CN113973057A - Network slicing service quality evaluation method and device - Google Patents
Network slicing service quality evaluation method and device Download PDFInfo
- Publication number
- CN113973057A CN113973057A CN202010640404.2A CN202010640404A CN113973057A CN 113973057 A CN113973057 A CN 113973057A CN 202010640404 A CN202010640404 A CN 202010640404A CN 113973057 A CN113973057 A CN 113973057A
- Authority
- CN
- China
- Prior art keywords
- network slice
- network
- information
- slice
- service quality
- 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 41
- 238000013441 quality evaluation Methods 0.000 title claims description 33
- 238000013210 evaluation model Methods 0.000 claims abstract description 33
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims description 75
- 230000003993 interaction Effects 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 5
- 238000001303 quality assessment method Methods 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 27
- 238000013473 artificial intelligence Methods 0.000 description 24
- 208000018910 keratinopathic ichthyosis Diseases 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 8
- 238000005259 measurement Methods 0.000 description 7
- 230000008520 organization Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000037424 autonomic function Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- GVVPGTZRZFNKDS-JXMROGBWSA-N geranyl diphosphate Chemical compound CC(C)=CCC\C(C)=C\CO[P@](O)(=O)OP(O)(O)=O GVVPGTZRZFNKDS-JXMROGBWSA-N 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- 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
- H04L41/08—Configuration management of networks or network elements
- H04L41/0876—Aspects of the degree of configuration automation
- H04L41/0886—Fully automatic configuration
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Automation & Control Theory (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides a method and a device for evaluating the service quality of a network slice, wherein the method comprises the following steps: acquiring related information of the network slice; performing model training according to the relevant information of the network slice to obtain an evaluation model; and evaluating the service quality of the network slice according to the evaluation model to obtain the evaluation result of the service quality of the network slice. In the embodiment of the invention, the service quality of the network slicing can be ensured, the operation and maintenance of the slicing instance deployment can be optimized, and the complexity of network slicing management and operation and maintenance can be reduced.
Description
Technical Field
The embodiment of the invention relates to the field of communication network management and intellectualization, in particular to a method and a device for evaluating the service quality of a network slice.
Background
The introduction of the network slice brings great flexibility to the network, and the introduction of the network slice is mainly embodied in that the slice can be customized according to needs, deployed in real time and dynamically guaranteed. In order to realize these functions, a special management network element needs to be introduced to realize the full-life-cycle management of the slice instances, thereby bringing complexity to the management and operation of the network, and leading operators to be faced with a highly complex mobile communication network. If the automation degree of the network slice is not enough, the network slice can not be customized according to the special requirements of users, and service innovation of operators through the network slice is limited.
In the current cooperation verification with the industry vertical, the creation of network slices is implemented by the management and arrangement of the whole life cycle through the network slice management function. The network slice management function module creates an end-to-end network slice instance by selecting and associating each domain slice template which is pre-configured manually.
However, the complexity of the current network slice management and operation and maintenance is high, which is a problem to be solved urgently.
Disclosure of Invention
An object of the embodiments of the present invention is to provide a method and an apparatus for evaluating service quality of a network slice, which solve the problem of high complexity of network slice management and operation and maintenance.
In a first aspect, an embodiment of the present invention provides a method for evaluating service quality of a network slice, which is applied to an auxiliary analysis system, and includes:
acquiring related information of the network slice;
performing model training according to the relevant information of the network slice to obtain an evaluation model;
and evaluating the service quality of the network slice according to the evaluation model to obtain the evaluation result of the service quality of the network slice.
Optionally, the evaluation model comprises one or more of the following in combination:
the traffic prediction model analyzes based on historical traffic data and real-time traffic data of the network slice and provides traffic prediction;
a root cause analysis model for identifying root faults and/or derivative faults according to preset rules;
and the service model is used for mapping the QoE information perceived by the network slice client and the QoS information provided by the network slice life cycle management and arrangement functional entity based on the analysis of the data stream in the network slice.
Optionally, the performing, according to the evaluation model, network slice service quality evaluation to obtain a network slice service quality evaluation result of the network slice includes:
and evaluating the service quality of the network slices according to the network attributes of the network slices and the evaluation model to obtain the evaluation result of the service quality of the network slices.
Optionally, the network attributes include one or more of: upload/download capacity, jitter, maximum delay, network availability, and other parameters specific to a particular service requirement.
Optionally, different network attributes configure the same or different weight information.
Optionally, the network slice service quality assessment result includes: configuration information of the optimal network slice.
Optionally, the obtaining information about the network slice includes:
acquiring network slice QoE information and/or network slice information from the network slice lifecycle management and orchestration functional entity;
alternatively, the first and second electrodes may be,
acquiring network slice QoE information and/or network slice information from a network slice life cycle management and arrangement functional entity;
and locally acquiring the service quality evaluation result of the network slice obtained by the previous analysis.
Optionally, the method further comprises:
and feeding back the service quality evaluation result of the network slice to a life cycle management and arrangement functional entity of the network slice.
In a second aspect, an embodiment of the present invention provides a device for evaluating service quality of a network slice, which is applied to an auxiliary analysis system, and includes:
the data acquisition module is used for acquiring related information of the network slice;
the model training module is used for carrying out model training according to the relevant information of the network slice to obtain an evaluation model;
and the evaluation module is used for carrying out network slice service quality evaluation according to the evaluation model to obtain a network slice service quality evaluation result of the network slice.
Optionally, the evaluation model comprises one or more of the following in combination:
the traffic prediction model analyzes based on historical traffic data and real-time traffic data of the network slice and provides traffic prediction;
a root cause analysis model for identifying root faults and/or derivative faults according to preset rules;
a service model for mapping QoE information perceived by a network slice client with QoS information provided by a network slice lifecycle management and orchestration functional entity based on analysis of data flows in the network slice.
Optionally, the evaluation module is further configured to: and evaluating the service quality of the network slices according to the network attributes of the network slices and the evaluation model to obtain the evaluation result of the service quality of the network slices.
Optionally, the apparatus further comprises:
and the feedback module is used for feeding back the service quality evaluation result of the network slice to the life cycle management and arrangement functional entity of the network slice.
Optionally, the data acquisition module performs information interaction with a slice life cycle management customer support module in the network slice life cycle management and arrangement functional entity through a first interface;
the data acquisition module carries out information interaction with an autonomous slice life cycle management decision module in the network slice life cycle management and arrangement functional entity through a second interface;
the evaluation module carries out information interaction with an autonomous slice life cycle management decision module in the network slice life cycle management and arrangement functional entity through a third interface;
the data acquisition module carries out information interaction with a knowledge information exchange repository in the network slice life cycle management and arrangement functional entity through a fourth interface;
the evaluation module carries out information interaction with a knowledge information exchange repository in the network slice life cycle management and arrangement functional entity through a fifth interface;
the second interface and the third interface are of the same or different interface types, and the fourth interface and the fifth interface are of the same or different interface types.
In a third aspect, the present invention provides a readable storage medium, characterized in that the readable storage medium stores thereon a computer program, which when executed by a processor implements the steps comprising the method as described above.
In the embodiment of the invention, the service quality of the network slicing can be ensured, the operation and maintenance of the slicing instance deployment can be optimized, and the complexity of network slicing management and operation and maintenance can be reduced.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a method for evaluating network slicing QoS according to an embodiment of the present invention;
FIG. 2 is a diagram of a network slice management orchestration device according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of network slice quality evaluation according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a network slice management and layout framework of an entity fusion auxiliary analysis system for network slice lifecycle management and layout according to an embodiment of the present invention;
FIG. 5 is a flowchart of a network slice management orchestration method according to an embodiment of the present invention;
fig. 6 is a second flowchart of a network slice management and arrangement method according to an embodiment of the invention.
Detailed Description
To facilitate an understanding of embodiments of the present invention, the following terminology will be introduced.
M & O: management and organization manages the Orchestration functions.
And OSS: the Operation Support System operates a Support System. The OSS often refers to systems such as network management and network optimization.
BSS: business Support System. BSS is often referred to as charging, settlement, accounting, customer service, business, etc. systems.
QoE: quality of service Experience of Quality of service.
KPI: key Performance Indicator.
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 some, not all, embodiments of the present invention. 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 "comprises," "comprising," or any other variation thereof, in the description and claims of this application, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Furthermore, the use of "and/or" in the specification and claims means that at least one of the connected objects, such as a and/or B, means that three cases, a alone, B alone, and both a and B, exist.
In the embodiments of the present invention, words such as "exemplary" or "for example" are used to mean serving as examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "e.g.," an embodiment of the present invention is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
The terms "system" and "network" are often used interchangeably. CDMA systems may implement Radio technologies such as CDMA2000, Universal Terrestrial Radio Access (UTRA), and so on. UTRA includes Wideband CDMA (Wideband Code Division multiple access, WCDMA) and other CDMA variants. TDMA systems may implement radio technologies such as Global System for Mobile communications (GSM). The OFDMA system can implement radio technologies such as Ultra Mobile Broadband (UMB), evolved-UTRA (E-UTRA)), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX)), IEEE 802.20, Flash-OFDM, and the like. UTRA and E-UTRA are parts of the Universal Mobile Telecommunications System (UMTS). LTE and higher LTE (e.g., LTE-A) are new UMTS releases that use E-UTRA. UTRA, E-UTRA, UMTS, LTE-A, and GSM are described in documents from an organization named "third Generation Partnership Project" (3 GPP). CDMA2000 and UMB are described in documents from an organization named "third generation partnership project 2" (3GPP 2). The techniques described herein may be used for both the above-mentioned systems and radio technologies, as well as for other systems and radio technologies.
Referring to fig. 1, an embodiment of the present invention provides a network slice management and arrangement method, where an execution subject of the method may be an auxiliary analysis system (or referred to as an Artificial Intelligence (AI) auxiliary analysis system), and the method includes the specific steps of: step 101, step 102, step 103 and step 104.
Step 101: acquiring related information of the network slice;
for example, the information related to the network slice may include one or more of the following: (1) quality of Experience (QoE) information for network slices; (2) network slice information; (3) analyzing the service quality evaluation result of the network slice obtained in the previous step; (4) network slice policy information.
Wherein the network slice QoE information may include one or more of the following combinations: (1) network coverage area (Network coverage area); (2) number of subscribers (Number of subscribers); (3) customer satisfaction (Customer satisfaction).
Wherein the network slice information may include one or more of the following combinations: (1) network function performance measurement data (Network function performance measurement data); (2) fault monitoring data (Fault supervision data); (3) network QoS data (Network QoS data).
In some embodiments, the data acquisition module of the auxiliary analysis system acquires the network slice QoE information and/or the network slice information from a network slice lifecycle management customer support module in the network slice lifecycle management and orchestration functional entity, and further, the data acquisition module of the auxiliary analysis system acquires the network slice policy information from a knowledge information exchange repository in the network slice lifecycle management and orchestration functional entity;
in other embodiments, the data acquisition module of the auxiliary analysis system acquires the QoE information and/or the QoE information of the network slice from the network slice lifecycle management client support module in the network slice lifecycle management and orchestration functional entity, and further, the data acquisition module of the auxiliary analysis system acquires the policy information of the network slice from the knowledge information exchange repository in the network slice lifecycle management and orchestration functional entity; and the data acquisition module of the auxiliary analysis system acquires the service quality evaluation result of the network slice obtained by the previous analysis from the analysis result storage module.
Step 102: performing model training according to the relevant information of the network slice to obtain an evaluation model;
for example, an AI algorithm or a Machine Learning (ML) algorithm is used to perform model training according to the related information of the network slice, so as to obtain an evaluation model.
Wherein, the evaluation model can comprise any one of the following items: a traffic prediction model (a traffic prediction model), a Root Cause Analysis (RCA) model, a service model (service model), and the like.
The traffic prediction model is used for analyzing based on historical traffic data and real-time traffic data of the network slice and providing traffic prediction;
a root cause analysis model for identifying root faults and/or derivative faults according to preset rules;
a service model for mapping QoE information perceived by a network slice client with QoS information provided by a network slice lifecycle management and orchestration functional entity based on analysis of data flows in the network slice.
Step 103: performing network slice service quality evaluation according to the evaluation model to obtain a network slice service quality evaluation result of the network slice;
for example, the service quality of the network slice is evaluated according to the network attribute and the evaluation model of the network slice, so as to obtain the service quality evaluation result of the network slice.
For example, the service quality of the network slice is evaluated according to the user experience value of the network slice, the network attribute of the network slice, the weight information of each network attribute and the evaluation model, so as to obtain the service quality evaluation result of the network slice, wherein different user experience values correspond to different network load degrees.
Wherein, the network slice service quality evaluation result comprises: configuration information of the optimal network slice.
The network attribute is used for representing KPI of the network slice and NSI performance measurement indicators of the network slice, and may include one or more of the following combinations: upload/download capacity, jitter, maximum delay, network availability, and other parameters specific to a particular service requirement.
Optionally, the method may further include: quantifying the network slicing service experience into different user experience values according to the network load degree; acquiring network indexes required by the network slices; and obtaining the user experience value of the network slice according to the network index required by the network slice.
In the embodiment of the present invention, in order to obtain the best user service experience, the optimal network slice configuration information is obtained by considering the allocation of appropriate weights for different network attributes. Such as upload/download capacity, jitter maximum delay, network availability and other parameters specific to a particular service requirement.
One key method for evaluating user experience is as follows: an operator can divide the network load degree into different levels through testing, quantize the network slicing service experience of a slicing client into a specific value interval, namely a user experience value according to the network load degree, and then according to each network index required by each type of input slicing, for example: the coverage condition of the service area cell, the current network load information and the like are input to the module for analysis, and the corresponding user experience value is output.
The Network index may be from a Network slice life cycle management and orchestration (slice M & O) functional entity/Network slice customer (Network slice client), such as a Vehicle to electronics (V2X) slice:
-slice life-cycle M & O: APPid, RAN load information, cell coverage information, etc.; application identification (APPid), quality of service Flow identification (QFI), Qos Flow Bit Rate (Qos Flow Bit Rate), Qos Flow Packet Delay (Qos Flow Packet Delay), Radio Access Network (RAN) load information, and the like.
-Network slice customer: APPid, vehicle speed, sampling period, etc.
Further, the method illustrated in fig. 1 may further include: and feeding back the service quality evaluation result of the network slice to the life cycle management and arrangement functional entity of the network slice.
In the embodiment of the invention, the input and output information is transmitted in the interfaces of the network slice life cycle management and arrangement functional entity and the auxiliary analysis system, and the information transmission and decision output are carried out through the interaction flow of each functional module, so that the service quality of the network slice is ensured, the deployment operation and maintenance of the slice example are optimized, and the complexity of the network slice management and operation and maintenance is reduced.
Referring to fig. 2, an embodiment of the present invention provides a device for evaluating network slicing service quality, which is applied to an auxiliary analysis system, where the device 200 includes:
the data acquisition module 201 is configured to acquire relevant information of the network slice;
the training module 202 is configured to perform model training according to the relevant information of the network slice to obtain an evaluation model;
and the evaluation module 203 is configured to perform network slicing service quality evaluation according to the evaluation model to obtain a network slicing service quality evaluation result of the network slice.
Further, the apparatus may further include: and the feedback module is used for feeding back the service quality evaluation result of the network slice to the life cycle management and arrangement functional entity of the network slice.
In some embodiments, the data acquisition module 201 is further configured to: acquiring network slice QoE information and/or network slice information from a network slice life cycle management and arrangement functional entity; or, acquiring the QoE information and/or the network slice information from the network slice life cycle management and arrangement functional entity; and locally acquiring the service quality evaluation result of the network slice obtained by the previous analysis.
In some embodiments, the evaluation module 203 is further configured to: performing network slice service quality evaluation according to the network attribute and the evaluation model of the network slice to obtain a network slice service quality evaluation result of the network slice; or, according to the user experience value of the network slice, the network attribute of the network slice, the weight information of each network attribute and the evaluation model, performing service quality evaluation on the network slice to obtain a service quality evaluation result of the network slice, wherein different user experience values correspond to different network load degrees.
In some embodiments, the evaluation module 203 is further configured to: quantifying the network slicing service experience into different user experience values according to the network load degree; acquiring network indexes required by the network slices; and obtaining the user experience value of the network slice according to the network index required by the network slice.
In the embodiment of the invention, in order to guarantee the quality of different network slice services and the Service-Level Agreement (SLA) Service experience of a user, different weighting methods are distributed for the network attributes of a certain slice in an evaluation module in an AI auxiliary analysis system.
From the perspective of the network slicing tenant, one of the KPIs that the tenant is most interested in meeting the user's percentage of service experience. To determine KPIs, tenants typically evaluate the end user's service experience (i.e., service mean opinion score) because tenants are well aware of their service logic.
From the operator's perspective, one of the KPIs of most concern to the operator is to satisfy the percentage of the UE service experience through the I-network functionality. However, the operator cannot determine KPIs as an operator cannot accurately weigh the tenant's end user service experience.
The slicing service quality evaluation module is used for effectively correlating the service experience of the end user with the network configuration and giving specific configuration weight, so that the requirement for meeting the service experience percentage of the user can be obtained by the network slicing service.
For a given slice 1, assume:
1) slice 1 consists of application 1 and application 2;
2) taking a linear regression model as an example:
hi(x) Representing the percentage of user experience, i-1, 2 … …, where 1,2 is the percentage of UE service experience that application 1 or application 2 of slice 1 satisfies. Application 1 is a slice 1 video service, satisfying 85% of the user service experience;
X＝(x0,x1x2,,…,xD) Is an input variable vector, i.e., a network slice KPI from the network slice lifecycle management and orchestration functions and network slice customer definitions, such as:
xi0～xiD(i: different slices) slice intrinsic properties KPI, intrinsic NSI performance measurement indicators;
xD+1～xENSI performance measurement indicators (special attributes);
Wi＝(wi0,wi1,wi2,wi3,…,wE) Weight information reflecting the performance data.
The specific calculation process can be seen in fig. 3, where θ represents the weight of the priority, and since the whole resource is limited, all the priority assignment is based on a set of network resources. It is to be understood that, in the embodiment of the present invention, the configuration of the weight information is not particularly limited.
Exemplarily, the following steps are carried out:
1) there are N slices, each slice may be composed of multiple applications;
2) the auxiliary analysis system trains a slice resource model for each application for each slice;
3) each slice has its own requirements, i.e. how many UE experiences each application satisfies.
If the network resources are sufficient to meet all slice service requirements, the auxiliary analysis system can easily cooperate with the network slice lifecycle management and orchestration functional entity to accurately adjust the network slice resources by providing the network slice KPI lists directly to the network slice lifecycle management and orchestration functional entity.
However, in real-time networks, network resources may not always meet all network slice requirements, and an operator may have to determine which network slice SLA should be guaranteed with higher priority:
1) some local policies have been configured in the network slice lifecycle management and orchestration function, e.g. network slice 1 and network slice 2 have high priority, while network slice N has low priority;
2) based on the configured local policy, the network slice lifecycle management and orchestration function entity determines a network slice requirement list, then queries b), a network slice KPI list for each network slice requirement list, for example:
a) inquiring a related network slice KPI list, and only meeting the requirements of a network slice 1 and a network slice 2;
b) and inquiring a KPI list related to the network slices to meet all the network slices, namely the network slices 1-N.
3) In the event that network resources are insufficient to satisfy all network slices, the network slice lifecycle management and orchestration function entity determines which network slice demand list should have a higher priority and provides an associated network slice KPI list to adjust the network resources.
An operator can divide the network load degree into different levels through testing, quantize the network slicing service experience of a slicing client into a specific value interval, namely a user experience value according to the network load degree, and then according to each network index required by each type of input slicing, for example: the coverage condition of the service area cell, the current network load information and the like are input to the module for analysis, and the corresponding user experience value is output to obtain the final parameter weight value.
In some embodiments, the data acquisition module interacts information with a slice lifecycle management customer support module in the network slice lifecycle management and orchestration functional entity through a first interface;
the data acquisition module carries out information interaction with an autonomous slice life cycle management decision module in the network slice life cycle management and arrangement functional entity through a second interface;
the evaluation module carries out information interaction with an autonomous slice life cycle management decision module in the network slice life cycle management and arrangement functional entity through a third interface;
the data acquisition module carries out information interaction with a knowledge information exchange repository in the network slice life cycle management and arrangement functional entity through a fourth interface;
the evaluation module carries out information interaction with a knowledge information exchange repository in the network slice life cycle management and arrangement functional entity through a fifth interface;
the second interface and the third interface are of the same or different interface types, and the fourth interface and the fifth interface are of the same or different interface types.
Referring to fig. 4, an intelligent network Slice management and organization framework of an AI-assisted analysis (AI-assisted analysis) system is shown as a network Slice lifecycle management and organization (Slice life-cycle management and organization) functional entity and interface messages are defined.
The network slice lifecycle management and orchestration functional entity may include: the following four functional modules:
(1) slice Life cycle management client support Module (Slice life-cycle management customer care support): for interacting with third party slicing clients or applications.
(2) Autonomous slice life-cycle Management decision module (automic slice life-cycle Management decision): an autonomic function is provided for the entire Network Slice lifecycle management perspective, which is a Network-wide self-management policy decision, single (NSI) self-management and control operations, and the highest level of automated OSS/BSS exchange management information that all affect to handle the self-management of legacy networks.
(3) Knowledge Information Exchange Repository (Knowledge Information Exchange Repository): providing the capability to store self-managed policy information across the entire network slice lifecycle management to handle large capacity scalability and the ability to access distributed information repositories.
(4) External management support module (External management entity support): for interacting with an external management entity.
The knowledge information exchange repository comprises: providing the capability to store self-managed policy information across the entire network slice lifecycle management to handle large capacity scalability and the ability to access distributed information repositories.
The AI-assisted analysis system is for:
-interacting with a customer service support function entity to support a network slice customer service.
-providing standardized interfaces through the network slice lifecycle management and orchestration functional entity to interact with network slice clients and applications. It supports requesting and receiving management operations and related information in a network slice lifecycle management and orchestration function.
The AI-assisted analysis system may include the following four functions:
data acquisition: web slice QoE information from web slice clients (including third parties using web slice services) and web slice information from web slice administrative orchestration systems are primarily obtained.
Model training: and (3) carrying out resource model training on the acquired data through an AI/Machine Learning (ML) algorithm, and giving a specific service model of the network slice.
Network slicing service quality assessment: to obtain the best user service experience, the evaluation module measures the service experience of sliced users by considering network attributes with appropriate weights (e.g., upload/download capacity, jitter, maximum delay, network availability) and other parameters specific to the particular service requirements.
An analysis result storage library: storing the analysis result (such as weight value information) each time, and providing useful information to the data acquisition module when the slice user information is analyzed next time.
Meanwhile, in order to ensure that the intelligent analysis function can obtain complete slice information through the network slice lifecycle management and arrangement functional entity, two external entities need to be introduced into the frame diagram:
external management systems (External management systems): the OSS/BSS and a specific domain management system are included in the network.
Intra-network slice Management (Intra-network slice Management): 1) a management support function entity provided for each NSI. 2) The core network control Plane configures the local offload policy and the identification information to a User Plane (UP).
With continued reference to fig. 4, the network slice lifecycle management and orchestration function interacts with the AI-assisted analysis system, requiring a total of 3 interfaces to pass messages:
RP-1: and the slice life cycle management customer support module performs information interaction with a data acquisition module in the AI auxiliary analysis system and inputs QoE information of the slice customer.
RP-2: the autonomous slice life cycle management decision module performs information interaction with a data acquisition module in the AI auxiliary analysis system and inputs network slice strategy information; and carrying out information interaction with an evaluation module in the AI auxiliary analysis system to obtain a slice analysis result.
RP-3: the knowledge information exchange storage library carries out information interaction with a data acquisition module in the AI auxiliary analysis system and inputs information stored in the network slice management arrangement library; and carrying out information interaction with an evaluation module in the AI auxiliary analysis system to obtain a slice analysis result.
In the embodiment of the invention, the input and output information is transmitted in the interfaces of the network slice life cycle management and arrangement functional entity and the auxiliary analysis system, and the information transmission and decision output are carried out through the interaction flow of each functional module, so that the service quality of the network slice is ensured, the deployment operation and maintenance of the slice example are optimized, and the complexity of the network slice management and operation and maintenance is reduced.
Example 1: the network slice life cycle management and arrangement function is integrated with the intelligent network slice management and arrangement process of the AI auxiliary analysis system.
1. The slice life cycle management client support module performs information interaction with a network slice client to acquire Quality of Experience (QoE) information of the slice client, and inputs the QoE information to a data acquisition module in the AI auxiliary analysis system.
2. And the autonomous slice life cycle management decision-making functional entity and the knowledge information exchange storage library functional entity input the stored network slice strategy information to a data acquisition module in the AI auxiliary analysis system.
And 3, after the AI auxiliary analysis system performs analysis, outputting the analysis information to a network slice life cycle management and arrangement function through a network slice service quality evaluation function module, wherein the main output party is an autonomous slice life cycle management decision function entity and a knowledge information exchange repository function entity.
Referring to fig. 5, the specific process is as follows:
step 1: a data collection (data collection) module in the AI auxiliary analysis system acquires information of the network slice client from the network slice lifecycle management and arrangement functional entity and through a slice lifecycle management client service support module.
Optionally, the information comprises one or more of the following in combination: network slice quality of experience information (network slice QoE information) and network slice information (network slice information).
Wherein the network slice information may include one or more of the following combinations: (1) network functional performance measurement data; (2) fault monitoring data; (3) network QoS data.
Wherein the network slice QoE information may include one or more of the following combinations: (1) a network coverage area; (2) the number of subscribers; (3) customer satisfaction.
Step 2: the data acquisition module stores the acquired network slice information and inputs the corresponding network slice information into the training module.
Step 2.1: and the training module analyzes and trains an evaluation model based on the acquired data according to the requirements of the slice clients.
Wherein, the evaluation model can comprise any one of the following items: a traffic prediction model (a traffic prediction model), a Root Cause Analysis (RCA) model, a service model (service model), and the like.
And step 3: the training module inputs the trained model result to the evaluation module.
Step 3.1: the evaluation module, in order to obtain the best user service experience, needs to derive the optimal network slice configuration information by considering the assignment of appropriate weights for different network attributes, such as upload/download capacity, jitter, maximum delay, network availability and other parameters specifically for a particular service requirement.
Step 4a-4 b: and the evaluation module feeds the analysis result back to an autonomous slice life cycle management decision module in the network slice life cycle management and arrangement functional entity and sends the analysis result to an analysis result library in the AI auxiliary analysis system for storage.
Example 2: the network slice life cycle management and arrangement functional entity integrates an intelligent network slice management and arrangement process of an AI auxiliary analysis system.
Referring to fig. 6, the specific process is as follows:
step 1 a: the data acquisition module in the AI auxiliary analysis system acquires the information of the network slice client from the network slice lifecycle management and arrangement functional entity and through the slice lifecycle management client service support module.
Optionally, the information comprises one or more of the following in combination: network slice quality of experience information (network slice QoE information) and network slice information (network slice information).
Wherein the network slice information may include one or more of the following combinations: (1) network functional performance measurement data; (2) fault monitoring data; (3) network QoS data.
Wherein the network slice QoE information may include one or more of the following combinations: (1) a network coverage area; (2) the number of subscribers; (3) customer satisfaction.
Step 1 b: a data collection module in the AI-assisted analysis system retrieves stored analysis results from an analysis results (analysis result) repository that were previously analyzed.
For example, the network attributes in the slice may be weighted differently, so as to provide a reference for the current demand analysis.
Step 2: the data acquisition module stores the acquired network slice information and inputs the corresponding network slice information into the training module.
Step 2.1: and the training module analyzes and trains an evaluation model based on the acquired data according to the requirements of the slice clients.
Wherein, the evaluation model can comprise any one of the following items: a traffic prediction model (a traffic prediction model), a Root Cause Analysis (RCA) model, a service model (servicemodel), and the like.
And step 3: the training module inputs the trained model result to the evaluation module.
Step 3.1: the evaluation module, in order to obtain the best user service experience, needs to derive the optimal network slice configuration information by considering the assignment of appropriate weights for different network attributes, such as upload/download capacity, jitter, maximum delay, network availability and other parameters specifically for a particular service requirement.
Step 4a-4 b: the feedback module feeds the analysis result back to an autonomous slice life cycle management decision module in the network slice life cycle management and arrangement functional entity and sends the analysis result to an analysis result library in the AI auxiliary analysis system for storage.
The steps of a method or algorithm described in connection with the disclosure herein may be embodied in hardware or may be embodied in software instructions executed by a processor. The software instructions may consist of corresponding software modules that may be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, a removable hard disk, a compact disk, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. In addition, the ASIC may be carried in a core network interface device. Of course, the processor and the storage medium may reside as discrete components in a core network interface device.
Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in this invention may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present invention should be included in the scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.
Claims (14)
1. A network slice service quality assessment method is applied to an auxiliary analysis system and is characterized by comprising the following steps:
acquiring related information of the network slice;
performing model training according to the relevant information of the network slice to obtain an evaluation model;
and evaluating the service quality of the network slice according to the evaluation model to obtain the evaluation result of the service quality of the network slice.
2. The method of claim 1, wherein the evaluation model comprises one or more of the following in combination:
the traffic prediction model analyzes based on historical traffic data and real-time traffic data of the network slice and provides traffic prediction;
a root cause analysis model for identifying root faults and/or derivative faults according to preset rules;
and the service model is used for mapping the QoE information perceived by the network slice client and the QoS information provided by the network slice life cycle management and arrangement functional entity based on the analysis of the data stream in the network slice.
3. The method of claim 1, wherein the performing network slice qos assessment according to the assessment model to obtain a network slice qos assessment result of the network slice comprises:
and evaluating the service quality of the network slices according to the network attributes of the network slices and the evaluation model to obtain the evaluation result of the service quality of the network slices.
4. The method of claim 3, wherein the network attributes comprise one or more of: upload/download capacity, jitter, maximum delay, network availability, and other parameters specific to a particular service requirement.
5. The method of claim 4, wherein different network attributes configure the same or different weight information.
6. The method of claim 3, wherein the network slice quality of service assessment result comprises: configuration information of the optimal network slice.
7. The method of claim 1, wherein the obtaining information about the network slice comprises:
acquiring network slice QoE information and/or network slice information from the network slice lifecycle management and orchestration functional entity;
alternatively, the first and second electrodes may be,
acquiring network slice QoE information and/or network slice information from a network slice life cycle management and arrangement functional entity;
and locally acquiring the service quality evaluation result of the network slice obtained by the previous analysis.
8. The method of claim 1, further comprising:
and feeding back the service quality evaluation result of the network slice to a life cycle management and arrangement functional entity of the network slice.
9. A network slice service quality assessment device is applied to an auxiliary analysis system and is characterized by comprising:
the data acquisition module is used for acquiring related information of the network slice;
the model training module is used for carrying out model training according to the relevant information of the network slice to obtain an evaluation model;
and the evaluation module is used for carrying out network slice service quality evaluation according to the evaluation model to obtain a network slice service quality evaluation result of the network slice.
10. The apparatus of claim 9, wherein the evaluation model comprises one or more of the following in combination:
the traffic prediction model analyzes based on historical traffic data and real-time traffic data of the network slice and provides traffic prediction;
a root cause analysis model for identifying root faults and/or derivative faults according to preset rules;
a service model for mapping QoE information perceived by a network slice client with QoS information provided by a network slice lifecycle management and orchestration functional entity based on analysis of data flows in the network slice.
11. The apparatus of claim 9, wherein the evaluation module is further configured to: and evaluating the service quality of the network slices according to the network attributes of the network slices and the evaluation model to obtain the evaluation result of the service quality of the network slices.
12. The apparatus of claim 9, further comprising:
and the feedback module is used for feeding back the service quality evaluation result of the network slice to the life cycle management and arrangement functional entity of the network slice.
13. The apparatus of claim 9,
the data acquisition module carries out information interaction with a slice life cycle management customer support module in the network slice life cycle management and arrangement functional entity through a first interface;
the data acquisition module carries out information interaction with an autonomous slice life cycle management decision module in the network slice life cycle management and arrangement functional entity through a second interface;
the evaluation module carries out information interaction with an autonomous slice life cycle management decision module in the network slice life cycle management and arrangement functional entity through a third interface;
the data acquisition module carries out information interaction with a knowledge information exchange repository in the network slice life cycle management and arrangement functional entity through a fourth interface;
the evaluation module carries out information interaction with a knowledge information exchange repository in the network slice life cycle management and arrangement functional entity through a fifth interface;
the second interface and the third interface are of the same or different interface types, and the fourth interface and the fifth interface are of the same or different interface types.
14. A readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out steps comprising the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010640404.2A CN113973057A (en) | 2020-07-06 | 2020-07-06 | Network slicing service quality evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010640404.2A CN113973057A (en) | 2020-07-06 | 2020-07-06 | Network slicing service quality evaluation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113973057A true CN113973057A (en) | 2022-01-25 |
Family
ID=79584520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010640404.2A Pending CN113973057A (en) | 2020-07-06 | 2020-07-06 | Network slicing service quality evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113973057A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106792739A (en) * | 2016-11-17 | 2017-05-31 | 北京邮电大学 | Network dicing method, device and equipment |
| US20180139106A1 (en) * | 2016-11-14 | 2018-05-17 | Huawei Technologies Co., Ltd. | System and method for accelerated provision of network services |
| US20180287891A1 (en) * | 2017-03-31 | 2018-10-04 | At&T Intellectual Property I, L.P. | Quality of service management for dynamic instantiation of network slices and/or applications |
| CN109495907A (en) * | 2018-11-29 | 2019-03-19 | 北京邮电大学 | A kind of the wireless access network-building method and system of intention driving |
| CN110831038A (en) * | 2019-11-06 | 2020-02-21 | 中国联合网络通信集团有限公司 | Network slice resource scheduling method and device |
-
2020
- 2020-07-06 CN CN202010640404.2A patent/CN113973057A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180139106A1 (en) * | 2016-11-14 | 2018-05-17 | Huawei Technologies Co., Ltd. | System and method for accelerated provision of network services |
| CN106792739A (en) * | 2016-11-17 | 2017-05-31 | 北京邮电大学 | Network dicing method, device and equipment |
| US20180287891A1 (en) * | 2017-03-31 | 2018-10-04 | At&T Intellectual Property I, L.P. | Quality of service management for dynamic instantiation of network slices and/or applications |
| CN109495907A (en) * | 2018-11-29 | 2019-03-19 | 北京邮电大学 | A kind of the wireless access network-building method and system of intention driving |
| CN110831038A (en) * | 2019-11-06 | 2020-02-21 | 中国联合网络通信集团有限公司 | Network slice resource scheduling method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11611891B2 (en) | Data analytics management (DAM), configuration specification and procedures, provisioning, and service based architecture (SBA) | |
| US11018958B2 (en) | Communication network quality of experience extrapolation and diagnosis | |
| Samba et al. | Instantaneous throughput prediction in cellular networks: Which information is needed? | |
| US20240137291A1 (en) | Systems and methods for remote collaboration | |
| KR101676743B1 (en) | Prediction and root cause recommendations of service access quality of experience issues in communication networks | |
| Kukliński et al. | Key Performance Indicators for 5G network slicing | |
| Banović-Ćurguz et al. | Mapping of QoS/QoE in 5G networks | |
| US11134409B2 (en) | Determining whether a flow is to be added to a network | |
| US20230084355A1 (en) | RESOLVING UNSATISFACTORY QoE FOR 5G NETWORKS OR HYBRID 5G NETWORKS | |
| CN107210852A (en) | By predicting smooth transport block size come control application operation system and method | |
| Yusuf-Asaju et al. | Framework for modelling mobile network quality of experience through big data analytics approach | |
| Bernal et al. | Near real-time estimation of end-to-end performance in converged fixed-mobile networks | |
| Khairi et al. | Novel QoE monitoring and management architecture with eTOM for SDN-based 5G networks: SLA verification scenario | |
| Barrachina-Muñoz et al. | Cloud-native 5G experimental platform with over-the-air transmissions and end-to-end monitoring | |
| Laselva et al. | Advancements of QoE assessment and optimization in mobile networks in the machine era | |
| Bonald et al. | A flow-level performance model for mobile networks carrying adaptive streaming traffic | |
| CN113973057A (en) | Network slicing service quality evaluation method and device | |
| WO2017212410A1 (en) | System to determine quality of internet services | |
| Parracho et al. | An improved capacity model based on radio measurements for a 4G and beyond wireless network | |
| CN115866634A (en) | Network performance abnormity analysis method and device and readable storage medium | |
| Alcalá-Marín et al. | kaNSaaS: Combining Deep Learning and Optimization for Practical Overbooking of Network Slices | |
| Cristobo et al. | A Machine Learning Methodology for Dynamic QoX Management in Modern Networks | |
| Hassan et al. | Artifact: implementation of an adaptive flow management framework for IoT spaces | |
| Vilà et al. | On the Implementation of a Reinforcement Learning-based Capacity Sharing Algorithm in O-RAN | |
| Bakri | Towards enforcing network slicing in 5G networks |
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 |