CN108259194A - Network failure method for early warning and device - Google Patents
Network failure method for early warning and device Download PDFInfo
- Publication number
- CN108259194A CN108259194A CN201611236959.0A CN201611236959A CN108259194A CN 108259194 A CN108259194 A CN 108259194A CN 201611236959 A CN201611236959 A CN 201611236959A CN 108259194 A CN108259194 A CN 108259194A
- Authority
- CN
- China
- Prior art keywords
- network
- target exchange
- node
- model
- network node
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/55—Prevention, detection or correction of errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning 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
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/069—Management of faults, events, alarms or notifications using logs of notifications; Post-processing of notifications
-
- 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
- H04L41/147—Network analysis or design for predicting network behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention relates to a kind of network failure method for early warning and device, wherein the method includes：Obtain the operation data of the target exchange network node in current network；Artificial nerve network model is trained according to the operation data of the target exchange network node；According to the trained artificial nerve network model and the operation data of the current network acquired in real time, the probability of malfunction of the target exchange network node is predicted.The network failure method for early warning and device of the present invention, which can be realized, predicts the failure of switching node according to the operation data of node each in network, by the training of adaptivity method and update artificial nerve network model, the precision of prediction of the failure rate of each switching node in current network can be improved, it realizes premature failure early warning, avoids losing.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of network failure method for early warning and device.
Background technology
Interchanger or router, hereinafter referred to as switching node are one of most important IT network hardware equipments.If it exchanges
Node often breaks down, and personal or enterprises and institutions routine works will necessarily be given to bring big inconvenience and loss.Therefore,
How effectively to prevent, switching node is avoided to break down for avoiding network contingency and reducing economic asset loss with great
Realistic meaning.
Many times, there is not phenomena such as crash in switching node, but still cannot keep normal communication.It is possible
Phenomenon of the failure includes：Switching node is working properly, but packet loss is serious, leads to not communicate；Or, telephone net node is working properly,
And because unknown cause is directly resulted in and can not be communicated.The main reason for causing this kind of phenomenon may include：Viral transmission and lead
The network congestion of cause, it is a large amount of caused by network congestion and individual terminal hardware fault caused by the resource downloading of big flow
It is first-class that rubbish message is published to network.
For above-mentioned the reason of may occurring, existing reply technology includes：The right to use of network terminal user is planned
Limit and rule, improve the anti-virus measure of network, and anti-virus software is installed for each station terminal, inhibit virus as far as possible in net
Propagation；And the data transfer of big flow in network is limited, network carrying ability is designed, the network management software, prison are installed
Survey network traffic information etc..
It delays machine accident there are server caused by some non-common causes in daily network job, and net may be caused
There are a series of related problems such as circuit in network, these problems often directly or indirectly cause to impact and lead to it to switching node
It can not continue to communicate under equipment normal condition.And for these problems, the prior art can only check exchange by Network Sniffing
The means such as machine daily record are investigated and are solved, and can not carry out early warning in advance to avoid causing damages.
Invention content
It can only check that the means such as interchanger daily record carry out network failure investigation and solution by Network Sniffing for the prior art
Certainly, the defects of early warning is to avoid causing damages can not be carried out in advance, and the following technical solutions are proposed by the present invention：
One aspect of the present invention provides a kind of network failure method for early warning, including：
Obtain the operation data of the target exchange network node in current network；
Artificial nerve network model is trained according to the operation data of the target exchange network node；
According to the trained artificial nerve network model and the operation data of the current network acquired in real time, in advance
Survey the probability of malfunction of the target exchange network node.
Optionally, the operation data for obtaining the target exchange network node in current network, including：
Obtain the running log of the target exchange network node and the network of the terminal node in the current network
Data on flows.
Optionally, it is described that artificial nerve network model, packet are trained according to the operation data of the target exchange network node
It includes：
Each target exchange network node artificial neuron is respectively trained according to the operation data of the target exchange network node
Network model, each regional network artificial nerve network model of the current network and the whole network artificial neuron of the current network
Network model.
Optionally, the method further includes：
By the probability of malfunction of the target exchange network node of display device displaying prediction, occur to realize to prediction
The target exchange network node of failure carries out key monitoring.
Optionally, it is described that artificial nerve network model, packet are trained according to the operation data of the target exchange network node
It includes：
The operation data update of target exchange network node in the current network obtained in real time is described artificial
Neural network prediction model.
On the other hand, the present invention also provides a kind of network failure prior-warning device, including：
Data capture unit, for obtaining the operation data of the target exchange network node in current network；
Model training unit, for training artificial neural network mould according to the operation data of the target exchange network node
Type；
Failure predication unit, for acquiring according to the trained artificial nerve network model and in real time described current
The operation data of network predicts the probability of malfunction of the target exchange network node.
Optionally, the data capture unit be specifically used for obtaining the target exchange network node running log and
The network flow data of terminal node in the current network.
Optionally, the model training unit is specifically used for being distinguished according to the operation data of the target exchange network node
Each regional network artificial nerve network model of each target exchange network node artificial nerve network model of training, the current network
And the whole network artificial nerve network model of the current network.
Optionally, described device further includes：
Device display unit, for general by the failure of the target exchange network node of display device displaying prediction
Rate carries out key monitoring to realize to the target exchange network node that prediction is broken down.
Optionally, the model training unit is additionally operable to：
The operation data update of target exchange network node in the current network obtained in real time is described artificial
Neural network prediction model.
The network failure method for early warning and device of the present invention, by obtaining the target exchange network node in current network
Operation data, and artificial nerve network model is trained according to the operation data of the target exchange network node, with according to training
The artificial nerve network model and the operation data of the current network that acquires in real time, predict the target switching network
The probability of malfunction of network node can realize and the failure of switching node is predicted according to the operation data of node each in network,
By the training of adaptivity method and artificial nerve network model is updated, the failure of each switching node in current network can be improved
The precision of prediction of rate realizes premature failure early warning, avoids losing.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments, for those of ordinary skill in the art, without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the flow diagram of the network failure method for early warning of one embodiment of the invention；
Fig. 2 is the structure diagram of the network failure prior-warning device of one embodiment of the invention；
Fig. 3 is that the flow of the training neural network model in the network failure method for early warning of another embodiment of the present invention is shown
It is intended to；
Fig. 4 is the structure diagram of the network failure prior-warning device of another embodiment of the present invention；
Fig. 5 is the structure diagram of the artificial nerve network model of one embodiment of the invention；
Fig. 6 is the prediction flow diagram in the network failure method for early warning of another embodiment of the present invention.
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment be the present invention
Part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
All other embodiments obtained under the premise of creative work are made, shall fall within the protection scope of the present invention.
Fig. 1 is the flow diagram of the network failure method for early warning of one embodiment of the invention；As shown in Figure 1, this method
Including：
S1：Obtain the operation data of the target exchange network node in current network；
Specifically, processor can obtain the running log file of the all-network node in current network, daily record text
Part may include the information of all recording equipment operating statuses such as the running log of the running log of terminal node, switching node.
Wherein, collected journal file can be stored in non-caching, the permanent memory blocks or default of respective nodes
Log server, the log information of whole network will be stored permanently.
S2：Artificial nerve network model is trained according to the operation data of the target exchange network node；
Specifically, the processor trains artificial neural network mould according to the operation data of the target exchange network node
Type, specific method include：
Each target exchange network node artificial neuron is respectively trained according to the operation data of the target exchange network node
Network model, each regional network artificial nerve network model of the current network and the whole network artificial neuron of the current network
Network model.
Wherein, the feedforward network of the artificial nerve network model may be used continuous function and characterize all possibility output
State, feedforward part are approached using two-tier network；
It is understood that a plurality of types of neural network models of above-mentioned training, it can be including being for output state
The prediction model of the single switching node of the probability of malfunction of target switching node；It is a certain local area network to further include for output state
The prediction model of network failure probability；And for the prediction model of output state for the whole network failure etc..
It should be noted that the method for the present embodiment includes all prediction models of adaptive updates, i.e., according to constantly accumulative
The data such as history log file periodically realize all prediction models of update.
S3：According to the trained artificial nerve network model and the operation number of the current network acquired in real time
According to predicting the probability of malfunction of the target exchange network node.
Specifically, the processor is acquired according to the trained artificial nerve network model and in real time described current
The operation data of network predicts the probability of malfunction of the target exchange network node.
Specifically, the processor can be to the prediction result of above-mentioned various types of Artificial Neural Network Prediction Models
It is weighted, the operating status for the switching node for needing key monitoring is obtained with COMPREHENSIVE CALCULATING.Further, as this reality
The preferred of example is applied, the method can also include：
By the probability of malfunction of the target exchange network node of display device displaying prediction, occur to realize to prediction
The target exchange network node of failure carries out key monitoring.
For example, the processor can be by functions such as mail push, mobile terminal app push, will be described in prediction
The probability of malfunction of target exchange network node is shown by the display device of terminal.
The network failure method for early warning of the present embodiment, by the operation for obtaining the target exchange network node in current network
Data, and artificial nerve network model is trained according to the operation data of the target exchange network node, with according to trained institute
The operation data of the current network stated artificial nerve network model and acquired in real time predicts the target exchange network section
The probability of malfunction of point, can realize that the operation data according to node each in network predicts the failure of switching node, pass through
The training of adaptivity method simultaneously updates artificial nerve network model, can improve the failure rate of each switching node in current network
Precision of prediction realizes premature failure early warning, avoids losing.
Fig. 2 is the structure diagram of the network failure prior-warning device of one embodiment of the invention；As shown in Fig. 2, the device
Including data capture unit 11, model training unit 12 and failure predication unit 13, wherein：
Data capture unit 11 is used to obtain the operation data of the target exchange network node in current network；
Model training unit 12 is used to train artificial neural network according to the operation data of the target exchange network node
Model；
Failure predication unit 13 is used to work as according to the trained artificial nerve network model and described in acquiring in real time
The operation data of preceding network predicts the probability of malfunction of the target exchange network node.
Specifically, data capture unit 11 obtains the operation data of the target exchange network node in current network；Mould
Type training unit 12 trains artificial nerve network model according to the operation data of the target exchange network node；Failure predication list
Member 13 predicts institute according to the trained artificial nerve network model and the operation data of the current network acquired in real time
State the probability of malfunction of target exchange network node.
Device described in the present embodiment can be used for performing above method embodiment, and principle is similar with technique effect, this
Place repeats no more.
Further, as the preferred of above device embodiment, the data capture unit 11 can be specifically used for obtaining
The running log of the target exchange network node and the network flow data of the terminal node in the current network.
Further, as the preferred of above device embodiment, the model training unit 12 is specifically used for according to
Each target exchange network node artificial nerve network model, described current is respectively trained in the operation data of target exchange network node
Each regional network artificial nerve network model of network and the whole network artificial nerve network model of the current network.
Further, as the preferred of above device embodiment, described device can also include：
Device display unit 14, for general by the failure of the target exchange network node of display device displaying prediction
Rate carries out key monitoring to realize to the target exchange network node that prediction is broken down.
Further, as the preferred of above device embodiment, the model training unit 12 can be also used for according to reality
When the current network that obtains in the operation data of target exchange network node update the neural network prediction mould
Type.
Device described in the present embodiment can be used for performing above method embodiment, and principle is similar with technique effect, this
Place repeats no more.
It should be noted that for device embodiment, since it is basicly similar to embodiment of the method, so description
Fairly simple, the relevent part can refer to the partial explaination of embodiments of method.
The present invention is illustrated, but do not limit protection scope of the present invention with a specific embodiment below.
Fig. 3 is that the flow of the training neural network model in the network failure method for early warning of another embodiment of the present invention is shown
It is intended to, as shown in figure 3, the flow includes：
Step 1：Gathered data and training artificial nerve network model；
Step 2：Acquisition network status data in real time, and be input in trained model, obtaining all switching nodes can
The probability that can be broken down；
Step 3：It pinpoints and key monitoring is carried out, and possible measure is taken to avoid entire net to the switching node being calculated
Network is affected；
Step 4, all kinds of neural network prediction models are constantly updated.
Fig. 4 is the structure diagram of the network failure prior-warning device of another embodiment of the present invention；As shown in figure 4, the dress
Put including：Log collection unit 21, network flow statistic unit 22, pretreatment unit 23, prediction and calculation unit 24 and monitoring
Unit 25, wherein：
Log collection unit 21 can be used for pulling the journal file of all-network node to pretreatment unit 23；Wherein,
The journal file may include all recording equipment operating statuses such as the running log of the running log of terminal node, switching node
Information；The collected journal file can be stored in non-caching, the permanent memory block of the node or separately set special
Log server, the log information of whole network can be stored permanently；
Network flow statistic unit 22 can be used for recording the features such as size, the type of all terminal node network flows,
And by the record result be individually stored in the persistent storage of all terminal nodes or the special log server that separately sets in；
Pretreatment unit 23 can be used for all numbers for collecting log collection unit 21 and network flow statistic unit 22
According to calculation processing into the input data matrix of neural network, and training and test sample data are provided for above-mentioned steps 1 and step 4
Collection provides predictive data set for step 2；
Specifically, the pretreatment unit 23 can recompile all data availables, obtain performance and speed
Compared with the data set format of balance.
Wherein, the pretreatment unit 23 to the pattern of neural network model propelling data support real-time tupe, from
Line handles isotype.
Prediction and calculation unit 24 can be used for training artificial nerve network model (referring to Fig. 5), and use the artificial neuron
Network model predicts the failure rate of switching node.
Specifically, the prediction and calculation unit 24 for all switching nodes establish respective neural network model into
Row prediction；
Further, the feedforward network of the neural network model characterizes all possibility using continuous function and exports shape
State, feedforward part are approached using two-tier network.
Specifically, Fig. 6 shows the pre- flow gauge in the network failure method for early warning of another embodiment of the present invention, such as schemes
Shown in 6, the prediction and calculation unit 24 can train a plurality of types of neural network models, such as output state to exchange
The prediction model of the single switching node of the probability of malfunction of node；It is a certain localized network failure probability for output state
Prediction model；And for the prediction model of output state for the whole network failure etc..
As the preferred of the present embodiment, the prediction and calculation unit 24 can update the skilled prediction of institute with dynamic self-adapting
Model regularly updates all prediction models according to constantly accumulative history log file and network flow statistic information.
Monitoring unit 25 can be used for, by the way that various types prediction model result is weighted, obtaining with COMPREHENSIVE CALCULATING
Go out to need the switching node of key monitoring, monitor the operating status of each unit module.
As the preferred of the present embodiment, the monitoring unit 25 has the function of platform displaying, mail push, mobile terminal app
The functions such as push.
The network failure method for early warning and device of the embodiment of the present invention, according to journal file and network traffic information, to handing over
Change planes, the network switching nodes such as router carry out early warning in the appearance communication failure of equipment under normal circumstances, can set
Characteristic dimension transformation is carried out after standby, communication network data, it, can be to handing over by a plurality of types of neural network prediction models of training
The probability for changing node and network generation communication failure is predicted, and can obtain what may be broken down by combined calculation
Emphasis equipment or network area.
Above example is merely to illustrate technical scheme of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
The present invention is described in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each implementation
Technical solution recorded in example modifies or carries out equivalent replacement to which part technical characteristic；And these are changed or replace
It changes, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of network failure method for early warning, which is characterized in that including：
Obtain the operation data of the target exchange network node in current network；
Artificial nerve network model is trained according to the operation data of the target exchange network node；
According to the trained artificial nerve network model and the operation data of the current network acquired in real time, institute is predicted
State the probability of malfunction of target exchange network node.
2. the according to the method described in claim 1, it is characterized in that, target exchange network node obtained in current network
Operation data, including：
Obtain the running log of the target exchange network node and the network flow of the terminal node in the current network
Data.
3. the according to the method described in claim 1, it is characterized in that, operation number according to the target exchange network node
According to training artificial nerve network model, including：
Each target exchange network node artificial neural network is respectively trained according to the operation data of the target exchange network node
Model, each regional network artificial nerve network model of the current network and the whole network artificial neural network of the current network
Model.
4. according to the method described in claim 1, it is characterized in that, the method further includes：
By the probability of malfunction of the target exchange network node of display device displaying prediction, broken down with realizing to prediction
Target exchange network node carry out key monitoring.
5. according to claim 1-4 any one of them methods, which is characterized in that described according to the target exchange network node
Operation data training artificial nerve network model, including：
The operation data of target exchange network node in the current network obtained in real time updates the artificial neuron
Network Prediction Model.
6. a kind of network failure prior-warning device, which is characterized in that including：
Data capture unit, for obtaining the operation data of the target exchange network node in current network；
Model training unit, for training artificial nerve network model according to the operation data of the target exchange network node；
Failure predication unit, for according to the trained artificial nerve network model and the current network acquired in real time
Operation data, predict the probability of malfunction of the target exchange network node.
7. device according to claim 6, which is characterized in that the data capture unit is specifically used for obtaining the target
The network flow data of the running log of exchange network node and the terminal node in the current network.
8. device according to claim 6, which is characterized in that the model training unit is specifically used for according to the target
Each target exchange network node artificial nerve network model, the current network is respectively trained in the operation data of exchange network node
Each regional network artificial nerve network model and the current network the whole network artificial nerve network model.
9. device according to claim 6, which is characterized in that described device further includes：
Device display unit, for showing the probability of malfunction of the target exchange network node of prediction by display device, with
It realizes and key monitoring is carried out to the target exchange network node that prediction is broken down.
10. according to claim 6-9 any one of them devices, which is characterized in that the model training unit is additionally operable to：
The operation data of target exchange network node in the current network obtained in real time updates the artificial neuron
Network Prediction Model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611236959.0A CN108259194B (en) | 2016-12-28 | 2016-12-28 | Network fault early warning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611236959.0A CN108259194B (en) | 2016-12-28 | 2016-12-28 | Network fault early warning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108259194A true CN108259194A (en) | 2018-07-06 |
| CN108259194B CN108259194B (en) | 2021-08-06 |
Family
ID=62719700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611236959.0A Expired - Fee Related CN108259194B (en) | 2016-12-28 | 2016-12-28 | Network fault early warning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108259194B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146097A (en) * | 2018-09-21 | 2019-01-04 | 中国联合网络通信集团有限公司 | A kind of plant maintenance method and system, server-side and plant maintenance end |
| CN109639450A (en) * | 2018-10-23 | 2019-04-16 | 平安壹钱包电子商务有限公司 | Fault alarming method, computer equipment and storage medium neural network based |
| CN109783324A (en) * | 2018-12-11 | 2019-05-21 | 平安科技（深圳）有限公司 | System runs method for early warning and device |
| CN110311825A (en) * | 2019-08-08 | 2019-10-08 | 河南中烟工业有限责任公司 | A method of quickly disposition communication network failure is recalled by early warning |
| CN110502398A (en) * | 2019-08-21 | 2019-11-26 | 吉林吉大通信设计院股份有限公司 | A kind of exchange fault forecasting system and method based on artificial intelligence |
| CN110601909A (en) * | 2019-10-22 | 2019-12-20 | 广州供电局有限公司 | Network maintenance method and device, computer equipment and storage medium |
| CN110851342A (en) * | 2019-11-08 | 2020-02-28 | 中国工商银行股份有限公司 | Fault prediction method, device, computing equipment and computer readable storage medium |
| CN112465055A (en) * | 2020-12-09 | 2021-03-09 | 西安邮电大学 | Network fault diagnosis method based on convolutional neural network |
| WO2021147469A1 (en) * | 2020-01-21 | 2021-07-29 | 株式会社Ntt都科摩 | Communication system based on neural network model, and configuration method therefor |
| WO2022083226A1 (en) * | 2020-10-21 | 2022-04-28 | 中兴通讯股份有限公司 | Anomaly identification method and system, storage medium and electronic device |
| CN114613303A (en) * | 2022-03-18 | 2022-06-10 | 西安诺瓦星云科技股份有限公司 | Display screen control system fault prediction method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101242549A (en) * | 2007-11-22 | 2008-08-13 | 中国移动通信集团山东有限公司 | Neutral network construction method for communication network alarm association |
| CN102749572A (en) * | 2012-06-26 | 2012-10-24 | 南京航空航天大学 | IECMAC parameter identification-based power electronic circuit failure predicting method |
| CN104598984A (en) * | 2014-12-08 | 2015-05-06 | 北京邮电大学 | Fuzzy neural network based fault prediction method |
| CN104657792A (en) * | 2015-03-06 | 2015-05-27 | 中电海康集团有限公司 | Early warning method based on rule engine and intelligent prediction |
| US20150193694A1 (en) * | 2014-01-06 | 2015-07-09 | Cisco Technology, Inc. | Distributed learning in a computer network |
| CN105743699A (en) * | 2016-01-27 | 2016-07-06 | 中国航空工业集团公司沈阳飞机设计研究所 | Fault early warning method and system for virtual environment |
-
2016
- 2016-12-28 CN CN201611236959.0A patent/CN108259194B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101242549A (en) * | 2007-11-22 | 2008-08-13 | 中国移动通信集团山东有限公司 | Neutral network construction method for communication network alarm association |
| CN102749572A (en) * | 2012-06-26 | 2012-10-24 | 南京航空航天大学 | IECMAC parameter identification-based power electronic circuit failure predicting method |
| US20150193694A1 (en) * | 2014-01-06 | 2015-07-09 | Cisco Technology, Inc. | Distributed learning in a computer network |
| CN104598984A (en) * | 2014-12-08 | 2015-05-06 | 北京邮电大学 | Fuzzy neural network based fault prediction method |
| CN104657792A (en) * | 2015-03-06 | 2015-05-27 | 中电海康集团有限公司 | Early warning method based on rule engine and intelligent prediction |
| CN105743699A (en) * | 2016-01-27 | 2016-07-06 | 中国航空工业集团公司沈阳飞机设计研究所 | Fault early warning method and system for virtual environment |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146097A (en) * | 2018-09-21 | 2019-01-04 | 中国联合网络通信集团有限公司 | A kind of plant maintenance method and system, server-side and plant maintenance end |
| CN109639450A (en) * | 2018-10-23 | 2019-04-16 | 平安壹钱包电子商务有限公司 | Fault alarming method, computer equipment and storage medium neural network based |
| CN109783324A (en) * | 2018-12-11 | 2019-05-21 | 平安科技（深圳）有限公司 | System runs method for early warning and device |
| CN109783324B (en) * | 2018-12-11 | 2022-08-26 | 平安科技（深圳）有限公司 | System operation early warning method and device |
| CN110311825A (en) * | 2019-08-08 | 2019-10-08 | 河南中烟工业有限责任公司 | A method of quickly disposition communication network failure is recalled by early warning |
| CN110502398A (en) * | 2019-08-21 | 2019-11-26 | 吉林吉大通信设计院股份有限公司 | A kind of exchange fault forecasting system and method based on artificial intelligence |
| CN110502398B (en) * | 2019-08-21 | 2022-03-29 | 吉林吉大通信设计院股份有限公司 | Switch fault prediction system and method based on artificial intelligence |
| CN110601909B (en) * | 2019-10-22 | 2022-02-25 | 广东电网有限责任公司广州供电局 | Network maintenance method and device, computer equipment and storage medium |
| CN110601909A (en) * | 2019-10-22 | 2019-12-20 | 广州供电局有限公司 | Network maintenance method and device, computer equipment and storage medium |
| CN110851342A (en) * | 2019-11-08 | 2020-02-28 | 中国工商银行股份有限公司 | Fault prediction method, device, computing equipment and computer readable storage medium |
| WO2021147469A1 (en) * | 2020-01-21 | 2021-07-29 | 株式会社Ntt都科摩 | Communication system based on neural network model, and configuration method therefor |
| WO2022083226A1 (en) * | 2020-10-21 | 2022-04-28 | 中兴通讯股份有限公司 | Anomaly identification method and system, storage medium and electronic device |
| CN112465055A (en) * | 2020-12-09 | 2021-03-09 | 西安邮电大学 | Network fault diagnosis method based on convolutional neural network |
| CN114613303A (en) * | 2022-03-18 | 2022-06-10 | 西安诺瓦星云科技股份有限公司 | Display screen control system fault prediction method and device |
| CN114613303B (en) * | 2022-03-18 | 2023-10-20 | 西安诺瓦星云科技股份有限公司 | Display screen control system fault prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108259194B (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108259194A (en) | Network failure method for early warning and device | |
| CN104796273B (en) | A kind of method and apparatus of network fault root diagnosis | |
| CN105812177B (en) | A kind of network failure processing method and processing equipment | |
| CN106603293A (en) | Network fault diagnosis method based on deep learning in virtual network environment | |
| CN102204181B (en) | Route selection apparatus, optimal route selection method, and program | |
| CN107872457B (en) | Method and system for network operation based on network flow prediction | |
| US20120026898A1 (en) | Formatting Messages from Sensor Nodes in a Sensor Network | |
| CN110891283A (en) | Small base station monitoring device and method based on edge calculation model | |
| US11063861B2 (en) | Ensuring backup path performance for predictive routing in SD-WANs | |
| CN110460454B (en) | Intelligent network equipment port fault prediction method based on deep learning | |
| CN109947585A (en) | The processing method and processing device of PCIE device failure | |
| US11240122B2 (en) | Event-triggered machine learning for rare event forecasting in a software defined wide area Network (SD-WAN) | |
| EP3923517A1 (en) | System and method for predicting and handling short-term overflow | |
| CN104468220A (en) | Early warning control platform of power telecommunication network | |
| CN108880888A (en) | A kind of SDN network method for predicting based on deep learning | |
| CN104252401A (en) | Weight based device status judgment method and system thereof | |
| CN107872339A (en) | O＆M implementation method and device, Virtual Networking System in a kind of virtualization network | |
| Araujo et al. | Dependability evaluation of an iot system: A hierarchical modelling approach | |
| CN108092794A (en) | Network failure processing method and device | |
| Li et al. | Layered fault management scheme for end-to-end transmission in internet of things | |
| CN107947988A (en) | A kind of Real Time Communication Network analogue system | |
| Benslimen et al. | Attacks and failures prediction framework for a collaborative 5G mobile network | |
| CN110474801A (en) | Powerline network fault simulation method based on service reliability | |
| Izaddoost et al. | Risk-adaptive strategic network protection in disaster scenarios | |
| CN106156079A (en) | Daily record data treating method and apparatus |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210806 Termination date: 20211228 |