CN114143167A - Light attenuation monitoring network security method based on Bayesian network - Google Patents
Light attenuation monitoring network security method based on Bayesian network Download PDFInfo
- Publication number
- CN114143167A CN114143167A CN202111470440.XA CN202111470440A CN114143167A CN 114143167 A CN114143167 A CN 114143167A CN 202111470440 A CN202111470440 A CN 202111470440A CN 114143167 A CN114143167 A CN 114143167A
- Authority
- CN
- China
- Prior art keywords
- time
- real
- database
- fault
- light attenuation
- 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
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/30—Network architectures or network communication protocols for network security for supporting lawful interception, monitoring or retaining of communications or communication related information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- H04L41/0604—Management of faults, events, alarms or notifications using filtering, e.g. reduction of information by using priority, element types, position or time
-
- 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
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
- H04L41/28—Restricting access to network management systems or functions, e.g. using authorisation function to access network configuration
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q11/00—Selecting arrangements for multiplex systems
- H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
- H04Q11/0062—Network aspects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q11/00—Selecting arrangements for multiplex systems
- H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
- H04Q11/0062—Network aspects
- H04Q2011/0079—Operation or maintenance aspects
- H04Q2011/0083—Testing; Monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Technology Law (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a Bayesian network-based method for monitoring network security by light attenuation, which comprises the following steps: the method comprises the following steps: acquiring real-time light attenuation values of the ports of the network equipment at regular time, judging whether the real-time light attenuation values are smaller than a light attenuation value threshold value, if so, storing the real-time light attenuation values into a real-time database, and if not, storing the real-time light attenuation values into a historical fault database; s2, forming a real-time data sub-base and a historical fault data sub-base; s3, confirming the prior probability DB (+ | D), the adjusting factor DB (+ | N) and the conditional probability DB (D) according to the real-time database and the historical fault database; s4, constructing a Bayesian network model, and constructing a real-time light attenuation value trend value and a fault light attenuation value early warning value; and S5, completing early warning according to the real-time light attenuation value trend value and the fault light attenuation value early warning value. The invention has the advantages of improving the accuracy of network safety monitoring and early warning and reducing the false alarm and the missing alarm of network alarm.
Description
Technical Field
The invention relates to the technical field of network security monitoring. More particularly, the invention relates to a method for monitoring network security based on light attenuation of a Bayesian network.
Background
The network security includes network layer security such as network packet loss and delay, and also includes network device security. Network security is an important part of the national security system, the development degree of the network society is continuously improved, the network application is increasingly popularized, and the network brings convenience to people and brings non-negligible security risk. With the large-scale application of the artificial intelligence technology, the problem elimination by the artificial experience and the automatic operation and maintenance is difficult to meet the timeliness requirement. How to introduce the early warning baseline to replace the artificial experience to carry out the warning discovery improves the accuracy of the network safety monitoring early warning and reduces the false alarm and the missing alarm of the network warning, which is the problem to be solved urgently at present.
Disclosure of Invention
An object of the present invention is to solve at least the above problems and to provide at least the advantages described later.
The invention also aims to provide a method for monitoring network security based on the optical attenuation of the Bayesian network, which improves the accuracy of monitoring and early warning on the network equipment security and reduces the false alarm and the false alarm missing of network alarm.
To achieve these objects and other advantages in accordance with the purpose of the invention, there is provided a method for monitoring network security based on optical attenuation of a bayesian network, comprising the steps of:
s1, collecting real-time light attenuation values of the network equipment ports at regular time, judging whether the real-time light attenuation values are smaller than a light attenuation value threshold value, if so, storing the real-time light attenuation values into a real-time database, and if not, storing the real-time light attenuation values into a historical fault database, wherein the light attenuation value threshold value is-30 db;
s2, dividing the time of day into N time periods, dividing the data of the real-time database and the historical fault database into N parts according to the acquisition time corresponding to the N time periods respectively to form a real-time database sub-database and a historical fault database sub-database;
s3, confirming a prior probability DB (+ | D), an adjusting factor DB (+ | N) and a conditional probability DB (D) according to the real-time database and the historical fault database, wherein the prior probability comprises a real-time prior probability and a fault prior probability, the adjusting factor comprises a real-time adjusting factor and a fault adjusting factor, and the conditional probability comprises a real-time conditional probability and a fault condition probability;
s4, constructing a Bayesian network model: b (D | +) DB (+ | D) DB (D))/(DB (+ | D) DB (D) + DB (+ | N) (1-DB (D));
the real-time conditional probability is taken as an essential condition, and a real-time light attenuation value trend value is constructed by utilizing a Bayesian network model in cooperation with the real-time prior probability; establishing a fault light attenuation value early warning value by using a Bayesian network model in cooperation with a fault prior probability by taking the fault condition probability as an essential condition;
and S5, completing early warning according to the real-time light attenuation value trend value and the fault light attenuation value early warning value.
Preferably, the timed interval is 1-5 min.
Preferably, the timing interval is 1 min.
Preferably, in step S1, if not, it is determined that a network quality fault occurs at the network device port, and when the network quality fault is recovered, the real-time optical attenuation value and the duration time acquired for the first time by the network quality fault constitute a fault data.
Preferably, the real-time adjustment factor is the number of times of false alarm of the historical fault data sub-library/total number of data of the real-time data sub-library, and the fault adjustment factor is the number of times of false alarm of the historical fault data sub-library/total number of data of the historical fault data sub-library, wherein the number of times of false alarm of the historical fault data sub-library is the number of pieces of fault data with duration equal to the fixed time interval in the historical fault data sub-library.
Preferably, the real-time prior probability is 1-the real-time adjustment factor, and the fault prior probability is 1-the fault adjustment factor.
Preferably, the real-time conditional probability is the sum of the light attenuation values of the real-time data sub-library/the total number of the data of the real-time data sub-library, and the historical conditional probability is the sum of the light attenuation values of the historical fault data sub-library/the total number of the data of the historical fault data sub-library.
Preferably, N is 24.
The invention at least comprises the following beneficial effects:
firstly, the safety of the network equipment is monitored and early-warned by utilizing the light attenuation value, the accuracy of monitoring and early-warning is improved, and the false alarm and the missing report of network warning are reduced.
Secondly, the real-time light attenuation value trend base line is an early warning base line generated by utilizing a real-time database and is closer to a trend graph which is possibly alarmed under the normal condition of a real-time network; the fault light attenuation value early warning baseline is an early warning baseline generated by utilizing a historical fault database and is closer to a trend graph of the alarm to be generated; by comparing the two baselines, the fluctuation range between the real-time light attenuation value and the fault light attenuation value baseline can be more intuitively obtained, so that the safety condition of the network equipment can be known, and the trend judgment on the current network safety is realized.
And thirdly, corresponding comparison and judgment are carried out in different time periods, so that the accuracy of monitoring and early warning is further improved, and the false alarm and the missing alarm of network alarm are reduced.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Detailed Description
The present invention is further described in detail below with reference to examples so that those skilled in the art can practice the invention with reference to the description.
Network equipment such as a core interaction machine in an internal local area network is monitored, and the network topology structure is specifically as follows: the method for monitoring the network security based on the optical attenuation of the Bayesian network comprises the following steps of:
s1, acquiring a real-time light attenuation value of a port of a core switch every 1min, judging whether the real-time light attenuation value is smaller than a light attenuation value threshold value (-30db), if so, storing the real-time light attenuation value into a real-time database, if not, determining that a network quality fault occurs at a port of network equipment, and when the network quality fault is recovered, forming fault data by the real-time light attenuation value, the duration and the acquisition time acquired for the first time by the network quality fault and storing the fault data into a historical fault database, wherein the acquisition time of each fault data in the historical database is the acquisition time of the data acquired for the first time, and the data acquired for each time in the real-time database comprises the real-time light attenuation value and the acquisition time and is recorded as one data;
TABLE 1 light decay data for a period of 1 day 00:01-01:00 in the monitoring process
As can be seen from table 1 above, during the above time period from 00:01 to 01:00, 11 pieces of fault data are generated, which are respectively shown in table 2 below:
TABLE 2 example of storing Fault data in historical Fault database
S2, dividing the time of day into 24 time periods, and dividing the time of day into 24 hours, wherein the time periods can be specifically divided according to (00:00-01:00], (01:00-02:00], (11:00-12:00], (12:00-13:00], (22:00-23: 00) and (23:00-24: 00), and then the data collected in the table 1 belong to the (00:00-01: 00) time periods;
dividing the data of the real-time database into 24 parts according to the acquisition time of each piece of data to obtain 24 parts of data, wherein each part of data in the real-time database corresponds to a time period, each part of data forms a real-time database sub-base, 24 parts of data form 24 real-time database sub-bases, and 24 real-time database sub-bases form the real-time database;
dividing the data of the historical fault database into 24 parts according to the acquisition time of each piece of data to obtain 24 parts of data, wherein each part of data in the historical fault database corresponds to a time period, each part of data forms a real-time database sub-database, 24 parts of data forms 24 historical fault database sub-databases, and the 24 historical fault database sub-databases form a historical fault database;
s3, obtaining the prior probability DB (+ | D), the adjusting factor DB (+ | N) and the conditional probability DB (D) corresponding to each time period according to the real-time database and the historical fault database, wherein:
obtaining corresponding prior probability DB (+ | D), adjustment factor DB (+ | N) and conditional probability DB (D) according to a real-time data sub-database and a historical fault data sub-database corresponding to one time period as follows:
s31, adjusting factors comprise real-time adjusting factors and fault adjusting factors;
the real-time adjustment factor is the number of times of false alarm of the historical fault data sub-library/the total number of data of the real-time data sub-library;
the fault adjustment factor is the number of false reports of the historical fault data sub-library/the total number of data of the historical fault data sub-library, wherein the number of false reports of the historical fault data sub-library is the number of fault data with the duration equal to 1min in the historical fault data sub-library, for example, fault data corresponding to sequence numbers of 2, 4, 5, 6, 9 and 11 in table 2 are all false reports of the historical fault data sub-library, and the number of false reports of the historical fault data sub-library is recorded;
s32, the prior probability comprises real-time prior probability and failure prior probability;
specifically, the method comprises the following steps: the real-time prior probability is 1-real-time adjustment factor, and the fault prior probability is 1-fault adjustment factor;
s33, the conditional probability comprises a real-time conditional probability and a fault conditional probability;
the real-time conditional probability is the sum of the light attenuation values of the real-time data sub-database/the total number of the data of the real-time data sub-database;
the historical conditional probability is the sum of the light attenuation values of the historical fault data sub-library/the total number of the data of the historical fault data sub-library;
s5, constructing a Bayesian network model of the probability of the network equipment port failure:
DB(D|+)＝DB(+|D)DB(D)/(DB(+|D)DB(D)+DB(+|N)(1-DB(D)))；
the real-time conditional probability is taken as an essential condition, and a real-time light attenuation value trend value is constructed by utilizing a Bayesian network model in cooperation with the real-time prior probability;
establishing a fault light attenuation value early warning value by using a Bayesian network model in cooperation with a fault prior probability by taking the fault condition probability as an essential condition;
s6, completing early warning according to the real-time light attenuation value trend value and the fault light attenuation value early warning value, wherein the early warning judgment comprises the following steps:
the method comprises the following steps:
constructing a real-time light attenuation value trend baseline according to the real-time light attenuation value trend value and the time period corresponding to the evening (off-duty time-on-duty time of the next day);
constructing a fault light attenuation value early warning value baseline according to the fault light attenuation value early warning value and the time period corresponding to the evening (off-duty time-on-duty time of the next day);
solving k as a difference value between the two early warning devices, and specifically judging as follows:
if k is less than 5, generating red early warning, defining the network quality as poor, and needing to check the core switch;
k is more than 10 and less than or equal to 5, yellow early warning is generated, and the network quality is defined as general;
k is more than or equal to 10, green early warning is generated, and the network quality is defined as good.
The method 2 comprises the following steps:
determining the purchase time and the warranty time of the core switch, starting to acquire data at the time 1 year and half year after the warranty period, and starting to early warn at the time half year after the warranty period;
extracting all real-time light attenuation value trend values and all fault light attenuation value early warning values corresponding to a certain time period before the current time point;
constructing a real-time light attenuation value trend base line by taking the occurrence time as a horizontal coordinate and all real-time light attenuation value trend values as a vertical coordinate;
constructing a fault light attenuation value early warning baseline by taking the occurrence time as a horizontal coordinate and all fault light attenuation value early warning values as a vertical coordinate;
judging the time T required by k less than 10 according to the real-time light attenuation value trend baseline and the fault light attenuation value early warning baseline, wherein k is the difference between the two early warning devices;
if T is less than or equal to 90d, generating red early warning, defining the network quality as poor, and needing to check the core switch;
t is more than 90d and less than or equal to 180d, yellow early warning is generated, and the network quality is defined as general;
t is more than or equal to 180d, green early warning is generated, and the network quality is defined as good.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable to various fields of endeavor for which the invention may be embodied with additional modifications as would be readily apparent to those skilled in the art, and the invention is therefore not limited to the details given herein and to the embodiments shown and described without departing from the generic concept as defined by the claims and their equivalents.
Claims (8)
1. The method for monitoring the network security based on the optical attenuation of the Bayesian network is characterized by comprising the following steps:
s1, collecting real-time light attenuation values of the network equipment ports at regular time, judging whether the real-time light attenuation values are smaller than a light attenuation value threshold value, if so, storing the real-time light attenuation values into a real-time database, and if not, storing the real-time light attenuation values into a historical fault database, wherein the light attenuation value threshold value is-30 db;
s2, dividing the time of day into N time periods, dividing the data of the real-time database and the historical fault database into N parts according to the acquisition time corresponding to the N time periods respectively to form a real-time database sub-database and a historical fault database sub-database;
s3, confirming a prior probability DB (+ | D), an adjusting factor DB (+ | N) and a conditional probability DB (D) according to the real-time database and the historical fault database, wherein the prior probability comprises a real-time prior probability and a fault prior probability, the adjusting factor comprises a real-time adjusting factor and a fault adjusting factor, and the conditional probability comprises a real-time conditional probability and a fault condition probability;
s4, constructing a Bayesian network model: b (D | +) DB (+ | D) DB (D))/(DB (+ | D) DB (D) + DB (+ | N) (1-DB (D));
the real-time conditional probability is taken as an essential condition, and a real-time light attenuation value trend value is constructed by utilizing a Bayesian network model in cooperation with the real-time prior probability; establishing a fault light attenuation value early warning value by using a Bayesian network model in cooperation with a fault prior probability by taking the fault condition probability as an essential condition;
and S5, completing early warning according to the real-time light attenuation value trend value and the fault light attenuation value early warning value.
2. The bayesian network-based method for monitoring network security by optical attenuation of light according to claim 1, wherein the timing interval is 1-5 min.
3. The bayesian network based optical attenuation monitoring network security method of claim 2, wherein the timing interval is 1 min.
4. The method for monitoring network security based on bayesian network optical attenuation of claim 1, wherein in step S1, if not, it is determined that a network quality failure occurs at a network device port, and when the network quality failure recovers, the real-time optical attenuation value and duration of the first time collected by the network quality failure constitute a piece of failure data.
5. The bayesian network-based optical attenuation monitoring network security method according to claim 4, wherein the real-time adjustment factor is the number of false reports of the historical failure database/total number of data in the real-time database, and the failure adjustment factor is the number of false reports of the historical failure database/total number of data in the historical failure database, wherein the number of false reports of the historical failure database is the number of failure data in the historical failure database with a duration equal to the fixed time interval.
6. The bayesian network-based method for monitoring network security by optical attenuation of light according to claim 5, wherein the real-time prior probability is 1-the real-time adjustment factor, and the fault prior probability is 1-the fault adjustment factor.
7. The bayesian network-based method for monitoring network security by optical attenuation of a network as recited in claim 1, wherein the real-time conditional probability is the sum of optical attenuation values of the real-time data sub-library/the total number of data of the real-time data sub-library, and the historical conditional probability is the sum of optical attenuation values of the historical failure data sub-library/the total number of data of the historical failure data sub-library.
8. The bayesian network-based method for monitoring network security by optical attenuation of light according to claim 1, wherein N is 24.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111470440.XA CN114143167B (en) | 2021-12-03 | 2021-12-03 | Light attenuation monitoring network safety method based on Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111470440.XA CN114143167B (en) | 2021-12-03 | 2021-12-03 | Light attenuation monitoring network safety method based on Bayesian network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114143167A true CN114143167A (en) | 2022-03-04 |
| CN114143167B CN114143167B (en) | 2023-06-20 |
Family
ID=80387812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111470440.XA Active CN114143167B (en) | 2021-12-03 | 2021-12-03 | Light attenuation monitoring network safety method based on Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114143167B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102299829A (en) * | 2011-09-01 | 2011-12-28 | 北京市天元网络技术股份有限公司 | Network failure probing and positioning method |
| CN106529582A (en) * | 2016-10-24 | 2017-03-22 | 杭州电子科技大学 | Prior probability assessment method aiming at introducing expert assessment in Bayesian network |
| CN108320040A (en) * | 2017-01-17 | 2018-07-24 | 国网重庆市电力公司 | Acquisition terminal failure prediction method and system based on Bayesian network optimization algorithm |
| CN109656239A (en) * | 2019-03-07 | 2019-04-19 | 长沙瑞纬电气有限公司 | A kind of rail locomotive network control system method for diagnosing faults and its diagnostic device |
| CN110781220A (en) * | 2019-09-20 | 2020-02-11 | 江苏欣皓测试技术有限公司 | Fault early warning method and device, storage medium and electronic equipment |
| CN110968061A (en) * | 2019-12-06 | 2020-04-07 | 珠海格力电器股份有限公司 | Equipment fault early warning method and device, storage medium and computer equipment |
| US20220357734A1 (en) * | 2019-07-05 | 2022-11-10 | Hitachi, Ltd. | Failure probability assessment system and method therefor |
-
2021
- 2021-12-03 CN CN202111470440.XA patent/CN114143167B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102299829A (en) * | 2011-09-01 | 2011-12-28 | 北京市天元网络技术股份有限公司 | Network failure probing and positioning method |
| CN106529582A (en) * | 2016-10-24 | 2017-03-22 | 杭州电子科技大学 | Prior probability assessment method aiming at introducing expert assessment in Bayesian network |
| CN108320040A (en) * | 2017-01-17 | 2018-07-24 | 国网重庆市电力公司 | Acquisition terminal failure prediction method and system based on Bayesian network optimization algorithm |
| CN109656239A (en) * | 2019-03-07 | 2019-04-19 | 长沙瑞纬电气有限公司 | A kind of rail locomotive network control system method for diagnosing faults and its diagnostic device |
| US20220357734A1 (en) * | 2019-07-05 | 2022-11-10 | Hitachi, Ltd. | Failure probability assessment system and method therefor |
| CN110781220A (en) * | 2019-09-20 | 2020-02-11 | 江苏欣皓测试技术有限公司 | Fault early warning method and device, storage medium and electronic equipment |
| CN110968061A (en) * | 2019-12-06 | 2020-04-07 | 珠海格力电器股份有限公司 | Equipment fault early warning method and device, storage medium and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 李涛: ""基于认知诊断的风电运维智能派遣机制研究"", 《CNKI》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114143167B (en) | 2023-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113556258B (en) | Anomaly detection method and device | |
| CN108494747B (en) | Digital substation flow abnormity detection method, electronic equipment and computer storage medium | |
| CN111768076B (en) | Monitoring alarm signal clustering method taking power grid event as center | |
| CN106932670B (en) | A kind of distribution power automation terminal method for diagnosing status based on D-S evidence theory | |
| CN111884840A (en) | IPRAN network equipment fault alarm merging analysis processing method and device | |
| CN109034400A (en) | A kind of substation's exception metric data predicting platform system | |
| CN111934434B (en) | Power distribution automation operation analysis and evaluation system and method | |
| CN112612669A (en) | Infrastructure monitoring and early warning method and system based on situation awareness | |
| CN116389223B (en) | Artificial intelligence visual early warning system and method based on big data | |
| CN107658980A (en) | A kind of analysis method and system for being used to check power system monitor warning information | |
| CN114328596A (en) | Bayes-based abnormal network flow backtracking method and system | |
| CN108521346B (en) | Method for positioning abnormal nodes of telecommunication bearer network based on terminal data | |
| CN114143167A (en) | Light attenuation monitoring network security method based on Bayesian network | |
| CN110513252B (en) | Wind power plant SCADA system data abnormity warning and repairing system and method | |
| CN102006613B (en) | Dual combined linear discrimination method of mobile core network failure data | |
| CN115550034B (en) | Service flow monitoring method and device for distribution network power monitoring system | |
| CN114598480B (en) | Method and system for processing machine data of network security operation platform | |
| CN115296846B (en) | Abnormal network flow backtracking method based on Markov chain | |
| CN113783710B (en) | Process layer network fault positioning method and device based on self-learning criteria | |
| CN114495007A (en) | Substation fault point monitoring method and device | |
| CN109803301B (en) | Offline identification management system for wireless network | |
| CN108365981B (en) | Method for realizing tracking of abnormal number or abnormal protocol of multiple signaling protocols | |
| CN105785949B (en) | A kind of binary channels molding machine processing quality parameter tracking system and its tracking | |
| Fei et al. | Research on intelligent diagnosis method of power grid fault components based on fault fingerprint technology | |
| CN106709158B (en) | Performance improvement method of power grid feeder automation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room 1308, 13th floor, East Tower, 33 Fuxing Road, Haidian District, Beijing 100036 Applicant after: China Telecom Digital Intelligence Technology Co.,Ltd. Address before: Room 1308, 13th floor, East Tower, 33 Fuxing Road, Haidian District, Beijing 100036 Applicant before: CHINA TELECOM GROUP SYSTEM INTEGRATION Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |