CN108959039A - A kind of method and device of virtual-machine fail prediction - Google Patents
A kind of method and device of virtual-machine fail prediction Download PDFInfo
- Publication number
- CN108959039A CN108959039A CN201810788913.2A CN201810788913A CN108959039A CN 108959039 A CN108959039 A CN 108959039A CN 201810788913 A CN201810788913 A CN 201810788913A CN 108959039 A CN108959039 A CN 108959039A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- data
- prediction model
- prediction
- virtual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/301—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is a virtual computing platform, e.g. logically partitioned systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
- G06F11/3433—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment for load management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Debugging And Monitoring (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of methods of virtual-machine fail prediction, it include: the comprehensive performance data of real-time acquisition current virtual machine, the comprehensive performance data include the external data and internal data of the virtual machine, wherein, the external data includes the load of the host where the performance data of the host where the virtual machine, the virtual machine and the load of the virtual machine, and the internal data includes the performance data of the virtual machine；Virtual machine classification belonging to the virtual machine is determined by the external data, calls the prediction model pre-established corresponding with the virtual machine classification；The internal data is inputted into the prediction model, failure predication is carried out to the virtual machine.This programme is to solve the problems, such as existing hysteresis quality during finding virtual-machine fail at present.
Description
Technical field
The present invention relates to the communication technology, espespecially a kind of method and device of virtual-machine fail prediction.
Background technique
In cloud computing era, extensive application, which is deployed on virtual machine, to be run, and the quantity of the virtual machine in data center is not
Disconnected to expand, the structure of virtual machine is increasingly complicated, once failure occurred for virtual machine, manually to the work of the investigation of failure and processing
It measures huge, operation system is caused to be unable to operate normally.
Summary of the invention
In order to solve the above-mentioned technical problems, the present invention provides a kind of method and devices of virtual-machine fail prediction, with solution
Certainly existing hysteresis quality problem during finding virtual-machine fail at present.
In order to reach the object of the invention, the present invention provides a kind of methods of virtual-machine fail prediction, comprising:
The comprehensive performance data of acquisition current virtual machine in real time, the comprehensive performance data include the outside of the virtual machine
Data and internal data, wherein the external data includes the performance data of the host where the virtual machine, the virtual machine
The load of the host at place and the load of the virtual machine, the internal data includes the performance data of the virtual machine；
Virtual machine classification belonging to the virtual machine is determined by the external data, is called and the virtual machine classification pair
The prediction model pre-established answered；
The internal data is inputted into the prediction model, failure predication is carried out to the virtual machine.
Further, the prediction model pre-establishes in the following manner:
Clustering processing is carried out to the external data of collected virtual machine in the predetermined length time, obtains multiple virtual machine classes
Not；
Each virtual machine classification is proceeded as follows respectively: the internal data to belong to the virtual machine of the virtual machine classification
As training data, the prediction model corresponding with the virtual machine classification is obtained by machine learning algorithm.
It is further, described to input the internal data after the prediction model progress failure predication, further includes:
Record prediction result, however, it is determined that precision of prediction is less than predetermined threshold, then carries out re -training to the prediction model.
It is further, described that re -training is carried out to the prediction model, comprising:
Clustering processing is carried out to the external data of currently collected all virtual machines, obtains multiple virtual machine classifications；
Each virtual machine classification is proceeded as follows respectively: the internal data to belong to the virtual machine of the virtual machine classification
As training data, by machine learning algorithm, the prediction model corresponding with the virtual machine classification is obtained.
Further, the precision of prediction is, at the appointed time in section to the virtual machine carry out the result of failure predication with
The consistent ratio of actual result.
A kind of device of virtual-machine fail prediction, comprising:
Acquisition module, for acquiring the comprehensive performance data of current virtual machine in real time, the comprehensive performance data include institute
State the external data and internal data of virtual machine, wherein the external data includes the performance of the host where the virtual machine
The load of host where data, the virtual machine and the load of the virtual machine, the internal data include the virtual machine
Performance data；
Calling module, for determining virtual machine classification belonging to the virtual machine, calling and institute by the external data
State the corresponding prediction model pre-established of virtual machine classification；
Prediction module carries out failure predication to the virtual machine for the internal data to be inputted the prediction model.
Further, described device further include:
Training module, for pre-establishing the prediction model in the following manner: to being collected in the predetermined length time
Virtual machine external data carry out clustering processing, obtain multiple virtual machine classifications；Each virtual machine classification is carried out such as respectively
Lower operation: using belong to the virtual machine classification virtual machine internal data as training data, obtained by machine learning algorithm
The prediction model corresponding with the virtual machine classification.
Further, described device further include:
Feedback module, for recording prediction result after the prediction module carries out failure predication, however, it is determined that prediction essence
Degree is less than predetermined threshold, then triggers the training module and carry out re -training to the prediction model.
Further, the training module, carrying out re -training to the prediction model includes: to currently collected institute
There is the external data of virtual machine to carry out clustering processing, obtains multiple virtual machine classifications；Each virtual machine classification is carried out such as respectively
Lower operation: using belong to the virtual machine classification virtual machine internal data as training data, obtained by machine learning algorithm
The prediction model corresponding with the virtual machine classification.
The device of a kind of virtual-machine fail prediction, comprising: memory, processor and storage on a memory and can handled
The computer program run on device, the processor perform the steps of when executing described program
The comprehensive performance data of acquisition current virtual machine in real time, the comprehensive performance data include the outside of the virtual machine
Data and internal data, wherein the external data includes the performance data of the host where the virtual machine, the virtual machine
The load of the host at place and the load of the virtual machine, the internal data includes the performance data of the virtual machine；
Virtual machine classification belonging to the virtual machine is determined by the external data, is called and the virtual machine classification pair
The prediction model pre-established answered；
The internal data is inputted into the prediction model, failure predication is carried out to the virtual machine.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right
Specifically noted structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
Attached drawing is used to provide to further understand technical solution of the present invention, and constitutes part of specification, with this
The embodiment of application technical solution for explaining the present invention together, does not constitute the limitation to technical solution of the present invention.
Fig. 1 is the flow chart for the method that a kind of virtual-machine fail of the embodiment of the present invention is predicted；
Fig. 2 is the schematic diagram for the device that a kind of virtual-machine fail of the embodiment of the present invention is predicted.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature can mutual any combination.
Step shown in the flowchart of the accompanying drawings can be in a computer system such as a set of computer executable instructions
It executes.Also, although logical order is shown in flow charts, and it in some cases, can be to be different from herein suitable
Sequence executes shown or described step.
Fig. 1 is the flow chart for the method that a kind of virtual-machine fail of the embodiment of the present invention is predicted, as shown in Figure 1, this implementation
Example method the following steps are included:
The comprehensive performance data of step 101, in real time acquisition current virtual machine, the comprehensive performance data include described virtual
The external data and internal data of machine；
In the present embodiment, the external data includes: the performance data of the host where the virtual machine, the virtual machine
The load of the host at place and the load of the virtual machine；
The internal data includes the performance data of the virtual machine.
Step 102 determines virtual machine classification belonging to the virtual machine by the external data, calls and described virtual
The corresponding prediction model pre-established of machine classification；
In the present embodiment, the prediction model can be trained in the following manner and be obtained:
Clustering processing is carried out to the external data of collected virtual machine in the predetermined length time, obtains multiple virtual machine classes
Not；
Each virtual machine classification is proceeded as follows respectively: the internal data to belong to the virtual machine of the virtual machine classification
As training data, the prediction model corresponding with the virtual machine classification is obtained by machine learning algorithm.
The internal data is inputted the prediction model by step 103, carries out failure predication to the virtual machine.
The embodiment of the present invention is predicted by operating status of the machine learning method to virtual machine, can be sent out in virtual machine
It reminds administrator to take fault-tolerant measure before raw failure, improves system reliability.
Machine learning is as a kind of intelligent algorithm, in recent years in fields such as fault detection, recognition of face, automatic Pilots
It is used widely.Machine learning is applied to the failure predication of virtual machine by the embodiment of the present invention, is solved commonsense method and is being handled
Existing hysteresis quality problem during virtual-machine fail, by being carried out to virtual machine comprehensive performance data a large amount of in data center
Modeling, establishes virtual-machine fail prediction model, predicts the operating status of virtual machine, issue early warning before virtual machine breaks down,
It reminds administrator to take fault-tolerant measure, reduces virtual-machine fail, improve operation system reliability.
The present embodiment specific implementation process may include the following two stage:
A, learn the stage:
1) the comprehensive performance data of virtual machine are acquired, including external data, (performance data of host, host are negative
Carry, the load of virtual machine) and internal data (virtual machine performance data)；
2) clustering processing is carried out to the external data of virtual machine in process of data preprocessing；
3) it by the internal data of the virtual machine in virtual machine classification same after clustering processing, inputs machine learning module and carries out
Training, obtains prediction model.
B, forecast period:
1) the comprehensive performance data of current virtual machine are acquired in real time；
2) using external data find with its similar in virtual machine classification；
3) the corresponding prediction model of the virtual machine classification is called, input internal data is predicted, according to prediction result
It chooses whether to make early warning.
It in one embodiment, can also be right after the internal data to be inputted to the prediction model and carries out failure predication
Prediction result is recorded, and when precision of prediction is less than predetermined threshold, then can carry out re -training to the prediction model, with
The parameter of prediction model is adjusted.
The precision of prediction is at the appointed time to carry out the result and actual result of failure predication in section to the virtual machine
Consistent ratio.
Re -training is carried out to the prediction model, may include:
Clustering processing is carried out to the external data of currently collected all virtual machines, obtains multiple virtual machine classifications；
Each virtual machine classification is proceeded as follows respectively: the internal data to belong to the virtual machine of the virtual machine classification
As training data, the prediction model corresponding with the virtual machine classification is obtained into algorithm by machine learning.
In the present embodiment, the data of re -training are the comprehensive performance data of the virtual machine currently acquired, data
The problem of update, data volume is bigger, can efficiently solve prediction model aging.
Fig. 2 is the schematic diagram for the device that a kind of virtual-machine fail of the embodiment of the present invention is predicted, as shown in Fig. 2, this implementation
Example device 200 include:
Acquisition module 201, for acquiring the comprehensive performance data of current virtual machine in real time, the comprehensive performance data include
The external data and internal data of the virtual machine, wherein the external data includes the property of the host where the virtual machine
The load of host where energy data, the virtual machine and the load of the virtual machine, the internal data include described virtual
The performance data of machine；
Calling module 202, for determining virtual machine classification belonging to the virtual machine by the external data, call with
The corresponding prediction model pre-established of the virtual machine classification；
It is pre- to carry out failure to the virtual machine for the internal data to be inputted the prediction model for prediction module 203
It surveys.
A kind of device of virtual-machine fail prediction of the embodiment of the present invention can issue early warning before virtual machine breaks down,
It reminds administrative staff to take fault-tolerant measure, reduces virtual-machine fail, improve operation system reliability.
In one embodiment, the fault prediction device can also include:
Training module 204, for pre-establishing the prediction model in the following manner: to being acquired in the predetermined length time
The external data of the virtual machine arrived carries out clustering processing, obtains multiple virtual machine classifications；Each virtual machine classification is carried out respectively
Following operation: using belong to the virtual machine classification virtual machine internal data as training data, obtained by machine learning algorithm
To the prediction model corresponding with the virtual machine classification.
Machine learning algorithm is as a kind of intelligent algorithm, in recent years in fault detection, recognition of face, automatic Pilot etc.
It is used widely in field.Machine learning is applied to the failure predication of virtual machine by the embodiment of the present invention, is solved commonsense method and is existed
It was found that existing hysteresis quality problem during virtual-machine fail.
In one embodiment, described device can also include:
Feedback module 205, for recording prediction result after the prediction module carries out failure predication, however, it is determined that pre-
It surveys precision and is less than predetermined threshold, then trigger the training module and re -training is carried out to the prediction model.
The feedback module 205 of the present embodiment can monitor the precision of prediction of prediction model, when precision of prediction is obviously insufficient,
Training module can be triggered, re -training is carried out to the prediction model.
In one embodiment, the training module 204, carrying out re -training to the prediction model includes: to currently
The external data of collected all virtual machines carries out clustering processing, obtains multiple virtual machine classifications；For each virtual machine classification
Proceed as follows respectively: using belong to the virtual machine classification virtual machine internal data as training data, pass through engineering
It practises algorithm and obtains the prediction model corresponding with the virtual machine classification.
In the present embodiment, the data of re -training are the comprehensive performance data of the virtual machine currently acquired, data
The problem of update, data volume is bigger, can efficiently solve prediction model aging.
The embodiment of the present invention also provides a kind of device of virtual-machine fail prediction, comprising: memory, processor and is stored in
On memory and the computer program that can run on a processor, the processor perform the steps of when executing described program
The comprehensive performance data of acquisition current virtual machine in real time, the comprehensive performance data include the outside of the virtual machine
Data and internal data, wherein the external data includes the performance data of the host where the virtual machine, the virtual machine
The load of the host at place and the load of the virtual machine, the internal data includes the performance data of the virtual machine；
Virtual machine classification belonging to the virtual machine is determined by the external data, is called and the virtual machine classification pair
The prediction model pre-established answered；
The internal data is inputted into the prediction model, failure predication is carried out to the virtual machine.
Machine learning is used for the failure predication of virtual machine by the scheme of the present embodiment, with clustering algorithm to virtual machine into
Row clustering processing establishes the failure predication that prediction model carries out virtual machine on this basis, can consider to transport outside virtual machine
Accurate Prediction is carried out to the operation conditions of virtual machine in the case where row environment and internal load, reduces the generation of failure, improves system
System reliability.
It will appreciated by the skilled person that whole or certain steps, system, dress in method disclosed hereinabove
Functional module/unit in setting may be implemented as software, firmware, hardware and its combination appropriate.In hardware embodiment,
Division between the functional module/unit referred in the above description not necessarily corresponds to the division of physical assemblies；For example, one
Physical assemblies can have multiple functions or a function or step and can be executed by several physical assemblies cooperations.Certain groups
Part or all components may be implemented as by processor, such as the software that digital signal processor or microprocessor execute, or by
It is embodied as hardware, or is implemented as integrated circuit, such as specific integrated circuit.Such software can be distributed in computer-readable
On medium, computer-readable medium may include computer storage medium (or non-transitory medium) and communication media (or temporarily
Property medium).As known to a person of ordinary skill in the art, term computer storage medium is included in for storing information (such as
Computer readable instructions, data structure, program module or other data) any method or technique in the volatibility implemented and non-
Volatibility, removable and nonremovable medium.Computer storage medium include but is not limited to RAM, ROM, EEPROM, flash memory or its
His memory technology, CD-ROM, digital versatile disc (DVD) or other optical disc storages, magnetic holder, tape, disk storage or other
Magnetic memory apparatus or any other medium that can be used for storing desired information and can be accessed by a computer.This
Outside, known to a person of ordinary skill in the art to be, communication media generally comprises computer readable instructions, data structure, program mould
Other data in the modulated data signal of block or such as carrier wave or other transmission mechanisms etc, and may include any information
Delivery media.
Claims (10)
1. a kind of method of virtual-machine fail prediction characterized by comprising
The comprehensive performance data of acquisition current virtual machine in real time, the comprehensive performance data include the external data of the virtual machine
And internal data, wherein the external data includes the performance data of the host where the virtual machine, virtual machine place
Host load and the virtual machine load, the internal data includes the performance data of the virtual machine；
Virtual machine classification belonging to the virtual machine is determined by the external data, is called corresponding with the virtual machine classification
The prediction model pre-established；
The internal data is inputted into the prediction model, failure predication is carried out to the virtual machine.
2. the method according to claim 1, wherein the prediction model is to pre-establish in the following manner
:
Clustering processing is carried out to the external data of collected virtual machine in the predetermined length time, obtains multiple virtual machine classifications；
Each virtual machine classification is proceeded as follows respectively: using belong to the virtual machine classification virtual machine internal data as
Training data obtains the prediction model corresponding with the virtual machine classification by machine learning algorithm.
3. according to the method described in claim 2, it is characterized in that, it is described by the internal data input the prediction model into
After row failure predication, further includes:
Record prediction result, however, it is determined that precision of prediction is less than predetermined threshold, then carries out re -training to the prediction model.
4. according to the method described in claim 3, it is characterized in that, described carry out re -training to the prediction model, comprising:
Clustering processing is carried out to the external data of currently collected all virtual machines, obtains multiple virtual machine classifications；
Each virtual machine classification is proceeded as follows respectively: using belong to the virtual machine classification virtual machine internal data as
Training data obtains the prediction model corresponding with the virtual machine classification by machine learning algorithm.
5. according to the method described in claim 3, it is characterized in that,
The precision of prediction is, at the appointed time consistent with actual result to the result of virtual machine progress failure predication in section
Ratio.
6. a kind of device of virtual-machine fail prediction characterized by comprising
Acquisition module, for acquiring the comprehensive performance data of current virtual machine in real time, the comprehensive performance data include the void
The external data and internal data of quasi- machine, wherein the external data include the host where the virtual machine performance data,
The load of host where the virtual machine and the load of the virtual machine, the internal data includes the performance of the virtual machine
Data；
Calling module calls and the void for determining virtual machine classification belonging to the virtual machine by the external data
The quasi- corresponding prediction model pre-established of machine classification；
Prediction module carries out failure predication to the virtual machine for the internal data to be inputted the prediction model.
7. device according to claim 6, which is characterized in that described device further include:
Training module, for pre-establishing the prediction model in the following manner: to collected void in the predetermined length time
The external data of quasi- machine carries out clustering processing, obtains multiple virtual machine classifications；Each virtual machine classification is grasped as follows respectively
Make: using belong to the virtual machine classification virtual machine internal data as training data, obtained and this by machine learning algorithm
The corresponding prediction model of virtual machine classification.
8. device according to claim 7, which is characterized in that described device further include:
Feedback module, for recording prediction result, however, it is determined that precision of prediction is small after the prediction module carries out failure predication
In predetermined threshold, then triggers the training module and re -training is carried out to the prediction model.
9. device according to claim 8, which is characterized in that
The training module, carrying out re -training to the prediction model includes: to currently collected all virtual machines
External data carries out clustering processing, obtains multiple virtual machine classifications；Each virtual machine classification is proceeded as follows respectively: to belong to
In the virtual machine classification virtual machine internal data as training data, obtained and the virtual machine class by machine learning algorithm
The not corresponding prediction model.
10. a kind of device of virtual-machine fail prediction, comprising: memory, processor and storage on a memory and can handled
The computer program run on device, which is characterized in that the processor performs the steps of when executing described program
The comprehensive performance data of acquisition current virtual machine in real time, the comprehensive performance data include the external data of the virtual machine
And internal data, wherein the external data includes the performance data of the host where the virtual machine, virtual machine place
Host load and the virtual machine load, the internal data includes the performance data of the virtual machine；
Virtual machine classification belonging to the virtual machine is determined by the external data, is called corresponding with the virtual machine classification
The prediction model pre-established；
The internal data is inputted into the prediction model, failure predication is carried out to the virtual machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810788913.2A CN108959039A (en) | 2018-07-18 | 2018-07-18 | A kind of method and device of virtual-machine fail prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810788913.2A CN108959039A (en) | 2018-07-18 | 2018-07-18 | A kind of method and device of virtual-machine fail prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108959039A true CN108959039A (en) | 2018-12-07 |
Family
ID=64497788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810788913.2A Pending CN108959039A (en) | 2018-07-18 | 2018-07-18 | A kind of method and device of virtual-machine fail prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108959039A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109634828A (en) * | 2018-12-17 | 2019-04-16 | 浪潮电子信息产业股份有限公司 | Failure prediction method, device, equipment and storage medium |
| CN110187990A (en) * | 2019-05-31 | 2019-08-30 | 东北大学 | A kind of virtual machine mixing for standby use dynamic reliability appraisal procedure based on mode shifts |
| CN113726771A (en) * | 2021-08-30 | 2021-11-30 | 上海仪电（集团）有限公司中央研究院 | Cloud platform virus searching and killing method and system based on vaccine model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104461821A (en) * | 2014-11-03 | 2015-03-25 | 浪潮(北京)电子信息产业有限公司 | Virtual machine monitoring and warning method and system |
| 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 |
| US20170012834A1 (en) * | 2013-04-11 | 2017-01-12 | Oracle International Corporation | Predictive diagnosis of sla violations in cloud services by seasonal trending and forecasting with thread intensity analytics |
| CN107247651A (en) * | 2017-05-09 | 2017-10-13 | 中国电子产品可靠性与环境试验研究所 | Cloud computing platform monitoring and pre-warning method and system |
| CN107957946A (en) * | 2017-12-01 | 2018-04-24 | 北京理工大学 | Software Defects Predict Methods based on neighborhood insertion protection algorism support vector machines |
-
2018
- 2018-07-18 CN CN201810788913.2A patent/CN108959039A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170012834A1 (en) * | 2013-04-11 | 2017-01-12 | Oracle International Corporation | Predictive diagnosis of sla violations in cloud services by seasonal trending and forecasting with thread intensity analytics |
| CN104461821A (en) * | 2014-11-03 | 2015-03-25 | 浪潮(北京)电子信息产业有限公司 | Virtual machine monitoring and warning method and system |
| 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 |
| CN107247651A (en) * | 2017-05-09 | 2017-10-13 | 中国电子产品可靠性与环境试验研究所 | Cloud computing platform monitoring and pre-warning method and system |
| CN107957946A (en) * | 2017-12-01 | 2018-04-24 | 北京理工大学 | Software Defects Predict Methods based on neighborhood insertion protection algorism support vector machines |
Non-Patent Citations (1)
| Title |
|---|
| 吴天舒等: "基于检测域划分的虚拟机异常检测算法", 《计算机应用》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109634828A (en) * | 2018-12-17 | 2019-04-16 | 浪潮电子信息产业股份有限公司 | Failure prediction method, device, equipment and storage medium |
| CN110187990A (en) * | 2019-05-31 | 2019-08-30 | 东北大学 | A kind of virtual machine mixing for standby use dynamic reliability appraisal procedure based on mode shifts |
| CN110187990B (en) * | 2019-05-31 | 2021-11-16 | 东北大学 | Virtual machine hybrid standby dynamic reliability assessment method based on mode transfer |
| CN113726771A (en) * | 2021-08-30 | 2021-11-30 | 上海仪电（集团）有限公司中央研究院 | Cloud platform virus searching and killing method and system based on vaccine model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10706308B2 (en) | Image processing for automated object identification | |
| US11294754B2 (en) | System and method for contextual event sequence analysis | |
| US20210383162A1 (en) | Data test method, electronic device and storage medium | |
| CN108959039A (en) | A kind of method and device of virtual-machine fail prediction | |
| US20200034279A1 (en) | Deep machine learning in software test automation | |
| CN111666187B (en) | Method and apparatus for detecting abnormal response time | |
| US20230060359A1 (en) | Systems and methods for managing physical connections of a connector panel | |
| US11157380B2 (en) | Device temperature impact management using machine learning techniques | |
| US20160162757A1 (en) | Multi-class object classifying method and system | |
| CN112749685B (en) | Video classification method, apparatus and medium | |
| US11711275B2 (en) | Impact predictions based on incident-related data | |
| CN111191590A (en) | Model training method and device, storage medium and electronic equipment | |
| CN112712498A (en) | Vehicle damage assessment method and device executed by mobile terminal, mobile terminal and medium | |
| CN112650885A (en) | Video classification method, device, equipment and medium | |
| CN110928889A (en) | Training model updating method, device and computer storage medium | |
| CN115113528B (en) | Operation control method, device, equipment and medium of neural network model | |
| CN114579626B (en) | Data processing method, data processing device, electronic equipment and medium | |
| KR102413588B1 (en) | Object recognition model recommendation method, system and computer program according to training data | |
| CN114882414A (en) | Abnormal video detection method, abnormal video detection device, electronic equipment, abnormal video detection medium and program product | |
| CN108520237B (en) | Risk behavior identification method | |
| CN113392867A (en) | Image identification method and device, computer equipment and storage medium | |
| US11330458B2 (en) | Systems and methods for detecting an unauthorized airborne device | |
| CN112527631A (en) | bug positioning method, system, electronic equipment and storage medium | |
| CN112379656A (en) | Processing method, device, equipment and medium for detecting abnormal data of industrial system | |
| CN110716778A (en) | Application compatibility testing method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181207 |