CN116032759A

CN116032759A - Method, device, storage medium and network equipment for slice management

Info

Publication number: CN116032759A
Application number: CN202111233416.4A
Authority: CN
Inventors: 兰世战; 徐烈; 莫晓斌; 刘静; 张玉兰; 谭彬
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Hangzhou Information Technology Co Ltd; China Mobile Group Guangxi Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Hangzhou Information Technology Co Ltd; China Mobile Group Guangxi Co Ltd
Priority date: 2021-10-22
Filing date: 2021-10-22
Publication date: 2023-04-28

Abstract

The embodiment of the invention discloses a method, a device, a storage medium and network equipment for slice management, wherein the method comprises the following steps: the fixed network slice management platform receives mirror image flow data from a first access network element; the mirror image flow data comprise mirror image data corresponding to service flow data communicated with the Internet by the second access network element through the first access network element based on a pre-established slicing channel; classifying the mirror image flow data to obtain a target service type; determining network element operation information according to the target service type and the pre-configured slice information, and sending the network element operation information to a second access network element; the network element operation information is used for controlling the second access network element to communicate with the Internet through the first access network element based on a target slice channel, wherein the target slice channel is a slice channel associated with slice information corresponding to a target service type. The invention realizes the unified configuration of network capability and can flexibly cope with different requirements and services.

Description

Method, device, storage medium and network equipment for slice management

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a method, an apparatus, a storage medium, and a network device for slice management.

Background

With the advent of 5G and cloud age diversification of new services, different industries, services or users have set forth various quality of service requirements on networks. Various home services require various network service level agreements (SLA, service Level Agreement) requirements (such as bandwidth, time delay, safety, etc.), all requirements cannot be met efficiently and economically by one network, and in order to meet the requirements of operators for the refined operation of the home services, the network is required to have the capability of intelligently guaranteeing different services.

At present, the technical scheme aiming at the network quality guarantee of the fixed network access network is mainly focused on: (1) The broadband access server (BRAS, broadband Remote Access Server) is utilized to carry out simple indiscriminate network quality assurance on various family services of the user, but the BRAS bandwidth user subscription attribute is utilized to carry out network quality assurance, the caliber is thick, the fine assurance for different family services cannot be realized, and the different family services compete with each other on network resources; (2) A local policy decision function entity is introduced to perform unified management on the home gateway, but the network quality assurance policy issued to the home gateway by the local policy decision function entity is focused on static configuration and cannot be dynamically changed according to the network link state.

On the other hand, the traditional quality of service (QoS, quality of Service) involves manual configuration of a plurality of network element devices, is relatively complicated, has high adjustment difficulty, is difficult to dynamically and flexibly adjust according to needs, and meanwhile, qoS performs corresponding QoS policy deployment on a network path of a service path in advance so as to realize guarantee of a network side, does not have the capability of providing isolation according to tenants and services, and is difficult to meet business operation requirements of service differentiation services.

Disclosure of Invention

In order to solve the existing technical problems, the embodiment of the invention provides a method, a device, a storage medium and network equipment for slice management.

In order to achieve the above object, the technical solution of the embodiment of the present invention is as follows:

in a first aspect, an embodiment of the present invention provides a method for slice management, including:

the fixed network slice management platform receives mirror image flow data from a first access network element; the mirror image flow data comprise mirror image data corresponding to service flow data communicated with the Internet by the second access network element through the first access network element based on a pre-established slicing channel;

classifying the mirror image flow data to obtain a target service type;

Determining network element operation information according to the target service type and pre-configured slice information, and sending the network element operation information to the second access network element; the network element operation information is used for controlling the second access network element to communicate with the internet through the first access network element based on a target slice channel, wherein the target slice channel is a slice channel associated with slice information corresponding to the target service type.

In some optional embodiments of the present invention, before the fixed network slice management platform receives the mirrored traffic data from the first access network element, the method further includes:

configuring different slice information according to different service types, and sending the slice information to the second access network element; the slice information is used for establishing an associated slice channel for the second access network element.

In some alternative embodiments of the invention, the method further comprises:

determining a classification target of a machine learning model based on the slice information, and training the machine learning model according to the classification target;

the classifying the mirror image flow data to obtain a target service class includes:

and classifying the mirror image flow data based on the trained machine learning model to obtain the target service type.

In some optional embodiments of the present invention, the classifying the mirrored traffic data based on the trained machine learning model to obtain the target traffic class includes:

classifying the mirror image flow data based on a trained machine learning model to obtain the target service type and quintuple information in slice information corresponding to the target service type;

the determining network element operation information according to the target service type and the pre-configured slice information, and sending the network element operation information to the second access network element, includes:

correlating or unbinding the target service type and the quintuple information with the pre-configured slice information, and determining the network element operation information;

and sending the network element operation information and the quintuple information to the second access network element.

In some alternative embodiments of the invention, the method further comprises:

and receiving first network state data from the first access network element and/or second network state data from the second access network element, adjusting the slice information based on the first network state data and/or the second network state data, and sending the adjusted slice information to the second access network element.

In some alternative embodiments of the invention, the method further comprises:

and re-determining a classification target of the machine learning model based on the adjusted slice information, and re-training the machine learning model according to the re-determined classification target.

In some optional embodiments of the invention, the adjusting the slice information based on the first network state data and/or the second network state data comprises:

and adjusting slice attribute information in the slice information based on the first network state data and/or the second network state data, and/or adding and deleting slice information based on the first network state data and/or the second network state data.

In some optional embodiments of the invention, the slice attribute information comprises at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

In a second aspect, an embodiment of the present invention further provides a method for slice management, including:

the second access network element communicates with the Internet through the first access network element based on a pre-established slicing channel to obtain service flow data;

Receiving network element operation information from a fixed network slice management platform, and determining a target slice channel according to the network element operation information; the target slice channel is a slice channel associated with slice information corresponding to a target service type, and the target service type is determined by classifying mirror image data of the service flow data by the fixed network slice management platform;

and transmitting the service flow data corresponding to the target service type based on the target slice channel.

