution step 106 to state the network state of tested network line；Step 106, to abnormal network status alert point out；With
Facilitate the timely handling failure of related personnel.
Embodiment 3
As shown in figure 3, a kind of intelligent network fault detection system, including data acquisition module 201, data processing module
202nd, model building module 203 and abnormal judge module 204；
The data acquisition module 201, is tested the network data of network line on batch capture in a period,
Obtain raw network data.
The data processing module 202, for the raw network data to be converted into primary standard data；
More specifically, for carrying out normal state processing to the raw network data, the primary standard data are obtained.
The model building module 203, for setting up Gauss model using the primary standard data；
More specifically, the model building module is used to ask for average and variance to the primary standard data, obtains institute
State Gauss model.
The data acquisition module 201, is additionally operable to gather the network data that network line is tested described in current time, obtains
Current network data.
The data processing module 202, is additionally operable to the current network data being converted into Current standards data；
More specifically, the data processing module is additionally operable to carry out normal state processing to the current network data, obtains
The Current standards data.
The abnormal judge module 204, for the Current standards data to be substituted into the Gauss model, obtains a probability
Value, judges whether the probable value meets the parameter probability valuing scope of small probability event, if, it is determined that the tested network line
Network state be abnormal；If not, it is determined that the network state of the tested network line is normal.
Embodiment 4
The present embodiment provides a kind of intelligent network fault detection system, and the present embodiment is substantially the same manner as Example 3, and it is distinguished
It is that the abnormal judge module is additionally operable to set network state abnormality mark variable, and by network state abnormality mark variable
Initial value is set to zero；The abnormal judge module is additionally operable to when being judged as YES, by the network state abnormality mark variable
Value add 1, judge the network state abnormality mark variable whether be more than first threshold, if, it is determined that the tested network
The network state of circuit is abnormal, calls the data acquisition module, and collection subsequent time is tested the network data of network line；
If it is not, then directly invoking the data acquisition module, collection subsequent time is tested the network data of network line.
The abnormal judge module is additionally operable to when being judged as NO, and the network state abnormality mark variable is reset, will
The Current standards data are added in the primary standard data, and delete the number of time earliest in the primary standard data
According to calling the data acquisition module, collection subsequent time is tested the network data of network line.
Preferably, the intelligent network fault detection system also includes alarm module, in the tested network line
Network state for it is abnormal when, abnormal network status alert is pointed out.
Although the embodiment of the present invention is the foregoing described, it will be appreciated by those of skill in the art that this is only
For example, protection scope of the present invention is to be defined by the appended claims.Those skilled in the art without departing substantially from
On the premise of the principle and essence of the present invention, various changes or modifications can be made to these embodiments, but these changes and
Modification each falls within protection scope of the present invention.
Claims (12)
1. a kind of intelligent network fault detection method, it is characterised in that the intelligent network fault detection method includes：
The network data of network line is tested on S1, batch capture in a period, raw network data is obtained；
S2, the raw network data is converted into primary standard data；
S3, using the primary standard data set up Gauss model；
The current network data are converted into current mark by S4, the current network data for gathering the tested network line in real time
The Current standards data are substituted into the Gauss model by quasi- data, and calculating obtains rate value without exception；
S5, judge whether the probable value meets the parameter probability valuing scope of small probability event, if, it is determined that the tested network
The network state of circuit is abnormal；If not, it is determined that the network state of the tested network line is normal.
2. intelligent network fault detection method as claimed in claim 1, it is characterised in that batch capture is by survey grid in step S1
The step of network data on winding thread road, includes：
On described in a period, test data bag is persistently sent to multiple address tests by the tested network line,
The address test is fed back by the tested network line, obtains the raw network data.
3. intelligent network fault detection method as claimed in claim 1, it is characterised in that step S2 includes：To described original
Network data carries out normal state processing, obtains the primary standard data；And/or, step S3 includes：To the primary standard number
According to average and variance is asked for, the Gauss model is obtained；And/or, step S4 includes：Normal state is carried out to the current network data
Change is handled, and obtains the Current standards data.
4. intelligent network fault detection method as claimed in claim 1, it is characterised in that the intelligent network fault detect side
Method also includes：
In step s 5, if the network state of the tested network line is abnormal, step S6 is performed；
S6, to abnormal network status alert point out.
