CN105357080B - A kind of traffic engineering method applied to software defined network - Google Patents
A kind of traffic engineering method applied to software defined network Download PDFInfo
- Publication number
- CN105357080B CN105357080B CN201510867549.5A CN201510867549A CN105357080B CN 105357080 B CN105357080 B CN 105357080B CN 201510867549 A CN201510867549 A CN 201510867549A CN 105357080 B CN105357080 B CN 105357080B
- Authority
- CN
- China
- Prior art keywords
- business stream
- link
- bandwidth
- network
- shortest path
- 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.)
- Expired - Fee Related
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/38—Flow based routing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2425—Traffic characterised by specific attributes, e.g. priority or QoS for supporting services specification, e.g. SLA
- H04L47/2433—Allocation of priorities to traffic types
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
Abstract
The invention discloses a kind of traffic engineering method applied to software defined network, step is main are as follows: obtains network topology, link capacity, Business Stream set and approximation parameters；Initialize linkage length, the first flow variables and the second flow variables；The identical Business Stream of source node is divided into one kind；Bandwidth allocation successively is carried out to every class Business Stream；Export final bandwidth allocation plan.Although the present invention is based on approximate algorithm, but obtained approximate solution is very close to utilize the obtained optimal solution of linear programming, simultaneously, approximate algorithm pairing approximation rate parameter proposed by the present invention is simultaneously insensitive, compared with approximate algorithm, even if the target function value acquired using larger approximation parameters and the target function value acquired using lesser approximation parameters are very close, due to algorithm proposed by the present invention and approximate algorithm on computation complexity, therefore, biggish approximation parameters are selected to can dramatically the computational efficiency of ground boosting algorithm, and this is significantly to the traffic engineering of large scale network.
Description
Technical field
The present invention relates to fields of communication technology, more particularly to a kind of traffic engineering side applied to software defined network
Method.
Background technique
What control logic and data forwarding capability in traditional network architecture were bound together, that is, control plane and data
Plane is coupling.With the sustainable growth of user demand, the type of service that network need to carry is more and more, large amount of complex
Network function needs to be added in mobile network.In this case, operator needs individually to carry out each network equipment
Configuration, management and function renewal, bring great operating difficulties and expense.A kind of new network architecture --- software definition
Network (SDN) is proposed by network-based control plane and data planar separation, and by the control and management function of various network nodes
It is concentrated to a website in logic, to simplify network-based control and management.Meanwhile SDN is using Business Stream as Control granularity,
Using global network and business information, it can be accurately controlled business conduct and distribution Internet resources, enabled the network to more
Efficiently run.
Business demand is mapped in network topology by traffic engineering, including is that business finds feasible transmission path and is it
Network bandwidth resources are distributed, congestion occur to avoid network and guarantee that user obtains certain service quality.In traditional network frame
In structure, network resource management is based primarily upon Routing Protocol realization.The Routing Protocol of Internet such as RIP, OSPF, based on distribution
The shortest path first of formula is that Business Stream finds path, and there is no the Internet resources distribution mechanisms of service-oriented stream.Each business
Stream competes with one another for Internet resources, is easy that network is made load imbalance occur, causes network congestion and wastes Internet resources.It will stream
Engineering is measured in conjunction with conventional wired networks Routing Protocol, as OSPF-TE routes by adjusting the weight of link in network to change
Path waits cost multi-paths (ECMP) to disperse business load using a plurality of equative route simultaneously, reduces the hair of network congestion
It is raw, improve network performance.Under SDN network framework, traffic engineering can play a greater role, more flexible status business point
With resource.Due to the global network and business information of having of SDN, traffic engineering mechanism can use these information into
Row global optimization, obtains multi-path routing mechanism, to optimize network resource utilization.Although the stream based on Multi-path route
Amount engineering machine has been made as Internet resources distribution and has brought great flexibility, still, corresponding mathematical problem (linear programming)
It is difficult to effectively Real-time solution under medium or large scale network, causes the traffic engineering mechanism based on Multi-path route cannot
It is effectively applied in existing network.If not pursuing Exact Solutions, approximate solution is taken, then usually requires that higher approximate essence
It spends and is just able to satisfy practical application request, and the higher approximation quality computation complexity on the contrary for improving approximate solution, it is allowed to
It is difficult to practical application.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of flow works applied to software defined network
Cheng Fangfa guarantees to calculate the time within the acceptable range while obtaining near-optimization Internet resources allocation plan.
The purpose of the present invention is achieved through the following technical solutions: a kind of flow work applied to software defined network
Cheng Fangfa, comprising the following steps:
S1. network topological information is obtained, network topological information includes: network topologyWhereinRepresent node
Set, number of nodes n,Link set is represented, link sum is m；The link capacity of link eBusiness Stream
SetWherein the bandwidth demand of Business Stream k is d (k)；Approximation parameters w；
S2. the linkage length for defining link e is l (e), and linkage length l (e) is initialized as δ/c (e), whereinIn formula, ε is intermediate parameters；
The first flow variables f is associated with for link ek(e) and the second flow variablesAnd by the first flow variables fk(e) and second
Flow variablesIt is initialized as 0；
S3. classified according to source node to Business Stream, the identical Business Stream of source node is divided into one kind, obtains S class industry
Business stream, S >=1, bandwidth demand Business Stream k to be allocated are initialized as dk=d (k)；
S4. for jth class Business Stream, 1≤j≤S finds its shortest path, jth for the Business Stream in jth class Business Stream
The shortest path of all Business Streams in class Business Stream constitutes shortest path tree t；
It S5. is the corresponding shortest path bandwidth allocation resource of every Business Stream in jth class Business Stream, until shortest path tree
The bandwidth demand of all Business Streams is all met in the bandwidth exhaustion or jth class Business Stream of a link on t；
The bandwidth f that record traffic stream k is assigned tok, the portfolio f (e) that passes through of shortest path tree t uplink e；Then, more
The associated first flow variables f of new link ek(e)；The bandwidth d' distributed needed for more new service flow k is remainingk, update the link of link e
Length l (e) removes the Business Stream that bandwidth demand is met from jth class Business Stream；
S6. judge whether iterated conditional D (l) < 1 meets:
If D (l) < 1 and when current class Business Stream still has bandwidth demand, jump procedure S4；
If D (l) < 1 and when current class Business Stream does not have bandwidth demand, the bandwidth allocation of lower a kind of Business Stream is carried out, is jumped
Go to step S4；
If when D (l) >=1, jump procedure S7；
S7. when S class Business Stream completes bandwidth allocation, if D (l) < 1, records intermediate result, evenJump procedure S3；If D (l) >=1, jump procedure S8；
S8. judge whether the bandwidth demand of all class Business Streams in last wheel iteration is met completely:
When the bandwidth demand of all class Business Streams does not obtain meeting completely, enable
G is the minimum value of the ratio between flow that the link capacity acquired to all links and chain pass through on the road, willAmplificationTimes, it is amplifiedExported as final bandwidth allocation scheme；
When the bandwidth demand of all class Business Streams obtains meeting completely, enableG is pair
The minimum value of the ratio between the flow that link capacity and the chain road that all links acquire pass through, by fk(e) amplify
Times, amplified fk(e) it is exported as final bandwidth allocation scheme.
In step S4, its shortest path is found using dijkstra's algorithm for the Business Stream in jth class Business Stream.
The mode of the linkage length of each link is updated in step S5 are as follows:
Wherein, l'(e) it is the updated linkage length of link e, l (e) is the linkage length before link e updates,p kFor business
The shortest path of k is flowed, c (e) is the link capacity of link e, fkThe bandwidth being assigned to for Business Stream k.
The mode of the remaining required bandwidth distributed of every Business Stream is updated in step S5 are as follows:
d'k=dk-fk
Wherein, d'kFor the updated bandwidth to be allocated of Business Stream k, dkBandwidth to be allocated before being updated for Business Stream k,
fkThe bandwidth being assigned to for Business Stream k.
The beneficial effects of the present invention are: although the present invention is based on approximate algorithm FPTAS, (subsequent descriptions indicate close with FPTAS
Like algorithm), but obtained approximate solution closely utilizes the obtained optimal solution of linear programming.Meanwhile it is proposed by the present invention close
Like algorithm pairing approximation rate parameter and insensitive, compared with FPTAS, even if using larger approximation parameters w, (subsequent descriptions are indicated with w
Approximation parameters) target function value that acquires and the target function value acquired using lesser w it is very close.Due to set forth herein
Algorithm and FPTAS on computation complexity, approximatively with w-2It is directly proportional, therefore, biggish w is selected to mention with can dramatically
The computational efficiency of algorithm is risen, and this is significantly to the traffic engineering of large scale network.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the traffic engineering method applied to software defined network of the present invention；
Fig. 2 is NSFNET network topology schematic diagram；
Fig. 3 is CERNET network topology schematic diagram；
Fig. 4 is the network topology schematic diagram using the data center of fat tree exchange network；
Fig. 5 is the schematic diagram of one embodiment of the random core net topology for assessment；
Fig. 6 is RMLU value variation diagram of the FPTAS and i-FPTAS under different approximation parameters；
Fig. 7 is the runing time figure of the i-FPTAS of linear programming and different approximation parameters；
Fig. 8 is RMLU value variation diagram of the FPTAS and i-FPTAS under different business matrix in NSFNET network topology；
Fig. 9 is RMLU value variation diagram of the FPTAS and i-FPTAS under different business matrix in CERNET network topology；
Figure 10 be using it is fat tree exchange network data center network topology in FPTAS and i-FPTAS in different business
RMLU value variation diagram under matrix；
Figure 11 is RMLU value of the FPTAS and i-FPTAS under different business matrix in random core net topology network topology
Variation diagram.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawing, but protection scope of the present invention is not limited to
It is as described below.
As shown in Figure 1, a kind of traffic engineering method applied to software defined network, comprising the following steps:
S1. network topological information is obtained, network topological information includes: network topologyWhereinRepresent node
Set, number of nodes n,Link set is represented, link sum is m；The link capacity of link eBusiness Stream
SetWherein the bandwidth demand of Business Stream k is d (k)；Approximation parameters w.
S2. the linkage length for defining link e is l (e), and linkage length l (e) is initialized as δ/c (e), whereinIn formula, ε is intermediate parameters；
The first flow variables f is associated with for link ek(e) and the second flow variablesAnd by the first flow variables fk(e) and second
Flow variablesIt is initialized as 0.First flow variables fk(e) and the second flow variablesIndicate that Business Stream leads on link e
The flow crossed, relative to the first flow variables fk(e) for, the second flow variablesIt is intermediate result.
S3. classified according to source node to Business Stream, the identical Business Stream of source node is divided into one kind, obtains S class industry
Business stream, S >=1, bandwidth demand Business Stream k to be allocated are initialized as dk=d (k).
S4. for jth class Business Stream, 1≤j≤S finds its shortest path, jth for the Business Stream in jth class Business Stream
The shortest path of all Business Streams in class Business Stream constitutes shortest path tree t.
In step S4, its shortest path is found using dijkstra's algorithm for the Business Stream in jth class Business Stream.
It S5. is the corresponding shortest path bandwidth allocation resource of every Business Stream in jth class Business Stream, until shortest path tree
The bandwidth demand of all Business Streams is all met in the bandwidth exhaustion or jth class Business Stream of a link on t；
The bandwidth f that record traffic stream k is assigned tok, the portfolio f (e) that passes through of shortest path tree t uplink e；Then, more
The associated first flow variables f of new link ek(e)；The bandwidth d' distributed needed for more new service flow k is remainingk, update the link of link e
Length l (e) removes the Business Stream that bandwidth demand is met from jth class Business Stream.
The mode of the linkage length of each link is updated in step S5 are as follows:
Wherein, l'(e) it is the updated linkage length of link e, l (e) is the linkage length before link e updates, pkFor industry
The shortest path of business stream k, c (e) are the link capacity of link e, fkThe bandwidth being assigned to for Business Stream k.
The mode of the remaining required bandwidth distributed of every Business Stream is updated in step S5 are as follows:
d'k=dk-fk
Wherein, d'kFor the updated bandwidth to be allocated of Business Stream k, dkBandwidth to be allocated before being updated for Business Stream k,
fkThe bandwidth being assigned to for Business Stream k.
