CN111277444B - Switch fault early warning method and device - Google Patents
Switch fault early warning method and device Download PDFInfo
- Publication number
- CN111277444B CN111277444B CN202010080690.1A CN202010080690A CN111277444B CN 111277444 B CN111277444 B CN 111277444B CN 202010080690 A CN202010080690 A CN 202010080690A CN 111277444 B CN111277444 B CN 111277444B
- Authority
- CN
- China
- Prior art keywords
- lstm
- predictor
- feature
- response
- prediction vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 239000013598 vector Substances 0.000 claims abstract description 114
- 230000004044 response Effects 0.000 claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000003062 neural network model Methods 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 12
- 230000007774 longterm Effects 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
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
- H04L41/02—Standardisation; Integration
- H04L41/0213—Standardised network management protocols, e.g. simple network management protocol [SNMP]
-
- 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
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a switch fault early warning method and a device, wherein the method comprises the following steps: continuously collecting operation data from a plurality of exchangers through a simple network management protocol and storing the operation data into a time sequence database; periodically performing feature engineering processing on the operation data to obtain feature vectors in response to determining that the plurality of switches all operate normally based on the time series database; determining in a comparator a difference of the feature vector and the prediction vector in response to an already existing prediction vector in the LSTM predictor; early warning information is output by the real-time annunciator in response to the difference exceeding a predetermined threshold. The invention can give intuitive undifferentiated early warning for different types of switches, reduce the requirement of personnel capacity and advance the early warning time so as to prevent accidents.
Description
Technical Field
The present invention relates to the field of switches, and in particular, to a method and an apparatus for early warning a switch failure.
Background
The switch is an important component in the internet system, is used for connecting each node in the network, and directly influences the communication between the networks once a fault occurs, so that the network transmission rate is reduced if the fault occurs, and the network is interrupted or data transmission is wrong if the fault occurs. In view of this, fault monitoring and early warning for switches are important components in network management. The switch provides some index information during operation, and the index information can be monitored by operation and maintenance personnel, such as the utilization rate of the processor, the packet loss rate, the throughput and the like, and can be processed in time once abnormal conditions are found.
However, index information provided by the switch in the prior art cannot directly explain whether the switch fails or not, and is judged by experienced network engineers and is not intuitive; different switch brands and models have inconsistent data, special experience knowledge is required, and if the switch is upgraded, corresponding parameters can be changed; in addition, the monitoring of the layer is already after the fact, only fault post-processing can be carried out, early warning cannot be carried out, and the hysteresis is too strong.
Aiming at the problems of difficult judgment, complex change and strong hysteresis of the switch in the prior art, no effective solution is available at present.
Disclosure of Invention
In view of this, an object of the embodiments of the present invention is to provide a method and an apparatus for early warning a failure of an exchange, which can provide an intuitive and undifferentiated early warning for different types of exchanges, reduce the requirement for personnel capacity, and advance the early warning time so as to prevent an accident.
Based on the above object, a first aspect of the embodiments of the present invention provides a method for early warning of a switch failure, including the following steps:
continuously collecting operation data from a plurality of exchangers through a simple network management protocol and storing the operation data into a time sequence database;
periodically performing feature engineering processing on the operation data to obtain a feature vector in response to determining that the plurality of switches all operate normally based on the time series database;
determining in a comparator a difference of the feature vector and the prediction vector in response to the prediction vector already existing in the LSTM predictor;
and outputting early warning information through a real-time alarm in response to the difference exceeding a predetermined threshold.
In some embodiments, further comprising: in response to a determination at any time that there is an operational abnormality in the plurality of exchanges based on the time-series database, alarm information other than the warning information is output directly through the real-time alarm.
In some embodiments, further comprising:
in response to the LSTM predictor that no prediction vector exists or the generation time of the prediction vector exceeds the preset service life, continuously storing the obtained feature vectors into the feature engineering database until the feature engineering database is determined to store enough feature vectors for generating the prediction vector;
a prediction vector is generated based on the feature engineering database by using the LSTM predictor, and long-term dependence information of the feature vector is learned and stored in the LSTM predictor.
In some embodiments, further comprising:
before generating a prediction vector by using an LSTM predictor, constructing a neural network model of the LSTM predictor by using a machine learning tool Tensorflow;
training the neural network model by using preset training data until the neural network model converges;
the converged neural network model is tested using the feature vectors to generate an LSTM predictor.
In some embodiments, further comprising: the feature vectors are stored in a feature engineering database in response to the difference not exceeding the predetermined threshold.
A second aspect of an embodiment of the present invention provides an apparatus for early warning a switch failure, including:
a processor; and
a memory storing program code executable by the processor, the program code when executed sequentially performing the steps of:
continuously collecting operation data from a plurality of exchangers through a simple network management protocol and storing the operation data into a time sequence database;
periodically performing feature engineering processing on the operation data to obtain feature vectors in response to determining that the plurality of switches all operate normally based on the time series database;
determining in a comparator a difference of the feature vector and the prediction vector in response to an already existing prediction vector in the LSTM predictor;
early warning information is output by the real-time annunciator in response to the difference exceeding a predetermined threshold.
In some embodiments, the steps further comprise: in response to a determination at any time that there is an operational abnormality in the plurality of exchanges based on the time-series database, alarm information different from the warning information is output directly through the real-time alarm.
In some embodiments, the steps further comprise: in response to the LSTM predictor that no prediction vector exists or the generation time of the prediction vector exceeds the preset service life, continuously storing the obtained feature vectors into the feature engineering database until the feature engineering database is determined to store enough feature vectors for generating the prediction vector;
a prediction vector is generated based on the feature engineering database by using the LSTM predictor, and long-term dependence information of the feature vector is learned and stored in the LSTM predictor.
In some embodiments, the steps further comprise:
before the LSTM predictor is used for generating a prediction vector, a machine learning tool Tensorflow is used for constructing a neural network model of the LSTM predictor;
training the neural network model by using preset training data until the neural network model converges;
the converged neural network model is tested using the feature vectors to generate an LSTM predictor.
In some embodiments, the steps further comprise: the feature vectors are stored in a feature engineering database in response to the difference not exceeding the predetermined threshold.
The invention has the following beneficial technical effects: according to the switch fault early warning method and device provided by the embodiment of the invention, the operation data is continuously collected from a plurality of switches through a simple network management protocol and is stored in a time sequence database; periodically performing feature engineering processing on the operation data to obtain feature vectors in response to determining that the plurality of switches all operate normally based on the time series database; determining in a comparator a difference of the feature vector and the prediction vector in response to the prediction vector already existing in the LSTM predictor; the technical scheme that the real-time alarm outputs the early warning information in response to the fact that the difference exceeds the preset threshold value can give intuitive non-difference early warning for different types of switches, requirements on personnel capacity are reduced, and early warning time is advanced so as to prevent accidents.
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 embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow diagram of a switch failure early warning method provided by the present invention;
fig. 2 is a schematic diagram of a structure of a switch failure early warning method provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following embodiments of the present invention are described in further detail with reference to the accompanying drawings.
It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two entities with the same name but different names or different parameters, and it should be noted that "first" and "second" are only used for convenience of expression and should not be construed as a limitation to the embodiments of the present invention, and no description is given in the following embodiments.
In view of the above, a first aspect of the embodiments of the present invention provides an embodiment of a method capable of giving an intuitive indifferent early warning to different types of switches. Fig. 1 is a schematic flow chart of a switch failure early warning method provided by the present invention.
