CN104869044B - A kind of virtual net mapping method and device - Google Patents
A kind of virtual net mapping method and device Download PDFInfo
- Publication number
- CN104869044B CN104869044B CN201510344602.3A CN201510344602A CN104869044B CN 104869044 B CN104869044 B CN 104869044B CN 201510344602 A CN201510344602 A CN 201510344602A CN 104869044 B CN104869044 B CN 104869044B
- Authority
- CN
- China
- Prior art keywords
- node
- physical
- link
- virtual
- physical node
- 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.)
- Active
Links
Abstract
The present invention provides a kind of virtual net mapping method and device, comprising: each physical node carries out safe capacity assessment in the bottom-layer network shared to virtual net, obtains safe capacity matrix；Based on the safe capacity matrix, the corresponding physical node of each dummy node in the virtual net is determined；The virtual link of dummy node each in the virtual net is mapped to a plurality of acyclic physical link of corresponding physical node；An acyclic physical link is randomly selected from a plurality of acyclic physical link of the physical node, selected acyclic physical link is used for transmission virtual net request, scheme i.e. provided by the invention can randomly select an acyclic physical link when carrying out virtual net request transmission and carry out the request of transfer of virtual net, this mode for randomly selecting physical link improves the unpredictability of link transmission, thus the safety of improve data transfer.
Description
Technical field
The invention belongs to technical field of the computer network, more specifically, more particularly to a kind of virtual net mapping method and
Device.
Background technique
To solve the problems, such as that network ossifys, extensive concern of the network virtualization technology by academia, wherein network virtualization
Technology allows to run the virtual net of multiple isomeries simultaneously on shared bottom-layer network, and each virtual net is equivalent to bottom-layer network
Resource fragment, carry specific type business.
In network virtualization technology, virtual net mapping problems is the key content of network virtualization research, main to complete
Virtual net request is mapped to the task on bottom-layer network idling-resource.Due to the bottom-layer network topology knot in virtual net mapping
Structure is in dynamic change (being mainly reflected in node/link failure), so how to realize under dynamic topology environment virtual
The reliability mapping of net is current research urgent problem to be solved.
It is relatively weak for the reliability mapping research of virtual net at present, it is broadly divided into active-standby switch and online two kinds of migration
Mode, wherein active-standby switch refers in bottom-layer network to be two physical links of every virtual link preparation, a physical link
For main path, another physical link is that backup path switches to backup path transfer of virtual net when main path breaks down
Request；Online migration is then to calculate another physical link in real time when physical link breaks down and carry out transfer of virtual net and ask
It asks.But both modes belong to Passive Defence, reduce the safety of data transmission.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of virtual net mapping method and device, it can be virtual by every
Link maps randomly select any one physical link in data transmission and are transmitted to a plurality of physical link, improve chain
The unpredictability of road transmission, thus the safety of improve data transfer.
The present invention provides a kind of virtual net mapping method, which comprises
Each physical node carries out safe capacity assessment in the bottom-layer network shared to virtual net, obtains safe capacity square
Battle array；
Based on the safe capacity matrix, the corresponding physical node of each dummy node in the virtual net is determined；
The virtual link of dummy node each in the virtual net is mapped to a plurality of nothing of corresponding physical node
Ring physical link；
An acyclic physical link, selected nothing are randomly selected from a plurality of acyclic physical link of the physical node
Ring physical link is used for transmission virtual net request.
Preferably, described that safe capacity assessment is carried out to physical node each in the bottom-layer network, obtain safe capacity
Matrix, comprising:
Any physical node is obtained in the bottom-layer network to the maximum flow valuve c between u and vu,v；
The link weight of physical node each in the bottom-layer network is revised as the impacted ratio of corresponding message
CoefficientInverse, wherein the impacted proportionality coefficient of message of each physical node and respective security defense capability system
Number is inversely proportional, and the security defense capability coefficient is known coefficient；
Any physical node is obtained in modified bottom-layer network to the maximum flow valuve f between u and vu,v；
Based on the maximum flow valuve fu,v, obtain the first calculating parameter e of each element in the safe capacity matrixu,v；
Based on the maximum flow valuve cu,vWith the first calculating parameter eu,v, obtain the element in the safe capacity matrix
mu,v, wherein 1≤u≤N, 1≤v≤N, N indicate the total number of physical node in the bottom-layer network, and N is the integer greater than 1.
Preferably, described to be based on the safe capacity matrix, determine that each dummy node in the virtual net is corresponding
Physical node, comprising:
Since the virtual net to the maximum dummy node of network resource requirement, be based on breadth first traversal principle,
Determine the mapping order of each dummy node in the virtual net；
Based on the mapping order, each dummy node is mapped, wherein the mapping to x-th of dummy node
Process includes: the network resource requirement based on x-th of dummy node, determines first of i-th of dummy node in bottom-layer network
Both candidate nodes set；Each physical node and xth-in the first both candidate nodes set are calculated based on the safe capacity matrix
The first average security capacity between the corresponding physical node of 1 dummy node；X-th of dummy node is mapped to described first
The first maximum physical node of average security capacity in both candidate nodes set, 2≤x≤M, M indicate virtually to save in the virtual net
The total number of point, and M is the integer greater than 2；
Mapping process to the 1st dummy node includes: the network resource requirement based on the 1st dummy node, determines the 1st
Second both candidate nodes set of a dummy node in bottom-layer network；It is candidate that described second is calculated based on the safe capacity matrix
Second average security capacity of each physical node in node set；1st dummy node is mapped to the described second candidate section
The second maximum physical node of average security capacity in point set.
Preferably, the virtual link by dummy node each in the virtual net is mapped to corresponding physics section
The a plurality of acyclic physical link of point, comprising:
The virtual link mapping problems of dummy node each in the virtual net is converted into linear programming problem, the line
Property planning problem be the corresponding stochastic flow of each virtual link linear function problem；
The linear programming problem is solved, the optimal stochastic Flow Policy P of each virtual link is obtainedi, Pk=
(p1,k,p2,k,......,pt,k), t is the number for the physical link that i-th of virtual link is mapped to, pj,kIt indicates to come from k-th
The stream probability of physical link j, 1≤k≤M are passed through in the virtual net request of virtual link；
The loop in the optimal stochastic Flow Policy of each virtual link is removed, the acyclic stochastic flow of each virtual link is obtained
Strategy；
The acyclic random Flow Policy is converted into acyclic random routing strategy Rk, RkIt is used to indicate each dummy node
Virtual link is mapped to a plurality of acyclic physical link of corresponding physical node, Rk=(r1,k,......,
rj,k,......,rz,k)T, rj,kIt requests for virtual net from physical linkA physical node u be forwarded to another object
The probability of node v is managed, z is the total number for the physical node that each dummy node is mapped to.
Preferably, the loop in the optimal stochastic Flow Policy of each virtual link of removal, obtains each virtual link
Acyclic random Flow Policy, comprising:
For optimal stochastic Flow Policy Pk, construct by pj,kThe network topology G of > 0 physical link compositiona；
If in the network topology GaIn find most short transmission path B between physical node u to physical node v, obtain
Take the minimum stream probability f on the most short transmission path B；Wherein u and v is virtual linkTwo after being mapped to bottom-layer network
Endpoint, and u is the starting physical node in the most short transmission path, v is the termination physical node in the most short transmission path；
Network topology is updated based on the minimum stream probability obtained every time, wherein renewal process includes: from net
Network topology GaIn most short transmission path on removal stream probability and minimum stream probability difference be zero physical link, after obtaining update
Network topology Ga, and to updated network topology GaIt executes in the network topology GaMiddle lookup physical node u is to physics section
Most short transmission path B between point v, and obtain the minimum stream probability f on the most short transmission path B until physical node u and
Most short transmission path, stream probability corresponding for the physical link removed in each virtual link are not present between physical node v
Constitute acyclic random Flow Policy；
If in the network topology GaIn find most short transmission path B between physical node u to physical node v, really
The optimal stochastic Flow Policy of fixed each virtual link is acyclic random Flow Policy.
The present invention also provides a kind of virtual net mapping devices, which is characterized in that described device includes:
Assessment unit carries out safe capacity assessment for each physical node in the bottom-layer network shared to virtual net, obtains
To safe capacity matrix；
Determination unit determines that each dummy node in the virtual net is corresponding for being based on the safe capacity matrix
Physical node；
Map unit, for the virtual link of dummy node each in the virtual net to be mapped to corresponding physics
The a plurality of acyclic physical link of node；
Selection unit, for randomly selecting an acyclic physics chain from a plurality of acyclic physical link of the physical node
Road, selected acyclic physical link are used for transmission virtual net request.
Preferably, the assessment unit includes:
First obtains subelement, for obtaining in the bottom-layer network any physical node to the maximum flow valuve between u and v
cu,v；
Subelement is modified, it is corresponding for the link weight of physical node each in the bottom-layer network to be revised as
The impacted proportionality coefficient of messageInverse, wherein the impacted proportionality coefficient of message of each physical node with it is respective
Security defense capability coefficient is inversely proportional, and the security defense capability coefficient is known coefficient；
Second obtains subelement, for obtaining in modified bottom-layer network any physical node to the maximum between u and v
Flow valuve fu,v；
First computation subunit, for based on the maximum flow valuve fu,v, obtain each element in the safe capacity matrix
The first calculating parameter eu,v；
Second computation subunit, for based on the maximum flow valuve cu,vWith the first calculating parameter eu,v, obtain described
Element m in safe capacity matrixu,v, wherein 1≤u≤N, 1≤v≤N, N indicate total of physical node in the bottom-layer network
Number, and N is the integer greater than 1.
Preferably, the determination unit includes:
Subelement is determined, for since the virtual net to the maximum dummy node of network resource requirement, based on width
First traversal principle is spent, determines the mapping order of each dummy node in the virtual net；
Subelement is mapped, for being based on the mapping order, each dummy node is mapped, wherein to xth
The mapping process of a dummy node includes: the network resource requirement based on x-th of dummy node, determines that i-th of dummy node exists
The first both candidate nodes set in bottom-layer network；It is calculated based on the safe capacity matrix every in the first both candidate nodes set
The first average security capacity between a physical node physical node corresponding with -1 dummy node of xth；By x-th of virtual section
Point is mapped to the first maximum physical node of average security capacity in the first both candidate nodes set, and 2≤x≤M, M indicate institute
The total number of dummy node in virtual net is stated, and M is the integer greater than 2；
Mapping process to the 1st dummy node includes: the network resource requirement based on the 1st dummy node, determines the 1st
Second both candidate nodes set of a dummy node in bottom-layer network；It is candidate that described second is calculated based on the safe capacity matrix
Second average security capacity of each physical node in node set；1st dummy node is mapped to the described second candidate section
The second maximum physical node of average security capacity in point set.
Preferably, the map unit includes:
First conversion subunit, for being converted to the virtual link mapping problems of dummy node each in the virtual net
Linear programming problem, the linear programming problem are the linear function problem of the corresponding stochastic flow of each virtual link；
It solves subelement and obtains the optimal stochastic of each virtual link for solving to the linear programming problem
Flow Policy Pi, Pk=(p1,k,p2,k,......,pt,k), t is the number for the physical link that i-th of virtual link is mapped to, pj,kTable
Show that the stream probability of physical link j, 1≤k≤M are passed through in the virtual net request from k-th of virtual link；
Subelement is removed, the loop in optimal stochastic Flow Policy for removing each virtual link obtains each virtual
The acyclic random Flow Policy of link；
Second conversion subunit, for the acyclic random Flow Policy to be converted to acyclic random routing strategy Rk, RkFor
Indicate that the virtual link of each dummy node is mapped to a plurality of acyclic physical link of corresponding physical node, Rk=
(r1,k,......,rj,k,......,rz,k)T, rj,kIt requests for virtual net from physical linkA physical node u turn
It is dealt into the probability of another physical node v, z is the total number for the physical node that each dummy node is mapped to.
Preferably, the removal subelement includes:
Subelement is constructed, for being directed to optimal stochastic Flow Policy Pk, construct by pj,kThe network of > 0 physical link composition is opened up
Flutter Ga；
Subelement is obtained, if in the network topology GaIn find between physical node u to physical node v most
Short transmission path B obtains the minimum stream probability f on the most short transmission path B；Wherein u and v is virtual linkIt is mapped to bottom
Two endpoints after layer network, and u is the starting physical node in the most short transmission path, v is the most short transmission path
Terminate physical node；
Subelement is updated, for being updated based on the minimum stream probability obtained every time to network topology, wherein more
New process includes: from network topology GaIn most short transmission path on removal stream probability and minimum stream probability difference be zero physics
Link obtains updated network topology Ga, and to updated network topology GaIt executes in the network topology GaMiddle lookup object
The most short transmission path B between node u to physical node v is managed, and obtains the minimum stream probability f on the most short transmission path B
Until most short transmission path is not present between physical node u and physical node v, for the physics chain removed in each virtual link
The corresponding stream probability in road constitutes acyclic random Flow Policy；
Strategy determines subelement, if in the network topology GaIn find between physical node u to physical node v
Most short transmission path B, determine each virtual link optimal stochastic Flow Policy be acyclic random Flow Policy.
Compared with prior art, above-mentioned technical proposal provided by the invention has the advantages that
Above-mentioned technical proposal provided by the invention is carried out by each physical node in the bottom-layer network shared to virtual net
Safe capacity assessment, obtains safe capacity matrix, can determine each dummy node pair in virtual net based on safe capacity matrix
The physical node answered, and the virtual link of each dummy node is mapped to a plurality of acyclic physics of corresponding physical node
In link, an acyclic physical link can be randomly selected in this way and carrys out the request of transfer of virtual net, it is this to randomly select physical link
Mode improve the unpredictability of link transmission, thus the safety of improve data transfer.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the flow chart of virtual net mapping method provided in an embodiment of the present invention；
Fig. 2 is the schematic diagram of virtual net provided in an embodiment of the present invention；
Fig. 3 is the schematic diagram of bottom-layer network provided in an embodiment of the present invention；
Fig. 4 is the schematic diagram that virtual net provided in an embodiment of the present invention is mapped to bottom-layer network；
Fig. 5 is to obtain the flow chart of safe capacity matrix in virtual net mapping method provided in an embodiment of the present invention；
Fig. 6 is the flow chart that virtual link maps in virtual net mapping method provided in an embodiment of the present invention；
Fig. 7 is the flow chart that loop is removed in virtual net mapping method provided in an embodiment of the present invention；
Fig. 8 is that the embodiment of the present invention provides the schematic diagram of network topology；
Fig. 9 is the schematic diagram to the updated network topology of network topology shown in Fig. 8；
Figure 10 is the structural schematic diagram of virtual net mapping device provided in an embodiment of the present invention；
Figure 11 is the structural schematic diagram of assessment unit in virtual net mapping device provided in an embodiment of the present invention；
Figure 12 is the structural schematic diagram of determination unit in virtual net mapping device provided in an embodiment of the present invention；
Figure 13 is the structural schematic diagram of map unit in virtual net mapping device provided in an embodiment of the present invention；
Figure 14 is the structural schematic diagram that subelement is removed in virtual net mapping device provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to Fig. 1, can be incited somebody to action it illustrates a kind of flow chart of virtual net mapping method provided in an embodiment of the present invention
The virtual link of each dummy node is mapped to a plurality of acyclic physical link of physical node in bottom-layer network in virtual net, in this way
A physical link can be randomly selected in the request of transfer of virtual net to transmit.Above-mentioned virtual net mapping method shown in FIG. 1
It may comprise steps of:
101: each physical node carries out safe capacity assessment in the bottom-layer network shared to virtual net, obtains safe capacity
Matrix.
In embodiments of the present invention, virtual net be carried on bottom-layer network be particular demands service virtual subnet
Net can be expressed as a two-dimensional plotIt is virtual net that wherein v, which is used to indicate and is labeled with the symbol of v,
In parameter,Indicate dummy node set in virtual net,Indicate virtual link set in virtual net,Indicate each virtual
Cpu resource needed for node,The bandwidth resources that virtual link needs are indicated, as shown in Fig. 2, lowercase a to c indicates virtual
Dummy node in net, cpu resource needed for each lowercase uses the digital representation dummy node of box out, two virtual sections
Arrow between point indicates virtual link, the bandwidth resources that digital representation virtual link thereon needs.
The physical network that bottom-layer network is shared as multiple virtual nets, can be expressed as a two-dimensional plot Gs=(Ns,Ls,
Cs,Bs), it is the parameter in bottom-layer network, N that wherein s, which is used to indicate and is labeled with the symbol of s,sIndicate the physical node in bottom-layer network
Set, LsIndicate the physical link set in bottom-layer network, CsIncluding Cs(ns) and Cr(ns), Cs(ns) indicate object in bottom-layer network
Manage node nsCPU (Central Processing Unit, central processing unit) total resources, Cr(ns) indicate in bottom-layer network
Physical node nsCpu resource surplus, BsIncludingWithIndicate physical node u in bottom-layer network
Physical link between vBandwidth resources total amount,Indicate the physics in bottom-layer network between physical node u and v
LinkBandwidth resources surplus, the schematic diagram of bottom-layer network as shown in Figure 3, wherein capitalization A to H indicate underlying network
Physical node in network, with the cpu resource surplus of the digital representation physical node of box, two physics at each physical node
Arrow between node indicates physical link, digital representation bandwidth left amount thereon.
Available safe capacity matrix is assessed by carrying out safe dose to physical node each in bottom-layer network, wherein pacifying
Each element in full capacity matrix is for indicating the safety that corresponding physical node and physical link carry out data transmission.
For given bottom-layer network Gs=(Ns,Ls,Cs,Bs), safe capacity matrix is M=[mu,v]N×N, N=| Ns| it is underlying network
Physical node number in network, mu,v=cu,v·eu,v。
102: being based on safe capacity matrix, determine the corresponding physical node of each dummy node in virtual net.
103: the virtual link of dummy node each in virtual net is mapped to a plurality of nothing of corresponding physical node
Ring physical link.
In embodiments of the present invention, above-mentioned steps 102 and 103 be virtual net mapping in node mapping and link maps this
In two stages, wherein virtual net mapping is in bottom-layer network GsIn be virtual netVirtual net request find meet node resource
With the optimal subgraph of link circuit resource constraint.
Node mapping can indicate are as follows:Dummy node in virtual net is mapped to bottom-layer network
Physical node, need to guarantee in the map physical node cpu resource surplus be greater than dummy node needed for cpu resource, i.e.,
Need to meet following formula:
Expression exists in bottom-layer network
Any one dummy node nvA corresponding physical node, and the remaining cpu resource of the physical node is more than or equal to virtually
Cpu resource needed for node can determine the corresponding multiple physical nodes of each dummy node in virtual net based on this point；Then
It obtains choosing a physical node based on safe capacity matrix from determining multiple physical nodes again, dummy node is mapped to
Selected physical node.As shown in figure 4, being mapped to physical node A, dummy node c by 102 dummy node b of above-mentioned steps
It is mapped to physical node D.
Corresponding link maps can indicate are as follows:Virtual link each in virtual net is mapped to
In acyclic physical link set in bottom-layer network, and determine the forwarding probability of every physical link, i.e. random routing strategy.Its
In, R is the set of all random routing strategies, and L is all acyclic physical link subset sets.
Random routing strategy is meant that in embodiments of the present invention: for giving virtual linkIts virtual net is asked
It asks and forwards probability distribution by the next-hop of the physical node in each bottom-layer network, asRandom routing strategy Rk=
(r1,k,......,rj,k,......,rz,k)T, rj,kThe physical link from bottom-layer network is requested for virtual netOne
Physical node u is forwarded to the probability of another physical node v, and random routing strategy needs to meet following condition:
Indicate virtual net request when without physics section
When point v, the probability of all contiguous physical nodes is forwarded to from physical node v and for 0；When by physical node v, from physics section
Point v will necessarily be forwarded to the probability of all contiguous physical nodes and for 1, as in Fig. 4 on arrow it is indicated not plus sign
Digital representation be every physical link forwarding probability.
From the above-mentioned introduction to random routing strategy it is found that obtaining the forwarding probability between physical node, and determine empty
After the quasi- corresponding physical node of node, the corresponding multiple acyclic physics chains of virtual link can determine based on random routing strategy
Road.Random routing strategy first has to obtain the random Flow Policy of each dummy node in order to obtain in embodiments of the present invention, often
A corresponding random routing strategy of random Flow Policy.
Wherein each random routing strategy Rk=(r1,k,......,rj,k,......,rz,k)TCorresponding random Flow Policy
Are as follows: Pk=(p1,k,...,pj,k,...,pM,k)T, pj,kIndicate that physical link is passed through in the virtual net request from i-th of virtual link
The stream probability of j adds the digital representation stream probability of sign as shown by the arrows in Figure 4, when stochastic flow indicates that direction is arrow instruction
It is when direction(+0.2 such as between physical node B and C) is when stochastic flow instruction direction is arrow instruction direction(- 0.2 such as between physical node B and C), the relationship between random routing strategy and random Flow Policy is as follows:
Therefore after obtaining random Flow Policy, random Flow Policy can be converted to by random road based on formula (1) and (2)
By strategy, the virtual link of each dummy node is mapped to a plurality of acyclic physical link of corresponding physical node
104: randomly selecting an acyclic physical link, selected nothing from a plurality of acyclic physical link of physical node
Ring physical link is used for transmission virtual net request.
From above scheme as can be seen that carrying out safe appearance by each physical node in the bottom-layer network shared to virtual net
Amount assessment, obtains safe capacity matrix, can determine the corresponding object of each dummy node in virtual net based on safe capacity matrix
Node is managed, and the virtual link of each dummy node is mapped to a plurality of acyclic physical link of corresponding physical node
In, an acyclic physical link can be randomly selected in this way comes the request of transfer of virtual net, this side for randomly selecting physical link
Formula improves the unpredictability of link transmission, thus the safety of improve data transfer.
Above-mentioned each step is described in detail below with reference to flow chart, referring to Fig. 5, it illustrates the present invention to implement
The flow chart of step 101 in the virtual net mapping method that example provides, may comprise steps of:
1011: any physical node is to the maximum flow valuve c between u and v in acquisition bottom-layer networku,v。
If bottom-layer network is regarded as an oil pipeline net, physical node u indicates the sending point in oil pipeline net, object
The receiving point in node v expression oil pipeline net is managed, other physical nodes indicate terminal, the bandwidth left of physical link instruction
Amount can indicate the maximum delivery of the segment pipe, then how arranging oil transportation route just can make from sending point u to receiving point v's
Total gross traffic is maximum, and such problems is known as maximum flow problem, therefore maximum flow valuve cu,vRefer to from physical node u, it can
Reach the max-flow of physical node v.Maximum flow valuve c in embodiments of the present inventionu,vIt can use Hao-Orlin algorithm to solve
It arrives.Wherein Hao and Orlin is the surname of Hao-Orlin algorithm two authors of paper respectively.
1012: the link weight of physical node each in bottom-layer network is revised as the impacted ratio of corresponding message
CoefficientInverse, wherein the impacted proportionality coefficient of the message of each physical node and respective security defense capability coefficient at
Inverse ratio, and security defense capability coefficient is known coefficient.In embodiments of the present invention, security defense capability is used to indicate each object
The safety for managing the physical link of node, can test to obtain by security level.
1013: obtaining in modified bottom-layer network any physical node to the maximum flow valuve f between u and vu,v.Max-flow
Value fu,vIt again indicates that in modified bottom-layer network from physical node u, the max-flow of physical node v can be reached,
It can use Hao-Orlin algorithm to solve to obtain.
1014: based on maximum flow valuve fu,v, obtain the first calculating parameter e of each element in safe capacity matrixu,v, wherein
eu,v=1-1/fu,v, the first calculating parameter e of each element in safe capacity matrix can be obtained based on the formulau,v。
1015: based on the first maximum flow valuve cu,vWith the first calculating parameter eu,v, obtain the element in safe capacity matrix
mu,v, wherein mu,v=cu,v·eu,v, 1≤u≤N, 1≤v≤N, N indicate the total number of physical node in bottom-layer network, and N is big
In 1 integer.
The safe capacity matrix that can obtain the shared bottom-layer network of virtual net through the above steps, due to safe capacity
Each element in matrix for indicating the safety that corresponding physical node and physical link carry out data transmission, so
It, can be with the higher physical node of preferred security, to improve when determining in virtual net the corresponding physical node of each dummy node
The safety of data transmission.
In embodiments of the present invention, it is based on safe capacity matrix, determines the corresponding object of each dummy node in virtual net
The process for managing node is as follows:
Firstly, since virtual net to the maximum dummy node of network resource requirement, be based on breadth first traversal principle,
The mapping order for determining each dummy node in virtual net is then based on mapping order and maps each dummy node,
According to the sequence of dummy node, its mapping process is also different when mapping dummy node.
Mapping process includes: to the mapping process of the 1st dummy node and to the 1st virtual section in embodiments of the present invention
The mapping process of dummy node after point.It include: wherein based on the 1st virtual section to the mapping process of the 1st dummy node
The network resource requirement of point, determines second both candidate nodes set of the 1st dummy node in bottom-layer network；Based on safe capacity
Matrix calculates the second average security capacity of each physical node in the second both candidate nodes set；1st dummy node is mapped
The second maximum physical node of average security capacity into the second both candidate nodes set.Second candidate node set determined by wherein
Cpu resource needed for the cpu resource surplus of each physical node is more than or equal to the 1st dummy node in conjunction.Second average peace
Full capacity is then the average value of the safe capacity between other all second both candidate nodes, such as in the second both candidate nodes set
Including four physical nodes, respectively physical node 1, physical node 2, physical node 3 and physical node 4, then physical node 1
Second average security capacity are as follows: (safe capacity+object between safe capacity+physical node 1 and 3 between physical node 1 and 2
Manage the safe capacity between node 1 and 4)/3, wherein the safe capacity between physical node 1 and 2 is m1.2。
It include: accordingly virtual based on x-th for the mapping process of other dummy nodes after the 1st dummy node
The network resource requirement of node determines first both candidate nodes set of i-th of dummy node in bottom-layer network；Based on safe appearance
Moment matrix calculates each physical node and the 1st, 2 ... in the first both candidate nodes set, the corresponding physics section of x-1 dummy node
The first average security capacity between point；X-th of dummy node is mapped to the first average security in the first both candidate nodes set
The maximum physical node of capacity, 2≤x≤M, M indicate the total number of dummy node in virtual net, and M is the integer greater than 2,
In determined by the first both candidate nodes set the cpu resource surplus of each physical node be more than or equal to x-th of dummy node
Required cpu resource.
It such as include four physical nodes, respectively object in the first both candidate nodes set determined by the 3rd dummy node
Node 5, physical node 6, physical node 7 and physical node 8 are managed, and physical node 5 is determined with the 1st and the 2nd dummy node
The safe capacities of the first both candidate nodes be a and b respectively, then the first average security capacity of physical node 5 are as follows: (a+b)/2.
Herein it should be noted is that: above-mentioned breadth-first variable principle be based on dummy node need bandwidth money
The descending sequence in source calculates the mapping order of each dummy node.Furthermore when maximum first average security capacity and most
When the number of the second big average security capacity is multiple, one of physical node can be randomly selected and mapped.
The above-mentioned node mapping elaborated in virtual net mapping, is below then situated between to the link maps in virtual net mapping
It continues, i.e., the detailed process of step 103 in virtual net mapping method shown in FIG. 1 is illustrated, it specifically can be refering to Fig. 6 institute
Show, comprising the following steps:
1031: the virtual link mapping problems of dummy node each in virtual net being converted into linear programming problem, linearly
Planning problem is the linear function problem of the corresponding stochastic flow of each virtual link.
In embodiments of the present invention, virtual link mapping problems is converted to linear programming problem is: assuming that variable be with
Machine stream pj,kWith λ (λ is newly-increased variable, no particular meaning), and min λ is solved, to the constraint of the two variables in solution procedure
Condition is bandwidth constraint condition, i.e., for every virtual link, be less than for the bandwidth that its physical link mapped distributes etc.
In the remaining bandwidth of the physical link, formula are as follows:
It can simplify are as follows:Variable pj,kThe condition of satisfaction is as follows:
1032: linear programming problem being solved, the optimal stochastic Flow Policy P of each virtual link is obtainedk=(p1,k,
p2,k,......,pt,k), t is the number for the physical link that i-th of virtual link is mapped to, pj,kIt indicates to come from k-th of virtual chain
The stream probability of physical link j, 1≤k≤M are passed through in the virtual net request on road.
After being converted into linear programming problem, above-mentioned linear programming problem is solved using lp_solve function library, is obtained
Optimal stochastic Flow Policy setWhereinIt is (P when objective function min λ obtains minimum value1,...,Pm)
Value, m are dummy node total number, and wherein lp_solve function library is an open source software program, dedicated for solving linear gauge
The problem of drawing.
1033: removing the loop in the optimal stochastic Flow Policy of each virtual link, obtain the acyclic of each virtual link
Random Flow Policy.Wherein so-called loop refers to the start node in the path of a plurality of physical link composition and terminal node is same
Node, however there is no pass through the case where multiple physical nodes pass start node back again, therefore this in actual transmission process
Inventive embodiments need to remove the loop in the optimal stochastic strategy of each virtual link.
With optimal stochastic Flow Policy PkFor, remove loop process can with as shown in fig.7, the following steps are included:
201: building is by pj,kThe network topology G of > 0 physical link compositiona.The signal of virtual net mapping as shown in Figure 4
Figure, wherein the arrow with sign number place is the stochastic flow of each dummy node, positive sign indicates that stochastic flow is forward direction
Transmission can construct p by number thereon if the transmission direction of physical node B to C is positive transmissionj,k> 0 physics chain
The network topology G of road compositiona, as shown in figure 8, Fig. 8 is the network topology G constructed based on Fig. 4a。
202: if in network topology GaIn find most short transmission path B between physical node u to physical node v, obtain
Take the minimum stream probability f on most short transmission path B.Wherein u and v is virtual linkTwo ends after being mapped to bottom-layer network
Point, and u is the starting physical node in most short transmission path, v is the termination physical node in most short transmission path.
In embodiments of the present invention, most short transmission path B is from the transmission range physical node u to physical node v
The smallest path can be obtained by dijkstra (Di Jiesitela) algorithm, and wherein dijkstra algorithm is typical list
Source shortest path first, the shortest path for calculating a node to other all nodes.It include extremely in most short transmission path B
A few stochastic flow, therefore after finding most short transmission path, it is chosen most from the stochastic flow that most short transmission path includes
Small stream probability is as minimum stream probability f.
203: network topology being updated based on the minimum stream probability obtained every time, wherein renewal process includes: from net
Network topology GaIn most short transmission path on removal stream probability and minimum stream probability difference be zero physical link, after obtaining update
Network topology Ga, and to updated network topology GaIt executes in network topology GaMiddle lookup physical node u to physical node v
Between most short transmission path B, and obtain the minimum stream probability f on most short transmission path B until can not find physical node u to object
The path between node v is managed, stream probability corresponding for the physical link removed in each virtual link constitutes acyclic stochastic flow
Strategy.
Assuming that most short transmission path is D → C → G → A in Fig. 8, minimum stream probability is 0.1, then updated network topology
GaAs shown in figure 9, to network topology G shown in Fig. 9aIt executes step 202 and searches updated network topology GaIn most short transmission
Path B, and minimum stream probability f thereon is obtained, then using minimum stream probability f to network topology G shown in Fig. 9aAgain into
Row is updated to obtain next most short transmission path and minimum stream probability.
It, can from the above process as can be seen that often finding a most short transmission path and getting a minimum stream probability
With with the two parameters to network topology GaIt is updated.
204: if in network topology GaIn find most short transmission path B between physical node u to physical node v, really
The optimal stochastic Flow Policy of fixed each virtual link is acyclic random Flow Policy.
1034: acyclic random Flow Policy is converted into acyclic random routing strategy Rk, RkIt is used to indicate each dummy node
Virtual link is mapped to a plurality of acyclic physical link of corresponding physical node, Rk=(r1,k,......,
rj,k,......,rz,k)T, rj,kIt requests for virtual net from physical linkA physical node u be forwarded to another object
The probability of node v is managed, z is the total number for the physical node that each dummy node is mapped to.
The corresponding relationship of above-mentioned formula (1) and (2) between random routing strategy and random Flow Policy, therefore obtaining nothing
After the random Flow Policy of ring, acyclic random routing strategy R can be obtained based on formula (1) and (2)k。
For the various method embodiments described above, for simple description, therefore, it is stated as a series of action combinations, but
Be those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because according to the present invention, certain
A little steps can be performed in other orders or simultaneously.Secondly, those skilled in the art should also know that, it is retouched in specification
The embodiment stated belongs to preferred embodiment, and related actions and modules are not necessarily necessary for the present invention.
Corresponding with above method embodiment, the embodiment of the present invention also provides a kind of virtual net mapping device, and structure is shown
It is intended to as shown in Figure 10, may include: assessment unit 11, determination unit 12, map unit 13 and selection unit 14.
Assessment unit 11 carries out safe capacity assessment for each physical node in the bottom-layer network shared to virtual net,
Obtain safe capacity matrix.Wherein each element in safe capacity matrix is for indicating corresponding physical node and physics chain
The safety that road carries out data transmission.For given bottom-layer network Gs=(Ns,Ls,Cs,Bs), safe capacity matrix is M=
[mu,v]N×N, N=| Ns| for physical node number in bottom-layer network, mu,v=cu,v·eu,v。
Determination unit 12 determines the corresponding physics of each dummy node in virtual net for being based on safe capacity matrix
Node.
Map unit 13, for the virtual link of dummy node each in virtual net to be mapped to corresponding physics section
The a plurality of acyclic physical link of point.
In embodiments of the present invention, the function that above-mentioned determination unit 12 and map unit 13 have is in virtual net mapping
Node mapping and the two stages of link maps, wherein virtual net mapping is in bottom-layer network GsIn be virtual netVirtual net
The optimal subgraph for meeting node resource and link circuit resource constraint, including node mapping and two processes of link maps are found in request,
The structure of specific determination unit 12 and map unit 13 as described below.
Selection unit 14, for randomly selecting an acyclic physics chain from a plurality of acyclic physical link of physical node
Road, selected acyclic physical link are used for transmission virtual net request.
From above scheme as can be seen that carrying out safe appearance by each physical node in the bottom-layer network shared to virtual net
Amount assessment, obtains safe capacity matrix, can determine the corresponding object of each dummy node in virtual net based on safe capacity matrix
Node is managed, and the virtual link of each dummy node is mapped to a plurality of acyclic physical link of corresponding physical node
In, an acyclic physical link can be randomly selected in this way comes the request of transfer of virtual net, this side for randomly selecting physical link
Formula improves the unpredictability of link transmission, thus the safety of improve data transfer.
In embodiments of the present invention, the structural schematic diagram of assessment unit 11 can such as Figure 11 so, comprising: first obtain son
Unit 111, modification subelement 112, second obtain subelement 113, the first computation subunit 114 and the second computation subunit 115.
First obtains subelement 111, for obtaining in bottom-layer network any physical node to the maximum flow valuve between u and v
cu,v.If bottom-layer network is regarded as an oil pipeline net, physical node u indicates the sending point in oil pipeline net, physics section
Point v indicates the receiving point in oil pipeline net, other physical nodes indicate terminal, and the bandwidth left amount of physical link instruction can
To indicate the maximum delivery of the segment pipe, then how to arrange oil transportation route just and can make total fortune from sending point u to receiving point v
Throughput rate is maximum, and such problems is known as maximum flow problem, therefore maximum flow valuve cu,vRefer to from physical node u, can reach
The max-flow of physical node v.Maximum flow valuve c in embodiments of the present inventionu,vIt can use Hao-Orlin algorithm to solve to obtain.Its
Middle Hao and Orlin is the surname of Hao-Orlin algorithm two authors of paper respectively.
Subelement 112 is modified, it is corresponding for the link weight of physical node each in bottom-layer network to be revised as
The impacted proportionality coefficient of messageInverse, wherein the impacted proportionality coefficient of the message of each physical node and respective safety
Defence capability coefficient is inversely proportional, and security defense capability coefficient is known coefficient.In embodiments of the present invention, security defense capability
It is used to indicate the safety of the physical link of each physical node, can test to obtain by security level.
Second obtains subelement 113, for obtaining in modified bottom-layer network any physical node between u and v
Maximum flow valuve fu,v.Maximum flow valuve fu,vIt again indicates that in modified bottom-layer network from physical node u, can reach
The max-flow of physical node v can use Hao-Orlin algorithm and solve to obtain.
First computation subunit 114, for based on maximum flow valuve fu,v, obtain of each element in safe capacity matrix
One calculating parameter eu,v.Wherein eu,v=1-1/fu,v, of each element in safe capacity matrix can be obtained based on the formula
One calculating parameter eu,v。
Second computation subunit 115, for based on maximum flow valuve cu,vWith the first calculating parameter eu,v, obtain safe capacity square
Element m in battle arrayu,v, wherein mu,v=cu,v·eu,v, 1≤u≤N, 1≤v≤N, N indicate total of physical node in bottom-layer network
Number, and N is the integer greater than 1.
Preceding to have addressed, determination unit 12 is used for the physics section being mapped as the dummy node in virtual net in bottom-layer network
Point, its corresponding structure are shown in Fig.12, comprising: determine subelement 121 and mapping subelement 122.
It determines subelement 121, for since virtual net to the maximum dummy node of network resource requirement, is based on width
First traversal principle determines the mapping order of each dummy node in virtual net.
Subelement 122 is mapped, for being based on mapping order, each dummy node is mapped, wherein virtual to x-th
The mapping process of node includes: the network resource requirement based on x-th of dummy node, determines i-th of dummy node in underlying network
The first both candidate nodes set in network.Each physical node and the in the first both candidate nodes set is calculated based on safe capacity matrix
The first average security capacity between the corresponding physical node of x-1 dummy node.X-th of dummy node is mapped to the first time
The first maximum physical node of average security capacity in node set is selected, dummy node is total in 2≤x≤M, M expression virtual net
Number, and M is the integer greater than 2.
Mapping process to the 1st dummy node includes: the network resource requirement based on the 1st dummy node, determines the 1st
Second both candidate nodes set of a dummy node in bottom-layer network.The second both candidate nodes set is calculated based on safe capacity matrix
In each physical node the second average security capacity.1st dummy node is mapped to second in the second both candidate nodes set
The maximum physical node of average security capacity.
Herein it should be noted is that: above-mentioned breadth-first variable principle be based on dummy node need bandwidth money
The descending sequence in source calculates the mapping order of each dummy node.Furthermore when maximum first average security capacity and most
When the number of the second big average security capacity is multiple, one of physical node can be randomly selected and mapped.
The structural schematic diagram of corresponding map unit 13 is as shown in figure 13, may include: the first conversion subunit 131,
Solve subelement 132, removal subelement 133 and the second conversion subunit 134.
First conversion subunit 131, for being converted to the virtual link mapping problems of dummy node each in virtual net
Linear programming problem, linear programming problem are the linear function problem of the corresponding stochastic flow of each virtual link.
It solves subelement 132 and obtains the optimal stochastic stream of each virtual link for solving to linear programming problem
Tactful Pi, Pk=(p1,k,p2,k,......,pt,k), t is the number for the physical link that i-th of virtual link is mapped to, pj,kIt indicates
The stream probability of physical link j, 1≤k≤M are passed through in virtual net request from k-th of virtual link.
Subelement 133 is removed, the loop in optimal stochastic Flow Policy for removing each virtual link obtains each void
The acyclic random Flow Policy of quasi- link.Wherein removal subelement 133 includes: building subelement 1331, obtains subelement 1332, more
New subelement 1333 and strategy determine subelement 1334, as shown in figure 14.
Subelement 1331 is constructed, for being directed to optimal stochastic Flow Policy Pk, construct by pj,kThe net of > 0 physical link composition
Network topology Ga。
Subelement 1332 is obtained, if in network topology GaIn find between physical node u to physical node v most
Short transmission path B obtains the minimum stream probability f on most short transmission path B.Wherein u and v is virtual linkIt is mapped to underlying network
Two endpoints after network, and u is the starting physical node in most short transmission path, v is the termination physical node in most short transmission path.
Subelement 1333 is updated, for being updated based on the minimum stream probability obtained every time to network topology, wherein more
New process includes: from network topology GaIn most short transmission path on removal stream probability and minimum stream probability difference be zero physics
Link obtains updated network topology Ga, and to updated network topology GaIt executes in network topology GaMiddle lookup physics section
Most short transmission path B between point u to physical node v, and the minimum stream probability f on most short transmission path B is obtained until physics
Most short transmission path is not present between node u and physical node v, it is corresponding for the physical link removed in each virtual link
It flows probability and constitutes acyclic random Flow Policy.
Strategy determines subelement 1334, if in network topology GaIn find between physical node u to physical node v
Most short transmission path B, determine each virtual link optimal stochastic Flow Policy be acyclic random Flow Policy.
Second conversion subunit 134, for acyclic random Flow Policy to be converted to acyclic random routing strategy Rk, RkFor
Indicate that the virtual link of each dummy node is mapped to a plurality of acyclic physical link of corresponding physical node, Rk=
(r1,k,......,rj,k,......,rz,k)T, rj,kIt requests for virtual net from physical linkA physical node u turn
It is dealt into the probability of another physical node v, z is the total number for the physical node that each dummy node is mapped to.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For device class embodiment, since it is basically similar to the method embodiment, so being described relatively simple, related place ginseng
See the part explanation of embodiment of the method.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
The foregoing description of the disclosed embodiments can be realized those skilled in the art or using the present invention.To this
A variety of modifications of a little embodiments will be apparent for a person skilled in the art, and the general principles defined herein can
Without departing from the spirit or scope of the present invention, to realize in other embodiments.Therefore, the present invention will not be limited
It is formed on the embodiments shown herein, and is to fit to consistent with the principles and novel features disclosed in this article widest
Range.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (6)
1. a kind of virtual net mapping method, which is characterized in that the described method includes:
Each physical node carries out safe capacity assessment in the bottom-layer network shared to virtual net, obtains safe capacity matrix；
Based on the safe capacity matrix, the corresponding physical node of each dummy node in the virtual net is determined；
The virtual link of dummy node each in the virtual net is mapped to a plurality of acyclic object of corresponding physical node
Manage link；
An acyclic physical link, selected acyclic object are randomly selected from a plurality of acyclic physical link of the physical node
Reason link is used for transmission virtual net request；
Wherein, described that safe capacity assessment is carried out to physical node each in the bottom-layer network, safe capacity matrix is obtained, is wrapped
It includes:
Any physical node is obtained in the bottom-layer network to the maximum flow valuve c between u and vu,v；
The link weight of physical node each in the bottom-layer network is revised as the impacted proportionality coefficient of corresponding messageInverse, wherein the impacted proportionality coefficient of message of each physical node and respective security defense capability coefficient at
Inverse ratio, and the security defense capability coefficient is known coefficient；
Any physical node is obtained in modified bottom-layer network to the maximum flow valuve f between u and vu,v；
Based on the maximum flow valuve fu,v, obtain the first calculating parameter e of each element in the safe capacity matrixu,v；
Based on the maximum flow valuve cu,vWith the first calculating parameter eu,v, obtain the element m in the safe capacity matrixu,v,
Wherein 1≤u≤N, 1≤v≤N, N indicate the total number of physical node in the bottom-layer network, and N is the integer greater than 1；
The virtual link by dummy node each in the virtual net is mapped to a plurality of nothing of corresponding physical node
Ring physical link, comprising:
The virtual link mapping problems of dummy node each in the virtual net is converted into linear programming problem, the linear gauge
The problem of drawing is the linear function problem of the corresponding stochastic flow of each virtual link；
The linear programming problem is solved, the optimal stochastic Flow Policy P of each virtual link is obtainedi, Pk=(p1,k,
p2,k,......,pt,k), t is the number for the physical link that i-th of virtual link is mapped to, pj,kIt indicates to come from k-th of virtual chain
The stream probability of physical link j is passed through in the virtual net request on road, and 1≤k≤M, M are the integer greater than 2；
The loop in the optimal stochastic Flow Policy of each virtual link is removed, the acyclic stochastic flow plan of each virtual link is obtained
Slightly；
The acyclic random Flow Policy is converted into acyclic random routing strategy Rk, RkIt is used to indicate the virtual of each dummy node
A plurality of acyclic physical link of the link maps to corresponding physical node, Rk=(r1,k,......,rj,k,......,
rz,k)T, rj,kIt requests for virtual net from physical linkA physical node u be forwarded to the general of another physical node v
Rate, z are the total number for the physical node that each dummy node is mapped to.
2. determining the void the method according to claim 1, wherein described be based on the safe capacity matrix
The corresponding physical node of each dummy node in quasi- net, comprising:
Since the virtual net to the maximum dummy node of network resource requirement, be based on breadth first traversal principle, determine
The mapping order of each dummy node in the virtual net；
Based on the mapping order, each dummy node is mapped, wherein to the mapping process of x-th of dummy node
Include: the network resource requirement based on x-th of dummy node, determines first candidate of i-th of dummy node in bottom-layer network
Node set；Based on each physical node in safe capacity matrix calculating the first both candidate nodes set and xth -1
The first average security capacity between the corresponding physical node of dummy node；X-th of dummy node is mapped to described first to wait
The first maximum physical node of average security capacity in node set is selected, 2≤x≤M, M indicate dummy node in the virtual net
Total number；
Mapping process to the 1st dummy node includes: the network resource requirement based on the 1st dummy node, determines the 1st void
Quasi- second both candidate nodes set of the node in bottom-layer network；Second both candidate nodes are calculated based on the safe capacity matrix
Second average security capacity of each physical node in set；1st dummy node is mapped to second candidate node set
The second maximum physical node of average security capacity in conjunction.
3. according to the method described in claim 2, it is characterized in that, the optimal stochastic Flow Policy of each virtual link of removal
In loop, obtain the acyclic random Flow Policy of each virtual link, comprising:
For optimal stochastic Flow Policy Pk, construct by pj,kThe network topology G of the physical link composition of > 0a；
If in the network topology GaIn find most short transmission path B between physical node u to physical node v, described in acquisition
Minimum stream probability f on most short transmission path B；Wherein u and v is virtual linkTwo endpoints after being mapped to bottom-layer network,
And u is the starting physical node in the most short transmission path, v is the termination physical node in the most short transmission path；
Network topology is updated based on the minimum stream probability obtained every time, wherein renewal process includes: to open up from network
Flutter GaIn most short transmission path on removal stream probability and minimum stream probability difference be zero physical link, obtain updated net
Network topology Ga, and to updated network topology GaIt executes in the network topology GaMiddle lookup physical node u to physical node v
Between most short transmission path B, and obtain the minimum stream probability f on the most short transmission path B until physical node u and physics
Most short transmission path is not present between node v, stream probability corresponding for the physical link removed in each virtual link is constituted
Acyclic random Flow Policy；
If in the network topology GaIn find most short transmission path B between physical node u to physical node v, determine each
The optimal stochastic Flow Policy of virtual link is acyclic random Flow Policy.
4. a kind of virtual net mapping device, which is characterized in that described device includes:
Assessment unit carries out safe capacity assessment for each physical node in the bottom-layer network shared to virtual net, is pacified
Full capacity matrix；
Determination unit determines the corresponding object of each dummy node in the virtual net for being based on the safe capacity matrix
Manage node；
Map unit, for the virtual link of dummy node each in the virtual net to be mapped to corresponding physical node
A plurality of acyclic physical link；
Selection unit, for randomly selecting an acyclic physical link from a plurality of acyclic physical link of the physical node,
Selected acyclic physical link is used for transmission virtual net request；
Wherein, the assessment unit includes:
First obtains subelement, for obtaining in the bottom-layer network any physical node to the maximum flow valuve c between u and vu,v；
Subelement is modified, for the link weight of physical node each in the bottom-layer network to be revised as corresponding message
Impacted proportionality coefficientInverse, wherein the impacted proportionality coefficient of message of each physical node and respective safety are anti-
Imperial capacity factor is inversely proportional, and the security defense capability coefficient is known coefficient；
Second obtains subelement, for obtaining in modified bottom-layer network any physical node to the maximum flow valuve between u and v
fu,v；
First computation subunit, for based on the maximum flow valuve fu,v, obtain of each element in the safe capacity matrix
One calculating parameter eu,v；
Second computation subunit, for based on the maximum flow valuve cu,vWith the first calculating parameter eu,v, obtain the safety
Element m in capacity matrixu,v, wherein 1≤u≤N, 1≤v≤N, N indicate the total number of physical node in the bottom-layer network,
And N is the integer greater than 1；
The map unit includes:
First conversion subunit, for being converted to linearly the virtual link mapping problems of dummy node each in the virtual net
Planning problem, the linear programming problem are the linear function problem of the corresponding stochastic flow of each virtual link；
It solves subelement and obtains the optimal stochastic stream plan of each virtual link for solving to the linear programming problem
Slightly Pi, Pk=(p1,k,p2,k,......,pt,k), t is the number for the physical link that i-th of virtual link is mapped to, pj,kIt indicates to come
Pass through the stream probability of physical link j from the virtual net request of k-th of virtual link, 1≤k≤M, M are the integer greater than 2；
Subelement is removed, the loop in optimal stochastic Flow Policy for removing each virtual link obtains each virtual link
Acyclic random Flow Policy；
Second conversion subunit, for the acyclic random Flow Policy to be converted to acyclic random routing strategy Rk, RkIt is used to indicate
The virtual link of each dummy node is mapped to a plurality of acyclic physical link of corresponding physical node, Rk=
(r1,k,......,rj,k,......,rz,k)T, rj,kIt requests for virtual net from physical linkA physical node u turn
It is dealt into the probability of another physical node v, z is the total number for the physical node that each dummy node is mapped to.
5. device according to claim 4, which is characterized in that the determination unit includes:
Determine subelement, it is excellent based on width for since the virtual net to the maximum dummy node of network resource requirement
Principle is first traversed, determines the mapping order of each dummy node in the virtual net；
Subelement is mapped, for being based on the mapping order, each dummy node is mapped, wherein to x-th of void
The mapping process of quasi- node includes: the network resource requirement based on x-th of dummy node, determines i-th of dummy node in bottom
The first both candidate nodes set in network；Each object in the first both candidate nodes set is calculated based on the safe capacity matrix
Manage the first average security capacity between node physical node corresponding with -1 dummy node of xth；X-th of dummy node is reflected
It is mapped to the first maximum physical node of average security capacity in the first both candidate nodes set, 2≤x≤M, M indicate the void
The total number of dummy node in quasi- net；
Mapping process to the 1st dummy node includes: the network resource requirement based on the 1st dummy node, determines the 1st void
Quasi- second both candidate nodes set of the node in bottom-layer network；Second both candidate nodes are calculated based on the safe capacity matrix
Second average security capacity of each physical node in set；1st dummy node is mapped to second candidate node set
The second maximum physical node of average security capacity in conjunction.
6. device according to claim 5, which is characterized in that the removal subelement includes:
Subelement is constructed, for being directed to optimal stochastic Flow Policy Pk, construct by pj,kThe network topology of the physical link composition of > 0
Ga；
Subelement is obtained, if in the network topology GaIn find most short pass between physical node u to physical node v
Defeated path B obtains the minimum stream probability f on the most short transmission path B；Wherein u and v is virtual linkIt is mapped to underlying network
Two endpoints after network, and u is the starting physical node in the most short transmission path, v is the termination in the most short transmission path
Physical node；
Subelement is updated, for being updated based on the minimum stream probability obtained every time to network topology, wherein updated
Journey includes: from network topology GaIn most short transmission path on removal stream probability and minimum stream probability difference be zero physics chain
Road obtains updated network topology Ga, and to updated network topology GaIt executes in the network topology GaMiddle lookup physics
Most short transmission path B between node u to physical node v, and the minimum stream probability f obtained on the most short transmission path B is straight
To most short transmission path is not present between physical node u and physical node v, for the physical link removed in each virtual link
Corresponding stream probability constitutes acyclic random Flow Policy；
Strategy determines subelement, if in the network topology GaIn find between physical node u to physical node v most
Short transmission path B determines that the optimal stochastic Flow Policy of each virtual link is acyclic random Flow Policy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510344602.3A CN104869044B (en) | 2015-06-19 | 2015-06-19 | A kind of virtual net mapping method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510344602.3A CN104869044B (en) | 2015-06-19 | 2015-06-19 | A kind of virtual net mapping method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104869044A CN104869044A (en) | 2015-08-26 |
| CN104869044B true CN104869044B (en) | 2019-01-29 |
Family
ID=53914583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510344602.3A Active CN104869044B (en) | 2015-06-19 | 2015-06-19 | A kind of virtual net mapping method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104869044B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107124287A (en) * | 2016-02-24 | 2017-09-01 | 中移(苏州)软件技术有限公司 | A kind of virtual network service method for quality control and device |
| CN107733677B (en) * | 2016-08-12 | 2022-11-15 | 中兴通讯股份有限公司 | Alarm generation method and device for overlay network |
| CN107231412A (en) * | 2017-05-22 | 2017-10-03 | 浙江工商大学 | A kind of service path building method mapped based on virtual net |
| EP3929781A1 (en) * | 2020-06-25 | 2021-12-29 | Vocalink Limited | Reconstructing a dataset after detection of a network security threat in a network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102136998A (en) * | 2010-08-30 | 2011-07-27 | 华为技术有限公司 | Traffic engineering and server selection joint optimization method, system and related equipment |
| CN102904794A (en) * | 2012-09-27 | 2013-01-30 | 北京邮电大学 | Method and device for mapping virtual network |
| CN102932479A (en) * | 2012-11-16 | 2013-02-13 | 北京邮电大学 | Virtual network mapping method for realizing topology awareness based on historical data |
| CN103457752A (en) * | 2012-05-30 | 2013-12-18 | 中国科学院声学研究所 | Virtual network mapping method |
| CN104320343A (en) * | 2014-10-28 | 2015-01-28 | 北京邮电大学 | Electric energy perception cross-domain virtual network mapping method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013157855A (en) * | 2012-01-31 | 2013-08-15 | Nec Corp | Method of connecting virtual network, virtual network connection device, and program |
-
2015
- 2015-06-19 CN CN201510344602.3A patent/CN104869044B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102136998A (en) * | 2010-08-30 | 2011-07-27 | 华为技术有限公司 | Traffic engineering and server selection joint optimization method, system and related equipment |
| CN103457752A (en) * | 2012-05-30 | 2013-12-18 | 中国科学院声学研究所 | Virtual network mapping method |
| CN102904794A (en) * | 2012-09-27 | 2013-01-30 | 北京邮电大学 | Method and device for mapping virtual network |
| CN102932479A (en) * | 2012-11-16 | 2013-02-13 | 北京邮电大学 | Virtual network mapping method for realizing topology awareness based on historical data |
| CN104320343A (en) * | 2014-10-28 | 2015-01-28 | 北京邮电大学 | Electric energy perception cross-domain virtual network mapping method and system |
Non-Patent Citations (2)
| Title |
|---|
| 《Energy-Aware Virtual Network Embedding》;Sen Su等;《IEEE/ACM TRANSACTIONS ON NETWORKING》;20141031;第22卷(第5期);全文 |
| 《基于负载均衡的虚拟网映射随机算法》;余建军等;《计算机科学》;20140630;第41卷(第6期);全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104869044A (en) | 2015-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104869044B (en) | A kind of virtual net mapping method and device | |
| US8862744B2 (en) | Optimizing traffic load in a communications network | |
| CN109146447A (en) | The transparent sharding method of block chain, apparatus and system | |
| CN107888496A (en) | Multiple path computings for label switched path | |
| CN108696777A (en) | The flexible optical network resource distribution method of space division multiplexing frequency spectrum of minimum cross-talk | |
| CN108322333A (en) | A kind of laying method of the virtual network function based on genetic algorithm | |
| CN108270557A (en) | A kind of backbone system and its trunking method based on quantum communications | |
| CN104683488B (en) | Streaming computing system and its dispatching method and device | |
| CN104917659B (en) | A kind of mapping method of virtual network based on virtual network connection performance | |
| CN103403683A (en) | Capabilities based routing of virtual data center service request | |
| CN105634974B (en) | Route determining methods and device in software defined network | |
| CN105191215A (en) | Data plane learning of bi-directional service chains | |
| CN102804712A (en) | Method and apparatus for selecting between multiple equal cost paths | |
| CN108809847A (en) | Realize the method, apparatus and network system of load balancing | |
| CN104158748B (en) | A kind of topological detecting method towards system for cloud computing | |
| CN105743763B (en) | A kind of mapping method of virtual network based on study and reasoning | |
| CN108667657A (en) | A kind of mapping method of virtual network based on local feature information towards SDN | |
| CN103236978B (en) | The determination method and apparatus of AS topology top layer autonomous system node | |
| Duarte et al. | Improved heuristics for the regenerator location problem | |
| CN101645919A (en) | Popularity-based duplicate rating calculation method and duplicate placement method | |
| US10038589B1 (en) | Network link capacity determination | |
| CN109039959A (en) | A kind of the consistency judgment method and relevant apparatus of SDN network rule | |
| CN109347657A (en) | The virtual data domain construction method of scientific and technological business is supported under SDN mode | |
| Guerrero et al. | Optimization policy for file replica placement in fog domains | |
| CN102821122A (en) | Method and apparatus for node distribution and computer program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |