CN104065509A - SDN multi-controller deployment method for reducing management load overhead - Google Patents
SDN multi-controller deployment method for reducing management load overhead Download PDFInfo
- Publication number
- CN104065509A CN104065509A CN201410291267.0A CN201410291267A CN104065509A CN 104065509 A CN104065509 A CN 104065509A CN 201410291267 A CN201410291267 A CN 201410291267A CN 104065509 A CN104065509 A CN 104065509A
- Authority
- CN
- China
- Prior art keywords
- controller
- network
- switch
- sdn
- limit
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an SDN multi-controller deployment novel method for reducing management load overhead, belonging to the technical field of the software defined network (SDN). The method is characterized in that the management load of a software defined network (SDN) controller is used as a decision variable, and a mathematical model about controller management load is constructed. An original SDN network multi-controller deployment problem is abstracted to be a graph theory problem, the graph theory problem is converted into an integer linear programming problem through establishing the mathematical model, and an NP difficult problem is solved by using an approximate algorithm. According to the method, in the process of constructing the mathematical model of the multi-controller deployment problem, the network performance and the management load of the SDN controller are creatively taken into consideration, effective deployment schemes can be provided for different SDN networks, the reasonable selection and effective deployment of the number of multiple controllers are realized, and the normal and effective operation of the SDN network in the condition of the satisfaction of certain network performance and minimum cost are ensured.
Description
Technical field
The invention belongs to software defined network (SDN) technical field, relate to a kind of SDN multi-controller dispositions method that reduces load management expense.
Background technology
Along with sharply expanding of network size and continuing to bring out of the new application of new technology, conventional network architecture and design concept expose wretched insufficiency gradually, in order to break the closure of network architecture, promote the opening of network architecture, for the innovation of network function lays the foundation, the thought of software defined network (Software DefinedNetwork, SDN) is arisen at the historic moment.For by network function opening to upper layer application, SDN comes the logic control plane of the network equipment and data retransmission planar separation, and adopts central controlled mode to realize the programmability of the network equipment.Compare legacy network, SDN has simplified network management and configuration operation, has reduced the complexity of network core device, has improved the flexibility of network control and management, strengthen the tenability to new network, New Deal, shortened the cycle of network function innovation.
Except OpenFlow exchange exerts an influence to network data transfer capability, for the centralized controller extensibility that in SDN network, all OpenFlow exchanges produce data retransmission rule plays decisive action especially to forwarded performance.Although it is called as slow-path (slow path); can work as network when reaching certain scale or user concurrent access and increasing suddenly; if controller cannot respond in time to the concurrent request of a large amount of OpenFlow exchanges; will cause OpenFlow exchange according to data retransmission rule, to forward the message reaching in a large number, be easy to occur network performance bottleneck.Therefore, controller scalability is not only determining the size of SDN network size, has also determined that can SDN network by extensive commercialization.Meanwhile, controller is as the control core of whole network, and himself reliability will determine that whether SDN network is available.When controller runs into hardware fault or software Bug, owing to cannot, for the raw rule that forwards of new miscarriage is handed down to OpenFlow switching equipment, easily causing network data to forward the interruption of service.Therefore, the distributed deployment in each switching network equipment of relatively traditional Non-SDN network central control function processed, the reliability of the centralized controller of SDN network is larger on the impact of network stabilization.
If adopt single-point to dispose to controller, SDN network stabilization will be difficult to be protected.Using for reference traditional server Clustering raising controller scalability and reliability is a kind of good Research Thinking.Result of study shows that controller utilizes the fast-developing trend of server hardware, and the chip ability of comparing conventional network equipment chain of command has larger computing capability; Separate unit server just can be competent at the chain of command computing capability that surpasses 1000 exchanges; If adopt active/standby mode deployment controller, have the active and standby role switching problem of controller and fault recovery problem; If adopt trunking mode deployment controller, exchange request load balancing between each controller in cluster how, with the collaborative work between Time Controller, topology and state, sharing etc. is all a very large difficult problem.Main stream approach is to adopt distributed control thought, in a SDN network, dispose a plurality of controllers, each controller is directly managed direct-connected with it OpenFlow exchange, by the indirectly connected OpenFlow of mode indirect control that programmes or inquire about, exchange, and between different OpenFlow controllers, mutually share whole net view and resource status, finally reach the low delay and the scalability needs that meet task key network.But in large scale network is disposed, the quantity of controller and position are disposed and have directly been determined network cost efficiency, how to the chain of command ownership Partitioning optimization of switching equipment, to be also difficult point, controller keeps requiring also very high to the management consistency of indirect node and Link State simultaneously.
Summary of the invention
According to the defect existing in above-mentioned background technology and deficiency, the invention provides a kind of SDN multi-controller that reduces load management expense and dispose new method; For different SDN networks, provide effective deployment scheme; In the process of Mathematical Modeling that builds multi-controller deployment issue, innovatively the load management of network performance and SDN controller to be included in and considered in the lump, the load management of controller of take is decision variable, chooses suitable approximate data; Thereby realize the Rational choice of multi-controller quantity and effectively dispose, guarantee SDN network in the situation that meeting certain network performance and minimum cost normally, effectively operation;
The solution of the SDN multi-controller deployment issue of reduction load management expense of the present invention comprises the analysis of network topology structure, the choosing and solving of the structure of Related Mathematical Models, approximate data; Specific as follows:
(1) analyze network topological structure
By the various factors of analyzing topology of networks and affecting network performance, choose the load management of SDN controller in network as decision variable; Controller management load mainly comprises the cost of controller processing request and the cost of installation rule etc.;
In wide area SDN network, in order to meet real network performance requirement, conventionally need to dispose many controllers.For the controller of this some, if not through rationally disposing, by being easy to cause the waste of resource, even can not meet network performance demand.In previously studying the work of SDN network multi-controller deployment issue, one be chosen node to the delay of controller as Optimal Decision-making variable, this is to consider that the size of delay has determined the quality of this network conventionally in wide area SDN network, postpones to play leading role; Another is to have chosen reliability as decision variable, when occurring, network failure effectively controls the expection percentage in path in network, this is to consider in SDN network, if a certain is controlled path failure, connection between forwarding unit and controller thereof is disconnected, thereby make part in network control link failure.On forefathers' research work basis, a kind of new tolerance has been proposed, be used for reflecting controller management load, load management mainly comprises the cost of controller processing request and the cost of installation rule etc., and usings this as decision variable.This is to consider that the disposal ability of controller is limited, if the load management of controller is too high, will have a strong impact on the performance of controller, thereby affects the performance of whole network.Target is exactly to meet amount controller the least possible in the situation that, guarantees that the load management of these controllers is minimum simultaneously.
A. by analyzing topology of networks, can turn to a graph theoretic problem by multi-controller deployment issue is abstract, being about to whole network abstract is a non-directed graph;
B. according to analysis, proposed a kind of new tolerance, be used for reflecting controller management load, load management mainly comprises the cost of controller processing request and the cost of installation rule etc., and usings this as decision variable;
(2) build Related Mathematical Models
Build to reduce the Mathematical Modeling of the SDN multi-controller deployment issue of load management expense, the load management of network central control device processed of take is decision variable, chooses suitable constraints, sets up integral linear programming; Specific as follows:
The factor that will achieve the goal according to impact finds decision variable.The load management of controller is as decision variable; Functional relation between being achieved the goal by decision variable and place is determined target function.According to decision variable and final goal, determine and will minimize load management as target function; By the suffered restrictive condition of decision variable determine decision variable will be satisfied constraints.To meet the network delay of certain threshold values and the disposal ability of limited controller as constraints.Although using the load management of controller as decision variable, still need to consider the delay in network.Owing to considering in one network, as long as within postponing to be in tolerable scope, this network just can normally be worked and the impact that do not postponed.Therefore, delay is considered as constraints.In order to reach this object, can set threshold values, make, as long as the value postponing is not more than a certain threshold values, just can meet the demand of the normal work of network.In addition, also need to consider the disposal ability of controller, certain hour internal controller the quantity of treatable request.Within a certain period of time, the total quantity of the stream that in network, switch produces be not more than controller the sum of treatable request, guarantee that whole network can normally effectively move.
The present invention turns to a graph theoretic problem by multi-controller deployment issue is abstract, then in a given k controller, selects the controller of suitable quantity, and these controllers are connected with the switch in figure by suitable method.Suppose that whole network is abstract in topological diagram G, S is the set of switch in network, and C is the set of network central control device processed, and setting the interior fluxion that switch i is forwarded to controller from network of unit interval is f
i, establishing the propagation cost of stream on the shortest path between switch i and controller j is d
ij(from the angle of propagation delay, representing), target function that so thus can this optimization problem is min Σ
i ∈ SΣ
j ∈ Cf
ix
ijd
ij, x wherein
ijrepresent switch i whether be connected with controller j (be to be 1, no is 0).For this multi-controller, dispose optimization problem, target is exactly to choose the controller of suitable quantity in k controller, thereby makes the load management minimum of the controller that uses in network;
In order to reach this target, also need to meet certain constraints.First, for network delay, in one network, as long as within postponing to be in tolerable scope, this network just can normally be worked.Concrete, setting a threshold values is δ, requirement for
with
, have x
ijd
ij≤ δ requires the value of network delay to be not more than this threshold values.Secondly, consider the disposal ability of controller, be embodied in certain hour internal controller the quantity of treatable request.Concrete, introduce controller ability description, definition U=<u
i, u
2... u
| C|> is the disposal ability vector of controller in the unit interval, so u
jbe exactly treatable largest request quantity in the controller j unit interval.Thereby can be for
, be required to meet Σ
i ∈ Sx
ijf
i≤ y
ju
j, y wherein
jrepresent whether controller j is connected in network and in state of activation (be to be 1, no is 0);
(3) approximate data choosing and solving
Integral linear programming problem for setting up in step (two), by solving its dual linear programming, solves initial planning problem innovatively; Choosing the degree of approximation reaches 3 approximate data the dual linear programming of initial planning is solved; Concrete steps are as follows:
A. by mentioned earlier, this optimization problem is a np hard problem, because np hard problem cannot be tried to achieve optimal solution and can only be tried to achieve approximate solution, then considers the demand of practical application, thereby finds suitable and effective approximate data just to seem particularly important;
B. lax according to the linear programming of Zero-one integer programming, is necessary for each variable 0 or 1 constraint, replaces with the constraint that each weak variable belongs to interval [0,1]; The optimization problem of NP difficulty (integer programming) is converted into the problem (linear programming) of a relevant solvable in polynomial time, then the linear programming after lax is solved;
C. first, for the linear programming after lax, try to achieve its dual program max Σ
i ∈ Sα
i-γ δ-bk, γ, b are arbitrary constant and meet γ, b>=0; Then, choosing the degree of approximation reaches 3 approximate data this dual program is solved;
D. by dual program, can be obtained the dual variable α of each switch in figure
iconstantly increase until remain unchanged when this switch is connected with certain controller.Initial condition, each switch is in not-connected status; Dual variable α
iincrease, in figure, some limit (i, j) reaches α
i=f
id
ij+ γ d
ij+ af
itime, it is " infeasible limit " that algorithm is declared this limit; As dual variable β
ijmeet β
ijduring >0, declaring this limit is " feasible limit "; Similarly, when limit (i, j) is feasible limit, statement switch i connects, and controller j is in state of activation.For controller j, if meet Σ
i ∈ Sβ
ij=b-au
j, declare this controller temporarily in state of activation; Meanwhile, between all and this controller, exist the switch on infeasible limit to become to be connected, declare " pseudo-controller " that this controller is these switches; Next, make C
trepresent the set of the temporary transient controller in state of activation, the subgraph G that comprises all feasible limits
1and to meet between switch and controller be 2 subgraph G more than the number of limit
2; Final goal is exactly to find maximum independent set
meet
(
for G
2subgraph), make set
in all controllers all in state of activation;
The invention has the beneficial effects as follows and turn to a graph theoretic problem by former SDN network multi-controller deployment issue is abstract, by setting up Mathematical Modeling, this graph theoretic problem is converted into integral linear programming problem, utilizes the approximate data that reaches certain degree of approximation to solve the difficult problem of this NP-; Finally, utilize the result the try to achieve problem in can fine solution multi-controller deployment.
Accompanying drawing explanation
Fig. 1 is that the bipartite graph of SDN network is abstract.
Fig. 2 is multi-controller deployment issue example.
In figure: the set of C controller; The set of S switch; I telephone net node; J controller node.
Embodiment
Below in conjunction with accompanying drawing, to of the present invention, be further detailed
As shown in Figure 1, SDN network topological diagram is abstracted into a bipartite graph.The collaborative management and control model of multi-controller can abstractly be the in the situation that of given network topology structure and amount controller, by calculating, obtain the connected mode of all switches and each controller in the required amount controller of this network and network, consider again that afterwards switch communicates by letter with controller, the problem such as collaborative between controller and controller.The solution of intending adopting is multi-controller to be disposed and worked in coordination with management and control be converted into the equipment location problem without capacity limit, thereby proposes the tolerance of reflection controller management load, and builds based on this Mathematical Modeling about controller management load.Then utilize linear programming to solve this Mathematical Modeling.Because this problem is generally np hard problem, can only obtain approximate solution, so choose suitable algorithm in research, it is solved, finally obtain the approximate solution of this Optimum Solution, thereby realize the Rational choice of multi-controller quantity and effectively dispose.
In research, turn to a graph theoretic problem by multi-controller deployment issue is abstract, i.e. a given non-directed graph, as shown in Figure 1, wherein S is the set of switch in network, C is the set of controller.This research work is exactly in a given k controller, to select the controller of suitable quantity, and these controllers are connected with the switch in figure by suitable method.
As shown in Figure 2, be an example of multi-controller deployment issue.By setting up Mathematical Modeling, this graph theoretic problem is converted into integral linear programming problem, utilizes the approximate data that reaches certain degree of approximation to solve the difficult problem of this NP-; By approximate data, solve the result of acquisition, finally can solve SDN network multi-controller deployment issue.Be a known network topological diagram, determine normal required SDN amount controller and the concrete connected mode of controller and switch moved of whole network.
Claims (1)
1. a SDN multi-controller dispositions method that reduces load management expense, is characterized in that following steps:
(1) analyze network topology structure
A. analyze topology of networks, turn to a graph theoretic problem by multi-controller deployment issue is abstract, being about to whole network abstract is a non-directed graph;
B. propose a kind of new tolerance, be used for reflecting controller management load, load management mainly comprises the cost of controller processing request and the cost of installation rule etc., and usings this as decision variable;
(2) build Related Mathematical Models
The load management of controller is as decision variable; Functional relation by decision variable and between will achieving the goal is determined target function; According to decision variable and final goal, determine and will minimize load management as target function; By the suffered restrictive condition of decision variable determine decision variable will be satisfied constraints; To meet the network delay of certain threshold values and the disposal ability of limited controller as constraints;
Turn to a graph theoretic problem by multi-controller deployment issue is abstract, selection control in a given k controller then, and these controllers are connected with the switch in figure; Suppose that whole network is abstract in topological diagram G, S is the set of switch in network, and C is the set of network central control device processed, and setting the interior fluxion that switch i is forwarded to controller from network of unit interval is f
i, establishing the propagation cost of stream on the shortest path between switch i and controller j is d
ij, the target function that obtains so thus this optimization problem is min Σ
i ∈ SΣ
j ∈ Cf
ix
ijd
ij, x wherein
ijrepresent whether switch i is connected with controller j; For this multi-controller, dispose optimization problem, target is exactly to choose the controller of suitable quantity in k controller, thereby makes the load management minimum of the controller that uses in network;
Setting a threshold values is δ, require for
with
, have x
ijd
ij≤ δ requires the value of network delay to be not more than this threshold values; Introduce controller ability description, definition U=<u
i, u
2... u
| C|> is the disposal ability vector of controller in the unit interval, so u
jbe exactly treatable largest request quantity in the controller j unit interval, must be for
, be required to meet Σ
i ∈ Sx
ijf
i≤ y
ju
j, y wherein
jrepresent whether controller j is connected in network and in state of activation;
(3) approximate data choosing and solving
A. lax according to the linear programming of Zero-one integer programming, is necessary for each variable 0 or 1 constraint, replaces with the constraint that each weak variable belongs to interval [0,1]; The optimization problem of NP difficulty is converted into the problem of a relevant solvable in polynomial time, then the linear programming after lax is solved;
B. for the linear programming after lax, try to achieve its dual program max Σ
i ∈ Sα
i-γ δ-bk, γ, b are arbitrary constant and meet γ, b>=0; Choosing the degree of approximation reaches 3 approximate data this dual program is solved;
C. by dual program, can be obtained the dual variable α of each switch in figure
iconstantly increase until remain unchanged when this switch is connected with certain controller; Initial condition, each switch is in not-connected status; Dual variable α
iincrease, in figure, some limit (i, j) reaches α
i=f
id
ij+ γ d
ij+ af
itime, it is " infeasible limit " that algorithm is declared this limit; As dual variable β
ijmeet β
ijduring >0, declaring this limit is " feasible limit "; Similarly, when limit (i, j) is feasible limit, statement switch i connects, and controller j is in state of activation; For controller j, if meet Σ
i ∈ Sβ
ij=b-au
j, declare this controller temporarily in state of activation; Meanwhile, between all and this controller, exist the switch on infeasible limit to become to be connected, declare " pseudo-controller " that this controller is these switches; Next, make C
trepresent the set of the temporary transient controller in state of activation, the subgraph G that comprises all feasible limits
1and to meet between switch and controller be 2 subgraph G more than the number of limit
2; Final goal is exactly to find maximum independent set
, meet
,
for G
2subgraph, make set
in all controllers all in state of activation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410291267.0A CN104065509B (en) | 2014-07-24 | 2014-07-24 | A kind of SDN multi-controller dispositions methods for reducing management load overhead |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410291267.0A CN104065509B (en) | 2014-07-24 | 2014-07-24 | A kind of SDN multi-controller dispositions methods for reducing management load overhead |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104065509A true CN104065509A (en) | 2014-09-24 |
| CN104065509B CN104065509B (en) | 2017-07-11 |
Family
ID=51553051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410291267.0A Active CN104065509B (en) | 2014-07-24 | 2014-07-24 | A kind of SDN multi-controller dispositions methods for reducing management load overhead |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104065509B (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104618130A (en) * | 2014-12-09 | 2015-05-13 | 中国人民解放军国防科学技术大学 | Minimum cost synchronization method of data center network controller by using software |
| CN104754053A (en) * | 2015-04-01 | 2015-07-01 | 清华大学深圳研究生院 | Distributed software-defined network and method of dynamically controlling controllers therein |
| CN105024939A (en) * | 2015-06-29 | 2015-11-04 | 南京邮电大学 | OpenFlow-based distributed controller system in SDN network environment |
| CN105376297A (en) * | 2015-09-17 | 2016-03-02 | 广州大学 | SDN controller quantity adjustment and controller and switch mapping method |
| CN105553846A (en) * | 2016-02-22 | 2016-05-04 | 南京大学 | Method for distributing resources in software defined network |
| CN105577729A (en) * | 2014-10-17 | 2016-05-11 | 中兴通讯股份有限公司 | Load balancing method and device |
| CN106656846A (en) * | 2017-01-17 | 2017-05-10 | 大连理工大学 | Construction method of coordination layer in software defined network (SDN) architecture |
| CN106713177A (en) * | 2016-11-21 | 2017-05-24 | 华南理工大学 | Multi-controller wmSDN networking method |
| CN106790318A (en) * | 2015-11-19 | 2017-05-31 | 上海贝尔股份有限公司 | Network function abstract method and its device in a kind of software defined network |
| CN106850454A (en) * | 2016-04-29 | 2017-06-13 | 大连理工大学 | A kind of mixing SDN dispositions method of high flow capacity adjustment capability |
| CN106911516A (en) * | 2017-03-20 | 2017-06-30 | 重庆邮电大学 | A kind of software defined network controller dispositions method |
| CN107094111A (en) * | 2017-05-17 | 2017-08-25 | 天津大学 | Label transmission method in the deployment of software defined network controller |
| CN107682203A (en) * | 2017-10-30 | 2018-02-09 | 北京计算机技术及应用研究所 | A kind of security function dispositions method based on service chaining |
| CN108199890A (en) * | 2018-01-11 | 2018-06-22 | 重庆邮电大学 | A kind of software defined network resilient controller dispositions method |
| CN108777636A (en) * | 2018-05-25 | 2018-11-09 | 陕西师范大学 | A kind of multi-controller Optimization deployment method of robust in software defined network |
| CN109067580A (en) * | 2018-08-02 | 2018-12-21 | 北京工业大学 | A kind of adaptive software definition wireless network multi-controller dispositions method |
| CN109286528A (en) * | 2018-10-16 | 2019-01-29 | 四川长虹电器股份有限公司 | A kind of SDN network multi-controller dispositions method based on time delay |
| CN109688432A (en) * | 2017-10-18 | 2019-04-26 | 北京京东尚科信息技术有限公司 | Information transferring method, device and system |
| CN109857676A (en) * | 2018-10-23 | 2019-06-07 | 重庆第二师范学院 | The method for reducing random access expense based on Greedy heuristic strategies |
| CN110741603A (en) * | 2017-06-16 | 2020-01-31 | 思科技术公司 | Topology detector |
| CN110830570A (en) * | 2019-11-01 | 2020-02-21 | 陕西师范大学 | Resource equalization deployment method for robust finite controller in software defined network |
| CN111770515A (en) * | 2020-06-28 | 2020-10-13 | 重庆邮电大学 | SDN controller deployment method based on network cost optimization |
| CN112311584A (en) * | 2019-12-04 | 2021-02-02 | 重庆邮电大学 | Deployment method of software defined network controller |
| CN113328889A (en) * | 2021-05-31 | 2021-08-31 | 河南财政金融学院 | Distributed optimization method for control layer architecture in software defined network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103346969A (en) * | 2013-07-05 | 2013-10-09 | 中国科学院计算机网络信息中心 | Method for achieving dynamic multicast spanning tree path adjustment based on OpenFlow |
| CN103457776A (en) * | 2013-09-04 | 2013-12-18 | 杭州华三通信技术有限公司 | Method and device for dynamically deploying rendezvous points in two-way protocol independent multicast |
| US20140078988A1 (en) * | 2012-09-17 | 2014-03-20 | Nishi Kant | Method and system for elastic and resilient 3g/4g mobile packet networking for subscriber data flow using virtualized switching and forwarding |
| CN103916265A (en) * | 2013-01-04 | 2014-07-09 | 特拉博斯股份有限公司 | A method and a controller system for configuring a software-defined network |
-
2014
- 2014-07-24 CN CN201410291267.0A patent/CN104065509B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140078988A1 (en) * | 2012-09-17 | 2014-03-20 | Nishi Kant | Method and system for elastic and resilient 3g/4g mobile packet networking for subscriber data flow using virtualized switching and forwarding |
| CN103916265A (en) * | 2013-01-04 | 2014-07-09 | 特拉博斯股份有限公司 | A method and a controller system for configuring a software-defined network |
| CN103346969A (en) * | 2013-07-05 | 2013-10-09 | 中国科学院计算机网络信息中心 | Method for achieving dynamic multicast spanning tree path adjustment based on OpenFlow |
| CN103457776A (en) * | 2013-09-04 | 2013-12-18 | 杭州华三通信技术有限公司 | Method and device for dynamically deploying rendezvous points in two-way protocol independent multicast |
Non-Patent Citations (1)
| Title |
|---|
| 张铖; 曹振; 邓辉;: "《2013年中国通信学会信息通信网络技术委员会年会论文集》", 31 December 2013, 中国通信学会信息通信网络技术委员会、《电信科学》杂志 * |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105577729A (en) * | 2014-10-17 | 2016-05-11 | 中兴通讯股份有限公司 | Load balancing method and device |
| CN104618130B (en) * | 2014-12-09 | 2017-12-15 | 中国人民解放军国防科学技术大学 | A kind of minimum cost synchronous method of software definition data center network controller |
| CN104618130A (en) * | 2014-12-09 | 2015-05-13 | 中国人民解放军国防科学技术大学 | Minimum cost synchronization method of data center network controller by using software |
| CN104754053A (en) * | 2015-04-01 | 2015-07-01 | 清华大学深圳研究生院 | Distributed software-defined network and method of dynamically controlling controllers therein |
| CN104754053B (en) * | 2015-04-01 | 2017-12-19 | 清华大学深圳研究生院 | A kind of distributed software defines network and the wherein method of dynamic control controller |
| CN105024939A (en) * | 2015-06-29 | 2015-11-04 | 南京邮电大学 | OpenFlow-based distributed controller system in SDN network environment |
| CN105376297B (en) * | 2015-09-17 | 2019-01-11 | 广州大学 | Method SDN amount controller adjustment and mapped with interchanger |
| CN105376297A (en) * | 2015-09-17 | 2016-03-02 | 广州大学 | SDN controller quantity adjustment and controller and switch mapping method |
| CN106790318A (en) * | 2015-11-19 | 2017-05-31 | 上海贝尔股份有限公司 | Network function abstract method and its device in a kind of software defined network |
| CN106790318B (en) * | 2015-11-19 | 2020-12-11 | 上海诺基亚贝尔股份有限公司 | Network function abstraction method and device in software defined network |
| CN105553846A (en) * | 2016-02-22 | 2016-05-04 | 南京大学 | Method for distributing resources in software defined network |
| CN105553846B (en) * | 2016-02-22 | 2019-03-19 | 南京大学 | A method of distributing resource in software defined network |
| CN106850454A (en) * | 2016-04-29 | 2017-06-13 | 大连理工大学 | A kind of mixing SDN dispositions method of high flow capacity adjustment capability |
| CN106850454B (en) * | 2016-04-29 | 2020-07-14 | 大连理工大学 | Hybrid SDN network deployment method with high flow adjustment capability |
| CN106713177A (en) * | 2016-11-21 | 2017-05-24 | 华南理工大学 | Multi-controller wmSDN networking method |
| CN106713177B (en) * | 2016-11-21 | 2019-11-15 | 华南理工大学 | A kind of wmSDN network-building method of multi-controller |
| CN106656846A (en) * | 2017-01-17 | 2017-05-10 | 大连理工大学 | Construction method of coordination layer in software defined network (SDN) architecture |
| CN106656846B (en) * | 2017-01-17 | 2019-07-16 | 大连理工大学 | The construction method of cooperation layer in a kind of SDN architectural framework |
| CN106911516A (en) * | 2017-03-20 | 2017-06-30 | 重庆邮电大学 | A kind of software defined network controller dispositions method |
| CN106911516B (en) * | 2017-03-20 | 2019-09-24 | 重庆邮电大学 | A kind of software defined network controller portion arranging method |
| CN107094111A (en) * | 2017-05-17 | 2017-08-25 | 天津大学 | Label transmission method in the deployment of software defined network controller |
| CN107094111B (en) * | 2017-05-17 | 2020-08-18 | 天津大学 | Label transfer method in software defined network controller deployment |
| CN110741603A (en) * | 2017-06-16 | 2020-01-31 | 思科技术公司 | Topology detector |
| CN110741603B (en) * | 2017-06-16 | 2022-09-02 | 思科技术公司 | Topology detector |
| US11463316B2 (en) | 2017-06-16 | 2022-10-04 | Cisco Technology, Inc. | Topology explorer |
| CN109688432B (en) * | 2017-10-18 | 2022-12-27 | 北京京东尚科信息技术有限公司 | Information transmission method, device and system |
| CN109688432A (en) * | 2017-10-18 | 2019-04-26 | 北京京东尚科信息技术有限公司 | Information transferring method, device and system |
| CN107682203A (en) * | 2017-10-30 | 2018-02-09 | 北京计算机技术及应用研究所 | A kind of security function dispositions method based on service chaining |
| CN107682203B (en) * | 2017-10-30 | 2020-09-08 | 北京计算机技术及应用研究所 | Security function deployment method based on service chain |
| CN108199890A (en) * | 2018-01-11 | 2018-06-22 | 重庆邮电大学 | A kind of software defined network resilient controller dispositions method |
| CN108777636A (en) * | 2018-05-25 | 2018-11-09 | 陕西师范大学 | A kind of multi-controller Optimization deployment method of robust in software defined network |
| CN109067580B (en) * | 2018-08-02 | 2021-01-08 | 北京工业大学 | Self-adaptive software-defined wireless network multi-controller deployment method |
