CN108900330A - A kind of multi-controller dispositions method defining network suitable for large scope software - Google Patents
A kind of multi-controller dispositions method defining network suitable for large scope software Download PDFInfo
- Publication number
- CN108900330A CN108900330A CN201810659538.1A CN201810659538A CN108900330A CN 108900330 A CN108900330 A CN 108900330A CN 201810659538 A CN201810659538 A CN 201810659538A CN 108900330 A CN108900330 A CN 108900330A
- Authority
- CN
- China
- Prior art keywords
- parent
- controller
- network
- solution
- filial generation
- 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
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0659—Management of faults, events, alarms or notifications using network fault recovery by isolating or reconfiguring faulty entities
- H04L41/0661—Management of faults, events, alarms or notifications using network fault recovery by isolating or reconfiguring faulty entities by reconfiguring faulty entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a kind of multi-controller dispositions methods that network is defined suitable for large scope software, use intersection, variation subalgorithm to change the quantity of controller, guarantee that solution concentrates amount controller to have diversity;And genetic optimization is carried out to multiple target based on Pareto optimality principle, the network given for one, it can be concluded that one group of Pareto optimal solution, characteristic based on Pareto sequence, it can guarantee all solutions of solution concentration in two performance yardsticks of network average delay or controller load balancing, at least one performance yardstick has preferable performance, to guarantee that network has preferable performance in terms of delay, load balancing;Meanwhile in network failure, Dynamical Deployment controller may be implemented;Under a part of network failure situation, the performance of network can be effectively ensured.
Description
Technical field
The invention belongs to multi-controller deployment techniques field more particularly to a kind of network is defined suitable for large scope software
Multi-controller dispositions method.
Background technique
In recent years, with the development of network technology, a kind of uncoupled network architecture --- software defined network
(Software Defined Network, SDN) is suggested.With deep and its technology the development studied SDN, SDN skill
Art is just constantly applied in multiple network field.With development and expansion that SDN is applied, the scale of SDN network also increasingly expands.
When SDN is applied in large scale network, single controller can not realize the whole network flow and efficiently grasp and control.It is based on
The considerations of controlling plane performance, network performance etc., needs to dispose multiple controllers in a network, to reach reduction and balance
The load of controller, improves the purpose of network robustness at the delay for optimizing network entirety.
Currently to the research and application of multi-controller deployment, analyzed primarily directed to single performance scale, not yet
Research simultaneously optimizes the problem from multiple angles;In addition, the analysis for network failure situation, is mainly expected from reduction
Failure rate accounts for, and the research in terms of Dynamical Deployment is less.Therefore, towards extensive SDN network, efficient more controls are designed
Device Deployment Algorithm processed has important application value.
Multi-controller deployment issue (CCP) is problem in need of consideration when disposing multiple SDN controllers in the wide area network,
Two sub-problems are proposed, i.e.,:
1) it needs to dispose how many a controllers in a network?
2) controller should be deployed in which position of network?
Research in response to the above problems usually considers following performance yardstick, i.e.,:
1) controller is to the time delay of inter-exchange, including mean time extends to maximum delay;
2) time delay between controller, including mean time extend to maximum delay;
3) load of controller, including a controller load balance feelings between receptible maximum load and controller
Condition;
4) variation and correspondence of network performance when the reliability of network, i.e. network link, node or controller node fail
Solution.
In solution of the prior art to multi-controller problem, mostly it is with network delay, load balancing or amount controller
Single optimization aim, the problem using other performance yardsticks as constraint solving, the solution obtained can only guarantee that optimization aim has preferably
Performance, it cannot be guaranteed that the performance of other performance yardsticks.
In addition, in clustering algorithm, it usually needs the quantity of prescription controller is solved, and in primary solve, can be obtained
More excellent solution in prescription controller quantity out cannot obtain influence of the different amount controllers for network performance, no
It can determine that the quantity for being suitble to the controller of deployment in network.
Other than considering conventional network delay, load-balancing performance scale, also there is part research to consider network strong
Strong this performance yardstick of property.In order to maintain network robustness, there are two types of different research directions.One is solving CPP problem
When using the expection failure rate of link between controller and interchanger as optimization aim, guarantee network by reducing expected failure rate
Robustness, the research contents of the direction is more at present, but when network failure, cannot achieve the dynamic state part of controller
Administration.The second is by design Dynamical Deployment scheme, when network failure, simultaneously using Dynamical Deployment scheme rapid solving CPP problem
Deployment controller improves the robustness of network to cope with network failure, and the researchers such as Bari M and Roy A propose a dynamic
Deployment scheme, the research contents of the direction is less at present.
Summary of the invention
Goal of the invention of the invention is:In order to solve problem above existing in the prior art, the invention proposes one kind
Multi-controller dispositions method suitable for extensive SDN network.
The technical scheme is that:A kind of multi-controller dispositions method suitable for extensive SDN network, including it is following
Step:
A, network G, Initial controller quantity k are obtained0, disaggregation size M, maximum number of iterations Iter;
B, judge whether network G breaks down;If so, using the disaggregation obtained according to network G as parent P;If it is not, then
According to Initial controller quantity k0K is selected in network G at random0A controller, the successively nearest controller of selected distance interchanger
Interchanger is controlled, M solution is obtained, as parent P;
C, two solutions are randomly choosed in parent P using crossover algorithm and carry out crossover operation, obtain a filial generation;Repeat M
M solution is obtained after secondary, as filial generation C1;
D, a solution is randomly choosed in parent P using mutation algorithm and carries out mutation operation, obtains two filial generations;Repeat M
2M solution is obtained after secondary, as filial generation C2;
E, using sort algorithm to parent P, filial generation C1, filial generation C2Pareto sequence is carried out, by M solution of highest priority
As new parent P;
F, judge whether the number of iterations is greater than maximum number of iterations Iter;If so, obtain comprising location of controls and with
The disaggregation of the deployment scheme of mapping relations between its interchanger controlled;If it is not, then return step C.
Further, two solutions are randomly choosed in parent P using crossover algorithm in step C and carries out crossover operation, obtained
One filial generation, specifically include it is following step by step:
C1, two parent solution p are randomly choosed in parent Pa,pb, according to its corresponding controller set Ca,Cb, random to cut
Take controller set Ca,CbA part of C of union0, so that | C0|=min | Ca|,|Cb|};
C2, according to controller set C0, the nearest controller of selected distance interchanger controls interchanger, obtains a solution,
As filial generation.
Further, a solution is randomly choosed in parent P using mutation algorithm in step D and carries out mutation operation, obtained
Two filial generations, specifically include it is following step by step:
D1, a parent solution p is randomly choosed in parent Pl, according to its corresponding controller set Cl, randomly choose one
Controller set ClMiddle controller ck, in controller set ClMiddle deletion controller ck, obtain new controller set Cc;
D2, a control network node is randomly choosed and not in controller set ClIn controller, in controller set Cl
Middle increase controller, obtains new controller set Cd;
D3, according to controller set Cc,Cd, the nearest controller of selected distance interchanger controls interchanger, obtains two
Solution, as two filial generations.
Further, step E is using sort algorithm to parent P, filial generation C1, filial generation C2Pareto sequence is carried out, by priority
Highest M solution as new parent P, specifically include it is following step by step:
E1, by parent P, filial generation C1, filial generation C2Union as parent P0If parent P0={ p1,p2...pq, parentParent
E2, parent P is successively selected0In two parent solution pi,pj, i ≠ j;If AvgL (pi) < AvgL (pj) and Imblc
(pi)≯Imblc(pj) or AcgL (pi)≯AvgL(pj) and Imblc (pi) < Imblc (pj), then parent solution pjBy parent solution pi
It dominates, otherwise parent solution piBy parent solution pjIt dominates;The parent solution dominated is put into parent P1;Wherein AvgL (pi),AvgL
(pj) it is illustrated respectively in deployment scheme pi,pjIn the case where network average delay, Imblc (pi),Imblc(pj) be illustrated respectively in
Deployment scheme pi,pjIn the case where laod unbalance scale between controller;
E3, judge each parent solution piWhether with any one parent solution pjDominate and has compared;If so, enabling newly
Parent P=P ∪ (P0-P1);If it is not, then return step E2;
E4, judgement | P | whether it is greater than disaggregation size M;If so, obtaining new parent P;If it is not, then step E2 is obtained
Parent P1As new parent P0, and reset parentReturn step E2.
The beneficial effects of the invention are as follows:The present invention is based on Pareto optimality principles to carry out genetic optimization to multiple target, obtains
A certain number of Pareto optimality deployment schemes guarantee that network has preferable performance in terms of delay, load balancing;Together
When, in network failure, Dynamical Deployment controller may be implemented;Under a part of network failure situation, can effectively it protect
Demonstrate,prove the performance of network.
Detailed description of the invention
Fig. 1 is the flow diagram of the multi-controller dispositions method suitable for extensive SDN network of the invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, the process for the multi-controller dispositions method suitable for extensive SDN network of the invention is illustrated
Figure.A kind of multi-controller dispositions method suitable for extensive SDN network of the present invention, includes the following steps:
A, network G, Initial controller quantity k are obtained0, disaggregation size M, maximum number of iterations Iter;
B, judge whether network G breaks down;If so, using the disaggregation obtained according to network G as parent P;If it is not, then
According to Initial controller quantity k0K is selected in network G at random0A controller, the successively nearest controller of selected distance interchanger
Interchanger is controlled, M solution is obtained, as parent P;
C, two solutions are randomly choosed in parent P using crossover algorithm and carry out crossover operation, obtain a filial generation;Repeat M
M solution is obtained after secondary, as filial generation C1;
D, a solution is randomly choosed in parent P using mutation algorithm and carries out mutation operation, obtains two filial generations;Repeat M
2M solution is obtained after secondary, as filial generation C2;
E, using sort algorithm to parent P, filial generation C1, filial generation C2Pareto sequence is carried out, by M solution of highest priority
As new parent P;
F, judge whether the number of iterations is greater than maximum number of iterations Iter;If so, obtain comprising location of controls and with
The disaggregation of the deployment scheme of mapping relations between its interchanger controlled;If it is not, then return step C.
The present invention extends to two targets of controller load balancing to the network mean time in CPP problem and optimizes, and is based on
The Multi-objective genetic algorithm of Pareto optimality can effectively optimize network mean time and extend to two individual character of controller load balancing
Energy scale, while controller Dynamical Deployment can be carried out to a part of network failure situation, it guarantee the overall performance of network.
In an alternate embodiment of the present invention where, above-mentioned steps A obtains network G, Initial controller quantity k0, disaggregation it is big
Small M, maximum number of iterations Iter;Wherein, network G=(V, E), V indicate that network node, E indicate link.
In an alternate embodiment of the present invention where, above-mentioned steps B judges whether network G breaks down;If so, will not
It is parent P that the network G to break down, which adopts the disaggregation being obtained by the present invention to make Res (G),;If it is not, then according to initial control
Device quantity k0K is selected in network G at random0A controller, successively the nearest controller of selected distance interchanger controls interchanger,
M solution is obtained, as parent P;Here interchanger to the distance between controller can according to interchanger between controller away from
From Dij(G) it obtains.Wherein Dij(G) d of each node to other nodes in expression network GijkstraDistance matrix, matrix n*n
Square matrix, n be network G interior joint quantity, dijIndicate node i, the d between jijkstraDistance.
In an alternate embodiment of the present invention where, above-mentioned steps C randomly chooses two using crossover algorithm in parent P
Solution carry out crossover operation, obtain a filial generation, specifically include it is following step by step:
C1, two parent solution p are randomly choosed in parent Pa,pb, according to its corresponding controller set Ca,Cb, i.e.,Random interception controller set Ca,CbUnion Ca∪CbA part of C0, so that | C0|=min | Ca|,
|Cb|};
C2, according to controller set C0, the nearest controller of selected distance interchanger controls interchanger, obtains a solution,
As filial generation.
Here parent P (Placement) indicates the solution obtained using method of the invention to CPP problem solving, includes control
Mapping relations between the set and controller and interchanger of device processed.Controller set C (Controllers) is indicated in network G
The position of deployment controller,C={ c1,c2...ck, c1,c2...ckIndicate different location of controls.
M solution is obtained after repeating the above steps C1-C2M times, as filial generation C1。
In an alternate embodiment of the present invention where, above-mentioned steps D randomly chooses one using mutation algorithm in parent P
Solution carry out mutation operation, obtain two filial generations, specifically include it is following step by step:
D1, a parent solution p is randomly choosed in parent Pl, according to its corresponding controller set Cl, randomly choose one
Controller set ClMiddle controller ck, in controller set ClMiddle deletion controller ck, obtain new controller set Cc;
D2, a control network node is randomly choosed and not in controller set ClIn controller, in controller set Cl
Middle increase controller, obtains new controller set Cd;
D3, according to controller set Cc,Cd, the nearest controller of selected distance interchanger controls interchanger, obtains two
Solution, as two filial generations.
2M solution is obtained after repeating the above steps D1-D3M times, as filial generation C2。
In an alternate embodiment of the present invention where, above-mentioned steps E is using sort algorithm to parent P, filial generation C1, filial generation C2
Carry out Pareto sequence, M of highest priority solved as new parent P, specifically include it is following step by step:
E1, by parent P, filial generation C1, filial generation C2Union as parent P0, i.e. P0=P ∪ C1∪C2If parent P0={ p1,
p2...pq, parentParent
E2, parent P is successively selected0In two parent solution pi,pj, i ≠ j;If AvgL (pi) < AvgL (pj) and Imblc
(pi)≯Imblc(pj) or AcgL (pi)≯AvgL(pj) and Imblc (pi) < Imblc (pj), then parent solution pjBy parent solution pi
It dominates, otherwise parent solution piBy parent solution pjIt dominates;The parent solution dominated is put into parent P1;
Wherein AvgL (pi),AvgL(pj) it is illustrated respectively in deployment scheme pi,pjIn the case where network average delay, table
It is shown as
v∈ckIndicate node v by controller ckIt is controlled;
Imblc(pi),Imblc(pj) it is illustrated respectively in deployment scheme pi,pjIn the case where load between controller it is uneven
Weigh scale, is expressed as
Indicate controller ciThe quantity of controlled interchanger;
E3, judge each parent solution piWhether with any one parent solution pjDominate and has compared;If so, enabling newly
Parent P=P ∪ (P0-P1);If it is not, then return step E2;
E4, judgement | P | whether it is greater than disaggregation size M;If so, obtaining new parent P;If it is not, then step E2 is obtained
Parent P1As new parent P0, and reset parentReturn step E2.
The present invention network given for one, it can be deduced that one group of Pareto optimal solution, the spy based on Pareto sequence
Property, it is ensured that all solutions of concentration are solved in two performance yardsticks of network average delay or controller load balancing, at least one
A performance yardstick has preferable performance;With the increase of disaggregation, it is ensured that solution, which is concentrated, will appear so that two performance rulers
Degree has the solution of good behaviour;Meanwhile intersection, variation subalgorithm change the quantity of controller, guarantee solution Centralized Controller number
Measurer has diversity;It is analyzed by the amount controller to deployment scheme in disaggregation, it can be deduced that different amount controllers
Deployment scheme solution concentrate the frequency of occurrences.It is apparent that for the amount controller that some is determined, the frequency of appearance
Height illustrates the deployment controller in the case where quantity, is easily guaranteed that network has good performance;If its frequency occurred
It is low, illustrate deployment controller in the case of the quantity, it is difficult to ensure that network has good performance, should select more or less
Controller disposed.
When network failure, it is divided into two kinds of situations.One is when the lesser nodes break down of degree of communication in network
When, it is at this time basic parent with Res (G) that big change, which will not occur, for the structure of network entirety, can using method of the invention
Iteratively faster obtains the deployment scheme being adapted under network failure situation.The second is when the biggish node generation of degree of communication in network
When failure, network overall structure has occurred and that larger change, can use such as k-center classic algorithm, realizes dynamic in time
Deployment.
In conclusion the present invention can optimize multiple target capabilities scales simultaneously, guarantee the performance of network entirety;Together
When, influence of the different amount controllers for network performance can be embodied, determines and is suitble to the amount controller of deployment in a network;
In addition, can be realized quick Dynamical Deployment to subnetwork fault condition, guarantee the robustness of network.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.This field
Those of ordinary skill disclosed the technical disclosures can make according to the present invention and various not depart from the other each of essence of the invention
The specific variations and combinations of kind, these variations and combinations are still within the scope of the present invention.
Claims (4)
1. a kind of multi-controller dispositions method for defining network suitable for large scope software, which is characterized in that include the following steps:
A, network G, Initial controller quantity k are obtained0, disaggregation size M, maximum number of iterations Iter;
B, judge whether network G breaks down;If so, using the disaggregation obtained according to network G as parent P;If it is not, then basis
Initial controller quantity k0K is selected in network G at random0A controller, the successively nearest controller control of selected distance interchanger
Interchanger obtains M solution, as parent P;
C, two solutions are randomly choosed in parent P using crossover algorithm and carry out crossover operation, obtain a filial generation;After repeating M times
M solution is obtained, as filial generation C1;
D, a solution is randomly choosed in parent P using mutation algorithm and carries out mutation operation, obtains two filial generations;After repeating M times
2M solution is obtained, as filial generation C2;
E, using sort algorithm to parent P, filial generation C1, filial generation C2Pareto sequence is carried out, by M solution conduct of highest priority
New parent P;
F, judge whether the number of iterations is greater than maximum number of iterations Iter;If so, obtaining comprising location of controls and being controlled with it
The disaggregation of the deployment scheme of mapping relations between the interchanger of system;If it is not, then return step C.
2. the multi-controller dispositions method of network is defined suitable for large scope software as described in claim 1, which is characterized in that
Two solutions are randomly choosed in parent P using crossover algorithm in step C and carry out crossover operation, a filial generation is obtained, specifically includes
Below step by step:
C1, two parent solution p are randomly choosed in parent Pa,pb, according to its corresponding controller set Ca,Cb, random interception control
Device set C processeda,CbA part of C of union0, so that | C0|=min | Ca|,|Cb|};
C2, according to controller set C0, the nearest controller of selected distance interchanger controls interchanger, a solution obtained, as son
Generation.
3. the multi-controller dispositions method of network is defined suitable for large scope software as described in claim 1, which is characterized in that
A solution is randomly choosed in parent P using mutation algorithm in step D and carries out mutation operation, two filial generations is obtained, specifically includes
Below step by step:
D1, a parent solution p is randomly choosed in parent Pl, according to its corresponding controller set Cl, randomly choose a control
Device set ClMiddle controller ck, in controller set ClMiddle deletion controller ck, obtain new controller set Cc;
D2, a control network node is randomly choosed and not in controller set ClIn controller, in controller set ClMiddle increasing
Add the controller, obtains new controller set Cd;
D3, according to controller set Cc,Cd, the nearest controller of selected distance interchanger controls interchanger, obtains two solutions, make
For two filial generations.
4. the multi-controller dispositions method of network is defined suitable for large scope software as described in claim 1, which is characterized in that
Step E is using sort algorithm to parent P, filial generation C1, filial generation C2Pareto sequence is carried out, by M solution of highest priority as new
Parent P, specifically include it is following step by step:
E1, by parent P, filial generation C1, filial generation C2Union as parent P0If parent P0={ p1,p2...pq, parent
Parent
E2, parent P is successively selected0In two parent solution pi,pj, i ≠ j;If AvgL (pi) < AvgL (pj) and Imblc (pi)≯
Imblc(pj) or AcgL (pi)≯AvgL(pj) and Imblc (pi) < Imblc (pj), then parent solution pjBy parent solution piIt dominates,
Otherwise parent solution piBy parent solution pjIt dominates;The parent solution dominated is put into parent P1;Wherein AvgL (pi),AvgL(pj) respectively
It indicates in deployment scheme pi,pjIn the case where network average delay, Imblc (pi),Imblc(pj) it is illustrated respectively in deployment side
Case pi,pjIn the case where laod unbalance scale between controller;
E3, judge each parent solution piWhether with any one parent solution pjDominate and has compared;If so, enabling new parent P
=P ∪ (P0-P1);If it is not, then return step E2;
E4, judgement | P | whether it is greater than disaggregation size M;If so, obtaining new parent P;If it is not, the father for then obtaining step E2
For P1As new parent P0, and reset parentReturn step E2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810659538.1A CN108900330B (en) | 2018-06-25 | 2018-06-25 | Multi-controller deployment method suitable for large-scale software defined network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810659538.1A CN108900330B (en) | 2018-06-25 | 2018-06-25 | Multi-controller deployment method suitable for large-scale software defined network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108900330A true CN108900330A (en) | 2018-11-27 |
CN108900330B CN108900330B (en) | 2021-04-27 |
Family
ID=64346086
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810659538.1A Active CN108900330B (en) | 2018-06-25 | 2018-06-25 | Multi-controller deployment method suitable for large-scale software defined network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108900330B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110149226A (en) * | 2019-05-14 | 2019-08-20 | 电子科技大学中山学院 | Improved particle swarm algorithm for multi-controller deployment problem in software defined network |
CN110390395A (en) * | 2019-07-15 | 2019-10-29 | 电子科技大学中山学院 | Improved genetic algorithm suitable for self-adaptive mutation crossing of SDN multi-controller deployment problem |
CN112217666A (en) * | 2020-09-29 | 2021-01-12 | 中国银行股份有限公司 | Software defined network optimization method and device |
CN112511453A (en) * | 2020-11-19 | 2021-03-16 | 中移(杭州)信息技术有限公司 | SDN controller deployment method, device and storage medium |
CN114679730A (en) * | 2022-03-15 | 2022-06-28 | 国网智能电网研究院有限公司 | Software defined network switching node layout method and device |
US20230205509A1 (en) * | 2021-12-29 | 2023-06-29 | Microsoft Technology Licensing, Llc | Smart deployment using graph optimization |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104579454A (en) * | 2015-01-17 | 2015-04-29 | 浙江大学 | Multi-objective optimization satellite flow control method based on software defined network |
CN107204880A (en) * | 2017-06-06 | 2017-09-26 | 重庆邮电大学 | A kind of key-course dispositions method based on software defined network framework |
CN108040012A (en) * | 2017-12-05 | 2018-05-15 | 西南交通大学 | Multi-object multicast routed path construction method in the SDN network that must be searched for based on longicorn |
-
2018
- 2018-06-25 CN CN201810659538.1A patent/CN108900330B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104579454A (en) * | 2015-01-17 | 2015-04-29 | 浙江大学 | Multi-objective optimization satellite flow control method based on software defined network |
CN107204880A (en) * | 2017-06-06 | 2017-09-26 | 重庆邮电大学 | A kind of key-course dispositions method based on software defined network framework |
CN108040012A (en) * | 2017-12-05 | 2018-05-15 | 西南交通大学 | Multi-object multicast routed path construction method in the SDN network that must be searched for based on longicorn |
Non-Patent Citations (3)
Title |
---|
KALYANMOY DEB等: "A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II", 《IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION》 * |
VAHID AHMADI等: "A Hybrid NSGA-II for Solving MultiObjective Controller Placement in SDN", 《2015 2ND INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED ENGINEERING AND INNOVATION (KBEI)》 * |
刘必果等: "基于多目标优化的软件定义网络负载均衡方案", 《计算机应用》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110149226A (en) * | 2019-05-14 | 2019-08-20 | 电子科技大学中山学院 | Improved particle swarm algorithm for multi-controller deployment problem in software defined network |
CN110149226B (en) * | 2019-05-14 | 2022-01-28 | 电子科技大学中山学院 | Improved particle swarm algorithm for multi-controller deployment problem in software defined network |
CN110390395A (en) * | 2019-07-15 | 2019-10-29 | 电子科技大学中山学院 | Improved genetic algorithm suitable for self-adaptive mutation crossing of SDN multi-controller deployment problem |
CN112217666A (en) * | 2020-09-29 | 2021-01-12 | 中国银行股份有限公司 | Software defined network optimization method and device |
CN112217666B (en) * | 2020-09-29 | 2022-02-25 | 中国银行股份有限公司 | Software defined network optimization method and device |
CN112511453A (en) * | 2020-11-19 | 2021-03-16 | 中移(杭州)信息技术有限公司 | SDN controller deployment method, device and storage medium |
US20230205509A1 (en) * | 2021-12-29 | 2023-06-29 | Microsoft Technology Licensing, Llc | Smart deployment using graph optimization |
US11861352B2 (en) * | 2021-12-29 | 2024-01-02 | Microsoft Technology Licensing, Llc | Smart deployment using graph optimization |
CN114679730A (en) * | 2022-03-15 | 2022-06-28 | 国网智能电网研究院有限公司 | Software defined network switching node layout method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108900330B (en) | 2021-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108900330A (en) | A kind of multi-controller dispositions method defining network suitable for large scope software | |
Xu et al. | Novel multiagent based load restoration algorithm for microgrids | |
CN105553869B (en) | A kind of risk balance method and system of power telecom network | |
US8606372B1 (en) | System and method of discovering and prioritizing loads in an isolated power grid with dynamic distributed control | |
CN105932775B (en) | The analysis method that a kind of information system influences micro-capacitance sensor operational reliability | |
CN109146173A (en) | Space domain sector cascade failure survivability modeling and optimization method | |
JPWO2019012627A1 (en) | Network control system, method and program | |
CN106651000B (en) | Black-start partitioning method based on semi-supervised spectral clustering | |
Massim et al. | Efficient immune algorithm for optimal allocations in series-parallel continuous manufacturing systems | |
CN110556877A (en) | distribution network distributed energy storage aggregation control method considering SOC balance | |
CN106067074B (en) | A method of network system robustness is promoted by optimizing the switch state of link | |
CN109286528A (en) | A kind of SDN network multi-controller dispositions method based on time delay | |
CN109491238A (en) | Subway platform accelerator control system controller redundancy approach | |
Celik et al. | DDDAMS-based dispatch control in power networks | |
CN106483393B (en) | Configuration method and system are unified in harmonic wave and voltage dip monitoring point | |
CN110165681A (en) | Consider the voltage partition method and pilot bus selection method of Reactive Power Margin | |
CN108830451A (en) | A kind of the convergence potential evaluation method and system of user side distributed energy storage | |
CN109861306A (en) | Power transmission network power generation dispatching method and device | |
CN109347657A (en) | The virtual data domain construction method of scientific and technological business is supported under SDN mode | |
CN111882125A (en) | Electric power information physical system cascading failure prediction method based on risk element theory | |
CN106059918A (en) | Energy internet control layered architecture based on SDN (Software Defined Networking) and scheduling method | |
Mangaiyarkarasi et al. | Optimal location and sizing of multiple static var compensators for voltage risk assessment using hybrid PSO-GSA algorithm | |
CN109004639A (en) | Power distribution network switched-mode power supply recovery policy optimization method based on complete distributed algorithm | |
CN110390395A (en) | Improved genetic algorithm suitable for self-adaptive mutation crossing of SDN multi-controller deployment problem | |
CN111953003B (en) | Site selection and capacity calculation method of flexible direct current access point |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |