CN106911516B - A kind of software defined network controller portion arranging method - Google Patents

A kind of software defined network controller portion arranging method Download PDF

Info

Publication number
CN106911516B
CN106911516B CN201710167522.4A CN201710167522A CN106911516B CN 106911516 B CN106911516 B CN 106911516B CN 201710167522 A CN201710167522 A CN 201710167522A CN 106911516 B CN106911516 B CN 106911516B
Authority
CN
China
Prior art keywords
controller
interchanger
candidate
restrictive condition
indicate
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710167522.4A
Other languages
Chinese (zh)
Other versions
CN106911516A (en
Inventor
柴蓉
朱磊
秦远征
陈前斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing University of Post and Telecommunications
Original Assignee
Chongqing University of Post and Telecommunications
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing University of Post and Telecommunications filed Critical Chongqing University of Post and Telecommunications
Priority to CN201710167522.4A priority Critical patent/CN106911516B/en
Publication of CN106911516A publication Critical patent/CN106911516A/en
Application granted granted Critical
Publication of CN106911516B publication Critical patent/CN106911516B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/12Discovery or management of network topologies
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/145Network analysis or design involving simulating, designing, planning or modelling of a network

Abstract

The present invention relates to a kind of software defined network controller portion arranging methods, belong to technical field of communication network.Method includes the following steps: communication overhead between step 1, the candidate controller of modeling and interchanger;Step 2 models candidate controller load restrictive condition;Step 3 models candidate controller node degree restrictive condition;Bitrate constraints are extended to when step 4, modeling interchanger, determine interchanger candidate's controller set;Step 5 models candidate controller and interchanger association identification restrictive condition;Step 6, in the case where meeting controller and interchanger restrictive condition, based on controller communication overhead minimize determine controller deployment strategy.This method can optimize in the case where comprehensively considering the restrictive conditions such as controller load, exchange service characteristic and determine SDN controller deployment strategy, to realize controller minimizing overhead.

Description

A kind of software defined network controller portion arranging method
Technical field
The invention belongs to technical field of communication network, are related to a kind of software defined network controller portion arranging method.
Background technique
Software defined network (Software Defined Networks, SDN) is proposed by Stanford Univ USA, with The new and innovative network platform based on OpenFlow.The typical architecture of SDN is divided into three layers, and top layer is application layer, including each Kind different business and application;Middle layer is control layer, is mainly responsible for the layout of processing data transfer equipment resource, safeguards network Topology and status information etc.;The bottom is data Layer, is mainly responsible for data processing, forwarding and state collection based on flow table.SDN Key property is that control plane is separated with data plane, centralized network controls, open between control layer and data Layer equipment Network interface, network can be programmed by external program.Due to the separation of control layer and data Layer, so that quickly opening and Configuration network Connection service becomes possible.In SDN framework, intelligentized SDN controller can obtain the global view of network, and can Control the data transfer equipment of whole network.
However, SDN centerized fusion also brings SDN network scalability problem.As network size increases, SDN net Network only relies on single controller multiple threads mode, it will be difficult to guarantee network QoS, and there are single point failures etc. to ask for single controller Topic, comprehensively considers from network stabilization, safety etc., and multi-controller deployment becomes current and solves SDN network scalability Main stream approach.Research shows that the position disposed in a network of multi-controller, quantity will all make a big impact to network performance, Therefore SDN network controller deployment issue becomes one of current SDN research emphasis.
Document [Adlen Ksentini, Miloud Bagaa, Tarik Taleb, Ilangko Balasingham.On using bargaining game for optimal placement of SDN controllers.2016IEEE International Conference on Communications (ICC)] propose that a kind of joint considers controller and control Between device between time delay and controller and interchanger time delay location of controls selection method, but this method does not consider to hand in network It changes planes practical business otherness.Document [Long Yao, Peilin Hong, Wen Zhang, Jianfei Li, Dan Ni.Controller placement and flow based dynamic management problem towards SDN.2015IEEE International Conference on Communication Workshop (ICCW)] propose one Controller portion arranging method of the kind based on SDN switch node weights, but author only passes through telephone net node in network topology Next-hop neighbor node number models exchange service otherness, does not comprehensively consider multi-hop link performance.Document [Tracy Yingying Cheng,Mengqing Wang,Xiaohua Jia.QoS-guaranteed controller placement In SDN.2015IEEE Global Communications Conference (GLOBECOM)] propose one kind to improve network QoS is that the controller of target is disposed, but is only modeled to controller side time delay, does not consider that exchanger side time delay and link are opened The factors such as pin.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of software defined network controller portion arranging method, this method energy It is enough to optimize in the case where comprehensively considering the restrictive conditions such as controller load, exchange service characteristic and determine SDN controller deployment strategy, To realize controller minimizing overhead.
In order to achieve the above objectives, the invention provides the following technical scheme:
A kind of software defined network controller portion arranging method, method includes the following steps: step 1, the candidate control of modeling Communication overhead between device and interchanger;Step 2 models candidate controller load restrictive condition;Step 3 models candidate controller Node degree restrictive condition;Bitrate constraints are extended to when step 4, modeling interchanger, determine interchanger candidate's controller set; Step 5 models candidate controller and interchanger association identification restrictive condition;Step 6 is meeting controller and interchanger limitation item Under part, is minimized based on controller communication overhead and determine controller deployment strategy.
Further, the step 1 specifically includes:
Assuming that in network at all interchangers can deployment controller, model communication overhead between candidate controller and interchanger The communication overhead summation between all candidate controllers and associated interchanger, i.e.,Wherein, DijIt is waited for i-th Controller corresponding communication overhead when being associated with j-th of interchanger is selected, respectively with Ci, VjIndicate i-th of candidate controller and jth A interchanger, yijFor CiWith VjBetween association identification, yij=1 indicates CiWith VjAssociation, otherwise, yij=0,1≤i≤M, 1≤j ≤ N, wherein M, N are respectively the number of network central control device and interchanger.
Further, the DijBe defined as communication link propagation delay, message transmission time delay and request message queuing delay it With that is,Wherein,Indicate CiWith VjCommunication link propagation delay when association,Indicate CiWith VjBetween Message transmission time delay,Indicate VjRequest message in CiThe queuing delay at place, if i=j
It is describedIt is defined asWherein, LijIndicate CiWith VjBetween link range, v0For Electromagnetic Wave Propagation speed Degree, For CiWith VjBetween h hop link distance, HijFor CiWith VjBetween transmission path hop count;
It is describedIt is defined asWherein, λjIndicate VjRequest message arrival rate, β indicate interchanger request Message packets size,Indicate CiWith VjBetween h hop link diameter transmission rate;
Each candidate controller processing switch message process is modeled as M/M/1 queuing model, and interchanger request message It reaches and obeys poisson arrival process,It is defined asWherein σiIndicate CiHandle the Mean Speed of request message, Si Expression and CiThe set of associated all interchangers.
Further, in step 2, the load difference that candidate controller load restrictive condition is any two controller is modeled Lower than given threshold value, i.e., for arbitrary controller i, k, haveWherein, ξ is controller load Difference threshold value.
Further, in step 3, it models candidate controller node degree restrictive condition and specifically enables NiFor CiA jump Neighbor node number, selected controller node should meet a hop neighbor interstitial content and be greater than given threshold valueI.e. when and only WhenCiIt can be target controller.
Further, in step 4, interchanger propagation delay time and bitrate constraints are modeled, specifically: if CiWith VjAssociation, It then needs to meet VjPropagation delay time restrictive conditionWhereinFor VjAllow maximum transmitted time delay;It also then needs to meet VjIt passes Defeated bitrate constraintsWhereinFor VjMinimum transmission rate requirements;It, can according to propagation delay time and rate qualifications Determine VjCandidate controller set
Further, in steps of 5, modeling interchanger and controller association identification restrictive condition: 1. yij∈{0,1};②5. ifThen yij=0.
Further, in step 6, minimum based on controller communication overhead in the case where meeting controller, interchanger restrictive condition Change and determine controller deployment strategy, i.e.,
The beneficial effects of the present invention are: the method for the invention can comprehensively consider controller load, interchanger industry Under the restrictive conditions such as characteristic of being engaged in, optimizes and determine SDN controller deployment strategy, to realize controller minimizing overhead.
Detailed description of the invention
In order to keep the purpose of the present invention, technical scheme and beneficial effects clearer, the present invention provides following attached drawing and carries out Illustrate:
Fig. 1 is software network interchanger, controller schematic diagram of a scenario;
Fig. 2 is the flow diagram of the method for the invention.
Specific embodiment
Below in conjunction with attached drawing, a preferred embodiment of the present invention will be described in detail.
A kind of software defined network controller portion arranging method of the present invention, it is assumed that distributed director uses flat control Mode processed, all controllers are placed on disjoint region, manage respective network respectively.Status phase between each controller Deng, and in-band communications are carried out by East and West direction interface.And controller issuing using quilt to SDN switch device request message Dynamic model formula.
Fig. 1 is software network interchanger, controller schematic diagram of a scenario, and interchanger is associated with different controls by strategy Device realizes controller to the centralized control of whole network in the case where most minimizing controller communication overhead.
Fig. 2 is the flow diagram of the method for the invention, as shown, the method for the invention specifically includes following step It is rapid:
1) communication overhead between candidate controller and interchanger is modeled:
Modeling communication overhead between candidate controller and interchanger is between all candidate controllers and associated interchanger Communication overhead andWherein, DijCorresponding communication overhead when being associated with for i-th of candidate controller with j-th of interchanger, Respectively with Ci, VjIndicate i-th of candidate controller and j-th of interchanger, yijFor CiWith VjAssociation identification, yij=1 indicates CiWith VjAssociation, otherwise, yij=0,1≤i≤M, 1≤j≤N, wherein M, N are respectively the number of network central control device and interchanger.
The DijIt is defined as communication link propagation delay, the sum of message transmission time delay and request message queuing delay, i.e.,Wherein,Indicate CiWith VjCommunication link propagation delay when association,Indicate CiWith VjBetween message pass Defeated time delay,Indicate VjRequest message in CiThe queuing delay at place.
It is describedIt is defined asWherein, LijIndicate CiWith VjBetween link range, v0For Electromagnetic Wave Propagation speed Degree; For CiWith VjBetween h hop link distance, HijFor CiWith VjBetween transmission path hop count.It is described It is defined asWherein, λjIndicate VjRequest message arrival rate, β indicate interchanger request message data package size,Indicate CiWith VjBetween h hop link diameter transmission rate.It is describedIn definition procedure, each candidate controller processing is handed over Message process of changing planes is modeled as M/M/1 queuing model, and interchanger request message reaches and obeys poisson arrival process,Definition ForWherein σiIndicate CiHandle the Mean Speed of request message, SiExpression and CiThe collection of associated all interchangers It closes.
2) it models candidate controller and loads restrictive condition:
It models the load difference that candidate controller load restrictive condition is any two controller and is lower than given threshold value, That is: for arbitrary controller i, k, haveWherein, ξ is controller load difference threshold value.The limit Condition processed ensures in SDN network load balancing between different controllers.
3) candidate controller node degree restrictive condition is modeled:
Enable NiFor CiA hop neighbor interstitial content, selected controller node should meet a hop neighbor interstitial content and be greater than Given threshold valueI.e. and if only ifCiIt can be target controller.The restrictive condition can be reduced to a certain extent and be asked Solve the Algorithms T-cbmplexity of optimal deployment strategy problem.
4) interchanger candidate's controller set is determined:
If CiWith VjAssociation, then need to meet VjPropagation delay time restrictive condition isWhereinFor VjAllow maximum Propagation delay time;If CiWith VjAssociation, then need to meet bitrate constraints beWhereinFor VjMinimum transmission rate needs It asks.According to propagation delay time and rate qualifications, it may be determined that VjCandidate controller set
5) candidate controller and interchanger association identification restrictive condition are modeled:
①yij∈{0,1};②5. ifThen yij=0, wherein limiting item 1. part indicates that association identification is the Boolean variable for belonging to 0 or 1;2. restrictive condition indicates that a SDN switch can only be controlled with one Device association processed;3. restrictive condition indicates the associated controller number of all SDN switches and no more than candidate controller number; 4. restrictive condition indicates that SDN switch all in network must be associated with controller;5. restrictive condition indicates to exchange in network Controller associated by machine should belong to respectively candidate controller set.
6) it is minimized based on controller communication overhead and determines controller deployment strategy:
In the case where meeting controller, interchanger restrictive condition, is minimized based on controller communication overhead and determine controller deployment Strategy, that is,
Finally, it is stated that preferred embodiment above is only used to illustrate the technical scheme of the present invention and not to limit it, although logical It crosses above preferred embodiment the present invention is described in detail, however, those skilled in the art should understand that, can be Various changes are made to it in form and in details, without departing from claims of the present invention limited range.

Claims (2)

1. a kind of software defined network controller portion arranging method, it is characterised in that: method includes the following steps:
Step 1 models communication overhead between candidate controller and interchanger;
Step 2 models candidate controller load restrictive condition;
Step 3 models candidate controller node degree restrictive condition;
Bitrate constraints are extended to when step 4, modeling interchanger, determine interchanger candidate's controller set;
Step 5 models candidate controller and interchanger association identification restrictive condition;
Step 6, in the case where meeting controller and interchanger restrictive condition, based on controller communication overhead minimize determine controller portion Administration's strategy;
The step 1 specifically includes:
Assuming that in network at all interchangers can deployment controller, modeling communication overhead between candidate controller and interchanger is institute There is communication overhead summation between candidate controller and associated interchanger, i.e.,Wherein, DijFor i-th of candidate Controller corresponding communication overhead when being associated with j-th of interchanger, respectively with Ci, VjIndicate i-th of candidate controller and j-th Interchanger, yijFor CiWith VjBetween association identification, yij=1 indicates CiWith VjAssociation, otherwise, yij=0,1≤i≤M, 1≤j≤ N, wherein M, N are respectively the number of network central control device and interchanger;
The DijIt is defined as communication link propagation delay, the sum of message transmission time delay and request message queuing delay, i.e.,Wherein,Indicate CiWith VjCommunication link propagation delay when association,Indicate CiWith VjBetween Message transmission time delay,Indicate VjRequest message in CiThe queuing delay at place, if i=j
It is describedIt is defined asWherein, LijIndicate CiWith VjBetween link range, v0For propagation velocity of electromagnetic wave, For CiWith VjBetween h hop link distance, HijFor CiWith VjBetween transmission path hop count;
It is describedIt is defined asWherein, λjIndicate VjRequest message arrival rate, β indicate interchanger request disappear Data package size is ceased,Indicate CiWith VjBetween h hop link diameter transmission rate;
Each candidate controller processing switch message process is modeled as M/M/1 queuing model, and interchanger request message reaches Poisson arrival process is obeyed,It is defined asWherein σiIndicate CiHandle the Mean Speed of request message, Si Expression and CiThe set of associated all interchangers;
In step 2, it models the load difference that candidate controller load restrictive condition is any two controller and is lower than given door Limit value has that is, for arbitrary controller i, kWherein, ξ is controller load difference door Limit value;
In step 3, it models candidate controller node degree restrictive condition and specifically enables NiFor CiA hop neighbor number of nodes Mesh, selected controller node should meet a hop neighbor interstitial content and be greater than given threshold valueI.e. and if only if CiIt can be target controller;
In step 4, interchanger propagation delay time and bitrate constraints are modeled, specifically: if CiWith VjAssociation, then need to meet Vj Propagation delay time restrictive conditionWhereinFor VjAllow maximum transmitted time delay;It also then needs to meet VjTransmission rate Restrictive conditionWhereinFor VjMinimum transmission rate requirements;It, can be true according to propagation delay time and rate qualifications Determine VjCandidate controller set
In steps of 5, modeling interchanger and controller association identification restrictive condition: 1. yij∈{0,1};②5. ifThen yij=0.
2. a kind of software defined network controller portion arranging method as described in claim 1, it is characterised in that: in step 6, Meet under controller, interchanger restrictive condition, is minimized based on controller communication overhead and determine controller deployment strategy, i.e.,
CN201710167522.4A 2017-03-20 2017-03-20 A kind of software defined network controller portion arranging method Active CN106911516B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710167522.4A CN106911516B (en) 2017-03-20 2017-03-20 A kind of software defined network controller portion arranging method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710167522.4A CN106911516B (en) 2017-03-20 2017-03-20 A kind of software defined network controller portion arranging method

Publications (2)

Publication Number Publication Date
CN106911516A CN106911516A (en) 2017-06-30
CN106911516B true CN106911516B (en) 2019-09-24

Family

ID=59195657

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710167522.4A Active CN106911516B (en) 2017-03-20 2017-03-20 A kind of software defined network controller portion arranging method

Country Status (1)

Country Link
CN (1) CN106911516B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108092895B (en) * 2017-12-26 2020-07-14 重庆邮电大学 Software Defined Network (SDN) joint routing selection and network function deployment method
CN108206790B (en) * 2018-01-11 2021-03-16 重庆邮电大学 SDN joint routing selection and resource allocation method based on network slice
CN109088755B (en) * 2018-08-01 2021-07-27 南京大学 Complex event processing system deployment method under edge calculation
CN110034955B (en) * 2019-03-26 2022-03-22 重庆邮电大学 Target controller selection method considering multiple switch migration indexes
CN111770515B (en) * 2020-06-28 2022-03-29 重庆邮电大学 SDN controller deployment method based on network cost optimization
CN112305973B (en) * 2020-11-12 2021-07-27 中国电子科技集团公司第五十四研究所 Controller cluster load sharing method based on link attributes
CN114979007A (en) * 2022-05-18 2022-08-30 公诚管理咨询有限公司 Load balancer adjusting method and system based on 5G core network NFV slicing technology

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104065509A (en) * 2014-07-24 2014-09-24 大连理工大学 SDN multi-controller deployment method for reducing management load overhead
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
CN105704192A (en) * 2014-11-28 2016-06-22 华为技术有限公司 Method and equipment for determining controller position in SDN network
US9436443B2 (en) * 2014-08-28 2016-09-06 At&T Intellectual Property I, L.P. Software defined network controller

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10516704B2 (en) * 2015-07-28 2019-12-24 Polycom, Inc. Relaying multimedia conferencing utilizing software defined networking architecture

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104065509A (en) * 2014-07-24 2014-09-24 大连理工大学 SDN multi-controller deployment method for reducing management load overhead
US9436443B2 (en) * 2014-08-28 2016-09-06 At&T Intellectual Property I, L.P. Software defined network controller
CN105704192A (en) * 2014-11-28 2016-06-22 华为技术有限公司 Method and equipment for determining controller position in SDN 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

Also Published As

Publication number Publication date
CN106911516A (en) 2017-06-30

Similar Documents

Publication Publication Date Title
CN106911516B (en) A kind of software defined network controller portion arranging method
CN108259367B (en) Service-aware flow strategy customization method based on software defined network
CN105516312B (en) A kind of software defined network load balancing apparatus and method
CN105227481B (en) SDN congestion control method for routing based on path cost and stream scheduling cost minimization
CN104639464B (en) The system and method for switch-spanning link aggregation is realized on OpenFlow interchangers
CN104065509B (en) A kind of SDN multi-controller dispositions methods for reducing management load overhead
CN105933227B (en) The method of routing decision and the optimization of flow table consistency in software definition satellite network
CN105553845A (en) Software defined network route selection method
CN106936705B (en) Software defined network routing method
CN105791175B (en) The method and apparatus of transfer resource is controlled in software defined network
CN105959221B (en) The method of the flow table consistency optimization of software definition satellite network
CN108206790B (en) SDN joint routing selection and resource allocation method based on network slice
CN107682258A (en) A kind of multi-path network transmission method and device based on virtualization
CN106572019B (en) Time delay guarantee hybrid SDN energy-saving flow scheduling method
CN105915419A (en) Wireless access controller deployment method based on SDN (Software Defined Network)
CN109150604A (en) A kind of powerline network system based on SDN and cross-domain dicing method
CN106685835A (en) Method for achieving high-speed distributed routing between computational nodes of data center
CN106851746A (en) The method for realizing software definition QoS configurations in radio sensing network is calculated based on mist
Yan et al. A survey of low-latency transmission strategies in software defined networking
CN108092895A (en) A kind of software defined network joint route selection and network function dispositions method
CN105847146B (en) A method of it improving level distribution SDN and controls plane router efficiency
CN106921571A (en) A kind of software defined network joint route selection and flow allocation method
CN115314355A (en) Electric power communication network architecture system and method based on deterministic network
CN207304583U (en) A kind of edge network architecture of Internet of things based on software defined network
CN108880895A (en) The selection of SDN joint route and the network function dispositions method of transport overhead optimization are flowed based on user

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