CN115022218A - Distributed Netconf protocol subscription alarm threshold setting method - Google Patents
Distributed Netconf protocol subscription alarm threshold setting method Download PDFInfo
- Publication number
- CN115022218A CN115022218A CN202210584807.9A CN202210584807A CN115022218A CN 115022218 A CN115022218 A CN 115022218A CN 202210584807 A CN202210584807 A CN 202210584807A CN 115022218 A CN115022218 A CN 115022218A
- Authority
- CN
- China
- Prior art keywords
- threshold
- alarm
- local
- central
- monitoring index
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 claims abstract description 92
- 238000012549 training Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000004931 aggregating effect Effects 0.000 claims abstract description 3
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000012423 maintenance Methods 0.000 description 9
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000006855 networking Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- 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
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/26—Special purpose or proprietary protocols or architectures
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Computing Systems (AREA)
- Computer Security & Cryptography (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Maintenance And Management Of Digital Transmission (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a distributed Netconf protocol subscription alarm threshold setting method, which starts by executing a central threshold model training through a central server and sends the central threshold model training to an ACS; after receiving the training start, the ACS accesses a model training identification field flag deployed in a local historical alarm database and judges whether to execute the following process; classifying and aggregating data in a local historical alarm database, training a central threshold model, submitting reasonable probability of monitoring index threshold values with optimal local corresponding types to a central server to update the central threshold model, and updating a local threshold database; and executing a program deployed in the local edge node server ACS to access the local threshold database to obtain a monitoring index threshold, and setting the monitoring index threshold for the Netconf event subscription message on the local threshold database. The invention overcomes the problem of model deviation and reduces the calculation complexity.
Description
Technical Field
The invention relates to the technical field of Netconf subscription alarm, in particular to a distributed Netconf protocol subscription alarm threshold setting method.
Background
With the gradual deepening of the digital development, the operation and maintenance equipment of each unit is gradually increased, the equipment is increased by 10-100 times compared with the equipment before ten years, and even if the operation and maintenance is developed from manual operation and maintenance to tool operation and maintenance and platform operation and maintenance, the operation and maintenance requirements of the current large-scale networking on the operation and maintenance supervision cannot be met. On such a large scale, managing monitored network devices through manual experience and automation becomes a technical bottleneck restricting operation and maintenance work. The threshold setting of the existing monitoring technology also mainly depends on manual experience, and the actual conditions of equipment and service operation cannot be comprehensively reflected. It is urgently needed to introduce a more intelligent and efficient method for setting a monitoring threshold of a network device to improve the monitoring operation and maintenance guarantee capability of managing the network device and to more comprehensively understand the actual operation condition of the monitored device, thereby effectively avoiding the problem that the monitored object causes important invisible problems due to excessive alarms.
Disclosure of Invention
Based on the above, the invention provides a distributed Netconf protocol subscription alarm threshold setting method, which highlights the rationality advantage of threshold setting in the process of monitoring a Netconf subscription alarm event by artificial intelligence, and carries out comprehensive data training on the threshold of a monitoring index corresponding to an edge node managed by a Netconf protocol, thereby obtaining the most reasonable probability of the alarm threshold of an edge node managed area, effectively overcoming the problem of model deviation and reducing the computational complexity.
In order to achieve the purpose, the invention adopts the following technical scheme: a distributed Netconf protocol subscription alarm threshold setting method specifically comprises the following steps:
step S1, executing a central threshold model training starting instruction through a central server program deployed in headquarters, and issuing the training starting instruction to a local edge node server ACS;
step S2, after receiving the training start instruction, the local edge node server ACS accesses a model training identification field flag deployed in the local historical alarm database, and judges whether to execute step S3 according to the value of the model training identification field flag;
step S3, classifying and aggregating the data in the local historical alarm database according to the monitoring indexes, training a central threshold model, and obtaining the optimal threshold reasonable probability of the monitoring indexes with the corresponding types;
step S4, submitting the optimal reasonable probability of the monitoring index threshold value of the corresponding type of the local to a central server to update a central threshold value model, and updating a local threshold value database;
step S5, the program deployed in the local edge node server ACS executes access to the local threshold database to obtain the monitoring index threshold, and sets the monitoring index item for the [ ColumnName ] field in the Netconf event subscription message in the subscription monitoring event [ ColumnCondition ] tag, and sets the threshold of the monitoring index for the [ ColumnValue ] field, thereby completing the monitoring and threshold setting process.
Further, the local edge node server ACS adopts a network device supporting the Netconf protocol.
Further, if the value of the model training flag field flag is not 0, executing step S3; otherwise, sending a central threshold model instruction to the central server, and sending the central threshold model to the local edge node server ACS after the central server receives the instruction.
Further, the central threshold model specifically includes:
ZY(D|+) = ZY(+|D)ZY(D)/(ZY(+|D)ZY(D)+ZY(+|N)ZY(N))
the ZY (D) marks the probability that the historical alarm data of the monitoring index type is close to the real without considering the false alarm rate, ZY (D | +) represents the optimal threshold reasonable probability of the monitoring index type, ZY (+ | D) represents the accuracy of the threshold setting of the monitoring index, ZY (+ | N) represents the alarm data false alarm rate of the same type of monitoring index, and ZY (N) represents the unreasonable probability of the threshold setting of the same type of monitoring index.
Further, the monitoring index includes: CPU utilization rate, memory utilization rate, flow size and hard disk space size.
Further, the training process of the central threshold model specifically includes: the prior probability, the conditional probability, the adjusting factor and the posterior probability are input into a central threshold model for training, the local reasonable probability of the monitoring index threshold of the type is obtained through training, and the reasonable probability of the optimal monitoring index threshold of the corresponding type is obtained after each monitoring index is balanced according to the adjusting factor.
Further, the prior probability is the total number of alarm data of the monitoring indexes of the same type.
Further, the conditional probability is obtained by performing data statistics on the historical data of the monitoring indexes of the same type according to the alarm level, the content and the alarm duration to obtain the training conditional probability.
Further, the adjustment factor is a ratio of the number of times of false alarm of the historical data of the monitoring index to the prior probability.
Further, the posterior probability is the product of the prior probability and the adjustment factor.
Compared with the prior art, the invention has the following beneficial effects: the scheme highlights the advantage of reasonability of threshold setting of artificial intelligence in the process of monitoring the Netconf subscription alarm event, effectively solves the problems of unreasonableness and particularity of unified threshold setting caused by different businesses and monitored objects in various regions of the existing network distributed edge node Netconf protocol management and monitoring network equipment. And meanwhile, comprehensive data training is carried out on the threshold of the monitoring index corresponding to the edge node managed by the Netconf protocol, so that the most reasonable probability of the alarm threshold of the area managed by the edge node is obtained. The invention effectively overcomes the problem of central threshold model deviation and reduces the calculation complexity.
Drawings
Fig. 1 is a flowchart of a distributed Netconf protocol subscription alarm threshold setting method of the present invention.
Detailed Description
The technical solution of the present invention is further explained below with reference to the accompanying drawings.
The invention manages the CPE of the non-edge node network equipment of each region through the Netconf protocol and sets a subscription monitoring event; each local edge node server ACS adopts network equipment supporting Netconf protocol. The method comprises the steps of obtaining a threshold value of each monitoring index through a local historical threshold value database, executing a 'ColumnCondition' field monitoring threshold value of each monitoring index of a subscription monitoring event through an ACS program of a local edge node server, and setting, wherein in the monitoring process, monitoring data exceed the set value of the monitoring index threshold value, a monitoring alarm event is triggered, the problem of central threshold value model deviation can be effectively solved, and the calculation complexity is reduced.
Fig. 1 is a flowchart of a distributed Netconf protocol subscription alarm threshold setting method of the present invention, and the distributed Netconf protocol subscription alarm threshold setting method specifically includes the following steps:
step S1, executing a central threshold model training starting command through a central server program deployed in headquarters, and issuing the training starting command to the ACS;
step S2, after receiving the training start instruction, the local edge node server ACS accesses a model training identification field flag deployed in the local historical alarm database, and judges whether to execute step S3 according to the value of the model training identification field flag; specifically, if the value of the model training flag field flag is not 0, which indicates that the central threshold model is not trained for the first time, step S3 is executed; otherwise, sending a central threshold model instruction to the central server, and sending the central threshold model to the local edge node server ACS after the central server receives the instruction. Through the distributed training central threshold model, the problems of irrationality and particularity of unified threshold setting caused by different local services and monitored objects of the conventional networking distributed edge node Netconf protocol management and monitoring network equipment are effectively solved.
Step S3, performing classification and aggregation on the data in the local historical alarm database according to the monitoring indexes to form real and effective analysis data of the central threshold model, specifically, performing classification on all the data in the local historical alarm database according to the monitoring indexes through a program deployed by the ACS of each local edge node server, where the classification basis includes: the alarm level, content and alarm duration are classified into the following monitoring indexes: and data sets of CPU utilization rate, memory utilization rate, flow rate and hard disk space size. And training the central threshold model according to the monitoring indexes to obtain the optimal reasonable threshold probability of the monitoring indexes of the corresponding types.
The central threshold model in the invention is specifically as follows:
ZY(D|+) = ZY(+|D)ZY(D)/(ZY(+|D)ZY(D)+ZY(+|N)ZY(N))
ZY (D) marks the probability that the historical alarm data of the monitoring index type is close to the real data without considering the false alarm rate; ZY (D | +) represents the optimal threshold reasonable probability of the monitoring index type; ZY (+ | D) represents the accuracy of the threshold setting of the monitoring index, namely 1-false alarm rate; ZY (+ | N) represents the false alarm rate of alarm data of the same type of monitoring index, namely the ratio of the alarm false alarm times of the same type of monitoring index to the total alarm number of the same type; ZY (N) represents the unreasonable probability of the same type of monitoring index threshold setting, i.e., 1-ZY (D).
The training process of the central threshold model in the invention specifically comprises the following steps: and inputting the prior probability, the conditional probability, the adjustment factor and the posterior probability into a central threshold model for training, obtaining the local reasonable probability of the monitoring index threshold of the type through training, and obtaining the optimal reasonable probability of the monitoring index threshold of the corresponding type after balancing each monitoring index according to the adjustment factor.
The prior probability is the total number of alarm data of the same type of monitoring indexes; the conditional probability is that the same type of monitoring index historical data is subjected to data statistics according to the alarm level, the content and the alarm duration to obtain the training conditional probability; the adjustment factor is the ratio of the alarm false alarm times of the historical data of the monitoring index to the prior probability; the posterior probability in the invention is the product of the prior probability and the adjusting factor.
And step S4, submitting the reasonable probability of the monitoring index threshold with the optimal local corresponding type to a central server to update a central threshold model, updating a local threshold database, and after storing the updated monitoring index after each training, executing a new round of central threshold model training again by a central server program.
Step S5, the program deployed in the local edge node server ACS executes access to the local threshold database to obtain the monitoring index threshold, and sets the monitoring index item for the [ ColumnName ] field in the Netconf event subscription message in the subscription monitoring event [ ColumnCondition ] tag, and sets the threshold of the monitoring index for the [ ColumnValue ] field, thereby completing the monitoring and threshold setting process. In the monitoring process, the monitoring data exceeds the set value of the monitoring index threshold value, the monitoring alarm event is triggered, the problem of central threshold value model deviation can be effectively solved, and the calculation complexity is reduced.
The distributed Netconf protocol subscription alarm threshold setting method highlights the advantage of reasonability of threshold setting in the process of monitoring the Netconf subscription alarm event by artificial intelligence, and effectively solves the problems of irrationality and particularity of unified threshold setting caused by different local services and monitored objects of the conventional network distributed edge node Netconf protocol management and monitoring network equipment. Meanwhile, comprehensive data training is carried out on the threshold of the monitoring index corresponding to the local edge node managed by the Netconf protocol, so that the most reasonable probability of the alarm threshold of the edge node managed area is obtained, the problem of central threshold model deviation is effectively solved, and the calculation complexity is reduced.
The above is only a preferred embodiment of the present invention, and the scope of the present invention is not limited to the above embodiment, and any technical solutions that fall under the spirit of the present invention fall within the scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (10)
1. A distributed Netconf protocol subscription alarm threshold setting method is characterized by specifically comprising the following steps:
step S1, executing a central threshold model training starting instruction through a central server program deployed in headquarters, and issuing the training starting instruction to a local edge node server ACS;
step S2, after receiving the training start instruction, the ACS accesses a model training identification field flag deployed in a local historical alarm database, and judges whether to execute step S3 according to the value of the model training identification field flag;
step S3, classifying and aggregating the data in the local historical alarm database according to the monitoring indexes, training a central threshold model, and obtaining the optimal threshold reasonable probability of the monitoring indexes with the corresponding types;
step S4, submitting the reasonable probability of the monitoring index threshold with the optimal local corresponding type to a central server to update a central threshold model, and updating a local threshold database;
step S5, accessing a local threshold database through program execution of the ACS deployed in the local edge node server to obtain a monitoring index threshold, setting a monitoring index item for a [ ColumnName ] field in a subscription monitoring event [ columnCondition ] tag in a Netconf event subscription message on the local threshold database, setting a threshold of a monitoring index for the [ ColumnValue ] field, and completing monitoring and threshold setting processes.
2. The distributed Netconf protocol subscription alarm threshold setting method of claim 1, wherein the local edge node server ACS employs a network device supporting the Netconf protocol.
3. The distributed Netconf protocol subscription alarm threshold setting method of claim 1, wherein if the value of the model training flag field flag is not 0, the step S3 is executed; otherwise, sending a central threshold model instruction to the central server, and sending the central threshold model to the local edge node server ACS after the central server receives the instruction.
4. The method for setting the alarm threshold for the subscription of the distributed Netconf protocol according to claim 1, wherein the central threshold model is specifically:
ZY(D|+) = ZY(+|D)ZY(D)/(ZY(+|D)ZY(D)+ZY(+|N)ZY(N))
the ZY (D) marks the probability that the historical alarm data of the monitoring index type is close to the real without considering the false alarm rate, ZY (D | +) represents the optimal threshold reasonable probability of the monitoring index type, ZY (+ | D) represents the accuracy of the threshold setting of the monitoring index, ZY (+ | N) represents the alarm data false alarm rate of the same type of monitoring index, and ZY (N) represents the unreasonable probability of the threshold setting of the same type of monitoring index.
5. The method for setting the alarm threshold value of the distributed Netconf protocol subscription according to claim 1, wherein the monitoring index comprises: CPU utilization rate, memory utilization rate, flow size and hard disk space size.
6. The method for setting the distributed Netconf protocol subscription alarm threshold according to claim 1, wherein the training process of the central threshold model specifically comprises: and inputting the prior probability, the conditional probability, the adjustment factor and the posterior probability into a central threshold model for training, obtaining the local reasonable probability of the monitoring index threshold of the type through training, and obtaining the optimal reasonable probability of the monitoring index threshold of the corresponding type after balancing each monitoring index according to the adjustment factor.
7. The method of claim 6, wherein the prior probability is a total number of alarm data of the same type of monitoring index.
8. The method for setting the subscription alarm threshold of the distributed Netconf protocol according to claim 6, wherein the conditional probability is obtained by performing data statistics on historical data of monitoring indexes of the same type according to alarm levels, contents and alarm durations to obtain the conditional probability of the training.
9. The method for setting the alarm threshold value for the subscription of the distributed Netconf protocol according to claim 6, wherein the adjustment factor is a ratio of the number of alarm false alarms of the historical data of the monitoring index to the prior probability.
10. The method of claim 6, wherein the posterior probability is a product of a prior probability and an adjustment factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210584807.9A CN115022218B (en) | 2022-05-27 | 2022-05-27 | Distributed Netconf protocol subscription alarm threshold setting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210584807.9A CN115022218B (en) | 2022-05-27 | 2022-05-27 | Distributed Netconf protocol subscription alarm threshold setting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115022218A true CN115022218A (en) | 2022-09-06 |
| CN115022218B CN115022218B (en) | 2024-01-19 |
Family
ID=83070667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210584807.9A Active CN115022218B (en) | 2022-05-27 | 2022-05-27 | Distributed Netconf protocol subscription alarm threshold setting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115022218B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115665590A (en) * | 2022-10-21 | 2023-01-31 | 北京中电飞华通信有限公司 | Internet of things data acquisition system and method based on eSIM card and 5G communication |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109582529A (en) * | 2018-09-29 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of setting method and device of alarm threshold value |
| CN110489306A (en) * | 2019-08-26 | 2019-11-22 | 北京博睿宏远数据科技股份有限公司 | A kind of alarm threshold value determines method, apparatus, computer equipment and storage medium |
| WO2020244336A1 (en) * | 2019-06-04 | 2020-12-10 | 深圳前海微众银行股份有限公司 | Alarm classification method and device, electronic device, and storage medium |
| CN113886173A (en) * | 2021-08-29 | 2022-01-04 | 苏州浪潮智能科技有限公司 | Method, device and equipment for monitoring multi-node distributed cluster and readable medium |
| CN114172786A (en) * | 2021-12-03 | 2022-03-11 | 中国电信集团系统集成有限责任公司 | Method and device for dynamically adjusting network monitoring threshold based on TR069 protocol and NETCONF protocol |
| CN114167181A (en) * | 2021-12-03 | 2022-03-11 | 中国电信集团系统集成有限责任公司 | Method and system for monitoring local and allopatric line fault tracing |
| CN114301817A (en) * | 2021-12-17 | 2022-04-08 | 中电信数智科技有限公司 | Equipment monitoring threshold setting method and system based on Netconf protocol |
| CN114358312A (en) * | 2021-12-31 | 2022-04-15 | 中国联合网络通信集团有限公司 | Training method, equipment and storage medium of network alarm event recognition model |
-
2022
- 2022-05-27 CN CN202210584807.9A patent/CN115022218B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109582529A (en) * | 2018-09-29 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of setting method and device of alarm threshold value |
| WO2020244336A1 (en) * | 2019-06-04 | 2020-12-10 | 深圳前海微众银行股份有限公司 | Alarm classification method and device, electronic device, and storage medium |
| CN110489306A (en) * | 2019-08-26 | 2019-11-22 | 北京博睿宏远数据科技股份有限公司 | A kind of alarm threshold value determines method, apparatus, computer equipment and storage medium |
| CN113886173A (en) * | 2021-08-29 | 2022-01-04 | 苏州浪潮智能科技有限公司 | Method, device and equipment for monitoring multi-node distributed cluster and readable medium |
| CN114172786A (en) * | 2021-12-03 | 2022-03-11 | 中国电信集团系统集成有限责任公司 | Method and device for dynamically adjusting network monitoring threshold based on TR069 protocol and NETCONF protocol |
| CN114167181A (en) * | 2021-12-03 | 2022-03-11 | 中国电信集团系统集成有限责任公司 | Method and system for monitoring local and allopatric line fault tracing |
| CN114301817A (en) * | 2021-12-17 | 2022-04-08 | 中电信数智科技有限公司 | Equipment monitoring threshold setting method and system based on Netconf protocol |
| CN114358312A (en) * | 2021-12-31 | 2022-04-15 | 中国联合网络通信集团有限公司 | Training method, equipment and storage medium of network alarm event recognition model |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115665590A (en) * | 2022-10-21 | 2023-01-31 | 北京中电飞华通信有限公司 | Internet of things data acquisition system and method based on eSIM card and 5G communication |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115022218B (en) | 2024-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220207434A1 (en) | Model training method, apparatus, and system | |
| US20220121994A1 (en) | Method and apparatus for implementing model training, and computer storage medium | |
| CN108415789B (en) | Node fault prediction system and method for large-scale hybrid heterogeneous storage system | |
| CN110351150A (en) | Fault rootstock determines method and device, electronic equipment and readable storage medium storing program for executing | |
| US20220179884A1 (en) | Label Determining Method, Apparatus, and System | |
| CN107070692A (en) | A kind of cloud platform monitoring service system analyzed based on big data and method | |
| CN110166290A (en) | Alarm method and device based on journal file | |
| CN104021195B (en) | Warning association analysis method based on knowledge base | |
| CN104468220B (en) | Power telecom network early warning control platform | |
| CN105721194B (en) | Mobile network potential faults intelligent positioning system | |
| CN107302449A (en) | Intelligent monitoring statistics and alarm processing system and method | |
| CN106844161A (en) | Abnormal monitoring and Forecasting Methodology and system in a kind of carrier state stream calculation system | |
| CN113542039A (en) | Method for positioning 5G network virtualization cross-layer problem through AI algorithm | |
| TWI684139B (en) | System and method of learning-based prediction for anomalies within a base station | |
| CN115022218A (en) | Distributed Netconf protocol subscription alarm threshold setting method | |
| CN115033450A (en) | Bayesian cluster monitoring early warning analysis method based on distribution | |
| CN108170702A (en) | A kind of power communication alarm association model based on statistical analysis | |
| US20210097432A1 (en) | Gpu code injection to summarize machine learning training data | |
| CN115001989A (en) | Equipment early warning method, device, equipment and readable storage medium | |
| CN110647086B (en) | Intelligent operation and maintenance monitoring system based on operation big data analysis | |
| CN117216713A (en) | Fault delimiting method, device, electronic equipment and storage medium | |
| CN106649034A (en) | Visual intelligent operation and maintenance method and platform | |
| CN116545867A (en) | Method and device for monitoring abnormal performance index of network element of communication network | |
| CN110045197A (en) | A kind of Distribution Network Failure method for early warning | |
| CN114443738A (en) | Abnormal data mining method, device, equipment and medium |
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 |