CN108600009A - A kind of network alarm root localization method based on alarm data analysis - Google Patents
A kind of network alarm root localization method based on alarm data analysis Download PDFInfo
- Publication number
- CN108600009A CN108600009A CN201810376453.2A CN201810376453A CN108600009A CN 108600009 A CN108600009 A CN 108600009A CN 201810376453 A CN201810376453 A CN 201810376453A CN 108600009 A CN108600009 A CN 108600009A
- Authority
- CN
- China
- Prior art keywords
- alarm
- network
- root
- loop
- alert
- 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
-
- 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
- H04L41/0677—Localisation of faults
-
- 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
- H04L41/12—Discovery or management of network topologies
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of network alarm root localization method based on alarm data analysis, includes modeling analysis step and on-line alarm root positioning step based on alarm history data;First, by analyzing alarm history data sample, the sequential correlation relationship between network alarm is excavated, to establish the network topology between alarm member;On this basis, Real-time Alarm is mapped in established network topology, the relative position based on the corresponding alarm member of current alarm in network topology infers alarm root.This method need not use network hardware connection relation, service logic dependence and other expertise knowledge, exploitation, maintenance cost low;Meanwhile this method can make full use of the probability and distribution characteristics that generation is alerted in real system, have higher precision of analysis.
Description
Technical field
The present invention relates to computer application technology more particularly to a kind of network alarm roots based on alarm data analysis
Source localization method.
Background technology
In telecommunication network system, soft or hard component is interrelated by application call and network connection.When in system
When certain component failures or monitor control index occur abnormal, component associated there or application can be by different degrees of shadows
It rings.Therefore, after certain components alert, component associated there may alert therewith in corresponding link.In order to
Ensure network system even running, needs quickly to position alarm root to eliminate network failure hidden danger.Wherein, Root alarm refers to
It is not to be caused by other alarms and caused the alarm of other alarms in the alarm that a certain moment has occurred;And derives alarm and refer to
In the alarm at a time occurred, since other alarm members generate alarm and the associated alarm of initiation.
Existing network failure location technology includes mainly following three aspects.First, it is taken out in being put into practice based on network O&M
As the expertise gone out, fault location is carried out using artificial intelligence technologys such as rule-based reasoning, neural network, decision trees;Second, base
In the topology information of the network hardware, fault source tracing is carried out using graph-theory techniques such as dependency graph, Bayesian networks;Third, base
Call relation between networking component carries out network fault root analysis using model trace-back technique.The relevant technologies or it is more or
Existing network hardware connection relation or service logic related information are depended on less.
However, in large-scale networks, the logic between the physical couplings and application between the network hardware relies on
Relationship and its complexity.These incidence relations can also with processing business and updates and system upgrade dynamic change, therefore, it is difficult to establishing and
Safeguard accurate and comprehensive network topology.On the other hand, that is, allow to establish huge applied topology relationship, in alarm root
The information content really used in the analysis of source is often also smaller.For example, when certain and its complicated application call paths only once in a while by
When accessing or running sufficiently stable, utilization rate of the corresponding network topological information in alerting root-cause analysis is relatively low.Therefore, long
Phase safeguards that the topological relations such as networking component or application call are also faced with cost benefit problem.In addition, from the angle of alarm root-cause analysis
Degree, although alarm propagation direction is in close relations related to the physical topology of network and application call, the static letter of these priori
Breath also can not directly reflect in real system the probability and distribution situation for alerting generation.
Invention content
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of network alarms based on alarm data analysis
Root localization method solves existing alarm root location technology and depends on the physical connection of priori or asking for application call relationship unduly
Topic.
The purpose of the present invention is achieved through the following technical solutions:A kind of network alarm based on alarm data analysis
Root localization method, including off-line analysis step and alarm root on-line analysis step;The off-line analysis step include with
Lower sub-step:
S11:Alarm data sample is traversed, calculates and causes what other alarm members alerted when each alarm member alerts
Conditional probability;Wherein, the alarm data sample refers to the history alarm set of records ends of storage in the database, the alarm
Member:Refer to the minimum unit that alarm is generated in network system;
S12:Confidence threshold value is set, adjacency matrix is generated according to conditioned probability matrix;
S13:The network topology between alarm member is obtained according to above-mentioned adjacency matrix;
S14:Loop detection is carried out, and eliminates the loop in network;
The alarm root on-line analysis step includes following sub-step:
S21:All alarms currently occurred are collected, by the corresponding alarm member composition set M of these alarms;
S22:Alarm member in set M is projected in the topological network established in off-line analysis step;
S23:In conjunction with network topology structure, positioned by analyzing the position of alarm member in a network corresponding to current alarm
Alert root.
Further, step S11 includes following sub-step:
S111:For each alarm member A, the alarm example quantity of alarm member A in alarm data sample is counted, is obtained simultaneously
Take the associated alarm set of each of which alarm example A.a, and all associated alarm set Ψs corresponding with alarm member AA=∪
ΨA.a;Wherein, the alarm example refers to the alarm data that alarm member generates, the associated alarm set of alarm example A.a
During occurring for alarm example A.a, other alarm member set of alarm occurred;
S112:Each alarm member A is calculated successively causes the conditional probability P that other each arbitrary alarm member B are alerted
(B | A), formula is as follows:
In formula, SB|AInclude the associated alarm of alarm member B in associated alarm set to alert all alarm examples of member A
Gather number;SATo alert the alarm instance number of member A;α is condition threshold;And SB|AComputational methods it is as follows:
SB|A=| ΨB|A|,
ΨB|A={ ΨA.x| alarm member B ∈ ΨA.x};
S113:All alarm members are caused into the conditional probability that other alarm members alert and are organized into a conditional probability square
Battle array:
Further, in step s 12, for the arbitrary element P (B | A) in conditioned probability matrix, if P (B | A) it is more than
Confidence threshold value then will abut against the corresponding elements of P in matrix (B | A) and be set to 1, is otherwise set to 0;In addition, to all alarm member A,
It will abut against the corresponding elements of P in matrix (A | A) and be set to 0.
Further, in step s 13, for the element P (B | A) in conditioned probability matrix, if its corresponding element exists
Numerical value in adjacency matrix is 1, then it is assumed that alarm member A may cause alarm member B and alert.
Further, step S14 includes following sub-step:
Loop size threshold is set, when the alarm member number for constituting ring is less than or equal to the threshold value, to the alarm member in loop
It is marked, is merged into a logic alarm member;Otherwise, conjugation condition probability matrix will abut against and constitute loop in matrix
Side set to 0 successively by the sequence of corresponding conditional probability value from small to large, until loop eliminate.
Further, step S23 includes following sub-step:
S231:For all alarms member in set M, make following judgement successively:For the alarm member A in set M, if
There is the side of any other alarm member from alarm member A to set M in adjacency matrix, and there is no any other from set M
Alarm member then further executes S232 to the side of alarm member A;Otherwise, continue to divide next alarm member in set M
Analysis, until all alarm member analyses finish in set M;
S232:If the alarm member A for meeting condition described in S231 is logic alarm member made of loop merging, continue to execute
Step S233, otherwise the alarm corresponding to judgement alarm member A is current alarm root;
S233:When the alarm member A for meeting condition described in S231 is logic alarm member made of loop merges, if the loop
Upper all alarm members alert, then judge that all corresponding alert of alarm member are alarm root on the loop, otherwise, will
Meet the alarm corresponding to the alarm member X of the following conditions as current alarm root:For alerting member X, it is not present from set M
In other any alarm members to sides of alarm member X.
The beneficial effects of the invention are as follows:
(1) this method first by analyzing alarm history data sample, close by the sequential excavated between network alarm
Connection relationship, to establish the network topology between alarm member;On this basis, Real-time Alarm is mapped to established network topology
In, the relative position based on the corresponding alarm member of current alarm in network topology infers alarm root.Need not deeply it understand
With the complex informations such as topological structure, application call relationship, the networking component dependence of safeguarding network system, therefore develop, dimension
It protects at low cost.
(2) this method establishes network topology by analyzing alarm history data, therefore this method can reflect
The probability and distribution characteristics that generation is alerted in real system, it is more targeted for solving alarm root orientation problem.
Description of the drawings
Fig. 1 is overall flow figure of the present invention;
Fig. 2 is off-line analysis flow chart of steps of the present invention;
Fig. 3 is present invention alarm root on-line analysis flow chart of steps.
Specific implementation mode
Technical scheme of the present invention is described in further detail below in conjunction with the accompanying drawings:
The alarm data that the present embodiment uses for the telecommunications industry truthful data by data cleansing, including alarm member ID,
Alert example generation time, alarm example eliminates the information such as time.
As shown in Figure 1, a kind of network alarm root localization method based on alarm data analysis, including off-line analysis step
With alarm root on-line analysis step;
As shown in Fig. 2, the off-line analysis step includes following sub-step:
S11:Alarm data sample is traversed, calculates and causes what other alarm members alerted when each alarm member alerts
Conditional probability;Wherein, the alarm data sample refers to the history alarm set of records ends of storage in the database, the alarm
Member:Refer to the minimum unit that alarm is generated in network system;
Preferably, in the present embodiment, step S11 includes following sub-step:
S111:For each alarm member A, the alarm example quantity S of alarm member A in alarm data sample is countedA, simultaneously
Obtain the associated alarm set Ψ of each of which alarm example A.aA.a, and all associated alarm set corresponding with alarm member A
ΨA=∪ ΨA.a;Wherein, the alarm example refers to the alarm data that alarm member generates, and the association of alarm example A.a is accused
During alert collection is combined into the A.a generations of alarm example, other alarm member set of alarm occurred;
S112:Each alarm member A is calculated successively causes the conditional probability P that other each arbitrary alarm member B are alerted
(B | A), formula is as follows:
In formula, SB|AInclude the associated alarm of alarm member B in associated alarm set to alert all alarm examples of member A
Gather number;SATo alert the alarm instance number of member A;α is condition threshold;And SB|AComputational methods it is as follows:
SB|A=| ΨB|A|,
ΨB|A={ ΨA.x| alarm member B ∈ ΨA.x};
S113:All alarm members are caused into the conditional probability that other alarm members alert and are organized into a conditional probability square
Battle array:
S12:Confidence threshold value is set, adjacency matrix is generated according to conditioned probability matrix;
Preferably, in the present embodiment, in step s 12, as follows according to conditioned probability matrix generation adjacency matrix mode:
For the arbitrary element P (B | A) in conditioned probability matrix, if P (B | A) is more than confidence threshold value, will abut against P in matrix (B |
A) corresponding element is set to 1, is otherwise set to 0;In addition, to all alarm member A, it will abut against the corresponding elements of P in matrix (A | A) and set
It is 0.
S13:The network topology between alarm member is obtained according to above-mentioned adjacency matrix;
Preferably, in the present embodiment, for the element P (B | A) in conditioned probability matrix, if its corresponding element is in neighbour
It is 1 to connect the numerical value in matrix, then it is assumed that alarm member A may cause alarm member B and alert.
S14:Loop detection is carried out, and eliminates the loop in network;
Preferably, in the present embodiment, step S14 includes following sub-step:Loop size threshold is set, when composition ring
When the first number of alarm is less than or equal to the threshold value, the alarm member in loop is marked, is merged into a logic alarm member;It is no
Then, conjugation condition probability matrix will abut against and constitute sequence of the side of loop by corresponding conditional probability value from small to large in matrix
It sets to 0 successively, until loop is eliminated.
As shown in figure 3, the alarm root on-line analysis step includes following sub-step:
S21:All alarms currently occurred are collected, by the corresponding alarm member composition set M of these alarms.
S22:Alarm member in set M is projected in the topological network established in off-line analysis step.
S23:In conjunction with network topology structure, positioned by analyzing the position of alarm member in a network corresponding to current alarm
Alert root.
Preferably, in the present embodiment, step S23 includes following sub-step:
S231:For all alarms member in set M, make following judgement successively:For the alarm member A in set M, if
There is the side of any other alarm member from alarm member A to set M in adjacency matrix, and there is no any other from set M
Alarm member then further executes S232 to the side of alarm member A;Otherwise, continue to divide next alarm member in set M
Analysis, until all alarm member analyses finish in set M;
S232:If the alarm member A for meeting condition described in S231 is logic alarm member made of loop merging, continue to execute
Step S233, otherwise the alarm corresponding to judgement alarm member A is current alarm root;
S233:When the alarm member A for meeting condition described in S231 is logic alarm member made of loop merges, if the loop
Upper all alarm members alert, then judge that all corresponding alert of alarm member are alarm root on the loop, otherwise, will
Meet the alarm corresponding to the alarm member X of the following conditions as current alarm root:For alerting member X, it is not present from set M
In other any alarm members to sides of alarm member X.
In above-mentioned steps S232 and S233, multiple alarm roots are may be simultaneously present.
The present invention is described by embodiment, but is not limited the invention, with reference to description of the invention, institute
Other variations of disclosed embodiment, are such as readily apparent that the professional person of this field, such variation should belong to
Within the scope of the claims in the present invention limit.
Claims (6)
1. a kind of network alarm root localization method based on alarm data analysis, it is characterised in that:Including off-line analysis step
With alarm root on-line analysis step;The off-line analysis step includes following sub-step:
S11:Alarm data sample is traversed, calculates and causes the condition that other alarm members alert when each alarm member alerts
Probability;Wherein, the alarm data sample refers to the history alarm set of records ends of storage in the database, alarm member:
Refer to the minimum unit that alarm is generated in network system;
S12:Confidence threshold value is set, adjacency matrix is generated according to conditioned probability matrix;
S13:The network topology between alarm member is obtained according to above-mentioned adjacency matrix;
S14:Loop detection is carried out, and eliminates the loop in network;
The alarm root on-line analysis step includes following sub-step:
S21:All alarms currently occurred are collected, by the corresponding alarm member composition set M of these alarms;
S22:Alarm member in set M is projected in the topological network established in off-line analysis step;
S23:In conjunction with network topology structure, alarm is positioned by analyzing the position of alarm member in a network corresponding to current alarm
Root.
2. a kind of network alarm root localization method based on alarm data analysis according to claim 1, feature exist
In:Step S11 includes following sub-step:
S111:For each alarm member A, the alarm example quantity of alarm member A in alarm data sample is counted, while obtaining it
The associated alarm set of each alarm example A.a, and all associated alarm set Ψs corresponding with alarm member AA=∪ ΨA.a;
Wherein, the alarm example refers to the alarm data that alarm member generates, and the associated alarm collection of alarm example A.a is combined into alarm
During example A.a occurs, other alarm member set of alarm occurred;
S112:Calculate successively each alarm member A cause conditional probability P that other each arbitrary alarm member B alert (B |
A), formula is as follows:
In formula, SB|AInclude the associated alarm set of alarm member B in associated alarm set to alert all alarm examples of member A
Number;SATo alert the alarm instance number of member A;α is condition threshold;And SB|AComputational methods it is as follows:
SB|A=| ΨB|A|,
ΨB|A={ ΨA.x| alarm member B ∈ ΨA.x};
S113:All alarm members are caused into the conditional probability that other alarm members alert and are organized into a conditioned probability matrix:
3. a kind of network alarm root localization method based on alarm data analysis according to claim 2, feature exist
In:In step s 12, for the arbitrary element P (B | A) in conditioned probability matrix, if P (B | A) it is more than confidence threshold value, it will
The corresponding elements of P in adjacency matrix (B | A) are set to 1, are otherwise set to 0;In addition, to all alarm member A, will abut against P in matrix (A |
A) corresponding element is set to 0.
4. a kind of network alarm root localization method based on alarm data analysis according to claim 3, feature exist
In:In step s 13, for the element P (B | A) in conditioned probability matrix, if its number of corresponding element in adjacency matrix
Value is 1, then it is assumed that alarm member A may cause alarm member B and alert.
5. a kind of network alarm root localization method based on alarm data analysis according to claim 4, feature exist
In:Step S14 includes following sub-step:
Loop size threshold is set, when the alarm member number for constituting ring is less than or equal to the threshold value, the alarm member in loop is carried out
Label is merged into a logic alarm member;Otherwise, conjugation condition probability matrix will abut against the side that loop is constituted in matrix
It is set to 0 successively by the sequence of corresponding conditional probability value from small to large, until loop is eliminated.
6. a kind of network alarm root positioning based on alarm data analysis according to any one of Claims 1 to 5
Method, it is characterised in that:Step S23 includes following sub-step:
S231:For all alarms member in set M, make following judgement successively:For the alarm member A in set M, if in adjoining
There is the side of any other alarm member from alarm member A to set M in matrix, and any other alarm from set M is not present
Member then further executes S232 to the side of alarm member A;Otherwise, continue to analyze next alarm member in set M, directly
It is finished to all alarm member analyses in set M;
S232:If the alarm member A for meeting condition described in S231 is logic alarm member made of loop merging, step is continued to execute
S233, otherwise the alarm corresponding to judgement alarm member A is current alarm root;
S233:When the alarm member A for meeting condition described in S231 is logic alarm member made of loop merges, if institute on the loop
There is alarm member to alert, then judges that all corresponding alert of alarm member are alarm root on the loop, otherwise, will be met
Alarm corresponding to the alarm member X of the following conditions is as current alarm root:For alert member X, be not present from set M its
His any alarm member arrives the side of alarm member X.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810376453.2A CN108600009B (en) | 2018-04-25 | 2018-04-25 | Network alarm root positioning method based on alarm data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810376453.2A CN108600009B (en) | 2018-04-25 | 2018-04-25 | Network alarm root positioning method based on alarm data analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108600009A true CN108600009A (en) | 2018-09-28 |
CN108600009B CN108600009B (en) | 2021-03-30 |
Family
ID=63609519
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810376453.2A Active CN108600009B (en) | 2018-04-25 | 2018-04-25 | Network alarm root positioning method based on alarm data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108600009B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110445665A (en) * | 2019-09-06 | 2019-11-12 | 国网江苏省电力公司信息通信分公司 | Based on the powerline network alarm association method for digging for improving GSP |
CN111342997A (en) * | 2020-02-06 | 2020-06-26 | 烽火通信科技股份有限公司 | Construction method of deep neural network model, fault diagnosis method and system |
JP2020136724A (en) * | 2019-02-13 | 2020-08-31 | 日本電信電話株式会社 | Network information collection device and method therefor |
WO2020238810A1 (en) * | 2019-05-25 | 2020-12-03 | 华为技术有限公司 | Alarm analysis method and related device |
CN112087316A (en) * | 2020-07-30 | 2020-12-15 | 北京思特奇信息技术股份有限公司 | Network anomaly root cause positioning method based on anomaly data analysis |
CN112118141A (en) * | 2020-09-21 | 2020-12-22 | 中山大学 | Communication network-oriented alarm event correlation compression method and device |
CN112202584A (en) * | 2019-07-08 | 2021-01-08 | 中国移动通信集团浙江有限公司 | Alarm correlation method, device, computing equipment and computer storage medium |
CN112528448A (en) * | 2021-01-01 | 2021-03-19 | 谭世克 | Topology and data management maintenance system |
CN113497721A (en) * | 2020-03-20 | 2021-10-12 | 中国移动通信集团四川有限公司 | Network fault positioning method and device |
CN113825148A (en) * | 2020-06-18 | 2021-12-21 | 中国移动通信集团浙江有限公司 | Method and device for determining alarm level of network node and computing equipment |
CN115174355A (en) * | 2022-07-26 | 2022-10-11 | 杭州东方通信软件技术有限公司 | Generation method of fault root cause positioning model, and fault root cause positioning method and device |
US11996974B2 (en) | 2019-05-25 | 2024-05-28 | Huawei Technologies Co., Ltd. | Alarm analysis method and related device |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020111755A1 (en) * | 2000-10-19 | 2002-08-15 | Tti-Team Telecom International Ltd. | Topology-based reasoning apparatus for root-cause analysis of network faults |
WO2010112855A1 (en) * | 2009-03-31 | 2010-10-07 | British Telecommunications | Network analysis system |
CN101945009A (en) * | 2010-09-14 | 2011-01-12 | 国网电力科学研究院 | Positioning method and device of power communication network fault based on case and pattern matching |
CN101997709A (en) * | 2009-08-10 | 2011-03-30 | 中兴通讯股份有限公司 | Root alarm data analysis method and system |
CN102130783A (en) * | 2011-01-24 | 2011-07-20 | 浪潮通信信息系统有限公司 | Intelligent alarm monitoring method of neural network |
CN105391579A (en) * | 2015-11-25 | 2016-03-09 | 国家电网公司 | Electric power communication network fault positioning method based on key alarm sets and supervised classification |
CN106250288A (en) * | 2016-07-29 | 2016-12-21 | 浪潮软件集团有限公司 | Root alarm analysis and identification method based on data mining |
CN106603317A (en) * | 2017-02-20 | 2017-04-26 | 山东浪潮商用系统有限公司 | Alarm monitoring strategy analysis method based on data mining technology |
CN106941423A (en) * | 2017-04-13 | 2017-07-11 | 腾讯科技(深圳)有限公司 | Failure cause localization method and device |
CN107196804A (en) * | 2017-06-01 | 2017-09-22 | 国网山东省电力公司信息通信公司 | Power system terminal communication access network Centralized Alarm Monitoring system and method |
-
2018
- 2018-04-25 CN CN201810376453.2A patent/CN108600009B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020111755A1 (en) * | 2000-10-19 | 2002-08-15 | Tti-Team Telecom International Ltd. | Topology-based reasoning apparatus for root-cause analysis of network faults |
EP1279211B1 (en) * | 2000-10-19 | 2013-11-20 | TTI-Team Telecom International LTD. | Topology-based reasoning apparatus for root-cause analysis of network faults |
WO2010112855A1 (en) * | 2009-03-31 | 2010-10-07 | British Telecommunications | Network analysis system |
CN101997709A (en) * | 2009-08-10 | 2011-03-30 | 中兴通讯股份有限公司 | Root alarm data analysis method and system |
CN101945009A (en) * | 2010-09-14 | 2011-01-12 | 国网电力科学研究院 | Positioning method and device of power communication network fault based on case and pattern matching |
CN102130783A (en) * | 2011-01-24 | 2011-07-20 | 浪潮通信信息系统有限公司 | Intelligent alarm monitoring method of neural network |
CN105391579A (en) * | 2015-11-25 | 2016-03-09 | 国家电网公司 | Electric power communication network fault positioning method based on key alarm sets and supervised classification |
CN106250288A (en) * | 2016-07-29 | 2016-12-21 | 浪潮软件集团有限公司 | Root alarm analysis and identification method based on data mining |
CN106603317A (en) * | 2017-02-20 | 2017-04-26 | 山东浪潮商用系统有限公司 | Alarm monitoring strategy analysis method based on data mining technology |
CN106941423A (en) * | 2017-04-13 | 2017-07-11 | 腾讯科技(深圳)有限公司 | Failure cause localization method and device |
CN107196804A (en) * | 2017-06-01 | 2017-09-22 | 国网山东省电力公司信息通信公司 | Power system terminal communication access network Centralized Alarm Monitoring system and method |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020136724A (en) * | 2019-02-13 | 2020-08-31 | 日本電信電話株式会社 | Network information collection device and method therefor |
JP7193725B2 (en) | 2019-02-13 | 2022-12-21 | 日本電信電話株式会社 | Network information collection device and method |
US11444857B2 (en) | 2019-02-13 | 2022-09-13 | Nippon Telegraph And Telephone Corporation | Network information collection device and method therefor |
WO2020238810A1 (en) * | 2019-05-25 | 2020-12-03 | 华为技术有限公司 | Alarm analysis method and related device |
CN112073208A (en) * | 2019-05-25 | 2020-12-11 | 成都华为技术有限公司 | Alarm analysis method and related equipment |
US11996974B2 (en) | 2019-05-25 | 2024-05-28 | Huawei Technologies Co., Ltd. | Alarm analysis method and related device |
CN112202584A (en) * | 2019-07-08 | 2021-01-08 | 中国移动通信集团浙江有限公司 | Alarm correlation method, device, computing equipment and computer storage medium |
CN112202584B (en) * | 2019-07-08 | 2022-07-29 | 中国移动通信集团浙江有限公司 | Alarm correlation method, device, computing equipment and computer storage medium |
CN110445665B (en) * | 2019-09-06 | 2022-06-14 | 国网江苏省电力有限公司信息通信分公司 | Electric power communication network alarm association mining method based on improved GSP |
CN110445665A (en) * | 2019-09-06 | 2019-11-12 | 国网江苏省电力公司信息通信分公司 | Based on the powerline network alarm association method for digging for improving GSP |
CN111342997A (en) * | 2020-02-06 | 2020-06-26 | 烽火通信科技股份有限公司 | Construction method of deep neural network model, fault diagnosis method and system |
CN111342997B (en) * | 2020-02-06 | 2022-08-09 | 烽火通信科技股份有限公司 | Construction method of deep neural network model, fault diagnosis method and system |
CN113497721B (en) * | 2020-03-20 | 2023-08-01 | 中国移动通信集团四川有限公司 | Network fault positioning method and device |
CN113497721A (en) * | 2020-03-20 | 2021-10-12 | 中国移动通信集团四川有限公司 | Network fault positioning method and device |
CN113825148A (en) * | 2020-06-18 | 2021-12-21 | 中国移动通信集团浙江有限公司 | Method and device for determining alarm level of network node and computing equipment |
CN113825148B (en) * | 2020-06-18 | 2023-08-18 | 中国移动通信集团浙江有限公司 | Method and device for determining alarm grade of network node and computing equipment |
CN112087316A (en) * | 2020-07-30 | 2020-12-15 | 北京思特奇信息技术股份有限公司 | Network anomaly root cause positioning method based on anomaly data analysis |
CN112118141A (en) * | 2020-09-21 | 2020-12-22 | 中山大学 | Communication network-oriented alarm event correlation compression method and device |
CN112528448B (en) * | 2021-01-01 | 2022-05-17 | 电管家能源管理(上海)有限公司 | Topology and data management maintenance system |
CN112528448A (en) * | 2021-01-01 | 2021-03-19 | 谭世克 | Topology and data management maintenance system |
CN115174355A (en) * | 2022-07-26 | 2022-10-11 | 杭州东方通信软件技术有限公司 | Generation method of fault root cause positioning model, and fault root cause positioning method and device |
CN115174355B (en) * | 2022-07-26 | 2024-01-19 | 杭州东方通信软件技术有限公司 | Method for generating fault root positioning model, fault root positioning method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108600009B (en) | 2021-03-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108600009A (en) | A kind of network alarm root localization method based on alarm data analysis | |
Yang et al. | A time efficient approach for detecting errors in big sensor data on cloud | |
CN105095048B (en) | A kind of monitoring system alarm association processing method based on business rule | |
CN108306756B (en) | Holographic evaluation system based on power data network and fault positioning method thereof | |
CN111858123B (en) | Fault root cause analysis method and device based on directed graph network | |
Liu et al. | Fault-tolerant event region detection on trajectory pattern extraction for industrial wireless sensor networks | |
CN112543465B (en) | Abnormity detection method, abnormity detection device, terminal and storage medium | |
CN108964995A (en) | Log correlation analysis method based on time shaft event | |
CN111162949A (en) | Interface monitoring method based on Java byte code embedding technology | |
CN109753385A (en) | A kind of restoration methods and system towards the monitoring of stream calculation system exception | |
US10884805B2 (en) | Dynamically configurable operation information collection | |
CN112822052B (en) | Network fault root cause positioning method based on network topology and alarm | |
CN115809183A (en) | Method for discovering and disposing information-creating terminal fault based on knowledge graph | |
CN113516174B (en) | Call chain abnormality detection method, computer device, and readable storage medium | |
CN112769605B (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
Mandal et al. | Decision‐theoretic rough sets under Pythagorean fuzzy information | |
Dou et al. | Pc 2 a: predicting collective contextual anomalies via lstm with deep generative model | |
CN111884859B (en) | Network fault diagnosis method and device and readable storage medium | |
Solmaz et al. | ALACA: A platform for dynamic alarm collection and alert notification in network management systems | |
Zhang et al. | Comparing the use of Bayesian networks and neural networks in response time modeling for service-oriented systems | |
JPH10502222A (en) | Hardware distributed management method and system | |
CN117221087A (en) | Alarm root cause positioning method, device and medium | |
De Sousa et al. | Event detection framework for wireless sensor networks considering data anomaly | |
CN115514627A (en) | Fault root cause positioning method and device, electronic equipment and readable storage medium | |
CN114500229B (en) | Network alarm positioning and analyzing method based on space-time information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |