CN108259194B - Network fault early warning method and device - Google Patents
Network fault early warning method and device Download PDFInfo
- Publication number
- CN108259194B CN108259194B CN201611236959.0A CN201611236959A CN108259194B CN 108259194 B CN108259194 B CN 108259194B CN 201611236959 A CN201611236959 A CN 201611236959A CN 108259194 B CN108259194 B CN 108259194B
- Authority
- CN
- China
- Prior art keywords
- network
- target switching
- node
- artificial neural
- operation data
- 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.)
- Expired - Fee Related
Links
Images
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 invention relates to a network fault early warning method and a device, wherein the method comprises the following steps: acquiring operation data of a target switching network node in a current network; training an artificial neural network model according to the operation data of the target switching network node; and predicting the fault probability of the target switching network node according to the trained artificial neural network model and the real-time collected operation data of the current network. The network fault early warning method and the network fault early warning device can predict the fault of the switching node according to the operation data of each node in the network, train and update the artificial neural network model through a self-adaptive method, can improve the prediction precision of the fault rate of each switching node in the current network, realize early fault early warning and avoid loss.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a network fault early warning method and device.
Background
A switch or router, hereinafter collectively referred to as a switching node, is one of the most important IT network hardware devices. If the switching node is frequently failed, great inconvenience and loss are inevitably brought to daily work of individuals or enterprises and public institutions. Therefore, how to effectively prevent and avoid the switching node from being out of order has great practical significance for avoiding network accidents and reducing economic property loss.
In many cases, the switching node does not have the phenomena of crash and the like, but still cannot maintain normal communication. Possible failure phenomena include: the switching node works normally, but packet loss is serious, so that communication cannot be performed; or, the switch node works normally, and communication is directly unavailable due to unknown reasons, and the like. The main causes of such phenomena may include: network congestion caused by virus propagation, network congestion caused by large-flow resource downloading, and a large amount of spam messages caused by individual terminal hardware faults are issued to the network.
For the reasons that may occur, the existing coping technologies include: the use authority and rules of network terminal users are planned, the anti-virus measures of the network are perfected, anti-virus software is installed for each terminal, and the propagation of viruses in the network is inhibited as much as possible; and limiting the data transmission of large flow in the network, designing the network bearing capacity, installing network management software, monitoring network flow information and the like.
In daily network operation, a server down accident caused by some very common reasons exists, and a series of associated problems such as loops of the network can be caused, and the problems can directly or indirectly impact the switching nodes and cause the switching nodes to be incapable of continuing communication in a normal state of equipment. Aiming at the problems, the prior art can only perform investigation and solution by means of network sniffing, exchanger log checking and the like, and cannot perform early warning in advance to avoid loss.
Disclosure of Invention
Aiming at the defects that network fault troubleshooting and solution can be carried out only by means of network sniffing, exchanger log checking and the like and early warning cannot be carried out in advance to avoid loss in the prior art, the invention provides the following technical scheme:
one aspect of the present invention provides a network fault early warning method, including:
acquiring operation data of a target switching network node in a current network;
training an artificial neural network model according to the operation data of the target switching network node;
and predicting the fault probability of the target switching network node according to the trained artificial neural network model and the real-time collected operation data of the current network.
Optionally, the obtaining operation data of the target switching network node in the current network includes:
and acquiring the running log of the target switching network node and the network flow data of the terminal node in the current network.
Optionally, the training an artificial neural network model according to the operation data of the target switching network node includes:
and respectively training an artificial neural network model of each target switching network node, an artificial neural network model of each area network of the current network and a whole artificial neural network model of the current network according to the operation data of the target switching network nodes.
Optionally, the method further comprises:
and displaying the predicted fault probability of the target switching network node through a display device so as to realize key monitoring on the target switching network node predicted to have a fault.
Optionally, the training an artificial neural network model according to the operation data of the target switching network node includes:
and updating the artificial neural network prediction model according to the real-time acquired operation data of the target switching network node in the current network.
On the other hand, the invention also provides a network fault early warning device, which comprises:
the data acquisition unit is used for acquiring the operation data of the target switching network node in the current network;
the model training unit is used for training an artificial neural network model according to the operation data of the target switching network nodes;
and the fault prediction unit is used for predicting the fault probability of the target switching network node according to the trained artificial neural network model and the real-time acquired operation data of the current network.
Optionally, the data obtaining unit is specifically configured to obtain an operation log of the target switching network node and network traffic data of the terminal node in the current network.
Optionally, the model training unit is specifically configured to respectively train an artificial neural network model of each target switching network node, an artificial neural network model of each area network of the current network, and an artificial neural network model of a whole network of the current network according to the operation data of the target switching network node.
Optionally, the apparatus further comprises:
and the device display unit is used for displaying the predicted failure probability of the target switching network node through a display device so as to realize key monitoring on the target switching network node with the predicted failure.
Optionally, the model training unit is further configured to:
and updating the artificial neural network prediction model according to the real-time acquired operation data of the target switching network node in the current network.
According to the network fault early warning method and device, the operation data of the target switching network node in the current network is obtained, the artificial neural network model is trained according to the operation data of the target switching network node, the fault probability of the target switching network node is predicted according to the trained artificial neural network model and the operation data of the current network collected in real time, the fault of the switching node can be predicted according to the operation data of each node in the network, the artificial neural network model is trained and updated through a self-adaptive method, the prediction precision of the fault rate of each switching node in the current network can be improved, early fault early warning is achieved, and loss is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a network fault early warning method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a network fault early warning apparatus according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of a neural network model training process in a network fault early warning method according to another embodiment of the present invention;
fig. 4 is a schematic structural diagram of a network fault warning apparatus according to another embodiment of the present invention;
FIG. 5 is a schematic diagram of an artificial neural network model according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a prediction flow in a network fault early warning method according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a network fault early warning method according to an embodiment of the present invention; as shown in fig. 1, the method includes:
s1: acquiring operation data of a target switching network node in a current network;
specifically, the processor may obtain an operation log file of all network nodes in the current network, where the log file may include an operation log of the terminal node, an operation log of the switching node, and other information for recording the operation state of the device.
The collected log files can be stored in a non-cached and permanent storage area of the corresponding node or a preset log server, and the log information of the whole network is permanently stored.
S2: training an artificial neural network model according to the operation data of the target switching network node;
specifically, the processor trains an artificial neural network model according to the operation data of the target switching network node, and the specific method includes:
and respectively training an artificial neural network model of each target switching network node, an artificial neural network model of each area network of the current network and a whole artificial neural network model of the current network according to the operation data of the target switching network nodes.
The feedforward part adopts two layers of networks to approximate;
it is understood that the above trained neural network models of various types may include a prediction model for a single switching node outputting a failure probability of a target switching node in a state; the system also comprises a prediction model used for outputting the fault probability of a certain local network; and a prediction model for outputting the state that the whole network fails, and the like.
It should be noted that the method of this embodiment includes updating all the prediction models adaptively, that is, updating all the prediction models periodically according to data such as a continuously accumulated historical log file.
S3: and predicting the fault probability of the target switching network node according to the trained artificial neural network model and the real-time collected operation data of the current network.
Specifically, the processor predicts the failure probability of the target switching network node according to the trained artificial neural network model and the real-time collected operation data of the current network.
Specifically, the processor may perform weighted calculation on the prediction results of the various types of artificial neural network prediction models, so as to obtain the operation state of the switching node that needs to be monitored intensively through comprehensive calculation. Further, as a preference of this embodiment, the method may further include:
and displaying the predicted fault probability of the target switching network node through a display device so as to realize key monitoring on the target switching network node predicted to have a fault.
For example, the processor may display the predicted failure probability of the target switching network node through a display device of a terminal through functions of mail push, mobile app push, and the like.