5. intelligent network fault detection method as claimed in claim 1, it is characterised in that in step S5 when being judged as NO,
The Current standards data are added in the primary standard data, and it is earliest to delete time in the primary standard data
Data, return to step S3.
6. intelligent network fault detection method as claimed in claim 1, it is characterised in that step S5 includes：
Network state abnormality mark variable is set, and the initial value of network state abnormality mark variable is set to zero；
When being judged as YES, then the value of the network state abnormality mark variable is added 1, judge the network state abnormality mark
Whether variable is more than first threshold, if, it is determined that the network state of the tested network line is abnormal, return to step S4；
If it is not, then direct return to step S4；
When being judged as NO, then the network state abnormality mark variable is reset, the Current standards data are added to described
In primary standard data, and delete the earliest data of time in the primary standard data, return to step S3.
7. intelligent network fault detection method as claimed in claim 1, it is characterised in that the raw network data and described
Current network data include at least one of network delay, packet loss, conditional code.
8. a kind of intelligent network fault detection system, it is characterised in that including data acquisition module, data processing module, model
Set up module and abnormal judge module；
The data acquisition module, the network data of network line is tested on batch capture, original is obtained in a period
Beginning network data；
The data processing module, for the raw network data to be converted into primary standard data；
The model building module, for setting up Gauss model using the primary standard data；
The data acquisition module, is additionally operable to gather the current network data that network line is tested described in current time；
The data processing module, is additionally operable to the current network data being converted into Current standards data；
The abnormal judge module, for the Current standards data to be substituted into the Gauss model, obtains a probable value, judges
Whether the probable value meets the parameter probability valuing scope of small probability event, if, it is determined that the network of the tested network line
State is abnormal；If not, it is determined that the network state of the tested network line is normal.
9. intelligent network fault detection system as claimed in claim 8, it is characterised in that the data processing module is used for pair
The raw network data carries out normal state processing, obtains the primary standard data；And/or, the model building module is used
In asking for average and variance to the primary standard data, the Gauss model is obtained；And/or, the data processing module is also
For carrying out normal state processing to the current network data, the Current standards data are obtained.
10. intelligent network fault detection system as claimed in claim 8, it is characterised in that the intelligent network fault detect
System also includes alarm module, during for the network state in the tested network line for exception, to abnormal network state report
Alert prompting.
11. intelligent network fault detection system as claimed in claim 8, it is characterised in that the abnormal judge module, is used for
When being judged as NO, the Current standards data are added in the primary standard data, and delete the primary standard data
Earliest data of middle time, call the model building module.
12. intelligent network fault detection system as claimed in claim 8, it is characterised in that the abnormal judge module is also used
In setting network state abnormality mark variable, and the initial value of network state abnormality mark variable is set to zero；The exception
Judge module is additionally operable to when being judged as YES, and is added 1 by the value of the network state abnormality mark variable, is judged the network state
Whether abnormality mark variable is more than first threshold, if, it is determined that the network state of the tested network line is abnormal, is called
The data acquisition module, collection subsequent time is tested the network data of network line；Adopted if it is not, then directly invoking the data
Collect module, collection subsequent time is tested the network data of network line；
The abnormal judge module is additionally operable to when being judged as NO, and the network state abnormality mark variable is reset, will be described
Current standards data are added in the primary standard data, and delete the earliest data of time in the primary standard data,
The data acquisition module is called, collection subsequent time is tested the network data of network line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710335783.2A CN107147526A (en) | 2017-05-12 | 2017-05-12 | Intelligent network fault detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710335783.2A CN107147526A (en) | 2017-05-12 | 2017-05-12 | Intelligent network fault detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107147526A true CN107147526A (en) | 2017-09-08 |
Family
ID=59778072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710335783.2A Pending CN107147526A (en) | 2017-05-12 | 2017-05-12 | Intelligent network fault detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107147526A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108011752A (en) * | 2017-11-21 | 2018-05-08 | 江苏天联信息科技发展有限公司 | Fault locating analysis method and device, computer-readable recording medium |
| CN109765878A (en) * | 2018-12-24 | 2019-05-17 | 上海大郡动力控制技术有限公司 | The aided analysis method of new-energy automobile CAN bus network failure |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4964126A (en) * | 1988-09-30 | 1990-10-16 | Massachusetts Institute Of Technology | Fault tolerant signal processing machine and method |
| CN103488091A (en) * | 2013-09-27 | 2014-01-01 | 上海交通大学 | Data-driving control process monitoring method based on dynamic component analysis |
| CN103631145A (en) * | 2013-12-11 | 2014-03-12 | 清华大学 | Monitoring index switching based multi-operating-mode process monitoring method and system |
| CN103745119A (en) * | 2014-01-22 | 2014-04-23 | 浙江大学 | Oil-immersed transformer fault diagnosis method based on fault probability distribution model |
| CN105335759A (en) * | 2015-11-12 | 2016-02-17 | 南方电网科学研究院有限责任公司 | Generating-probability-model-based transformer fault detection method |
-
2017
- 2017-05-12 CN CN201710335783.2A patent/CN107147526A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4964126A (en) * | 1988-09-30 | 1990-10-16 | Massachusetts Institute Of Technology | Fault tolerant signal processing machine and method |
| CN103488091A (en) * | 2013-09-27 | 2014-01-01 | 上海交通大学 | Data-driving control process monitoring method based on dynamic component analysis |
| CN103631145A (en) * | 2013-12-11 | 2014-03-12 | 清华大学 | Monitoring index switching based multi-operating-mode process monitoring method and system |
| CN103745119A (en) * | 2014-01-22 | 2014-04-23 | 浙江大学 | Oil-immersed transformer fault diagnosis method based on fault probability distribution model |
| CN105335759A (en) * | 2015-11-12 | 2016-02-17 | 南方电网科学研究院有限责任公司 | Generating-probability-model-based transformer fault detection method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108011752A (en) * | 2017-11-21 | 2018-05-08 | 江苏天联信息科技发展有限公司 | Fault locating analysis method and device, computer-readable recording medium |
| CN108011752B (en) * | 2017-11-21 | 2020-06-16 | 江苏天联信息科技发展有限公司 | Fault positioning analysis method and device and computer readable storage medium |
| CN109765878A (en) * | 2018-12-24 | 2019-05-17 | 上海大郡动力控制技术有限公司 | The aided analysis method of new-energy automobile CAN bus network failure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103544093B (en) | Monitoring alarm control method and system thereof | |
| CN110493042B (en) | Fault diagnosis method and device and server | |
| CN101997709B (en) | Root alarm data analysis method and system | |
| CN103220173B (en) | A kind of alarm monitoring method and supervisory control system | |
| CN102929773B (en) | information collecting method and device | |
| CN109992440A (en) | A kind of IT root accident analysis recognition methods of knowledge based map and machine learning | |
| US10708155B2 (en) | Systems and methods for managing network operations | |
| US11770199B2 (en) | Traffic data self-recovery processing method, readable storage medium, server and apparatus | |
| CN106209405A (en) | Method for diagnosing faults and device | |
| CN115118581B (en) | Internet of things data all-link monitoring and intelligent guaranteeing system based on 5G | |
| CN105917625A (en) | Classification of detected network anomalies using additional data | |
| CN104574219A (en) | System and method for monitoring and early warning of operation conditions of power grid service information system | |
| CN106506226B (en) | A kind of starting method and device of fault detection | |
| CN109698734A (en) | Abnormality judgment method based on the bis- net reception mechanisms of GOOSE | |
| CN110635950A (en) | Double-data-center disaster recovery system | |
| CN112699007A (en) | Method, system, network device and storage medium for monitoring machine performance | |
| CN113671909A (en) | Safety monitoring system and method for steel industrial control equipment | |
| CN107995066A (en) | A kind of method and apparatus of automatic test network interface card | |
| CN110365534A (en) | A kind of intelligent substation communication system is chopped off automatically and restoration methods | |
| CN107147526A (en) | Intelligent network fault detection method and system | |
| CN107968727A (en) | A kind of detection method, device and the medium of CIFS services | |
| US20150271045A1 (en) | Method, apparatus and system for detecting network element load imbalance | |
| WO2017059904A1 (en) | Anomaly detection in a data packet access network | |
| CN109309577A (en) | Alert processing method, apparatus and system for SDN network | |
| CN109218113B (en) | Communication network fault positioning method and fault monitoring device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170908 |
|
| RJ01 | Rejection of invention patent application after publication |