S6. judge whether iterated conditional D (l) < 1 meets:
If D (l) < 1 and when current class Business Stream still has bandwidth demand, jump procedure S4；
If D (l) < 1 and when current class Business Stream does not have bandwidth demand, the bandwidth allocation of lower a kind of Business Stream is carried out, is jumped
Go to step S4；
If when D (l) >=1, jump procedure S7.
S7. when S class Business Stream completes bandwidth allocation, if D (l) < 1, records intermediate result, evenJump procedure S3；If D (l) >=1, jump procedure S8.
S8. judge whether the bandwidth demand of all class Business Streams in last wheel iteration (step S3~S7) is expired completely
Foot:
When the bandwidth demand of all class Business Streams does not obtain meeting completely, enable
G is the minimum value of the ratio between flow that the link capacity acquired to all links and chain pass through on the road, willAmplificationTimes, it is amplifiedExported as final bandwidth allocation scheme；
When the bandwidth demand of all class Business Streams obtains meeting completely, enableG is pair
The minimum value of the ratio between the flow that link capacity and the chain road that all links acquire pass through, by fk(e) amplify
Times, amplified fk(e) it is exported as final bandwidth allocation scheme.
Embodiment one:
The present embodiment includes NSFNET and CERNET using famous backbone net topology, data center network and average degree number
For 3 random core net topology.As shown in Fig. 2, NSFNET has 13 nodes and 21 undirected links, as shown in figure 3,
CERNET has 36 nodes and 54 wireless links.The present embodiment uses topology of the fat tree as data center network,
As shown in Fig. 4.Fig. 5 is for assessing an example in random core net topology.
Traffic matrix generates at random, and the parameter of random traffic is listed in table I.The each of the links capacity of network is pre-configured with.
We run linear programming first to determine each of the links at least need how many capacity, so that all test business can be connect
It receives.The process is similar to the content of network planning phase.Then, the capabilities double of each of the links, so that network be made to allow business
Fluctuation and offer redundant link resource are to prevent link failure.
Table I random traffic parameter
It is assessed in random core network topology first in interstitial content between 20~120 proposed by the present invention improved
Complete multinomial time approximate algorithm i-FPTAS (improved Fully Polynomial Time Approximation
Scheme, subsequent descriptions indicate improved complete multinomial time approximate algorithm with i-FPTAS) approximate performance.Each calculating
It include a random network topology and 10 traffic matrixs in example.In order to show i-FPTAS with respect to FPTAS in approximate performance
On promotion, define relative maximum link utilization (relative maximum link utilization, RMLU, it is subsequent
Description indicates maximum link utilization with RMLU) be
RMLU=θapprox/θopt
In formula, θapproxThe objective function of approximate solution, θoptThe target function value of optimal solution.
θoptIt can be obtained by solving linear programming, but linear programming will lead to high computing cost in large scale network.
Obvious RMLU is always greater than 1, and closer to 1, then it represents that approximate performance is better.
Fig. 6 compare FPTAS and i-FPTAS under different approximation parameters (w=1,5,10) RMLU value；Band square in Fig. 6
The dotted line of shape indicates RMLU value of the FPTAS when approximation parameters are 1, and the dotted line with triangle indicates that FPTAS is in approximation parameters
RMLU value when 5 indicates RMLU value of the FPTAS when approximation parameters are 10 with circular dotted line；I- is indicated with star-shaped solid line
RMLU value of the FPTAS when approximation parameters are 1, the solid line with triangle indicate RMLU of the i-FPTAS when approximation parameters are 1
Value indicates RMLU value of the i-FPTAS when approximation parameters are 1 with circular solid line.It can be found that the objective function of i-FPTAS
Value is very close with 1.In contrast, the functional value of FPTAS then has a distance with optimal value, and table II also illustrates equally
The problem of.Therefore, it is proposed that i-FPTAS can promote approximate performance significantly, especially when w is larger.In addition, different
The RMLU value difference that the FPTAS of approximation parameters configuration is obtained is huge, and i-FPTAS is then unobvious.Therefore i-FPTAS pairing approximation
Rate is insensitive, and this illustrates that we can obtain the solution of near-optimization (in the algorithm using larger with lower computation complexity
W).
The RMLU value of Table II FPTAS and i-FPTAS compare
Then the computational efficiency of i-FPTAS is verified.Table III list FPTAS and i-FPTAS number of network node from 20 to
Runing time in the case where 200.The result shows that the computation complexity of i-FPTAS and FPTAS is very close, because running
There was only nuance on time.Fig. 7 is by the Operational Timelines of the i-FPTAS of different approximate rates and optimal linear programming (LP)
It is shown as the function of network size, indicates the runing time of linear programming, the dotted line table with triangle in Fig. 7 with circular dotted line
Show RMLU value of the i-FPTAS when approximation parameters are 1, solid line with rectangle indicates i-FPTAS when approximation parameters are 5
RMLU value, the solid line with triangle indicate RMLU value of the i-FPTAS when approximation parameters are 10.Just as expected, lesser
The i-FPTAS of approximate rate (closer to optimal solution) leads to longer runing time.For the network of small-scale, for example, it is few
It can may also be greater than LP in the runing time of 40 nodes, i-FPTAS.However, the runing time of LP with network size increase and
Increase to be exceedingly fast, and has soon been more than the runing time of i-FPTAS.Such as 120 node network, the runing time of LP
Beyond i-FPTAS an order of magnitude.In fact, LP solve extensive even medium scale TE problem be it is infeasible,
It is the polynomial function of flow variables quantity that, which is because of its computation complexity, and the complexity of i-FPTAS is the multinomial of parameter
Formula.
The runing time (second) of Table III FPTAS and i-FPTAS compare
In order to further illustrate the approximate performance of i-FPTAS, we demonstrate under the configuration of w=5 i-FPTAS with
The robustness of FPTAS.We are in famous backbone network NSFNET, CERNET, data center network (size=4) and with 50
30 groups of different traffic matrixs are tested in the random network of node respectively.Fig. 8 to Figure 11 is shown under four network topologies,
The RMLU of i-FPTAS is always significantly lower than FPTAS, indicates RMLU of the FPTAS when approximation parameters are 5 with circular line in figure
Value indicates RMLU value of the i-FPTAS when approximation parameters are 5 with star-shaped line.Particularly, it has been found that FPTAS is not of the same trade or business
The RMLU obtained under business matrix has significant oscillation, and i-FPTAS then maintains stable RMLU to export.
It can be seen from the above result that obtain very close optimal solution, a relatively large approximate rate carrys out i-FPTAS
Say it is enough, and do not have to as FPTAS, it is necessary to use high computation complexity exchange approximate optimal solution for.
The above is only a preferred embodiment of the present invention, it should be understood that the present invention is not limited to described herein
Form should not be regarded as an exclusion of other examples, and can be used for other combinations, modifications, and environments, and can be at this
In the text contemplated scope, modifications can be made through the above teachings or related fields of technology or knowledge.And those skilled in the art institute into
Capable modifications and changes do not depart from the spirit and scope of the present invention, then all should be in the protection scope of appended claims of the present invention
It is interior.
Claims (4)
1. a kind of traffic engineering method applied to software defined network, it is characterised in that: the following steps are included:
S1. network topological information is obtained, network topological information includes: network topologyWhereinNode set is represented,
Number of nodes is n,Link set is represented, link sum is m；The link capacity of link eBusiness Stream setWherein the bandwidth demand of Business Stream k is d (k)；Approximation parameters w；
S2. the linkage length for defining link e is l (e), and linkage length l (e) is initialized as δ/c (e), whereinε≤1-(1+w)-1/3, in formula, ε is intermediate parameters；
The first flow variables f is associated with for link ek(e) and the second flow variablesAnd by the first flow variables fk(e) and the second rheology
AmountIt is initialized as 0；
S3. classified according to source node to Business Stream, the identical Business Stream of source node be divided into one kind, obtains S class Business Stream,
S >=1, bandwidth demand Business Stream k to be allocated are initialized as dk=d (k)；
S4. for jth class Business Stream, 1≤j≤S finds its shortest path, jth class industry for the Business Stream in jth class Business Stream
The shortest path of all Business Streams in business stream constitutes shortest path tree t；
It S5. is the corresponding shortest path bandwidth allocation resource of every Business Stream in jth class Business Stream, until on shortest path tree t
The bandwidth exhaustion of a link or the bandwidth demand of all Business Streams in jth class Business Stream all met；
The bandwidth f that record traffic stream k is assigned tok, the portfolio f (e) that passes through of shortest path tree t uplink e；Then, link is updated
The associated first flow variables f of ek(e)；The bandwidth d' distributed needed for more new service flow k is remainingk, update the linkage length l of link e
(e), the Business Stream that bandwidth demand is met is removed from jth class Business Stream；
S6. judge whether iterated conditional D (l) < 1 meets:
If D (l) < 1 and when current class Business Stream still has bandwidth demand, jump procedure S4；
If D (l) < 1 and when current class Business Stream does not have bandwidth demand, the bandwidth allocation of lower a kind of Business Stream is carried out, step is jumped
Rapid S4；
If when D (l) >=1, jump procedure S7；
S7. when S class Business Stream completes bandwidth allocation, if D (l) < 1, records intermediate result, evenJump procedure S3；If D (l) >=1, jump procedure S8；
S8. judge whether the bandwidth demand of all class Business Streams in last wheel iteration is met completely:
When the bandwidth demand of all class Business Streams does not obtain meeting completely, enableG is pair
The minimum value of the ratio between the flow that link capacity and the chain road that all links acquire pass through, willAmplification
Times, it is amplifiedExported as final bandwidth allocation scheme；
When the bandwidth demand of all class Business Streams obtains meeting completely, enableG is to all
The minimum value of the ratio between the flow that link capacity and the chain road that link acquires pass through, by fk(e) amplifyTimes, it puts
F after bigk(e) it is exported as final bandwidth allocation scheme.
2. a kind of traffic engineering method applied to software defined network according to claim 1, it is characterised in that: step
In S4, its shortest path is found using dijkstra's algorithm for the Business Stream in jth class Business Stream.
3. a kind of traffic engineering method applied to software defined network according to claim 1, it is characterised in that: step
The mode of the linkage length of each link is updated in S5 are as follows:
Wherein, l'(e) it is the updated linkage length of link e, l (e) is the linkage length before link e updates,p kFor Business Stream k
Shortest path, c (e) be link e link capacity, fkThe bandwidth being assigned to for Business Stream k.
4. a kind of traffic engineering method applied to software defined network according to claim 1, it is characterised in that: step
The mode of the remaining required bandwidth distributed of every Business Stream is updated in S5 are as follows:
d'k=dk-fk
Wherein, d'kFor the updated bandwidth to be allocated of Business Stream k, dkBandwidth to be allocated before being updated for Business Stream k, fkFor
The bandwidth that Business Stream k is assigned to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510867549.5A CN105357080B (en) | 2015-12-01 | 2015-12-01 | A kind of traffic engineering method applied to software defined network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510867549.5A CN105357080B (en) | 2015-12-01 | 2015-12-01 | A kind of traffic engineering method applied to software defined network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105357080A CN105357080A (en) | 2016-02-24 |
| CN105357080B true CN105357080B (en) | 2019-01-04 |
Family
ID=55332956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510867549.5A Expired - Fee Related CN105357080B (en) | 2015-12-01 | 2015-12-01 | A kind of traffic engineering method applied to software defined network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105357080B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115277429B (en) * | 2022-09-30 | 2023-03-03 | 北京中电飞华通信有限公司 | Power communication service resource allocation method and device based on flexible Ethernet |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104363170A (en) * | 2014-11-25 | 2015-02-18 | 杭州华三通信技术有限公司 | Data flow forwarding method and device in software defined network (SDN) |
| WO2015081817A1 (en) * | 2013-12-05 | 2015-06-11 | Huawei Technologies Co., Ltd. | Framework for traffic engineering in software defined networking |
| WO2015116580A1 (en) * | 2013-12-26 | 2015-08-06 | Huawei Technologies Co., Ltd. | Inter-domain sdn traffic engineering |
| CN104885431A (en) * | 2012-12-13 | 2015-09-02 | 华为技术有限公司 | Content based traffic engineering in software defined information centric networks |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9485689B2 (en) * | 2014-01-06 | 2016-11-01 | Huawei Technologies Co., Ltd. | Adaptive traffic engineering configuration |
| US9397917B2 (en) * | 2014-01-10 | 2016-07-19 | Huawei Technologies Co., Ltd. | System and method for zoning in software defined networks |
-
2015
- 2015-12-01 CN CN201510867549.5A patent/CN105357080B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104885431A (en) * | 2012-12-13 | 2015-09-02 | 华为技术有限公司 | Content based traffic engineering in software defined information centric networks |
| WO2015081817A1 (en) * | 2013-12-05 | 2015-06-11 | Huawei Technologies Co., Ltd. | Framework for traffic engineering in software defined networking |
| WO2015116580A1 (en) * | 2013-12-26 | 2015-08-06 | Huawei Technologies Co., Ltd. | Inter-domain sdn traffic engineering |
| CN104363170A (en) * | 2014-11-25 | 2015-02-18 | 杭州华三通信技术有限公司 | Data flow forwarding method and device in software defined network (SDN) |
Non-Patent Citations (3)
| Title |
|---|
| FlexRay网络中带宽利用率的理论研究;王刚等;《计算机应用》;20111031;第31卷(第10期);第2634-2637页 |
| Towards an Elastic Distributed SDN Controller;Advait Dixit等;《Proceedings of the second ACM SIGCOMM workshop on Hot topics in software defined networking》;20130816;第7-12页 |
| 基于软件定义网络的流量工程;周桐庆等;《软件学报》;20151106;第27卷(第2期);第392-417页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105357080A (en) | 2016-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106470168B (en) | data transmission method, switch using the method and network control system | |
| CN106549779A (en) | A kind of maximum non-intersect double route collocation method of multiple constraint energy communication service | |
| CN100417138C (en) | Load sharing method | |
| CN103348638A (en) | Communication system, control device, communication node, and communication method | |
| JP2019122040A (en) | Network source reuse and routing mechanism defining multi-source by software | |
| CN112104558B (en) | Method, system, terminal and medium for implementing block chain distribution network | |
| JP5943431B2 (en) | Network, data transfer node, communication method and program | |
| US20160065449A1 (en) | Bandwidth-Weighted Equal Cost Multi-Path Routing | |
| CN103348639A (en) | Path selection method and control server | |
| Sun et al. | Correlated scale-free network with community: modeling and transportation dynamics | |
| CN107637030A (en) | Method and apparatus for self-adjusting adaptability route | |
| CN105450741A (en) | Supply server selection and restoration data transmission method in distributed storage system | |
| CN105262534B (en) | A kind of method for routing and device suitable for satellite communication network | |
| Li et al. | Pasr: An efficient flow forwarding scheme based on segment routing in software-defined networking | |
| Quy et al. | A multi-metric routing protocol to improve the achievable performance of mobile ad hoc networks | |
| CN105357080B (en) | A kind of traffic engineering method applied to software defined network | |
| CN106789642A (en) | A kind of dynamic load balancing method based on SDN | |
| Sekar et al. | Third generation memetic optimization technique for energy efficient routing stability and load balancing in MANET | |
| CN104093182A (en) | Method for acquiring a plurality of reliable communication paths based on field intensity in multi-layer wireless network | |
| CN109922161A (en) | Content distribution method, system, equipment and the medium of dynamic cloud content distributing network | |
| CN107733796A (en) | A kind of preferentially path calculation method and system | |
| JP6293487B2 (en) | Network design method and system | |
| Shirmarz et al. | A novel flow routing algorithm based on non-dominated ranking and crowd distance sorting to improve the performance in SDN | |
| Thirumurugan et al. | Ex-PAC: An improved clustering technique for ad hoc network | |
| Kai et al. | Upper bound of network capacity and a static optimal packet routing strategy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190104 Termination date: 20191201 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |