CN112488326A - Intelligent operation and maintenance fault early warning method and device based on 5G core network - Google Patents
Intelligent operation and maintenance fault early warning method and device based on 5G core network Download PDFInfo
- Publication number
- CN112488326A CN112488326A CN202011236167.XA CN202011236167A CN112488326A CN 112488326 A CN112488326 A CN 112488326A CN 202011236167 A CN202011236167 A CN 202011236167A CN 112488326 A CN112488326 A CN 112488326A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- early warning
- characteristic data
- time point
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012423 maintenance Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims description 37
- 238000012549 training Methods 0.000 claims description 36
- 238000012795 verification Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000001502 supplementing effect Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000001934 delay Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an intelligent operation and maintenance fault early warning method and device based on a 5G core network, wherein the method is based on past network performance characteristics and corresponding fault characteristics as historical data to be processed, a fault early warning model is trained, the fault early warning model of a component can input network performance data at any moment to predict whether a fault occurs at the next moment, and fault early warning analysis can be effectively carried out.
Description
Technical Field
The invention relates to the technical field of electronic information, in particular to an intelligent operation and maintenance fault early warning method and device based on a 5G core network.
Background
The core network is located in the center of network data interaction and is mainly responsible for mobility management, session management and data transmission of end users. The 4G core network mainly includes network elements such as mme (mobility Management entity), SGW (Serving GateWay), PGW (PDN GateWay), hss (home Subscriber server), and the like. The SGW and the PGW not only need to process and forward user plane data, but also need to be responsible for performing control plane functions such as session management and bearer control, and the defects of the user plane and control plane interleaving lead to the problems of complex service change, difficult efficiency optimization, and great difficulty in deployment, operation and maintenance.
The 5G core network adopts a service-based architecture (SBA), introduces virtualization, separates a control plane from a user plane, separates calculation and storage, comprehensively supports network slicing, and can open an interface for a third party. The traditional network element is a tightly-coupled black box design combining software and hardware, software and hardware are decoupled after virtualization is introduced, the hardware is free from the constraint of special equipment, a universal server is used, and the cost is greatly reduced. Meanwhile, software does not pay attention to bottom hardware any more, and expandability is greatly improved. By using the architecture of micro-services in an IT system for reference, large single software is further decomposed into a plurality of small modular components, the components are called Network Function Services (NFS), are highly independent and autonomous, communicate with each other through an open interface, and can be combined into a large Network Function (NF) like building blocks, so that the agility and the elasticity of service deployment are improved. Each network function is logically equivalent to a network element, and the functions are completely independent and autonomous, and other functions cannot be influenced no matter the functions are newly added, upgraded or expanded, so that great convenience is provided for upgrading and expanding the network.
The operation and maintenance of the 5G core network plans information, networks and services according to service requirements, and the services are in a long-term stable and usable state through means of network monitoring, event early warning, service scheduling, troubleshooting upgrading and the like. Most of the early operation and maintenance work is manually completed by operation and maintenance personnel, and the operation and maintenance mode is not only inefficient, but also consumes a large amount of human resources. The method is limited by the physiological limit and the cognition limit of human, cannot continuously provide high-quality operation and maintenance service for a large-scale and high-complexity system, and is lack of early warning analysis on network faults in advance.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide an intelligent operation and maintenance fault early warning method and device based on a 5G core network, which can solve the problem that the traditional 5G core network cannot perform fault early warning analysis at the next moment aiming at the current data.
In the first aspect, the invention is realized by adopting the following technical scheme:
the intelligent operation and maintenance fault early warning method based on the 5G core network comprises the following steps:
acquiring historical data corresponding to a plurality of time points respectively, wherein the historical data comprises network performance characteristic data and fault characteristic data; the time intervals between every two adjacent time points are first preset time lengths; the network performance characteristic data comprises at least one performance characteristic data;
replacing corresponding fault characteristic data at any time point with corresponding fault characteristic data at a next time point corresponding to the time point to form fitting data respectively corresponding to each time point, wherein the fitting data comprise network performance characteristic data and fault characteristic data of the next time point;
training according to the fitting data to obtain a fault early warning model, collecting index data at each moment in real time, inputting the index data into the fault early warning model, and outputting fault characteristic data at the next moment corresponding to the moment; and each adjacent moment is spaced by a second preset time length.
In a preferred embodiment, the network performance characteristic data includes at least one of time, request times, success rate, rejection times, no response times, and response time delay.
In a preferred embodiment, the fault signature data includes 1 and 0, where 1 indicates that the data is normal and 0 indicates that the data is abnormal.
As a preferred embodiment, the method for forming the fitting data corresponding to each time segment and training the obtained fault early warning model further comprises the following steps:
performing feature processing on the fitting data, wherein the feature processing comprises:
when the fault characteristic data corresponding to the time point is judged to be missing, deleting the fitting data of the time point or actively supplementing the missing fault characteristic data;
deleting useless performance characteristic data in the network performance characteristic data;
and adding other performance characteristic data to the network performance characteristic data at the corresponding time point.
In a preferred embodiment, the added other performance characteristic data includes at least one of the number of users, the number of requests, and the requesting users.
As a preferred embodiment, training to obtain a fault early warning model according to the fitting data includes:
selecting one part from the fitting data as training data, and using the other part as verification data;
and training according to the training data to obtain a plurality of fault early warning models, and inputting the verification data into all the fault early warning models to verify to obtain an optimal fault early warning model.
In a preferred embodiment, the ratio of the training data to the fitting data is 75%, and the ratio of the validation data to the fitting data is 25%.
In the second aspect, the invention is realized by adopting the following technical scheme:
intelligent operation and maintenance fault early warning device based on 5G core network includes:
a data acquisition module: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring historical data corresponding to a plurality of time points respectively, and the historical data comprises network performance characteristic data and fault characteristic data; the time intervals between every two adjacent time points are first preset time lengths; the network performance characteristic data comprises at least one performance characteristic data;
a data processing module: the system comprises a data processing unit, a data processing unit and a data processing unit, wherein the data processing unit is used for replacing corresponding fault characteristic data at any time point with corresponding fault characteristic data at the next time point corresponding to the time point according to the corresponding fault characteristic data at the time point to form fitting data corresponding to each time point, and the fitting data comprises network performance characteristic data and fault characteristic data at the next time point;
a model construction module: the fault early warning module is used for obtaining a fault early warning model according to the fitting data training, collecting index data at each moment in real time and inputting the index data into the fault early warning model so as to output fault characteristic data at the next moment corresponding to the moment; and each adjacent moment is spaced by a second preset time length.
In a preferred embodiment, the network performance characteristic data includes at least one of time, request times, success rate, rejection times, no response times, and response time delay.
In a preferred embodiment, the fault signature data includes 1 and 0, where 1 indicates that the data is normal and 0 indicates that the data is abnormal.
As a preferred embodiment, a feature processing module is further included between the data processing module and the model building module: for performing feature processing on the fitting data, the feature processing comprising:
when the fault characteristic data corresponding to the time point is judged to be missing, deleting the fitting data of the time point or actively supplementing the missing fault characteristic data;
deleting useless performance characteristic data in the network performance characteristic data;
and adding other performance characteristic data to the network performance characteristic data at the corresponding time point.
In a preferred embodiment, the added other performance characteristic data includes at least one of the number of users, the number of requests, and the requesting users.
As a preferred embodiment, in the model building module, training the fault early warning model according to the fitting data includes:
selecting one part from the fitting data as training data, and using the other part as verification data;
and training according to the training data to obtain a plurality of fault early warning models, and inputting the verification data into all the fault early warning models to verify to obtain an optimal fault early warning model.
In a preferred embodiment, the ratio of the training data to the fitting data is 75%, and the ratio of the validation data to the fitting data is 25%.
In a third aspect, the invention is realized by adopting the following technical scheme:
an electronic device having a processor, a memory, and a computer readable program stored in the memory and executable by the processor, the computer readable program, when executed by the processor, implementing a fault pre-warning method as set forth in any one of the first aspects of the invention.
In the fourth aspect, the invention is realized by adopting the following technical scheme:
a computer storage medium having a computer readable program stored thereon which is executable by a processor, wherein the computer readable program, when executed by the processor, implements a fault pre-warning method as set forth in any one of the first aspects of the invention.
Compared with the prior art, the invention has the beneficial effects that:
the intelligent operation and maintenance fault early warning method disclosed by the invention is based on past network performance characteristics and corresponding fault characteristics as historical data to be processed, a fault early warning model is trained, the network performance data at any moment can be input through the fault early warning model of the component to predict whether a fault occurs at the next moment, and the fault early warning analysis can be effectively carried out.
Drawings
Fig. 1 is a schematic flow chart of a fault early warning method based on a 5G core network according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a fault early warning apparatus based on a 5G core network according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, article, or article that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or article.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention discloses an intelligent operation and maintenance fault early warning method and device based on a 5G core network, which can be used for processing historical data based on past network performance characteristics and corresponding fault characteristics, training a fault early warning model, inputting network performance data at any moment through the fault early warning model of a component to predict whether a fault occurs at the next moment, and effectively performing fault early warning analysis.
Referring to fig. 1, fig. 1 is a schematic flow chart of an intelligent operation and maintenance fault early warning method based on a 5G core network according to an embodiment of the present invention. As shown in fig. 1, the intelligent operation and maintenance fault early warning method includes the following operations:
101: acquiring historical data corresponding to a plurality of time points respectively, wherein the historical data comprises network performance characteristic data and fault characteristic data; the time intervals between every two adjacent time points are first preset time lengths; the network performance characteristic data comprises at least one performance characteristic data.
In a 5G core network, information, networks, services and the like are planned according to business requirements, the services are in a long-term stable and usable state through means of network monitoring, event early warning, business scheduling, troubleshooting upgrading and the like, and most of early operation and maintenance work is finished manually. The embodiment of the invention provides a fault early warning method, which aims to combine historical data to process and model data, predict whether the same network performance characteristic data will have faults at the next moment through a constructed fault model, and early warn other prevention and control in advance, so that operation and maintenance instructions are improved.
The embodiment of the invention summarizes and combines the XGB and other artificial intelligent algorithms to construct and analyze the network fault early warning model.
In this step, history data is acquired. For the acquisition of the historical data, the embodiment of the present invention sets and selects to acquire one historical data every first preset time, and as an optimization, the first preset time may be 1 hour. For example, if the history data of the first time point is acquired and then the history data of the second time point is acquired, the interval between the first time point and the second time point is 1 hour.
As a preferred implementation manner, the network performance characteristic data may include at least one of time, request times, success rate, rejection times, no-response times, and response time delay in the embodiment of the present invention. In another aspect, the fault signature data includes 1 and 0, where 1 indicates that the data is normal and 0 indicates that the data is abnormal.
102: and replacing the corresponding fault characteristic data at any time point with the corresponding fault characteristic data at the next time point corresponding to the time point to form fitting data respectively corresponding to each time point, wherein the fitting data comprises network performance characteristic data and the fault characteristic data at the next time point.
This step actually processes the historical data. The network performance characteristic data of each time point t is taken as an input of the XGBOOST model and is denoted as (X1t, X2 t.., Xnt), where n is the nth performance characteristic data in the network performance data. The fault feature data corresponding to the time point t is denoted as Yt, and the fault feature data at the next time is Yt + 1. Since the purpose of the embodiment of the present invention is to predict the fault feature data at the next time according to the network performance feature data at the current time, the fault feature data Yt +1 at the next time is replaced with the fault feature data Yt at the current time.
See tables 1 and 2:
TABLE 1
TABLE 2
Table 1 is historical data at a corresponding time point, which includes network performance characteristic data and fault characteristic data, and table 2 is processed fitting data, that is, Yt +1 in table 1 has been replaced by Yt, and fault characteristic data corresponding to a next time is replaced by fault characteristic data at a previous time. Since the historical data of five time points are selected in the total table, the fault characteristic data of the 5 th time point is replaced by the fault characteristic data of the 6 th time point, and therefore the fault condition occurs.
103: training according to the fitting data to obtain a fault early warning model, collecting index data at each moment in real time, inputting the index data into the fault early warning model, and outputting fault characteristic data at the next moment corresponding to the moment; and each adjacent moment is spaced by a second preset time length.
And predicting whether a network fault occurs at the next moment by using the finally obtained fault early warning model according to the network performance index data collected in real time. The second preset duration in this step may be equal to or different from the first preset duration, and even the second preset duration may be set to be extremely small. The index data in this step is the same as the data actually included in the network performance index data in the history data in step 101, and only the specific numerical value may be different according to different times.
The above is the basic scheme of the fault early warning method disclosed by the embodiment of the invention. As a further improvement and supplement to the embodiment of the present invention, further, between forming fitting data respectively corresponding to each time period and training the obtained fault early warning model, the method further includes the following steps:
performing feature processing on the fitting data, wherein the feature processing comprises:
when the fault characteristic data corresponding to the time point is judged to be missing, deleting the fitting data of the time point or actively supplementing the missing fault characteristic data;
deleting useless performance characteristic data in the network performance characteristic data;
and adding other performance characteristic data to the network performance characteristic data at the corresponding time point.
The above steps are further completed for step 102, for example, the fault feature data of the fifth time point is missing in table 2, and through this step, the fault feature data can be filled up, or the history data corresponding to the time point can be directly deleted.
The useless performance characteristic data is judged by combining the past experience for example, and the data is deleted actively. The addition of other performance characteristic data is mainly used for discovering that other data has influence on the fault characteristic, and the data is not contained in the existing network performance characteristic data and is actively supplemented, wherein the performance characteristic data comprises at least one of the number of users, the request times and the request users. As shown in table 3 below:
TABLE 3
Further, training the fault early warning model according to the fitting data includes:
selecting one part from the fitting data as training data, and using the other part as verification data;
and training according to the training data to obtain a plurality of fault early warning models, and inputting the verification data into all the fault early warning models to verify to obtain an optimal fault early warning model.
Wherein the proportion of the training data in the fitting data is 75%, and the proportion of the verification data in the fitting data is 25%.
And constructing a plurality of fault early warning models through training data, wherein the input of verification data is used for selecting an optimal fault model from the plurality of fault models, and carrying out model scoring on the plurality of fault early warning models. Wherein model evaluation is performed by calculating accuracy and recall.
The recall rate is how many positive samples are predicted correctly, and the accuracy rate is how many positive samples are predicted correctly. The calculation formula is as follows: r ═ TP/(TP + FN); p ═ TP/(TP + FP), where TP represents the true positive sample, and the correctly predicted positive sample, i.e. the comparison result is consistent with the fault signature data in the true historical data. TN is a true negative sample, i.e., the negative sample is correctly predicted as a negative sample. FP is a false positive sample, i.e. negative samples are mispredicted as positive samples, FN is a false negative sample, i.e. positive samples are mispredicted as negative samples. Positive and negative examples represent two types of faults in embodiments of the invention.
Example two
Fig. 2 shows a schematic structural diagram of a fault early warning device based on a 5G core network according to an embodiment of the present invention. As shown in fig. 2, the fault early warning device of the present invention includes the following schemes:
fault early warning device based on 5G core network includes: a data acquisition module 201, a data processing module 202 and a model construction module 203. Wherein:
the data acquisition module 201: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring historical data corresponding to a plurality of time points respectively, and the historical data comprises network performance characteristic data and fault characteristic data; the time intervals between every two adjacent time points are first preset time lengths; the network performance characteristic data comprises at least one performance characteristic data;
the data processing module 202: the system comprises a data processing unit, a data processing unit and a data processing unit, wherein the data processing unit is used for replacing corresponding fault characteristic data at any time point with corresponding fault characteristic data at the next time point corresponding to the time point according to the corresponding fault characteristic data at the time point to form fitting data corresponding to each time point, and the fitting data comprises network performance characteristic data and fault characteristic data at the next time point;
the model building module 203: the fault early warning module is used for obtaining a fault early warning model according to the fitting data training, collecting index data at each moment in real time and inputting the index data into the fault early warning model so as to output fault characteristic data at the next moment corresponding to the moment; and each adjacent moment is spaced by a second preset time length.
In a preferred embodiment, the network performance characteristic data includes at least one of time, request times, success rate, rejection times, no response times, and response time delay. The fault characteristic data comprises 1 and 0, wherein 1 represents that the data is normal, and 0 represents that the data is abnormal.
In a preferred embodiment, the data processing module 202 and the model building module 203 further include a feature processing module: for performing feature processing on the fitting data, the feature processing comprising: when the fault characteristic data corresponding to the time point is judged to be missing, deleting the fitting data of the time point or actively supplementing the missing fault characteristic data; deleting useless performance characteristic data in the network performance characteristic data; and adding other performance characteristic data to the network performance characteristic data at the corresponding time point.
In a preferred embodiment, the added other performance characteristic data includes at least one of the number of users, the number of requests, and the requesting users.
As a preferred embodiment, in the model building module, training the fault early warning model according to the fitting data includes: selecting one part from the fitting data as training data, and using the other part as verification data; and training according to the training data to obtain a plurality of fault early warning models, and inputting the verification data into all the fault early warning models to verify to obtain an optimal fault early warning model. Preferably, the proportion of the training data in the fitting data is 75%, and the proportion of the verification data in the fitting data is 25%.
EXAMPLE III
The embodiment of the invention discloses an electronic device, which is provided with a processor, a memory and a computer readable program stored in the memory and capable of being executed by the processor, wherein when the computer readable program is executed by the processor, the fault early warning method is realized.
Example four
The embodiment of the invention discloses a computer storage medium, on which a computer readable program executable by a processor is stored, wherein the computer readable program is used for implementing the fault early warning method according to any one of the first aspect of the invention when being executed by the processor.
Various other modifications and changes may be made by those skilled in the art based on the above-described technical solutions and concepts, and all such modifications and changes should fall within the scope of the claims of the present invention.
Claims (10)
1. The intelligent operation and maintenance fault early warning method based on the 5G core network is characterized by comprising the following steps:
acquiring historical data corresponding to a plurality of time points respectively, wherein the historical data comprises network performance characteristic data and fault characteristic data; the time intervals between every two adjacent time points are first preset time lengths; the network performance characteristic data comprises at least one performance characteristic data;
replacing corresponding fault characteristic data at any time point with corresponding fault characteristic data at a next time point corresponding to the time point to form fitting data respectively corresponding to each time point, wherein the fitting data comprise network performance characteristic data and fault characteristic data of the next time point;
training according to the fitting data to obtain a fault early warning model, collecting index data at each moment in real time, inputting the index data into the fault early warning model, and outputting fault characteristic data at the next moment corresponding to the moment; and each adjacent moment is spaced by a second preset time length.
2. The intelligent operation and maintenance fault pre-warning method according to claim 1, wherein the network performance characteristic data comprises at least one of time, request times, success rates, rejection times, no-response times and response time delays.
3. The intelligent operation and maintenance fault early warning method according to claim 1 or 2, wherein the fault feature data comprises 1 and 0, wherein 1 represents that the data is normal, and 0 represents that the data is abnormal.
4. The intelligent operation and maintenance fault early warning method as claimed in claim 2, wherein fitting data corresponding to each time period is formed and a fault early warning model is obtained through training, and the method further comprises the following steps:
performing feature processing on the fitting data, wherein the feature processing comprises:
when the fault characteristic data corresponding to the time point is judged to be missing, deleting the fitting data of the time point or actively supplementing the missing fault characteristic data;
deleting useless performance characteristic data in the network performance characteristic data;
and adding other performance characteristic data to the network performance characteristic data at the corresponding time point.
5. The intelligent operation and maintenance fault pre-warning method according to claim 4, wherein the added other performance characteristic data comprises at least one of the number of users, the number of requests, and the requesting users.
6. The intelligent operation and maintenance fault early warning method according to claim 1, wherein training to obtain a fault early warning model according to the fitting data comprises:
selecting one part from the fitting data as training data, and using the other part as verification data;
and training according to the training data to obtain a plurality of fault early warning models, and inputting the verification data into all the fault early warning models to verify to obtain an optimal fault early warning model.
7. The intelligent operation and maintenance fault early warning method as claimed in claim 1, wherein the proportion of the training data in the fitting data is 75%, and the proportion of the verification data in the fitting data is 25%.
8. Intelligence operation and maintenance trouble early warning device based on 5G core network, its characterized in that includes:
a data acquisition module: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring historical data corresponding to a plurality of time points respectively, and the historical data comprises network performance characteristic data and fault characteristic data; the time intervals between every two adjacent time points are first preset time lengths; the network performance characteristic data comprises at least one performance characteristic data;
a data processing module: the system comprises a data processing unit, a data processing unit and a data processing unit, wherein the data processing unit is used for replacing corresponding fault characteristic data at any time point with corresponding fault characteristic data at the next time point corresponding to the time point according to the corresponding fault characteristic data at the time point to form fitting data corresponding to each time point, and the fitting data comprises network performance characteristic data and fault characteristic data at the next time point;
a model construction module: the fault early warning module is used for obtaining a fault early warning model according to the fitting data training, collecting index data at each moment in real time and inputting the index data into the fault early warning model so as to output fault characteristic data at the next moment corresponding to the moment; and each adjacent moment is spaced by a second preset time length.
9. An electronic device having a processor, a memory, and a computer readable program stored in the memory and executable by the processor, wherein the computer readable program, when executed by the processor, implements the intelligent operation and maintenance fault pre-warning method according to any one of claims 1 to 7.
10. A computer storage medium having a computer readable program stored thereon, the computer readable program being executable by a processor, wherein the computer readable program, when executed by the processor, implements the intelligent operation and maintenance fault warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011236167.XA CN112488326A (en) | 2020-11-09 | 2020-11-09 | Intelligent operation and maintenance fault early warning method and device based on 5G core network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011236167.XA CN112488326A (en) | 2020-11-09 | 2020-11-09 | Intelligent operation and maintenance fault early warning method and device based on 5G core network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112488326A true CN112488326A (en) | 2021-03-12 |
Family
ID=74929100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011236167.XA Pending CN112488326A (en) | 2020-11-09 | 2020-11-09 | Intelligent operation and maintenance fault early warning method and device based on 5G core network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488326A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114900441A (en) * | 2022-04-29 | 2022-08-12 | 华为技术有限公司 | Network performance prediction method, performance prediction model training method and related device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109634820A (en) * | 2018-11-01 | 2019-04-16 | 华中科技大学 | A kind of fault early warning method, relevant device and the system of the collaboration of cloud mobile terminal |
| CN109635997A (en) * | 2018-11-02 | 2019-04-16 | 广州裕申电子科技有限公司 | A kind of prediction technique and system on equipment maintenance opportunity |
| CN109886328A (en) * | 2019-02-14 | 2019-06-14 | 国网浙江省电力有限公司电力科学研究院 | A kind of electric car electrically-charging equipment failure prediction method and system |
| CN110689203A (en) * | 2019-09-30 | 2020-01-14 | 国网山东省电力公司电力科学研究院 | Self-encoder-based primary fan fault early warning method for thermal power plant |
| CN111858526A (en) * | 2020-06-19 | 2020-10-30 | 国网福建省电力有限公司信息通信分公司 | Failure time space prediction method and system based on information system log |
-
2020
- 2020-11-09 CN CN202011236167.XA patent/CN112488326A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109634820A (en) * | 2018-11-01 | 2019-04-16 | 华中科技大学 | A kind of fault early warning method, relevant device and the system of the collaboration of cloud mobile terminal |
| CN109635997A (en) * | 2018-11-02 | 2019-04-16 | 广州裕申电子科技有限公司 | A kind of prediction technique and system on equipment maintenance opportunity |
| CN109886328A (en) * | 2019-02-14 | 2019-06-14 | 国网浙江省电力有限公司电力科学研究院 | A kind of electric car electrically-charging equipment failure prediction method and system |
| CN110689203A (en) * | 2019-09-30 | 2020-01-14 | 国网山东省电力公司电力科学研究院 | Self-encoder-based primary fan fault early warning method for thermal power plant |
| CN111858526A (en) * | 2020-06-19 | 2020-10-30 | 国网福建省电力有限公司信息通信分公司 | Failure time space prediction method and system based on information system log |
Non-Patent Citations (2)
| Title |
|---|
| 徐保荣等: "《装甲车辆动力传动系统试验技术》", 30 June 2020, 北京理工大学出版社, pages: 319 - 326 * |
| 桂学勤: "《计算机网络系统集成》", 31 August 2020, 中国铁道出版社有限公司, pages: 122 - 124 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114900441A (en) * | 2022-04-29 | 2022-08-12 | 华为技术有限公司 | Network performance prediction method, performance prediction model training method and related device |
| CN114900441B (en) * | 2022-04-29 | 2024-04-26 | 华为技术有限公司 | Network performance prediction method, performance prediction model training method and related devices |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110002B (en) | Big data visualization interaction system | |
| CN105376335B (en) | Collected data uploading method and device | |
| CN109582289B (en) | Method, system, storage medium and processor for processing rule flow in rule engine | |
| CN112149838A (en) | Method, device, electronic equipment and storage medium for realizing automatic model building | |
| CN106506212A (en) | Abnormal information acquisition methods and user terminal | |
| CN105487970A (en) | Interface display method and apparatus | |
| CN111311014B (en) | Service data processing method, device, computer equipment and storage medium | |
| CN112199154A (en) | Distributed collaborative sampling central optimization-based reinforcement learning training system and method | |
| CN118250288A (en) | AIoT middle station data processing method, device and system based on scene assembly | |
| CN112488326A (en) | Intelligent operation and maintenance fault early warning method and device based on 5G core network | |
| CN101495978B (en) | Reduction of message flow between bus-connected consumers and producers | |
| CN112235164B (en) | Neural network flow prediction device based on controller | |
| CN108540302B (en) | Big data processing method and equipment | |
| CN110457448A (en) | Question pushing method, device, computer readable storage medium and computer equipment | |
| CN110399095A (en) | A kind of statistical method and device of memory space | |
| CN213126061U (en) | Neural network flow prediction device based on controller | |
| CN109672788B (en) | Incoming call monitoring method and device for user, electronic equipment and storage medium | |
| CN112883110A (en) | Terminal big data distribution method, storage medium and system based on NIFI | |
| CN109684159A (en) | Method for monitoring state, device, equipment and the storage medium of distributed information system | |
| CN112636976B (en) | Service quality determination method, device, electronic equipment and storage medium | |
| Pelayo et al. | An example of performance evaluation by using the stochastic process algebra: ROSA | |
| CN114143279B (en) | Interactive recording sampling method and device and storage medium | |
| CN113765773B (en) | Method and device for processing communication record | |
| CN116915870B (en) | Task creation request processing method, device, electronic equipment and readable medium | |
| CN115002871B (en) | Signal connection system, signal connection method, computer device, and storage 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 |