CN105634781A - Multi-fault data decoupling method and device - Google Patents
Multi-fault data decoupling method and device Download PDFInfo
- Publication number
- CN105634781A CN105634781A CN201410620670.3A CN201410620670A CN105634781A CN 105634781 A CN105634781 A CN 105634781A CN 201410620670 A CN201410620670 A CN 201410620670A CN 105634781 A CN105634781 A CN 105634781A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- group
- alarm
- faults
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a multi-fault data decoupling method and device. The method uses a frequent item set analysis result obtained by using a correlation analysis method in fault data decoupling to perform dereason and decorrelation, and based on fault data after dereason and decorrelation, uses a correlation coefficient matrix under the condition of single-fault data to select an affiliation fault for alarm data. The decoupling method has the characteristics of the correlation analysis method: a high accuracy rate and strong robustness, compared with a manual method in an existing network, improves work efficiency, and provides possibility for large-scale data mining analysis of fault alarm data.
Description
Technical field
The present invention relates to communication technical field, particularly relate to a kind of multiple faults data decoupler method and apparatus.
Background technology
The dysfunction that fault in communication network refers to the composition hardware device of managed network or software equipment occurs. Alarm in communication network refers to the event report that the circular that when particular event occurs, managed object sends is constituted, and is used for transmitting warning information. Between fault and fault in communication network, the relation between fault and alarm is complex.
Between fault and fault, a fault can be individually present, it is also possible to a fault causes multiple faults, for instance the fault of IUB mouth causes the call drop of user, and electric power system fault causes veneer power down to take conversation loss etc. thus community is moved back. Between fault and alarm, a fault is likely to create an alarm and is likely to the multiple alarms of generation. Article one, the appearance of alarm also indicates that and is likely to have fault to occur, rather than necessarily has fault to occur.
According to the warning information in network, the accident analysis communicating network is one of important process of maintenance management studying network. Being currently based in the research that the method for data mining communicates Analysis of Network Malfunction, the method according to warning information, single fault data message being carried out accident analysis by the various sorting algorithms of data mining has many achievements in research.
And the data gathered in real network, for the multiple faults data at many warning information of the same area and time and correspondence. Both occurring while having there is dependent failure, namely root exists because of fault and misjudgement failure simultaneously, and a situation arises simultaneously to there is also how incoherent fault.
Therefore fault root cause analysis is carried out according to existing research method according to warning information, it is necessary to consider that multiple faults is under a situation arises, the alarm data of collection and carry out data decoupler method between multiple faults:
To, in multiple faults situation, carrying out the correlation analysis between fault data;
To relevant multiple faults, to out of order because of;
Provide the ownership fault of alarm data.
Real network is taked at present network operation engineer carry out artificial data process. The method cost of labor on the one hand is high, and accuracy is limited to the level of engineer, and work efficiency cannot meet the demand of the accident analysis of big data on the other hand.
Summary of the invention
The present invention provides a kind of multiple faults data decoupler method and apparatus, in order to solve the data decoupler method inefficiency that prior art adopts, it is impossible to the problem meeting the accident analysis demand of big data.
According to one aspect of the present invention, it is provided that a kind of multiple faults data decoupler method, including:
Obtaining K group alarm data and K group fault data that the same time gathers at the same area, wherein, often group fault data is all by fault prioritization;
K group fault data is used association analysis algorithm, obtains faults frequent item collection X, and described faults frequent item collection X is converted into fault correlation matrix R between two;
Based on described fault correlation matrix R between two, the fault data group that there is multiple faults is carried out fault decorrelation and root because changing in K group fault data;
Extract with fault decorrelation and root because of each fault data group that there is how uncorrelated fault after changing corresponding respectively organize alarm data, according to the dependency between alarm and each fault, it is determined that extraction respectively organize the fault that in alarm data, each alarm belongs to.
Alternatively, in the method for the invention, described faults frequent item collection X is converted into fault correlation matrix R between two conversion principle be: be relevant for fault flag between two simultaneous in arbitrary frequent item set, for all frequent item sets are uncorrelated all without simultaneous fault flag between two; Whether the element representation in described fault correlation matrix R between two is correlated with between fault between two.
Alternatively, in the method for the invention, described based on described fault correlation matrix R between two, the fault data group that there is multiple faults in K group fault data carrying out fault decorrelation and root because of the principle changed is:
If representing that two relevant faults are concurrently present in the fault data group of multiple faults in fault correlation matrix R between two, then high priority fault is deposited in case, retains high priority fault, deletes low priority fault;
If representing in fault correlation matrix R between two, incoherent two faults are concurrently present in the fault data group of multiple faults, then two faults retain simultaneously.
Alternatively, in the method for the invention, described according to the dependency between alarm and each fault, it is determined that the fault that in each group alarm data of extraction, each alarm belongs to, specifically include:
For the often group alarm data extracted, obtain corresponding fault decorrelation and root because of each fault comprised in the fault data group after changing, obtain failure collection;
For the often group alarm data extracted, it is determined that the fault that in alarm data, each alarm is the highest with each failure dependency in corresponding failure collection is the fault that corresponding alarm belongs to.
Alternatively, in the method for the invention, also include: according to the fault data group of single fault in K group fault data, calculate the Pearson's correlation coefficient between each alarm and each fault, and represent the dependency between alarm and each fault by Pearson's correlation coefficient.
Another each side according to the present invention, it is provided that a kind of multiple faults data decoupler device, including:
Data input cell, for obtaining K group alarm data and the K group fault data that the same time gathers at the same area, wherein, often organizes fault data all by fault prioritization;
Data processing unit, for K group fault data is used association analysis algorithm, obtain faults frequent item collection X, described faults frequent item collection X is converted into fault correlation matrix R between two, and based on described fault correlation matrix R between two, the fault data group that there is multiple faults is carried out fault decorrelation and root because changing in K group fault data;
Decoupling unit, for extract with fault decorrelation and root because of each fault data group that there is how uncorrelated fault after changing corresponding respectively organize alarm data, according to the dependency between alarm and each fault, it is determined that the fault that in each group alarm data of extraction, each alarm belongs to.
Alternatively, in device of the present invention, the conversion principle that faults frequent item collection X is converted into fault correlation matrix R between two is by described data processing unit: be relevant for fault flag between two simultaneous in arbitrary frequent item set, for being uncorrelated all without simultaneous fault flag between two in all frequent item sets; Whether the element representation in described fault correlation matrix R between two is correlated with between fault between two.
Alternatively, in device of the present invention, described data processing unit is based on described fault correlation matrix R between two, and the fault data group that there is multiple faults in K group fault data carrying out fault decorrelation and root because of the principle changed is:
If representing that two relevant faults are concurrently present in the fault data group of multiple faults in fault correlation matrix R between two, then high priority fault is deposited in case, retains high priority fault, deletes low priority fault; If representing in fault correlation matrix R between two, incoherent two faults are concurrently present in the fault data group of multiple faults, then two faults retain simultaneously.
Alternatively, in device of the present invention, described fault de couple unit, specifically for the often group alarm data for extracting, obtain corresponding fault decorrelation and root because of each fault comprised in the fault data group after changing, obtain failure collection; For the often group alarm data extracted, it is determined that the fault that in alarm data, each alarm is the highest with each failure dependency in corresponding failure collection is the fault that corresponding alarm belongs to.
Alternatively, in device of the present invention, described data processing unit, it is additionally operable to according to the fault data group of single fault in K group fault data, calculate the Pearson's correlation coefficient between each alarm and each fault, to be represented the dependency between alarm and each fault by Pearson's correlation coefficient.
The present invention has the beneficial effect that:
The technical scheme that the present invention discloses, has the feature of association analysis method: accuracy rate height and strong robustness, and improves work efficiency relative to the manual method in existing network, and the large-scale data mining analysis for fault warning data provides possibility.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The flow chart of a kind of multiple faults data decoupler method that Fig. 1 provides for the embodiment of the present invention one;
The flow chart of a kind of multiple faults data decoupler method that Fig. 2 provides for the embodiment of the present invention two;
Fig. 3 is the structured flowchart of a kind of multiple faults data decoupler device provided by the invention.
Detailed description of the invention
In order to solve the data decoupler method inefficiency that prior art adopts, it is impossible to the problem meeting the accident analysis demand of big data, the present invention provides a kind of multiple faults data decoupler method and apparatus. Scheme Innovation provided by the invention is in that, the frequent item set using association analysis method is analyzed result and is used in fault data decoupling to go root because changing and decorrelation, based on going with the fault data because changing and after decorrelation, using the correlation matrix under single fault data cases is that alarm data selects ownership fault. Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments. Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
Embodiment one
The embodiment of the present invention provides a kind of multiple faults data decoupler method, as it is shown in figure 1, comprise the steps:
Step S101, obtains K group alarm data and K group fault data that the same time gathers at the same area, and wherein, often group fault data is all by fault prioritization;
Wherein, often all comprising M data in group alarm data, the corresponding alarm of each data, in order to represent whether this alarm exists;
Often all comprising N number of data in group fault data, the corresponding fault of each data, in order to represent whether this fault exists.
Step S102, uses association analysis algorithm to K group fault data, obtains faults frequent item collection X, and described faults frequent item collection X is converted into fault correlation matrix R between two;
Wherein, by the conversion principle that faults frequent item collection X is converted into fault correlation matrix R between two it is: be relevant for fault flag between two simultaneous in arbitrary frequent item set, for all frequent item sets are uncorrelated all without simultaneous fault flag between two;
Whether the element representation in described fault correlation matrix R between two is correlated with between fault between two.
Step S103, based on fault correlation matrix R between two, carries out fault decorrelation and root because changing to the fault data group that there is multiple faults in K group fault data;
Wherein, described based on described fault correlation matrix R between two, the fault data group that there is multiple faults in K group fault data carrying out fault decorrelation and root because of the principle changed is:
If representing that two relevant faults are concurrently present in the fault data group of multiple faults in fault correlation matrix R between two, then high priority fault is deposited in case, retains high priority fault, deletes low priority fault;
If representing in fault correlation matrix R between two, incoherent two faults are concurrently present in the fault data group of multiple faults, then two faults retain simultaneously.
Step S104, extract with fault decorrelation and root because of each fault data group that there is how uncorrelated fault after change corresponding respectively organize alarm data, according to the dependency between alarm and each fault, it is determined that the fault that in each group alarm data of extraction, each alarm belongs to.
Wherein, according to the dependency between alarm and each fault, it is determined that the fault that in each group alarm data of extraction, each alarm belongs to, specifically include:
For the often group alarm data extracted, obtain corresponding fault decorrelation and root because of each fault comprised in the fault data group after changing, obtain failure collection;
For the often group alarm data extracted, it is determined that the fault that in alarm data, each alarm is the highest with each failure dependency in corresponding failure collection is the fault that corresponding alarm belongs to.
Wherein, the dependency between alarm and fault, it is preferred that represented by Pearson's correlation coefficient.
The calculation of described Pearson's correlation coefficient is: according to the fault data group of single fault in K group fault data, calculate the Pearson's correlation coefficient between each alarm and each fault. The concrete calculation being directed to belongs to known technology, then this is not described further.
In sum, the multiple faults data decoupler scheme described in the present embodiment has the high feature with strong robustness of accuracy rate, and improves work efficiency relative to the manual method in existing network, and the large-scale data mining analysis for fault warning data provides possibility.
Embodiment two
Present embodiments providing a kind of multiple faults data decoupler method, the enforcement principle of the method is identical with embodiment one, and it is by openly realizing more ins and outs of the method for the invention, implements process with the clearer statement present invention. It should be noted that the present embodiment is a kind of preferred embodiment, disclosure of which is not used to uniquely limit the implementation process of the present invention.
The present embodiment provides the fault data decoupling method in a kind of communication network in multiple faults situation, as in figure 2 it is shown, comprise the steps:
Step 1: data acquisition and preprocess method:
For communication network, the priority of failure definition, and it is ranked up according to priority. The criticality of the NE quantity that fault priority can involve according to fault, hardware quantity and the KPI (KeyPerformanceIndicator, Key Performance Indicator) being affected by is estimated.
{ G will be designated as according to the fault (in order to distinguish with follow-up fault data, following stated by fault variable) after prioritization1,G2,...,GN. Such as network element NODEB, the set of fault variable can be: { NODEB power-off ..NODEB moves back clothes, and NODEB controls single board default ..IUB chain rupture ..}
ALM (in order to distinguish with follow-up alarm data, following by alerting variable statement) is designated as { E1,E2,...,EM. Such as { NODEB alarm for power-off ..RRU moves back clothes, and communication between plates flow exceedes alarming threshold, and performance threshold is crossed the border }.
Gather the K group alarm data in existing network and the K group fault data after prioritization, form following matrix:
Wherein, element e in matrixim(1��i��K, 1��m��M), records in i-th group of sampled data, alerts variable EmWhether exist: if alarm variable EmExist, then eim=1, otherwise eim=0.
Wherein, element g in matrixin(1��i��K, 1��n��N) records in i-th group of sampled data, fault variable GnWhether exist: if alarm variable GnExist, then gin=1, otherwise gin=0.
Assume in i-th group of sampled data, there is multiple faults and occur, then gi1...giNIn there is multiple nonzero term, such as gi1...giN=1,0 ... 1,0..}
Step 2: use Apriori association analysis algorithm to obtain frequent item set X in K group fault message sample. Assume that the number of frequent item set obtained is J, the frequent item set of fault message is designated as { x1,x2,...,xJ, wherein x1��xJIt is all fault variable { G1,G2,...,GNThe subset gathered. Such as xj={ NODEB power-off, NODEB moves back clothes }, wherein, j=1 ..., J.
Step 3: faults frequent item collection X is converted into fault correlation matrix R between two.
Element r in failure definition correlation matrix R between twoxyFor fault GxAnd GyCorrelation coefficient between two. rxyComputational methods as follows: if all without G in all frequent item setsxAnd GyExist, then r simultaneouslyxy=0, otherwise rxy=1. Wherein, x=1 ..., N; Y=1 ..., N
Step 4: according to fault correlation matrix R between two, carries out fault decorrelation and root because changing to the data set of multiple faults in sample.
For in i-th group of fault data, if gi1...giNIn there is multiple nonzero term, then it is assumed that be multiple faults data, then to fault data group gi1...giNCarry out decorrelation and root because changing operation, be converted to the fault data group g ' after decorrelation and Gen Yini1...g��iN. Wherein, g 'in(n=1 ..., N) computational methods as follows:
g��in=ginIf, g 'inNon-zero, then:
All fault g of current failure it are higher than in priorityi1,gi2,...gi(n-1)In scan for, if there is certain fault data gin��Non-zero, and the fault correlation coefficient r of this fault and current failuren��n=1, then make g 'in=0.
Step 5: the data set of screening single fault, and the data set according to single fault, calculates alarm variable { E1,E2,...,EMAnd fault variable { G1,G2,...,GNBetween Pearson's correlation coefficient. Definition alarm EmWith fault GnPearson's correlation coefficient be pmn��
Step 6: traversal fault decorrelation and root are because of each fault data after changing, if certain fault data { g 'i1...g��iNBe how uncorrelated fault data, then analyze the alarm data { e that how uncorrelated fault data with this be correspondingi1...eiMIn each alarm ownership fault.
For in i-th group of sampled data, if g 'i1...g��iNIn there is multiple nonzero term, then it is assumed that be how uncorrelated fault data.
If eimNon-zero (namely has alarm), then analyze eimThe method of ownership fault is as follows:
By { g 'i1...g��iNIn nonzero term corresponding fault composition failure collection, in trouble-shooting set with alarm EmThe maximum fault of Pearson's correlation coefficient is eimOwnership fault.
Embodiment three
The embodiment of the present invention provides a kind of multiple faults data decoupler device, each unit involved in this device can add the mode of software program by hardware and realize, described software program is for realizing the function of following each unit, described hardware is supported for running to provide for software program, thus forming an entity hardware unit. As it is shown on figure 3, device includes described in the present embodiment:
Data input cell 310, for obtaining K group alarm data and the K group fault data that the same time gathers at the same area, wherein, often organizes fault data all by fault prioritization;
Data processing unit 320, for K group fault data is used association analysis algorithm, obtain faults frequent item collection X, described faults frequent item collection X is converted into fault correlation matrix R between two, and based on described fault correlation matrix R between two, the fault data group that there is multiple faults is carried out fault decorrelation and root because changing in K group fault data;
Decoupling unit 330, for extract with fault decorrelation and root because of each fault data group that there is how uncorrelated fault after changing corresponding respectively organize alarm data, according to the dependency between alarm and each fault, it is determined that the fault that in each group alarm data of extraction, each alarm belongs to.
Based on said structure framework and enforcement principle, several concrete and preferred implementation under the above constitution is given below, in order to refine and to optimize the function of device of the present invention, is specifically related to following content:
In the present embodiment, the conversion principle that faults frequent item collection X is converted into fault correlation matrix R between two is by data processing unit 320: be relevant for fault flag between two simultaneous in arbitrary frequent item set, for being uncorrelated all without simultaneous fault flag between two in all frequent item sets; Whether the element representation in described fault correlation matrix R between two is correlated with between fault between two.
In the present embodiment, data processing unit 330 is based on described fault correlation matrix R between two, and the fault data group that there is multiple faults in K group fault data carrying out fault decorrelation and root because of the principle changed is:
If representing that two relevant faults are concurrently present in the fault data group of multiple faults in fault correlation matrix R between two, then high priority fault is deposited in case, retains high priority fault, deletes low priority fault; If representing in fault correlation matrix R between two, incoherent two faults are concurrently present in the fault data group of multiple faults, then two faults retain simultaneously.
In the present embodiment, fault de couple unit 330, specifically for the often group alarm data for extracting, obtain corresponding fault decorrelation and root because of each fault comprised in the fault data group after changing, obtain failure collection; For the often group alarm data extracted, it is determined that the fault that in alarm data, each alarm is the highest with each failure dependency in corresponding failure collection is the fault that corresponding alarm belongs to.
Preferably, in the present embodiment, data processing unit 320, it is additionally operable to according to the fault data group of single fault in K group fault data, calculate the Pearson's correlation coefficient between each alarm and each fault, to be represented the dependency between alarm and each fault by Pearson's correlation coefficient.
Multiple faults data decoupler scheme described in the present embodiment has the high feature with strong robustness of accuracy rate, and improves work efficiency relative to the manual method in existing network, and the large-scale data mining analysis for fault warning data provides possibility.
Obviously, the present invention can be carried out various change and modification without deviating from the spirit and scope of the present invention by those skilled in the art. So, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. a multiple faults data decoupler method, it is characterised in that including:
Obtaining K group alarm data and K group fault data that the same time gathers at the same area, wherein, often group fault data is all by fault prioritization;
K group fault data is used association analysis algorithm, obtains faults frequent item collection X, and described faults frequent item collection X is converted into fault correlation matrix R between two;
Based on described fault correlation matrix R between two, the fault data group that there is multiple faults is carried out fault decorrelation and root because changing in K group fault data;
Extract with fault decorrelation and root because of each fault data group that there is how uncorrelated fault after changing corresponding respectively organize alarm data, according to the dependency between alarm and each fault, it is determined that extraction respectively organize the fault that in alarm data, each alarm belongs to.
2. the method for claim 1, it is characterized in that, described faults frequent item collection X is converted into fault correlation matrix R between two conversion principle be: be relevant for fault flag between two simultaneous in arbitrary frequent item set, for all frequent item sets are uncorrelated all without simultaneous fault flag between two;
Whether the element representation in described fault correlation matrix R between two is correlated with between fault between two.
3. method as claimed in claim 2, it is characterised in that described based on described fault correlation matrix R between two, the fault data group that there is multiple faults in K group fault data carrying out fault decorrelation and root because of the principle of change is:
If representing that two relevant faults are concurrently present in the fault data group of multiple faults in fault correlation matrix R between two, then high priority fault is deposited in case, retains high priority fault, deletes low priority fault;
If representing in fault correlation matrix R between two, incoherent two faults are concurrently present in the fault data group of multiple faults, then two faults retain simultaneously.
4. the method for claim 1, it is characterised in that described according to the dependency between alarm and each fault, it is determined that the fault that in each group alarm data of extraction, each alarm belongs to, specifically includes:
For the often group alarm data extracted, obtain corresponding fault decorrelation and root because of each fault comprised in the fault data group after changing, obtain failure collection;
For the often group alarm data extracted, it is determined that the fault that in alarm data, each alarm is the highest with each failure dependency in corresponding failure collection is the fault that corresponding alarm belongs to.
5. the method as described in claim 1 or 4, it is characterized in that, in described method, according to the fault data group of single fault in K group fault data, calculate the Pearson's correlation coefficient between each alarm and each fault, and represent the dependency between alarm and each fault by Pearson's correlation coefficient.
6. a multiple faults data decoupler device, it is characterised in that including:
Data input cell, for obtaining K group alarm data and the K group fault data that the same time gathers at the same area, wherein, often organizes fault data all by fault prioritization;
Data processing unit, for K group fault data is used association analysis algorithm, obtain faults frequent item collection X, described faults frequent item collection X is converted into fault correlation matrix R between two, and based on described fault correlation matrix R between two, the fault data group that there is multiple faults is carried out fault decorrelation and root because changing in K group fault data;
Decoupling unit, for extract with fault decorrelation and root because of each fault data group that there is how uncorrelated fault after changing corresponding respectively organize alarm data, according to the dependency between alarm and each fault, it is determined that the fault that in each group alarm data of extraction, each alarm belongs to.
7. device as claimed in claim 6, it is characterized in that, the conversion principle that faults frequent item collection X is converted into fault correlation matrix R between two is by described data processing unit: be relevant for fault flag between two simultaneous in arbitrary frequent item set, for being uncorrelated all without simultaneous fault flag between two in all frequent item sets; Whether the element representation in described fault correlation matrix R between two is correlated with between fault between two.
8. device as claimed in claim 7, it is characterised in that described data processing unit is based on described fault correlation matrix R between two, and the fault data group that there is multiple faults in K group fault data carrying out fault decorrelation and root because of the principle of change is:
If representing that two relevant faults are concurrently present in the fault data group of multiple faults in fault correlation matrix R between two, then high priority fault is deposited in case, retains high priority fault, deletes low priority fault; If representing in fault correlation matrix R between two, incoherent two faults are concurrently present in the fault data group of multiple faults, then two faults retain simultaneously.
9. device as claimed in claim 6, it is characterized in that, described fault de couple unit, specifically for the often group alarm data for extracting, obtain corresponding fault decorrelation and root because of each fault comprised in the fault data group after changing, obtain failure collection; For the often group alarm data extracted, it is determined that the fault that in alarm data, each alarm is the highest with each failure dependency in corresponding failure collection is the fault that corresponding alarm belongs to.
10. the device as described in claim 6 or 9, it is characterized in that, described data processing unit, it is additionally operable to according to the fault data group of single fault in K group fault data, calculate the Pearson's correlation coefficient between each alarm and each fault, to be represented the dependency between alarm and each fault by Pearson's correlation coefficient.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410620670.3A CN105634781B (en) | 2014-11-05 | 2014-11-05 | Multi-fault data decoupling method and device |
| PCT/CN2015/083480 WO2016070642A1 (en) | 2014-11-05 | 2015-07-07 | Multi-fault data decoupling method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410620670.3A CN105634781B (en) | 2014-11-05 | 2014-11-05 | Multi-fault data decoupling method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105634781A true CN105634781A (en) | 2016-06-01 |
| CN105634781B CN105634781B (en) | 2020-03-13 |
Family
ID=55908518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410620670.3A Active CN105634781B (en) | 2014-11-05 | 2014-11-05 | Multi-fault data decoupling method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105634781B (en) |
| WO (1) | WO2016070642A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114693186A (en) * | 2022-05-31 | 2022-07-01 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing and processing multiple fault events of differentiated combined type transformer substation |
| CN116091045A (en) * | 2023-02-28 | 2023-05-09 | 武汉烽火技术服务有限公司 | Knowledge-graph-based communication network operation and maintenance method and operation and maintenance device |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110300011B (en) * | 2018-03-23 | 2022-07-01 | 中国移动通信集团有限公司 | Alarm root cause positioning method, device and computer readable storage medium |
| CN112003718B (en) * | 2020-09-25 | 2021-07-27 | 南京邮电大学 | Network alarm positioning method based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080162991A1 (en) * | 2007-01-02 | 2008-07-03 | International Business Machines Corporation | Systems and methods for improving serviceability of a memory system |
| CN102571407A (en) * | 2010-12-30 | 2012-07-11 | 中国移动通信集团河北有限公司 | Alarm correlation analysis method and device |
| CN103414581A (en) * | 2013-07-24 | 2013-11-27 | 佳都新太科技股份有限公司 | Equipment fault alarm, prediction and processing mechanism based on data mining |
| CN103996077A (en) * | 2014-05-22 | 2014-08-20 | 中国南方电网有限责任公司电网技术研究中心 | Electrical equipment fault prediction method based on multi-dimensional time sequence |
-
2014
- 2014-11-05 CN CN201410620670.3A patent/CN105634781B/en active Active
-
2015
- 2015-07-07 WO PCT/CN2015/083480 patent/WO2016070642A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080162991A1 (en) * | 2007-01-02 | 2008-07-03 | International Business Machines Corporation | Systems and methods for improving serviceability of a memory system |
| CN102571407A (en) * | 2010-12-30 | 2012-07-11 | 中国移动通信集团河北有限公司 | Alarm correlation analysis method and device |
| CN103414581A (en) * | 2013-07-24 | 2013-11-27 | 佳都新太科技股份有限公司 | Equipment fault alarm, prediction and processing mechanism based on data mining |
| CN103996077A (en) * | 2014-05-22 | 2014-08-20 | 中国南方电网有限责任公司电网技术研究中心 | Electrical equipment fault prediction method based on multi-dimensional time sequence |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114693186A (en) * | 2022-05-31 | 2022-07-01 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing and processing multiple fault events of differentiated combined type transformer substation |
| CN114693186B (en) * | 2022-05-31 | 2022-08-23 | 广东电网有限责任公司佛山供电局 | Method and system for analyzing and processing multiple fault events of differentiated combined type transformer substation |
| CN116091045A (en) * | 2023-02-28 | 2023-05-09 | 武汉烽火技术服务有限公司 | Knowledge-graph-based communication network operation and maintenance method and operation and maintenance device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105634781B (en) | 2020-03-13 |
| WO2016070642A1 (en) | 2016-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104410163B (en) | A kind of safety in production based on electric energy management system and power-economizing method | |
| CN209607185U (en) | A kind of electric power monitoring system network safety prevention experience system | |
| CN107204894A (en) | The monitoring method and device of network servicequality | |
| CN105634781A (en) | Multi-fault data decoupling method and device | |
| CN111147306B (en) | Fault analysis method and device of Internet of things equipment and Internet of things platform | |
| CN109118075B (en) | Electric power industrial control terminal safety monitoring method based on business logic consistency | |
| CN104468220A (en) | Early warning control platform of power telecommunication network | |
| CN101854652A (en) | Telecommunications network service performance monitoring system | |
| CN110460454B (en) | Intelligent network equipment port fault prediction method based on deep learning | |
| CN105991337A (en) | Alarm compression method and alarm compression device | |
| CN105678651A (en) | Power grid big data quality standardization-based power grid information management system and method | |
| CN110286300A (en) | A kind of multi branch electric power lines road Fault Locating Method, device, equipment and system | |
| CN105790990A (en) | Method and system for monitoring and managing power distribution and utilization communication business | |
| CN109981326B (en) | Method and device for positioning household broadband sensing fault | |
| CN103778569A (en) | Distributed generation island detection method based on meta learning | |
| CN105049253A (en) | Method for obtaining mobile network fault location and fault early warning | |
| CN104252401A (en) | Weight based device status judgment method and system thereof | |
| CN106850733A (en) | A kind of engineering construction high in the clouds monitoring management system | |
| Min et al. | Evaluation of cross-layer network vulnerability of power communication network based on multi-dimensional and multi-layer node importance analysis | |
| CN104168137A (en) | Alarm compressing method | |
| CN107483240A (en) | Power communication network service health degree analysis method based on Internet resources incidence relation | |
| CN101296122B (en) | Analytical method and device for alarm relativity | |
| CN104978837B (en) | A kind of warning system and its implementation of user oriented end electric substation | |
| CN109587145B (en) | False data intrusion detection method, device and equipment in power network | |
| CN105307185B (en) | A kind of gunz cooperation spectrum sensing method based on data purification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |