CN104702694B - The dynamic data stream scheduling method of data center based on mixed transmission modes - Google Patents
The dynamic data stream scheduling method of data center based on mixed transmission modes Download PDFInfo
- Publication number
- CN104702694B CN104702694B CN201510122705.5A CN201510122705A CN104702694B CN 104702694 B CN104702694 B CN 104702694B CN 201510122705 A CN201510122705 A CN 201510122705A CN 104702694 B CN104702694 B CN 104702694B
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- data center
- represent
- interference
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000010586 diagram Methods 0.000 claims abstract description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 22
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 238000004040 coloring Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000006855 networking Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
A kind of dynamic data stream scheduling method of the data center based on mixed transmission modes,Under the data center network of mixed transmission modes,By the size of data flow,The network topological diagram that exchanger is made up of wired connection,Input is used as in interference figure and the available wireless connection that exchanger is formed by wireless connection,With reference to relaxed algorithm,The methods of linear programming, solves to data flow scheduling problem,It is final to obtain data flow transmission route and link behaviour in service,Exported as algorithm,The present invention to the high amount of traffic in data center by carrying out rational management,Eliminate the hot issue of data center,Solves congestion,Lift the overall performance of data center,Simultaneously,The consumption control of scheme in itself is within limits,New burden will not be introduced to data center,The present invention can be on the premise of data center's consumption be ensured,Rational management is carried out to the high amount of traffic in networking,Eliminate the focus and congestion of data center network,Lift data center's performance.
Description
Technical field
The invention belongs to Internet technical field, the dynamic of more particularly to a kind of data center based on mixed transmission modes
Data stream scheduling method.
Background technology
In recent years, Internet technology is quickly grown, and cloud computing technology has obtained great propulsion and raising.As cloud computing
Infrastructure, the propulsion and popularization of the development of data center to cloud computing bring unprecedented benefit.At present, based on cloud
Rapid growth state is presented in the application service of calculating, the every field applied in life, work, study, amusement to people
Bring great convenience.However, with the development of data center, and the increasing of the extensive service based on cloud computing technology
Long, data flow caused by these services shows polarization feature, the existing low-volume traffic stream to latency sensitive, has again to output
Sensitive high amount of traffic, route to these data flows and is scheduled to data center network and brings huge challenge.It is how high
Effect processing mixed data flow turns into a bottleneck of limitation data center network development.
Low-volume traffic stream and the high amount of traffic sensitive to output to delay-sensitive are combined together, in data center network
Dynamic produces popular connection, causes network congestion, data center's performance is severely impacted.In the recent period, there is researcher proposition,
By the data flow of hot topic connection by reasonably dispatching, assign it in the relatively low connection of other utilization rate, can effectively delay
Solve network congestion problem.
At present, the solution for network congestion problem is broadly divided into two types, and first, data are realized in redesign
Central site network topological structure, solve network congestion and hot issue using new topological property.Second, in traditional data center
Central addition wireless portion, the characteristics of using high-speed, low latency is wirelessly transferred, solves network congestion problem.
60GHz wireless communication techniques as a kind of emerging technology, have transmission rate height, strong interference immunity, it is safe,
The features such as high directivity, high transmission power allowed, applied to traditional cable data center, form mixed transmission modes
Data center.By reasonably disposing and dispatching, high amount of traffic is transmitted using 60GHz technologies, can be to solve net
Network congestion problems provide a new thinking.
The content of the invention
The shortcomings that in order to overcome above-mentioned prior art, it is an object of the invention to provide a kind of based on mixed transmission modes
The dynamic data stream scheduling method of data center, in the case where ensureing application program normal work, in mixed transmission modes
Data center is scheduled by the way of mixed logic dynamic to high amount of traffic, by using wired connection and wireless connection, is solved
Data center network congestion problems, lifting data center overall performance.
To achieve these goals, the technical solution adopted by the present invention is：
A kind of dynamic data stream scheduling method of the data center based on mixed transmission modes, in the number of mixed transmission modes
Realized according under central site network according to following steps：
Step (1), by data flow fkSize dk, the network topological diagram G that is made up of wired connection of exchangerw(V,Ew)、
The interference figure G that exchanger is formed by wireless connectionI(VI,EI) and available wireless connectionAs input, wherein, V is represented
Exchanger set, EwRepresent wired connection set, VIRepresent the set that the exchanger node interfered is formed be present, EIRepresent
The set that the wireless connection interfered is formed, interference figure GI(VI,EI) representIn interference relationships；
Step (2), the optimal Decomposition set of optimum link assignment problem is obtained using linear programming
Step (3), for arbitrary interfering nodes vi, vi∈VI, according toWith
The optimal Decomposition set that step (2) obtainsObtain its corresponding weights omega (vi), wherein eijConnection i and j side is represented,
If there is connection, then eiiFor 1, if it does not exist, then eijRepresent to deal with objects for 0, F, be several data flows fkForm
Set, λ represent link utilization, CijRepresent link capacity, ω (ve) represent interfering nodes weight；
Step (4a), multiple independent set IS and its corresponding score set { y (I after being decomposedi)}；
Step (4b), the score set obtained according to (4a) select an independent set IS, referred to as I*；
Step (5), for arbitraryFor γijAssignment, if eij∈I*, γijFor 1, e is representedijIt is added into
Solution is gathered, otherwise γij=0, represent eijSolution set is not added into；
Step (6), with reference to γ obtained in the previous stepij, update { γijSet, obtain new { γij, i.e., it is final
{γij, for { γijIn be 1 element, its represent connection belong to final disaggregation；With reference to final { γijAnd step
(2) the optimal Decomposition set obtained inObtainRepresent whether k-th of data flow passes through i-node and j nodes；
Step (7a), according toBy data flow fkIt is assigned to different paths, obtains a set of paths, each
Path is required for the requirement for meeting data flow；
Step (7b), for arbitrary data flow fk, according to the paths of probability selection one, it is added to set of paths；
Step (8), return path set { PkAnd { γij, terminate computing.
Connected for available wirelessIn any a line, put it into interference figure GI(VI,EI) node is used as,
If any two node has interference, a line (e is added between the two nodes1,e2)；For interference figure GI(VI,
EI) in node, if side is not present between two nodes, show that the two nodes are separate, independent set IS is dry
Disturb figure GI(VI,EI) a subset, any two node is independent in IS, in order to establish wireless connection, from interference figure GI(VI,
EI) one independent set IS of middle selection, it is assumed that
Wherein, for eij∈Ew, γijRepresent eijWhether it is selected, is otherwise 0, if two quilts for 1 if choosing
There is interference in the connection chosen, then can not meet formula (2), i.e. all selected connections come from same independent set IS.
Optimal Decomposition set in the step (2)Method for solving be：
For Cij
Solve
minλ
Belong to NP-hard problems, with relaxed algorithm by decomposition step, finally obtain optimum link using linear programming
The optimal Decomposition set of assignment problemThat is, a score set is obtained using Linear programming thought, corresponding convex combination is worked as
If doing in, that is, gather
For binary number, data flow f is representedkWhether by connection eij,
Wherein, δ1、δ2Represent the wired and quantity of wireless connection in routed path.
With reference to the size of every a data stream and the occupancy situation of each edge, and link capacity and link utilization, meter
Calculate eijWeights omega (eij)。
In the step (4a), using graph coloring algorithm, by interference figure GIWith weight set ω (vi) obtained as algorithm input
Obtain interference figure GIDecomposition result { y (Ii):Ii∈ I }, independent set IS and its corresponding score set after being decomposed
{y(Ii)}。
In the step (4b), according to score set y (I*) corresponding to fraction property, select an optimal independent set
IS。
In the step (6), with reference to final { γijAnd the middle optimal Decomposition set obtained of step (2)ObtainIfFor 1, represent that k-th of data flow passes through i-node and j nodes, otherwise, without i-node and j nodes.
In the step (7a), forIfFor 1, fkBy eij, otherwise, without it, final fkObtain
Mulitpath, random selection one are transmitted.
Compared with prior art, the present invention solves Path Selection by approximate data and linear programming.This is calculated
Method applies to the data center of mixed transmission modes, can effectively solve hot issue, alleviates the pressure of wire transmission, lifts number
According to efficiency of transmission.
Brief description of the drawings
Fig. 1 is schematic flow sheet of the present invention.
Embodiment
Describe embodiments of the present invention in detail with reference to the accompanying drawings and examples.
A kind of dynamic dataflow scheduling scheme of the present invention, with reference to wire transmission stabilization and be wirelessly transferred flexible, logarithm
It is scheduled according to stream, the invention is mainly used in the transmission for solving high amount of traffic, alleviates the hot issue in data center network.For
The transmission bandwidth of Gb ranks is realized, 60GHz wireless technologys are used among the present invention, however, the technology can produce one
Sector interference.
The set that the process object of the present invention is formed for several high amount of traffics, it is assumed that the collection is combined into F, for arbitrary fk
, d be present in ∈ FkRepresent the size of the data flow.The invention represents blended data central site network with G (V, E), and V represents exchanger
Set, E represent the set of paths of connection interchanger, EwRepresent wired connection set, EsWireless connection set is represented, E=E can be obtainedw
+Es.In the present invention,Represent available wireless connection set, interference figure GI(VI,EI) representIn interference relationships.It is right
InIn any a line, put it into GI, as a node, if interference be present in any two nodes, this two
A line (e is added between individual node1,e2)。
For the node in interference figure, if side is not present between two nodes, show that the two nodes are separate.
Independent sets IS, which is closed, represents interference figure GIA subset, any two node is independent among IS.
In order to establish wireless connection, it is necessary to select an independent set from interference set, it is assumed that
Wherein, γijRepresent eij(eij∈Ew) whether be selected, it is otherwise 0 for 1 if choosing.If two selected
Connection exist interference, then (2) are run counter to.So all selected connections need to come from same independent set IS.
In the invention, wired connection and wireless connection among mixed logic dynamic can be controlled, uses a binary number
Represent data flow fkWhether by connection eij, can obtain
Wherein, δ1、δ2Represent the wired and quantity of wireless connection in routed path.
For eij∈ E,Represent link utilization, wherein CijRepresent link capacity.Need to solve
One maximum link utilization λ so thatMinimum λ is required solution.
In order to solve the problems, such as, the λ of minimum is obtained, it is necessary to solve a linear programming problem P.By being carried out to former problem
Relaxation processes, a score set is obtained using Linear programming thought, if doing among corresponding convex combination, is gathered
According to being solved, according to
Calculate any vi∈VICorresponding ω (vi).Afterwards, the decomposition result { y (I obtained according to Similarity algorithmi):Ii
∈ I }, the IS after being decomposed.According to y (I*), select an independent set IS.
For arbitraryIf eij∈I*, then γij1 is set to, is otherwise 0.According to new { γij, obtain
Next need to solve the problems, such as one it is new, willDecompose a set of paths { Pk:fk∈ F }, it is each
Individual path p should meet the requirement D (p) of data flow.
To any fk∈ F, according to probabilityObtain P*, then by P*Add Pk。
Finally return to { PkAnd { γij, algorithm terminates.
Step (1) starts the algorithm, by data flow fkSize dk, wired network topology figure Gw(V,Ew), interference figure GI
(VI,EI), available wireless connectionInputted as algorithm, wherein, V represents exchanger set, EwRepresent wired connection set, Gw
(V,Ew) represent the network topological diagram that exchanger is made up of wired connection.For the exchanger node of wireless connection, due to
The interference characteristics of 60GHza in itself, there can be interference relationships between node, the node interfered be present and form set VI, mutually
The wireless connection of interference forms set EI, interference figure GIThen by VIAnd EICollectively form.
It is the final solution target of the invention that step (2), which solves maximum link utilization, for
Solve
minλ
Belong to NP-hard problems, we use relaxed algorithm to former problem, by decomposition step, are obtained using linear programming
Obtain the optimal Decomposition set of optimum link assignment problem
Step (3) is for arbitrary interfering nodes vi, according to
The optimal Decomposition set obtained with step (1)Obtain its corresponding weights omega (vi), wherein eijThe company of expression
Connect i and j side.
Weights omega (v corresponding to the interfering nodes that the interference figure and previous step that step (4) inputs algorithm obtaini) form
Inputs of the set ω as colouring algorithm, obtain independent set IS and its corresponding score set { y (Ii)}.According to y (I*) choosing
Select an independent set I*。
Step (5) is for arbitraryFor γijAssignment.If eij∈I*, γijFor 1, otherwise γij=0.γij
Represent eijWhether set is added into, whereinRepresent the set that available wireless connection is formed.
Step (6) combines the γ that previous step obtainsij, update { γijSet, obtain new { γij, i.e., it is final
{γij}.For { γijBe 1 element, its represent connection belong to final disaggregation.With reference to { γijAnd the middle acquisition of step (2)
Optimal Decomposition setIt can obtainRepresent whether k-th of data flow passes through i-node and j nodes.
Step (7) basisBy data flow fkDifferent paths is assigned to, obtains a set of paths, each road
Footpath is required for the requirement for meeting data flow.For arbitrary data flow fk, according to the paths of probability selection one, it is added to path set
Close.
Step (8) return path set { PkAnd { γij, terminate computing.
Claims (9)
1. a kind of dynamic data stream scheduling method of the data center based on mixed transmission modes, it is characterised in that passed in mixing
Realized under the data center network of defeated pattern according to following steps：
Step (1), by data flow fkSize dk, the network topological diagram G that is made up of wired connection of exchangerw(V,Ew), exchange
The interference figure G that device is formed by wireless connectionI(VI,EI) and available wireless connectionAs input, wherein, V represents to exchange
Device set, EwRepresent wired connection set, VIRepresent the set that the exchanger node interfered is formed be present, EIRepresent mutual
The set that the wireless connection of interference is formed, interference figure GI(VI,EI) representIn interference relationships；
Step (2), the optimal Decomposition set of optimum link assignment problem is obtained using linear programming
Step (3), for arbitrary interfering nodes vi, vi∈VI, according toAnd step
(2) the optimal Decomposition set obtainedObtain its corresponding weights omega (vi), wherein eijConnection i and j side is represented, if
In the presence of connection, then eijFor 1, if it does not exist, then eijRepresent to deal with objects for 0, F, be several data flows fkThe set of composition,
λ represents link utilization, CijRepresent link capacity, ω (ve) represent interfering nodes weight；
Step (4a), multiple independent set IS and its corresponding score set { y (I after being decomposedi)}；
Step (4b), the score set obtained according to (4a) select an independent set IS, referred to as I*；
Step (5), for arbitraryFor γijAssignment, if eij∈I*, γijFor 1, e is representedijIt is added into disaggregation
Close, otherwise γij=0, represent eijSolution set is not added into；
Step (6), with reference to γ obtained in the previous stepij, update { γijSet, obtain new { γij, i.e., final { γij, it is right
In { γijIn be 1 element, its represent connection belong to final disaggregation；With reference to final { γijAnd the middle acquisition of step (2)
Optimal Decomposition setObtainRepresent whether k-th of data flow passes through i-node and j nodes；
Step (7a), according toBy data flow fkDifferent paths is assigned to, obtains a set of paths, each paths
It is required for the requirement for meeting data flow；
Step (7b), for arbitrary data flow fk, according to the paths of probability selection one, it is added to set of paths；
Step (8), return path set { PkAnd { γij, terminate computing.
2. the dynamic data stream scheduling method of the data center based on mixed transmission modes according to claim 1, its feature
It is, is connected for available wirelessIn any a line, put it into interference figure GI(VI,EI) node is used as, such as
There is interference in fruit any two node, then a line (e is added between the two nodes1,e2)；For interference figure GI(VI,EI)
In node, if side is not present between two nodes, show that the two nodes are separate, independent set IS is interference figure
GI(VI,EI) a subset, any two node is independent in IS, in order to establish wireless connection, from interference figure GI(VI,EI) in
Select an independent set IS, it is assumed that
<mrow>
<msub>
<mi>&gamma;</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<mn>0</mn>
<mo>,</mo>
<mo>&ForAll;</mo>
<msub>
<mi>e</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>&Element;</mo>
<mover>
<msub>
<mi>E</mi>
<mi>s</mi>
</msub>
<mo>&OverBar;</mo>
</mover>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>&gamma;</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>&gamma;</mi>
<mrow>
<mi>u</mi>
<mi>v</mi>
</mrow>
</msub>
<mo>&le;</mo>
<mn>1</mn>
<mo>,</mo>
<mo>&ForAll;</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>e</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>,</mo>
<msub>
<mi>e</mi>
<mrow>
<mi>u</mi>
<mi>v</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mo>&Element;</mo>
<msub>
<mi>E</mi>
<mi>I</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, for eij∈Ew, γijRepresent eijWhether it is selected, is otherwise 0 for 1 if choosing, if two selected
There is interference in connection, then can not meet formula (2), i.e. all selected connections come from same independent set IS.
3. the dynamic data stream scheduling method of the data center based on mixed transmission modes according to claim 1, its feature
It is, optimal Decomposition set in the step (2)Method for solving be：
For
<mrow>
<munder>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>f</mi>
<mi>k</mi>
</msub>
<mo>&Element;</mo>
<mi>F</mi>
</mrow>
</munder>
<msup>
<mi>d</mi>
<mi>k</mi>
</msup>
<msubsup>
<mi>x</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
<mi>k</mi>
</msubsup>
<mo>&le;</mo>
<msub>
<mi>&lambda;C</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
</mrow>
Solve
minλ
Belong to NP-hard problems, with relaxed algorithm by decomposition step, finally obtain optimum link distribution using linear programming
The optimal Decomposition set of problem
For binary number, data flow f is representedkWhether by connection eij,
<mrow>
<msub>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>e</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>&Element;</mo>
<msub>
<mi>E</mi>
<mi>w</mi>
</msub>
</mrow>
</msub>
<msubsup>
<mi>x</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
<mi>k</mi>
</msubsup>
<mo>&le;</mo>
<msub>
<mi>&delta;</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<mo>&ForAll;</mo>
<msub>
<mi>f</mi>
<mi>k</mi>
</msub>
<mo>&Element;</mo>
<mi>F</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>e</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mo>&Element;</mo>
<mover>
<msub>
<mi>E</mi>
<mi>s</mi>
</msub>
<mo>&OverBar;</mo>
</mover>
</mrow>
</msub>
<msubsup>
<mi>x</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
<mi>k</mi>
</msubsup>
<mo>&le;</mo>
<msub>
<mi>&delta;</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<mo>&ForAll;</mo>
<msub>
<mi>f</mi>
<mi>k</mi>
</msub>
<mo>&Element;</mo>
<mi>F</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, δ1、δ2Represent the wired and quantity of wireless connection in routed path.
4. the dynamic data stream scheduling method of the data center based on mixed transmission modes according to claim 3, its feature
Be, with relaxed algorithm by decomposition step after, obtain a score set using Linear programming thought, corresponding convex combination is worked as
If doing in, that is, gather
5. the dynamic data stream scheduling method of the data center based on mixed transmission modes according to claim 3, its feature
It is, with reference to the size of every a data stream and the occupancy situation of each edge, and link capacity and link utilization, calculates
eijWeights omega (eij)。
6. the dynamic data stream scheduling method of the data center based on mixed transmission modes according to claim 3, its feature
It is, in the step (4a), using graph coloring algorithm, by interference figure GIWith weight set ω (vi) obtained as algorithm input
Interference figure GIDecomposition result { y (Ii):Ii∈ I }, independent set IS and its corresponding score set { y after being decomposed
(Ii)}。
7. the dynamic data stream scheduling method of the data center based on mixed transmission modes according to claim 3, its feature
It is, in the step (4b), according to score set y (I*) corresponding to fraction property, select an optimal independent set IS.
8. the dynamic data stream scheduling method of the data center based on mixed transmission modes according to claim 1, its feature
It is, in the step (6), with reference to final { γijAnd the middle optimal Decomposition set obtained of step (2)ObtainIfFor 1, represent that k-th of data flow passes through i-node and j nodes, otherwise, without i-node and j nodes.
9. the dynamic data stream scheduling method of the data center based on mixed transmission modes according to claim 1, its feature
It is, in the step (7a), forIfFor 1, fkBy eij, otherwise, without it, final fkObtain a plurality of
Path, random selection one are transmitted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510122705.5A CN104702694B (en) | 2015-03-19 | 2015-03-19 | The dynamic data stream scheduling method of data center based on mixed transmission modes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510122705.5A CN104702694B (en) | 2015-03-19 | 2015-03-19 | The dynamic data stream scheduling method of data center based on mixed transmission modes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104702694A CN104702694A (en) | 2015-06-10 |
| CN104702694B true CN104702694B (en) | 2017-12-19 |
Family
ID=53349452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510122705.5A Active CN104702694B (en) | 2015-03-19 | 2015-03-19 | The dynamic data stream scheduling method of data center based on mixed transmission modes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104702694B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105376112B (en) * | 2015-11-24 | 2018-06-19 | 清华大学 | Heterogeneous network resource allocation method under intermediate treatment constraint |
| CN105827540B (en) * | 2016-05-30 | 2018-11-02 | 清华大学深圳研究生院 | A kind of data center network transport layer data stream transmission method priority-based |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2612532A1 (en) * | 2010-09-03 | 2013-07-10 | Nokia Corp. | Resource sharing between secondary networks |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BRPI0822299A2 (en) * | 2008-03-11 | 2015-06-30 | Thomson Licensing | Joint association, proper routing, and rate allocation in multi-hop wireless mesh networks |
| US8559908B2 (en) * | 2008-06-16 | 2013-10-15 | Qualcomm Incorporated | Jamming graph and its application in network resource assignment |
-
2015
- 2015-03-19 CN CN201510122705.5A patent/CN104702694B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2612532A1 (en) * | 2010-09-03 | 2013-07-10 | Nokia Corp. | Resource sharing between secondary networks |
Non-Patent Citations (2)
| Title |
|---|
| Tunnel Concentrator Placement for Traffic Optimization in IPv4-IPv6 Coexisting Networks;Peng Wu, Yong Cui, Jianping Wu;《IEEE International Conference on Communications 2013》;20131231;全文 * |
| Wireless Data Center Networking;Yong Cui, Hongyi Wang, Xiuzhen Cheng, Biao Chen;《IEEE Wireless Communications》;20111231;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104702694A (en) | 2015-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104217073B (en) | A kind of visual layout's method of network community gravitation guiding | |
| CN108111335B (en) | A kind of method and system of scheduling and link virtual network function | |
| Qu et al. | Empowering edge intelligence by air-ground integrated federated learning | |
| CN106993298A (en) | A kind of intelligent electric power communication service difference dispatching method based on QoS | |
| CN104537178B (en) | A kind of power system associative simulation modeling method based on Matlab and Netlogo | |
| CN105722206A (en) | Energy efficiency optimization algorithm of multi-user OFDM relay system | |
| CN103971160A (en) | Particle swarm optimization method based on complex network | |
| CN105391056B (en) | A kind of power system distribution economic load dispatching method for considering uneven communication network | |
| CN106651628A (en) | Regional cool and thermal power comprehensive energy optimizing configuration method and apparatus based on graph theory | |
| CN103428805B (en) | The virtual mapping method of a kind of wireless network based on link anti-interference | |
| CN104702694B (en) | The dynamic data stream scheduling method of data center based on mixed transmission modes | |
| CN103619066B (en) | Method for distributing downlink interference mitigation based on distributed channel | |
| CN104994508A (en) | Cognitive radio mesh network resource distribution and routing method | |
| CN106230737B (en) | A kind of software definition network-building method of state aware | |
| CN106209294B (en) | A kind of full light interconnection network system of data center and communication means of high extension | |
| CN105873217B (en) | Based on multifactor STDMA self-organizing network dynamic time slot allocating method | |
| CN102946443B (en) | Multitask scheduling method for realizing large-scale data transmission | |
| CN106060876A (en) | Load balancing method for heterogeneous wireless network | |
| CN109685279A (en) | A kind of Complicated Distribution Network PQM optimization method based on topology degradation | |
| CN103826282B (en) | Set based on dump energy divides multi-hop routing method | |
| CN103442367B (en) | OFDM network uplink link circuit resource distribution method based on discrete multicomponent coding | |
| CN103427884B (en) | Acquisition methods is worked in coordination with in multiple terminals based on service generation ubiquitous in mobile ad hoc network | |
| Mufid et al. | Performance evaluation of PEGASIS protocol for energy efficiency | |
| CN104993483B (en) | Power transmission channel dynamic identifying method based on real-time power flow | |
| CN105357115B (en) | A kind of network utility maximization approach being route based on asynchronous back pressure type with scheduling |
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 |