CN106341346A - Routing algorithm of guaranteeing QoS in data center network based on SDN - Google Patents
Routing algorithm of guaranteeing QoS in data center network based on SDN Download PDFInfo
- Publication number
- CN106341346A CN106341346A CN201610810708.2A CN201610810708A CN106341346A CN 106341346 A CN106341346 A CN 106341346A CN 201610810708 A CN201610810708 A CN 201610810708A CN 106341346 A CN106341346 A CN 106341346A
- Authority
- CN
- China
- Prior art keywords
- bandwidth
- priority
- delay
- allocated
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/6215—Individual queue per QOS, rate or priority
-
- 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
- H04L45/12—Shortest path evaluation
- H04L45/121—Shortest path evaluation by minimising delays
-
- 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
- H04L45/12—Shortest path evaluation
- H04L45/125—Shortest path evaluation based on throughput or bandwidth
-
- 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
- H04L45/302—Route determination based on requested QoS
Abstract
The invention discloses a routing algorithm of guaranteeing QoS (quality of service) in a data center network based on SDN. Aiming at problems that user terminal transmission time delay is high and a link congestion is generated in the data center network, the routing algorithm of guaranteeing QoS in the data center network is provided. In the algorithm, priority classification is performed on a data flow arriving at a switch so that a high priority data flow which is sensitive to the time delay adopts a time delay guarantee algorithm; a path with minimum data plane time delay is found to carry out flow table issuing; for a low priority data flow which has a high requirement to a bandwidth, a bandwidth guarantee algorithm is adopted; and according to a demand of the data flow for the bandwidth, dynamic bandwidth adjusting is performed. The QoS of a user is effectively guaranteed and a resource utilization rate in the data center network is increased.
Description
Technical field
The present invention relates to technical field of communication network, it is related to based on the route in the data center network of sdn being guarantee qos
Algorithm.
Background technology
With all kinds of business, the demand of the Internet is increased increasingly, the Internet is to guarantee user qos (quality of
Service, service quality) ability there is obvious defect.In traditional data center network due to complicated integral structure and
Equipment performance saturation, has been difficult to meet the currently different requirements to qos for the new business, and the network traffics ratio under emerging service
Conventional data centers network traffics are increasingly complex, and inside data center, the frequent communication between multiple spot may make network send out simultaneously
Raw congestion, the network bandwidth is not fully utilized, and the time delay between terminal use is elongated the problems such as wait, and leads under overall performance
Fall.Therefore how to ensure that the qos demand of different data streams has become as data center network using current Internet resources
One key difficult problem.
For improving the efficiency of data exchange, realize the calculating to data center network resource, storage and flexible allotment, simultaneously
Strengthen data center network controllability, by openflow technology combine sdn (software defined networking, soft
Part defines network) it is applied in data center network, because it has the ability of global view, can be from overall angle spirit
That lives makes resource allocation, also can realize network traffics equilibrium by the rational deployment of the Optimized Operation of stream and server, then
Sdn can lift the utilization rate of Internet resources while ensureing user qos.
In recent years, ensure that the Research of Routing Algorithm of qos just receives more and more attention in sdn data center network.
Existing document is retrieved and finds, pertinent literature is as follows:
Document [ishimori a, farias f, cerqueira e, et al.control of multiple packet
schedulers for improving qos on openflow/sdn networking[c]//proc of the 2nd
european workshop on software defined networks.berlin:ieee press,2013:81-86.]
Qos scheduling strategy based on queue on middle proposition sdn framework, but the data flow not being directed to different priorities carries out qos
Route；Document [bueno i, aznar j i, escalona e, et al.an opennaas based sdn framework
for dynamic qos control[c]//proc of ieee sdn for future networks and
Services. the qos strategy proposing on sdn framework in [s.l.]: ieee press, 2013:1-7.] automatically configures framework,
But this framework only to the delay requirement of different data streams and adjust automatically forward-path, have ignored the need to bandwidth for the data flow
Ask；Tomovic s et al. is in document [sdn control framework for qos provisioning [c] //proc of
The 22nd telecommunications forum [s.l.]: ieee press, 2014:111-114.] the middle algorithm proposing
Convection current lacks fine dividing it is impossible to realize the fine granularity guarantee of data flow；And document [egilmez h e, dane s t,
gorkemli b,et al.openqos:an openflow controller design for multimedia
delivery with end-to-end quality of service over software-defined networks
[c]//proc of asia-pacific signal&information processing association annual
Summit and conference. [s.l.]: ieee press, 2012:22-27.] in for specific stream devise guarantee qos
Routing algorithm and other ensure gff (coupling preferential) algorithm of qos strategy, but the extensibility of this algorithm is too poor.Song Jianwei
Document [the qos Queue Algorithm based on differentiated services network studies [d]. Chengdu: University of Electronic Science and Technology, 2014.] inner proposition base
Algorithm in queue to ensure qos, but is simply verified on theoretical model, does not test its property in real network
Energy.
From correlational study, in order to solve terminal use's time delay height and network in the data center network under sdn framework
The problem that bandwidth cannot make full use of, the data flow entering switch is carried out priority classification by the present invention, is directed to different excellent
The data flow of first level adopts different routing algorithms, improves the utilization of Internet resources while ensureing the qos of user terminal
Rate.
Content of the invention
Present invention seek to address that above problem of the prior art.Propose a kind of based in the data center network of sdn one
Plant the routing algorithm ensureing qos.Technical scheme is as follows:
Based on the routing algorithm of guarantee qos a kind of in the data center network of sdn, it comprises the following steps:
101st, each openflow switch receiving data stream, and flow table coupling is carried out to the data flow receiving, if energy
Match with the flow table in openflow switch, then trigger forwarding behavior；If can not mate, enter step 102；
102nd, the data flow that height according to priority can not be matched with flow table to step 101 is classified, if belonging to
In the high-priority traffic to delay sensitive, jump to step 103, if it is for controlled load, streamed multimedia etc.
Step 104 is then jumped to the low-priority data stream of bandwidth sensitive；
103rd, it is directed to the high-priority traffic of delay sensitive, enable delay guarantee algorithm, when selecting on the whole
Prolong minimal path, the flow table being about to generate of going forward side by side is written in switch；
104th, it is directed to the high low-priority data stream of bandwidth requirement, enable bandwidth safeguard algorithm, Mobile state is entered to bandwidth
Adjustment, thus meeting the required amount of bandwidth of low-priority data stream, and then prevents network congestion.
Further, the high-priority traffic of described delay sensitive is low-volume traffic stream, higher low preferential of bandwidth demand
Level DBMS stream is high amount of traffic.
Further, whether step 101 enters the vlan priority that switch then judges this data flow if there are data flow
Less than 5, i.e. the value of the vlan priority of vlan < 5, wherein data flow is 0～7, and priority 7 is the relevant information of network management
Including routing information rip agreement and open shortest path ospf agreement；Priority 6 and 5 is mainly delay-sensitive；Priority
4 to 1 is mainly used in controlled load, streamed multimedia, key service traffics, and priority 0 is default value, is being not provided with other
Automatically enable in the case of priority value, setting vlan priority herein and being less than 5 is low-priority data stream, otherwise preferential for height
DBMS stream.
Further, when switch receive when being high-priority traffic, using delay guarantee algorithm, sdn controller
Select and meet the latency path of high priority and carry out flow table issuance, specifically include: to constructing network topology cost function, set up
Meet the mathematical model of delay constraint and Least-cost, the link cost function of structure is:
cij=(1- β) gij+βpij, 0 < β < 1, in formula, gijRepresent node i, the delay variation between j, pijRepresent node i,
Packet loss between j, β represents proportionality coefficient；
Meet delay constraint and the mathematical model of Least-cost is expressed as: r*=argrmin{fc(r)|r∈rst,fd(r)≤
dmax, in formula, rstRepresent all of route set between node s and t, r ∈ rstIn one route, fcR () represents that path r's is total
Cost, dijRepresent the chain-circuit time delay between node i and j, fdR () represents the overall delay of path r, dmaxRepresent the maximum of data flow
Time delay.
Further, the solution procedure of the described mathematical model meeting delay constraint and Least-cost is: c firstijAs
Link metric, by the path of d Algorithm for Solving Least-cost；Judge whether the time delay in path meets demand, meet and then issue phase
Answer flow table, otherwise, with dijAs the weights of link, solve the minimum path of time delay, judge whether the path delay of time meets demand, such as
Fruit satisfaction then issues corresponding flow table, and otherwise controller will be recalculated.
Further, in step 104 when switch receive when being low-priority data stream, sdn controller enters to bandwidth
Mobile state adjusts, and selects and meets the optimum bandwidth path of data flow requirements and carry out flow table issuance, specifically includes step: to all kinds of
Being expressed as of parameter: (1) bandwidth availability ratio qu, represent the ratio with total bandwidth using bandwidth, its expression formula is qu=ballocated/
btotal, b in formulaallocatedRepresent and use bandwidth, btotalRepresent link total bandwidth；(2) total bandwidth is represented by remaining bandwidth
bresidualWith using bandwidth ballocatedSum: btotal=bresidual+ballocated；(3) initial bandwidth: binit=btotal/φi,
Wherein φiRepresent weighted value；Additionally, the overload of link bandwidth is represented by: brequest>binit；Wherein brequestRepresent data flow
Demand bandwidth；First consider that data flow distribution uses bandwidth b accordinglyallocatedIf, in brequest≤binitUnder the conditions of, then count
The band that should distribute according to stream is a width of: ballocated=brequest；Otherwise bandwidth is set to ballocated=binit；Secondly, heavy duty road
The bandwidth demand in footpath is black=brequest-ballocated-binit；To the remaining bandwidth b in linkresidual=binit+
ballocated-brequestThe method of salary distribution be: first as the remaining bandwidth b in systemresidualMore than blackWhen, then ballocated=
brequest；Secondly work as the remaining bandwidth b in systemresidualLess than blackWhen be allocated by a certain percentage, in being so thatB in formulaaddAttach most importance to newly assigned bandwidth, bi lackBandwidth for demand on i-th link；And
ballocated=ballocated+badd, when receiving new data stream, satisfactory path is calculated according to current demand, simultaneously
Controller detects to Link State, if meeting current qos demand, path bandwidth distribution is not done and changed, and link requirement is not
When can meet qos demand, redistributed by bandwidth safeguard algorithm, to ensure low-priority data stream bandwidth, at next
When data flow arrives, to ensure that previous data flow is all sent.
Advantages of the present invention and having the beneficial effect that:
The present invention provides the routing algorithm ensureing qos in a kind of data center network in sdn, and this algorithm is incited somebody to action: enters
Data flow in openflow switch is according to priority classified；Secondly the high-priority traffic to delay sensitive, adopts
Delay guarantee algorithm is selecting the minimum route of time delay；And the low-priority data stream to bandwidth sensitive, using dynamically distributes band
Wide mode ensures the bandwidth demand of low-priority data stream；Thus reducing the propagation delay time of data flow and improving network money
The utilization rate in source.
Brief description
Fig. 1 is that the present invention provides the network topological diagram that preferred embodiment generates；
Fig. 2 is global design flow chart of the present invention；
Fig. 3 is the time delay simulation result figure that delay guarantee algorithm of the present invention contrasts matching precedence algorithm
Fig. 4 is bandwidth safeguard algorithm effect analogous diagram of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, detailed
Carefully describe.Described embodiment is only a part of embodiment of the present invention.
Technical scheme is as follows:
In the present embodiment, the network topological diagram that Fig. 1 generates for the present invention；4 switch are had inside each pod.?
The port switch of edge is connected with main frame, and the switch of remaining 2 port last layer connects.There are 4 switch in core layer,
Single port is had to be connected with a pod in the every switch of core layer, one 4 yuan of fat-tree topology supports 16 main frames and 20
Individual switch (4 switches of core layer, 8 switches of convergence-level and Access Layer 8 switch) composition.The initial strip of each of the links
Width is set to 11.3gbps, and setting peak transfer rate is 2000, tcp acquiescence sliding window size is 85.3kbyte, every chain
The time delay of road setting is set to 10ms.
In the present embodiment, Fig. 2 is global design flow chart of the present invention；The data flow of high priority is quicker to time delay
Sense, therefore this algorithm construct cost function, set up the mathematical model meeting delay constraint and Least-cost, and using improvement
D algorithm carry out flow table issuance selecting time delay minimal path.
First, by link discovery module, switch is monitored, waits data flow to enter switch.If there are data flow
Enter switch and then judge whether the vlan priority of this data flow is less than 5, i.e. the vlan priority of vlan < 5, wherein data flow
Value be 0～7, priority 7 is relevant information such as rip (as the routing information) agreement of network management and ospf (opening
Shortest path) agreement；Priority 6 and 5 is mainly delay-sensitive；Priority 4 to 1 be mainly used in controlled load, streamed multimedia,
Key service traffics.Priority 0 is default value, automatically enables in the case of being not provided with other priority values.Set herein
Determine vlan priority to be less than 5 is low-priority data stream, otherwise is high-priority traffic.
Then, for the data flow of low priority, the need of the data flow of low priority are ensured using bandwidth safeguard algorithm
Seek bandwidth, detailed process is: (1) bandwidth availability ratio qu, represent the ratio with total bandwidth using bandwidth, its expression formula is qu=
ballocated/btotal, b in formulaallocatedRepresent and use bandwidth, btotalRepresent link total bandwidth；(2) total bandwidth is represented by
Remaining bandwidth bresidualWith using bandwidth ballocatedSum: btotal=bresidual+ballocated；(3) initial bandwidth: binit=
btotal/φi, wherein φiRepresent weighted value；Additionally, the overload of link bandwidth is represented by: brequest>binit.Consider number first
According to stream distribution respective bandwidth ballocatedIf, in brequest≤binitUnder the conditions of, then the band that data flow should be distributed is a width of:
ballocated=brequest；Otherwise bandwidth is set to ballocated=binit.Secondly, the bandwidth demand b in heavy duty pathlack=
brequest-ballocated-binit.To the remaining bandwidth b in linkresidual=binit+ballocated-brequestThe method of salary distribution be:
First as the remaining bandwidth b in systemresidualMore than blackWhen, then ballocated=brequest；Secondly work as the tape remaining in system
Wide bresidualLess than blackWhen be allocated by a certain percentage, in being so thatB in formulaaddFor again
The bandwidth of distribution.bi lackBandwidth for demand on i-th link；And ballocated=ballocated+badd.Receiving new data
During stream, satisfactory path is calculated according to current demand, controller detects to Link State simultaneously, if meet worked as
Front qos demand, path bandwidth distribution is not done and is changed, and when link requirement can not meet qos demand, is carried out by bandwidth safeguard algorithm
Redistribute, to ensure low-priority data stream bandwidth, when next data flow arrives, will ensure that previous data flow is all sent out
Send and finish.
Finally, for the data flow of high priority, to ensure the time delay of high-priority traffic using delay guarantee algorithm
Demand, detailed process is: to constructing network topology cost function, sets up the mathematical model meeting delay constraint and Least-cost.
The link cost function building and the model of structure are:
cij=(1- β) gij+βpij, 0 < β < 1, in formula, gijRepresent i, the delay variation between j, pijRepresent i, between j
Packet loss, β represents proportionality coefficient.Meet delay constraint and the mathematical model of Least-cost is expressed as: r*=argrmin{fc(r)|
r∈rst,fd(r)≤dmax, in formula, rstRepresent all of route set between node s and t, r ∈ rstIn one route, fc(r)
Represent total cost of path r, dijRepresent the chain-circuit time delay between node i and j, fdR () represents the overall delay of path r, dmaxRepresent
The maximum delay of data flow.The solution procedure of this model is: c firstijAs link metric, by d Algorithm for Solving Least-cost
Path.Judge whether the time delay in path meets demand, meet and then issue corresponding flow table, otherwise, with dijAs the weights of link,
Solving the minimum path of time delay, judge whether the path delay of time meets demand, if met, issuing corresponding flow table, otherwise controller
To be recalculated.
Fig. 3 is the time delay simulation result figure that delay guarantee algorithm of the present invention contrasts matching precedence algorithm: wherein qdba is herein
Modified hydrothermal process, gff is the alignment algorithm chosen.H1 end from Fig. 1 sends data flow to h16 end, constant loading
In the case of, time delay also can increase to certain value, next can fluctuate within the specific limits.As can be seen from Figure 3 in gff algorithm
Increase to 300ms about after time delay just level off to stable, increase over time fluctuation range also in 300ms about enter traveling wave
Dynamic.The maximum of qdba time delay is relatively small, in experiment the time delay of qdba in 150ms about fluctuation, this fluctuation is pre- with experiment
Phase coincide, and due to due to gff itself when link load increases to certain numerical value, link starts congestion phenomenon, data
Time delay increase leads to network performance to decline.Qdba can select optimal path for data flow on the whole, can be according to data flow
Bandwidth demand carry out routing, therefore can be by timing_delay estimation in less scope.In the case of identical load, according in data
Heart network characterization is that time delay is required in transmitting procedure to data stream claims, qdba algorithm presented herein, time delay one
Directly it is maintained at 150ms, substantially conform to the demand of data center network flow, demonstrate this algorithm in data center network
Effectiveness.
Fig. 4 is bandwidth safeguard algorithm effect analogous diagram of the present invention: initial bandwidth is set to 11.3gbps, by result
When the data stream bandwidth demand being currently received is 2.71mbits, if using traditional matching precedence algorithm, this algorithm is not to
Make a distinction with the data flow on path, understand that current h1 to h2 only has a queue, the bandwidth value of this queue in Fig. 4 (b)
It is less than 2.71mbits always, if this data flow, to bandwidth sensitive, can not ensure the qos of stream；In Fig. 4 (a), start band
Wide ensure algorithm after, have between h1 to h2 two queues according to the demand of data flow be respectively 2.59mbits and
0.12kbits, it can thus be appreciated that bandwidth safeguard algorithm can make a distinction to data flow end to end treat, to ensure different data streams
Bandwidth.Occurring in that after bandwidth safeguard after startup that two queues differing come as can be seen from the results in end-to-end bandwidth can
To meet the bandwidth safeguard of different demands.Because this experiment condition is limited, carry out only on bandwidth safeguard can be in chain end to end
Bandwidth safeguard test is carried out to the data flow of different bandwidth demand on road, bandwidth safeguard strategy presented herein can be implemented in one
On bar link, the demand according to data flow carries out bandwidth safeguard.
The above embodiment is interpreted as being merely to illustrate the present invention rather than limits the scope of the invention.?
After the content of the record having read the present invention, technical staff can make various changes or modifications to the present invention, these equivalent changes
Change and modify and equally fall into the scope of the claims in the present invention.
Claims (6)
1. based on the routing algorithm of guarantee qos a kind of in the data center network of sdn it is characterised in that comprising the following steps:
101st, the data flow that each openflow switch receives carries out flow table coupling, if can with openflow switch in
Flow table match, then trigger forwarding behavior；If can not mate, enter step 102；
102nd, the data flow that height according to priority can not be matched with flow table to step 101 is classified, if be belonging to right
The high-priority traffic of delay sensitive, jumps to step 103, if it is for controlled load, streamed multimedia etc. is to band
Wide sensitive low-priority data stream then jumps to step 104；
103rd, it is directed to the high-priority traffic of delay sensitive, enables delay guarantee algorithm, select time delay on the whole
Small path, the flow table being about to generate of going forward side by side is written in switch；
104th, it is directed to for controlled load, the low-priority data stream to bandwidth sensitive for the streamed multimedia etc., enable bandwidth and protect
Barrier algorithm, entering Mobile state adjustment, thus meeting the required amount of bandwidth of low-priority data stream, and then preventing network from gathering around to bandwidth
Plug.
2. according to claim 1 based on the routing algorithm of guarantee qos a kind of in the data center network of sdn, its feature
It is, the high-priority traffic of described delay sensitive is the flow of information related to network management, higher low excellent of bandwidth demand
First level DBMS stream is for controlled load, the service traffics such as streamed multimedia.
3. according to claim 1 based on the routing algorithm of guarantee qos a kind of in the data center network of sdn, its feature
Be, step 101 enters switch if there are data flow and then judges that whether the vlan priority of this data flow be less than 5, that is, vlan <
5, the wherein value of the vlan priority of data flow is 0～7, and priority 7 is that the relevant information of network management includes Route Selection
Information rip agreement and open shortest path ospf agreement；Priority 6 and 5 is mainly delay-sensitive；Priority 4 to 1 is mainly used in
Controlled load, streamed multimedia, key service traffics, priority 0 is default value, in the feelings being not provided with other priority values
Automatically enable under condition, setting vlan priority herein and being less than 5 is low-priority data stream, otherwise is high-priority traffic.
4. according to claim 1 based on the routing algorithm of guarantee qos a kind of in the data center network of sdn, its feature
Be, when switch receive when being high-priority traffic, using delay guarantee algorithm, it is high that satisfaction selected by sdn controller
The latency path of priority carries out flow table issuance, specifically includes: to constructing network topology cost function, sets up and meets delay constraint
And the mathematical model of Least-cost, the link cost function of structure is:
cij=(1- β) gij+βpij, 0 < β < 1, in formula, gijRepresent node i, the delay variation between j, pijRepresent node i, between j
Packet loss, β represents proportionality coefficient；
Meet delay constraint and the mathematical model of Least-cost is expressed as: r*=argrmin{fc(r)|r∈rst,fd(r)≤
dmax, in formula, rstRepresent all of route set between node s and t, r ∈ rstIn one route, fcR () represents that path r's is total
Cost, dijRepresent the chain-circuit time delay between node i and j, fdR () represents the overall delay of path r, dmaxRepresent the maximum of data flow
Time delay.
5. according to claim 1 based on the routing algorithm of guarantee qos a kind of in the data center network of sdn, its feature
It is, the solution procedure of the described mathematical model meeting delay constraint and Least-cost is: c firstijAs link metric, pass through
The path of d Algorithm for Solving Least-cost；Judge whether the time delay in path meets demand, meet and then issue corresponding flow table, otherwise, with
dijAs the weights of link, solving the minimum path of time delay, judge whether the path delay of time meets demand, if met, issuing phase
Answer flow table, otherwise controller will be recalculated.
6. according to claim 1 based on the routing algorithm of guarantee qos a kind of in the data center network of sdn, its feature
Be, in step 104 when switch receive when being low-priority data stream, sdn controller bandwidth is entered Mobile state adjustment, choosing
Select out and meet the optimum bandwidth path of data flow requirements and carry out flow table issuance, specifically include step: all kinds of parameters are expressed as:
(1) bandwidth availability ratio qu, represent the ratio with total bandwidth using bandwidth, its expression formula is qu=ballocated/btotal, in formula
ballocatedRepresent and use bandwidth, btotalRepresent link total bandwidth；(2) total bandwidth is represented by remaining bandwidth bresidualWith make
Use bandwidth ballocatedSum: btotal=bresidual+ballocated；(3) initial bandwidth: binit=btotal/φi, wherein φiRepresent
Weighted value；Additionally, the overload of link bandwidth is represented by: brequest>binit；Wherein brequestRepresent the demand bandwidth of data flow；
First consider that data flow distribution uses bandwidth b accordinglyallocatedIf, in brequest≤binitUnder the conditions of, then data flow should be distributed
Band a width of: ballocated=brequest；Otherwise bandwidth is set to ballocated=binit；Secondly, the bandwidth in heavy duty path needs
Ask as black=brequest-ballocated-binit；To the remaining bandwidth b in linkresidual=binit+ballocated-brequest's
The method of salary distribution is: first as the remaining bandwidth b in systemresidualMore than blackWhen, then ballocated=brequest；Secondly work as and be
Remaining bandwidth b in systemresidualLess than blackWhen be allocated by a certain percentage, in being so thatFormula
Middle baddAttach most importance to newly assigned bandwidth, bi lackBandwidth for demand on i-th link；And ballocated=ballocated+badd, connecing
When receiving new data stream, satisfactory path is calculated according to current demand, controller detects to Link State simultaneously,
If meeting current qos demand, path bandwidth distribution is not done and is changed, and when link requirement can not meet qos demand, is protected by bandwidth
Barrier algorithm is redistributed, and to ensure low-priority data stream bandwidth, when next data flow arrives, will ensure previous number
All it is sent according to stream.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610810708.2A CN106341346B (en) | 2016-09-08 | 2016-09-08 | A kind of routing algorithm ensureing QoS in data center network based on SDN |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610810708.2A CN106341346B (en) | 2016-09-08 | 2016-09-08 | A kind of routing algorithm ensureing QoS in data center network based on SDN |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106341346A true CN106341346A (en) | 2017-01-18 |
| CN106341346B CN106341346B (en) | 2019-07-19 |
Family
ID=57822518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610810708.2A Active CN106341346B (en) | 2016-09-08 | 2016-09-08 | A kind of routing algorithm ensureing QoS in data center network based on SDN |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106341346B (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106656805A (en) * | 2017-02-17 | 2017-05-10 | 华北电力大学（保定） | Multiservice QoS route selection method of power wide-area communication network |
| CN106656806A (en) * | 2017-02-17 | 2017-05-10 | 华北电力大学（保定） | Power wide-area communication network multi-service QoS routing method |
| CN106789660A (en) * | 2017-03-31 | 2017-05-31 | 中国科学技术大学苏州研究院 | The appreciable flow managing methods of QoS in software defined network |
| CN107241277A (en) * | 2017-05-17 | 2017-10-10 | 天津大学 | Node method for annealing in SDN |
| CN107360483A (en) * | 2017-08-21 | 2017-11-17 | 西安邮电大学 | A kind of controller load-balancing algorithm for software definition optical-fiber network |
| CN107454017A (en) * | 2017-06-05 | 2017-12-08 | 上海交通大学 | Mixed data flow coordinated dispatching method in a kind of cloud data center network |
| CN108064064A (en) * | 2017-12-20 | 2018-05-22 | 浙江省公众信息产业有限公司 | Wireless sensor network Ad Hoc is by method and apparatus |
| CN108401015A (en) * | 2018-02-02 | 2018-08-14 | 广州大学 | A kind of data center network method for routing based on deeply study |
| CN108512760A (en) * | 2018-03-09 | 2018-09-07 | 西安电子科技大学 | The method for routing of QoS of survice is ensured based on SDN |
| CN108540384A (en) * | 2018-04-13 | 2018-09-14 | 西安交通大学 | Intelligent heavy route method and device based on congestion aware in software defined network |
| CN108768776A (en) * | 2018-05-30 | 2018-11-06 | 郑州云海信息技术有限公司 | A kind of method for monitoring network and device based on OpenFlow |
| CN108768713A (en) * | 2018-05-09 | 2018-11-06 | 西安工业大学 | A kind of guarantee QoS dynamic routing algorithms in SDN |
| CN108933742A (en) * | 2018-06-21 | 2018-12-04 | 重庆邮电大学 | A kind of business stream scheduling method of SD-DCN link failure |
| CN108989210A (en) * | 2017-06-02 | 2018-12-11 | 中兴通讯股份有限公司 | A kind of tunnel selecting method and software defined network controller based on strategy |
| CN109547340A (en) * | 2018-12-28 | 2019-03-29 | 西安电子科技大学 | SDN data center network jamming control method based on heavy-route |
| CN109600319A (en) * | 2018-12-11 | 2019-04-09 | 浙江工商大学 | A kind of traffic scheduling method in real-time Transmission mechanism |
| CN110149282A (en) * | 2019-01-30 | 2019-08-20 | 华为技术有限公司 | Traffic scheduling method and device |
| CN111600754A (en) * | 2020-05-11 | 2020-08-28 | 重庆邮电大学 | Industrial heterogeneous network scheduling method for interconnection of TSN (transmission time network) and non-TSN (non-Transmission time network) |
| CN111817983A (en) * | 2020-06-12 | 2020-10-23 | 浪潮思科网络科技有限公司 | Irrigation equipment network regulation and control method, equipment and system based on SDN |
| CN112187657A (en) * | 2020-09-16 | 2021-01-05 | 北京理工大学 | Extensible routing method for realizing load balancing in software defined wide area network |
| WO2021047401A1 (en) * | 2019-09-10 | 2021-03-18 | 华为技术有限公司 | Service classification method and apparatus, and internet system |
| CN109905364B (en) * | 2019-01-08 | 2021-04-20 | 山东省计算中心（国家超级计算济南中心） | Streaming media data packet transmission method and system based on SDN architecture |
| CN113242182A (en) * | 2021-05-08 | 2021-08-10 | 东南大学 | QoS-sensitive route distribution method in mobile self-organizing network based on SDN |
| WO2021258408A1 (en) * | 2020-06-22 | 2021-12-30 | 北京交通大学 | Tolerance analysis method and apparatus for multi-service flow converged communication in industrial heterogeneous network |
| CN113938955A (en) * | 2021-09-09 | 2022-01-14 | 中国联合网络通信集团有限公司 | Data transmission method, device, equipment and system |
| CN114513241A (en) * | 2021-04-19 | 2022-05-17 | 南京航空航天大学 | SDN-based high-performance QoS guaranteed low-orbit satellite inter-satellite routing method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104994033A (en) * | 2015-05-13 | 2015-10-21 | 南京航空航天大学 | Method for guaranteeing QoS (quality of service) of SDN (software defined network) by means of dynamic resource management |
| CN105357068A (en) * | 2015-11-03 | 2016-02-24 | 华中科技大学 | OpenFlow network flow control method for QoS assurance of application |
| CN105847151A (en) * | 2016-05-25 | 2016-08-10 | 安徽大学 | Multi-constrained QoS (Quality of Service) routing strategy designing method for software defined network |
-
2016
- 2016-09-08 CN CN201610810708.2A patent/CN106341346B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104994033A (en) * | 2015-05-13 | 2015-10-21 | 南京航空航天大学 | Method for guaranteeing QoS (quality of service) of SDN (software defined network) by means of dynamic resource management |
| CN105357068A (en) * | 2015-11-03 | 2016-02-24 | 华中科技大学 | OpenFlow network flow control method for QoS assurance of application |
| CN105847151A (en) * | 2016-05-25 | 2016-08-10 | 安徽大学 | Multi-constrained QoS (Quality of Service) routing strategy designing method for software defined network |
Non-Patent Citations (2)
| Title |
|---|
| HILMI E. EGILMEZ 等: "OpenQoS: An OpenFlow Controller Design for Multimedia Delivery with End-to-End Quality of Service over Software-Defined Networks", 《PROCEEDINGS OF THE 2012 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE》 * |
| 曹绍华，张鑫: "面向业务的SDN网络带宽保障研究", 《计算机工程与应用》 * |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106656806A (en) * | 2017-02-17 | 2017-05-10 | 华北电力大学（保定） | Power wide-area communication network multi-service QoS routing method |
| CN106656805A (en) * | 2017-02-17 | 2017-05-10 | 华北电力大学（保定） | Multiservice QoS route selection method of power wide-area communication network |
| CN106656805B (en) * | 2017-02-17 | 2019-08-23 | 华北电力大学（保定） | A kind of electric power WAN communication network multi-service QoS route selection method |
| CN106789660A (en) * | 2017-03-31 | 2017-05-31 | 中国科学技术大学苏州研究院 | The appreciable flow managing methods of QoS in software defined network |
| CN106789660B (en) * | 2017-03-31 | 2020-08-28 | 中国科学技术大学苏州研究院 | QoS sensible flow management method in software defined network |
| CN107241277A (en) * | 2017-05-17 | 2017-10-10 | 天津大学 | Node method for annealing in SDN |
| CN108989210B (en) * | 2017-06-02 | 2021-08-24 | 中兴通讯股份有限公司 | Strategy-based tunnel selection method and software defined network controller |
| CN108989210A (en) * | 2017-06-02 | 2018-12-11 | 中兴通讯股份有限公司 | A kind of tunnel selecting method and software defined network controller based on strategy |
| CN107454017B (en) * | 2017-06-05 | 2021-05-11 | 上海交通大学 | Mixed data stream cooperative scheduling method in cloud data center network |
| CN107454017A (en) * | 2017-06-05 | 2017-12-08 | 上海交通大学 | Mixed data flow coordinated dispatching method in a kind of cloud data center network |
| CN107360483A (en) * | 2017-08-21 | 2017-11-17 | 西安邮电大学 | A kind of controller load-balancing algorithm for software definition optical-fiber network |
| CN107360483B (en) * | 2017-08-21 | 2020-04-24 | 西安邮电大学 | Controller load balancing algorithm for software defined optical network |
| CN108064064A (en) * | 2017-12-20 | 2018-05-22 | 浙江省公众信息产业有限公司 | Wireless sensor network Ad Hoc is by method and apparatus |
| CN108401015A (en) * | 2018-02-02 | 2018-08-14 | 广州大学 | A kind of data center network method for routing based on deeply study |
| CN108401015B (en) * | 2018-02-02 | 2020-10-02 | 广州大学 | Data center network routing method based on deep reinforcement learning |
| CN108512760B (en) * | 2018-03-09 | 2020-07-28 | 西安电子科技大学 | Routing method based on SDN guarantee service QoS |
| CN108512760A (en) * | 2018-03-09 | 2018-09-07 | 西安电子科技大学 | The method for routing of QoS of survice is ensured based on SDN |
| CN108540384A (en) * | 2018-04-13 | 2018-09-14 | 西安交通大学 | Intelligent heavy route method and device based on congestion aware in software defined network |
| CN108540384B (en) * | 2018-04-13 | 2020-07-28 | 西安交通大学 | Intelligent rerouting method and device based on congestion awareness in software defined network |
| CN108768713A (en) * | 2018-05-09 | 2018-11-06 | 西安工业大学 | A kind of guarantee QoS dynamic routing algorithms in SDN |
| CN108768776A (en) * | 2018-05-30 | 2018-11-06 | 郑州云海信息技术有限公司 | A kind of method for monitoring network and device based on OpenFlow |
| CN108933742A (en) * | 2018-06-21 | 2018-12-04 | 重庆邮电大学 | A kind of business stream scheduling method of SD-DCN link failure |
| CN109600319A (en) * | 2018-12-11 | 2019-04-09 | 浙江工商大学 | A kind of traffic scheduling method in real-time Transmission mechanism |
| CN109600319B (en) * | 2018-12-11 | 2022-07-08 | 浙江工商大学 | Flow scheduling method in real-time transmission mechanism |
| CN109547340A (en) * | 2018-12-28 | 2019-03-29 | 西安电子科技大学 | SDN data center network jamming control method based on heavy-route |
| CN109905364B (en) * | 2019-01-08 | 2021-04-20 | 山东省计算中心（国家超级计算济南中心） | Streaming media data packet transmission method and system based on SDN architecture |
| CN110149282A (en) * | 2019-01-30 | 2019-08-20 | 华为技术有限公司 | Traffic scheduling method and device |
| WO2021047401A1 (en) * | 2019-09-10 | 2021-03-18 | 华为技术有限公司 | Service classification method and apparatus, and internet system |
| CN111600754A (en) * | 2020-05-11 | 2020-08-28 | 重庆邮电大学 | Industrial heterogeneous network scheduling method for interconnection of TSN (transmission time network) and non-TSN (non-Transmission time network) |
| CN111600754B (en) * | 2020-05-11 | 2022-02-25 | 重庆邮电大学 | Industrial heterogeneous network scheduling method for interconnection of TSN (transmission time network) and non-TSN (non-Transmission time network) |
| CN111817983A (en) * | 2020-06-12 | 2020-10-23 | 浪潮思科网络科技有限公司 | Irrigation equipment network regulation and control method, equipment and system based on SDN |
| WO2021258408A1 (en) * | 2020-06-22 | 2021-12-30 | 北京交通大学 | Tolerance analysis method and apparatus for multi-service flow converged communication in industrial heterogeneous network |
| CN113923125A (en) * | 2020-06-22 | 2022-01-11 | 北京交通大学 | Tolerance analysis method and device for multi-service flow converged communication in industrial heterogeneous network |
| CN113923125B (en) * | 2020-06-22 | 2022-12-06 | 北京交通大学 | Tolerance analysis method and device for multi-service flow converged communication in industrial heterogeneous network |
| CN112187657A (en) * | 2020-09-16 | 2021-01-05 | 北京理工大学 | Extensible routing method for realizing load balancing in software defined wide area network |
| CN112187657B (en) * | 2020-09-16 | 2022-04-15 | 北京理工大学 | Extensible routing method for realizing load balancing in software defined wide area network |
| CN114513241A (en) * | 2021-04-19 | 2022-05-17 | 南京航空航天大学 | SDN-based high-performance QoS guaranteed low-orbit satellite inter-satellite routing method |
| CN113242182A (en) * | 2021-05-08 | 2021-08-10 | 东南大学 | QoS-sensitive route distribution method in mobile self-organizing network based on SDN |
| CN113242182B (en) * | 2021-05-08 | 2022-08-16 | 东南大学 | QoS-sensitive route distribution method in mobile self-organizing network based on SDN |
| CN113938955A (en) * | 2021-09-09 | 2022-01-14 | 中国联合网络通信集团有限公司 | Data transmission method, device, equipment and system |
| CN113938955B (en) * | 2021-09-09 | 2023-06-06 | 中国联合网络通信集团有限公司 | Data transmission method, device, equipment and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106341346B (en) | 2019-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106341346B (en) | A kind of routing algorithm ensureing QoS in data center network based on SDN | |
| US11316795B2 (en) | Network flow control method and network device | |
| CN111600754A (en) | Industrial heterogeneous network scheduling method for interconnection of TSN (transmission time network) and non-TSN (non-Transmission time network) | |
| CN109787801B (en) | Network service management method, device and system | |
| EP2575329B1 (en) | Proportional bandwidth sharing of the excess part in a MEF Traffic Profile | |
| WO2017078922A1 (en) | Apparatus and method for network flow scheduling | |
| WO2017024824A1 (en) | Aggregated link-based traffic management method and device | |
| CN105122747A (en) | Control device and control method in software defined network (sdn) | |
| US20170187632A1 (en) | Telecommunication systems and methods using dynamic shaping for allocating network bandwidth | |
| CN112350949B (en) | Rerouting congestion control method and system based on flow scheduling in software defined network | |
| CN101841487A (en) | Configuration method for aggregating link service flow and packet switching device | |
| CN107454015A (en) | A kind of QoS control method and system based on OF DiffServ models | |
| EP4184937A1 (en) | Method, apparatus, and system for communication in data centre | |
| CN101924781B (en) | Terminal device, QoS implementation method and flow classifier thereof | |
| Chemeritskiy et al. | On QoS management in SDN by multipath routing | |
| CN107547418A (en) | A kind of jamming control method and device | |
| WO2018036516A1 (en) | Method and system for traffic management, packet switching device and user device | |
| Soorki et al. | Label switched protocol routing with guaranteed bandwidth and end to end path delay in MPLS networks | |
| US20150109922A1 (en) | Method and apparatus for bandwidth adjustment in network virtualization system | |
| US20230336486A1 (en) | Service flow scheduling method and apparatus, and system | |
| Xu et al. | An adaptive flow table adjustment algorithm for SDN | |
| CN116319565A (en) | Load balancing system, method, equipment and storage medium based on online computing | |
| CN107786468A (en) | MPLS network bandwidth allocation methods and device based on HQoS | |
| CN110233803B (en) | Scheduling device and method for transmission network node | |
| Bonald et al. | Scheduling network traffic |
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 |