CN105634781B - Multi-fault data decoupling method and device - Google Patents
Multi-fault data decoupling method and device Download PDFInfo
- Publication number
- CN105634781B CN105634781B CN201410620670.3A CN201410620670A CN105634781B CN 105634781 B CN105634781 B CN 105634781B CN 201410620670 A CN201410620670 A CN 201410620670A CN 105634781 B CN105634781 B CN 105634781B
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- alarm
- faults
- group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—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 a multi-fault data decoupling device. The decoupling method has the characteristics of a correlation analysis method: the method has high accuracy and strong robustness, improves the working efficiency compared with a manual method in the existing network, and provides possibility for large-scale data mining analysis of fault alarm data.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a multi-fault data decoupling method and device.
Background
A failure in a communication network refers to a functional abnormality occurring in a hardware device or a software device constituting a managed network. An alarm in a communication network refers to an event report consisting of a notification issued by a managed object when a specific event occurs, for conveying alarm information. The relationship between faults and alarms in a communication network is complex.
Between the failures, one failure may exist independently, or one failure may cause multiple failures, for example, a failure of the IUB port causes a call drop of a user, a failure of the power system causes a single board to power down, so that a user in a cell returns to service and the like. Between a failure and an alarm, one failure may generate one alarm or multiple alarms may be generated. The occurrence of an alarm also indicates that a fault may occur, rather than necessarily.
Performing fault analysis of a communication network based on alarm information in the network is one of the important tasks in the research of maintenance and management of the network. In the current research of communication network fault analysis based on a data mining method, a method for carrying out fault analysis on single fault data information according to alarm information through various classification algorithms of data mining has a lot of research results.
The data collected in the actual network is the multi-alarm information and the corresponding multi-fault data in the same area and time. There are both simultaneous occurrences of correlated faults, i.e., root cause faults and dependent faults, and multiple simultaneous occurrences of uncorrelated faults.
Therefore, fault root cause analysis is carried out according to alarm information by the existing research method, and under the condition that multiple faults occur, the collected alarm data and the data decoupling method between the multiple faults need to be considered:
analyzing the correlation between fault data under the condition of multiple faults;
giving the root cause of the fault to the related multiple faults;
and giving the attribution fault of the alarm data.
In an actual network, a network maintenance engineer is currently used for manual data processing. On one hand, the method is high in labor cost, the accuracy is limited by the level of engineers, and on the other hand, the working efficiency cannot meet the requirement of fault analysis of big data.
Disclosure of Invention
The invention provides a multi-fault data decoupling method and device, which are used for solving the problems that the data decoupling method adopted in the prior art is low in efficiency and cannot meet the fault analysis requirement of big data.
According to an aspect of the present invention, a multi-fault data decoupling method is provided, including:
acquiring K groups of alarm data and K groups of fault data acquired in the same area at the same time, wherein each group of fault data is sorted according to the fault priority;
using a correlation analysis algorithm for K groups of fault data to obtain a fault frequent item set X, and converting the fault frequent item set X into a fault pairwise correlation matrix R;
based on the fault pairwise correlation matrix R, fault decorrelation and root ization are carried out on fault data groups with multiple faults in the K groups of fault data;
and extracting each group of alarm data corresponding to each fault data group with a plurality of irrelevant faults after the fault decorrelation and the root cause are carried out, and determining the fault to which each alarm belongs in each extracted group of alarm data according to the relevance between the alarm and each fault.
Optionally, in the method of the present invention, the principle of converting the frequent fault item set X into the pairwise fault correlation matrix R is as follows: the method comprises the following steps of marking two faults which exist in any frequent item set at the same time as related, and marking two faults which do not exist in all frequent item sets at the same time as unrelated; and elements in the fault pairwise correlation matrix R indicate whether the faults are correlated or not.
Optionally, in the method of the present invention, the principle of performing fault decorrelation and radicalization on the fault data group with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R is as follows:
if two faults which are related in the pairwise correlation matrix R indicate that the two related faults exist in the multi-fault data group at the same time, the high-priority fault is reserved and the low-priority fault is deleted under the condition that the high-priority fault exists;
if two irrelevant faults are simultaneously present in the fault data group with multiple faults in the fault pairwise correlation matrix R, the two faults are simultaneously reserved.
Optionally, in the method of the present invention, the determining, according to the correlation between the alarm and each fault, a fault to which each alarm in each extracted set of alarm data belongs specifically includes:
for each extracted group of alarm data, acquiring each fault contained in the fault data group subjected to decorrelation and root treatment of the fault corresponding to the extracted group of alarm data to obtain a fault set;
and for each group of extracted alarm data, determining that the fault with the highest correlation between each alarm in the alarm data and each fault in the corresponding fault set is the fault to which the corresponding alarm belongs.
Optionally, the method of the present invention further includes: and calculating a Pearson correlation coefficient between each alarm and each fault according to the fault data group of the single fault in the K groups of fault data, and expressing the correlation between the alarms and each fault through the Pearson correlation coefficient.
In accordance with another aspect of the present invention, there is provided a multi-fault data decoupling apparatus, comprising:
the data input unit is used for acquiring K groups of alarm data and K groups of fault data which are acquired in the same area at the same time, wherein each group of fault data is sorted according to the fault priority;
the data processing unit is used for obtaining a fault frequent item set X by using a correlation analysis algorithm for K groups of fault data, converting the fault frequent item set X into a fault pairwise correlation matrix R, and performing fault decorrelation and root formation on fault data groups with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R;
and the decoupling unit is used for extracting each group of alarm data corresponding to each fault data group with a plurality of irrelevant faults after the fault decorrelation and the root cause are carried out, and determining the fault to which each alarm belongs in each extracted group of alarm data according to the correlation between the alarm and each fault.
Optionally, in the apparatus of the present invention, a principle of converting the frequent fault item set X into the pairwise fault correlation matrix R by the data processing unit is as follows: the method comprises the following steps of marking two faults which exist in any frequent item set at the same time as related, and marking two faults which do not exist in all frequent item sets at the same time as unrelated; and elements in the fault pairwise correlation matrix R indicate whether the faults are correlated or not.
Optionally, in the apparatus of the present invention, the principle that the data processing unit performs fault decorrelation and radicalization on the fault data group with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R is as follows:
if two faults which are related in the pairwise correlation matrix R indicate that the two related faults exist in the multi-fault data group at the same time, the high-priority fault is reserved and the low-priority fault is deleted under the condition that the high-priority fault exists; if two irrelevant faults are simultaneously present in the fault data group with multiple faults in the fault pairwise correlation matrix R, the two faults are simultaneously reserved.
Optionally, in the apparatus of the present invention, the fault decoupling unit is specifically configured to, for each extracted set of alarm data, obtain each fault included in the fault data set after decorrelation and root processing of the fault corresponding to the extracted set of alarm data, and obtain a fault set; and for each group of extracted alarm data, determining that the fault with the highest correlation between each alarm in the alarm data and each fault in the corresponding fault set is the fault to which the corresponding alarm belongs.
Optionally, in the apparatus of the present invention, the data processing unit is further configured to calculate a pearson correlation coefficient between each alarm and each fault according to the fault data group of a single fault in the K sets of fault data, so as to represent a correlation between the alarm and each fault by the pearson correlation coefficient.
The invention has the following beneficial effects:
the technical scheme disclosed by the invention has the characteristics of a correlation analysis method: the method has high accuracy and strong robustness, improves the working efficiency compared with a manual method in the existing network, and provides possibility for large-scale data mining analysis of fault alarm data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a multi-fault data decoupling method according to an embodiment of the present invention;
fig. 2 is a flowchart of a multi-fault data decoupling method according to a second embodiment of the present invention;
fig. 3 is a structural block diagram of a multi-fault data decoupling device provided in the present invention.
Detailed Description
The invention provides a multi-fault data decoupling method and device, and aims to solve the problems that a data decoupling method adopted in the prior art is low in efficiency and cannot meet the fault analysis requirement of big data. The scheme provided by the invention is innovative in that frequent item set analysis results using a correlation analysis method are used for de-rooting and de-correlating in fault data decoupling, and based on fault data after de-rooting and de-correlating, a correlation coefficient matrix under the condition of single fault data is used for selecting an attribution fault for alarm data. The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
The embodiment of the invention provides a multi-fault data decoupling method, which comprises the following steps as shown in figure 1:
step S101, acquiring K groups of alarm data and K groups of fault data acquired in the same area at the same time, wherein each group of fault data is sorted according to fault priority;
each group of alarm data comprises M data, and each data corresponds to an alarm and is used for indicating whether the alarm exists or not;
each group of fault data comprises N data, and each data corresponds to a fault and is used for indicating whether the fault exists or not.
Step S102, obtaining a fault frequent item set X by using a correlation analysis algorithm for K groups of fault data, and converting the fault frequent item set X into a fault pairwise correlation matrix R;
the conversion principle of converting the fault frequent item set X into the fault pairwise correlation matrix R is as follows: the method comprises the following steps of marking two faults which exist in any frequent item set at the same time as related, and marking two faults which do not exist in all frequent item sets at the same time as unrelated;
and elements in the fault pairwise correlation matrix R indicate whether the faults are correlated or not.
Step S103, fault decorrelation and root ization are carried out on fault data groups with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R;
the principle of performing fault decorrelation and root ization on the fault data group with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R is as follows:
if two faults which are related in the pairwise correlation matrix R indicate that the two related faults exist in the multi-fault data group at the same time, the high-priority fault is reserved and the low-priority fault is deleted under the condition that the high-priority fault exists;
if two irrelevant faults are simultaneously present in the fault data group with multiple faults in the fault pairwise correlation matrix R, the two faults are simultaneously reserved.
And step S104, extracting each group of alarm data corresponding to each fault data group with a plurality of irrelevant faults after the fault decorrelation and the root cause are carried out, and determining the fault to which each alarm belongs in each extracted group of alarm data according to the relevance between the alarm and each fault.
Wherein, according to the correlation between the alarm and each fault, determining the fault to which each alarm belongs in each group of extracted alarm data, specifically comprising:
for each extracted group of alarm data, acquiring each fault contained in the fault data group subjected to decorrelation and root treatment of the fault corresponding to the extracted group of alarm data to obtain a fault set;
and for each group of extracted alarm data, determining that the fault with the highest correlation between each alarm in the alarm data and each fault in the corresponding fault set is the fault to which the corresponding alarm belongs.
Wherein the correlation between the alarm and the fault is preferably represented by a pearson correlation coefficient.
The calculation mode of the Pearson correlation coefficient is as follows: and calculating the Pearson correlation coefficient between each alarm and each fault according to the fault data group of the single fault in the K groups of fault data. The specific calculation methods involved therein are well known in the art and will not be described in detail.
In conclusion, the multi-fault data decoupling scheme has the characteristics of high accuracy and strong robustness, improves the working efficiency compared with a manual method in the existing network, and provides possibility for large-scale data mining analysis of fault alarm data.
Example two
The embodiment provides a multi-fault data decoupling method, the implementation principle of the method is the same as that of the embodiment one, and the specific implementation process of the invention is more clearly expressed by disclosing more technical details for implementing the method of the invention. It should be noted that this embodiment is a preferred embodiment, and the disclosure is not intended to limit the implementation of the present invention.
The embodiment provides a fault data decoupling method under the condition of multiple faults in a communication network, as shown in fig. 2, which includes the following steps:
step 1: the data acquisition and preprocessing method comprises the following steps:
for a communication network, the priority of the failures is defined and sorted according to priority. The fault priority can be evaluated according to the number of network elements affected by the fault, the number of hardware, and the Key degree of the KPI (Key Performance Indicator) affected by the hardware.
The failures sorted by priority (expressed by failure variables in the following description for the purpose of distinguishing them from the subsequent failure data) are denoted as { G }1,G2,...,GN}. For example, taking the network element NODEB as an example, the set of fault variables may be: { NODEB outage.. NODEB quits service, NODEB controls single board failure.. IUB link failure. }
The system alarm (for distinction from subsequent alarm data, expressed by alarm variables below) is denoted as { E }1,E2,...,EM}. For example, { NODEB power-off alarm,. RRU quits service, inter-board communication traffic exceeds an alarm threshold, performance threshold crosses }.
Collecting K groups of alarm data and K groups of fault data after priority sorting in the existing network, and forming the following matrixes:
wherein, the element e in the matrixim(1<＝i<＝K,1<＝m<M), recording an alarm variable E in the ith group of sampling datamWhether or not there is: if the alarm variable EmExist, then eim1, otherwise eim＝0。
Wherein, the element g in the matrixin(1<＝i<＝K,1<＝n<N) recording fault variable G in ith group of sampling datanWhether or not there is: if the alarm variable GnIf present, then gin1, otherwise gin＝0。
Assuming that there are multiple failures in the ith set of sampled data, gi1...giNThere are a number of non-zero terms such as: gi1...giN＝{1,0,…1,0..}
Step 2: and (4) acquiring a frequent item set X by using an Apriori correlation analysis algorithm on the K groups of fault information samples. Assuming that the number of the acquired frequent item sets is J, the frequent item set of the fault information is recorded as { x1,x2,...,xJIn which x1～xJAre all fault variables { G1,G2,...,GNA subset of the set. E.g. xjNo deb is powered off, no deb is taken back, where J is 1.
And step 3: and converting the fault frequent item set X into a fault pairwise correlation matrix R.
Defining element R in fault pairwise correlation matrix RxyTo a fault GxAnd GyTwo correlation coefficients. r isxyThe calculation method of (2) is as follows: if all frequent item sets do not have GxAnd GyExist simultaneously, then rxy0, otherwise rxy1. Wherein, x is 1.., N; 1, N
And 4, step 4: and according to the pairwise correlation matrix R of the faults, performing fault decorrelation and root factorization on the data group with multiple faults in the sample.
For the ith group of fault data, if gi1...giNIf there are multiple non-zero entries in the data, then it is considered as multiple fault data, then for the fault data set gi1...giNPerforming decorrelation and rootage operation, and converting into a post-decorrelation and rootage fault data group g'i1...g′iN. Wherein, g'inThe calculation method of (N ═ 1.., N) is as follows:
g′in＝ginif g'inIf not, then:
all faults g having higher priority than the current faulti1,gi2,...gi(n-1)If there is some fault data g, the search is carried outin′Is non-zero, and the fault correlation coefficient r of the fault and the current faultn′nLet g '1'in＝0。
And 5: screening the data group of the single fault, and calculating an alarm variable { E) according to the data group of the single fault1,E2,...,EMAnd fault variable { G }1,G2,...,GNPearson correlation coefficient between. Define alarms EmAnd fault GnHas a Pearson correlation coefficient of pmn。
Step 6: traversing each fault data after fault decorrelation and root cause, and if some fault data { g'i1...g′iNIf the data is irrelevant fault data, analyzing alarm data e corresponding to the irrelevant fault datai1...eiMAnd each alarm in the network belongs to the fault.
For the ith group of sampled data, if g'i1...g′iNIf there are multiple non-zero entries, it is considered as multiple irrelevant fault data.
If eimNon-zero (i.e. alarm), then analyze eimThe method of attributing a fault is as follows:
will { g'i1...g′iNThe faults corresponding to the non-zero items in the set constitute a fault set, and the fault set and the alarm E are searchedmThe fault with the largest Pearson correlation coefficient is eimThe home failure of (2).
EXAMPLE III
The embodiment of the invention provides a multi-fault data decoupling device, wherein each unit related in the device can be realized by a mode of adding a software program to hardware, the software program is used for realizing the functions of the following units, and the hardware is used for providing support for the operation of the software program, so that an entity hardware device is formed. As shown in fig. 3, the apparatus of the present embodiment includes:
the data input unit 310 is configured to acquire K sets of alarm data and K sets of fault data acquired in the same area at the same time, where each set of fault data is sorted according to fault priority;
the data processing unit 320 is configured to use a correlation analysis algorithm for K groups of fault data to obtain a fault frequent item set X, convert the fault frequent item set X into a fault pairwise correlation matrix R, and perform fault decorrelation and root processing on fault data groups with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R;
the decoupling unit 330 is configured to extract each set of alarm data corresponding to each fault data set having multiple irrelevant faults after the fault decorrelation and the root cause are performed, and determine a fault to which each alarm in each extracted set of alarm data belongs according to a correlation between the alarm and each fault.
Based on the above structural framework and implementation principles, several specific and preferred embodiments under the above structure are given below to refine and optimize the function of the device of the present invention, specifically referring to the following:
in this embodiment, the principle of converting the fault frequent item set X into the fault pairwise correlation matrix R by the data processing unit 320 is as follows: the method comprises the following steps of marking two faults which exist in any frequent item set at the same time as related, and marking two faults which do not exist in all frequent item sets at the same time as unrelated; and elements in the fault pairwise correlation matrix R indicate whether the faults are correlated or not.
In this embodiment, the principle that the data processing unit 330 performs fault decorrelation and radicalization on the fault data group with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R is as follows:
if two faults which are related in the pairwise correlation matrix R indicate that the two related faults exist in the multi-fault data group at the same time, the high-priority fault is reserved and the low-priority fault is deleted under the condition that the high-priority fault exists; if two irrelevant faults are simultaneously present in the fault data group with multiple faults in the fault pairwise correlation matrix R, the two faults are simultaneously reserved.
In this embodiment, the fault decoupling unit 330 is specifically configured to, for each extracted group of alarm data, obtain each fault included in the fault data group after decorrelation and root of the fault corresponding to the extracted group of alarm data, and obtain a fault set; and for each group of extracted alarm data, determining that the fault with the highest correlation between each alarm in the alarm data and each fault in the corresponding fault set is the fault to which the corresponding alarm belongs.
Preferably, in this embodiment, the data processing unit 320 is further configured to calculate a pearson correlation coefficient between each alarm and each fault according to the fault data group of a single fault in the K sets of fault data, so as to represent the correlation between the alarm and each fault by the pearson correlation coefficient.
The multi-fault data decoupling scheme has the characteristics of high accuracy and strong robustness, improves the working efficiency compared with a manual method in the existing network, and provides possibility for large-scale data mining analysis of fault alarm data.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A multi-fault data decoupling method, comprising:
acquiring K groups of alarm data and K groups of fault data acquired in the same area at the same time, wherein each group of fault data is sorted according to the fault priority;
using a correlation analysis algorithm for K groups of fault data to obtain a fault frequent item set X, and converting the fault frequent item set X into a fault pairwise correlation matrix R;
based on the fault pairwise correlation matrix R, fault decorrelation and root ization are carried out on fault data groups with multiple faults in the K groups of fault data;
extracting each group of alarm data corresponding to each fault data group with a plurality of irrelevant faults after the fault decorrelation and the root cause are carried out, and determining the fault to which each alarm belongs in each extracted group of alarm data according to the relevance between the alarm and each fault;
the conversion principle of converting the fault frequent item set X into the fault pairwise correlation matrix R is as follows: the method comprises the following steps of marking two faults which exist in any frequent item set at the same time as related, and marking two faults which do not exist in all frequent item sets at the same time as unrelated;
and elements in the fault pairwise correlation matrix R indicate whether the faults are correlated or not.
2. The method according to claim 1, wherein the principle of performing fault decorrelation and root on fault data groups with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R is as follows:
if two faults which are related in the pairwise correlation matrix R indicate that the two related faults exist in the multi-fault data group at the same time, the high-priority fault is reserved and the low-priority fault is deleted under the condition that the high-priority fault exists;
if two irrelevant faults are simultaneously present in the fault data group with multiple faults in the fault pairwise correlation matrix R, the two faults are simultaneously reserved.
3. The method according to claim 1, wherein the determining the fault to which each alarm belongs in the extracted sets of alarm data according to the correlation between the alarms and the faults specifically comprises:
for each extracted group of alarm data, acquiring each fault contained in the fault data group subjected to decorrelation and root treatment of the fault corresponding to the extracted group of alarm data to obtain a fault set;
and for each group of extracted alarm data, determining that the fault with the highest correlation between each alarm in the alarm data and each fault in the corresponding fault set is the fault to which the corresponding alarm belongs.
4. A method according to claim 1 or 3, characterized in that in the method, based on the fault data set for a single fault in the K sets of fault data, a pearson correlation coefficient is calculated between each alarm and each fault, and the correlation between the alarm and each fault is represented by the pearson correlation coefficient.
5. A multi-fault data decoupling apparatus, comprising:
the data input unit is used for acquiring K groups of alarm data and K groups of fault data which are acquired in the same area at the same time, wherein each group of fault data is sorted according to the fault priority;
the data processing unit is used for obtaining a fault frequent item set X by using a correlation analysis algorithm for K groups of fault data, converting the fault frequent item set X into a fault pairwise correlation matrix R, and performing fault decorrelation and root formation on fault data groups with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R;
the decoupling unit is used for extracting each group of alarm data corresponding to each fault data group with a plurality of irrelevant faults after the fault decorrelation and the root cause are carried out, and determining the fault to which each alarm belongs in each extracted group of alarm data according to the correlation between the alarm and each fault;
the conversion principle of converting the fault frequent item set X into the fault pairwise correlation matrix R by the data processing unit is as follows: the method comprises the following steps of marking two faults which exist in any frequent item set at the same time as related, and marking two faults which do not exist in all frequent item sets at the same time as unrelated; and elements in the fault pairwise correlation matrix R indicate whether the faults are correlated or not.
6. The apparatus according to claim 5, wherein the data processing unit performs the principle of fault decorrelation and root on fault data groups with multiple faults in the K groups of fault data based on the fault pairwise correlation matrix R:
if two faults which are related in the pairwise correlation matrix R indicate that the two related faults exist in the multi-fault data group at the same time, the high-priority fault is reserved and the low-priority fault is deleted under the condition that the high-priority fault exists; if two irrelevant faults are simultaneously present in the fault data group with multiple faults in the fault pairwise correlation matrix R, the two faults are simultaneously reserved.
7. The apparatus according to claim 5, wherein the fault decoupling unit is specifically configured to, for each extracted set of alarm data, obtain each fault included in the fault data set after decorrelation and root processing of the fault corresponding to the extracted set of alarm data, and obtain a fault set; and for each group of extracted alarm data, determining that the fault with the highest correlation between each alarm in the alarm data and each fault in the corresponding fault set is the fault to which the corresponding alarm belongs.
8. The apparatus according to claim 5 or 7, wherein the data processing unit is further configured to calculate a Pearson correlation coefficient between each alarm and each fault based on the fault data set of a single fault in the K sets of fault data to represent a correlation between the alarm and each fault by the Pearson 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 CN105634781A (en) | 2016-06-01 |
| CN105634781B true 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) |
Families Citing this family (4)
| 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 |
| 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 |
| CN116091045B (en) * | 2023-02-28 | 2024-07-19 | 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 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7721140B2 (en) * | 2007-01-02 | 2010-05-18 | International Business Machines Corporation | Systems and methods for improving serviceability of a memory system |
-
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 (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105634781A (en) | 2016-06-01 |
| WO2016070642A1 (en) | 2016-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111262722B (en) | Safety monitoring method for industrial control system network | |
| CN106330533B (en) | large-scale network alarm real-time topology establishing method | |
| CN101783749B (en) | Network fault positioning method and device | |
| CN105634781B (en) | Multi-fault data decoupling method and device | |
| CN112953738B (en) | Root cause alarm positioning system, method and device and computer equipment | |
| US20170206458A1 (en) | Computer-readable recording medium, detection method, and detection apparatus | |
| JP6657885B2 (en) | Data collection device and optical transmission system | |
| CN115689320A (en) | Health management method and device for base station operation and computer readable storage medium | |
| CN113409555A (en) | Real-time alarm linkage method and system based on Internet of things | |
| CN109587145B (en) | False data intrusion detection method, device and equipment in power network | |
| WO2019138073A1 (en) | Method for monitoring devices in a network, computerized system and application program interface | |
| CN110609761B (en) | Method and device for determining fault source, storage medium and electronic equipment | |
| CN108763281A (en) | A kind of business intelligence analysis platform and system based on ETL | |
| CN111092861A (en) | Communication network safety prediction system | |
| CN117194171A (en) | Heterogeneous cloud resource panoramic anomaly detection system | |
| CN114978878B (en) | Positioning method, positioning device, electronic equipment and computer readable storage medium | |
| CN116600329A (en) | Message error identification code delimitation method and device | |
| CN117034149A (en) | Fault processing strategy determining method and device, electronic equipment and storage medium | |
| CN114358121A (en) | Monitoring method and device based on substation equipment and terminal equipment | |
| Zhao et al. | Research on machine learning-based correlation analysis method for power equipment alarms | |
| CN118509527B (en) | Abnormality detection method and system for multi-dimensional KPI (key performance indicator) time sequence of 5G core network | |
| WO2024138968A1 (en) | Base station fault diagnosis method and apparatus | |
| CN113347021B (en) | Model generation method, collision library detection method, device, electronic equipment and computer readable storage medium | |
| CN116993307B (en) | Collaborative office method and system with artificial intelligence learning capability | |
| CN117200458B (en) | Digital management method and device based on intelligent low-voltage switch cabinet |
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 |