CN106201828A - A kind of virtual-machine fail detection method based on data mining and system - Google Patents
A kind of virtual-machine fail detection method based on data mining and system Download PDFInfo
- Publication number
- CN106201828A CN106201828A CN201610559999.2A CN201610559999A CN106201828A CN 106201828 A CN106201828 A CN 106201828A CN 201610559999 A CN201610559999 A CN 201610559999A CN 106201828 A CN106201828 A CN 106201828A
- Authority
- CN
- China
- Prior art keywords
- data
- virtual
- fault
- acquisition
- detection method
- 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
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2205—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45591—Monitoring or debugging support
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/815—Virtual
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention devises a kind of virtual-machine fail detection method based on data mining and system, and system includes data acquisition module, data analysis module and display and alarm module.Gathered in real time and historical data by VMware vSphere SDK and vCenter data base.And combine coarseness and fine-grained acquisition mode and obtain data and provide essential condition for data mining.In conjunction with many algorithms analyze mass data set up fault diagnosis model, by focusing solutions analysis virtual machine state and set up further fault tree judgement virtual-machine fail type.It is that abnormal node alerts to user and passes through topological diagram display systems situation to data mining results.Through test, fault type is also diagnosed by this system good judgement virtual machine health condition of energy, and performance can fully meet user's needs, and good with other software compatibilities.Meanwhile, this system is virtual-machine fail detection, it is provided that a kind of unified solution.
Description
Technical field
The invention belongs to data mining technology field, be specifically related to a kind of virtual-machine fail detection side based on data mining
Method and system.
Background technology
In cloud computing with under the background of big data development, a large amount of status files, log information that virtual resources produces will
Fault diagnosis and fault prediction for cloud platform provides effectively prediction and quick basis on location.Virtual machine is carried out failure monitoring main
It is divided into the monitoring of Single Point of Faliure and the monitoring of relevant fault.Single Point of Faliure refers in certain period, certain virtual machine occurs that CPU accounts for
Taking or store the abnormal conditions of the aspects such as resource occupation with, the network bandwidth, relevant fault refers to the behavior of certain virtual machine
Different normally due to some behavior of other virtual machines is caused, it is solely focused on the virtual machine that Deviant Behavior occurs in this case
The source of fault can not be positioned by self.
Manually directly carrying out fault diagnosis is largely dependent upon the experience of system manager, and its reliability is difficult to protect
Card.Due to without reference to, diagnostic error is difficult to be found and correct.The impact brought in order to avoid anthropic factor and error are right
Carry out, such as Bayesian network, neutral net, fuzzy logic etc. in the fault diagnosis now certain model of many uses.
On end described use fault diagnosis model can reduce the occasionality that brought by anthropic factors such as expertises with
Subjectivity, improves degree of accuracy and the reliability of diagnosis.By excavating the information such as virtual resources pond daily record, find out the most potential
Related information.Build and be suitable for the big Data Analysis Model of virtual machine in Yunnan Power Grid Company's IAAS resource pool, utilize big data skill
Fault and performance bottleneck, to virtual machine daily record being associated property analysis, are quickly detected by art, accurately provide detect out every
Layer faulty resource path or performance bottleneck track, replace randomness and experimental artificial mode in intelligentized mode.
Summary of the invention
The fault detection system purpose that the present invention realizes is reason or the abort situation of trouble-shooting generation, accelerates to repair
Journey.The complexity that the relation of fault and inefficacy is often abnormal, is difficult to directly describe from fault to the direct relation that lost efficacy.Fault diagnosis
By the fault mode of checkout and diagnosis object, extract fault signature, according to predetermined reasoning principle, assess fault message, upwards
Layer makes prompting, in order to fault restoration.System carries out detection and gathers virtual-machine data.Utilize the data characteristics square of big data
Configuration analyzes virtual machine performance barrier in active analysis resource pool, it is ensured that stablizing of operation system operation platform.Prison is concentrated with IT
Ore-controlling Role and the linkage of cloud resource management system, synchronize in time to report to the police and fault message, and under no manual intervention automatically, quickly enter
Row active analysis and representing.
The present invention is realized by lower technical scheme:
A kind of virtual-machine fail detection method based on data mining, comprises the following steps:
1) historical data in vCenter data base is derived；
2) historical data of derivation is standardized and dimension-reduction treatment；
3) pretreated historical data is divided into there is label and the data sample without label, and set up fault diagnosis mould
Type；
4) parameter is set, utilizes vShphere SDK to carry out data acquisition, and data are stored in data base；
5) read the data collected from data base, carry out pretreatment；
6) to pretreated data, utilize fault diagnosis model that data are processed；
7) analysis result is displayed by data visualization.
The step 3 of the present invention) in set up fault diagnosis model, particularly as follows: for principal character select data analysis pattern,
Fault diagnosis model set up by the data sample training grader with not tape label utilizing tape label.
The step 4 of the present invention) in data acquisition modes be a kind of coarseness acquisition strategies and fine granularity acquisition strategies
The tactful mode combined.
In the data acquisition of coarseness acquisition strategies, the time interval of the data acquisition of setting is big, data acquisition
Frequency low.
In the data acquisition of fine granularity acquisition strategies, the time interval of the data acquisition of setting is little, data acquisition
Frequency high.
The step 6 of the present invention) in fault diagnosis model diagnostic method particularly as follows:
A, employing clustering method split data into clustering under different situations；
B, set up a threshold value, when test sample with bunch distance more than threshold value time think system exception；
C, different types of fault sample is set up fault verification tree, to thinking that abnormal data use fault tree further
Carry out fault type judgement.
The step 6 of the present invention) in utilize fault diagnosis model that data are processed result be 2 kinds:
If A trouble point, this fault is marked, in order to follow-up displaying, and continues to perform downwards；
If B non-faulting point, then these data are carried out non-faulting labelling, and continues to perform downwards analysis.
The step 7 of the present invention) in analysis result is shown by data visualization, particularly as follows: the visualization of this step is first
First contain the topological structure of whole virtual pool, then according to data mining results, self-align to concrete object, and quote relevant
Fault.
A kind of virtual-machine fail detecting system based on data mining, including:
Data acquisition module
Owing to the CPU of virtual machine, internal memory, network indices can not only reflect the state that machine currently runs, also
Can help to judge the most whether main frame exception occurs, be the foundation stone of whole accident analysis and quickly location.This module is by setting up
Probe technique mode obtains CPU, internal memory and Internet resources, carries out real-time data acquisition by VMware vSphere SDK, and
By the data base of vCenter, historical data is directly derived.
Data analysis module
Data analysis module data acquisition module obtain virtual machine Various types of data and build Analysis on Fault Diagnosis mould
Type.Use big data analysis technique that the indices data gathered are analyzed, build an adaptation numerous types of data and divide
The data of different resource type and daily record can comprehensively be analyzed, from these by analysis and the algorithm model of prediction by this model
Data capture virtual-machine fail status information.This module first to collect bulk information carry out pretreatment include standardization and
Dimensionality reduction.Then select data analysis pattern for principal character, and utilize tape label and not tape label data sample training
Fault diagnosis model set up by grader.The model finally utilizing foundation carries out fault diagnosis.
Display and alarm module
The achievement that data mining is processed by display and alarm module carries out visual presentation, uses B/S framework to enter with user
Row is mutual, uses Java EE technology to develop, it is provided that the instrument operating total system to operation maintenance personnel and monitoring.
The topological structure of virtual machine in this modules exhibit system, and set alarming mechanism according to data mining results, abnormal for occurring
Situation alert in time, and provide position location.
Beneficial effects of the present invention: built and data feature analysis by automatization and intelligentized Data Analysis Model,
Quick Acquisition, analyze, find and intuitively show virtual-machine fail reason and phenomenon, improve efficiency and the accuracy of fault diagnosis,
Basic monitoring implementation method is provided for supporting and build automatization's O&M in cloud computing infrastructure resources pond.
Accompanying drawing explanation
Fig. 1 is the fault diagnosis schematic diagram of the present invention；
Fig. 2 is the flow chart of part of data acquisition of the present invention；
Fig. 3 is the data collection strategy figure of the present invention；
Fig. 4 is the model training flow chart of the present invention；
Fig. 5 is the flow chart of data analysis component of the present invention.
Detailed description of the invention
A kind of virtual-machine fail detection method based on data mining, comprises the following steps:
1) historical data in vCenter data base is derived；
2) historical data of derivation is standardized and dimension-reduction treatment；
3) pretreated historical data is divided into there is label and the data sample without label, and set up fault diagnosis mould
Type；
4) parameter is set, utilizes vShphere SDK to carry out data acquisition, and data are stored in data base；
5) read the data collected from data base, carry out pretreatment；
6) to pretreated data, utilize fault diagnosis model that data are processed；
7) analysis result is displayed by data visualization.
The step 3 of the present invention) in set up fault diagnosis model, particularly as follows: for principal character select data analysis pattern,
Fault diagnosis model set up by the data sample training grader with not tape label utilizing tape label.
The step 4 of the present invention) in data acquisition modes be a kind of coarseness acquisition strategies and fine granularity acquisition strategies
The tactful mode combined.
In the data acquisition of coarseness acquisition strategies, the time interval of the data acquisition of setting is big, data acquisition
Frequency low.
In the data acquisition of fine granularity acquisition strategies, the time interval of the data acquisition of setting is little, data acquisition
Frequency high.
The step 6 of the present invention) in fault diagnosis model diagnostic method particularly as follows:
A, employing clustering method split data into clustering under different situations；
B, set up a threshold value, when test sample with bunch distance more than threshold value time think system exception；
C, different types of fault sample is set up fault verification tree, to thinking that abnormal data use fault tree further
Carry out fault type judgement.
The step 6 of the present invention) in utilize fault diagnosis model that data are processed result be 2 kinds:
If A trouble point, this fault is marked, in order to follow-up displaying, and continues to perform downwards；
If B non-faulting point, then these data are carried out non-faulting labelling, and continues to perform downwards analysis.
The step 7 of the present invention) in analysis result is shown by data visualization, particularly as follows: the visualization of this step is first
First contain the topological structure of whole virtual pool, then according to data mining results, self-align to concrete object, and quote relevant
Fault.
A kind of virtual-machine fail detecting system based on data mining, including:
Data acquisition module: this module obtains CPU, internal memory and Internet resources by setting up probe technique mode, passes through
VMware vSphere SDK carries out real-time data acquisition, and historical data is directly derived by the data base of vCenter；
Data analysis module: data analysis module data acquisition module obtain virtual machine Various types of data and build therefore
Barrier diagnostic analysis model；And
Display and alarm module: the topological structure of virtual machine in this modules exhibit system, and set according to data mining results
Determine alarming mechanism, alert in time during for occurring abnormal, and position location is provided.
It follows that the detailed description of the invention of the present invention is described by combining explanation accompanying drawing, in order to the technology of this area
Personnel are more fully understood that the present invention.It is significant to note that, in the following description, when retouching in detail of known function and design
When stating the main contents that perhaps can desalinate the present invention, these are described in and will be left in the basket here.
Fig. 1 is the fault diagnosis schematic diagram of the present invention, by diagnostic cast at historical data training, then uses diagnosis mould
Type carries out data analysis to the data of Real-time Collection, it is judged that whether it is fault.
Fig. 2 is the detailed description of the invention flow chart of data acquisition module of the present invention, reflects the whole process of data acquisition.
Which resource is step 201: user arranges relevant parameter, such as, to gather and (calculate resource, storage resource, network
Resource) the acquisition interval time etc..
Step 202: carry out data acquisition by VMwarevSphere SDK.
Step 203: the data of collection are stored in data base.
Fig. 3 is the data collection strategy figure of the present invention.The data collection strategy of native system is that one gathers plan coarseness
The tactful mode slightly combined with fine granularity acquisition strategies.
Traditional data acquisition modes by arranging certain time interval, timing virtual machine performance index is adopted
Collection.If the time interval of the data acquisition arranged is less, data acquiring frequency is relatively big, then can seriously consume resources of virtual machine,
Affect the normal use of user.If the time interval of the data acquisition arranged is relatively big, the frequency of data acquisition is less, during unit
In the virtual-machine data that collects few, can not well reflect the practical operation situation of virtual machine.
In the data acquisition of coarseness, the time interval of the data acquisition of setting is relatively big, and data acquiring frequency is relatively
Low, under this pattern, the performance impact to virtual machine is less.
In fine-grained data acquisition, the time interval of the data acquisition of setting is less, the frequency of data acquisition
Higher, under this pattern, the performance impact to virtual machine is relatively big, but the data gathered in the unit interval are relatively big, the reality of virtual machine
The reflection of operation conditions is more comprehensively, accurately.
Fig. 4 is the model training flow chart of the present invention, reflects the process of Data Analysis Model study.
Step 401: historical data is derived from the data base of vCenter by data acquisition module.
Step 402: the bulk information collected is carried out pretreatment and includes standardization and dimensionality reduction.Utilize tape label and without
Fault diagnosis model set up by the data sample training grader of label.
Fig. 5 is the detailed description of the invention flow chart of data analysis component of the present invention, the data collected is carried out data and divides
Analysis, thus detect fault.
Step 501: the data collected are standardized and fault diagnosis is not affected by the pretreatment removing of dimensionality reduction
Nuisance parameter.The original data range of the different system metric value owing to collecting is very different, needs to mark data
Quasi-ization processes.Use indexation processing method by data nondimensionalization.Then PCA method is utilized to carry out Data Dimensionality Reduction.
Step 502: when utilizing data set up fault model and data are carried out fault diagnosis after data prediction success.
Step 503: fail result is fed back to user by data visualization.For be judged to abnormal node in time to
User alerts.
Method for diagnosing faults detailed process in step 502 is as follows: use clustering method to split data under different situations
Cluster, set up a threshold value when test sample with bunch distance more than threshold value time think system exception.To different types of event
Barrier Sample Establishing fault verification tree, to thinking that abnormal data use fault tree to carry out fault type judgement further.
Although detailed description of the invention illustrative to the present invention is described above, in order to the technology of the art
Personnel understand the present invention, it should be apparent that the invention is not restricted to the scope of concrete real-time mode.All employing equivalents or equivalence
Replacing, these changes are it is clear that all utilize the innovation and creation of present inventive concept all at the row of protection.
Claims (8)
1. a virtual-machine fail detection method based on data mining, it is characterised in that comprise the following steps:
1) historical data in vCenter data base is derived；
2) historical data of derivation is standardized and dimension-reduction treatment；
3) pretreated historical data is divided into there is label and the data sample without label, and set up fault diagnosis model；
4) parameter is set, utilizes vShphere SDK to carry out data acquisition, and data are stored in data base；
5) read the data collected from data base, carry out pretreatment；
6) to pretreated data, utilize fault diagnosis model that data are processed；
7) analysis result is displayed by data visualization.
A kind of virtual-machine fail detection method based on data mining the most according to claim 1, it is characterised in that step
3) fault diagnosis model is set up in, particularly as follows: select data analysis pattern for principal character, utilize tape label and without mark
Fault diagnosis model set up by the data sample training grader signed.
A kind of virtual-machine fail detection method based on data mining the most according to claim 1, it is characterised in that step
4) the tactful mode that the data acquisition modes in is a kind of coarseness acquisition strategies and fine granularity acquisition strategies combines.
A kind of virtual-machine fail detection method based on data mining the most according to claim 3, it is characterised in that
1) in the data acquisition of coarseness acquisition strategies, the time interval of the data acquisition of setting is big, data acquisition
Frequency is low；
2) in the data acquisition of fine granularity acquisition strategies, the time interval of the data acquisition of setting is little, data acquisition
Frequency is high.
A kind of virtual-machine fail detection method based on data mining the most according to claim 1, it is characterised in that step
6) diagnostic method of the fault diagnosis model in particularly as follows:
A, employing clustering method split data into clustering under different situations；
B, set up a threshold value, when test sample with bunch distance more than threshold value time think system exception；
C, different types of fault sample is set up fault verification tree, to thinking that abnormal data use fault tree to carry out further
Fault type judges.
A kind of virtual-machine fail detection method based on data mining the most according to claim 1, it is characterised in that step
6) result utilizing fault diagnosis model to process data in is 2 kinds:
If A trouble point, this fault is marked, in order to follow-up displaying, and continues to perform downwards；
If B non-faulting point, then these data are carried out non-faulting labelling, and continues to perform downwards analysis.
A kind of virtual-machine fail detection method based on data mining the most according to claim 1, it is characterised in that step
7) in, analysis result is shown by data visualization, particularly as follows: first the visualization of this step contains whole virtual pool
Topological structure, then according to data mining results, self-align to concrete object, and quote dependent failure.
8. a virtual-machine fail detecting system based on data mining, it is characterised in that including:
Data acquisition module: this module obtains CPU, internal memory and Internet resources by setting up probe technique mode, passes through VMware
VSphere SDK carries out real-time data acquisition, and historical data is directly derived by the data base of vCenter；
Data analysis module: virtual machine Various types of data that data analysis module data acquisition module obtains also builds fault and examines
Disconnected analysis model；And show and alarm module: the topological structure of virtual machine in this modules exhibit system, and according to data mining
Result sets alarming mechanism, alerts in time, and provide position location during for occurring abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610559999.2A CN106201828A (en) | 2016-07-18 | 2016-07-18 | A kind of virtual-machine fail detection method based on data mining and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610559999.2A CN106201828A (en) | 2016-07-18 | 2016-07-18 | A kind of virtual-machine fail detection method based on data mining and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106201828A true CN106201828A (en) | 2016-12-07 |
Family
ID=57474801
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610559999.2A Pending CN106201828A (en) | 2016-07-18 | 2016-07-18 | A kind of virtual-machine fail detection method based on data mining and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106201828A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106774087A (en) * | 2017-01-12 | 2017-05-31 | 深圳万发创新进出口贸易有限公司 | Energy management control system for electronic information system machine rooms based on cloud computing |
| CN107357730A (en) * | 2017-07-17 | 2017-11-17 | 郑州云海信息技术有限公司 | A kind of system fault diagnosis restorative procedure and device |
| CN107943665A (en) * | 2017-12-14 | 2018-04-20 | 中盈优创资讯科技有限公司 | A kind of system host monitoring method and device |
| CN108206747A (en) * | 2016-12-16 | 2018-06-26 | 中国移动通信集团山西有限公司 | Method for generating alarm and system |
| CN108345523A (en) * | 2017-01-22 | 2018-07-31 | 中兴通讯股份有限公司 | A kind of lookup method and device of warping apparatus |
| CN109325071A (en) * | 2018-10-31 | 2019-02-12 | 福建南威软件有限公司 | A method of reference template realizes fast large according to mining analysis |
| CN109413149A (en) * | 2018-09-19 | 2019-03-01 | 上海哔哩哔哩科技有限公司 | Information distribution control method, system, server and computer readable storage medium |
| CN109471698A (en) * | 2018-10-19 | 2019-03-15 | 中国电子科技集团公司第二十八研究所 | System and method for detecting abnormal behavior of virtual machine in cloud environment |
| CN109905262A (en) * | 2017-12-11 | 2019-06-18 | 上海逸云信息科技发展有限公司 | A kind of monitoring system and monitoring method of CDN device service |
| CN110222452A (en) * | 2019-06-14 | 2019-09-10 | 国网上海市电力公司 | Oil-immersed transformer failure based on big data association mining deduces visualization system |
| CN110333962A (en) * | 2019-05-16 | 2019-10-15 | 上海精密计量测试研究所 | A kind of electronic component fault diagnosis model based on data analysis prediction |
| CN111382029A (en) * | 2020-03-05 | 2020-07-07 | 清华大学 | Mainboard abnormity diagnosis method and device based on PCA and multidimensional monitoring data |
| CN113094235A (en) * | 2021-04-14 | 2021-07-09 | 天津大学 | Tail delay abnormal cloud auditing system and method |
| CN114442543A (en) * | 2021-10-29 | 2022-05-06 | 南京河海南自水电自动化有限公司 | Computer monitoring method suitable for early warning of hydropower station fault |
| CN114630352A (en) * | 2020-12-11 | 2022-06-14 | 中国移动通信集团湖南有限公司 | Fault monitoring method and device of access equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005207644A (en) * | 2004-01-21 | 2005-08-04 | Mitsubishi Electric Corp | Apparatus diagnosing device, refrigeration cycle device, fluid circuit diagnosing method, apparatus monitoring system and refrigeration cycle monitoring system |
| CN101742540A (en) * | 2010-02-05 | 2010-06-16 | 华为技术有限公司 | Method and device for online self-diagnosis |
| CN104363106A (en) * | 2014-10-09 | 2015-02-18 | 国网辽宁省电力有限公司信息通信分公司 | Electric power information communication fault early warning analysis method based on big-data technique |
-
2016
- 2016-07-18 CN CN201610559999.2A patent/CN106201828A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005207644A (en) * | 2004-01-21 | 2005-08-04 | Mitsubishi Electric Corp | Apparatus diagnosing device, refrigeration cycle device, fluid circuit diagnosing method, apparatus monitoring system and refrigeration cycle monitoring system |
| CN101742540A (en) * | 2010-02-05 | 2010-06-16 | 华为技术有限公司 | Method and device for online self-diagnosis |
| CN104363106A (en) * | 2014-10-09 | 2015-02-18 | 国网辽宁省电力有限公司信息通信分公司 | Electric power information communication fault early warning analysis method based on big-data technique |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108206747A (en) * | 2016-12-16 | 2018-06-26 | 中国移动通信集团山西有限公司 | Method for generating alarm and system |
| CN108206747B (en) * | 2016-12-16 | 2021-09-03 | 中国移动通信集团山西有限公司 | Alarm generation method and system |
| CN106774087A (en) * | 2017-01-12 | 2017-05-31 | 深圳万发创新进出口贸易有限公司 | Energy management control system for electronic information system machine rooms based on cloud computing |
| CN106774087B (en) * | 2017-01-12 | 2019-07-16 | 河北辛大洲环保科技有限公司 | Energy management control system for electronic information system machine rooms based on cloud computing |
| CN108345523A (en) * | 2017-01-22 | 2018-07-31 | 中兴通讯股份有限公司 | A kind of lookup method and device of warping apparatus |
| CN107357730A (en) * | 2017-07-17 | 2017-11-17 | 郑州云海信息技术有限公司 | A kind of system fault diagnosis restorative procedure and device |
| CN109905262A (en) * | 2017-12-11 | 2019-06-18 | 上海逸云信息科技发展有限公司 | A kind of monitoring system and monitoring method of CDN device service |
| CN107943665A (en) * | 2017-12-14 | 2018-04-20 | 中盈优创资讯科技有限公司 | A kind of system host monitoring method and device |
| CN109413149A (en) * | 2018-09-19 | 2019-03-01 | 上海哔哩哔哩科技有限公司 | Information distribution control method, system, server and computer readable storage medium |
| CN109471698B (en) * | 2018-10-19 | 2021-03-05 | 中电莱斯信息系统有限公司 | System and method for detecting abnormal behavior of virtual machine in cloud environment |
| CN109471698A (en) * | 2018-10-19 | 2019-03-15 | 中国电子科技集团公司第二十八研究所 | System and method for detecting abnormal behavior of virtual machine in cloud environment |
| CN109325071A (en) * | 2018-10-31 | 2019-02-12 | 福建南威软件有限公司 | A method of reference template realizes fast large according to mining analysis |
| CN110333962A (en) * | 2019-05-16 | 2019-10-15 | 上海精密计量测试研究所 | A kind of electronic component fault diagnosis model based on data analysis prediction |
| CN110333962B (en) * | 2019-05-16 | 2023-10-13 | 上海精密计量测试研究所 | Electronic component fault diagnosis model based on data analysis and prediction |
| CN110222452A (en) * | 2019-06-14 | 2019-09-10 | 国网上海市电力公司 | Oil-immersed transformer failure based on big data association mining deduces visualization system |
| CN111382029A (en) * | 2020-03-05 | 2020-07-07 | 清华大学 | Mainboard abnormity diagnosis method and device based on PCA and multidimensional monitoring data |
| CN111382029B (en) * | 2020-03-05 | 2021-09-03 | 清华大学 | Mainboard abnormity diagnosis method and device based on PCA and multidimensional monitoring data |
| CN114630352A (en) * | 2020-12-11 | 2022-06-14 | 中国移动通信集团湖南有限公司 | Fault monitoring method and device of access equipment |
| CN114630352B (en) * | 2020-12-11 | 2023-08-15 | 中国移动通信集团湖南有限公司 | Fault monitoring method and device for access equipment |
| CN113094235A (en) * | 2021-04-14 | 2021-07-09 | 天津大学 | Tail delay abnormal cloud auditing system and method |
| CN113094235B (en) * | 2021-04-14 | 2023-03-10 | 天津大学 | Tail delay abnormal cloud auditing system and method |
| CN114442543A (en) * | 2021-10-29 | 2022-05-06 | 南京河海南自水电自动化有限公司 | Computer monitoring method suitable for early warning of hydropower station fault |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106201828A (en) | A kind of virtual-machine fail detection method based on data mining and system | |
| US9672085B2 (en) | Adaptive fault diagnosis | |
| CN109343987A (en) | IT system fault diagnosis and restorative procedure, device, equipment, storage medium | |
| CN115809183A (en) | Method for discovering and disposing information-creating terminal fault based on knowledge graph | |
| CN105337765A (en) | Distributed hadoop cluster fault automatic diagnosis and restoration system | |
| CN109800127A (en) | A kind of system fault diagnosis intelligence O&M method and system based on machine learning | |
| CN105474577B (en) | System and method for monitoring system performance and availability | |
| CN104796273A (en) | Method and device for diagnosing root of network faults | |
| CN111353911A (en) | Power equipment operation and maintenance method, system, equipment and storage medium | |
| CN101848477A (en) | Method and system for diagnosing fault | |
| CN109710501B (en) | Method and system for detecting data transmission stability of server | |
| CN105045689A (en) | Method for monitoring and alarming hard disks by using RAID card batch detection | |
| CN110162445A (en) | The host health assessment method and device of Intrusion Detection based on host log and performance indicator | |
| CN113946499A (en) | Micro-service link tracking and performance analysis method, system, equipment and application | |
| CN104574219A (en) | System and method for monitoring and early warning of operation conditions of power grid service information system | |
| CN103675357B (en) | The method of anemoscope fault pre-alarming and system | |
| CN113157521B (en) | Monitoring method and monitoring system for block chain full life cycle | |
| CN107121616B (en) | Method and device for fault positioning of intelligent instrument | |
| CN117220917A (en) | Network real-time monitoring method based on cloud computing | |
| CN112363432A (en) | Monitoring system and monitoring method for hydropower station auxiliary equipment | |
| CN117313845A (en) | Power grid fault detection auxiliary method and system based on knowledge graph | |
| Soualhia et al. | Automated traces-based anomaly detection and root cause analysis in cloud platforms | |
| CN116881958A (en) | Power grid big data safety protection method, system, electronic equipment and storage medium | |
| ZHANG et al. | Approach to anomaly detection in microservice system with multi-source data streams | |
| CN114710505A (en) | Method and system for realizing ecological safety supervision of digital RMB (national currency) based on block chain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161207 |
|
| WD01 | Invention patent application deemed withdrawn after publication |