CN107204874A - Ensure the minimum SDN multi-controller dispositions method of time delay - Google Patents
Ensure the minimum SDN multi-controller dispositions method of time delay Download PDFInfo
- Publication number
- CN107204874A CN107204874A CN201710322262.3A CN201710322262A CN107204874A CN 107204874 A CN107204874 A CN 107204874A CN 201710322262 A CN201710322262 A CN 201710322262A CN 107204874 A CN107204874 A CN 107204874A
- Authority
- CN
- China
- Prior art keywords
- time delay
- point
- controller
- interchanger
- node
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- 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
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
-
- 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
- H04L41/12—Discovery or management of network topologies
Abstract
The invention belongs to network technique field, to propose a kind of SDN controller Deployment Algorithms for ensureing time delay, it is ensured that the time delay of whole network is minimum.The present invention, ensure the minimum SDN multi-controller dispositions method of time delay, network delay and topological structure are analyzed first, each interchanger is calculated to the time delay for being left all interchangers, then arbitrarily one interchanger of selection is used as initial controller deployment point, the deployed position is updated to a new interchanger further according to K medoids algorithms, it is ensured that minimum to remaining all interchanger time delays;The interchanger in whole network is redistributed according to time delay as another new controller deployment point to the maximum interchanger of controller deployment point time delay in reselection whole network, each controller deployment point is then updated by K medoids algorithms;Said process is repeated always until there is K controller deployment point.Present invention is mainly applied to network control and management occasion.
Description
Technical field
It it is a kind of novel be used for soft the invention belongs to next generation network control and management and software defined network field
Part defines network rationalization partition and deployment controller algorithm.It is specifically related to a kind of to ensure time delay in the case of optimal to software
Define network full wafer network and carry out subregion, a kind of algorithm of line control unit of going forward side by side deployment.Concretely relate to ensure time delay minimum
SDN multi-controller Deployment Algorithm.
Background technology
In recent years, major operators, equipment vendor and large-scale government and enterprises user are increasing to the input cost of internet, with this
Meanwhile, the development speed of social networks, Internet of Things etc. is speeded, and data volume blast increases, and these all cause conventional internet framework
The problem of exposing more and more.
Software defined network is a kind of emerging network architecture, and its main thought is by the control of data and forwarding point
Leave and, so as to realize centralized Control.Control function is realized that a controller controls many forwarding units, forwarding by controller
Equipment realizes the forwarding of data according to the rule that controller is issued.
SDN allows forwarding of the manager to data to carry out fine control, while interchanger also can be made simple
With it is cheap, interchanger only needs to realize data forwarding function, and the control task such as route, security strategy is responsible for by controller.SDN nets
Another benefit that network is brought is exactly to be easy to extension, because all control logics are transferred on controller, as long as upgrading control
The software of device processed, whole network just can support corresponding new features.But, because controller has undertaken the control work of whole network
Make, the experiment communicated between the disposal ability and controller and interchanger of controller has important to the performance of whole network
Influence.For large-scale network, the distribution for carrying out flow table by separate unit controller can not be competent at the demand of all interchangers, at this moment need
Multiple controllers are used to share the communication pressure of whole system jointly.Therefore, how whole SDN is reasonably controlled
Device is disposed, and has both ensured the load balancing of each controller, be can guarantee that average delay is minimum again, is that one of SDN is very important
Research direction.
Document [1] proposes the deployment issue of controller earliest, and measurement index is used as using average delay and maximum delay
Carry out the deployment issue of analyzer-controller, and it is solved using greedy algorithm.Document [2] proposes K-critical algorithms, root
Amount controller and deployed position needed for being calculated according to maximum allowable delay, but the document is also without the negative of consideration controller
Carry equalization problem.Controller deployment issue of the document [3] in this WAN is solved using spectral clustering.Document [4] is used
Particle cluster algorithm solves SDN controller deployment issue.
[1]HELLER B,SHERWOOD R,MCKEOWN N.The controller placement problem
[C]//Proceedings of the First Workshop on Hot Topics in Software Defined
Networks. ACM,2012:7-12
[2] Y,-PASTOR C,GARCIA AJ.On the controller
placement for designing a distributed SDN control layer[C]//Networking
Conference,2014IFIP.IEEE,2014:1-9.
[3]Xiao P,Qu W,Qi H,et al.The SDN controller placement problem for
WAN[C]//Ieee/cic International Conference on Communications in China.IEEE,
2014:220-224.
[4]GAO C,WANG H,ZHU F,et al.A particle swarm optimization algorithm
for controller placement problem in software defined network[C]//
International Conference on Algorithms and Architectures for Parallel
Processing.Springer International Publishing,2015:44-54。
The content of the invention
To overcome the deficiencies in the prior art, the present invention is directed to propose a kind of SDN controller Deployment Algorithms for ensureing time delay, are protected
The time delay for demonstrate,proving whole network is minimum.The technical solution adopted by the present invention is, it is ensured that the minimum SDN multi-controller deployment of time delay
Method, is analyzed network delay and topological structure first, each interchanger of calculating to the time delay for being left all interchangers, so
Arbitrarily one interchanger of selection updates the deployed position as initial controller deployment point further according to K-medoids algorithms afterwards
To a new interchanger, it is ensured that minimum to remaining all interchanger time delays;Disposed in reselection whole network to controller
The maximum interchanger of point time delay as another new controller deployment point, according to time delay to the interchanger in whole network again
Distribution, then updates each controller deployment point by K-medoids algorithms;Said process is repeated always until there is K control
Device deployment point.
K-medoids algorithm steps are as follows:
Step 1:Arbitrarily K point of selection is used as initial central point;
Step 2:Whole network is divided into by all node distributions by K to the central point nearest from them according to shortest path
Individual class;
Step 3:Central point is updated to the node for arriving the time delay sum minimum that distance is left all nodes in each class;
Step 4:Repeat step 2,3, until central point no longer changes or reached iterations.
In one example:
If a topological structure is G (V, E), V represents node set, and E represents the set on side, and interchanger sum is N, portion
K controller is affixed one's name to, controller deployment point regards central point as, and telephone net node is counted as node;
Step 1:Point centered on a node i, i=0,1 ... N-1 is selected in the entire network, uses CiRepresent, it is now whole
Individual network is centered on the node, so node label is all Ci, i.e., all interchangers are all attributed to CiManagement;
Step 2:Central point is updated according to K-medoids algorithms, now given before K-medoids initial center point
It is fixed;
Step 3:The point farthest from central point is looked in each class, it is present in a set T, calculates and is each saved in T
Point, apart from sum, is selected to all central points and maximum node is a new central point, use Cj, j=0,1 ... N-1;
Step 4:Repeat step 2 updates central point now, calculates the number K' of now central point, judges whether K' is equal to
K:
If K'< K, return to step 3 continues the algorithm;
If K'=K, the tag set Q of now center point set P and the affiliated central point of each node is returned, is terminated.
The features of the present invention and beneficial effect are:
Advantages of the present invention is mainly after deployment controller, and the time delay of whole network is minimum, can generate rational control
Device processed disposes result.
On the problem of SDN controllers are disposed, also there are some scholars to do many researchs.Also the scholar having is calculated using greed
Method, particle cluster algorithm, simulated annealing scheduling algorithm are solved to controller deployment issue.From unlike these algorithms, this calculation
Method takes full advantage of the simplicity of software defined network flexibility and topological structure, with reference to improved kmedoids algorithms pair
SDN controllers deployment sum time delay minimum problem is solved.Solution procedure complexity is relatively low, and run time is extremely short.
In terms of solving result performance estimation, this algorithm minimum measurement index as performance of time delay.As a result such as Fig. 2 institutes
Show, by taking U.S. Internet2 topologys as an example, it is assumed that K=3, its interior joint 0,10,29 is respectively Centroid.
Brief description of the drawings:
Fig. 1 algorithm flow charts.
Fig. 2 K=3 classification results.
Embodiment
Existing SDN controllers Deployment Algorithm is few, and controller deployment is controlled without specific time delay optimal case after deployment
Device processed disperses.This skewness, the time delay for causing controller to interchanger in whole network is not minimum, operating efficiency
Compare low, and cause the waste of resource.So, rational controller deployed position is critically important for reducing time delay.This
The purpose of invention is to propose a kind of SDN controller Deployment Algorithms for ensureing time delay, it is ensured that the time delay of whole network is minimum.
The main process of the present invention is that network delay and topological structure are analyzed first, calculates each interchanger and arrives
It is left the time delay of all interchangers.Then arbitrarily one interchanger of selection is used as initial controller deployment point.Further according to k-
Medoids algorithms update the deployed position to a new interchanger (minimum to remaining all interchanger time delays).Reselection
To the maximum interchanger of controller deployment point time delay as another new controller deployment point in whole network, according to time delay pair
Interchanger in whole network is redistributed.Then each controller deployment point is updated by k-medoids algorithms.Repeat always
Said process is until there is K controller deployment point.
Concrete scheme is as follows:
Ensure the minimum SDN multi-controller Deployment Algorithms of time delay:
The present invention is an improvement K-medoids minimum controller Deployment Algorithm of time delay.K-medoids algorithm steps are such as
Under:
Step 1:Arbitrarily K point of selection is used as initial central point.
Step 2:Whole network is divided into by all node distributions by K to the central point nearest from them according to shortest path
Individual class.
Step 3:Central point is updated to the node for arriving the time delay sum minimum that distance is left all nodes in each class.
Step 4:Repeat step 2,3, until central point no longer changes or reached iterations.
Assuming that a topological structure is G (V, E), V represents node set, and E represents the set on side.Interchanger sum is N,
Dispose K controller.Controller deployment point regards central point as, and telephone net node is counted as node.
Step 1:A node arbitrarily is selected as initial center point from N number of node.
Step 2:Central point is updated according to K-medoids algorithms.
Step 3:Node farthest apart from central point in each class is found, it is present in a set.Select the set
In to all central points apart from sum it is maximum o'clock be used as a new central point.
Step 4:Repeat step 2.Judge whole network either with or without being divided into K class:
If being divided into K class, classification results are returned to, terminate algorithm.
If being not separated into K class, repeat step 3 simultaneously continues.
Specific steps are as shown in Figure 1.
The following is an example of the present invention.
Ensure the minimum SDN multi-controller Deployment Algorithms of time delay:
Step 1:Point centered on a node i, i=0,1 ... N-1 is selected in the entire network, uses CiRepresent.It is now whole
Individual network is centered on the node, so node label is all Ci, i.e., all interchangers are all attributed to CiManagement.
Step 2:Central point is updated according to K-medoids algorithms (now to have given before K-medoids initial center point
It is fixed).
Step 3:The point farthest from central point is looked in each class, it is present in a set T.Calculate and each saved in T
Point, apart from sum, is selected to all central points and maximum node is a new central point, use Cj, j=0,1 ... N-1.
Step 4:Repeat step 2 updates central point now.The number K' of now central point is calculated, judges whether K' is equal to
K:
If K'< K, return to step 3 continues the algorithm;
If K'=K, the tag set Q of now center point set P and the affiliated central point of each node is returned, terminates the calculation
Method.
Claims (3)
1. a kind of SDN multi-controller dispositions method for ensureing that time delay is minimum, it is characterized in that, first to network delay and topology
Structure is analyzed, and calculates each interchanger to the time delay for being left all interchangers, then arbitrarily one interchanger conduct of selection
Initial controller deployment point, the deployed position is updated to a new interchanger further according to K-medoids algorithms, it is ensured that to surplus
Under all interchanger time delay it is minimum;To the maximum interchanger of controller deployment point time delay as another in reselection whole network
Individual new controller deployment point, redistributes to the interchanger in whole network according to time delay, then passes through K-medoids algorithms
Update each controller deployment point;Said process is repeated always until there is K controller deployment point.
2. ensure the minimum SDN multi-controller dispositions method of time delay as claimed in claim 1, it is characterized in that, K-
Medoids algorithm steps are as follows:
Step 1:Arbitrarily K point of selection is used as initial central point;
Step 2:Whole network is divided into by all node distributions by K class to the central point nearest from them according to shortest path;
Step 3:Central point is updated to the node for arriving the time delay sum minimum that distance is left all nodes in each class;
Step 4:Repeat step 2,3, until central point no longer changes or reached iterations.
3. ensure the minimum SDN multi-controller dispositions method of time delay as claimed in claim 1, it is characterized in that, a reality
In example:If a topological structure is G (V, E), V represents node set, and E represents the set on side, and interchanger sum is N, to dispose K
Individual controller, controller deployment point regards central point as, and telephone net node is counted as node;
Step 1:Point centered on a node i, i=0,1 ... N-1 is selected in the entire network, uses CiRepresent, now whole network
Centered on the node, so node label is all Ci, i.e., all interchangers are all attributed to CiManagement;
Step 2:Central point is updated according to K-medoids algorithms, now given before K-medoids initial center point;
Step 3:The point farthest from central point is looked in each class, it is present in a set T, each node in T is calculated and arrives
All central points are selected apart from sum and maximum node are a new central point, use Cj, j=0,1 ... N-1;
Step 4:Repeat step 2 updates central point now, calculates the number K' of now central point, judges whether K' is equal to K:
If K'< K, return to step 3 continues the algorithm;
If K'=K, the tag set Q of now center point set P and the affiliated central point of each node is returned, is terminated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710322262.3A CN107204874A (en) | 2017-05-09 | 2017-05-09 | Ensure the minimum SDN multi-controller dispositions method of time delay |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710322262.3A CN107204874A (en) | 2017-05-09 | 2017-05-09 | Ensure the minimum SDN multi-controller dispositions method of time delay |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107204874A true CN107204874A (en) | 2017-09-26 |
Family
ID=59905986
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710322262.3A Pending CN107204874A (en) | 2017-05-09 | 2017-05-09 | Ensure the minimum SDN multi-controller dispositions method of time delay |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107204874A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108322525A (en) * | 2018-01-23 | 2018-07-24 | 浙江工商大学 | A kind of industry multi-core network establishing method |
CN108400890A (en) * | 2018-01-30 | 2018-08-14 | 天津城建大学 | A kind of software defined network multi-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 |
CN110061859A (en) * | 2019-03-20 | 2019-07-26 | 重庆邮电大学 | A kind of SDN controller portion arranging method under the survivability constraint based on user |
CN110120892A (en) * | 2019-04-30 | 2019-08-13 | 山东工商学院 | SDN multi-controller dispositions method and system based on improved glowworm swarm algorithm |
CN110233752A (en) * | 2019-05-28 | 2019-09-13 | 中国人民解放军战略支援部队信息工程大学 | A kind of the controller robust dispositions method and device of attack resistance |
CN110891019A (en) * | 2019-12-10 | 2020-03-17 | 重庆邮电大学 | Data center flow scheduling method based on load balancing |
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 |
CN112702186A (en) * | 2020-11-23 | 2021-04-23 | 福建师范大学 | Multi-controller deployment method and terminal under SD-WAN environment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104410529A (en) * | 2014-12-09 | 2015-03-11 | 中国人民解放军国防科学技术大学 | Minimum cover deployment method for controllers based on software definition data center network |
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 |
WO2015087468A1 (en) * | 2013-12-10 | 2015-06-18 | International Business Machines Corporation | Software-defined networking single-source enterprise workload manager |
CN106572019A (en) * | 2016-11-07 | 2017-04-19 | 电子科技大学 | Network energy-saving flow scheduling method based on mixing of time delay guaranteeing and SDN |
-
2017
- 2017-05-09 CN CN201710322262.3A patent/CN107204874A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015087468A1 (en) * | 2013-12-10 | 2015-06-18 | International Business Machines Corporation | Software-defined networking single-source enterprise workload manager |
CN104410529A (en) * | 2014-12-09 | 2015-03-11 | 中国人民解放军国防科学技术大学 | Minimum cover deployment method for controllers based on software definition data center network |
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 |
CN106572019A (en) * | 2016-11-07 | 2017-04-19 | 电子科技大学 | Network energy-saving flow scheduling method based on mixing of time delay guaranteeing and SDN |
Non-Patent Citations (1)
Title |
---|
郑莉莉: "基于SDN的智能网络控制机制研究", 《中国知网|博硕论文》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108322525A (en) * | 2018-01-23 | 2018-07-24 | 浙江工商大学 | A kind of industry multi-core network establishing method |
CN108400890A (en) * | 2018-01-30 | 2018-08-14 | 天津城建大学 | A kind of software defined network multi-controller dispositions method |
CN108400890B (en) * | 2018-01-30 | 2022-04-12 | 天津城建大学 | Software defined network multi-controller deployment 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 |
CN110061859A (en) * | 2019-03-20 | 2019-07-26 | 重庆邮电大学 | A kind of SDN controller portion arranging method under the survivability constraint based on user |
CN110061859B (en) * | 2019-03-20 | 2021-11-12 | 重庆邮电大学 | SDN controller deployment method based on user survivability condition constraint |
CN110120892A (en) * | 2019-04-30 | 2019-08-13 | 山东工商学院 | SDN multi-controller dispositions method and system based on improved glowworm swarm algorithm |
CN110233752B (en) * | 2019-05-28 | 2021-11-09 | 中国人民解放军战略支援部队信息工程大学 | Robust deployment method and device for anti-attack controller |
CN110233752A (en) * | 2019-05-28 | 2019-09-13 | 中国人民解放军战略支援部队信息工程大学 | A kind of the controller robust dispositions method and device of attack resistance |
CN110891019A (en) * | 2019-12-10 | 2020-03-17 | 重庆邮电大学 | Data center flow scheduling method based on load balancing |
CN110891019B (en) * | 2019-12-10 | 2021-11-30 | 重庆邮电大学 | Data center flow scheduling method based on load balancing |
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 |
CN112702186A (en) * | 2020-11-23 | 2021-04-23 | 福建师范大学 | Multi-controller deployment method and terminal under SD-WAN environment |
CN112702186B (en) * | 2020-11-23 | 2023-10-27 | 福建师范大学 | Multi-controller deployment method and terminal in SD-WAN environment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107204874A (en) | Ensure the minimum SDN multi-controller dispositions method of time delay | |
CN103870340B (en) | Data processing method, control node and stream calculation system in stream calculation system | |
WO2020181761A1 (en) | Sdn enhanced path allocation device and method employing bin-packing technique | |
Feng et al. | An alternating direction method approach to cloud traffic management | |
CN108400890A (en) | A kind of software defined network multi-controller dispositions method | |
CN110213363A (en) | Cloud resource dynamic allocation system and method based on software defined network | |
Paganini et al. | Network stability under alpha fair bandwidth allocation with general file size distribution | |
CN107612771A (en) | A kind of SDN load-balancing method based on dynamic migration | |
CN109286528A (en) | A kind of SDN network multi-controller dispositions method based on time delay | |
CN106161270B (en) | A kind of network deployment method | |
CN103414612A (en) | Communication network real-time simulation method based on OPNET | |
Li et al. | GSPN-based reliability-aware performance evaluation of IoT services | |
Wang et al. | Distributed join-the-idle-queue for low latency cloud services | |
CN107465966A (en) | A kind of topology reconstruction control method for optical-fiber network | |
Saravanan et al. | Advance Map Reduce Task Scheduling algorithm using mobile cloud multimedia services architecture | |
Liu et al. | Heuristics for sdn controller deployment using community detection algorithm | |
Xu et al. | OMCO: Online multiple coflow scheduling in optical circuit switch | |
CN107241277A (en) | Node method for annealing in SDN | |
Liu et al. | Multi-controller placement based on two-sided matching in inter-datacenter elastic optical networks | |
CN108616569B (en) | A kind of Based on Distributed calculates the light Measurement Request dispatching method of application | |
CN107911763B (en) | Intelligent power distribution and utilization communication network EPON network planning method based on QoS | |
CN109688068A (en) | Network load balancing method and device based on big data analysis | |
Huang et al. | Exploiting inter-flow relationship for coflow placement in datacenters | |
Liu et al. | Optimal site selection of China railway data centers by the PSO algorithm | |
Li et al. | Energy aware green spine switch management for Spine-Leaf datacenter networks |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170926 |
|
WD01 | Invention patent application deemed withdrawn after publication |