CN108809829B - SDN rule deployment method - Google Patents
SDN rule deployment method Download PDFInfo
- Publication number
- CN108809829B CN108809829B CN201810613458.2A CN201810613458A CN108809829B CN 108809829 B CN108809829 B CN 108809829B CN 201810613458 A CN201810613458 A CN 201810613458A CN 108809829 B CN108809829 B CN 108809829B
- Authority
- CN
- China
- Prior art keywords
- user
- rule
- flow
- controller
- user flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/14—Routing performance; Theoretical aspects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/121—Shortest path evaluation by minimising delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/74—Address processing for routing
- H04L45/742—Route cache; Operation thereof
Abstract
The invention relates to an SDN rule deployment method, and belongs to the technical field of communication networks. The method takes modeling of the total time delay of user stream transmission as an optimization target, and realizes a rule cache deployment strategy. The method comprises the following steps: s1: modeling a user flow identifier; s2: modeling the path hop number of the user flow to a destination node; s3: modeling a user flow link selection variable; s4: modeling the total time delay of user stream transmission; s5: modeling switch capacity limits; s6: and determining a rule cache deployment strategy based on the minimization of the total time delay of user stream transmission. The method provided by the invention can effectively guarantee the service quality of the user, meet the requirement of the user rule cache, achieve the optimal routing selection and realize the minimization of the total time delay of the user stream transmission.
Description
Technical Field
The invention belongs to the technical field of communication networks, and relates to a SDN rule deployment method.
Background
Software-defined networking (SDN) decouples the control logic of the network from the data plane, with unified control and management of data forwarding devices (routers and switches) in the data plane in a logically centralized manner by introducing one or more controllers at the control plane.
In SDN, each network flow is associated with a set of flow processing rules, such as packet forwarding, deletion, and modification. According to the processing rules in the flow path, a data forwarding device in the network, such as a switch, may cache the relevant rules in its flow table. If the forwarding rules of some data flows are not cached in the flow table of the switch, a flow establishing request needs to be sent to the controller, the controller determines a data flow forwarding path, and sends a notification to the relevant switch. Due to the long control plane delay between the SDN controller and the switch, the data stream transmission performance is limited. Aiming at the problem, the data stream transmission performance can be improved by optimizing a design rule cache mechanism.
Research is carried out on SDN rule caching problems by existing related articles, such as a rule deployment algorithm based on caching cost minimization is provided; for the problem of rule cache content, the existing article provides a rule pre-caching algorithm based on deep learning, but the existing research rarely considers the problem of rule deployment based on time delay optimization.
In summary, how to implement minimization of network delay by optimizing a design rule deployment strategy in the SDN becomes an urgent problem to be solved.
Disclosure of Invention
In view of this, an object of the present invention is to provide an SDN rule deployment method, in the method, for an SDN scenario formed by one controller and a plurality of switches, it is assumed that each switch caches some rules according to popularity of a flow to perform corresponding processing on an arriving flow, if no corresponding rule is found in the switch, the controller calculates a routing rule for the flow according to a related algorithm, and caches the rule in all switches on the path, modeling total transmission delay of a user flow is an optimization target, and a rule caching deployment policy is implemented.
In order to achieve the purpose, the invention provides the following technical scheme:
an SDN rule deployment method comprises the following steps: for an SDN scene formed by a controller and a plurality of switches, assuming that a certain rule is cached in each switch according to the popularity of a flow, and accordingly correspondingly processing the arriving flow; if the corresponding forwarding rule is not stored in the switch, the controller calculates the routing rule according to the relevant algorithm and caches the routing rule to all switches on the path, the total time delay of user stream transmission is modeled as an optimization target, and a rule cache deployment strategy is realized; the method comprises the following specific steps:
s1: modeling a user flow identifier;
s2: modeling the path hop number of the user flow to a destination node;
s3: modeling a user flow link selection variable;
s4: modeling the total time delay of user stream transmission;
s5: modeling switch capacity limits;
s6: and determining a rule cache deployment strategy based on the minimization of the total time delay of user stream transmission.
Further, theStep S1 specifically includes: let Uf={f1,...,fMDenotes the set of user flows arriving at the switch, where fiRepresents the ith user stream, let SiFor a user flow fiI is more than or equal to 1 and less than or equal to F, and F is the number of user streams.
Further, the step S2 specifically includes: within each switch certain rules are cached according to the popularity of the stream, user stream fiSelecting the next hop node according to the cached rule, order VjJ is more than or equal to 1 and less than or equal to N, and N is the number of the exchangers; let m denote the user flow fiM is not less than 1 and not more than Mi,MiFor a user flow fiThe total number of hops of (a) is,i.m∈ {0,1} represents user flow fiThe identity of the node is selected,i,muser flow f is denoted by 1iThe source node of the mth hop link sends a flow establishing request to the controller, otherwise,i,m=0。
further, the step S3 specifically includes: let Ej,kIndicating a switch VjAnd a switch VkJ is more than or equal to 1, k is more than or equal to N, and j is not equal to k; order toRepresenting a user flow fiThe identification of the link selection of (a),representing a user flow fiIs selected to link Ej,kThe data transmission is carried out, otherwise,
further, in step S4, the modeled total user transmission delay D is the sum of all user stream transmission delays, that is, the modeled total user transmission delay D is the sum of all user stream transmission delaysWherein the content of the first and second substances,representing a user flow fiPerform data conversionTransmitting corresponding transmission time delay;indicating that a flow request message is sent by the switch to the controller, which is the user flow fiDetermining transmission time delay corresponding to a forwarding rule;
the user flow is directly matched with the transmission time delay corresponding to the cache rule by the switchWherein the content of the first and second substances,representing a user flow fiAt link Ej,kThe delay of the transmission of the data packet over the data packet,representing a user flow fiAt the exchange VjQueuing delay of (1);
the user flow fiAt link Ej,kThe calculation formula of the transmission delay isαi,j,k> 0, wherein, αi,j,k∈ {0,1} represents user flow fiAssigned link Ej,kTransmission resource identification, Tj,kIs a link Ej,kThe transmission rate of (c);
the user flow fiAt the exchange VjThe calculation formula of the queuing delay is as follows: the user flow processing at the exchange follows M/M/1 queuing model according to the formulaCalculating a user flow fiAt the exchange VjQueuing delay of where mujAnd λjRespectively representing exchanges VjThe service rate and the arrival rate of the station,indicating a switch VjFor a user flow fiAn assigned processing resource identification;
if the user flow does not find a forwarding rule matched with the user flow in the switch, the switch interacts with the controller, the controller determines the transmission path of the user flow and caches the rule in all switches on the path, so the user flow fiThe transmission time delay corresponding to the buffer rule is distributed by the controllerWherein D iscqIndicating the queuing delay of the streaming request at the controller, DcpIndicating the processing delay required by the controller to calculate and issue the rules,the transmission time delay required by the controller to send the rule to each switch on the selected path is represented;
the calculation formula of the queuing delay of the flow building request at the controller is as follows: setting the flow establishing request processing at the SDN controller to follow an M/M/1 queuing model according to a formulaCalculating a queuing delay of the streaming request at the controller, wherein mucAnd λcRespectively representing a service rate and an arrival rate at the controller;
the user flow fiThe buffer rule is distributed at the controller, and the calculation method of the required processing time delay isWherein S isoRequesting packet size for streaming, CaComputing power for the controller;
the user flow fiThe transmission delay between the switch and the controller is calculated byWherein the content of the first and second substances,Tc,jfor controllers and switches VjThe transmission rate therebetween.
Further, the step S5 specifically includes: the capacity limitation condition is modeled asCjFor the exchange VjThe rule cache size of (2).
Further, optimizing the SDN network rule deployment method by using the minimization of time delay as the target under the condition of meeting the limit conditions of rule cache and the internal capacity of the switch, namely
The invention has the beneficial effects that: the invention can effectively guarantee the service quality of the user, meet the requirement of the user rule cache, achieve the optimal routing selection and realize the minimization of the total time delay of the user stream transmission.
Drawings
In order to make the object, technical scheme and beneficial effect of the invention more clear, the invention provides the following drawings for explanation:
FIG. 1 is a schematic diagram of a network scenario supporting network rule deployment;
FIG. 2 is a schematic flow chart of the method of the present invention.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a network scenario supporting network rule deployment, as shown in the figure, in an SDN scenario formed by the controller and the switches, it is assumed that each switch caches some rules according to the popularity of a flow to perform corresponding processing on an arriving flow, if no corresponding rule is found in the switch, the controller calculates a routing rule for the flow according to a related algorithm, and caches the rule in all switches on the path, models the total transmission delay of a user flow as an optimization target, and implements a rule caching deployment policy.
Fig. 2 is a schematic flow chart of the method of the present invention, and as shown in the figure, the method of the present invention specifically includes the following steps:
an SDN rule deployment method comprises the following steps: for an SDN scenario consisting of one controller and multiple switches, it is assumed that certain rules are cached in each switch according to the popularity of the flow, so that the arriving flow can be processed accordingly. If the corresponding forwarding rule is not stored in the switch, the controller calculates the routing rule according to the relevant algorithm and caches the routing rule to all switches on the path, the total time delay of user stream transmission is modeled as an optimization target, and a rule cache deployment strategy is realized; the method comprises the following specific steps:
1) modeling user flow identification
Modeling the user flow identification, specifically: let Uf={f1,...,fMDenotes the set of user flows arriving at the switch, where fiRepresents the ith user stream, let SiFor a user flow fiI is more than or equal to 1 and less than or equal to F, and F is the number of user streams.
2) Modeling the number of path hops from a user flow to a destination node
Modeling the path hop number of the user flow to the destination node, specifically: within each switch certain rules are cached according to the popularity of the stream, user stream fiSelecting the next hop node according to the cached rule, order VjJ is more than or equal to 1 and less than or equal to N, and N is the number of the exchangers; let m denote the user flow fiM is not less than 1 and not more than Mi,MiFor a user flow fiThe total number of hops of (a) is,i.m∈ {0,1} represents user flow fiThe identity of the node is selected,i,muser flow f is denoted by 1iThe source node of the mth hop link sends a flow establishing request to the controller, otherwise,i,m=0。
3) modeling user flow link selection variables
The modeling user flow link selection variable specifically comprises: let Ej,kIndicating a switch VjAnd a switch VkJ is more than or equal to 1, k is more than or equal to N, and j is not equal to k; order toRepresenting a user flow fiThe identification of the link selection of (a),representing a user flow fiIs selected to link Ej,kThe data transmission is carried out, otherwise,
4) modeling total time delay of user stream transmission
The total delay D of the user stream transmission is modeled as the sum of the transmission delays of all the user streams, i.e.Wherein the content of the first and second substances,representing a user flow fiCorresponding transmission time delay when data forwarding is carried out;indicating that a flow request message is sent by the switch to the controller, which is the user flow fiAnd determining the transmission time delay corresponding to the forwarding rule.
According to the formulaCalculating the transmission time delay corresponding to the user flow directly matched with the cache rule by the switch, wherein,representing a user flow fiAt link Ej,kThe delay of the transmission of the data packet over the data packet,representing a user flow fiAt the exchange VjQueuing delay. According to the formulaαi,j,k> 0 computing said user flow fiAt link Ej,kA transmission delay of (c), wherein αi,j,k∈ {0,1} represents user flow fiAssigned link Ej,kTransmission resource identification, Tj,kIs a link Ej,kThe transmission rate of (c). According to the formulaCalculating a user flow fiAt the exchange VjQueuing delay of where mujAnd λjRespectively representing exchanges VjThe service rate and the arrival rate of the station,indicating a switch VjFor a user flow fiAn identification of the allocated processing resource.
If the user flow does not find a forwarding rule matched with the user flow in the switch, the switch interacts with the controller, the controller determines the transmission path of the user flow and caches the rule in all switches on the path, so the user flow fiThe transmission time delay corresponding to the buffer rule is distributed by the controllerWherein D iscqIndicating the queuing delay of the streaming request at the controller, DcpIndicating the processing delay required by the controller to calculate and issue the rules,indicating that the controller issues rules to the required transmission delay of each switch on the selected path. According to the formulaCalculating a queuing delay of the streaming request at the controller, wherein mucAnd λcRespectively representing the service rate and arrival rate at the controller. The user flow fiIs allocated a buffer at the controllerThe rule, the required processing time delay is calculated byWherein S isoRequesting packet size for streaming, CaComputing power for the controller. According to the formulaCalculating the user flow fiA transmission delay between the switch and the controller, wherein,Tc,jfor controllers and switches VjThe transmission rate therebetween.
5) Modeling switch capacity limits
The capacity limit of the modeling switch is specifically as follows: the capacity limitation condition is modeled asCjFor the exchange VjThe rule cache size of (2).
6) Determining a rule cache deployment strategy based on minimizing total user stream transmission delay
Determining a rule cache deployment strategy based on the minimization of the total user stream transmission delay, specifically: optimizing the SDN network rule deployment method by using the minimization of time delay as the target under the condition of meeting the limit conditions of rule cache and the internal capacity of a switch, namely
Finally, it is noted that the above-mentioned preferred embodiments illustrate rather than limit the invention, and that, although the invention has been described in detail with reference to the above-mentioned preferred embodiments, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the invention as defined by the appended claims.
Claims (3)
1. An SDN rule deployment method is characterized in that: the method comprises the following steps: for an SDN scene formed by a controller and a plurality of switches, assuming that a certain rule is cached in each switch according to the popularity of a flow, and accordingly correspondingly processing the arriving flow; if the corresponding forwarding rule is not stored in the switch, the controller calculates the routing rule according to the relevant algorithm and caches the routing rule to all switches on the path, the total time delay of user stream transmission is modeled as an optimization target, and a rule cache deployment strategy is realized; the method comprises the following specific steps:
s1: modeling a user flow identifier;
s2: modeling the path hop number of the user flow to a destination node;
s3: modeling a user flow link selection variable;
s4: modeling the total time delay of user stream transmission;
s5: modeling switch capacity limits;
s6: determining a rule cache deployment strategy based on minimizing total user stream transmission delay
The step S1 specifically includes: let Uf={f1,...,fMDenotes the set of user flows arriving at the switch, where fiRepresents the ith user stream, let SiFor a user flow fiI is more than or equal to 1 and less than or equal to F, wherein F is the number of user streams;
the step S2 specifically includes: within each switch certain rules are cached according to the popularity of the stream, user stream fiSelecting the next hop node according to the cached rule, order VjJ is more than or equal to 1 and less than or equal to N, and N is the number of the exchangers; let m denote the user flow fiM is not less than 1 and not more than Mi,MiFor a user flow fiThe total number of hops of (a) is,i,m∈ {0,1} represents user flow fiThe identity of the node is selected,i,muser flow f is denoted by 1iThe source node of the mth hop link sends a flow establishing request to the controller, otherwise,i,m=0;
the step S3 specifically includes: let Ej,kIndicating a switch VjAnd a switch VkJ is more than or equal to 1, k is more than or equal to N, and j is not equal to k; order toRepresenting a user flow fiThe identification of the link selection of (a),representing a user flow fiIs selected to link Ej,kThe data transmission is carried out, otherwise,
2. The SDN rule deployment method of claim 1, wherein: in step S4, the modeled total user transmission delay D is the sum of all user stream transmission delays, i.e. the total user stream transmission delay D is calculatedWherein the content of the first and second substances,representing a user flow fiCorresponding transmission time delay when data forwarding is carried out;indicating that a flow request message is sent by the switch to the controller, which is the user flow fiDetermining transmission time delay corresponding to a forwarding rule;
the user flow is directly matched with the transmission time delay corresponding to the cache rule by the switchWherein the content of the first and second substances,representing a user flow fiAt link Ej,kThe delay of the transmission of the data packet over the data packet,representing a user flow fiAt the exchange VjQueuing delay of (1);
the user flow fiAt link Ej,kThe calculation formula of the transmission delay isαi,j,k> 0, wherein, αi,j,k∈ {0,1} represents user flow fiAssigned link Ej,kTransmission resource identification, Tj,kIs a link Ej,kThe transmission rate of (c);
the user flow fiAt the exchange VjThe calculation formula of the queuing delay is as follows: the user flow processing at the exchange follows M/M/1 queuing model according to the formulaCalculating a user flow fiAt the exchange VjQueuing delay of where mujAnd λjRespectively representing exchanges VjThe service rate and the arrival rate of the station,indicating a switch VjFor a user flow fiAn assigned processing resource identification;
if the user flow does not find a forwarding rule matched with the user flow in the switch, the switch interacts with the controller, the controller determines the transmission path of the user flow and caches the rule in all switches on the path, so the user flow fiThe transmission time delay corresponding to the buffer rule is distributed by the controllerWherein D iscqIndicating the queuing delay of the streaming request at the controller, DcpIndicating the processing delay required by the controller to calculate and issue the rules,the transmission time delay required by the controller to send the rule to each switch on the selected path is represented;
the calculation formula of the queuing delay of the flow building request at the controller is as follows: setting the flow establishing request processing at the SDN controller to follow an M/M/1 queuing model according to a formulaCalculating a queuing delay of the streaming request at the controller, wherein mucAnd λcRespectively representing a service rate and an arrival rate at the controller;
the user flow fiThe buffer rule is distributed at the controller, and the calculation method of the required processing time delay isWherein S isoRequesting packet size for streaming, CaComputing power for the controller;
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810613458.2A CN108809829B (en) | 2018-06-14 | 2018-06-14 | SDN rule deployment method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810613458.2A CN108809829B (en) | 2018-06-14 | 2018-06-14 | SDN rule deployment method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108809829A CN108809829A (en) | 2018-11-13 |
CN108809829B true CN108809829B (en) | 2020-09-08 |
Family
ID=64085956
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810613458.2A Active CN108809829B (en) | 2018-06-14 | 2018-06-14 | SDN rule deployment method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108809829B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110380972B (en) * | 2019-07-19 | 2021-08-31 | 重庆邮电大学 | SDN joint routing selection and rule caching method based on user stream transmission cost optimization |
CN111770515B (en) * | 2020-06-28 | 2022-03-29 | 重庆邮电大学 | SDN controller deployment method based on network cost optimization |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105207912A (en) * | 2015-09-16 | 2015-12-30 | 江苏省未来网络创新研究院 | Method for handling SDN multi-module deployment rule conflicts |
WO2018067889A1 (en) * | 2016-10-06 | 2018-04-12 | vIPtela Inc. | Method and system for synchronizing policy in a control plane |
CN108092895A (en) * | 2017-12-26 | 2018-05-29 | 重庆邮电大学 | A kind of software defined network joint route selection and network function dispositions method |
-
2018
- 2018-06-14 CN CN201810613458.2A patent/CN108809829B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105207912A (en) * | 2015-09-16 | 2015-12-30 | 江苏省未来网络创新研究院 | Method for handling SDN multi-module deployment rule conflicts |
WO2018067889A1 (en) * | 2016-10-06 | 2018-04-12 | vIPtela Inc. | Method and system for synchronizing policy in a control plane |
CN108092895A (en) * | 2017-12-26 | 2018-05-29 | 重庆邮电大学 | A kind of software defined network joint route selection and network function dispositions method |
Non-Patent Citations (1)
Title |
---|
基于SDN的信息网络及其高效缓存机制的研究与实现;贺婧;《中国优秀硕士学位论文全文数据库》;20150430;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN108809829A (en) | 2018-11-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | Toward concurrent video multicast orchestration for caching-assisted mobile networks | |
CN106572019B (en) | Time delay guarantee hybrid SDN energy-saving flow scheduling method | |
CN102714628A (en) | Communication system, control apparatus, processing rule setting method, packet transmitting method and program | |
CN108092895B (en) | Software Defined Network (SDN) joint routing selection and network function deployment method | |
CN105553845A (en) | Software defined network route selection method | |
CN105357124B (en) | A kind of MapReduce bandwidth optimization methods | |
CN105743804B (en) | Data flow control method and system | |
CN106559330A (en) | A kind of dynamic path planning method based on SDN | |
CN108809829B (en) | SDN rule deployment method | |
CN106533733A (en) | CCN collaborative cache method and device based on network clustering and Hash routing | |
Wu et al. | MBP: A max-benefit probability-based caching strategy in information-centric networking | |
CN112689163A (en) | Video service transmission system and method based on SDN and in-network cache | |
CN107124303A (en) | The service chaining optimization method of low transmission time delay | |
Kassabalidis et al. | Adaptive-SDR: Adaptive swarm-based distributed routing | |
Bhatnagar et al. | A stochastic approximation approach to active queue management | |
CN110621052A (en) | Multipath routing optimization method | |
CN108880895B (en) | SDN joint routing selection and network function deployment method based on user flow transmission overhead optimization | |
CN111770362B (en) | Video transmission system facing edge environment and transmission method thereof | |
CN109039951B (en) | Method and system for realizing QoS (quality of service) strategy of heterogeneous network | |
CN1787475B (en) | Access network system and method of moving internal network relay devices | |
Yufei et al. | A centralized control caching strategy based on popularity and betweenness centrality in ccn | |
CN106790421B (en) | ICN two-step caching method based on community | |
CN110380972B (en) | SDN joint routing selection and rule caching method based on user stream transmission cost optimization | |
Yeh et al. | VIP: Joint traffic engineering and caching in Named Data Networks | |
CN110012071B (en) | Caching method and device for Internet of things |
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 |