In some alternative embodiments of the invention, the method further comprises:

receiving slice information from the fixed network slice management platform, and establishing an associated slice channel based on the slice information; wherein different slice information corresponds to different service types.

In some optional embodiments of the present invention, the receiving network element operation information from the fixed network slice management platform, and determining the target slice channel according to the network element operation information, includes:

receiving the network element operation information and quintuple information from the fixed network slice management platform, and determining the target slice channel based on the network element operation information and the quintuple information; and the quintuple information is quintuple information in slice information corresponding to the target service type.

In some alternative embodiments of the invention, the method further comprises:

transmitting network state data to the fixed network slice management platform;

and receiving slice information adjusted by the fixed network slice management platform based on the network state data, and reestablishing an associated slice channel based on the adjusted slice information.

In some optional embodiments of the invention, the reestablishing the associated slice path based on the adjusted slice information comprises:

modifying attribute information of a slice channel associated with the slice information based on the adjusted slice information, and/or adding and deleting the associated slice channel based on the adjusted slice information.

In some optional embodiments of the present invention, the attribute information of the slicing channel includes at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

In a third aspect, an embodiment of the present invention further provides an apparatus for slice management, including:

the first communication module is used for receiving mirror image flow data from a first access network element; the mirror image flow data comprise mirror image data corresponding to service flow data communicated with the Internet by the second access network element through the first access network element based on a pre-established slicing channel;

The service classification module is used for classifying the mirror image flow data received by the first communication module to obtain a target service type;

the first processing module is used for determining network element operation information according to the target service type and the pre-configured slice information obtained by the service classification module; the network element operation information is used for controlling the second access network element to communicate with the internet through the first access network element based on a target slice channel, wherein the target slice channel is a slice channel associated with slice information corresponding to the target service type;

the first communication module is further configured to send the network element operation information to the second access network element.

In some alternative embodiments of the invention, the apparatus further comprises:

the slice arrangement module is used for configuring different slice information according to different service types;

the first communication module is further configured to send the slice information to the second access network element; the slice information is used for establishing an associated slice channel for the second access network element.

In some optional embodiments of the invention, the service classification module is further configured to determine a classification target of a machine learning model based on the slice information configured by the slice arrangement module, and train the machine learning model according to the classification target; and classifying the mirror image flow data received by the first communication module based on the trained machine learning model to obtain the target service type.

In some optional embodiments of the present invention, the service classification module is further configured to classify the mirror traffic data received by the first communication module based on a trained machine learning model, to obtain the target service class and quintuple information in slice information corresponding to the target service class;

the first processing module is further configured to associate or unbind the target service class and the quintuple information with the pre-configured slice information, and determine the network element operation information;

the first communication module is further configured to send the network element operation information and the quintuple information to the second access network element.

In some optional embodiments of the invention, the first communication module is further configured to receive first network status data from the first access network element and/or second network status data from the second access network element;

the slice arranging module is further configured to adjust the slice information based on the first network state data and/or the second network state data received by the first communication module;

the first communication module is further configured to send the slice information adjusted by the slice arrangement module to the second access network element.

In some optional embodiments of the present invention, the service classification module is further configured to re-determine a classification target of the machine learning model based on the slice information adjusted by the slice arrangement module, and re-train the machine learning model according to the re-determined classification target.

In some optional embodiments of the present invention, the slice arranging module is configured to adjust slice attribute information in the slice information based on the first network state data and/or the second network state data received by the first communication module, and/or add/delete slice information based on the first network state data and/or the second network state data received by the first communication module.

In a fourth aspect, an embodiment of the present invention further provides an apparatus for slice management, including:

the second communication module is used for communicating with the Internet through the first access network element based on a pre-established slicing channel to obtain service flow data;

The third communication module is used for receiving network element operation information from the fixed network slice management platform;

the second processing module is used for determining a target slice channel according to the network element operation information received by the third communication module; the target slice channel is a slice channel associated with slice information corresponding to a target service type, and the target service type is determined by classifying mirror image data of the service flow data by the fixed network slice management platform;

the second communication module is further configured to transmit service traffic data corresponding to the target service class based on the target slice channel.

In some optional embodiments of the present invention, the third communication module is further configured to receive slice information from the fixed network slice management platform;

the second processing module is further used for establishing an associated slice channel based on the slice information received by the third communication module; wherein different slice information corresponds to different service types.

In some optional embodiments of the present invention, the third communication module is further configured to receive the network element operation information and five-tuple information from the fixed network slice management platform;

The second processing module is further configured to determine the target slice channel based on the network element operation information and the quintuple information received by the third communication module; and the quintuple information is quintuple information in slice information corresponding to the target service type.

In some optional embodiments of the present invention, the third communication module is further configured to send network status data to the fixed network slice management platform; receiving slice information adjusted by the fixed network slice management platform based on the network state data;

the second processing module is further configured to reestablish an associated slice channel based on the adjusted slice information received by the third communication module.

In some optional embodiments of the present invention, the second processing module is configured to modify attribute information of a slice channel associated with the slice information based on the adjusted slice information received by the third communication module, and/or add/delete an associated slice channel based on the adjusted slice information received by the third communication module.

In a fifth aspect, embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.

In a sixth aspect, an embodiment of the present invention further provides a network device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the above method when executing the program.

The method, the device, the storage medium and the network equipment for slice management provided by the embodiment of the invention uniformly manage slices through the fixed network slice management platform, realize uniform configuration of network capacity, monitor the overall network quality and realize end-to-end quality analysis and positioning; meanwhile, on the same network infrastructure, the physical network is divided into a plurality of logically independent virtual networks, and each virtual network has different functional characteristics and can flexibly cope with different requirements and services.

Drawings

FIG. 1 is a schematic diagram of a fixed network slice management system according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method for slice management according to an embodiment of the present invention;

FIG. 3 is a second flow chart of a method for slice management according to an embodiment of the present invention;

FIG. 4 is a flow chart III of a method for slice management according to an embodiment of the present invention;

FIG. 5 is a flow chart of a method for slice management according to an embodiment of the present invention;

FIG. 6 is a flow chart of a method for slice management according to an embodiment of the present invention;

fig. 7 is a flow chart of a method for managing fixed network slices according to an embodiment of the invention;

fig. 8 is a schematic diagram of the composition structure of an apparatus for slice management according to an embodiment of the present invention;

fig. 9 is a schematic diagram of a second component structure of an apparatus for slice management according to an embodiment of the present invention;

fig. 10 is a schematic diagram of a third component structure of an apparatus for slice management according to an embodiment of the present invention;

fig. 11 is a schematic hardware structure of a network device according to an embodiment of the present invention.

Detailed Description

The invention will be described in further detail with reference to the accompanying drawings and specific examples.

Fig. 1 is a schematic diagram of an architecture of a fixed network slice management system according to an embodiment of the present invention. As shown in fig. 1, the fixed network slice management system in this embodiment may include a fixed network slice management platform, a first access network element, a second access network element, and a third access network element. The fixed network slice management platform is used as a control plane of the fixed network slice management system and is used for uniformly managing slices and realizing uniform configuration of network capacity; the first access network element, the second access network element and the third access network element belong to the field of access networks in the aspect of fixed network hierarchical division, and form a user data plane of the fixed network slice management system, wherein the second access network element is connected with the first access network element through the third access network element and communicates with the Internet through the first access network element.

The control plane is mainly responsible for arranging and issuing slice information, and perceiving service flow data from the network element of the access network to identify specific services; the user data plane is mainly responsible for forwarding user service flow data to the control plane, and constructs a slice channel according to slice information issued by the control plane. Meanwhile, the control plane is also responsible for sensing the network link state change of the user data plane, adjusting the slice information and issuing the access network element to execute the attribute of changing the slice channel so as to lead the specific service to be carried in different slice channels to realize the differentiated service.

In this embodiment, the first access network element may be a BRAS, which is configured to implement a network bearer function to connect to aggregate user traffic, and implement functions such as user access authentication, charging, and management. The second access network element can be a home gateway, and is used as an access point for various home service terminals to access the network, and is the core of the import and export of the home network and the intelligent home. The third access network element may be an optical line terminal (OLT, optical line terminal).

The following embodiments of the present invention are at least presented based on the fixed network slice management system shown in fig. 1, and it should be noted that fig. 1 is only an example of a fixed network slice management system to which the embodiments of the present invention are applicable, and the embodiments of the present invention are not limited to the system structure shown in fig. 1, and other system structures may also be within the scope of the embodiments of the present invention.

The embodiment of the invention provides a method for slice management, which is applied to a fixed network slice management platform. Fig. 2 is a flowchart of a method for slice management according to an embodiment of the present invention, as shown in fig. 2, the method includes:

step 101, a fixed network slice management platform receives mirror image flow data from a first access network element; the mirror image flow data comprise mirror image data corresponding to service flow data communicated with the Internet by the second access network element through the first access network element based on a pre-established slicing channel;

102, classifying the mirror image flow data to obtain a target service type;

step 103, determining network element operation information according to the target service type and the pre-configured slice information, and sending the network element operation information to the second access network element; the network element operation information is used for controlling the second access network element to communicate with the internet through the first access network element based on a target slice channel, wherein the target slice channel is a slice channel associated with slice information corresponding to the target service type.

In this embodiment, the second access network element establishes an associated slice channel in advance according to the preconfigured slice information. Taking a home gateway as an example, the pre-established slicing channel may be used to transmit traffic data corresponding to all home services, or may be used only to transmit traffic data corresponding to specific services, such as a cloud game, a high-definition video call, an AR/VR and other emerging digital home services. The second access network element can realize an end-to-end, virtual, isolated and customized special logic network through a slicing channel, thereby realizing one-network multi-purpose.

As an example, the fixed network slice management platform pre-configures corresponding slice information according to different types of services, and issues the slice information to the second access network element, so that the second access network element establishes an associated slice channel according to the slice information.

Optionally, the slice information may include a slice name, a specific service type, a slice level, five-tuple information, a network guarantee duration, a guaranteed flow limit, slice attribute information, and the like, where the slice name may be used to identify and distinguish different slice information, the service type may be used to identify a service type that can be carried by a slice channel associated with the corresponding slice information, the slice level may be used to identify a capability of a slice network, for example, according to an existing network capability, combining capabilities of wireless, transmission, core network, security, operation, and the like, and a deployment policy most likely to match the network is formed at a plurality of slice levels to satisfy three major demands of 5G to public network users, general industry users, and special industry users. The five-tuple information includes information of a service source IP address, a source port number, a destination IP address, a destination port number, a transport layer protocol, and the like. The slice attribute information represents SLA related parameters of the slice network, and specifically comprises a service guarantee level, a fixed uplink and downlink bandwidth, a maximum time delay of service guarantee, a maximum jitter of service guarantee, a maximum packet loss rate of service guarantee and the like.

The second access network element communicates with the Internet through the first access network element based on a pre-established slicing channel to obtain service flow data, and the first access network element is used as a network bearing unit to mirror the service flow data and then send the mirror image to a fixed network slicing management platform. It should be noted that the mirror image traffic data includes mirror image data corresponding to uplink traffic data transmitted from the second access network element to the internet, and mirror image data corresponding to downlink traffic data transmitted from the internet to the second access network element.

In step 102, the fixed network slice management platform classifies the mirror image traffic data to obtain target service types corresponding to the service traffic data, for example, the target service types may be game service, video service, etc., according to the pre-configured slice information, the game service may be implemented based on the game slice, and the video service may be implemented based on the video slice.

In step 103, network element operation information is determined according to the target service type and pre-configured slice information, the network element operation information is issued to a second access network element, the second access network element can switch from a pre-established slice channel to a target slice channel associated with slice information corresponding to the target service type according to the network element operation information, and communicate with the internet through a first access network element based on the target slice channel, and the fixed network slice management platform determines the corresponding service type as game service according to mirror image flow data classification, further determines the network element operation information according to game slices and issues the same, and the home gateway can switch from a common slice channel for transmitting non-specific service data to a specific slice channel for transmitting game service data after receiving the network element operation information. Subsequently, steps 101 to 103 are repeatedly performed, so that different services are carried on different logic channels/slicing channels.

According to the embodiment of the invention, the fixed network slice management platform is used for uniformly managing slices, so that uniform configuration of network capacity is realized, the quality of the whole network can be monitored, and end-to-end quality analysis and positioning are realized; meanwhile, on the same network infrastructure, the physical network is divided into a plurality of logically independent virtual networks, each virtual network has different functional characteristics, different demands and services can be flexibly met, the virtual networks are isolated from each other, and one virtual network cannot be influenced by faults.

The embodiment of the invention also provides a method for slice management, which is applied to the fixed network slice management platform. Fig. 3 is a second flowchart of a method for slice management according to an embodiment of the present invention, as shown in fig. 3, where the method includes:

step 201, configuring different slice information according to different service types by a fixed network slice management platform, and sending the slice information to a second access network element; the slice information is used for establishing an associated slice channel by the second access network element;

step 202, determining a classification target of a machine learning model based on the slice information, and training the machine learning model according to the classification target;

Step 203, receiving mirror image traffic data from a first access network element; the mirror image flow data comprise mirror image data corresponding to service flow data communicated with the Internet by the second access network element through the first access network element based on a pre-established slicing channel;

step 204, classifying the mirror image flow data based on a trained machine learning model to obtain a target service type;

step 205, determining network element operation information according to the target service type and the pre-configured slice information, and sending the network element operation information to the second access network element; the network element operation information is used for controlling the second access network element to communicate with the internet through the first access network element based on a target slice channel, wherein the target slice channel is a slice channel associated with slice information corresponding to the target service type.

The descriptions of the

steps

203 and 205 in this embodiment may refer to the descriptions of the

steps

101 and 103 in the foregoing embodiments, which are not repeated here for the sake of brevity.

In step 201, the fixed network slice management platform may configure different slice information for emerging digital home services such as cloud games, high definition video calls, AR/VR and other services, specifically including slice names, service types, slice levels, quintuple information, network guarantee duration, guaranteed flow limit, slice attribute information and the like, and issue the configured slice information to a second access network element, where the second access network element establishes an associated slice channel according to the slice information, and realizes service data transmission based on the slice channel.

On the other hand, the fixed network slice management platform determines a classification target of a machine learning model based on configured slice information, and trains the machine learning model according to the classification target. In this embodiment, the machine learning model is configured to classify mirror traffic data to obtain a service class corresponding to the mirror traffic data, and illustratively, the input of the machine learning model may be traffic data, and the output may include the corresponding service class. In step 202, based on the service types corresponding to the slice information, a classification target of the machine learning model is determined, and the machine learning model is trained according to the classification target and training data corresponding to each classification target, so as to obtain a trained machine learning model, wherein the training data can be from an external database, or can be historical traffic data from an access network element and corresponding classification targets received by a fixed network slice management platform.

In step 204, the fixed network slice management platform classifies the received mirror image traffic data based on the trained machine learning model, and obtains the target service type corresponding to the mirror image traffic data. In step 205, corresponding slice information is determined according to the configured plurality of slice information of the target service type, and network element operation information is generated and issued to the access network element, so that the access network element changes the slice channel for transmitting uplink and downlink service traffic data according to the network element operation information. It should be noted that, in this embodiment, the sending the network element operation information to the second access network element may include: and sending the network element operation information to the second access network element through the first access network element.

The embodiment of the invention divides the traditional fixed network access network into a control plane and a user data plane through the fixed network slice management platform, the user data plane and the control plane have clear responsibilities, and the user data plane is responsible for forwarding user service traffic; the control plane is responsible for arranging slice information, adopts a machine learning model to analyze and learn flow data reported by a user data plane, and issues operation instructions for constructing different service slice channels of different users, so that the access network gateway can provide the slice channels isolated from each other and ensuring the service quality according to service characteristics.

As an alternative embodiment, the output data of the machine learning model may further include quintuple information, so step 204 may include: and classifying the mirror image flow data based on a trained machine learning model to obtain the target service type and quintuple information in slice information corresponding to the target service type.

Accordingly, in the step 205, network element operation information is determined according to the target service type and the preconfigured slice information, and the network element operation information is sent to the second access network element, which includes: correlating or unbinding the target service type and the quintuple information with the pre-configured slice information, and determining the network element operation information; and sending the network element operation information and the quintuple information to the second access network element.

In this embodiment, the machine learning model is used to classify the mirror traffic data, obtain the target service class corresponding to the mirror traffic data and quintuple information in the slice information corresponding to the target service class, associate or unbind the target service class and quintuple information with the slice information configured in step 201, for example, a game service associated game class slice, a video service associated video class slice, where the quintuple information can be used for the second access network element to perform uplink and downlink service traffic data transmission based on the slice channel associated with the slice information corresponding to the target service class.

Based on the foregoing embodiment, steps 201 to 205, the embodiment of the present invention further provides an image processing method. Fig. 4 is a flowchart third of a method for slice management according to an embodiment of the present invention, as shown in fig. 4, where the method further includes:

step 206, receiving first network state data from the first access network element and/or second network state data from the second access network element, adjusting the slice information based on the first network state data and/or the second network state data, and sending the adjusted slice information to the second access network element;

Step 207, redetermining a classification target of the machine learning model based on the adjusted slice information, and retraining the machine learning model according to the redetermined classification target.

For a home gateway, various SLA requirements (such as bandwidth, time delay, safety and the like) are required for various home services, all requirements cannot be met efficiently and economically by one network, and in order to meet the requirements of operators on the refined operation of the home services, the network is required to have the capability of intelligently guaranteeing different services. The intelligent guarantee capability of the network is embodied in two aspects, namely, differentiated service indexes such as time delay, uplink bandwidth, downlink bandwidth and the like aiming at different services, and the capability of dynamically adjusting the state of a network link, such as dynamically sensing network congestion phenomenon and optimizing routing.

In this embodiment, the first network state data and the second network state data are current network state data reported by the first access network element and the second access network element to the fixed network slice management platform respectively, so that the current network congestion condition can be reflected, the fixed network slice management platform adjusts slice information according to the network state data reported by each access network element in real time, sends the adjusted slice information to each access network element, and simultaneously determines a classification target of the machine learning model based on the adjusted slice information again, retrains the model, and repeatedly executes steps 203 to 207.

It should be noted that, in this embodiment, the fixed network slice management platform may further receive third network state data from the third access network element described in fig. 1, where both the second network state data and the third network state data may be reported to the fixed network slice management platform via the first access network element.

As an alternative embodiment, said adjusting the slice information based on the first network state data and/or the second network state data comprises: and adjusting slice attribute information in the slice information based on the first network state data and/or the second network state data, and/or adding and deleting slice information based on the first network state data and/or the second network state data. Illustratively, the slice attribute information includes at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

According to the embodiment, slice attribute information is adjusted or slices are added and deleted in real time according to network state data, the dynamic adjustment capability is achieved, meanwhile, the machine learning model is utilized to analyze and learn user data plane reporting data, the current network dynamic information can be displayed in a panoramic view, the current network dynamic information can be evolved to a unified arrangement control scheme subsequently, a basis is provided for analyzing and positioning network problems, and the method has the characteristics of achieving efficient identification of a full path, intelligent arrangement of services and guarantee of service differentiation.

The embodiment of the invention also provides a method for slice management, which is applied to the second access network element. Fig. 5 is a flow chart of a method for slice management according to an embodiment of the present invention, as shown in fig. 5, the method includes:

step 301, the second access network element communicates with the internet through the first access network element based on a pre-established slicing channel to obtain service flow data;

step 302, receiving network element operation information from a fixed network slice management platform, and determining a target slice channel according to the network element operation information; the target slice channel is a slice channel associated with slice information corresponding to a target service type, and the target service type is determined by classifying mirror image data of the service flow data by the fixed network slice management platform;

and 303, transmitting service flow data corresponding to the target service type based on the target slice channel.

In this embodiment, the second access network element may first construct a common slice channel for transmitting non-specific service data based on pre-configured slice information or slice information from a fixed network slice management platform, and communicate with the internet based on the slice channel to obtain uplink and downlink service traffic data. And then, receiving network element operation information from a fixed network slice management platform, determining target slice channels corresponding to different kinds of service flow data according to the network element operation information, and respectively transmitting corresponding service flow data based on each target slice channel.

The second access network element is a home gateway, and based on the same network infrastructure, the physical network is divided into a plurality of virtual networks with independent logic, for example, a specific slicing channel for realizing services with higher network SLA requirements such as cloud games, live broadcast in real time, high definition video calls, AR/VR and the like, and a common slicing channel for realizing other services; or, slice channels respectively used for different services, such as a game slice channel used for game services, a video slice channel used for services such as live broadcast, high definition video call and the like, an office slice channel used for remote office services and the like. It can be appreciated that the type and number of the second access network element to establish the slicing channels depends on the refinement degree of the network operation and the device capability, and may be used to transmit different service data based on different slicing channels, or may be used to transmit different service data based on the same slicing channel.

According to the second access network element provided by the embodiment of the invention, the slice networks which are mutually isolated and guaranteed in service quality can be realized according to service characteristics under the unified management of the fixed network slice management platform aiming at different service scenes, and the full-flow light-weight slice service can be provided for home users.

The embodiment of the invention also provides a method for slice management, which is applied to the second access network element. Fig. 6 is a flowchart fifth of a method for slice management according to an embodiment of the present invention, as shown in fig. 6, where the method includes:

step 401, a second access network element receives slice information from a fixed network slice management platform, and establishes an associated slice channel based on the slice information; wherein different slice information corresponds to different service types;

step 402, communicating with the internet via a first access network element based on a pre-established slicing channel to obtain service flow data;

step 403, receiving network element operation information from the fixed network slice management platform, and determining a target slice channel according to the network element operation information; the target slice channel is a slice channel associated with slice information corresponding to a target service type, and the target service type is determined by classifying mirror image data of the service flow data by the fixed network slice management platform;

step 404, transmitting service flow data corresponding to the target service type based on the target slice channel;

step 405, sending network status data to the fixed network slice management platform; and receiving slice information adjusted by the fixed network slice management platform based on the network state data, and reestablishing an associated slice channel based on the adjusted slice information.

The descriptions of the steps 402 to 404 in this embodiment may be referred to the descriptions of the steps 301 to 303 in the foregoing embodiments, and are not repeated here for brevity.

In step 401, the second access network element may receive, through the first access network element, slice information sent from the fixed network slice management platform, where different slice information corresponds to different service types, and the second access network element establishes an associated slice channel according to the slice information. It should be noted that different slice information may be associated with the same slice channel, or may be associated with different slice channels, that is, different kinds of services may be implemented based on the same slice channel. For details of the slice information, reference may be made to the description of the foregoing embodiments, and details are not repeated here.

As an example, in step 403, the receiving network element operation information from the fixed network slice management platform, and determining the target slice channel according to the network element operation information may include: receiving the network element operation information and quintuple information from the fixed network slice management platform, and determining the target slice channel based on the network element operation information and the quintuple information; and the quintuple information is quintuple information in slice information corresponding to the target service type.

The second access network element changes a target slice channel corresponding to the service flow data according to the network element operation information, and determines a source IP address, a source port, a destination IP address, a destination port and a transport layer protocol corresponding to the changed target slice channel based on the quintuple information.

In step 405, the second access network element sends network status data to the fixed network slice management platform in real time, so that the platform monitors the network congestion status and issues and analyzes the adjusted slice information in real time, and the second access network element reestablishes an associated slice channel based on the adjusted slice information and reestablishes transmission of service traffic data based on the associated slice channel.

As an optional implementation manner, in step 405, reestablishing the associated slice channel based on the adjusted slice information may include: modifying attribute information of a slice channel associated with the slice information based on the adjusted slice information, and/or adding and deleting the associated slice channel based on the adjusted slice information. Illustratively, the attribute information of the slicing channel includes at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

In this embodiment, the second access network element changes attribute information of the slice channel according to the adjusted slice information, or establishes a new slice channel or deletes an established slice channel, and transmits corresponding uplink and downlink traffic flow data based on the adjusted slice channel.

The following describes a fixed network slice management scheme according to an embodiment of the present invention in connection with a specific home service application scenario. Fig. 7 is a flow chart of a fixed network slice management method provided by the embodiment of the present invention, and as shown in fig. 7, the fixed network slice management method applied to a fixed network slice management platform, a BRAS and a home gateway includes:

and step 501, configuring various slice information by the fixed network slice management platform, and sending the slice information to the home gateway through the BRAS.

The slice information mainly relates to slice names, specific family service types, slice grades, quintuple information, network guarantee duration, guaranteed flow limit and SLA related parameters such as service guarantee grades, fixed uplink and downlink bandwidths, maximum time delay of service guarantee, maximum jitter of service guarantee, maximum packet loss rate of service guarantee and the like.

Step 502, the fixed network slice management platform determines a classification target of the machine learning model based on the slice information, and trains the machine learning model according to the classification target.

And step 503, the home gateway establishes an associated slice channel based on the slice information.

And 504, the home gateway communicates with the Internet through the BRAS based on the established slicing channel to obtain uplink and downlink service flow data.

Step 505, the BRAS mirrors the uplink and downlink traffic data to the fixed network slice management platform respectively.

Step 506, the fixed network slicing management platform classifies the mirror image flow data based on the trained machine learning model, the classification result includes the flow attribution service type, five-tuple information and the like, and the classification result is associated with or unbinding slicing information, such as the game service is changed from the original slicing channel to the game type slicing channel.

And 507, the fixed network slice management platform transmits quintuple information and related association and unbinding operations to access network elements such as a home gateway.

And step 508, the home gateway changes the uplink and downlink service flow data into the corresponding slicing channel according to the issued five-tuple information and the operation information.

Step 509, the network elements of the access network such as the BRAS and the home gateway report the network state data in real time.

And 510, adjusting SLA related parameters in slice information or adding and deleting slice information by the fixed network slice management platform according to the reported network state data, and synchronizing the adjusted slice information to access network elements such as a home gateway and the like.

Step 511, the fixed network slice management platform re-determines the classification target of the machine learning model based on the adjusted slice information, and retrains the machine learning model according to the re-determined classification target.

Step 512, the home gateway changes the slice channel attribute or adds and deletes the slice channel.

The steps 504 to 508 and 509 to 512 are not performed in the same order.

The embodiment is based on the current network situation, introduces a fixed network slice management platform, and does not make large-scale adjustment on the whole, thereby constructing a closed-loop structure. The method provides slicing channels which are isolated from each other and ensure the service quality according to the service characteristics, has the capability of dynamic adjustment, can be evolved to a unified arrangement control scheme, and has the characteristics of realizing efficient identification of a full path, intelligent arrangement of the service and differential guarantee of the service. Meanwhile, the machine learning model analyzes and learns the data reported by the user data plane, can display network dynamic information in a panoramic view, and provides basis for analyzing and positioning network problems.

The embodiment of the invention also provides a device for slice management. Fig. 8 is a schematic diagram of the composition structure of an apparatus for slice management according to an embodiment of the present invention, as shown in fig. 8, an apparatus 600 for slice management includes:

A first communication module 601, configured to receive mirror traffic data from a first access network element; the mirror image flow data comprise mirror image data corresponding to service flow data communicated with the Internet by the second access network element through the first access network element based on a pre-established slicing channel;

the service classification module 602 is configured to classify the mirror image traffic data received by the first communication module 601 to obtain a target service class;

and a first processing module 603, configured to determine network element operation information according to the target service class and preconfigured slice information obtained by the service classification module 602; the network element operation information is used for controlling the second access network element to communicate with the internet through the first access network element based on a target slice channel, wherein the target slice channel is a slice channel associated with slice information corresponding to the target service type;

the first communication module 601 is further configured to send the network element operation information to the second access network element.

In an alternative embodiment of the present invention, as shown in fig. 9, the apparatus 600 further includes:

a slice arranging module 604, configured to configure different slice information according to different service types;

The first communication module 601 is further configured to send the slice information to the second access network element; the slice information is used for establishing an associated slice channel for the second access network element.

In an alternative embodiment of the present invention, the service classification module 602 is further configured to determine a classification target of a machine learning model based on the slice information configured by the slice arrangement module 604, and train the machine learning model according to the classification target; and classifying the mirror image traffic data received by the first communication module 601 based on a trained machine learning model to obtain the target service class.

In an optional embodiment of the present invention, the service classification module 602 is further configured to classify the mirror image traffic data received by the first communication module 601 based on a trained machine learning model, to obtain the target service type and quintuple information in slice information corresponding to the target service type;

the first processing module 603 is further configured to associate or unbind the target service class and the quintuple information with the slice information configured in advance, and determine the network element operation information;

The first communication module 601 is further configured to send the network element operation information and the quintuple information to the second access network element.

In an alternative embodiment of the present invention, the first communication module 601 is further configured to receive first network status data from the first access network element and/or second network status data from the second access network element;

the slice arranging module 604 is further configured to adjust the slice information based on the first network state data and/or the second network state data received by the first communication module 601;

the first communication module 601 is further configured to send the slice information adjusted by the slice arrangement module 604 to the second access network element.

In an alternative embodiment of the present invention, the service classification module 602 is further configured to re-determine a classification target of the machine learning model based on the slice information adjusted by the slice arrangement module 604, and re-train the machine learning model according to the re-determined classification target.

In an optional embodiment of the present invention, the slice arranging module 604 is configured to adjust slice attribute information in the slice information based on the first network state data and/or the second network state data received by the first communication module 601, and/or add/delete slice information based on the first network state data and/or the second network state data received by the first communication module 601.

In an alternative embodiment of the present invention, the slice attribute information includes at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

In the embodiment of the present invention, the service classification module 602, the first processing module 603 and the slice arranging module 604 in the apparatus 600 may be implemented by a central processing unit (CPU, central Processing Unit), a digital signal processor (DSP, digital Signal Processor), a micro control unit (MCU, microcontroller Unit) or a programmable gate array (FPGA, field-Programmable Gate Array) in the apparatus 600 in practical applications; the first communication module 601 in the device 600 may be implemented in practical applications by a communication module (including a basic communication suite, an operating system, a communication module, a standardized interface and protocol, etc.) and a transceiver antenna.

It should be noted that: in the apparatus for slice management provided in the above embodiment, only the division of each program module is used for illustration, and in practical application, the process allocation may be performed by different program modules according to needs, that is, the internal structure of the apparatus is divided into different program modules to complete all or part of the processes described above. In addition, the apparatus for slice management provided in the foregoing embodiments and the method embodiment for slice management applied to the fixed network slice management platform belong to the same concept, and detailed implementation processes of the apparatus for slice management are referred to the method embodiment, which is not repeated herein.

The embodiment of the invention also provides a device for slice management. Fig. 10 is a schematic diagram of a third component structure of an apparatus for slice management according to an embodiment of the present invention, as shown in fig. 10, an apparatus 700 for slice management includes:

a second communication module 701, configured to communicate with the internet via the first access network element based on a pre-established slicing channel, to obtain service traffic data;

a third communication module 702, configured to receive network element operation information from the fixed network slice management platform;

and a second processing module 703, configured to determine a target slice channel according to the network element operation information received by the third communication module 702; the target slice channel is a slice channel associated with slice information corresponding to a target service type, and the target service type is determined by classifying mirror image data of the service flow data by the fixed network slice management platform;

the second communication module 701 is further configured to transmit service traffic data corresponding to the target service class based on the target slice channel.

In an alternative embodiment of the present invention, the third communication module 702 is further configured to receive slice information from the fixed network slice management platform;

A second processing module 703, configured to establish an associated slice channel based on the slice information received by the third communication module 702; wherein different slice information corresponds to different service types.

In an alternative embodiment of the present invention, the third communication module 702 is further configured to receive the network element operation information and five-tuple information from the fixed network slice management platform;

the second processing module 703 is further configured to determine the target slice channel based on the network element operation information and the quintuple information received by the third communication module 702; and the quintuple information is quintuple information in slice information corresponding to the target service type.

In an alternative embodiment of the present invention, the third communication module 702 is further configured to send network status data to the fixed network slice management platform; receiving slice information adjusted by the fixed network slice management platform based on the network state data;

the second processing module 703 is further configured to reestablish an associated slice channel based on the adjusted slice information received by the third communication module 702.

In an optional embodiment of the invention, the second processing module 703 is configured to modify attribute information of a slice channel associated with the slice information based on the adjusted slice information received by the third communication module 702, and/or add or delete an associated slice channel based on the adjusted slice information received by the third communication module 702.

In an alternative embodiment of the present invention, the attribute information of the slicing channel includes at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

In the embodiment of the present invention, the second processing module 703 in the apparatus 700 may be implemented by CPU, DSP, MCU or FPGA in the apparatus 700 in practical application; the second communication module 701 and the third communication module 702 in the device 700 may be implemented in practical applications by a communication module (including a basic communication suite, an operating system, a communication module, a standardized interface, a standardized protocol, etc.) and a transceiver antenna.

It should be noted that: in the apparatus for slice management provided in the above embodiment, only the division of each program module is used for illustration, and in practical application, the process allocation may be performed by different program modules according to needs, that is, the internal structure of the apparatus is divided into different program modules to complete all or part of the processes described above. In addition, the apparatus for slice management provided in the foregoing embodiment belongs to the same concept as the method embodiment for slice management applied in the second access network element, and the specific implementation process of the apparatus for slice management is detailed in the method embodiment, which is not repeated herein.

The embodiment of the invention also provides network equipment. Fig. 11 is a schematic hardware structure of a network device according to an embodiment of the present invention, where the network device 800 may be a computer, a virtual machine, an information transceiver device, a console, or the like. The network device 800 shown in fig. 11 includes: at least one processor 801, memory 802, and at least one network interface 803. The various components in network device 800 are coupled together by bus system 804. It is to be appreciated that the bus system 804 is employed to enable connected communications between these components. The bus system 804 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration the various buses are labeled as bus system 804 in fig. 11.

It is to be appreciated that memory 802 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. Wherein the nonvolatile Memory may be Read Only Memory (ROM), programmable Read Only Memory (PROM, programmable Read-Only Memory), erasable programmable Read Only Memory (EPROM, erasable Programmable Read-Only Memory), electrically erasable programmable Read Only Memory (EEPROM, electrically Erasable Programmable Read-Only Memory), magnetic random access Memory (FRAM, ferromagnetic random access Memory), flash Memory (Flash Memory), magnetic surface Memory, optical disk, or compact disk Read Only Memory (CD-ROM, compact Disc Read-Only Memory); the magnetic surface memory may be a disk memory or a tape memory. The volatile memory may be random access memory (RAM, random Access Memory), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (SRAM, static Random Access Memory), synchronous static random access memory (SSRAM, synchronous Static Random Access Memory), dynamic random access memory (DRAM, dynamic Random Access Memory), synchronous dynamic random access memory (SDRAM, synchronous Dynamic Random Access Memory), double data rate synchronous dynamic random access memory (ddr SDRAM, double Data Rate Synchronous Dynamic Random Access Memory), enhanced synchronous dynamic random access memory (ESDRAM, enhanced Synchronous Dynamic Random Access Memory), synchronous link dynamic random access memory (SLDRAM, syncLink Dynamic Random Access Memory), direct memory bus random access memory (DRRAM, direct Rambus Random Access Memory). The memory 802 described by embodiments of the present invention is intended to comprise, without being limited to, these and any other suitable types of memory.

The memory 802 in embodiments of the present invention is used to store various types of data to support the operation of the network device 800. Examples of such data include: any computer program for operating on the network device 800, such as a machine learning model in the method of an embodiment of the present invention, training data for training the machine learning model, and stored upstream and downstream traffic data, mirrored traffic data, network state data, etc.

The method disclosed in the above embodiment of the present invention may be applied to the processor 801 or implemented by the processor 801. The processor 801 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware in the processor 801 or by instructions in software. The processor 801 may be a general purpose processor, DSP, or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The processor 801 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in the embodiment of the invention can be directly embodied in the hardware of the decoding processor or can be implemented by combining hardware and software modules in the decoding processor. The software modules may be located in a storage medium in a memory 802. The processor 801 reads information from the memory 802 and in combination with its hardware performs the steps of the method described above.

In an exemplary embodiment, the network device 800 may be implemented by one or more application specific integrated circuits (ASICs, application Specific Integrated Circuit), DSPs, programmable logic devices (PLDs, programmable Logic Device), complex programmable logic devices (CPLDs, complex Programmable Logic Device), FPGAs, general purpose processors, controllers, MCUs, microprocessors, or other electronic elements for performing the aforementioned methods.

In an exemplary embodiment, the present invention also provides a computer readable storage medium, such as a memory 802, comprising a computer program executable by the processor 801 of the network device 800 to perform the steps described in the foregoing methods. The computer readable storage medium may be FRAM, ROM, PROM, EPROM, EEPROM, flash Memory, magnetic surface Memory, optical disk, or CD-ROM; but may be a variety of devices including one or any combination of the above-described memories, such as a mobile phone, computer, tablet device, personal digital assistant, or the like.

The methods disclosed in the several method embodiments provided in the present application may be arbitrarily combined without collision to obtain a new method embodiment.

The features disclosed in the several product embodiments provided in the present application may be combined arbitrarily without conflict to obtain new product embodiments.

The features disclosed in the several method or apparatus embodiments provided in the present application may be arbitrarily combined without conflict to obtain new method embodiments or apparatus embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.

The units described as separate units may or may not be physically separate, and units displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable storage medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.

Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for slice management, the method comprising:

classifying the mirror image flow data to obtain a target service type;

2. The method of claim 1, wherein before the fixed network slice management platform receives mirrored traffic data from a first access network element, the method further comprises:

3. The method according to claim 2, wherein the method further comprises:

4. The method of claim 3, wherein classifying the mirrored traffic data based on the trained machine learning model to obtain the target traffic class comprises:

5. The method according to claim 3 or 4, characterized in that the method further comprises:

6. The method of claim 5, wherein the method further comprises:

7. The method according to claim 5 or 6, wherein said adjusting the slice information based on the first network state data and/or the second network state data comprises:

8. The method of claim 7, wherein the slice attribute information comprises at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

9. A method for slice management, the method comprising:

10. The method according to claim 9, wherein the method further comprises:

11. The method of claim 9, wherein receiving network element operation information from a fixed network slice management platform, determining a target slice path based on the network element operation information, comprises:

12. The method according to claim 10 or 11, characterized in that the method further comprises:

transmitting network state data to the fixed network slice management platform;

13. The method of claim 12, wherein the reestablishing the associated slice path based on the adjusted slice information comprises:

14. The method of claim 13, wherein the slice channel attribute information comprises at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

15. An apparatus for slice management, the apparatus comprising:

16. The apparatus of claim 15, wherein the apparatus further comprises:

17. The apparatus of claim 16, wherein the traffic classification module is further configured to determine a classification target for a machine learning model based on the slice information configured by the slice orchestration module, the machine learning model being trained in accordance with the classification target; and classifying the mirror image flow data received by the first communication module based on the trained machine learning model to obtain the target service type.

18. The apparatus of claim 17, wherein the service classification module is further configured to classify the mirrored traffic data received by the first communication module based on a trained machine learning model to obtain five-tuple information in the target service class and slice information corresponding to the target service class;

19. The apparatus according to claim 17 or 18, wherein the first communication module is further configured to receive first network state data from the first access network element and/or second network state data from the second access network element;

20. The apparatus of claim 19, wherein the traffic classification module is further configured to re-determine a classification target for the machine learning model based on the slice information adjusted by the slice orchestration module, and re-train the machine learning model based on the re-determined classification target.

21. The apparatus according to claim 19 or 20, wherein the slice orchestration module is configured to adjust slice attribute information in the slice information based on the first network state data and/or the second network state data received by the first communication module, and/or to add/delete slice information based on the first network state data and/or the second network state data received by the first communication module.

22. The apparatus of claim 21, wherein the slice attribute information comprises at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

23. An apparatus for slice management, the apparatus comprising:

24. The apparatus of claim 23, wherein the third communication module is further configured to receive slice information from the fixed network slice management platform;

25. The apparatus of claim 24, wherein the third communication module is further configured to receive the network element operation information and five-tuple information from the fixed network slice management platform;

26. The apparatus of claim 24 or 25, wherein the third communication module is further configured to send network status data to the fixed network slice management platform; receiving slice information adjusted by the fixed network slice management platform based on the network state data;

27. The apparatus of claim 26, wherein the second processing module is configured to modify attribute information of a slice channel associated with the slice information based on the adjusted slice information received by the third communication module, and/or to add or delete an associated slice channel based on the adjusted slice information received by the third communication module.

28. The apparatus of claim 27, wherein the slice channel attribute information comprises at least one of: service guarantee level, fixed uplink and downlink bandwidth, maximum time delay of service guarantee, maximum jitter of service guarantee and maximum packet loss rate of service guarantee.

29. A computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor realizes the steps of the method according to any of claims 1 to 8; alternatively, the program when executed by a processor implements the steps of the method of any of claims 9 to 14.

30. A network device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the program is executed; alternatively, the program when executed by a processor performs the steps of the method of any of claims 8 to 14.