| CN109067580A (en) * | 2018-08-02 | 2018-12-21 | 北京工业大学 | A kind of adaptive software definition wireless network multi-controller dispositions method |
| CN109286528A (en) * | 2018-10-16 | 2019-01-29 | 四川长虹电器股份有限公司 | A kind of SDN network multi-controller dispositions method based on time delay |
| CN109286528B (en) * | 2018-10-16 | 2020-11-03 | 四川长虹电器股份有限公司 | SDN network multi-controller deployment method based on time delay |
| CN109857676A (en) * | 2018-10-23 | 2019-06-07 | 重庆第二师范学院 | The method for reducing random access expense based on Greedy heuristic strategies |
| CN110830570B (en) * | 2019-11-01 | 2022-02-01 | 陕西师范大学 | Resource equalization deployment method for robust finite controller in software defined network |
| CN110830570A (en) * | 2019-11-01 | 2020-02-21 | 陕西师范大学 | Resource equalization deployment method for robust finite controller in software defined network |
| CN112311584A (en) * | 2019-12-04 | 2021-02-02 | 重庆邮电大学 | Deployment method of software defined network controller |
| CN112311584B (en) * | 2019-12-04 | 2023-09-26 | 重庆邮电大学 | Deployment method of software defined network controller |
| CN111770515B (en) * | 2020-06-28 | 2022-03-29 | 重庆邮电大学 | SDN controller deployment method based on network cost optimization |
| CN111770515A (en) * | 2020-06-28 | 2020-10-13 | 重庆邮电大学 | SDN controller deployment method based on network cost optimization |
| CN113328889A (en) * | 2021-05-31 | 2021-08-31 | 河南财政金融学院 | Distributed optimization method for control layer architecture in software defined network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104065509B (en) | 2017-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104065509A (en) | SDN multi-controller deployment method for reducing management load overhead | |
| Hu et al. | Multi-controller based software-defined networking: A survey | |
| Pashkov et al. | Controller failover for SDN enterprise networks | |
| CN103888360B (en) | Method for integrating covering method to obtain service node in SDN based on greedy algorithm | |
| CN108400890B (en) | Software defined network multi-controller deployment method | |
| Zhang et al. | Cascading failures in interdependent systems under a flow redistribution model | |
| Zhang et al. | Joint NFV placement and routing for multicast service on SDN | |
| CN103093276B (en) | Urban power grid risk assessment method | |
| Aydeger et al. | SDN-based resilience for smart grid communications | |
| CN109066654B (en) | Power distribution network maximum power supply capacity evaluation method based on mixed integer linear programming | |
| CN111244919B (en) | Distribution network topology self-adaptive identification method suitable for intelligent distributed FA | |
| CN102104542A (en) | Method for realizing service group router under forwarding and controlling separated network architecture | |
| Liu et al. | On optimal hierarchical SDN | |
| CN105704180B (en) | The configuration method and its system of data center network | |
| CN114123186B (en) | Self-healing optimization control method, system, terminal and medium based on intelligent power distribution network | |
| CN104362615A (en) | Non-fault segment power supply recovery method based on information platform | |
| CN104410529B (en) | A kind of minimum vertex-covering dispositions method of software definition data center network controller | |
| CN110958297A (en) | Data migration method and system | |
| CN109687432A (en) | A kind of distribution terminal addressing method for shaping and system based on multistage collaboration | |
| Pashkov et al. | On high availability distributed control plane for software-defined networks | |
| CN102355370B (en) | Method for Ethernet board-level protection, device and system | |
| Xu et al. | A management model for SDN-based data center networks | |
| CN108199890B (en) | A kind of software defined network resilient controller dispositions method | |
| CN109902361B (en) | Logic operator-based power distribution network switch optimal configuration method | |
| Oleiwi et al. | Design and Implementation of Distributed Controller Clustering for Solving the Issue of Single Failure in SDN Networks. |
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 |