CN105357068A - OpenFlow network flow control method for QoS assurance of application - Google Patents
OpenFlow network flow control method for QoS assurance of application Download PDFInfo
- Publication number
- CN105357068A CN105357068A CN201510737123.8A CN201510737123A CN105357068A CN 105357068 A CN105357068 A CN 105357068A CN 201510737123 A CN201510737123 A CN 201510737123A CN 105357068 A CN105357068 A CN 105357068A
- Authority
- CN
- China
- Prior art keywords
- link
- qos
- path
- delay
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- 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
- H04L45/38—Flow based routing
-
- 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
-
- 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
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2425—Traffic characterised by specific attributes, e.g. priority or QoS for supporting services specification, e.g. SLA
-
- 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
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2491—Mapping quality of service [QoS] requirements between different networks
Abstract
The invention provides an OpenFlow network flow control method for the QoS assurance of an application. The OpenFlow network flow control method comprises the following steps that: a user requests a service from a server; the server sends a QoS request message to an SDN controller; after receiving the message, the controller calculates an optimal transmission path for the server according to a network resource use condition and reserves a resource; and simultaneously, the transmission state and the network link condition of the server are monitored when the server transmits a QoS data flow, such that a QoS flow is transmitted reliably and stably. A required network resource is provided for an application service by strictly assuring the QoS transmission of the application service and utilizing the service difference to network resource requirements; therefore, the QoS of the application is effectively ensured; and simultaneously, the network resource is utilized effectively.
Description
Technical field
The present invention relates in the method for network guarantee application QoS (QualityofService, service quality), particularly OpenFlow network as applying the flow control methods that QoS provides safeguard.
Background technology
Multimedia, the new business such as online interaction have higher qos requirement for transmission, usually require enough transmission bandwidths, alap time delay etc., are different from the service of " doing one's best " type.The method providing QoS to ensure at present concentrates on resource reservation, the aspects such as queue priority scheduling, but be all based upon in traditional network system, there is many deficiencies, as resource reservation requires that router has high-performance, result in expense large, autgmentability difference etc. shortcoming, queue management with scheduling for be convergence flow, there is the shortcomings such as Control granularity is thick, and because large multi-method is all the mechanism adopting forwarded hop-by-hop, be difficult to reach the effective utilization to global resource.Data Layer and the key-course separating thought of SDN system provide brand-new solution, and controller provides logic control function, and this mode that data Layer only need perform corresponding operation substantially increases the autgmentability of network and the flexibility of flow control.
OpenFlow agreement is vital agreement in the present invention.OpenFlow is a kind of new network agreement, originates from the CleanSlate project team of Stanford University, for carrying out transmission via net experiment.Its main thought is separated with data Layer by the key-course of the network equipment, and controlling functions all concentrates on key-course, thus can simplify the function of underlying device, enhances the extensibility of network.Since the end of the year 2009 issued first official release v1.0, OpenFlow agreement experienced by the evolution process of the versions such as 1.4 of 1.1,1.2,1.3 and up-to-date issue.Define the mode communicated between controller and switch in OpenFlow agreement, comprise controller and how to obtain bottom-layer network information, control a series of associative operations such as the data retransmission of switch.Therefore set up application layer on the controller can indirectly and controller carry out communication to obtain bottom-layer network information, and utilize these information to improve the service quality of application.
Summary of the invention
Technical problem to be solved is in SDN, provide a kind of distribution according to need resource herein, for application provides high-quality QoS transmission policy, make the QoS transmission requirement that network can flow according to application, for its allocation of network resources, to make rational planning for transmission path simultaneously, reach the maximization of network resource usage.
For solving the problems of the technologies described above, the present invention proposes the communication pattern between a kind of application service and controller, the design of its basic fundamental is: when user asks application service, first application server communicates with controller, and the transmission requirement of service is issued controller.After controller receives server message, for this QoS flow collects current network link information, calculate Optimization route, bandwidth resource, announcement server starts flow transmission simultaneously, afterwards the QoS flow transmitted and Link State are monitored, according to reliable, the stable transfer of network resource conditions timely adjustable strategies guaranteed qos stream.
Based on above-mentioned design, the technical scheme that feature of the present invention adopts is as follows:
The OpenFlow method for controlling network flow that application-oriented QoS ensures, is characterized in that, comprise the following steps:
(1) after server receives user's service request, send QoS transfer request message to SDN controller, transferring service transmission QoS requires parameter, and SDN controller is resolved QoS transfer request message, and distributes QoSID for it; The maximum packet loss that wherein qos requirement parameter comprises bandwidth demand, service transmission allows the shake of maximum delay, end-to-end permission maximum delay, allows;
(2) SDN controller sends message to switch, inquiry current network flow information, obtain the flow information of telephone net node and link in the network of SDN controller place, comprise transmission rate, switch ports themselves forwarding rate, the average delay of the remaining bandwidth of every bar link, every bar data flow;
(3) calculated data stream by, differentiate data flow whether be non-QoS flow data, be, adopt shortest path first calculate route, go to step (4); Otherwise carry out the router-level topology of QoS flow according to the following steps:
SDN controller is using the telephone net node that obtains in the qos requirement parameter in step (1) and step (2) and the link flow information parameter as router-level topology, adopt the minimum cost routing algorithm based on delay constraint, judge whether to calculate the path meeting delay requirement, it is then SDN controller initialization stream table, No. QoSID of setting stream, concrete path and ensure the queue priority information of bandwidth, be issued to switch, and reply message to server, announcement server starts transmitting data stream, goes to step (4); Otherwise reply and postpone transmitting data stream message, the QoS transfer request message of controller waiting for server again, goes to step (1);
(4) controller is monitored the QoS flow of transmission and link circuit condition, when link occur congested and exist in congestion link the middle bandwidth demand of speed and step (1) of QoS flow or QoS flow transmission inconsistent time, perform the regulation strategy preset, with effective utilization of the normal transmission of guaranteed qos stream and Internet resources;
(5) after QoS flow end of transmission, server sends resource release message to SDN controller, terminates.
In described method for controlling network flow, described server is that described SDN controller is responsible for flow control in software defined network (SDN) for user provides the equipment of application service; Described switch refers to the switch supporting OpenFlow agreement; Described stream table is one group of rule that OpenFLow network central control device generates, and is issued to switch and performs, for flow control; Server has been sent the data flow of QoS-Request message, be called QoS flow, the data flow not sending QoS-Request is non-QoS flow.Server and controller communication information are http message, and wherein qos requirement parameter with the encapsulation of the form of XML or JSON in the message.
Further, in described method for controlling network flow, the OFPT_STATS_REQUEST message that the message that SDN controller sends to switch specifically defines in OpenFLow agreement, it comprises the polytypes such as single current request message, single current request message, stream table request message, port request message, queue request message, that relate in this step is single current request OFPFlowStatsRequest and port request OFPPortStatsRequest, and wherein major parameter comprises stream table number, output slogan, stream matching domain.The OFPT_STATS_REPLY message that switch is replied mainly comprises OFPFlowStatsReply and OFPPortStatsReply message, consistent with request message.OFPFlowStatsReply message major parameter comprises flow priority, and data flow has transmitted data packet number packet_count and data flow has transmitted byte number byte_count, and data flow is transmission time duration_sec.Flow rate can be expressed as the byte number of transmitted per unit time
time delay can be expressed as the time required for transmission individual data bag
oFPPortStatsReply message major parameter comprises port transmission time duration_sec, port has received data packet number rx_packets, the data packet number tx_packets that port sends, port has received byte number rx_bytes, port has sent byte number tx_bytes, then port up-downgoing forwarding rate can be expressed as
Further, in described method for controlling network flow, to the router-level topology of non-QoS flow, using link bandwidth as weights, link metric is set to
this link metric is substituted into dijkstra's algorithm and calculates most short transmission path; Wherein C
erepresent the bandwidth capacity of link e, U
erepresent the bandwidth that link e has used, e represents a wherein link.Wherein dijkstra's algorithm is typical shortest-path rout ing algorithms, for calculating the shortest path of a node to other nodes.Main feature outwards expands layer by layer centered by starting point.Need during calculating for every bar link set up parameters, parameter can be the bandwidth of link, time delay, packet loss or other combined values.Here the capacity of link and the ratio of the remaining bandwidth parameter as link is chosen, mainly in order to reach the load balancing of network traffics,
Further, in described method for controlling network flow, the DCLC algorithm calculating route also can choose other QoS routing algorithms in light of the circumstances, it can calculate and meet delay constraint in polynomial time, and the path of delay variation and packet loss Least-cost, wherein cost optimum configurations variable element, can get different values to process the different QoS flow required, and the time complexity of algorithm reduces to O ([m+nlogn] according to the particular type of application
2), wherein n representation node number, m represents number of links, and time complexity is low compared with other QoS routing algorithms, and its detailed process is as follows:
(3.1) link cost parameter is constructed:
C
ij＝(1-β)g
ij+βp
ij，0＜β＜1；
Wherein i, j represent two nodes adjacent in link, g
ijrepresent i, the delay jitter between j, p
ijrepresentation node i, the packet loss between j; β is proportionality coefficient, and its value is variable, as little in required high QoS flow to get to delay jitter, to packet loss require higher should get larger;
(3.2) foundation meets delay constraint and the Mathematical Modeling of the route r* of Least-cost:
r*＝arg
rmin{f
c(r)|r∈r
st,f
d(r)≤d
max}；
Wherein r
strepresent all route sets between source node s and destination node t, r ∈ r
strepresent a route wherein,
for total cost of path r, d
ijrepresent adjacent node i, the time delay of link between j,
the overall delay of path r, d
maxfor QoS flow allows maximum delay, its value is that the service transmission that step (1) is determined allows maximum delay;
(3.3) adopt Lagrangian Relaxation Algorithm to solve above-mentioned QoS route matrix, detailed process is:
(3.3.1) by C
ijas link metric, substitute into the path r that dijkstra's algorithm solves Least-cost
c;
(3.3.2) path r is judged
ctime delay whether be less than d
max, be then by r
cas required path, return r
croute, turns (3.3.8); Otherwise turn (3.3.3);
(3.3.3) by d
ijas link metric, substitute into dijkstra's algorithm and solve the minimum path r of time delay
d;
(3.3.4) path r is judged
dtime delay whether be greater than d
max, be show to calculate satisfactory path, reply delayed delivery message to server, turn (3.3.8); Otherwise turn (6.3.5);
(3.3.5) relaxation parameter is made
wherein f
c(r
c) be path r
ccost value, f
c(r
d) be path r
dcost value, f
d(r
d) be path r
doverall delay, f
d(r
c) be path r
coverall delay; Link metric is set to the combination parameter value of cost parameter and delay parameter, i.e. C
λ=C
ij+ λ d
ij, it is C that substitution dijkstra's algorithm solves link metric
λtime minimum path r
λ;
(3.3.6) f is judged
λ(r
λ) and f
λ(r
c) whether equal, be then by r
das required path, turn (3.3.8); Otherwise turn (3.3.7), wherein f
λ(r
λ), f
λ(r
c) be path r respectively
λand r
cwith C
λas the total combination parameter value in path of bar link metric every in path, consistent with link overall delay concept, just overall delay is using the weights of the time delay of link as link;
(3.3.7) path r is judged
ctime delay whether be less than d
max, be make r
d=r
λ, turn (3.3.5); Otherwise make r
c=r
λ, turn (3.3.5);
(3.3.8) terminate.
Further, in described method for controlling network flow, below the regulation strategy detailed process in step (4):
(4.1) to data flow sampling, judge whether traffic transmission rate is greater than bandwidth on demand, be then perform speed limit strategy at inflow entrance place, namely between entrance, limit its speed, make it consistent with the bandwidth of request, turn (4.3); Otherwise turn (4.2);
(4.2) reduction process (3) is its reserved bandwidth, is set to current QoS flow transmission rate size;
(4.3) to link sampling, judge whether link bandwidth utilization rate reaches 80% and link exist QoS flow transmission, is represent link congestion state, turns (4.4); Otherwise turn (4.7);
(4.4) judging whether there is non-QoS data stream in all data flow on link, is perform (4.5); Otherwise perform (4.6);
(4.5) the non-QoS flow selecting transmission rate maximum, adopts shortest path first to recalculate route after deleting congestion link, turns (4.3);
(4.6) QoS flow selecting transmission rate maximum, adopts DCLC algorithm to recalculate route after deleting congestion link, turns (4.3);
(4.7) delay T turned (4.1) after second; T determines according to network concrete condition, is generally 1-3 second.
The present invention by establishing a kind of effective message mechanism between controller and application server, the QoS-Request that controller can be proposed according to application service requires and QoS-Release message, Internet resources are reasonably distributed, adopt the minimum cost QoS routing algorithm of delay constraint to ensure that the normal table transmission of QoS flow simultaneously, and in QoS flow transmitting procedure, have employed the method for traffic sampling monitoring, enable controller adjustresources distribution in time and QoS flow control strategy to ensure that user can obtain high-quality QoS service, make Internet resources be effectively utilized simultaneously.
Compared with prior art, the present invention has the following advantages: by the message mechanism between controller and application server, controller is distributed according to need Internet resources, ensure that the maximization of network resource usage.Adopt simultaneously based on delay constraint minimum cost routing algorithm and QoS flow and link state monitoring algorithm be that QoS flow transmission provides strict QoS and ensures, make switch need not realize complicated agreement, extra function be provided, realize simple, dispose easily.
Accompanying drawing explanation
Fig. 1 is schematic flow sheet of the present invention;
Fig. 2 is working timing figure of the present invention;
Fig. 3 is the topological diagram of the embodiment of the present invention;
Fig. 4 is the QoS flow transmission topological diagram of the embodiment of the present invention;
Fig. 5 is the non-QoS flow transmission topological diagram of the embodiment of the present invention;
Fig. 6 is that Link State of the present invention monitors flow chart.
Embodiment
Below in conjunction with accompanying drawing, the invention will be further described.Apply QoS flow transmission can not get effective to ensure and the resource of network can not get effective Utilizing question to solve in network, the present invention proposes the OpenFlow method for controlling network flow that a kind of application-oriented QoS ensures, the method comprises following step, as shown in Figure 1:
(1) after server receives user's service request, send QoS transfer request message to SDN controller, transferring service transmission QoS requires parameter, and SDN controller is resolved QoS transfer request message, and distributes QoSID for it; The maximum packet loss that wherein qos requirement parameter comprises bandwidth demand, service transmission allows the shake of maximum delay, end-to-end permission maximum delay, allows;
(2) SDN controller sends message to switch, inquiry current network flow information, obtain the flow information of telephone net node and link in the network of SDN controller place, comprise transmission rate, switch ports themselves forwarding rate, the average delay of the remaining bandwidth of every bar link, every bar data flow;
(3) calculated data stream by, to non-QoS flow data, adopt shortest path first calculate route, go to step (4), to the router-level topology of QoS flow, SDN controller is using the telephone net node that obtains in the qos requirement parameter in step (1) and step (2) and the link flow information parameter as router-level topology, adopt the minimum cost routing algorithm (DCLC algorithm) based on delay constraint, judge whether to calculate the path meeting delay requirement, it is then SDN controller initialization stream table, set No. QoSID of stream, the queue priority information of concrete path and guarantee bandwidth, be issued to switch, and reply message to server, announcement server starts transmitting data stream, go to step (4), otherwise reply and postpone transmitting data stream message, go to step (1),
(4) controller is monitored the QoS flow of transmission and link circuit condition, when link occur congested and exist in congestion link the middle bandwidth demand of speed and step (1) of QoS flow or QoS flow transmission inconsistent time, perform the regulation strategy preset, with effective utilization of the normal transmission of guaranteed qos stream and Internet resources;
(5) after QoS flow end of transmission, server sends resource release message to SDN controller, terminates.
Fig. 2 is the working timing figure of present system, also be the core message mechanism in the present invention, it mainly comprises QoS request message, beginning message transfer, end of transmission message and the stream list deletion success message expanded http message, be respectively used to transmission QoS parameter, announcement server starts transmission, notification controller deletes stream table message, stream list deletion pass signal; Comprise the stream of being initiated by controller that defines in OpenFlow agreement in addition and link flow status inquiry message is respectively used to inquiry QoS flow state information and port links information, controller issues stream table information to switch, and due to network link is congested or flow transmission rate variation time the message of carrying out the amendment of stream table.
In order to further illustrate concrete methods of realizing of the present invention, be now described with Fig. 3 embodiment.In the present embodiment, T gets 2 seconds, that controller is chosen is the Open Framework OpenDaylight dominated by community, and application service is Video service (not considering concrete coding and decoding video), and it is as the QoS flow of transmission, FTP service is as non-QoS flow, and network topology link bandwidth is 10Mbps.
Step one, SDN controller receive the qos requirement of application server, and ordinary video flow qos requirement is 2M bandwidth at least, and permission maximum delay is 50ms, packet loss is not more than 5%, delay variation is no more than 10ms, and FTP, as the non-QoS flow in the present embodiment, does not have qos requirement parameter.
Step 2, SDN controller obtain current full mesh topology link and flow information and (suppose now also there is not QoS flow in topology, non-QoS is only had to transmit again), each component as shown in Figure 4 on link represents the remaining bandwidth of every bar link successively, time delay, shake and packet drop, now adopt the minimum cost routing algorithm based on time delay to be that video flowing calculates route, using chain-circuit time delay as constraints, delay variation and packet loss go out video streaming path as cost calculation of parameter.First it delete the link S3-S4 of discontented sufficient bandwidth requirement, S4-S0, S2-S0, then dijkstra's algorithm is utilized to find out the path of Least-cost for S6-S5-S1-S0 from residue topology, its time delay is 29ms, meets delay requirement (this is the best-case of this router-level topology, otherwise constantly must carry out iterative computation), be then the original transmission path that path is video flowing, and notify that video server can start transmission.
Step 3, simultaneously user ask FTP to serve, then ftp server also starts to transmit its non-QoS flow, and now network topology bandwidth information is for shown in Fig. 5, due to the remaining bandwidth for being only concerned about link when non-QoS flow calculates route.This Time Controller will utilize link bandwidth weights dijkstra's algorithm for its calculate route, now path S6-S2-S1-S0 total link weights and be
for minimum in all paths, as its transmission route.When the transmission rate of non-QoS flow is below 2M, if now detect link S6-S5-S1-S0, link does not meet congestion judging condition.But cause link S1-S0 more than 8M when reaching more than 2M, cause congested, now need to carry out heavy-route to this non-QoS flow.First delete congestion link S0-S1, again calculate route with link bandwidth weights dijkstra's algorithm for it, calculating path is S6-S2-S0, so both ensure that the normal transmission of QoS flow, makes again network traffics reach load balancing simultaneously.
It should be noted last that, above embodiment is only in order to illustrate technical scheme of the present invention, although carried out detailed elaboration from all angles to each part of the present invention, those of ordinary skill in the art is to be understood that, can modify to technical scheme of the present invention or equivalent replacement, and not departing from the spirit and scope of technical solution of the present invention, it all should be encompassed in the middle of right of the present invention.
Claims (7)
1. an OpenFlow method for controlling network flow for application-oriented QoS guarantee, is characterized in that, comprise the following steps:
(1) after server receives user's service request, send QoS transfer request message to SDN controller, transferring service transmission QoS requires parameter, and SDN controller is resolved QoS transfer request message, and distributes QoSID for it; The maximum packet loss that wherein qos requirement parameter comprises bandwidth demand, service transmission allows the shake of maximum delay, end-to-end permission maximum delay, allows;
(2) SDN controller sends message to switch, inquiry current network flow information, obtain the flow information of telephone net node and link in the network of SDN controller place, comprise transmission rate, switch ports themselves forwarding rate, the average delay of the remaining bandwidth of every bar link, every bar data flow;
(3) calculated data stream by, differentiate data flow whether be non-QoS flow data, be, adopt shortest path first calculate route, go to step (4); Otherwise carry out the router-level topology of QoS flow according to the following steps:
SDN controller is using the telephone net node that obtains in the qos requirement parameter in step (1) and step (2) and the link flow information parameter as router-level topology, adopt the minimum cost routing algorithm based on delay constraint, judge whether to calculate the path meeting delay requirement, it is then SDN controller initialization stream table, No. QoSID of setting stream, concrete path and ensure the queue priority information of bandwidth, be issued to switch, and reply message to server, announcement server starts transmitting data stream, goes to step (4); Otherwise reply and postpone transmitting data stream message, the QoS transfer request message of controller waiting for server again, goes to step (1);
(4) controller is monitored the QoS flow of transmission and link circuit condition, when link occur congested and exist in congestion link the middle bandwidth demand of speed and step (1) of QoS flow or QoS flow transmission inconsistent time, perform the regulation strategy preset, with effective utilization of the normal transmission of guaranteed qos stream and Internet resources;
(5) after QoS flow end of transmission, server sends resource release message to SDN controller, terminates.
2. method for controlling network flow according to claim 1, is characterized in that, server and controller communication information are http message.
3. method for controlling network flow according to claim 1, is characterized in that, the message that the SDN controller in step (2) sends to switch, includes but not limited to wall scroll traffic flow information, stream table information, port information, queuing message.
4. method for controlling network flow according to claim 1, it is characterized in that, the algorithm calculating route in step (3) also can choose other QoS routing algorithms in light of the circumstances, can calculate and meet delay variation and the minimum path of packet loss under the condition meeting delay constraint.
5. the method for controlling network flow according to claim 1 or 4, is characterized in that, to the router-level topology of non-QoS flow, using link bandwidth as weights, is set to by link metric
this link metric is substituted into dijkstra's algorithm and calculates most short transmission path; Wherein C
erepresent the bandwidth capacity of link e, U
erepresent the bandwidth that link e has used, e represents a wherein link.
6. the flow control methods according to claim 1,4 or 5, is characterized in that, step (3) calculates the minimum cost routing algorithm based on delay constraint of route, comprises following sub-step:
(3.1) link cost parameter is constructed:
C
ij＝(1-β)g
ij+βp
ij，0＜β＜1；
Wherein i, j represent two nodes adjacent in link, g
ijrepresent i, the delay jitter between j, p
ijrepresentation node i, the packet loss between j; β is proportionality coefficient, and its value is variable, as little in required high QoS flow to get to delay jitter, to packet loss require higher should get larger;
(3.2) foundation meets delay constraint and the Mathematical Modeling of the route r* of Least-cost:
r*＝arg
rmin{f
c(r)|r∈r
st,f
d(r)≤d
max}；
Wherein r
strepresent all route sets between source node s and destination node t, r ∈ r
strepresent a route wherein,
for total cost of path r, d
ijrepresent adjacent node i, the time delay of link between j,
the overall delay of path r, d
maxfor QoS flow allows maximum delay, its value is that the service transmission that step (1) is determined allows maximum delay;
(3.3) adopt Lagrangian Relaxation Algorithm to solve above-mentioned QoS route matrix, detailed process is:
(3.3.1) by C
ijas link metric, substitute into the path r that dijkstra's algorithm solves Least-cost
c;
(3.3.2) path r is judged
ctime delay whether be less than d
max, be then by r
cas required path, return r
croute, turns (3.3.8); Otherwise turn (3.3.3);
(3.3.3) by d
ijas link metric, substitute into dijkstra's algorithm and solve the minimum path r of time delay
d;
(3.3.4) path r is judged
dtime delay whether be greater than d
max, be show to calculate satisfactory path, reply delayed delivery message to server, turn (3.3.8); Otherwise turn (6.3.5);
(3.3.5) relaxation parameter is made
wherein f
c(r
c) be path r
ccost value, f
c(r
d) be path r
dcost value, f
d(r
d) be path r
doverall delay, f
d(r
c) be path r
coverall delay; Link metric is set to the combination parameter value of cost parameter and delay parameter, i.e. C
λ=C
ij+ λ d
ij, it is C that substitution dijkstra's algorithm solves link metric
λtime minimum path r
λ;
(3.3.6) f is judged
λ(r
λ) and f
λ(r
c) whether equal, be then by r
das required path, turn (3.3.8); Otherwise turn (3.3.7), wherein f
λ(r
λ), f
λ(r
c) be path r respectively
λand r
cwith C
λas the total combination parameter value in path of bar link metric every in path, consistent with link overall delay concept, just overall delay is using the weights of the time delay of link as link;
(3.3.7) path r is judged
ctime delay whether be less than d
max, be make r
d=r
λ, turn (3.3.5); Otherwise make r
c=r
λ, turn (3.3.5);
(3.3.8) terminate.
7. the method for controlling network flow according to claim 1,4,5 or 6, is characterized in that, the regulation strategy in step (4) comprises following sub-step:
(4.1) to data flow sampling, judge whether traffic transmission rate is greater than bandwidth on demand, be then perform speed limit strategy at inflow entrance place, namely limit its speed in porch, make it consistent with the bandwidth of request, turn (4.3); Otherwise turn (4.2);
(4.2) reduction process (3) is its reserved bandwidth, is set to current QoS flow transmission rate size;
(4.3) to link sampling, judge whether link bandwidth utilization rate reaches 80% and link exist QoS flow transmission, is represent link congestion state, turns (4.4); Otherwise turn (4.7);
(4.4) judging whether there is non-QoS data stream in all data flow on link, is perform (4.5); Otherwise perform (4.6);
(4.5) the non-QoS flow selecting transmission rate maximum, adopts shortest path first to recalculate route after deleting congestion link, turns (4.3);
(4.6) QoS flow selecting transmission rate maximum, adopts DCLC algorithm to recalculate route after deleting congestion link, turns (4.3);
(4.7) delay T turned (4.1) after second; T determines according to network concrete condition, is generally 1-3 second.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510737123.8A CN105357068B (en) | 2015-11-03 | 2015-11-03 | The OpenFlow method for controlling network flow that a kind of application-oriented QoS is ensured |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510737123.8A CN105357068B (en) | 2015-11-03 | 2015-11-03 | The OpenFlow method for controlling network flow that a kind of application-oriented QoS is ensured |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105357068A true CN105357068A (en) | 2016-02-24 |
| CN105357068B CN105357068B (en) | 2018-06-12 |
Family
ID=55332944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510737123.8A Expired - Fee Related CN105357068B (en) | 2015-11-03 | 2015-11-03 | The OpenFlow method for controlling network flow that a kind of application-oriented QoS is ensured |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105357068B (en) |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105703976A (en) * | 2016-04-11 | 2016-06-22 | 浪潮集团有限公司 | Switch port state monitoring method |
| CN105897586A (en) * | 2016-05-20 | 2016-08-24 | 电子科技大学 | Hybrid SDN network-oriented Energy-saving flow scheduling method |
| CN106209440A (en) * | 2016-06-28 | 2016-12-07 | 杭州华三通信技术有限公司 | Service quality QoS implementation method in software defined network SDN and device |
| CN106341346A (en) * | 2016-09-08 | 2017-01-18 | 重庆邮电大学 | Routing algorithm of guaranteeing QoS in data center network based on SDN |
| CN106411772A (en) * | 2016-09-29 | 2017-02-15 | 四川通信科研规划设计有限责任公司 | Network traffic load balancing method based on software defined network (SDN) |
| CN106656866A (en) * | 2016-10-13 | 2017-05-10 | 烽火通信科技股份有限公司 | Software defined optical access network-based method and system for time-based bandwidth customization |
| CN106789179A (en) * | 2016-11-30 | 2017-05-31 | 中国人民解放军国防科学技术大学 | A kind of resource allocation methods based on SDN frameworks |
| CN107360473A (en) * | 2017-07-20 | 2017-11-17 | 中国传媒大学 | A kind of DASH systems of the flow scheduling of the congestion aware based on SDN |
| CN107360483A (en) * | 2017-08-21 | 2017-11-17 | 西安邮电大学 | A kind of controller load-balancing algorithm for software definition optical-fiber network |
| CN107896192A (en) * | 2017-11-20 | 2018-04-10 | 电子科技大学 | The QoS control method of differentiated service priority in a kind of SDN |
| WO2018108093A1 (en) * | 2016-12-13 | 2018-06-21 | ***通信有限公司研究院 | Congestion control method and apparatus, and computer storage medium |
| CN108366015A (en) * | 2018-05-24 | 2018-08-03 | 湖南师范大学 | Routing algorithm for software defined network |
| CN108494707A (en) * | 2018-04-03 | 2018-09-04 | 郑州云海信息技术有限公司 | A kind of elastic bandwidth management method and device based on SDN network |
| CN108521375A (en) * | 2018-04-17 | 2018-09-11 | 中国矿业大学 | The transmission of the network multi-service flow QoS based on SDN a kind of and dispatching method |
| CN108809765A (en) * | 2018-06-19 | 2018-11-13 | 刘昱 | Network quality test method and device |
| CN108833279A (en) * | 2018-05-08 | 2018-11-16 | 西安交通大学 | The method of Multi-constraint QoS paths based on business classification in software defined network |
| CN108900413A (en) * | 2018-06-05 | 2018-11-27 | 北京邮电大学 | A kind of routed path selection method, device, electronic equipment and storage medium |
| CN109067648A (en) * | 2018-07-27 | 2018-12-21 | 西安电子科技大学 | The calculation method of multiple constraint routing optimality based on DAG |
| CN109088795A (en) * | 2018-09-17 | 2018-12-25 | 电子科技大学 | A kind of controller performance analysis method based on systematic sampling |
| CN109104592A (en) * | 2018-09-30 | 2018-12-28 | 广东电网有限责任公司 | A kind of method, SDN controller, system and the equipment of mobile video transmission |
| CN109391563A (en) * | 2017-08-08 | 2019-02-26 | 华为技术有限公司 | A kind of method for obligating resource and relevant device |
| CN109769139A (en) * | 2018-11-23 | 2019-05-17 | 深圳秦云网科技有限公司 | A kind of method and device of transmitting video data |
| CN109792411A (en) * | 2016-08-22 | 2019-05-21 | 西门子股份公司 | For managing the device and method of end to end connection |
| CN110089077A (en) * | 2016-12-16 | 2019-08-02 | 华为技术有限公司 | The system and method for wavelength switched optical network traffic engineering topology are abstracted in SDN control hierarchy |
| CN110098976A (en) * | 2019-04-08 | 2019-08-06 | 京信通信***（中国）有限公司 | Measurement method, device, computer equipment and the storage medium of network parameter |
| CN110167032A (en) * | 2019-04-30 | 2019-08-23 | 陕西师范大学 | The network-building method and system of the software definition wireless self-organization network of unmanned aerial vehicle (UAV) control |
| CN110311864A (en) * | 2019-06-20 | 2019-10-08 | 山东省计算中心（国家超级计算济南中心） | Method for routing and device based on entropy assessment in a kind of SDN network |
| CN110365582A (en) * | 2019-06-20 | 2019-10-22 | 山东省计算中心（国家超级计算济南中心） | A kind of multiple constraint method for routing based on SDN network, a kind of controller |
| CN111083050A (en) * | 2019-12-26 | 2020-04-28 | 北京邮电大学 | Data stream transmission method and device based on software defined network |
| CN112099871A (en) * | 2020-09-03 | 2020-12-18 | 中国联合网络通信集团有限公司 | Service quality configuration method and device |
| CN112565008A (en) * | 2020-11-26 | 2021-03-26 | 深信服科技股份有限公司 | Network monitoring method, device and related equipment |
| CN113114587A (en) * | 2021-03-29 | 2021-07-13 | 华南理工大学 | QoS guarantee system based on SDN and broadband resource reservation method thereof |
| CN113543206A (en) * | 2020-04-21 | 2021-10-22 | 华为技术有限公司 | Method, system and device for data transmission |
| WO2021258408A1 (en) * | 2020-06-22 | 2021-12-30 | 北京交通大学 | Tolerance analysis method and apparatus for multi-service flow converged communication in industrial heterogeneous network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130201831A1 (en) * | 2012-02-02 | 2013-08-08 | Huawei Technologies Co., Ltd. | Traffic scheduling device |
| CN103618679A (en) * | 2013-11-25 | 2014-03-05 | 上海华为技术有限公司 | Service quality control method, device and system |
| CN103916302A (en) * | 2013-01-04 | 2014-07-09 | 上海贝尔股份有限公司 | Method and device for providing SDN stream route for virtual WLAN |
| CN104468352A (en) * | 2014-12-26 | 2015-03-25 | 深圳市新格林耐特通信技术有限公司 | SDN based special flow QOS guaranteeing method |
| CN104994033A (en) * | 2015-05-13 | 2015-10-21 | 南京航空航天大学 | Method for guaranteeing QoS (quality of service) of SDN (software defined network) by means of dynamic resource management |
-
2015
- 2015-11-03 CN CN201510737123.8A patent/CN105357068B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130201831A1 (en) * | 2012-02-02 | 2013-08-08 | Huawei Technologies Co., Ltd. | Traffic scheduling device |
| CN103916302A (en) * | 2013-01-04 | 2014-07-09 | 上海贝尔股份有限公司 | Method and device for providing SDN stream route for virtual WLAN |
| CN103618679A (en) * | 2013-11-25 | 2014-03-05 | 上海华为技术有限公司 | Service quality control method, device and system |
| CN104468352A (en) * | 2014-12-26 | 2015-03-25 | 深圳市新格林耐特通信技术有限公司 | SDN based special flow QOS guaranteeing method |
| CN104994033A (en) * | 2015-05-13 | 2015-10-21 | 南京航空航天大学 | Method for guaranteeing QoS (quality of service) of SDN (software defined network) by means of dynamic resource management |
Non-Patent Citations (1)
| Title |
|---|
| 李文娟: "基于多约束条件的QoS路由算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (56)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105703976B (en) * | 2016-04-11 | 2018-11-09 | 浪潮集团有限公司 | A kind of monitoring method of switch port state |
| CN105703976A (en) * | 2016-04-11 | 2016-06-22 | 浪潮集团有限公司 | Switch port state monitoring method |
| CN105897586B (en) * | 2016-05-20 | 2017-03-15 | 电子科技大学 | Energy-conservation traffic scheduling method towards mixing SDN software defined networks |
| CN105897586A (en) * | 2016-05-20 | 2016-08-24 | 电子科技大学 | Hybrid SDN network-oriented Energy-saving flow scheduling method |
| CN106209440B (en) * | 2016-06-28 | 2019-11-12 | 新华三技术有限公司 | Service quality QoS implementation method and device in software defined network SDN |
| CN106209440A (en) * | 2016-06-28 | 2016-12-07 | 杭州华三通信技术有限公司 | Service quality QoS implementation method in software defined network SDN and device |
| CN109792411A (en) * | 2016-08-22 | 2019-05-21 | 西门子股份公司 | For managing the device and method of end to end connection |
| US10764191B2 (en) | 2016-08-22 | 2020-09-01 | Siemens Aktiengesellschaft | Device and method for managing end-to-end connections |
| CN106341346A (en) * | 2016-09-08 | 2017-01-18 | 重庆邮电大学 | Routing algorithm of guaranteeing QoS in data center network based on SDN |
| CN106341346B (en) * | 2016-09-08 | 2019-07-19 | 重庆邮电大学 | A kind of routing algorithm ensureing QoS in data center network based on SDN |
| CN106411772A (en) * | 2016-09-29 | 2017-02-15 | 四川通信科研规划设计有限责任公司 | Network traffic load balancing method based on software defined network (SDN) |
| CN106411772B (en) * | 2016-09-29 | 2019-04-23 | 四川通信科研规划设计有限责任公司 | Network traffic load equalization methods based on SDN |
| CN106656866A (en) * | 2016-10-13 | 2017-05-10 | 烽火通信科技股份有限公司 | Software defined optical access network-based method and system for time-based bandwidth customization |
| CN106656866B (en) * | 2016-10-13 | 2019-07-05 | 烽火通信科技股份有限公司 | The method and system that bandwidth customizes on time are realized based on software definition Optical Access Network |
| CN106789179A (en) * | 2016-11-30 | 2017-05-31 | 中国人民解放军国防科学技术大学 | A kind of resource allocation methods based on SDN frameworks |
| CN106789179B (en) * | 2016-11-30 | 2019-07-09 | 中国人民解放军国防科学技术大学 | A kind of resource allocation methods based on SDN framework |
| CN108449279A (en) * | 2016-12-13 | 2018-08-24 | ***通信有限公司研究院 | Jamming control method and device |
| WO2018108093A1 (en) * | 2016-12-13 | 2018-06-21 | ***通信有限公司研究院 | Congestion control method and apparatus, and computer storage medium |
| CN110089077B (en) * | 2016-12-16 | 2021-06-04 | 华为技术有限公司 | System and method for abstracting wavelength switched optical network traffic engineering topology in SDN control hierarchy |
| CN110089077A (en) * | 2016-12-16 | 2019-08-02 | 华为技术有限公司 | The system and method for wavelength switched optical network traffic engineering topology are abstracted in SDN control hierarchy |
| CN107360473A (en) * | 2017-07-20 | 2017-11-17 | 中国传媒大学 | A kind of DASH systems of the flow scheduling of the congestion aware based on SDN |
| CN109391563B (en) * | 2017-08-08 | 2022-04-05 | 华为技术有限公司 | Resource reservation method and related equipment |
| US11310167B2 (en) | 2017-08-08 | 2022-04-19 | Huawei Technologies Co., Ltd. | Resource reservation method and related device |
| CN109391563A (en) * | 2017-08-08 | 2019-02-26 | 华为技术有限公司 | A kind of method for obligating resource and relevant device |
| CN107360483B (en) * | 2017-08-21 | 2020-04-24 | 西安邮电大学 | Controller load balancing algorithm for software defined optical network |
| CN107360483A (en) * | 2017-08-21 | 2017-11-17 | 西安邮电大学 | A kind of controller load-balancing algorithm for software definition optical-fiber network |
| CN107896192B (en) * | 2017-11-20 | 2020-09-25 | 电子科技大学 | QoS control method for differentiating service priority in SDN network |
| CN107896192A (en) * | 2017-11-20 | 2018-04-10 | 电子科技大学 | The QoS control method of differentiated service priority in a kind of SDN |
| CN108494707A (en) * | 2018-04-03 | 2018-09-04 | 郑州云海信息技术有限公司 | A kind of elastic bandwidth management method and device based on SDN network |
| CN108521375A (en) * | 2018-04-17 | 2018-09-11 | 中国矿业大学 | The transmission of the network multi-service flow QoS based on SDN a kind of and dispatching method |
| CN108833279A (en) * | 2018-05-08 | 2018-11-16 | 西安交通大学 | The method of Multi-constraint QoS paths based on business classification in software defined network |
| CN108833279B (en) * | 2018-05-08 | 2020-06-12 | 西安交通大学 | Method for multi-constraint QoS routing based on service classification in software defined network |
| CN108366015A (en) * | 2018-05-24 | 2018-08-03 | 湖南师范大学 | Routing algorithm for software defined network |
| CN108366015B (en) * | 2018-05-24 | 2021-04-13 | 湖南师范大学 | Route calculation method for software defined network |
| CN108900413A (en) * | 2018-06-05 | 2018-11-27 | 北京邮电大学 | A kind of routed path selection method, device, electronic equipment and storage medium |
| CN108809765B (en) * | 2018-06-19 | 2022-06-03 | 刘昱 | Network quality testing method and device |
| CN108809765A (en) * | 2018-06-19 | 2018-11-13 | 刘昱 | Network quality test method and device |
| CN109067648B (en) * | 2018-07-27 | 2020-11-10 | 西安电子科技大学 | Computing method for multi-constraint route optimization based on DAG |
| CN109067648A (en) * | 2018-07-27 | 2018-12-21 | 西安电子科技大学 | The calculation method of multiple constraint routing optimality based on DAG |
| CN109088795A (en) * | 2018-09-17 | 2018-12-25 | 电子科技大学 | A kind of controller performance analysis method based on systematic sampling |
| CN109088795B (en) * | 2018-09-17 | 2021-11-02 | 电子科技大学 | Controller performance analysis method based on equal-interval sampling |
| CN109104592A (en) * | 2018-09-30 | 2018-12-28 | 广东电网有限责任公司 | A kind of method, SDN controller, system and the equipment of mobile video transmission |
| CN109769139A (en) * | 2018-11-23 | 2019-05-17 | 深圳秦云网科技有限公司 | A kind of method and device of transmitting video data |
| CN110098976A (en) * | 2019-04-08 | 2019-08-06 | 京信通信***（中国）有限公司 | Measurement method, device, computer equipment and the storage medium of network parameter |
| CN110167032A (en) * | 2019-04-30 | 2019-08-23 | 陕西师范大学 | The network-building method and system of the software definition wireless self-organization network of unmanned aerial vehicle (UAV) control |
| CN110365582A (en) * | 2019-06-20 | 2019-10-22 | 山东省计算中心（国家超级计算济南中心） | A kind of multiple constraint method for routing based on SDN network, a kind of controller |
| CN110311864A (en) * | 2019-06-20 | 2019-10-08 | 山东省计算中心（国家超级计算济南中心） | Method for routing and device based on entropy assessment in a kind of SDN network |
| CN111083050A (en) * | 2019-12-26 | 2020-04-28 | 北京邮电大学 | Data stream transmission method and device based on software defined network |
| CN113543206A (en) * | 2020-04-21 | 2021-10-22 | 华为技术有限公司 | Method, system and device for data transmission |
| WO2021213227A1 (en) * | 2020-04-21 | 2021-10-28 | 华为技术有限公司 | Data transmission method, system and device |
| CN113543206B (en) * | 2020-04-21 | 2023-08-22 | 华为技术有限公司 | Method, system and device for data transmission |
| WO2021258408A1 (en) * | 2020-06-22 | 2021-12-30 | 北京交通大学 | Tolerance analysis method and apparatus for multi-service flow converged communication in industrial heterogeneous network |
| CN112099871A (en) * | 2020-09-03 | 2020-12-18 | 中国联合网络通信集团有限公司 | Service quality configuration method and device |
| CN112099871B (en) * | 2020-09-03 | 2023-06-02 | 中国联合网络通信集团有限公司 | Service quality configuration method and device |
| CN112565008A (en) * | 2020-11-26 | 2021-03-26 | 深信服科技股份有限公司 | Network monitoring method, device and related equipment |
| CN113114587A (en) * | 2021-03-29 | 2021-07-13 | 华南理工大学 | QoS guarantee system based on SDN and broadband resource reservation method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105357068B (en) | 2018-06-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105357068A (en) | OpenFlow network flow control method for QoS assurance of application | |
| US10044593B2 (en) | Smart ethernet edge networking system | |
| EP2911348B1 (en) | Control device discovery in networks having separate control and forwarding devices | |
| CN104468352B (en) | Special flow QOS support methods based on SDN | |
| CN104994033A (en) | Method for guaranteeing QoS (quality of service) of SDN (software defined network) by means of dynamic resource management | |
| CN109787921B (en) | CDN bandwidth scheduling method, acquisition and scheduling server and storage medium | |
| CN103516602B (en) | For transmitting method, the network equipment and the network system of data | |
| US8493869B2 (en) | Distributed constraints-based inter-domain network traffic management | |
| CN101483539B (en) | Method, path computing unit and system for obtaining path | |
| CN105897575A (en) | Path computing method based on multi-constrained path computing strategy under SDN | |
| WO2007143904A1 (en) | Method and system of multiple domain route computation | |
| WO2008111027A2 (en) | Quality of service admission control network | |
| CN101228739A (en) | Dynamic enforcement of MPLS-TE inter-domain policy and QoS | |
| CN104780056B (en) | A kind of method and apparatus of network management | |
| WO2018233580A1 (en) | Method, controller and system for establishing forwarding path in network | |
| Tomovic et al. | A new traffic engineering approach for QoS provisioning and failure recovery in SDN-based ISP networks | |
| WO2012065466A1 (en) | Method and device for allocating aggregated link bandwidth in packet-switched network | |
| WO2018107432A1 (en) | Real-time video transmission method of multipath network | |
| WO2007019758A1 (en) | A method, system and apparatus for implementing traffic engineering | |
| CN115714749A (en) | End-to-end data determination method, device and system and electronic equipment | |
| CN101127718B (en) | LSP establishment method in MPLS-TE based NGN | |
| CN102123089B (en) | Tunnel establishing method and device | |
| WO2012068834A1 (en) | Method and system for managing aggregation link | |
| Hertiana et al. | A joint approach to multipath routing and rate adaptation for congestion control in openflow software defined network | |
| TW200303670A (en) | Inverse multiplexing of managed traffic flows over a multi-star network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180612 Termination date: 20181103 |