The switch failure early warning method, as shown in fig. 1, includes the following steps:
step S101: continuously collecting operation data from a plurality of exchangers through a simple network management protocol and storing the operation data into a time sequence database;
step S103: periodically performing feature engineering processing on the operation data to obtain feature vectors in response to determining that the plurality of switches all operate normally based on the time series database;
step S105: determining in a comparator a difference of the feature vector and the prediction vector in response to an already existing prediction vector in the LSTM predictor;
step S107: early warning information is output by the real-time annunciator in response to the difference exceeding a predetermined threshold.
The LSTM is a special neural network model type, and can learn long-term dependence information so as to solve the problem of long-term dependence.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a Random Access Memory (RAM), or the like. Embodiments of the computer program may achieve the same or similar effects as any of the preceding method embodiments to which it corresponds.
In some embodiments, further comprising: in response to a determination at any time that there is an operational abnormality in the plurality of exchanges based on the time-series database, alarm information different from the warning information is output directly through the real-time alarm.
In some embodiments, further comprising: in response to the LSTM predictor that no prediction vector exists or the generation time of the prediction vector exceeds the preset service life, continuously storing the obtained feature vectors into the feature engineering database until the feature engineering database is determined to store enough feature vectors for generating the prediction vector;
a prediction vector is generated based on the feature engineering database by using the LSTM predictor, and long-term dependence information of the feature vector is learned and stored in the LSTM predictor.
In some embodiments, further comprising:
before generating a prediction vector by using an LSTM predictor, constructing a neural network model of the LSTM predictor by using a machine learning tool Tensorflow;
training the neural network model by using preset training data until the neural network model converges;
the converged neural network model is tested using the feature vectors to generate an LSTM predictor.
In some embodiments, further comprising: the feature vectors are stored in a feature engineering database in response to the difference not exceeding the predetermined threshold.
The method disclosed according to an embodiment of the present invention may also be implemented as a computer program executed by a CPU (central processing unit), and the computer program may be stored in a computer-readable storage medium. The computer program, when executed by the CPU, performs the above-described functions defined in the method disclosed in the embodiments of the present invention. The above-described method steps and system elements may also be implemented using a controller and a computer-readable storage medium for storing a computer program for causing the controller to implement the functions of the above-described steps or elements.
The following further illustrates embodiments of the invention in accordance with the specific example shown in fig. 2.
As shown in fig. 2, the relevant data of the switch is collected into the time sequence database by snmp (simple network management protocol) timing. And the switch data is processed by feature engineering to generate a feature vector fv. At this time, if the prediction vector pv is already present, the difference between fv and pv is compared by the comparator; if the difference is too large, the exchanger is determined to be in fault, a real-time alarm gives out early warning, and if the difference is not large, fv is added into the feature vector database. And if the predicted feature vector which is generated in advance does not exist at present, directly storing the feature vector fv into a feature engineering database. If the collected feature vector data is enough, the next reasonable prediction vector pv is predicted by the LSTM predictor and stored for later use.
In particular embodiments, the operational data includes switch brand, model, date of manufacture, number of ports in use, number of chassis affiliated, total flow into, total flow out, number of boards, firmware version, packet loss rate, number of packets lost, tree utilization, temperature, and the like.
The feature vector and the prediction vector include:
switch brand: hua is 0, cisco 1, others 2
The model is as follows: 4 bits after md5 are taken, and converted into 10-system numbers according to 16-system
The production date is as follows: making 8-bit integer according to year and month diary
After the number of ports used: integer number of
The machine frame comprises: 4 bits after md5 are taken, and converted into 10-system numbers according to 16-system
Total flow rate of inflow: in bit units
Total flow rate of effluent: in bit units
The number of board cards is as follows: integer number of
Firmware version: removing points among large version number, medium version number and small version number to form integer
Packet loss rate: decimal between 0 and 1, 4 significant digits
Number of lost packets: integer number of
Processor utilization: decimal between 0 and 1, two decimal places being reserved
Temperature: decimal fraction, 1 digit decimal fraction
These values combine to form a 13-dimensional feature vector, such as (0,53294,20130604,24,66432,6500234221,2400323832,8,301,0.000,0,0.23, 75.1)
Where feature vectors that are not generated in advance are not involved and feature vectors that are reasonable for subsequent prediction are not involved.
It can be seen from the above embodiments that, the switch failure early warning method provided by the embodiments of the present invention continuously collects operation data from a plurality of switches through a simple network management protocol and stores the operation data in a time series database; periodically performing feature engineering processing on the operation data to obtain feature vectors in response to determining that the plurality of switches all operate normally based on the time series database; determining in a comparator a difference of the feature vector and the prediction vector in response to an already existing prediction vector in the LSTM predictor; the technical scheme that the real-time alarm outputs the early warning information in response to the fact that the difference exceeds the preset threshold value can give intuitive non-difference early warning for different types of switches, requirements on personnel capacity are reduced, and early warning time is advanced so as to prevent accidents.
It should be noted that, the steps in the embodiments of the switch failure early warning method described above may be mutually intersected, replaced, added, or deleted, and therefore, the switch failure early warning method based on these reasonable permutation and combination transformations shall also belong to the protection scope of the present invention, and shall not limit the protection scope of the present invention to the embodiments.
In view of the above, a second aspect of the embodiments of the present invention provides an embodiment of an apparatus capable of giving an intuitive undifferentiated warning for different types of switches. The switch failure early warning device includes:
a processor; and
a memory storing program code executable by the processor, the program code when executed sequentially performing the steps of:
continuously collecting operation data from a plurality of exchangers through a simple network management protocol and storing the operation data into a time sequence database;
periodically performing feature engineering processing on the operation data to obtain feature vectors in response to determining that the plurality of switches all operate normally based on the time series database;
determining in a comparator a difference of the feature vector and the prediction vector in response to an already existing prediction vector in the LSTM predictor;
early warning information is output by the real-time annunciator in response to the difference exceeding a predetermined threshold.
In some embodiments, the steps further comprise: in response to a determination at any time that there is an operational abnormality in the plurality of exchanges based on the time-series database, alarm information different from the warning information is output directly through the real-time alarm.
In some embodiments, the steps further comprise: in response to the LSTM predictor that no prediction vector exists or the generation time of the prediction vector exceeds the preset service life, continuously storing the obtained feature vectors into the feature engineering database until the feature engineering database is determined to store enough feature vectors for generating the prediction vector;
a prediction vector is generated based on the feature engineering database by using the LSTM predictor, and long-term dependence information of the feature vector is learned and stored in the LSTM predictor.
In some embodiments, the steps further comprise:
before the LSTM predictor is used for generating a prediction vector, a machine learning tool Tensorflow is used for constructing a neural network model of the LSTM predictor;
training the neural network model by using preset training data until the neural network model converges;
the converged neural network model is tested using the feature vectors to generate an LSTM predictor.
In some embodiments, the steps further comprise: storing the feature vector in a feature engineering database in response to the difference not exceeding the predetermined threshold.
It can be seen from the above embodiments that, the switch failure early warning device provided by the embodiment of the present invention continuously collects operation data from a plurality of switches through a simple network management protocol and stores the operation data in a time series database; periodically performing feature engineering processing on the operation data to obtain feature vectors in response to determining that the plurality of switches all operate normally based on the time series database; determining in a comparator a difference of the feature vector and the prediction vector in response to the prediction vector already existing in the LSTM predictor; the technical scheme that the real-time alarm outputs the early warning information in response to the fact that the difference exceeds the preset threshold value can give intuitive non-difference early warning for different types of switches, requirements on personnel capacity are reduced, and early warning time is advanced so as to prevent accidents.
It should be particularly noted that, the embodiment of the switch failure early warning apparatus described above employs the embodiment of the switch failure early warning method to specifically describe the working process of each module, and those skilled in the art can easily think that these modules are applied to other embodiments of the switch failure early warning method. Of course, since the steps in the embodiment of the switch failure warning method may be intersected, replaced, added, and deleted, the switch failure warning apparatus that is transformed by these reasonable permutations and combinations also should belong to the protection scope of the present invention, and the protection scope of the present invention should not be limited to the embodiment.
The foregoing is an exemplary embodiment of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the present disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the disclosed embodiments of the invention may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.
It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items. The numbers of the embodiments disclosed in the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, of embodiments of the invention is limited to these examples; within the idea of an embodiment of the invention, also technical features in the above embodiment or in different embodiments may be combined and there are many other variations of the different aspects of an embodiment of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present invention are intended to be included within the scope of the embodiments of the present invention.
Claims (4)
1. A switch failure early warning method is characterized by comprising the following steps:
continuously collecting operation data from a plurality of exchangers through a simple network management protocol and storing the operation data into a time sequence database;
outputting alarm information directly through a real-time alarm in response to determining that there is an operational anomaly in the plurality of exchanges at any time based on the time-series database;
periodically performing feature engineering processing on the operational data to obtain feature vectors in response to determining that the plurality of switches are all operating properly based on the time series database;
in response to the LSTM predictor not having a prediction vector or the generation time of the prediction vector exceeding the predetermined life span, continuously storing the obtained feature vector into a feature engineering database until it is determined that the feature engineering database stores enough feature vectors to generate the prediction vector, and generating the prediction vector with long-term dependence information of the feature vector learned based on the feature engineering database by using the LSTM predictor and storing the prediction vector in the LSTM predictor;
determining in a comparator a difference of the feature vector and the prediction vector in response to an already existing prediction vector in an LSTM predictor;
storing the feature vector in the feature engineering database in response to the difference not exceeding a predetermined threshold;
outputting, by a real-time alarm, pre-warning information in response to the difference exceeding a predetermined threshold, the pre-warning information being different from the warning information.
2. The method of claim 1, further comprising:
before generating the prediction vector using the LSTM predictor, constructing a neural network model of the LSTM predictor using a machine learning tool Tensorflow;
training the neural network model using preset training data until the neural network model converges;
testing the converged neural network model using the feature vectors to generate the LSTM predictor.
3. A switch fault early warning device, characterized in that includes:
a processor; and
a memory storing program code executable by the processor, the program code when executed sequentially performing the steps of:
continuously collecting operation data from a plurality of exchangers through a simple network management protocol and storing the operation data into a time sequence database;
outputting alarm information directly through a real-time alarm in response to determining that there is an operational anomaly in the plurality of switches based on the time-series database at any time;
periodically performing feature engineering processing on the operational data to obtain a feature vector in response to determining that the plurality of switches are all functioning properly based on the time series database;
in response to no prediction vector existing in the LSTM predictor or the generation time of the prediction vector exceeding the predetermined life span of the LSTM predictor, continuously storing the obtained feature vector in a feature engineering database until the feature engineering database is determined to store the feature vector enough to generate the prediction vector, and generating the prediction vector learning the long-term dependence information of the feature vector based on the feature engineering database by using the LSTM predictor and storing the prediction vector in the LSTM predictor;
determining in a comparator a difference of the feature vector and the prediction vector in response to an already existing prediction vector in an LSTM predictor;
storing the feature vector in the feature engineering database in response to the difference not exceeding a predetermined threshold;
outputting, by a real-time alarm, pre-warning information in response to the difference exceeding a predetermined threshold, the pre-warning information being different from the warning information.
4. The apparatus of claim 3, wherein the steps further comprise:
before generating the prediction vector using the LSTM predictor, constructing a neural network model of the LSTM predictor using a machine learning tool Tensorflow;
training the neural network model using preset training data until the neural network model converges;
testing the converged neural network model using the feature vectors to generate the LSTM predictor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010080690.1A CN111277444B (en) | 2020-02-05 | 2020-02-05 | Switch fault early warning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010080690.1A CN111277444B (en) | 2020-02-05 | 2020-02-05 | Switch fault early warning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111277444A CN111277444A (en) | 2020-06-12 |
| CN111277444B true CN111277444B (en) | 2022-12-27 |
Family
ID=71001987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010080690.1A Active CN111277444B (en) | 2020-02-05 | 2020-02-05 | Switch fault early warning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111277444B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657628A (en) * | 2021-08-20 | 2021-11-16 | 武汉霖汐科技有限公司 | Industrial equipment monitoring method and system, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108681496A (en) * | 2018-05-09 | 2018-10-19 | 北京奇艺世纪科技有限公司 | Prediction technique, device and the electronic equipment of disk failure |
| CN108900546A (en) * | 2018-08-13 | 2018-11-27 | 杭州安恒信息技术股份有限公司 | The method and apparatus of time series Network anomaly detection based on LSTM |
| 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 |
| CN109814527A (en) * | 2019-01-11 | 2019-05-28 | 清华大学 | Based on LSTM Recognition with Recurrent Neural Network industrial equipment failure prediction method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11675641B2 (en) * | 2018-07-02 | 2023-06-13 | Nec Corporation | Failure prediction |
-
2020
- 2020-02-05 CN CN202010080690.1A patent/CN111277444B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108681496A (en) * | 2018-05-09 | 2018-10-19 | 北京奇艺世纪科技有限公司 | Prediction technique, device and the electronic equipment of disk failure |
| CN108900546A (en) * | 2018-08-13 | 2018-11-27 | 杭州安恒信息技术股份有限公司 | The method and apparatus of time series Network anomaly detection based on LSTM |
| 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 |
| CN109814527A (en) * | 2019-01-11 | 2019-05-28 | 清华大学 | Based on LSTM Recognition with Recurrent Neural Network industrial equipment failure prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111277444A (en) | 2020-06-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110601898B (en) | Abnormity early warning method, abnormity early warning device, server and storage medium | |
| CN109787817B (en) | Network fault diagnosis method, device and computer readable storage medium | |
| US6353902B1 (en) | Network fault prediction and proactive maintenance system | |
| WO2020211561A1 (en) | Data processing method and device, storage medium and electronic device | |
| CN112769605B (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
| CN110968061B (en) | Equipment fault early warning method and device, storage medium and computer equipment | |
| CN105187255B (en) | Failure analysis methods, fail analysis device and server | |
| CN114448774B (en) | Alarm processing method, device and storage medium | |
| CN111277444B (en) | Switch fault early warning method and device | |
| CN116582414A (en) | Fault root cause positioning method, device, equipment and readable storage medium | |
| CN116471196B (en) | Operation and maintenance monitoring network maintenance method, system and equipment | |
| CN111078503B (en) | Abnormality monitoring method and system | |
| CN116015707A (en) | Network topology optimization method, device and terminal for power distribution network information physical system | |
| CN114547600A (en) | Industrial control system safety protection method, device, equipment and medium | |
| CN111611097A (en) | Fault detection method, device, equipment and storage medium | |
| CN113325708B (en) | Fault estimation method of multi-unmanned aerial vehicle system based on heterogeneous multi-agent | |
| CN110609761B (en) | Method and device for determining fault source, storage medium and electronic equipment | |
| CN108248641A (en) | A kind of urban track traffic data processing method and device | |
| CN114205214B (en) | Power communication network fault identification method, device, equipment and storage medium | |
| CN114598480B (en) | Method and system for processing machine data of network security operation platform | |
| CN114254471A (en) | Element identification method, device, equipment and storage medium of power network | |
| JP3895700B2 (en) | Communication network failure frequency calculation method, communication network failure frequency calculation device, communication network failure frequency calculation program, and recording medium recording the program | |
| CN114422324B (en) | Alarm information processing method and device, electronic equipment and storage medium | |
| EP4336883A1 (en) | Modeling method, network element data processing method and apparatus, electronic device, and medium | |
| EP3120598B1 (en) | Method and network element for implementing policies in a mobile network |
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 |