According to the network fault early warning method, the operation data of the target switching network node in the current network is obtained, the artificial neural network model is trained according to the operation data of the target switching network node, the fault probability of the target switching network node is predicted according to the trained artificial neural network model and the operation data of the current network collected in real time, the fault of the switching node can be predicted according to the operation data of each node in the network, the artificial neural network model is trained and updated through a self-adaptive method, the prediction precision of the fault rate of each switching node in the current network can be improved, early fault early warning is achieved, and loss is avoided.
Fig. 2 is a schematic structural diagram of a network fault early warning apparatus according to an embodiment of the present invention; as shown in fig. 2, the apparatus includes a data acquisition unit 11, a model training unit 12, and a failure prediction unit 13, wherein:
the data obtaining unit 11 is configured to obtain operation data of a target switching network node in a current network;
the model training unit 12 is configured to train an artificial neural network model according to the operation data of the target switching network node;
the fault prediction unit 13 is configured to predict a fault probability of the target switching network node according to the trained artificial neural network model and the operation data of the current network collected in real time.
Specifically, the data obtaining unit 11 obtains operation data of a target switching network node in a current network; the model training unit 12 trains an artificial neural network model according to the operation data of the target switching network node; the fault prediction unit 13 predicts the fault probability of the target switching network node according to the trained artificial neural network model and the real-time collected operation data of the current network.
The apparatus described in this embodiment may be used to implement the above method embodiments, and the principle and technical effect are similar, which are not described herein again.
Further, as a preferable example of the foregoing apparatus, the data obtaining unit 11 may be specifically configured to obtain an operation log of the target switching network node and network traffic data of the terminal node in the current network.
Further, as a preferred embodiment of the foregoing apparatus, the model training unit 12 is specifically configured to train, according to the operation data of the target switching network nodes, the artificial neural network models of the area networks of the current network, and the artificial neural network model of the whole network of the current network, respectively.
Further, as a preference of the above-mentioned apparatus embodiment, the apparatus may further include:
and the device display unit 14 is configured to display the predicted failure probability of the target switching network node through a display device, so as to implement key monitoring on the target switching network node predicted to have a failure.
Further, as a preferable example of the foregoing apparatus, the model training unit 12 may be further configured to update the artificial neural network prediction model according to operation data of a target switching network node in the current network, which is acquired in real time.
The apparatus described in this embodiment may be used to implement the above method embodiments, and the principle and technical effect are similar, which are not described herein again.
It should be noted that, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to part of the description of the method embodiment.
The present invention is described below with reference to a specific example, but the scope of the present invention is not limited thereto.
Fig. 3 is a schematic flowchart of a process of training a neural network model in a network fault early warning method according to another embodiment of the present invention, as shown in fig. 3, the process includes:
step 1: collecting data and training an artificial neural network model;
step 2: collecting network state data in real time, and inputting the data into a trained model to obtain the probability that all the switching nodes possibly have faults;
and step 3: the fixed point carries out key monitoring on the exchange node obtained by calculation and takes possible measures to avoid the influence on the whole network;
and 4, continuously updating various neural network prediction models.
Fig. 4 is a schematic structural diagram of a network fault warning apparatus according to another embodiment of the present invention; as shown in fig. 4, the apparatus includes: log collection unit 21, network traffic statistics unit 22, preprocessing unit 23, prediction calculation unit 24 and monitoring unit 25, wherein:
the log collection unit 21 may be configured to pull log files of all network nodes to the preprocessing unit 23; the log file can include running logs of the terminal node, running logs of the exchange node and other information of running states of all recording devices; the collected log files can be stored in a non-cached and permanent storage area of the node or a special log server is additionally arranged, and the log information of the whole network can be permanently stored;
the network traffic statistic unit 22 may be configured to record characteristics of network traffic of all terminal nodes, such as size and type, and separately store the recording result in a permanent storage area of all terminal nodes or an additional special log server;
the preprocessing unit 23 may be configured to calculate and process all data collected by the log collecting unit 21 and the network traffic statistical unit 22 into an input data matrix of the neural network, provide a training and testing sample data set for the above steps 1 and 4, and provide a prediction data set for the step 2;
specifically, the preprocessing unit 23 can re-encode all available data to obtain a data set format with balanced performance and speed.
The mode of pushing data to the neural network model by the preprocessing unit 23 supports a real-time processing mode, an offline processing mode, and the like.
The prediction computation unit 24 may be used to train an artificial neural network model (see fig. 5) and predict the failure rate of the switching node using the artificial neural network model.
Specifically, the prediction calculation unit 24 establishes respective neural network models for all the switching nodes to perform prediction;
further, the feedforward network of the neural network model uses a continuous function to characterize all possible output states, and the feedforward part uses a two-layer network to perform approximation.
Specifically, fig. 6 shows a prediction flow in the network fault early warning method according to another embodiment of the present invention, as shown in fig. 6, the prediction calculation unit 24 may train multiple types of neural network models, for example, a prediction model of a single switching node for outputting a fault probability of a switching node as an output state; the prediction model is used for outputting the fault probability of a local network in a state; and a prediction model for outputting the state that the whole network fails, and the like.
Preferably, the prediction calculation unit 24 may dynamically and adaptively update all trained prediction models, that is, periodically update all the prediction models according to the continuously accumulated historical log files and the network traffic statistical information.
The monitoring unit 25 may be configured to perform weighted calculation on the results of the various types of prediction models to obtain the switching nodes that need to be monitored intensively and monitor the operating states of the unit modules.
Preferably, the monitoring unit 25 has functions of platform display, mail pushing, mobile app pushing, and the like.
According to the network fault early warning method and device provided by the embodiment of the invention, communication faults of network switching nodes such as switches and routers under normal equipment conditions are early warned according to log files and network flow information, characteristic scale transformation can be carried out after equipment and communication network data are obtained, the probability of the communication faults of the switching nodes and the network can be predicted by training various types of neural network prediction models, and key equipment or network areas which are possible to have faults can be obtained through joint calculation.
The above examples are only for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. A network fault early warning method is characterized by comprising the following steps:
acquiring operation data of a target switching network node in a current network;
training an artificial neural network model according to the operation data of the target switching network node;
predicting the fault probability of the target switching network node according to the trained artificial neural network model and the real-time collected operation data of the current network;
the acquiring of the operation data of the target switching network node in the current network includes:
acquiring the running log of the target switching network node and the network flow data of the terminal node in the current network;
the training of the artificial neural network model according to the operation data of the target switching network node comprises the following steps:
respectively training an artificial neural network model of each target switching network node, an artificial neural network model of each area network of the current network and a whole artificial neural network model of the current network according to the operation data of the target switching network nodes;
and performing weighted calculation on the prediction results of various artificial neural network models to obtain the operation state of the exchange node which is mainly monitored.
2. The method of claim 1, further comprising:
and displaying the predicted fault probability of the target switching network node through a display device so as to realize key monitoring on the target switching network node predicted to have a fault.
3. The method of any of claims 1-2, wherein training an artificial neural network model based on operational data of the target switching network node comprises:
and updating the artificial neural network model according to the real-time acquired operation data of the target switching network node in the current network.
4. A network fault early warning device, comprising:
the data acquisition unit is used for acquiring the operation data of the target switching network node in the current network;
the model training unit is used for training an artificial neural network model according to the operation data of the target switching network nodes;
the fault prediction unit is used for predicting the fault probability of the target switching network node according to the trained artificial neural network model and the real-time collected operation data of the current network;
the data acquisition unit is specifically configured to acquire an operation log of the target switching network node and network traffic data of a terminal node in the current network;
the model training unit is specifically used for respectively training an artificial neural network model of each target switching network node, an artificial neural network model of each area network of the current network and a whole artificial neural network model of the current network according to the operation data of the target switching network nodes;
and performing weighted calculation on the prediction results of various artificial neural network models to obtain the operation state of the exchange node which is mainly monitored.
5. The apparatus of claim 4, further comprising:
and the device display unit is used for displaying the predicted failure probability of the target switching network node through a display device so as to realize key monitoring on the target switching network node with the predicted failure.
6. The apparatus of any of claims 4-5, wherein the model training unit is further configured to:
and updating the artificial neural network model according to the real-time acquired operation data of the target switching network node in the current network.
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 CN108259194A (en) | 2018-07-06 |
| CN108259194B true 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) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146097B (en) * | 2018-09-21 | 2021-02-02 | 中国联合网络通信集团有限公司 | Equipment maintenance method and system, server and equipment maintenance terminal |
| CN109639450B (en) * | 2018-10-23 | 2023-06-23 | 平安壹钱包电子商务有限公司 | Fault alarm method, system, computer equipment and medium based on neural network |
| 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 |
| 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 |
| 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 |
| CN113225197A (en) * | 2020-01-21 | 2021-08-06 | 株式会社Ntt都科摩 | Communication system based on neural network model and configuration method thereof |
| CN114465739A (en) * | 2020-10-21 | 2022-05-10 | 中兴通讯股份有限公司 | Abnormality recognition method and system, storage medium, and electronic apparatus |
| CN112465055A (en) * | 2020-12-09 | 2021-03-09 | 西安邮电大学 | Network fault diagnosis method based on convolutional neural network |
| 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 |
Citations (5)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9870537B2 (en) * | 2014-01-06 | 2018-01-16 | Cisco Technology, Inc. | Distributed learning in a computer network |
-
2016
- 2016-12-28 CN CN201611236959.0A patent/CN108259194B/en not_active Expired - Fee Related
Patent Citations (5)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108259194A (en) | 2018-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108259194B (en) | Network fault early warning method and device | |
| JP6097889B2 (en) | Monitoring system, monitoring device, and inspection device | |
| US20150195154A1 (en) | Creating a Knowledge Base for Alarm Management in a Communications Network | |
| US20100100775A1 (en) | Filtering Redundant Events Based On A Statistical Correlation Between Events | |
| KR20180120558A (en) | System and method for predicting communication apparatuses failure based on deep learning | |
| CN110752951A (en) | Industrial network flow monitoring and auditing method, device and system | |
| CN105763387B (en) | network traffic monitoring method and device | |
| CN101248360A (en) | Method and apparatus for managing a communication link | |
| Nguyen et al. | Absence: Usage-based failure detection in mobile networks | |
| CN107635003A (en) | The management method of system journal, apparatus and system | |
| WO2021143483A1 (en) | System maintenance method and apparatus, device, and storage medium | |
| CN116166499A (en) | Data monitoring method and device, electronic equipment and nonvolatile storage medium | |
| CN109995558A (en) | Failure information processing method, device, equipment and storage medium | |
| CN111082998A (en) | Architecture system of operation and maintenance monitoring campus convergence layer | |
| CN116155581A (en) | Network intrusion detection method and device based on graph neural network | |
| CN113300914A (en) | Network quality monitoring method, device, system, electronic equipment and storage medium | |
| CN108248641A (en) | A kind of urban track traffic data processing method and device | |
| CN110609761B (en) | Method and device for determining fault source, storage medium and electronic equipment | |
| CN105743726A (en) | Traffic statistics and analysis method for feature data message and corresponding device | |
| CN110719197A (en) | Train-mounted Ethernet state prediction method and device | |
| CN101557321A (en) | Method for monitoring bandwidth of interface in distributed system and device | |
| CN112260903B (en) | Link monitoring method and device | |
| KR100450415B1 (en) | A Network Management Method using Availability Prediction | |
| CN116522213A (en) | Service state level classification and classification model training method and electronic equipment | |
| AT&T |
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 |
Granted publication date: 20210806 Termination date: 20211228 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |