CN115550955A - Networking method, network management system, server and computer readable storage medium - Google Patents
Networking method, network management system, server and computer readable storage medium Download PDFInfo
- Publication number
- CN115550955A CN115550955A CN202110736270.9A CN202110736270A CN115550955A CN 115550955 A CN115550955 A CN 115550955A CN 202110736270 A CN202110736270 A CN 202110736270A CN 115550955 A CN115550955 A CN 115550955A
- Authority
- CN
- China
- Prior art keywords
- network element
- hardware
- data
- networking
- health
- 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
- 230000006855 networking Effects 0.000 title claims abstract description 125
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000036541 health Effects 0.000 claims abstract description 216
- 238000003745 diagnosis Methods 0.000 claims abstract description 66
- 238000004891 communication Methods 0.000 claims abstract description 8
- 230000008439 repair process Effects 0.000 claims description 42
- 238000012423 maintenance Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 27
- 238000012795 verification Methods 0.000 claims description 24
- 238000007726 management method Methods 0.000 claims description 20
- 238000013500 data storage Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000003862 health status Effects 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims 1
- 230000036449 good health Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005195 poor health Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W36/00—Hand-off or reselection arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W48/00—Access restriction; Network selection; Access point selection
- H04W48/08—Access restriction or access information delivery, e.g. discovery data delivery
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computer Security & Cryptography (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the application relates to the technical field of communication, in particular to a networking method, a network management system, a server and a computer readable storage medium. The networking method comprises the following steps: collecting hardware operation diagnosis data of each network element in real time; predicting the current health condition of each network element according to the collected hardware operation diagnosis data of each network element and a pre-trained network element health prediction model; acquiring a network element with the current health condition matched with the networking requirement according to the networking requirement and the matching relationship between the preset networking requirement and the health condition of the network element; and networking by using the network element with the current health condition matched with the networking requirement. The networking method provided by the embodiment of the application aims to automatically select the network elements with good health states to carry out network slicing networking, improve the performance of a slicing network, meet the actual networking requirements and business requirements of users and further improve the use experience of the users.
Description
Technical Field
The embodiment of the application relates to the technical field of communication, in particular to a networking method, a network management system, a server and a computer readable storage medium.
Background
With the rapid development of Communication Technology, a fifth Generation Mobile Communication Technology (5 th Generation Mobile Communication Technology, abbreviated as 5G) has gradually started to be commercially available and forms a certain scale, the 5G Technology can use a network slicing Technology for networking, the network slicing Technology is a networking mode according to needs, the network slicing Technology can carry out network slicing on different application scenes and services, not only is the original physical network isolated, but also the original physical network is decomposed into a plurality of logical networks, and a plurality of slices are configured differently, so that the network used by a user is smoother, and high-quality services are provided for the user.
However, the creation of network slices requires base station devices (i.e. network elements) as supports, the number of base station devices operating in the global range exceeds ten million, the base station devices are distributed in thousands of machine rooms or signal towers in various cities and villages, the base station devices inevitably have various faults during working, if network slice networking is performed based on the network elements with faults or poor performance, the networking performance is greatly reduced, the actual networking requirements and service requirements of users cannot be met, and poor use experience is brought to the users.
Disclosure of Invention
The embodiment of the application mainly aims to provide a networking method, a network management system, a server and a computer readable storage medium, and aims to automatically select a network element with a good health state to perform network slicing networking, improve the performance of a sliced network, and meet the actual networking requirements and service requirements of a user, so that the use experience of the user is improved.
In order to achieve the above object, an embodiment of the present application provides a networking method, where the method includes: collecting hardware operation diagnosis data of each network element in real time; predicting the current health condition of each network element according to the collected hardware operation diagnosis data of each network element and a pre-trained network element health prediction model; acquiring a network element with the current health condition matched with the networking requirement according to the networking requirement and the matching relationship between the preset networking requirement and the health condition of the network element; and networking by using the network element with the current health condition matched with the networking requirement.
In order to achieve the above object, an embodiment of the present application further provides a network management system, which includes a data acquisition module, a data storage module, an operation and maintenance analysis module, and a slice management module, where the data acquisition module is configured to acquire hardware operation diagnostic data of each network element in real time and store the acquired hardware operation diagnostic data of each network element in the data storage module; the operation and maintenance analysis module is used for acquiring the collected hardware operation diagnosis data of each network element and a pre-trained network element health prediction model from the data storage module, and predicting the current health condition of each network element according to the collected hardware operation diagnosis data of each network element and the pre-trained network element health prediction model; the slice management module is used for acquiring the network element with the current health condition matched with the networking requirement according to the matching relationship between the preset networking requirement and the network element health condition and the networking requirement, and networking by using the network element with the current health condition matched with the networking requirement; the data storage module is used for storing the hardware operation diagnosis data of each network element, the pre-trained network element health prediction model and the matching relationship between the preset networking requirement and the network element health condition, which are acquired by the data acquisition module in real time.
In order to achieve the above object, an embodiment of the present application further provides a server, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the networking method described above.
To achieve the above object, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, where the computer program is executed by a processor to implement the above networking method.
The networking method, the network management system, the server and the computer readable storage medium provided by the application collect hardware operation diagnosis data of each network element in real time, predict the current health condition of each network element according to the collected hardware operation diagnosis data of each network element and a pre-trained network element health prediction model, then obtain the network element with the matching current health condition and the networking requirement according to the matching relation between the networking requirement and the preset networking requirement and the network element health condition, finally perform networking by using the network element with the matching current health condition and the networking requirement, and consider that various faults or problems can be generated inevitably in work. In addition, the current health condition of each network element is predicted based on the pre-trained network element health prediction model, so that the prediction of the health condition of the network element is more convenient, accurate and efficient.
Drawings
FIG. 1 is a first flowchart of a networking method according to one embodiment of the present application;
FIG. 2 is a flow diagram of training a network element health prediction model provided in one embodiment according to the present application;
fig. 3 is a flowchart for training a network element health prediction model according to hardware rework data acquired within a preset time period and hardware operation diagnosis data belonging to the same hardware as the hardware rework data provided in an embodiment of the present application;
fig. 4 is a flowchart for outputting the current health condition of each network element to an operation and maintenance client according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a network management system according to another embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that in the various embodiments of the present application, numerous technical details are set forth in order to provide a better understanding of the present application. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not constitute any limitation to the specific implementation manner of the present application, and the embodiments may be mutually incorporated and referred to without contradiction.
For convenience of description, this embodiment and other embodiments below are all described with reference to a server. The following describes the implementation details of the networking method of the present embodiment in detail, and the following is only provided for the convenience of understanding and is not necessary for implementing the present embodiment.
The specific process of the networking method of this embodiment may be as shown in fig. 1, and includes:
Specifically, the server may perform hardware operation diagnosis on the hardware of each network element in real time, and acquire hardware operation diagnosis data of each network element in real time.
In a specific implementation, the hardware operation diagnostic data of each network element collected by the server includes diagnostic data of hardware operation of the network element and environmental data affecting hardware operation, and considering that the geographical positions of the network elements are different, the hardware of each network element is likely to be affected by external environment in the operation process, so that the performance of the hardware of the network element is affected, and even the network element is caused to be in fault.
In one example, the hardware operation diagnostic data of the network element includes more than 200 kinds of hardware operation diagnostic data of the network element including clock status data, resource utilization rate information and light ranging, and the server may collect the hardware operation diagnostic data of tens of thousands of network elements every day and store the data in the database.
In an example, the hardware of the network element may be a board of the network element, and the diagnostic data of the board of the network element during operation may include, but is not limited to: the link state of the single board, the error rate of the single board, the power of the single board, the CPU occupancy of the single board, the temperature of the single board and the like.
In an example, the hardware of the network element may be a board of the network element, and the environmental data affecting the board operation of the network element may include, but is not limited to: the input voltage of the single board, the air inlet temperature and the air outlet temperature of the single board, the fan rotating speed of the single board and the like.
In one example, a board of a network element includes: a single board of a Baseband processing Unit (Baseband Unit, BBU for short), a single board of a Remote Radio Unit (RRU for short), a single board of a Centralized Unit (CU for short), a single board of a Distributed Unit (DU for short), and a single board of an Active Antenna Unit (AAU for short).
In one example, the hardware operation diagnostic data collected by the server for each network element may be as shown in table 1:
table 1: hardware run diagnostic data table
Wherein, 1 represents that the hardware operation diagnosis data is abnormal, and 0 represents that the hardware operation diagnosis data is normal.
And step 102, predicting the current health condition of each network element according to the collected hardware operation diagnosis data of each network element and a pre-trained network element health prediction model.
Specifically, after acquiring the hardware operation diagnosis data of each network element, the server may predict the current health condition of each network element according to the acquired hardware operation diagnosis data of each network element and the pre-trained network element health prediction model. The pre-trained network element health prediction model may be stored in a memory inside the server, and the pre-trained network element health prediction model may be obtained by training according to actual needs by a person skilled in the art, or may be an open source model directly obtained from the internet, which is not specifically limited in this embodiment.
In a specific implementation, the server may input the acquired hardware operation diagnosis data of each network element as input data into the pre-trained network element health prediction model, obtain the fault probability of each network element output by the pre-trained network element health prediction model, and obtain the current health condition of each network element according to the fault probability.
In one example, the input and output data of the pre-trained net element health prediction model can be as shown in table 2:
table 2: input and output data table of pre-trained network element health prediction model
Wherein, 1 represents that the hardware operation diagnosis data is abnormal, and 0 represents that the hardware operation diagnosis data is normal.
In one example, the current health condition of each network element output by the pre-trained network element health prediction model may be: very healthy, relatively healthy, moderate and unhealthy, etc.
And 103, acquiring the network element with the matching between the current health condition and the networking requirement according to the matching relationship between the networking requirement and the preset networking requirement and the health condition of the network element.
Specifically, after obtaining the predicted current health condition of each network element, the server may obtain the network element with the current health condition matched with the networking requirement according to the networking requirement and the matching relationship between the preset networking requirement and the network element health condition.
In an example, the server may determine the networking requirement before acquiring the hardware operation diagnostic data of each network element, that is, after acquiring the networking requirement, the server may acquire the hardware operation diagnostic data of each network element in real time.
In one example, the server may obtain the networking result after obtaining the predicted current health condition of each network element, so as to perform networking.
In an example, the networking requirement may be a network speed requirement, and the preset matching relationship between the networking requirement and the health condition of the network element includes a matching relationship between the network speed requirement and the health condition of the network element, where the network speed requirement is in a direct proportion to the health condition of the network element, that is, the higher the network speed requirement is, the better the health condition of the network element is.
Such as: the method comprises the steps that the current health condition of a network element obtained by a server is very healthy, relatively healthy, medium and unhealthy, the server divides a network speed requirement into three grades of high speed, medium speed and low speed, and if the network speed requirement is high speed, the network element with the very healthy current health condition is matched; if the network speed requirement is medium speed, matching the current health condition as a relatively healthy network element; and if the network speed requirement is low speed, matching the network element with the current health condition being medium, wherein the network element with the current health condition being unhealthy may be a failed network element, and setting the network element with the health condition being unhealthy by the server not to participate in the networking process.
And 104, networking by using the network element with the current health condition matched with the networking requirement.
Specifically, after the server obtains the network element with the current health condition matched with the networking requirement according to the networking requirement and the matching relationship between the preset networking requirement and the network element health condition, networking can be performed by using the network element with the current health condition matched with the networking requirement.
In one example, the networking requirement may be a slicing networking requirement, and the server may slice the network based on a network element whose current health condition matches the networking requirement, to obtain a plurality of sliced networks.
In the embodiment, a server acquires hardware operation diagnosis data of each network element in real time, predicts the current health condition of each network element according to the acquired hardware operation diagnosis data of each network element and a pre-trained network element health prediction model, acquires a network element with the current health condition matched with networking requirements according to the networking requirements and the matching relationship between the preset networking requirements and the network element health conditions, and finally performs networking by using the network element with the current health condition matched with the networking requirements, so that various faults or problems are avoided in work. In addition, the current health condition of each network element is predicted based on the pre-trained network element health prediction model, so that the prediction of the health condition of the network element is more convenient, accurate and efficient.
In one embodiment, the pre-trained net element health prediction model may be trained through the steps shown in fig. 2, which specifically include:
In the embodiment of the application, a server acquires hardware rework data within a preset time period and acquires hardware operation diagnosis data belonging to the same hardware as the hardware rework data from a work log or an operation and maintenance database, wherein the hardware rework data can represent whether the hardware has a fault.
In one example, the hardware rework data and the hardware operation diagnostic data belonging to the same hardware as the hardware rework data obtained by the server may be as shown in table 3:
table 3: hardware repair data and hardware operation diagnosis data table belonging to same hardware with the hardware repair data
Wherein, 1 represents that the hardware operation diagnosis data is abnormal, 0 represents that the hardware operation diagnosis data is normal, and for a column of the repair data, 1 represents that the hardware has a fault, and 0 represents that the hardware does not have the fault.
Specifically, the server may train the network element health prediction model according to the hardware rework data and the hardware operation diagnosis data belonging to the same hardware as the hardware rework data within the preset time period when acquiring the hardware rework data and the hardware operation diagnosis data belonging to the same hardware as the hardware rework data within the preset time period.
In an example, the step of training the network element health prediction model may be performed in a preset first cycle, the server obtains the hardware rework data within a preset time period and a preset time period in the hardware operation diagnosis data belonging to the same hardware as the hardware rework data, and may refer to the hardware rework data obtained within the preset time period and the hardware operation diagnosis data belonging to the same hardware as the hardware rework data, and the network element health prediction model is updated regularly within a preset time period before the step of training the network element health prediction model is performed, so that the prediction effect of the network element health prediction model may be more accurate and stable.
In this embodiment, the pre-trained network element health prediction model is trained by the following steps: acquiring hardware repair data in a preset time period and hardware operation diagnosis data belonging to the same hardware as the hardware repair data; the network element health prediction model is trained according to the hardware repair data and the hardware operation diagnosis data which belong to the same hardware as the hardware repair data and are obtained within a preset time period, the fact that the hardware repair data come from the data in the first line of work is real and reliable data is considered, and the network element health prediction model is trained based on the hardware repair data and the hardware operation diagnosis data which belong to the same hardware as the hardware repair data, so that the network element health prediction model with scientific, stable and accurate prediction results can be obtained.
In one embodiment, the hardware rework data acquired within the preset time period includes rework data of a plurality of pieces of hardware, the hardware operation diagnosis data belonging to the same piece of hardware as the hardware rework data includes operation diagnosis data of a plurality of pieces of hardware, and the operation diagnosis data and the rework data of each piece of hardware in the plurality of pieces of hardware are used as a training sample, and the server trains the network element health prediction model according to the hardware rework data acquired within the preset time period and the hardware operation diagnosis data belonging to the same piece of hardware as the hardware rework data, which may be implemented through the steps shown in fig. 3, specifically including:
Specifically, each layer of the network element health prediction model comprises an input layer, an intermediate layer and an output layer, when the network element health prediction model is trained, the last output layer can be skipped, the server inputs the operation diagnosis data in the training sample to the input layer of the network element health prediction model, and the repair data output by the intermediate layer of the network element health prediction model is obtained from the intermediate layer of the network element health prediction model.
In the specific implementation, each layer of the network element health prediction model is provided with a weight and an offset, and the server obtains the repair data output by the middle layer based on the operation diagnosis data input in the training sample and the weight and the offset of each layer.
And step 302, verifying the repair data output by the middle layer by using the repair data in the training sample to obtain a verification value.
In a specific implementation, after the server obtains the repair data output by the middle layer of the network element health prediction model, the repair data output by the middle layer can be verified by using the repair data in the same training sample to obtain a verification value.
In an example, the server may invoke a preset cost function to verify the rework data output by the middle layer to obtain a verification value, where the preset cost function may be set by a person skilled in the art according to actual needs, and this embodiment is not particularly limited to this.
And 303, adjusting the model parameters of the network element health prediction model according to the verification value until the verification value represents that the verification passes.
In a specific implementation, after obtaining the verification value, the server may determine whether the verification value meets a preset verification standard, if the verification value meets the preset verification standard, the verification is confirmed to be passed, and if the verification value does not meet the preset verification standard, the server may adjust a model parameter of the network element health prediction model, and perform iterative training until the verification value represents that the verification passes.
In an example, the server may invoke a preset back propagation algorithm, adjust model parameters, such as weights and biases, of the network element health prediction model, and perform iterative training based on the adjusted parameters, where the preset back propagation algorithm may be set by a person skilled in the art according to actual needs, and this embodiment is not specifically limited to this.
In this embodiment, the hardware repair data acquired within the preset time period includes repair data of a plurality of pieces of hardware, the hardware operation diagnostic data belonging to the same piece of hardware as the hardware repair data includes operation diagnostic data of the plurality of pieces of hardware, and the operation diagnostic data and the repair data of each piece of hardware in the plurality of pieces of hardware are used as a training sample; the training of the network element health prediction model according to the hardware repair data acquired within the preset time period and the hardware operation diagnosis data belonging to the same hardware as the hardware repair data comprises the following steps: inputting the operation diagnosis data in the training sample into the network element health prediction model, and acquiring repair data output by an intermediate layer of the network element health prediction model; verifying the repair data output by the middle layer by using the repair data in the training sample to obtain a verification value; and adjusting the model parameters of the network element health prediction model according to the verification value until the verification value represents that the verification passes, wherein the embodiment of the application can perform iterative training on the network element health prediction model based on massive training samples, continuously optimize the model parameters and the model structure, and further improve the accuracy and the stability of the prediction of the network element health prediction model.
In one embodiment, the networking requirement is a networking requirement of a 5G network slice, the types of the networking requirement of the 5G network slice include enhanced Mobile Broadband (eMBB), ultra-Reliable and Low Latency Communications (URLLC), and large-scale Machine Type Communications (mtc), the health condition of the network element includes a health score, i.e., the health score is higher and the performance of the network element is better when the health condition of the network element is represented by the health score, and the matching relationship between the preset networking requirement and the health condition of the network element may include: the eMBB is matched with a network element with a health degree score larger than or equal to a first threshold value, the uRLLC is matched with a network element with a health degree score smaller than the first threshold value and larger than or equal to a second threshold value, and the mMTC is matched with a network element with a health degree score smaller than the second threshold value and larger than or equal to a third threshold value, wherein the first threshold value is larger than the second threshold value, and the second threshold value is larger than the third threshold value.
In one example, the first threshold is 90 points, the second threshold is 80 points, and the third threshold is 70 points, if the networking requirement is the eMBB, the server may perform the eMBB networking by using the network element whose health score is greater than or equal to 90 points; if the networking requirement is URLLC, the server can utilize the network elements with the health degree scores of more than or equal to 80 points and less than 90 points to carry out URLLC networking; if the networking requirement is mMTC, the server can utilize the network elements with the health degree score larger than or equal to 70 points and smaller than 80 points to conduct mMTC networking, and selects the network elements with high scores as much as possible to establish wireless slices, so that the networking success rate can be ensured.
In another example, if the networking requirement is URLLC, the server may use the network element with the health score greater than or equal to 80 points to perform URLLC networking; if the networking requirement is mMTC, the server can use the network elements with the health degree score larger than or equal to 70 points to carry out mMTC networking, and for some slicing scenes with low requirements on the health degree of the network elements, the server can also select the network elements with slightly poor health degree of the network elements to meet the networking requirement of users as much as possible.
In one embodiment, the step of predicting the current health status of each network element by the server according to the collected hardware operation diagnostic data of each network element and the pre-trained network element health prediction model may be performed at a preset second cycle.
In one embodiment, the step of predicting the current health condition of each network element by the server according to the collected hardware operation diagnostic data of each network element and the pre-trained network element health prediction model may be performed when the presence of a networking requirement is detected. The method has the advantages that the health condition of the network element is predicted before networking is needed, the current health condition of the network element can be obtained, the selection of the network element during networking is more accurate, and the actual performance and the theoretical performance of the network slice obtained after networking are more consistent.
In an embodiment, after predicting the current health condition of each network element according to the acquired hardware operation diagnostic data of each network element and the pre-trained network element health prediction model, the server can also output the current health condition of each network element to the operation and maintenance client.
In an example, the server represents the health condition of the network element by using the health degree score, and the server may output the current health degree score, fault location, and other information of each network element to the operation and maintenance client. Such as: after the server detects the first city network element A, the health degree score of the first city network element A is determined to be 65 points, the server outputs the health degree score of the first city network element A to the operation and maintenance client side to be 65 points, and fault positioning information is output as follows: the method comprises the following steps of overhigh temperature of a machine room, reset of a clock single board, failure of a wiring single board, out-of-service of a cell and abnormal communication.
In an embodiment, the outputting, by the server, the current health condition of each network element to the operation and maintenance client may be implemented by the steps shown in fig. 4, which specifically include:
In a specific implementation, after predicting the current health condition of each network element according to the acquired hardware operation diagnostic data of each network element and the pre-trained network element health prediction model, the server may sort the health conditions of each network element according to the current health condition of each network element, wherein the server may sort the health conditions in a sequence from poor to good according to the health conditions, and may sort the health conditions in a sequence from good to poor according to the health conditions.
In one example, the server represents the health condition of the network element by using the health degree score, the health degree score of the network element a is 85 points, the health degree score of the network element B is 23 points, the health degree score of the network element C is 98 points, the health degree score of the network element D is 67 points, the health degree score of the network element E is 76 points, and the server ranks the health conditions of the network elements in the order of the scores from low to high as follows: network element B, network element D, network element E, network element A and network element C.
And 402, presenting the health condition sequencing result of each network element to the operation and maintenance client in a visual mode.
In a specific implementation, the server may present the health condition ranking results of the network elements to the operation and maintenance client in a visual manner.
In one example, the server may present the health condition ranking results of the network elements in a form of a table on the operation and maintenance client interactive interface.
In this embodiment, the outputting the current health condition of each network element to the operation and maintenance client includes: sorting the health conditions of the network elements according to the current health conditions of the network elements; and presenting the health condition sequencing result of each network element to the operation and maintenance client in a visual mode, so that the health condition of each network element can be presented more intuitively, and a reference is provided for operation and maintenance personnel to formulate a network element health promotion operation plan.
In one embodiment, after the server predicts the current health condition of each network element according to the collected hardware operation diagnostic data of each network element and the pre-trained network element health prediction model, the server can perform operation and maintenance operation on the network element with poor current health condition, so as to improve the health condition of the network element, thereby better meeting networking requirements.
In an example, the server represents the current health condition of each network element by using the network element health degree, and after obtaining the network element health degree of each network element, the server may perform operation and maintenance operation on the network element of which the network element health degree is lower than a preset threshold according to a prestored operation and maintenance experience rule, so as to improve the health degree of the network element, where the preset threshold and the prestored operation and maintenance experience rule may be set by a person skilled in the art according to an actual need, and the embodiment of the present application is not specifically limited thereto.
In another example, the server represents the current health condition of each network element by using the network element health degree, and after obtaining the network element health degree of each network element, the server may obtain an operation and maintenance operation instruction input by an operation and maintenance worker, and perform operation and maintenance operation on the network element of which the network element health degree is lower than a preset threshold according to the operation and maintenance operation instruction, so as to improve the health degree of the network element, wherein the operation and maintenance operation instruction is formulated by the operation and maintenance worker according to the network element health degree of each network element and hardware operation diagnosis data of each network element.
Another embodiment of the present application relates to a network management system, and details of the network management system of the present embodiment are specifically described below, the following are only implementation details provided for facilitating understanding, and are not necessary for implementing the present embodiment, and fig. 5 is a schematic diagram of the network management system of the present embodiment, and includes: the system comprises a data acquisition module 501, a data storage module 502, an operation and maintenance analysis module 503 and a slice management module 504.
The data acquisition module 501 is connected with the data storage module 502, the data storage module 502 is respectively connected with the operation and maintenance analysis module 503 and the slice management module 504, and the operation and maintenance analysis module 503 is further connected with the slice management module 504.
The data acquisition module 501 is configured to acquire hardware operation diagnosis data of each network element in real time, and store the acquired hardware operation diagnosis data of each network element in the data storage module 502;
the operation and maintenance analysis module 503 is configured to obtain the acquired hardware operation diagnosis data of each network element and the pre-trained network element health prediction model from the data storage module 502, and predict the current health condition of each network element according to the acquired hardware operation diagnosis data of each network element and the pre-trained network element health prediction model;
the slice management module 504 is configured to obtain a network element whose current health condition matches the networking requirement according to a matching relationship between a preset networking requirement and a network element health condition and the networking requirement, and perform networking by using the network element whose current health condition matches the networking requirement;
the data storage module 502 is configured to store the hardware operation diagnosis data of each network element, the pre-trained network element health prediction model, and the matching relationship between the preset networking requirement and the network element health condition, which are acquired in real time by the data acquisition module 501.
It is obvious that this embodiment is a system embodiment corresponding to the above method embodiment, and this embodiment can be implemented in cooperation with the above method embodiment. The related technical details and technical effects mentioned in the above embodiments are still valid in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the above-described embodiments.
It should be noted that, all the modules involved in this embodiment are logic modules, and in practical application, one logic unit may be one physical unit, may also be a part of one physical unit, and may also be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, a unit which is not so closely related to solve the technical problem proposed by the present invention is not introduced in the present embodiment, but this does not indicate that there is no other unit in the present embodiment.
Another embodiment of the present application relates to an electronic device, as shown in fig. 6, including: at least one processor 601; and a memory 602 communicatively coupled to the at least one processor 601; the memory 602 stores instructions executable by the at least one processor 601, and the instructions are executed by the at least one processor 601 to enable the at least one processor 601 to execute the networking method in the foregoing embodiments.
Where the memory and processor are connected by a bus, the bus may comprise any number of interconnected buses and bridges, the bus connecting together various circuits of the memory and the processor or processors. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor is transmitted over a wireless medium via an antenna, which further receives the data and transmits the data to the processor.
The processor is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. While the memory may be used to store data used by the processor in performing operations.
Another embodiment of the present application relates to a computer-readable storage medium storing a computer program. The computer program realizes the above-described method embodiments when executed by a processor.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (13)
1. A networking method, comprising:
collecting hardware operation diagnosis data of each network element in real time;
predicting the current health condition of each network element according to the collected hardware operation diagnosis data of each network element and a pre-trained network element health prediction model;
acquiring a network element with the current health condition matched with the networking requirement according to the networking requirement and the matching relationship between the preset networking requirement and the health condition of the network element;
and networking by using the network element with the current health condition matched with the networking requirement.
2. The networking method of network slices of claim 1, wherein the pre-trained network element health prediction model is trained by:
acquiring hardware repair data in a preset time period and hardware operation diagnosis data which belong to the same hardware as the hardware repair data;
and training a network element health prediction model according to the hardware repair data acquired within a preset time period and hardware operation diagnosis data belonging to the same hardware as the hardware repair data.
3. The networking method for network slices according to claim 2, wherein the hardware rework data obtained within the preset time period includes rework data of a plurality of pieces of hardware, the hardware operation diagnostic data belonging to the same piece of hardware as the hardware rework data includes operation diagnostic data of the plurality of pieces of hardware, and the operation diagnostic data and the rework data of each piece of hardware in the plurality of pieces of hardware are used as a training sample;
the training of the network element health prediction model according to the hardware repair data acquired within the preset time period and the hardware operation diagnosis data belonging to the same hardware as the hardware repair data comprises the following steps:
inputting the operation diagnosis data in the training sample into the network element health prediction model, and acquiring repair data output by an intermediate layer of the network element health prediction model;
verifying the repair data output by the middle layer by using the repair data in the training sample to obtain a verification value;
and adjusting the model parameters of the network element health prediction model according to the verification value until the verification value represents that the verification is passed.
4. The networking method of network slice of claim 1, wherein after predicting the current health of each network element according to the collected hardware operation diagnosis data of each network element and the pre-trained network element health prediction model, further comprising:
and outputting the current health condition of each network element to the operation and maintenance client.
5. The networking method of network slice of claim 4, wherein the outputting the current health status of each network element to an operation and maintenance client comprises:
sorting the health conditions of the network elements according to the current health conditions of the network elements;
and presenting the health condition sequencing result of each network element to the operation and maintenance client in a visual mode.
6. The networking method of the network slice according to claim 2, wherein the step of training the network element health prediction model is performed at a preset first cycle;
the preset time period is a preset time period before the step of training the network element health prediction model is executed according to the hardware repair data acquired in the preset time period and the hardware operation diagnosis data belonging to the same hardware as the hardware repair data.
7. The networking method of a network slice of claim 1,
the step of predicting the current health condition of each network element according to the acquired hardware operation diagnosis data of each network element and a pre-trained network element health prediction model is executed at a preset second period; alternatively, the first and second electrodes may be,
and the step of predicting the current health condition of each network element according to the acquired hardware operation diagnosis data of each network element and the pre-trained network element health prediction model is executed when the networking requirement is detected.
8. The networking method of a network slice according to claim 1, wherein the networking requirement is that of a 5G network slice, and comprises the following requirement types: enhanced mobile broadband eMBB, ultra-reliable low-delay communication uRLLC and large-scale machine type communication mMTC; the health condition comprises a healthfulness score;
the matching relationship comprises: the eMBB is matched with a network element with a health degree score larger than or equal to a first threshold, the uRLLC is matched with a network element with a health degree score smaller than the first threshold and larger than or equal to a second threshold, and the mMTC is matched with a network element with a health degree score smaller than the second threshold and larger than or equal to a third threshold; the first threshold is greater than the second threshold, which is greater than the third threshold; wherein the higher the health score, the better the network element performance.
9. The networking method of a network slice of claim 1, wherein the hardware operational diagnostic data comprises diagnostic data of a hardware of a network element on the fly and environmental data having an impact on the hardware operation.
10. The networking method of network slice according to claim 9, wherein the hardware is a board of the network element;
the diagnostic data of the hardware in operation comprises: the link state of the single board, the bit error rate of the single board, the power of the single board, the CPU occupancy of the single board, and the temperature of the single board;
the environmental data having an effect on the hardware operation includes: the input voltage of the single board, the air inlet temperature and the air outlet temperature of the single board, and the fan rotating speed of the single board.
11. A network management system is characterized by comprising a data acquisition module, a data storage module, an operation and maintenance analysis module and a slice management module:
the data acquisition module is used for acquiring hardware operation diagnosis data of each network element in real time and storing the acquired hardware operation diagnosis data of each network element to the data storage module;
the operation and maintenance analysis module is used for acquiring the acquired hardware operation diagnosis data of each network element and a pre-trained network element health prediction model from the data storage module, and predicting the current health condition of each network element according to the acquired hardware operation diagnosis data of each network element and the pre-trained network element health prediction model;
the slice management module is used for acquiring the network element with the current health condition matched with the networking requirement according to the matching relationship between the preset networking requirement and the network element health condition and the networking requirement, and networking by using the network element with the current health condition matched with the networking requirement;
the data storage module is used for storing the hardware operation diagnosis data of each network element, the pre-trained network element health prediction model and the matching relationship between the preset networking requirement and the network element health condition, which are acquired by the data acquisition module in real time.
12. A server, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the networking method of any of claims 1-10.
13. A computer-readable storage medium storing a computer program, wherein the computer program is configured to implement the networking method according to any one of claims 1 to 10 when executed by a processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110736270.9A CN115550955A (en) | 2021-06-30 | 2021-06-30 | Networking method, network management system, server and computer readable storage medium |
| PCT/CN2022/097233 WO2023273804A1 (en) | 2021-06-30 | 2022-06-06 | Networking method, network management system, server and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110736270.9A CN115550955A (en) | 2021-06-30 | 2021-06-30 | Networking method, network management system, server and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115550955A true CN115550955A (en) | 2022-12-30 |
Family
ID=84690001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110736270.9A Pending CN115550955A (en) | 2021-06-30 | 2021-06-30 | Networking method, network management system, server and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115550955A (en) |
| WO (1) | WO2023273804A1 (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108141374B (en) * | 2015-12-21 | 2020-12-18 | 泉州台商投资区天泰工业设计有限公司 | Network sub-health diagnosis method and device |
| CN107919975B (en) * | 2016-10-09 | 2022-06-03 | 中兴通讯股份有限公司 | Business resource allocation method and device |
| CN106411609A (en) * | 2016-11-08 | 2017-02-15 | 上海新炬网络信息技术有限公司 | IT software and hardware running state monitoring system |
| CN109842910A (en) * | 2017-11-28 | 2019-06-04 | 中国移动通信有限公司研究院 | A kind of processing method and access network elements of network slice |
| CN112929187B (en) * | 2019-12-05 | 2023-04-07 | 中国电信股份有限公司 | Network slice management method, device and system |
| CN111065116B (en) * | 2019-12-10 | 2021-03-16 | 中盈优创资讯科技有限公司 | Automatic deployment method and system for end-to-end slicing |
-
2021
- 2021-06-30 CN CN202110736270.9A patent/CN115550955A/en active Pending
-
2022
- 2022-06-06 WO PCT/CN2022/097233 patent/WO2023273804A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023273804A1 (en) | 2023-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210326729A1 (en) | Recommendation Model Training Method and Related Apparatus | |
| Mahdavi et al. | A multiple hill climbing approach to software module clustering | |
| CN106803799B (en) | Performance test method and device | |
| CN107911251B (en) | Network equipment configuration method, device and medium | |
| CN107360026A (en) | Distributed message performance of middle piece is predicted and modeling method | |
| CN115174416B (en) | Network planning system, method and device and electronic equipment | |
| CN105471647A (en) | Power communication network fault positioning method | |
| CN105808588A (en) | Crowdsourcing model based distributed directional vertical information search system and method | |
| WO2023022755A1 (en) | Inference engine configured to provide a heat map interface | |
| CN107918358B (en) | Fault analysis method and device for numerical control equipment | |
| CN106502856B (en) | A kind of information processing method and device | |
| CN110380890A (en) | A kind of CDN system service quality detection method and system | |
| CN115550955A (en) | Networking method, network management system, server and computer readable storage medium | |
| CN104392101B (en) | Data sharing method and device | |
| CN113704077A (en) | Test case generation method and device | |
| CN108267683A (en) | The method and device that a kind of FPGA tests oneself | |
| CN115952098A (en) | Performance test tuning scheme recommendation method and system | |
| CN112733453B (en) | Equipment predictive maintenance method and device based on joint learning | |
| CN114723303A (en) | Method, device and equipment for determining energy-saving space of machine room and storage medium | |
| CN116415385A (en) | Fan joint debugging simulation method and device, server and computer storage medium | |
| CN115884195A (en) | Model training method, wireless resource scheduling method and device and electronic equipment | |
| CN1295615C (en) | Distribution type software reliability evaluation system having time restraint | |
| CN114548353A (en) | Model training method, electronic device and storage medium | |
| CN114039868B (en) | Value added service management method and device | |
| Wenting et al. | Task Scheduling Algorithm of Administrative Management System Based on Ant Colony Optimization Neural Network |
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 |