CN108833162A - A kind of network node sort method and mapping method of virtual network - Google Patents
A kind of network node sort method and mapping method of virtual network Download PDFInfo
- Publication number
- CN108833162A CN108833162A CN201810600998.7A CN201810600998A CN108833162A CN 108833162 A CN108833162 A CN 108833162A CN 201810600998 A CN201810600998 A CN 201810600998A CN 108833162 A CN108833162 A CN 108833162A
- Authority
- CN
- China
- Prior art keywords
- node
- network
- network node
- importance
- virtual
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45504—Abstract machines for programme code execution, e.g. Java virtual machine [JVM], interpreters, emulators
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
Abstract
The invention discloses one kind to provide a kind of network node sort method and mapping method of virtual network, node importance index calculating method of this method based on vector center degree, the importance index of network node is calculated, the influence of network node own resource attribute and direct-link node to the influence and indirectly connected neighboring network node of node importance to present node importance is considered simultaneously, and the mapping order of virtual network node is finally determined according to network node importance index.Can the resourceful bottom physical network nodes of limited consideration and link, be effectively reduced network occur fragment probability；And rationally utilize physical network resource.
Description
Technical field
The invention belongs to build virtual networking field；More particularly to a kind of network node sort method and virtual network
Mapping method.
Background technique
Group in order to construct completely new oriented Internet Architecture, headed by Princeton University Larry Peterson professor
Team proposed the fundamental change that future network architectural framework is pushed using network virtualization technology in 2005.Virtualization technology is
A kind of being abstracted for height, conceals the realization details of bottom, virtual network just looks like true Physical Network under virtualized environment
Network, and multiple virtual networks can use the physical infrastructure of bottom simultaneously.The primary entity of network virtualization is virtual
Network, a virtual network are the virtual topologies of the formation of one group of dummy node and virtual link.On the same physical network
Multiple logical network, belong to different service providers, and infrastructure provider can provide different to different virtual networks
Network topology resource, using and managing for different virtual networks is mutually indepedent, is independent of each other each other.In recent years, the world is each
State and many international organizations all recognize that network virtualization technology for the significance of future network, expands many phases successively
The large-scale research project of pass, for example, GENI, 4WARD, PlanetLab, VITRO etc., these have all greatly pushed network virtual
The development of change.
An important technology is exactly virtual network mapping in network virtualization environment, in the process of running due to network
There are a large amount of uncertain factor, such as the variations of buffer queue of nodes, the variation of the bandwidth of link and delay,
The dynamic for causing resource in physical network changes, and has uncertainty.How efficiently underlying resource to be managed and be divided
Match, complete the processing of virtual network requests, required Internet resources are provided for user, guarantees service quality, this is network virtual
Change must solve the problems, such as, such issues that extensively be referred to as virtual network mapping problems (Virtual Network Mapping)
Or virtual network imbedding problem (Virtual Network Embedding)
In virtual network mapping problems, there is a kind of typical algorithm to be called two stage mapping algorithm, this kind of algorithm is held
The mapping of row virtual network is divided into two step node mappings and link maps, and the money according to node is needed when carrying out node mapping
Source is ranked up node, then executes mapping, and whens link maps uses shortest path first or multiple commodity flow algorithm.Such is calculated
The implementation strategy of method is when carrying out virtual network mapping, it should it is preferential to occupy bottom physical resource node abundant and link,
The fragmentation of physical network resource can be led to by premature run out of to avoid the resource of certain nodes and link in this way, so that always
Resource it is enough, but appearance the case where can not distribute.
Summary of the invention
The present invention provides a kind of network node sort methods；Node mapping phase in virtual network mapping process is true
Determine network node mapping order and corresponding mapping relations, to reach to resource rational utilization, reduce local nodes or
Link circuit resource uses up the case where leading to network fragment appearance.
The present invention also provides a kind of mapping method of virtual network, construct virtual net based on above-mentioned network node sort method
Network, can the resourceful bottom physical network nodes of limited consideration and link, be effectively reduced network occur fragment probability；And
And rationally utilize physical network resource.
The technical scheme is that：A kind of network node sort method, including net is calculated based on vector center degree thought
The importance index of network node, its calculation formula is：Wherein Ni(n) node set jumped for present node i；Wherein γ0The money of r (n) expression node itself
Source size, r (n) are the Local resource of network node n after normalization；Indicate neighbor node
Contribution to present node importance；The importance of all nodes is calculated, according to node importance to virtual network node
Sort descending is carried out with physical network nodes.
Further, the features of the present invention also characterized in that：
Wherein neighbor node includes directly-connected neighbor node to present node importance to the contribution of present node importance
Contribution and contribution of the indirectly connected neighbor node to present node importance；It is expressed as：
Wherein the importance index of network node is expressed as in the form of matrix：V=γ0·R+γ1·P1·V+
γ2·P2·V；Wherein V=(v (x1),v(x2),…,v(xn)), R=(r (x1),r(x2),…,r(xn)),
Wherein the calculation formula of the importance index of network node is also shown as：V=(I- γ1·P1-γ2·P2)-1
γ0·R；Wherein γ1And γ2It is expressed as respective item specific gravity shared in the calculating of node importance index, I is unit
Matrix, I- γ1·P1-γ2·P2For invertible matrix.
Wherein the calculation of the Local resource of network node n is：Wherein N (n)
For the neighbor node set of node n, cpu (n) is the available computational resources of node n, bw (n, m) link between node n and m
Remaining bandwidth；Then the Local resource c (n) of network node n is normalized, obtains r (n), specifically
Another technical solution of the invention is：A kind of mapping method of virtual network uses network as described in claim 1
Node sequencing method obtains the sequence of network node importance, and according to sequence, virtual network node is mapped to physical network
On.
Compared with prior art, the beneficial effects of the invention are as follows：This method is by the thought of vector center degree, in virtual net
Network node mapping phase by calculating the importance index of network node, and is ranked up, realization pair according to importance index
Network node and surrounding resource have carried out reasonable measurement, so that in virtual network mapping process, it being capable of limited consideration money
The physical network nodes and link of source bottom abundant are effectively reduced the probability that fragment occurs for network, close physical network resource
Reason utilizes.
Further, according to the network node sort method, building virtual network node is further carried out, it can
Realize the reasonable distribution to physical network resource.
Detailed description of the invention
Fig. 1 is network virtualization framework map in the present invention.
Fig. 2 is virtual network graph topology in the present invention；
Fig. 3 is physical network topology figure in the present invention；
Fig. 4 is virtual network and physical network mapping result figure in the present invention.
Specific embodiment
Technical solution of the present invention is further illustrated in the following with reference to the drawings and specific embodiments.
In virtual network mapping process, network node mapping phase calculates virtual section according to the Resource Properties of network node
The importance index of point and its corresponding physical node, is then ranked up network node according to importance index.The present invention
Provide a kind of network node sort method, node importance index calculating method of this method based on vector center degree, to net
The importance index of network node is calculated, while considering that network node own resource attribute and direct-link node are important to node
Property influence to present node importance of influence and indirectly connected neighboring network node, finally referred to according to network node importance
Mark the mapping order for determining virtual network node.The detailed process of this method is：
Step S1 calculates the Local resource of network node, is indicated with c (n), specially：Wherein N (n) is the neighbor node set of node n, and cpu (n) is using tricks for node n
Calculate resource, the remaining bandwidth of bw (n, m) link between node n and m.
Step S2, is normalized c (n), and the Local resource of normalization posterior nodal point n is indicated with r (n), and
Step S3, the importance index of network node is calculated according to vector center degree thought, and vector center degree indicates one
The importance of node is not only related with the number of its neighbor node, also related to the importance of neighbor node.It is reflected in virtual network
It penetrates under situation, the resources occupation amount of network node illustrates the size of the network node importance.Node is indicated using V (n)
Importance, in order to which the thought of vector center degree to be introduced to the calculating of node importance, its calculation formula is：Wherein：Ni(n) current for distance
The node set that node i is jumped；Wherein γ0R (n) indicates the resource size of node itself,
Indicate contribution of the neighbor node to present node importance.
Step S4 carries out sort descending according to node importance index to virtual network node and physical network nodes, obtains
To the importance ranking of virtual network node.
Wherein, neighbor node includes directly-connected neighbor node pair to the contribution of present node importance in step S3 in the present invention
The contribution and contribution of the indirectly connected neighbor node to present node importance of present node importance.Considering directly-connected neighbor section
On the basis of point, increase the calculating to indirectly connected neighbor node, therefore work asThe radiation of middle i
When range increases, and as i=2, obtain：The time of algorithm is complicated
Degree increases with the increase of i；When i is every increases by 1, the complexity of the calculation method is time complexity multiplied by O (n), O (n)
Description.
Above-mentioned calculation can also be expressed as with matrix form：V=γ0·R+γ1·P1·V+γ2·P2·V；Wherein
V=(v (x1),v(x2),…,v(xn)), R=(r (x1),r(x2),…,r(xn))；
Further, it is expressed as using matrix form：
Converting to above-mentioned Matrix Formula can also obtain：V=(I- γ1·P1-γ2·P2)-1γ0·R；Wherein γ1,
γ2Respective item specific gravity shared in the calculating of node importance index is respectively indicated, I is unit matrix, I- γ1·P1-
γ2·P2Invertible matrix can also obtain the importance index of respective network node by the calculation formula.
The present invention also provides a kind of mapping method of virtual network, this method is obtained by above-mentioned network node sort method
Virtual network node is mapped on physical network according to sequence to the sequence of network node importance.
As shown in Figure 1, two physical networks (SP1 and SP2) have mapped two virtual networks respectively, they are collectively resided in
On the same physical network, physical network is provided to virtual network tool by the way that virtualization technology is abstract to bottom physical facility
The service of variantization, multiple virtual networks are isolated from each other.
Fig. 2, Fig. 3 and Fig. 4 describe simple virtual network mapping schematic diagram, and Fig. 2 indicates a virtual SDN network data
Layer request example, the cpu resource of the digital representation node request of near nodal, bandwidth needed for the digital representation link of chain road
Resource, the bottom-layer network topology before Fig. 3 mapping；Fig. 2 indicates the bottom-layer network topology after mapping.The mapping side of the example interior joint
Case is as shown in figure 4, { a → A, b → B, c → D }, the mapping scheme of link are { (a, b) → (A, B), (a, c) → (A, D), (b, c)
→(B,D)}.Virtual network mapping algorithm quality, determines the number for the virtual network that physical network can carry, final to determine
The interests of physical infrastructure provider.So under the network virtualization environment, virtual network mapping algorithm is extremely important, it is high
The virtual network mapping algorithm of effect can increase the income of infrastructure provider to greatest extent, improve the utilization of physical resource
Rate.
Claims (6)
1. a kind of network node sort method, which is characterized in that the weight including calculating network node based on vector center degree thought
The property wanted index, its calculation formula is：Whereinγi-1
> γi, Ni(n) node set jumped for present node i；Wherein γ0R (n) indicates the resource size of node itself, and r (n) is
The Local resource of network node n after normalization；Indicate that neighbor node is important to present node
The contribution of property；The importance of all nodes is calculated, according to node importance to virtual network node and physical network nodes
Carry out sort descending.
2. network node sort method according to claim 1, which is characterized in that the neighbor node is to present node weight
The contribution for the property wanted is including directly-connected neighbor node to the contribution of present node importance and indirectly connected neighbor node to present node weight
The contribution for the property wanted；It is expressed as：
3. network node sort method according to claim 2, which is characterized in that the importance index of the network node
It is expressed as in the form of matrix：V=γ0·R+γ1·P1·V+γ2·P2·V；Wherein V=(v (x1),v(x2),…,v
(xn)), R=(r (x1),r(x2),…,r(xn)),
4. network node sort method according to claim 2, which is characterized in that the importance index of the network node
Calculation formula be also shown as：V=(I- γ1·P1-γ2·P2)-1·γ0·R；Wherein γ1And γ2It is expressed as respective item
The shared specific gravity in the calculating of node importance index, I are unit matrix, I- γ1·P1-γ2·P2For invertible matrix.
5. network node sort method according to claim 1, which is characterized in that the Local resource of the network node n
Calculation be：Wherein N (n) is the neighbor node set of node n, and cpu (n) is
The available computational resources of node n, the remaining bandwidth of bw (n, m) link between node n and m；Then to the part of network node n
Resource c (n) is normalized, and obtains r (n), specifically
6. a kind of mapping method of virtual network, which is characterized in that network node sort method as described in claim 1 is used,
The sequence of network node importance is obtained, according to sequence, virtual network node is mapped on physical network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810600998.7A CN108833162B (en) | 2018-06-12 | 2018-06-12 | Network node sequencing method and virtual network mapping method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810600998.7A CN108833162B (en) | 2018-06-12 | 2018-06-12 | Network node sequencing method and virtual network mapping method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108833162A true CN108833162A (en) | 2018-11-16 |
| CN108833162B CN108833162B (en) | 2020-10-27 |
Family
ID=64145065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810600998.7A Active CN108833162B (en) | 2018-06-12 | 2018-06-12 | Network node sequencing method and virtual network mapping method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108833162B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112653580A (en) * | 2020-12-16 | 2021-04-13 | 国网河南省电力公司信息通信公司 | Virtual network resource allocation method based on active detection under network slice |
| CN113852515A (en) * | 2021-08-26 | 2021-12-28 | 西安电子科技大学广州研究院 | Node state control method and system of digital twin network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105591876A (en) * | 2016-03-04 | 2016-05-18 | 重庆邮电大学 | Virtual network mapping method |
| CN107979545A (en) * | 2017-10-17 | 2018-05-01 | 南京邮电大学 | A kind of mapping method of virtual network based on nodal community |
-
2018
- 2018-06-12 CN CN201810600998.7A patent/CN108833162B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105591876A (en) * | 2016-03-04 | 2016-05-18 | 重庆邮电大学 | Virtual network mapping method |
| CN107979545A (en) * | 2017-10-17 | 2018-05-01 | 南京邮电大学 | A kind of mapping method of virtual network based on nodal community |
Non-Patent Citations (3)
| Title |
|---|
| 任晓龙: "网络重要节点排序方法综述", 《科学通报》 * |
| 王子厚等: "可重构网络中基于中心度与拓扑势排序的资源分配算法", 《通信学报》 * |
| 王文钊等: "基于网络中心性分析的虚拟网络映射算法", 《计算机应用研究》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112653580A (en) * | 2020-12-16 | 2021-04-13 | 国网河南省电力公司信息通信公司 | Virtual network resource allocation method based on active detection under network slice |
| CN113852515A (en) * | 2021-08-26 | 2021-12-28 | 西安电子科技大学广州研究院 | Node state control method and system of digital twin network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108833162B (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9794370B2 (en) | Systems and methods for distributed network-aware service placement | |
| Zhang et al. | Virtual network embedding based on the degree and clustering coefficient information | |
| CN103179052B (en) | A kind of based on the central virtual resource allocation method and system of the degree of approach | |
| CN107196806B (en) | Topological proximity matching virtual network mapping method based on sub-graph radiation | |
| CN107566194A (en) | A kind of method for realizing the mapping of cross-domain virtual network network | |
| Li et al. | Resource allocation with multi-factor node ranking in data center networks | |
| CN103763174B (en) | Virtual network mapping method based on function block | |
| CN110365568A (en) | A kind of mapping method of virtual network based on deeply study | |
| CN107277832A (en) | A kind of mapping method of wireless dummy network | |
| CN105677447B (en) | Time delay minimization of bandwidth virtual machine deployment method in distributed cloud based on cluster | |
| CN109347657B (en) | Method for constructing virtual data domain of scientific and technological service under SDN mode | |
| CN107979545A (en) | A kind of mapping method of virtual network based on nodal community | |
| Zhang et al. | VNE-HPSO: Virtual network embedding algorithm based on hybrid particle swarm optimization | |
| CN108833162A (en) | A kind of network node sort method and mapping method of virtual network | |
| WO2019148605A1 (en) | Resource-aware backup node allocation algorithm for service chain, and device | |
| Yuan et al. | Topology-oriented virtual network embedding approach for data centers | |
| Malik et al. | Latency based group discovery algorithm for network aware cloud scheduling | |
| CN105187322B (en) | A kind of virtual net mapping method based on load balancing | |
| Shi et al. | Partitioning dynamic graph asynchronously with distributed FENNEL | |
| CN106681795B (en) | Virtual network mapping method for node local topology and available resource capacity | |
| WO2021027745A1 (en) | Graph reconstruction method and apparatus | |
| Yuan et al. | Efficient graph query processing over geo-distributed datacenters | |
| CN105049315A (en) | Improved virtual network mapping method based on virtual network partition | |
| Cao et al. | A resource allocation strategy in fog-cloud computing towards the Internet of Things in the 5g era | |
| Fan et al. | DRL-D: revenue-aware online service function chain deployment via deep reinforcement learning |
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 |