CN113490279A - Network slice configuration method and device - Google Patents
Network slice configuration method and device Download PDFInfo
- Publication number
- CN113490279A CN113490279A CN202110681375.9A CN202110681375A CN113490279A CN 113490279 A CN113490279 A CN 113490279A CN 202110681375 A CN202110681375 A CN 202110681375A CN 113490279 A CN113490279 A CN 113490279A
- Authority
- CN
- China
- Prior art keywords
- network
- slice
- network slice
- virtual network
- deploying
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000002955 isolation Methods 0.000 claims abstract description 53
- 230000006870 function Effects 0.000 claims description 69
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002787 reinforcement Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 abstract description 8
- 238000005457 optimization Methods 0.000 description 13
- 230000009471 action Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 3
- 230000006855 networking Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/54—Allocation or scheduling criteria for wireless resources based on quality criteria
-
- 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
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
- H04W28/24—Negotiating SLA [Service Level Agreement]; Negotiating QoS [Quality of Service]
Abstract
The application discloses a network slice configuration method and a device, wherein the network slice configuration method is executed on a controller in a network slice management system and comprises the following steps: acquiring a network slice; the network slice corresponds to a sequence formed by at least two virtual network functional units; determining a state set of resource utilization of the network slice to an infrastructure network in a corresponding configuration thread; and deploying the virtual network function units in the sequence according to the requirement of the application borne by the network slice on the safety and the state set, so as to realize the configuration of the network slice. The method and the device realize the customized isolation mechanism of the slices and improve the usability of the slices.
Description
Technical Field
The present application relates to the field of network slicing technologies, and in particular, to a method and an apparatus for configuring a network slice.
Background
The 5G era has rich vertical industry application, and the requirements of each service on time delay, bandwidth, node load balance and the like are greatly different. A single physical network has not been able to simultaneously meet the SLA requirements of the various industries mentioned above. Personalized and differentiated service requirements urge the generation of 5G network slices.
The network slice is a networking mode according to needs, an operator can separate a plurality of virtual end-to-end networks on a unified infrastructure, and each network slice is logically isolated from a wireless network, a bearer network and a core network so as to adapt to various types of applications. The NFV (network function virtualization) is the core of a network slicing technology, hardware and software parts are separated from a traditional network by the NFV, the hardware is deployed by a uniform server, the software is born by different network functions, a logic network can be generated on one physical network as required, and multiple slices can be provided for the same user to realize various bandwidth, time delay, node load balancing and slice isolation services under different requirements, so that the requirement of flexibly assembling services is met.
A network slice provides a logical network of specific network functions and network features. The network slice enables the network resources to be decoupled from the deployment positions of the network resources, and the flexibility and the resource utilization rate of the network service are improved. How to intelligently arrange network functions according to the requirements of service scenes is an important problem of 5G network slice operation.
Disclosure of Invention
In view of this, the present application provides a method and an apparatus for configuring a network slice, which solve how to intelligently arrange network functions according to the needs of a service scenario in 5G network slice operation.
In order to achieve the above object, an embodiment of the present application provides a network slice configuration method, where the network slice configuration method is executed on a controller in a network slice management system, and the method includes:
acquiring a network slice; the network slice corresponds to a sequence formed by at least two virtual network functional units;
determining a state set of resource utilization of the network slice to an infrastructure network in a corresponding configuration thread;
and deploying the virtual network function units in the sequence according to the requirement of the application borne by the network slice on the safety and the state set, so as to realize the configuration of the network slice.
Correspondingly, in order to achieve the above object, the present application provides a network slice configuration apparatus, where the network slice configuration apparatus includes a memory and a processor; wherein the memory is to store computer program instructions; the processor is configured to execute the computer program instructions to implement the network slice configuration method described above.
Through the technical means, the following beneficial effects can be realized:
the application provides a network slice configuration scheme, which is oriented to network slice intelligent collaborative arrangement of availability and QoS optimization. Firstly, the scheme starts from a three-level safety isolation mode of the slices, and by limiting the differentiated isolation level requirements as constraint conditions, a customized isolation mechanism of the slices is realized, specifically including inter-slice isolation and intra-slice isolation, and the slice availability is improved. Secondly, by cooperating with the core data center and the edge data center, the bandwidth is effectively saved and the network delay is reduced in the aspect of QoS optimization. In addition, the method provides a dedicated scheduling optimization target matched with the service requirement, and differentiates the differentiated requirements of different slices on time delay, bandwidth and node load balance.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a 5G network slice overall architecture diagram;
fig. 2 is a flowchart of a network slice configuration method proposed in the present application;
fig. 3 is a schematic diagram of a network slice configuration apparatus according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
NFV, Network Function Virtualization. Many types of Network devices (such as servers, switches, and storage) are constructed as a Data Center Network, and very multifunctional software processing is carried by using general-purpose hardware such as x86 and virtualization technology. Thereby reducing the cost of expensive equipment for the network. The functions of the network equipment do not depend on special hardware any more, resources can be shared fully and flexibly, and the rapid development and deployment of new services are realized.
The VNF, which refers to a specific virtual network function, provides a certain network service, and is implemented at a software level, and is deployed in a resource on a cloud side by using an infrastructure provided by the NFVI. Resources on the cloud side include, but are not limited to, virtual machines, containers, or barrel-metal physical machines.
Further, a standard architecture of NFV includes NFV infrastructure (NFVI), mano (management and organization), and VNFs. Wherein the VNF is a virtual network function unit in the NFV architecture. It can be understood that in the process of virtualizing functions of existing physical network elements in a telecommunication service network, the existing physical network elements are deployed on virtual resources provided by NFVI in the form of software modules, so as to implement virtualization of network functions. Therefore, three identical letters of NFV and VNF are exchanged in sequence, and the meanings are distinct. NFV is a virtualization technology or concept that solves the problem of deploying network functions on generic hardware.
One hardware electronic device forms a network as a terminal side device, and the network is a running bit stream. After various types of services of all end-side equipment are fully researched, priorities are arranged for different service requirements, services with high network requirements are preferentially ensured, and then services with low priorities are considered, which is the practical requirement for network slicing.
As shown in fig. 1, the 5G network slice overall architecture diagram. The 5G end-to-end network slice is characterized in that network resources are flexibly distributed, networking is carried out as required, a plurality of logic sub-networks which have different characteristics and are mutually isolated are virtualized on the basis of the 5G network, each end-to-end network slice is formed by combining a wireless network, a transmission network and a core network sub-slice, and unified management is carried out through an end-to-end slice management system. In the urrllc slice, scenarios such as automatic driving/assisted driving, remote control, etc. have extremely strict delay requirements on the network. In an mMTC slice, a large-scale Internet of things service scene has massive connection, the interactive data volume in a network is small, and high computing resources and low congestion are required. In eMBB slicing, large-flow mobile broadband services such as 3D/ultra-high definition video and the like have the characteristics of high user data rate and high bandwidth. Based on the method, resources are reasonably configured, limited networks are utilized, different network slices are configured through the slice network according to different requirements of different services on the networks, and an operator can flexibly provide personalized network services for users at low cost according to third party requirements and network conditions.
In order to understand the existing network slice configuration scheme, the existing technical materials are searched, compared and analyzed, and the following literature schemes are found:
literature scheme 1: in the "Optimal virtual network function placement in multi-closed service function linking architecture", the author studies the virtual network function placement problem, aiming at realizing the optimized SFC formation in the cloud which is distributed across geography. The author sets up an ILP optimization problem with the objective of minimizing inter-cloud traffic and response time in a multi-cloud scenario, meeting important constraints such as total deployment cost and service level agreements. They propose affinity-based approaches to solve problems in large network topologies.
Document scheme 2: in Adaptive Interference-Aware VNF platform for Service-conditioned 5 global services, authors consider both edge cloud servers and core cloud servers to deploy required VNFs on demand for each network slice, aiming to maximize the total throughput of accepted requests. And a demand model is proposed to quantify the performance degradation that VNF consolidation may cause. The main idea is to place the delay sensitive slice more probabilistically on the edge side.
The above-mentioned document scheme 1 and document scheme 2 use only a simple policy when cloud edge coordination is considered. The former uses the placement restrictions imposed by SLAs when considering the deployment of core or edge clouds, i.e. some VNFs must be placed in the core network and some VNFs must be placed in the edge network. The method only restricts the deployment position and cannot flexibly place slice network functions. The latter places delay-sensitive slices more probabilistically on the edge side based on a simple greedy strategy. These methods lack the flexibility to implement optimal methods for saving bandwidth and reducing network latency.
Document scheme 3: in A Service-organized delivery Policy of End-to-End Network Slicing Based on complete Network Theory, authors propose a slice Service requirement Oriented collaboration strategy. The overall goal is to minimize placement costs. For three typical use cases (enhanced mobile broadband (eMBB), large-scale machine type communication (mMTC) and ultra-reliable and low-delay communication (uRLLC)) of a 5G scene, three sub-optimization target objective objectives are provided and a corresponding greedy algorithm is designed to solve a corresponding arrangement scheme.
Document scheme 3 designs a proprietary layout object and a proprietary layout algorithm that fits the slice requirements for three typical end-to-end slices. Node importance indexes are defined by node deployment in the arranging process in combination with infrastructure network structural features and physical node resources. But this approach does not take into account the slice isolation customization requirements of slice organization.
Based on this, further, there are still some key points to consider in the current network slicing research:
the first is to implement a customized slice isolation mechanism. The 5G network slice provides differentiated on-demand service customization capability for service features of different vertical industries, and safety is one of key factors which must be considered. Unlike the privacy and closure of traditional physical private networks, 5G network slices are virtualized private networks built on shared resources, and for the security of the network slices, in addition to providing traditional mobile network security mechanisms (e.g., access authentication, encryption and integrity protection of access layer and non-access layer signaling and data, etc.), an isolation mechanism between network slices needs to be provided. In order to meet the isolation level requirements of different services and improve the slice availability, the network slice can comprehensively adopt different inter-slice isolation and intra-slice isolation mechanisms to realize multiple isolation protection.
Secondly, comprehensively utilizing core edge resources. With the mature business of 5G and vertical industries, networks need to access more devices and process massive data, however, the computational load pressure of low latency and high bandwidth makes the current centralized "core" data processing model difficult to continue. In addition, AR/VR, industrial internet, car networking, etc. put forward higher demands on communication delay. The proposal of edge calculation greatly facilitates the deployment implementation of the network slice. Thus, part of the functionality of the network slice can be sunk from the core data center to the network edge data center, constituting edge computing power. By shortening the link distance and improving the intelligent capability of the edge network, the effects of saving the return bandwidth, reducing the network delay and intelligently supporting the user experience are achieved.
Again, differentiation of slice traffic types is considered. The customized network slice based on the service requirement can enable the 5G network to have good service adaptability and meet the differentiation requirements of different services, such as time delay, bandwidth, node load balancing and the like. With the obvious difference in demand among the three major types of services, in order to improve user experience, the differentiation of network slice service types should be emphasized. Network slice arrangement needs to provide an arrangement target and a strategy matched with business requirements, and flexible and diverse differentiated business requirements are met.
And finally, the intellectualization of slicing arrangement is strengthened. The existing slice arrangement research mostly adopts the optimal solution or proposes a heuristic algorithm to solve the suboptimal solution, and the time complexity and the optimal solution cannot be well compromised. In addition, slicing orchestration requires automation and intelligence to save cost, quickly deploy, and adapt to network changes. On the basis of a 5G full-cloud network architecture, the intelligent arrangement of the slice network can be realized by introducing a mature AI technology taking machine learning as a core. The introduction of AI can better weigh time complexity and achieve optimal solution.
Based on the analysis, the application provides an intelligent network slice collaborative arrangement scheme oriented to usability and QoS optimization. Firstly, the scheme limits the requirement of differentiated network slice isolation levels to constraint conditions, realizes customized isolation of network slices, and improves the usability of the network slices. Secondly, by cooperating with the core data center and the edge data center, the bandwidth is effectively saved and the network delay is reduced in the aspect of QoS optimization. In addition, a dedicated scheduling optimization target matched with the service requirement is provided, and the differentiated requirements of different network slices on time delay, bandwidth and node load balance are distinguished.
As shown in fig. 2, a flow chart of a network slice configuration method proposed by the present application is shown. The network slice configuration method is executed on a controller in the network slice management system shown in fig. 1. The method comprises the following steps:
step 201): acquiring a network slice; the network slice corresponds to a sequence formed by at least two virtual network function units.
In this embodiment, the network slice is a logically isolated network on the same infrastructure network. Network slice s for customizing service corresponding to each business requirementkExpressed as a collection containing network functions required for a network service
Wherein M represents the number of functions required. Set of network functions skOne for each network function (VNF).
Step 202): in a corresponding configuration thread, a state set of resource utilization of the infrastructure network by the network slice is determined.
In the technical scheme, for the same network slice, the network slice is divided into at least two threads to execute the arranging algorithm of the network slice in parallel, so that the aim of accelerating the configuration of the network slice is fulfilled. The number of threads may be determined based on device processor performance, with each thread executing the same network slice configuration flow.
The network slice configuration needs to consider the resource utilization condition of the infrastructure network, so the scheme calculates the residual resource occupation ratio of each physical node and each link of the infrastructure network. In addition, the scheme considers customizing network slices, and the deployment decision is also related to the inter-slice isolation level and the intra-slice isolation level. The state set of the network slice configuration can therefore be represented as an M + N +2 dimensional feature:
wherein, the first M elements { w1，...wMDenotes the resource usage of the physical node, followed by N elements { v }1，...vNDenotes the bandwidth usage of the link, the penultimate element
Indicating the inter-slice separation level, the last element KrankIndicating the level of intra-chip isolation.
Step 203): and deploying the virtual network function units in the sequence according to the requirement of the application borne by the network slice on the safety and the state set, so as to realize the configuration of the network slice.
The security isolation of network slices can be divided into inter-slice isolation and intra-slice isolation. According to the requirements of the application borne by the slices on the security, such as the resource competition degree among the slices, the information protection requirement among the slices and the like, the isolation among the slices can be subdivided into physical isolation and logical isolation. The physical isolation is to allocate independent physical resources to the network slices, and each network slice monopolizes the physical resources without mutual influence, which is similar to the traditional physical private network and has application scenes such as industrial control application with strict requirements on safety and the like. Logical isolation is achieved using NFV-based resource isolation techniques,and distributing network functions borne by different virtual machines or containers for different network slices, and realizing the isolation of the slices in a basic resource layer through an isolation mechanism of the virtual machines or the containers. For example, for isolation level L1, physical isolation is provided, and independent physical resources are allocated. For isolation level L2, full logical isolation is provided, allocating independent network functions when deploying a network slice. For isolation level L3, shared logical isolation is provided, sharing part of the network functionality. Logical isolation is the use of NFV-based resource isolation techniques, and thus uses
Representation of network slices skWhether there is a requirement for physical isolation between slices, if so, network slice skPhysical isolation between slices is required, then
The value is 1. Different network functions need to provide mutual isolation between the network functions according to the security level requirements and trust relationships of the network functions. In addition to considering flexibility and economic cost, the on-chip isolation level of the network slice can be represented by the ratio of the total number of physical nodes for deploying the network slice to the total number of network functions required by the network slice. Therefore, use KrankIndicating the intra-slice isolation level, a higher value indicates a higher intra-slice isolation requirement for the network slice. In the technical scheme, the requirement of differentiated network slice isolation levels is limited as a constraint condition, so that customized isolation of the network slices is realized, and the usability of the network slices is improved.
In another embodiment, based on the solution shown in fig. 2, the infrastructure network is divided into an edge data center and a core data center. In the technical scheme, the infrastructure network is divided into K edge data centers and M core data centers, and each data center can use an assigned undirected graph
Denotes that K is 1. ltoreq. k.ltoreq.K + M. Wherein N issRepresenting a set of physical nodes, one of which, i, is used
Is represented by LsRepresenting a set of physical links between physical nodes, wherein the physical nodes
And
for the link between
And (4) showing. Use of
Representing a collection of physical nodes on the edge data center,
representing a collection of physical nodes on a core data center. For each physical node i, assume that the available computing resources are
The remaining computing resources are
The bandwidth resource of each link is
The remaining link bandwidth resources are
Link delay of
Physical nodes in a core data center
Has relatively sufficient resource capacity and high time delay, andphysical nodes in edge data centers
Closer to the end user, the resource capacity is limited but the delay is low.
In the case of a network slice configuration scheme,
if so, the arranging algorithm of the network slices can be executed. Wherein the content of the first and second substances,
the meaning of (A) is: a sum of remaining computing resources of each physical node in the infrastructure network;
the meaning of (A) is: the network slice contains a sum of the computing resources of the corresponding physical node that each network function uses at deployment.
For the technical scheme, a new problem model is provided from the viewpoint of slice customization isolation mechanism and core edge cooperation, and bandwidth is effectively saved and network delay is reduced in the aspect of QoS optimization through cooperation of a core data center and an edge data center.
Further, the network slice corresponds to a sequence of at least two virtual network functional units. Deploying a first virtual network function unit in the sequence according to the requirement of the application carried by the network slice on the security; and deploying other virtual network functional units in the sequence according to a reinforcement learning strategy.
In this case, for a first virtual network function unit in the sequence, in a corresponding configuration thread, if the network slice allows sharing of the virtual network function unit, the first virtual network function unit of the network slice is deployed on a physical node of the infrastructure network; wherein the physical nodes of the infrastructure network have deployed virtual network function units of the same type as the first virtual network function unit of the network slice and also allow sharing of virtual network function units. Otherwise, deploying the first virtual network function unit on a physical node corresponding to the minimum load of the resources in the infrastructure network according to the slice type of the first virtual network function unit of the network slice.
For other virtual network function units except the first virtual network function unit in the sequence, in the corresponding configuration thread, according to a feedback value received by each state in the state set executing a deployment strategy on the other virtual network function units, determining a proprietary parameter of the corresponding configuration thread; wherein the feedback value is determined according to a feedback function; and performing deployment on other virtual network functional units on physical nodes in the infrastructure network according to a reinforcement learning strategy by using the state set and the corresponding proprietary parameters.
In further detail, the scheme aims to perform comprehensive optimization aiming at different requirements of three typical network slices, so that the optimization objective function consists of slice delay, load balance of physical nodes and link bandwidth consumption. In the urrllc slice, scenarios such as automatic driving/assisted driving, remote control, etc. have very stringent delay requirements on the network, and the first part of the objective function represents the minimized slice delay. In an mMTC slice, a large-scale Internet of things service scene has massive connection, the interactive data volume in a network is small, and high computing resources and low congestion are required. Thus, the second part of the objective function represents the load balancing of the physical nodes. In the eMBB slice, the large-flow mobile broadband service such as 3D/ultra-high definition video has the characteristics of high user data rate and high bandwidth, so that the third part of the objective function represents the minimum link bandwidth consumption. Aiming at the customized requirement, different weights are set for the three slices to synthesize the three key performance indexes, so that an exclusive optimization target matched with the requirement is set. The optimized objective function expression is as follows:
wherein, alpha is the time delay weight of the network slice; beta is the load balancing weight of the physical node; and gamma is a bandwidth consumption weight. These three parameters are dynamically adjusted according to the requirements of each network slice. In this example, α, β, and γ were set to 0.8, 0.1, and 0.1, respectively, for the urlllc section. For mMTC slices, alpha, beta and gamma are set to be 0.1, 0.8 and 0.1 respectively. For eMBB sections, α, β, and γ were set to 0.1, and 0.8, respectively. The above is only an example, and for the technical solution, the values of α, β, and γ are not limited to these, for network slices of different service types.
The state set of the current network slice which needs to consider the resource utilization condition of the infrastructure network in the process of arranging the current configuration thread is st. Where t is used to characterize the number of steps in each thread to perform the network slice configuration. For the state set stFor each state, selecting a corresponding physical node from the infrastructure network for the virtual network function unit to be deployed according to the feedback function, and deploying the virtual network function unit (VNF). And physical links are deployed in all paths between the physical nodes required for deploying this VNF and the physical nodes required for deploying the last VNF. Thus the action set can be expressed as: a ═ n, P, where n denotes the selected physical node and P denotes the selected physical link.
Performing a different set of actions a for each state receives different feedback, but the selected action may violate the constraint. Thus, when the selected action violates the constraint, the feedback value is set to-1. When the constraint condition is satisfied, defining a feedback function as follows by using a formula (b);
wherein Z is a positive number for adjusting the feedback value to a positive number;
representing the system load balance in the state set st +1, i.e. global sectionVariance of usage of point resources; d is the propagation delay between the physical node selected when the current VNF is deployed and the physical node selected when the previous VNF is deployed; b denotes physical link resource consumption. α, β, γ represent coefficients, including normalization of the data.
For other virtual network functional units except the first virtual network functional unit in the network slice corresponding sequence, according to the reinforced learning strategy pi (a)t|st(ii) a θ') selecting action atAnd deploying other virtual network functional units. After the action is completed, calculating a corresponding feedback value for each VNF of the sequence corresponding to the network slice using equation (b). If all VNFs corresponding to the current network slice are configured or arranged according to stAnd (c) determining the Rt value corresponding to the currently configured thread by using the formula (c). The expression of formula (c) is:
and (d) calculating a corresponding feedback value according to each VNF of the sequence corresponding to the network slice and an Rt value corresponding to the current configuration thread by using a formula (d) in an iterative manner until the current network slice is arranged. The expression of formula (d) is:
wherein, tstart＝t。
And (3) respectively and correspondingly finishing gradient accumulation according to a formula (e) and a formula (f) by using the R obtained by each iterative calculation, thereby obtaining the global sharing parameter corresponding to each iterative calculation. The expression of equation (e) is:
cumulative gradient wrt
The expression of equation (f) is:
cumulative gradient wrt
In the formula (e) and the formula (f), θ and θvAre all global shared parameters, θ 'and θ'vAre parameters specific to the thread.
And determining the proprietary parameters corresponding to the current thread by the global shared parameters corresponding to each iteration. Since the reinforcement learning strategy is pi (a)t|st(ii) a Theta') of the current thread, so that the technical scheme can learn on line according to the system state and the feedback value given by the environment after different action set mappings are executed. And aiming at the typical slice, providing a special arrangement optimization target matched with the service requirement corresponding to the network slice, and distinguishing the differentiated requirements of different slices on time delay, bandwidth and node load balance by adjusting the weight.
Fig. 3 is a schematic diagram of a network slice configuration apparatus according to the present application. The method comprises the following steps: a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the network slice configuration method as shown in fig. 2 when executing the computer program.
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present application.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, both for the embodiments of the client and the server, reference may be made to the introduction of embodiments of the method described above.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
Claims (10)
1. A network slice configuration method, implemented on a controller in a network slice management system, comprising:
acquiring a network slice; the network slice corresponds to a sequence formed by at least two virtual network functional units;
determining a state set of resource utilization of the network slice to an infrastructure network in a corresponding configuration thread;
and deploying the virtual network function units in the sequence according to the requirement of the application borne by the network slice on the safety and the state set, so as to realize the configuration of the network slice.
2. The method of claim 1, wherein the infrastructure network is divided into an edge data center and a core data center.
3. The method of claim 1 or 2, wherein deploying the virtual network function units in the sequence comprises:
deploying a first virtual network function unit in the sequence according to the requirement of the application carried by the network slice on the security;
and deploying other virtual network functional units in the sequence according to a reinforcement learning strategy.
4. The method of claim 3, wherein deploying the first virtual network function in the sequence comprises:
in a corresponding configuration thread, if the network slice allows sharing of a virtual network function unit, deploying a first virtual network function unit of the network slice on a physical node of the infrastructure network; wherein the physical nodes of the infrastructure network have deployed virtual network function units of the same type as the first virtual network function unit of the network slice and also allow sharing of virtual network function units.
5. The method of claim 3, wherein deploying the first virtual network function in the sequence comprises:
in a corresponding configuration thread, if the network slice does not allow sharing of the virtual network function units already deployed by the physical nodes of the infrastructure network, deploying the first virtual network function unit of the network slice at the physical node corresponding to the minimum load of the resources in the infrastructure network.
6. The method of claim 3, wherein deploying other virtual network functional units in the sequence according to a reinforcement learning strategy comprises:
in the corresponding configuration thread, according to a feedback value received by executing a deployment strategy on other virtual network function units by each state in the state set, determining a proprietary parameter of the corresponding configuration thread; wherein the feedback value is determined according to a feedback function;
and performing deployment on other virtual network functional units on physical nodes in the infrastructure network according to a reinforcement learning strategy by using the state set and the corresponding proprietary parameters.
7. The method of claim 6, wherein the feedback function is determined based on an objective function; the objective function is determined according to differentiated requirements of minimized slice delay, load balance of the physical nodes and minimized link bandwidth consumption of the comprehensive consideration of service requirements corresponding to the network slices.
8. The method of claim 1 or 2, wherein the state set comprises resource usage of physical nodes in the infrastructure network, bandwidth usage of links in the infrastructure network, a level of intra-slice isolation of the network slice, a level of inter-slice isolation of the network slice.
9. The method of claim 8, wherein the inter-slice isolation is physical isolation or full logical isolation or shared logical isolation.
10. A network slice configuration apparatus, wherein the network slice configuration apparatus comprises a memory and a processor; wherein the content of the first and second substances,
the memory to store computer program instructions;
the processor, configured to execute the computer program instructions to implement the network slice configuration method of any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110681375.9A CN113490279B (en) | 2021-06-18 | 2021-06-18 | Network slice configuration method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110681375.9A CN113490279B (en) | 2021-06-18 | 2021-06-18 | Network slice configuration method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113490279A true CN113490279A (en) | 2021-10-08 |
| CN113490279B CN113490279B (en) | 2024-02-06 |
Family
ID=77934088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110681375.9A Active CN113490279B (en) | 2021-06-18 | 2021-06-18 | Network slice configuration method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113490279B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115002783A (en) * | 2022-04-20 | 2022-09-02 | 燕山大学 | Industrial Internet of things resource dynamic allocation method based on network slice |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160353367A1 (en) * | 2015-06-01 | 2016-12-01 | Huawei Technologies Co., Ltd. | System and Method for Virtualized Functions in Control and Data Planes |
| CN106792692A (en) * | 2016-12-27 | 2017-05-31 | 兴唐通信科技有限公司 | A kind of physics dicing method based on SDN technologies |
| CN107888425A (en) * | 2017-11-27 | 2018-04-06 | 北京邮电大学 | The network splitting and disposing method and apparatus of GSM |
| WO2018089634A1 (en) * | 2016-11-11 | 2018-05-17 | Intel IP Corporation | Network slice management |
| CN108495358A (en) * | 2018-03-09 | 2018-09-04 | 西安电子科技大学 | A kind of network slice selection method based on NFV |
| WO2018224151A1 (en) * | 2017-06-08 | 2018-12-13 | Huawei Technologies Co., Ltd. | Device and method for providing a network slice |
| CN109586938A (en) * | 2017-09-29 | 2019-04-05 | 华为技术有限公司 | The generation method and device of example traffic topology |
| US20190174347A1 (en) * | 2017-12-01 | 2019-06-06 | At&T Intellectual Property I, L.P. | Dynamic access slice pooling and software defined network controlled capabilities |
| CN110034944A (en) * | 2018-01-12 | 2019-07-19 | 华为技术有限公司 | Network splitting and disposing method and device thereof |
| CN110896355A (en) * | 2018-09-12 | 2020-03-20 | 华为技术有限公司 | Network slice selection method and device |
| WO2020258920A1 (en) * | 2019-06-26 | 2020-12-30 | 华为技术有限公司 | Network slice resource management method and apparatus |
| CN112822050A (en) * | 2021-01-05 | 2021-05-18 | 北京信息科技大学 | Method and apparatus for deploying network slices |
-
2021
- 2021-06-18 CN CN202110681375.9A patent/CN113490279B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160353367A1 (en) * | 2015-06-01 | 2016-12-01 | Huawei Technologies Co., Ltd. | System and Method for Virtualized Functions in Control and Data Planes |
| WO2018089634A1 (en) * | 2016-11-11 | 2018-05-17 | Intel IP Corporation | Network slice management |
| CN106792692A (en) * | 2016-12-27 | 2017-05-31 | 兴唐通信科技有限公司 | A kind of physics dicing method based on SDN technologies |
| WO2018224151A1 (en) * | 2017-06-08 | 2018-12-13 | Huawei Technologies Co., Ltd. | Device and method for providing a network slice |
| CN109586938A (en) * | 2017-09-29 | 2019-04-05 | 华为技术有限公司 | The generation method and device of example traffic topology |
| CN107888425A (en) * | 2017-11-27 | 2018-04-06 | 北京邮电大学 | The network splitting and disposing method and apparatus of GSM |
| US20190174347A1 (en) * | 2017-12-01 | 2019-06-06 | At&T Intellectual Property I, L.P. | Dynamic access slice pooling and software defined network controlled capabilities |
| CN110034944A (en) * | 2018-01-12 | 2019-07-19 | 华为技术有限公司 | Network splitting and disposing method and device thereof |
| CN108495358A (en) * | 2018-03-09 | 2018-09-04 | 西安电子科技大学 | A kind of network slice selection method based on NFV |
| CN110896355A (en) * | 2018-09-12 | 2020-03-20 | 华为技术有限公司 | Network slice selection method and device |
| WO2020258920A1 (en) * | 2019-06-26 | 2020-12-30 | 华为技术有限公司 | Network slice resource management method and apparatus |
| CN112822050A (en) * | 2021-01-05 | 2021-05-18 | 北京信息科技大学 | Method and apparatus for deploying network slices |
Non-Patent Citations (3)
| Title |
|---|
| GABRIEL ANTONIO F等: "Providing a Sliced，Secure，and isolated Software Infrastructure of Virtual Functions Through Blockchain Technology", 2019 IEEE 20TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE SWITCHING AND ROUTING * |
| 张恒升;: "基于NFV和SDN的无线网络虚拟化关键技术研究", 现代导航, no. 03 * |
| 杨德龙;万俐;李晦龄;丁慧霞;路兆铭;马宝娟;陈亚文;: "基于网络切片的能源互联网***架构", 电力信息与通信技术, no. 01 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115002783A (en) * | 2022-04-20 | 2022-09-02 | 燕山大学 | Industrial Internet of things resource dynamic allocation method based on network slice |
| CN115002783B (en) * | 2022-04-20 | 2024-04-05 | 燕山大学 | Industrial Internet of things resource dynamic allocation method based on network slicing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113490279B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Islam et al. | A survey on task offloading in multi-access edge computing | |
| Zhang et al. | Adaptive interference-aware VNF placement for service-customized 5G network slices | |
| Feng et al. | Optimal dynamic cloud network control | |
| JP6380110B2 (en) | Resource control system, control pattern generation device, control device, resource control method, and program | |
| Kim et al. | Multi-agent reinforcement learning-based resource management for end-to-end network slicing | |
| CN111010295B (en) | SDN-MEC-based power distribution and utilization communication network task migration method | |
| Wang et al. | Microservice-oriented service placement for mobile edge computing in sustainable internet of vehicles | |
| WO2020134133A1 (en) | Resource allocation method, substation, and computer-readable storage medium | |
| CN116032767A (en) | Intelligent fusion identification network-oriented computing power service chain management and control system architecture | |
| Li et al. | Scalable knowledge-defined orchestration for hybrid optical–electrical datacenter networks | |
| Gu et al. | Cooperative mobile edge computing‐cloud computing in Internet of vehicle: Architecture and energy‐efficient workload allocation | |
| CN114374605A (en) | Dynamic adjustment and migration method for service function chain in network slice scene | |
| Lin et al. | Column generation based service function chaining embedding in multi-domain networks | |
| Garg et al. | SDN-NFV-Aided edge-cloud interplay for 5G-envisioned energy internet ecosystem | |
| Zhu et al. | Double-agent reinforced vNFC deployment in EONs for cloud-edge computing | |
| Pereira et al. | Increasing the efficiency of fog nodes through of priority-based load balancing | |
| Xiang et al. | Resource calendaring for mobile edge computing: centralized and decentralized optimization approaches | |
| CN113490279A (en) | Network slice configuration method and device | |
| CN113315806B (en) | Multi-access edge computing architecture for cloud network fusion | |
| Saravanan et al. | Improving map reduce task scheduling and micro-partitioning mechanism for mobile cloud multimedia services | |
| CN115665258B (en) | Priority perception deployment method of multi-target service function chain based on deep reinforcement learning | |
| Tang et al. | A hybrid learning framework for service function chaining across geo-distributed data centers | |
| Qu et al. | Survivable SFC deployment method based on federated learning in multi-domain network | |
| Zhang et al. | SFC-based multi-domain service customization and deployment | |
| Zhang et al. | A novel resource optimization algorithm for dynamic networks combined with NFV and SDN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |