CN111245735A - Flow scheduling method for ensuring service quality in SDN environment - Google Patents

Flow scheduling method for ensuring service quality in SDN environment Download PDF

Info

Publication number
CN111245735A
CN111245735A CN202010067312.XA CN202010067312A CN111245735A CN 111245735 A CN111245735 A CN 111245735A CN 202010067312 A CN202010067312 A CN 202010067312A CN 111245735 A CN111245735 A CN 111245735A
Authority
CN
China
Prior art keywords
flow
node
bandwidth
link
service
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
Application number
CN202010067312.XA
Other languages
Chinese (zh)
Other versions
CN111245735B (en
Inventor
陈立水
唐亚哲
陈星�
左宇飞
李宁
王静
王俊芳
吴巍
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.)
CETC 54 Research Institute
Original Assignee
CETC 54 Research Institute
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 CETC 54 Research Institute filed Critical CETC 54 Research Institute
Priority to CN202010067312.XA priority Critical patent/CN111245735B/en
Publication of CN111245735A publication Critical patent/CN111245735A/en
Application granted granted Critical
Publication of CN111245735B publication Critical patent/CN111245735B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/12—Avoiding congestion; Recovering from congestion
    • 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
    • H04L47/215—Flow control; Congestion control using token-bucket

Abstract

The invention discloses a flow scheduling method for ensuring service quality in an SDN environment, belongs to the field of computer network flow scheduling, and particularly relates to a method for routing based on QoS and completing consistency updating of a flow transmission path. The invention mainly integrates network resource fragments for the service flow reserved by a user under the condition of higher network bandwidth occupancy rate, decides a flow scheduling scheme, dynamically updates flow table entries to ensure the updating consistency of a flow table and prevent deadlock when the flow is scheduled, and prevents burst flow from occupying bandwidth and ensures the service quality in the transmission process by end node flow shaping. By the mode, the invention can improve the utilization rate of network bandwidth by integrating network resource fragments, accommodate more streams and simultaneously ensure lower packet loss rate of service streams.

Description

Flow scheduling method for ensuring service quality in SDN environment
Technical Field
The invention belongs to the field of computer network flow scheduling, and particularly relates to a QoS-based routing and method for completing consistency update of a flow transmission path.
Background
With the development of data centers, network services requested by users are increasing continuously, and the traffic in the network increases rapidly, however, bandwidth resources provided by the whole network are often limited, and when the demands of the users on the network resources exceed the upper limit provided by the network, the network may be congested, causing packet loss or increased delay. Traditional traffic scheduling techniques mainly include Native IP and MPLS-TE. The former is based on Dijkstra algorithm, and selects a shortest path according to constraints such as hop count, thereby causing local link congestion. The latter is based on CSPF algorithm, synthesizes link bandwidth resource information when selecting route, improves congestion problem. Because the traditional network node always calculates the shortest path by taking itself as a center, the obtained result is often a local optimal result, and under the condition of complex technology, due to the distributed structure of the traditional network, the traditional network node sometimes needs to be deployed by switches, and the process is quite complicated.
The core idea of the SDN network architecture is that control and forwarding are separated, only the improvement of forwarding rate needs to be concerned for the bottom equipment, and a control layer is responsible for complex control functions and protocol updating. The logically centralized controller has a global view angle, developers obtain global network resources and network state information through an open northbound interface, and the traffic scheduling technology can flexibly allocate and integrate the network resources according to the basic information and the requirements of users, thereby providing service quality guarantee and improving the bandwidth utilization rate. In the existing related research of flow scheduling in the SDN environment, the balance use of the bandwidth resources of the whole network as much as possible under one or more constraint conditions is mainly considered, and in the scenes of relatively congested networks and relatively more fragmented link resources, an existing scheduling algorithm is adopted, so that a new service flow may not be able to be directly added into the network.
When a transmission path of the SDN architecture downstream changes, the controller needs to instruct the data plane to update the path, where the updating of the data flow transmission path includes deleting an old flow table and installing a new flow table. However, updating the flow tables on the SDN switch is generally any order in which the switches are selected for updating, which may cause many problems, for example, the inconsistency problem of the data plane may cause problems of black holes of the flow, flow loops, deadlock, link congestion, and the like. The existing consistency updating algorithm cannot solve the problems under the condition of ensuring low packet loss rate.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a traffic scheduling method, which can integrate fragmented bandwidths in a network, and improve the bandwidth utilization rate, so that a greater number of streams can be accommodated in the network. Meanwhile, the consistency updating problem in the flow migration process is solved by using the Petri network modeling.
The technical scheme adopted by the invention is as follows:
a flow scheduling method for guaranteeing service quality in an SDN environment comprises the following steps:
(1) when receiving a new service flow subscribed by a user, if the new service flow can not be directly added into the network, recalculating transmission path information of all service flows in the network, and determining a flow scheduling scheme;
(2) after a flow scheduling scheme is determined, constructing a dependency graph according to the calculated transmission path information and the original transmission path information, and deciding the updating sequence of the flow table;
(3) and updating the dependency graph, if the problem of deadlock loops is found in the updating process, submitting the switch nodes generating deadlock to a controller for assisting forwarding through loop detection, and updating the link bandwidth information.
Wherein, the step (1) comprises the following steps:
(101) when a new service flow S reserved by a user enters a network, calculating the shortest path of the new service flow S, and judging whether the new service flow S can be directly added into the network, if so, ending, otherwise, executing the step (102);
(102) all service flows including the new service flow are arranged completely, and all link bandwidth resources in the network are set as initial values; wherein the full-permutation sequence is that the bandwidth is from large to small, the first service flow in the full-permutation sequence is a father node, and the rest service flows are leaf nodes, and the processing is firstly carried out according to the flow sequence specified by the full-permutation sequence;
(103) for the ith flow, calculating the shortest path from the source node to the destination node; let its required bandwidth be biThe source switch is uiThe destination switch is viAfter the first i-1 flows join the network, set B for any link e (u, v) on the network topologye(u,v)The bandwidth of the link already occupied by the first i-1 streams satisfies formula Ce(u,v)-Be(u,v)≥biAnd (3) constraint: wherein
Figure BDA0002376359600000031
u∈V v∈V；Ce(u,v)The initial bandwidth of a link, E is a link set between forwarding nodes, and V is a set of all switch nodes in the network;
(104) for the ith flow, if a transmission path which meets the bandwidth from the source node to the destination node exists, updating the use condition of the link bandwidth, and executing the step (105); if not, rearranging the leaf nodes to obtain a new full-permutation sequence, and taking the next leaf node of the father node in the new full-permutation sequence as the ith flow to carry out the step (103);
(105) detecting whether the traversal of the full-permutation sequence is completed, if so, ending; if not, step (103) is performed for the traffic flow of the next leaf node in the sequence.
Wherein, the step (2) is specifically as follows: creating a dependency graph of link nodes and flow nodes, and then sequencing the service flows according to the occupied bandwidth; wherein the link node is represented as ((u, v), b), where u, v are the neighboring nodes of the link, b is the current remaining bandwidth of the link, and the stream node is represented as (f)i,bi) Wherein f isiAs the ith stream, biThe bandwidth required for the stream; each flow node in the dependency graph is a dependent link node in the old and new transmission paths.
Wherein, the step (3) comprises the following steps:
(301) selecting a node occupying the largest bandwidth, and then checking whether the residual bandwidth of a front link of the node can meet the migration requirement; if yes, completing the migration of the flow, updating the corresponding preposed link node and the postpositional link node, and deleting the node from the migration flow node set; if not, selecting the node occupying the largest bandwidth from the rest nodes and repeating the step (301);
(302) checking whether the size of the flow node set changes or not, if the size does not change, indicating that deadlock occurs, and using a controller as an out-of-band transmission point to assist in forwarding flow; if the set element is decreased, performing step (303);
(303) checking whether elements exist in the migration flow node set or not, and if so, repeating the steps (301) to (302) until the set is empty; otherwise, the flow table of the service flow forwarded by the aid of the controller is issued to the switch node.
Wherein, the controller in step (302) is used as an out-of-band transmission point to assist in forwarding the traffic, and the specific processing procedure is as follows: in the process of updating the dependency graph, any one service flow cannot be moved due to insufficient link bandwidth, one or more flows are determined to be temporarily uploaded to the controller in a plurality of service flows generating deadlock, the controller assists in forwarding, the data packet is directly forwarded to a target switch node until a deadlock loop is untied, and then the controller issues switch flow tables on new transmission paths of the service flows so as to finish updating of the transmission paths of all the service flows.
Compared with the prior art, the invention has the advantages that:
(1) the method comprises the steps of firstly utilizing the control characteristic of an SDN controller on the global resources, reallocating the global bandwidth resources, deploying the transmission path of the service flow, and enabling the network to contain more flows by integrating bandwidth resource fragments.
(2) According to the invention, after the transmission path is changed, the corresponding flow table needs to be updated, the dynamic updating of the flow table can cause consistency updating problems of flow black holes, link congestion, loops and the like, and the system carefully coordinates the updating sequence of each switch rule through Petri network modeling.
(3) The invention regards the controller as a forwarding node in a short time by means of an out-of-band transmission path, and completes consistency updating on the premise of ensuring low packet loss rate.
(4) The invention limits the flow out of the network by using the token bucket algorithm, ensures that the bandwidth occupation among all the service flows can not be mutually occupied, and always meets the bandwidth requirement.
(5) The invention can integrate fragmented bandwidth in the network, improve the bandwidth utilization rate and enable the network to contain more streams. Meanwhile, when the transmission path is dynamically switched, the consistency updating of the flow table is ensured.
Drawings
FIG. 1 is a schematic diagram of the overall architecture of the system of the present invention;
FIG. 2 is a flow chart of a QoS based routing algorithm;
FIG. 3 is a schematic flow chart of a consistency update algorithm;
FIG. 4 is a schematic flow migration diagram;
FIG. 5 is an exemplary diagram of a flow migration deadlock;
figure 6 is a schematic diagram of SDN host communication.
Detailed Description
The invention will be further explained and explained with reference to the attached drawings
Fig. 1 is a diagram of the overall architecture of a system, in an application layer 101, the system operating in an SDN environment. In the control layer 102, the QoS-based routing module first calculates new transmission paths of all service flows in the network according to the new flow reservation information, determines a traffic scheduling scheme, and transmits the calculated path information and the original path information to the consistency updating module. Then, the consistency updating module decides the updating sequence of the flow table for the dynamic migration of the flow, and simultaneously issues the corresponding updated flow table to the switch of the forwarding layer 103 through the southbound interface, and after the switch flow table is installed, the data packet will be transmitted according to a new path. When the deadlock problem occurs and the updating of the paths of all the service flows cannot be completed, the module submits the current service flow dependence information to the conflict processing module for processing. And the conflict processing module temporarily submits the nodes generating the deadlock to the controller for assisting forwarding through loop detection, and simultaneously updates the link bandwidth information in the consistency updating module. The node flow shaping module is used as an independent module to be responsible for limiting the end node flow speed, limiting the rate of each service flow entering a network, ensuring that each service flow does not invade the bandwidth, and avoiding link congestion.
Fig. 2 is a flow chart of a QoS-based routing algorithm.
Step 201 begins with a new stream S subscribing to the network.
In step 202, the S shortest path is calculated.
Step 203, judging whether the user can directly join the network, if so, ending the process. If the new stream subscribed by the user cannot be directly joined to the current network, step 204 is performed.
Step 204, all service flows including the reservation flow are arranged completely, and all link bandwidth resources in the network are initial values. Wherein the full-permutation sequence is that the bandwidth is from large to small, the first service flow in the full-permutation sequence is a father node, and the rest service flows are leaf nodes, and the processing is firstly carried out according to the flow sequence specified by the full-permutation sequence;
step 205, for the ith flow, calculating the shortest path from the source node to the destination node; let its required bandwidth be biThe source switch is uiThe destination switch is viAfter the first i-1 flows join the network, set B for any link e (u, v) on the network topologye(u,v)The bandwidth of the link already occupied by the first i-1 streams satisfies formula Ce(u,v)-Be(u,v)≥biAnd (3) constraint: wherein
Figure BDA0002376359600000071
u∈V v∈V；Ce(u,v)For link initial bandwidth, E is that of the forwarding nodeThe link between the nodes is collected, and V is the collection of all the switch nodes in the network;
in step 206, for the ith flow, if there is a transmission path from the source node to the destination node that satisfies the bandwidth, step 208 is performed to update the link bandwidth usage, and then step 209 is performed. If not, go to step 207, trace back to the next full permutation sequence with the common parent node, take the next node of the parent node as the ith flow, and then go to step 205. For example: 3, 2, 1 are the bandwidths occupied by the three streams, respectively, and the initial sequence is 3, 2, 1. If the sequence is calculated as 3, 2 finding a path and 1 not, then consider the order of 3, 1, 2. Since a stream occupies multiple links, it is possible to change the transmission path from 2 to 2, and all streams can be accommodated. In this example, 3 is the parent node, 2, 1 and 1, 2 are two subsequences;
step 209 detects whether the sequence is traversed, if so, the process is ended; if not, step 210 is performed, i ═ i +1, and then step 205 is returned to.
FIG. 3 is a schematic flow chart of a consistency update algorithm.
Step 301, creating a dependency graph of the link nodes and the stream nodes, and then performing step 302.
Step 302, the traffic is sorted according to the occupied bandwidth.
Step 303, selecting the node occupying the largest bandwidth, and then executing step 304;
step 304, checking whether the residual bandwidth of the front link can meet the migration requirement.
If so, the flow migration is completed in step 305 and the relevant pre-configured post-link nodes are updated in steps 306 and 307, and the node is removed from the migration flow node set. Illustrating how the flow migration order decision is made as shown in fig. 4. Setting the initial value of the bandwidth of each link in the network to 10M, wherein the network has four flows, F1, F2, F3, and F4, respectively occupying bandwidths 6M, 10M, and 4M, and the transmission paths corresponding to the flows before and after the flow migration are as shown in fig. 4, in the migration process, if the flow tables are updated randomly according to a certain sequence, for example, (F1, F2, F3, and F4), the links (s1, s5) and (s2, s5) will have link congestion in the update process, which may cause packet loss or increase delay, and the service quality of the traffic flow cannot be guaranteed. A reasonable update sequence can be found through the Petri net model so as to avoid the above problem.
If not, the next largest node occupying bandwidth is selected and step 303 is repeated.
Step 308 checks whether the size of the stream node set changes, if the size does not change, it indicates that deadlock occurs, and steps 309 and 310 are executed to utilize the controller as an out-of-band transmission point to assist in forwarding traffic and update the residual bandwidth resources of the front node and the rear node. The stream migration deadlock is generated, as shown in fig. 5, three streams cannot perform traffic migration because they wait for each other to release occupied bandwidth and generate deadlock.
If the set elements are reduced, executing step 311, checking whether the stream node set has elements, if so, repeating steps 303 to 308 until the set is empty; otherwise, step 312 is executed to issue a flow table of the traffic flow forwarded with the assistance of the controller.
Fig. 6 is a schematic diagram of a host communication mode in an SDN environment.
After generating a data Packet, the host h 1402 transmits the data Packet to the OpenFlow Switch 403 directly connected to the host h 1402, and after receiving the data Packet, the OpenFlow Switch 1403 does not have a related Flow table to process the data Packet, so that a Packet-in message is generated to upload the data Packet to the controller 401 through a secure channel, the controller 401 determines a transmission path of the data Packet according to the information of the data Packet, including a source IP address, a destination IP address, a source MAC address, a destination MAC address, and the like, and then issues a Flow-mod message carrying Flow table information to all OpenFlow switches 404 on the transmission path, installs a new Flow table entry, guides the transmission of the data Packet at a forwarding layer, and simultaneously, after completing encapsulation of a Packet-out message carrying data Packet information, sends the Packet-out message to the OpenFlow Switch 1403. When the deadlock occurs in updating the flow table, the scheme provided by the invention is that one or more flows in a loop are found out from a plurality of service flows generating the deadlock, the flows are temporarily uploaded to the controller 401, the controller 401 assists in forwarding, the data packet is directly forwarded to a target switch until the deadlock loop is untied, and then the controller 401 issues the switch flow tables on a new transmission path of the flows. And finally transmitted to the host h 2403.
The above description is only for the purpose of illustrating preferred embodiments of the present invention and is not to be construed as limiting the present invention, which may be modified, combined and varied by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (5)

1. A flow scheduling method for guaranteeing service quality in an SDN environment is characterized by comprising the following steps:
(1) when receiving a new service flow subscribed by a user, if the new service flow can not be directly added into the network, recalculating transmission path information of all service flows in the network, and determining a flow scheduling scheme;
(2) after a flow scheduling scheme is determined, constructing a dependency graph according to the calculated transmission path information and the original transmission path information, and deciding the updating sequence of the flow table;
(3) and updating the dependency graph, if the problem of deadlock loops is found in the updating process, submitting the switch nodes generating deadlock to a controller for assisting forwarding through loop detection, and updating the link bandwidth information.
2. The traffic scheduling method for guaranteeing service quality in an SDN environment according to claim 1, wherein step (1) specifically includes the steps of:
(101) when a new service flow S reserved by a user enters a network, calculating the shortest path of the new service flow S, and judging whether the new service flow S can be directly added into the network, if so, ending, otherwise, executing the step (102);
(102) all service flows including the new service flow are arranged completely, and all link bandwidth resources in the network are set as initial values; wherein the full-permutation sequence is that the bandwidth is from large to small, the first service flow in the full-permutation sequence is a father node, and the rest service flows are leaf nodes, and the processing is firstly carried out according to the flow sequence specified by the full-permutation sequence;
(103) for the ith flow, calculating the shortest path from the source node to the destination node; let its required bandwidth be biThe source switch is uiThe destination switch is viAfter the first i-1 flows join the network, set B for any link e (u, v) on the network topologye(u,v)The bandwidth of the link already occupied by the first i-1 streams satisfies formula Ce(u,v)-Be(u,v)≥biAnd (3) constraint: wherein
Figure FDA0002376359590000011
Ce(u,v)The initial bandwidth of a link, E is a link set between forwarding nodes, and V is a set of all switch nodes in the network;
(104) for the ith flow, if a transmission path which meets the bandwidth from the source node to the destination node exists, updating the use condition of the link bandwidth, and executing the step (105); if not, rearranging the leaf nodes to obtain a new full-permutation sequence, and taking the next leaf node of the father node in the new full-permutation sequence as the ith flow to carry out the step (103);
(105) detecting whether the traversal of the full-permutation sequence is completed, if so, ending; if not, step (103) is performed for the traffic flow of the next leaf node in the sequence.
3. The traffic scheduling method for guaranteeing service quality in an SDN environment according to claim 1, wherein the step (2) is specifically: creating a dependency graph of link nodes and flow nodes, and then sequencing the service flows according to the occupied bandwidth; wherein the link node is represented as ((u, v), b), where u, v are the neighboring nodes of the link, b is the current remaining bandwidth of the link, and the stream node is represented as (f)i,bi) Wherein f isiAs the ith stream, biThe bandwidth required for the stream; each flow node in the dependency graph is a dependent link node in the old and new transmission paths.
4. The traffic scheduling method for guaranteeing service quality in an SDN environment according to claim 3, wherein the step (3) specifically includes the steps of:
(301) selecting a node occupying the largest bandwidth, and then checking whether the residual bandwidth of a front link of the node can meet the migration requirement; if yes, completing the migration of the flow, updating the corresponding preposed link node and the postpositional link node, and deleting the node from the migration flow node set; if not, selecting the node occupying the largest bandwidth from the rest nodes and repeating the step (301);
(302) checking whether the size of the flow node set changes or not, if the size does not change, indicating that deadlock occurs, and using a controller as an out-of-band transmission point to assist in forwarding flow; if the set element is decreased, performing step (303);
(303) checking whether elements exist in the migration flow node set or not, and if so, repeating the steps (301) to (302) until the set is empty; otherwise, the flow table of the service flow forwarded by the aid of the controller is issued to the switch node.
5. The method for traffic scheduling according to claim 4, wherein the controller in step (302) assists in forwarding the traffic as an out-of-band transmission point, and the specific processing procedure is as follows: in the process of updating the dependency graph, any one service flow cannot be moved due to insufficient link bandwidth, one or more flows are determined to be temporarily uploaded to the controller in a plurality of service flows generating deadlock, the controller assists in forwarding, the data packet is directly forwarded to a target switch node until a deadlock loop is untied, and then the controller issues switch flow tables on new transmission paths of the service flows so as to finish updating of the transmission paths of all the service flows.
CN202010067312.XA 2020-01-20 2020-01-20 Flow scheduling method for ensuring service quality in SDN environment Active CN111245735B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010067312.XA CN111245735B (en) 2020-01-20 2020-01-20 Flow scheduling method for ensuring service quality in SDN environment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010067312.XA CN111245735B (en) 2020-01-20 2020-01-20 Flow scheduling method for ensuring service quality in SDN environment

Publications (2)

Publication Number Publication Date
CN111245735A true CN111245735A (en) 2020-06-05
CN111245735B CN111245735B (en) 2022-08-12

Family

ID=70874877

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010067312.XA Active CN111245735B (en) 2020-01-20 2020-01-20 Flow scheduling method for ensuring service quality in SDN environment

Country Status (1)

Country Link
CN (1) CN111245735B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111770070A (en) * 2020-06-22 2020-10-13 中国电子科技集团公司第五十四研究所 SDN-based security service chain aggregation deployment method
CN111918340A (en) * 2020-07-08 2020-11-10 河北百亚信息科技有限公司 WiFi wireless network bandwidth allocation method
CN111935022A (en) * 2020-07-28 2020-11-13 华中科技大学 Flow table consistency updating method in software defined network
CN113612691A (en) * 2021-08-06 2021-11-05 浙江工商大学 Path conversion method, storage medium and terminal equipment
CN113973092A (en) * 2020-07-24 2022-01-25 中国移动通信集团浙江有限公司 Link resource scheduling method and device, computing equipment and computer storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104158753A (en) * 2014-06-12 2014-11-19 南京工程学院 Dynamic flow dispatch method and system based on software definition network
CN105227481A (en) * 2015-09-02 2016-01-06 重庆邮电大学 The SDN congestion control method for routing of cost minimization is dispatched based on path cost and stream
CN106789658A (en) * 2016-12-29 2017-05-31 南京邮电大学 Satellite MPLS network flow equalization method based on SDN controllers
CN107018073A (en) * 2017-03-14 2017-08-04 电子科技大学 A kind of SDN flow control systems concatenated based on subpath
CN107332766A (en) * 2017-06-05 2017-11-07 西安交通大学 A kind of method of raising network throughput under the scheduling based on software defined network stream
US20190190819A1 (en) * 2017-12-18 2019-06-20 At&T Intellectual Property I, L.P. Deadlock-Free Traffic Rerouting in Software-Defined Networking Networks

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104158753A (en) * 2014-06-12 2014-11-19 南京工程学院 Dynamic flow dispatch method and system based on software definition network
CN105227481A (en) * 2015-09-02 2016-01-06 重庆邮电大学 The SDN congestion control method for routing of cost minimization is dispatched based on path cost and stream
CN106789658A (en) * 2016-12-29 2017-05-31 南京邮电大学 Satellite MPLS network flow equalization method based on SDN controllers
CN107018073A (en) * 2017-03-14 2017-08-04 电子科技大学 A kind of SDN flow control systems concatenated based on subpath
CN107332766A (en) * 2017-06-05 2017-11-07 西安交通大学 A kind of method of raising network throughput under the scheduling based on software defined network stream
US20190190819A1 (en) * 2017-12-18 2019-06-20 At&T Intellectual Property I, L.P. Deadlock-Free Traffic Rerouting in Software-Defined Networking Networks

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111770070A (en) * 2020-06-22 2020-10-13 中国电子科技集团公司第五十四研究所 SDN-based security service chain aggregation deployment method
CN111918340A (en) * 2020-07-08 2020-11-10 河北百亚信息科技有限公司 WiFi wireless network bandwidth allocation method
CN113973092A (en) * 2020-07-24 2022-01-25 中国移动通信集团浙江有限公司 Link resource scheduling method and device, computing equipment and computer storage medium
CN111935022A (en) * 2020-07-28 2020-11-13 华中科技大学 Flow table consistency updating method in software defined network
CN111935022B (en) * 2020-07-28 2021-05-18 华中科技大学 Flow table consistency updating method in software defined network
CN113612691A (en) * 2021-08-06 2021-11-05 浙江工商大学 Path conversion method, storage medium and terminal equipment

Also Published As

Publication number Publication date
CN111245735B (en) 2022-08-12

Similar Documents

Publication Publication Date Title
CN111245735B (en) Flow scheduling method for ensuring service quality in SDN environment
US10263889B2 (en) Data forwarding method, device, and system in software-defined networking
US7965654B2 (en) System and method for designing a network
CN109257287B (en) Shortest path determining method and controller
US7230924B2 (en) Method and apparatus for communications traffic engineering
CN108833279B (en) Method for multi-constraint QoS routing based on service classification in software defined network
CN111147370B (en) Method and control device for determining forwarding path
US7958209B2 (en) Methods and systems to generate and implement a changeover sequence to reconfigure a connection-oriented network
CN103765834B (en) For minimizing the soft method and device seized seized in data network
CN107332766B (en) Method for improving network throughput based on software defined network flow scheduling
CN112291791B (en) Power communication mesh bandwidth resource allocation method based on 5G slice
CN109274589B (en) Service transmission method and device
WO2007019758A1 (en) A method, system and apparatus for implementing traffic engineering
CN110581806B (en) Method, device and equipment for automatically segmenting network and storage medium
CN102415063B (en) Method for controlling admission and assigning resources to data flows, without a priori knowledge, in a virtual network
CN108494597A (en) Intelligent Optical Network analogue system and method
CN105207906A (en) Service path determining method and device
Cameron et al. Prioritized deflection routing in optical burst switching networks
CN105610712B (en) The method for reducing whole network data stream forward delay based on software defined network framework
CN112039774B (en) Tunnel and SR combined network flow adjusting and optimizing method
CN111490902B (en) 664 Network message construction algorithm
Nleya et al. A bursts contention avoidance scheme based on streamline effect awareness and limited intermediate node buffering in the core network
CN106453145A (en) Transmission link control method and transmission link control device
Reinemo Quality of service in interconnection networks
JP2005277714A (en) Band securing method for lsp design server system

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