CN110535778A - Transmission rate allocation method for Transmission Control Protocol in data center network - Google Patents
Transmission rate allocation method for Transmission Control Protocol in data center network Download PDFInfo
- Publication number
- CN110535778A CN110535778A CN201910805843.1A CN201910805843A CN110535778A CN 110535778 A CN110535778 A CN 110535778A CN 201910805843 A CN201910805843 A CN 201910805843A CN 110535778 A CN110535778 A CN 110535778A
- Authority
- CN
- China
- Prior art keywords
- transmission rate
- priority
- service
- data center
- different
- 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
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/19—Flow control; Congestion control at layers above the network layer
- H04L47/193—Flow control; Congestion control at layers above the network layer at the transport layer, e.g. TCP related
-
- 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
-
- 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
- H04L47/27—Evaluation or update of window size, e.g. using information derived from acknowledged [ACK] packets
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/80—Actions related to the user profile or the type of traffic
- H04L47/805—QOS or priority aware
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
Abstract
Transmission rate allocation method for Transmission Control Protocol in data center network, include the following steps: the transmission rate and congestion window information of aggregation node collection service with different priority levels first, secondly aggregation node obtains the ratio of high-priority service and low priority traffice, and counts the transmission rate of the service with different priority levels monitored in the period every duration;Aggregation node obtains the adjusting method of different TCP flow congestion windows according to the transmission rate of the different business of acquisition later, to carry out transmission rate allocation.The message transmission rate of aggregation node real-time monitoring record service with different priority levels of the present invention, and different transmission rates is distributed for the Business Stream of different priorities, to ensure the QoS of high-priority service.The distribution method highest can be by the throughput hoisting of high-priority service to 25%, and the time delay of high-priority service is maintained at 0.1 second hereinafter, packet loss is maintained at 5% or so.
Description
Technical field
The present invention relates to mobile communication technology field, it is particularly used for the transmission of Transmission Control Protocol in data center network
Method of rate allocation.
Background technique
Transmission control protocol (Transmission Control Protocol, TCP) is common in data center network
Transport protocol.However, due to the Fairshare principle of Transmission Control Protocol, TCP can not ensure different preferential under the same network environment
The service quality of grade business.
Data center network technology web search, online retail, ad system, in terms of popularization with answer
With providing the network service of high quality for user.These services all use online interaction formula application OLDI (online data-
Intensive), and there are two major features: first is that application program all has the different cut-off time limits, it can not be complete within the cut-off time limit
Stream at transmission will not counted in the result of feedback, second is that these applications are using based on tree, i.e. division-polymerization design
Mode.Under normal conditions, the request of user can be assigned to multiple work station parallel processings.Data center network service it is above-mentioned
Feature is that the design of transport layer protocol proposes huge challenge.
For the application demand of data center network, transport layer protocol designer proposes two point targets: (1) reducing stream
Average completion time;(2) transmission window is limited according to the cut-off time limit of not cocurrent flow.Under the guide of preceding aim, at present
Data-oriented central site network transport layer protocol research main flow direction first is that in traditional TCP (Transmission
Control Protocol) adaptive improvement is carried out for the characteristic of data center network on the basis of agreement, to adapt to data
The demand of central site network, such as: DCTCP (data center TCP) agreement, D3Agreement and much to the optimization of Transmission Control Protocol.
Above-mentioned agreement is from the characteristic of data center network, by the transmission flow or optimization Transmission Control Protocol ginseng of improving Transmission Control Protocol
Number, to improve the performance of Transmission Control Protocol in data center network.But above-mentioned agreement fails to consider the clothes of guarantee business
It is engaged in quality (Quality of Service, QoS).However, in data center network, if can not ensure that user asks in sending
Related data is obtained in deadline after asking, then directly affects the performance and user experience of network service, lead to the stream of user
The decline for network profit of becoming estranged.
Researcher proposes the scheme of many Protocol Designs for the QoS problem ensured in data center network.But
These research work mainly consider the optimization of single Business Stream, overall load situation and congestion shape without considering network
Condition is unable to satisfy user's QoS demand.
Summary of the invention
Aiming at the problem that current data center network transmission mechanism can not effectively ensure Business Stream QoS, the present invention is mentioned
The transmission rate allocation method for Transmission Control Protocol in data center network is gone out.Compared with prior art, the distribution method highest
Can by the throughput hoisting of high-priority service to 25%, and the time delay of high-priority service is maintained at 0.1 second hereinafter,
Packet loss is maintained at 5% or so.
To achieve the goals above, the present invention use the specific scheme is that biography for Transmission Control Protocol in data center network
Defeated method of rate allocation, the distribution method include the following steps:
Step 1, aggregation node collect the transmission rate and congestion window information of service with different priority levels, the different priorities industry
Business includes high-priority service and low priority traffice;
Step 2, aggregation node obtain the ratio of high-priority service and low priority traffice, and count the time every S duration
The transmission rate of the service with different priority levels monitored in section, wherein S is the period that aggregation node calculates service transmission rate;
Step 3, aggregation node obtain the adjusting side of different TCP flow congestion windows according to the transmission rate of the different business of acquisition
Method, to carry out transmission rate allocation.
As a preferred embodiment, in step 2, high-priority service transmission rate summation isLow priority
Service transmission rate summation isWherein, N is that there are the sum of high-priority service, T (i) in data center network
For the transmission rate of each high-priority service, M is in data center network there are the sum of low priority traffice, and T (j) is every
A low priority traffice transmission rate.
As a preferred embodiment, the specific monitoring method of step 2 real-time monitoring service with different priority levels transmission rate is such as
Under: if step 21, Thigh>=NT*, wherein T*For target transmission speed, then return step 1;Otherwise, step 22 is executed;
After step 22, aggregation node get the transmission rate of service with different priority levels, high-priority service and low excellent is calculated
First grade business proportion relationship β are as follows:
Step 23, in order to judge that can the configuration of current network meet the transmission rate requirements of high-priority service, calculate Gao You
First service transmission rate Lifting Coefficients γ is as follows:
Step 24 defines congestion parameter α, and records the congestion condition of aggregation node network entirety:
α=(1-g) × α+g × F;
Wherein, 0≤α≤1, F are the grouping ratio that congestion occurs in the S time, and g is weight proportion shared by a upper alpha parameter.
As a preferred embodiment, in step 23, when γ is greater than 0, aggregation node re-starts transmission rate allocation.
As a preferred embodiment, the adjusting method that step 3 calculates different TCP flow congestion windows includes the following steps:
Step 31, the congestion window that high-priority service can be obtained according to step 2 need to be promoted to before (1+ γ) times, it may be assumed that
W(i)*=W (i) × (1+ γ);
Wherein, W (i) is the congestion window of i-th of high-priority service;
The congestion window reduction of step 32, integrated network entiretyBefore increasing to the congestion window of the business of high priority
(1+ γ) times calculates the overall congestion window value for needing to reduce;
Step 33 calculates the reduced congestion window numerical value of each low priority traffice needs according to step 32, to get height
The adjusting method of priority and low priority congestion window, backward work station feedback regulation result.
As a preferred embodiment, in step 32, the overall congestion window value calculating method that needs to reduce are as follows:
Wherein, W (j) is the congestion window of j-th of low priority traffice;In conjunction with W (i)*=W (i) × (1+ γ), can obtain:
As a preferred embodiment, in step 33, each low priority traffice is calculated and needs reduced congestion window
Numerical value are as follows:
W(j)*=W (j) × (1- η);
Wherein,η is that low priority traffice transmission rate reduces ratio.
The utility model has the advantages that the present invention provides the transmission rate allocation method for Transmission Control Protocol in data center network, convergence
Node real-time monitoring record service with different priority levels message transmission rate, and for different priorities Business Stream distribute it is different
Transmission rate, to ensure the QoS of high-priority service.The distribution method highest can be by the throughput hoisting of high-priority service
0.1 second is maintained at hereinafter, packet loss is maintained at 5% or so to 25%, and by the time delay of high-priority service.
Detailed description of the invention
Fig. 1 is the simulation result diagram of handling capacity of the present invention;
Fig. 2 is the simulation result diagram of average delay of the present invention;
Fig. 3 is the simulation result diagram of packet loss of the present invention.
Specific embodiment
The present invention will be described in detail below with reference to specific embodiments, the present embodiment based on the technical solution of the present invention,
The detailed implementation method and specific operation process are given.
For the transmission rate allocation method of Transmission Control Protocol in data center network, which includes the following steps:
Step 1, aggregation node collect the transmission rate and congestion window information of service with different priority levels, the different priorities industry
Business includes high-priority service and low priority traffice;
Step 2, aggregation node obtain the ratio of high-priority service and low priority traffice, and count the time every s duration
The transmission rate of the service with different priority levels monitored in section, wherein s is the period that aggregation node calculates service transmission rate;
Step 3, aggregation node obtain the adjusting side of different TCP flow congestion windows according to the transmission rate of the different business of acquisition
Method, to carry out transmission rate allocation.It is specific as follows:
(1) congestion window adjustment algorithm
The input parameter of algorithm is the target transmission speed of high-priority service and the period of network adjustment;Algorithm exports
Congestion window after high priority and low priority traffice adjusting.Variable-definition of the present invention is as follows: T (i) is i-th of high priority
The transmission rate of business;W (i) is the congestion window of i-th of high-priority service;T (j) is the biography of j-th of low priority traffice
Defeated rate;W (j) is the congestion window of j-th of low priority traffice;N is the sum of high-priority service;M is low priority industry
The sum of business;β is the ratio between high-priority service and low priority traffice transmission rate;γ is that high-priority service transmission rate mentions
The ratio of liter;η is that low priority traffice transmission rate reduces ratio.
(2) service transmission rate real-time monitoring mechanism
For aggregation node, since it receives the traffic packets at all working station, therefore the available height of aggregation node
The ratio (having Priority flag position in the packet header IP) of priority service and low priority traffice, and monitor service with different priority levels
Transmission rate.Assuming that each high-priority service transmission rate is T there are N number of high-priority service in data center network
(i), congestion window is W (i), and M low priority traffice, each low priority traffice transmission rate is T (j), congestion window W
(j), and aggregation node calculates the period of service transmission rate as S, i.e., can count in this period every S duration aggregation node
The transmission rate of the service with different priority levels monitored.
After aggregation node gets the transmission rate of service with different priority levels, high-priority service and low priority are defined
Business proportion relationship β are as follows:
Because the target transmission speed of the high priority business of network settings is T*, therefore calculate high priority business transmission rate and mention
Can coefficient gamma be risen meet the transmission rate requirements of high-priority service to describe the configuration of current network.The calculating of γ is as follows:
It when γ is greater than 0, indicates that network is unable to satisfy the target transmission speed of high-priority service, otherwise indicates high preferential
The target transmission speed of grade business is met.Therefore, when γ is greater than 0, aggregation node needs to re-start transmission rate point
Match.
In addition, aggregation node uses active queue adjustment algorithm (RED), therefore will when buffer queue is greater than threshold value
Packet loss event occurs, therefore aggregation node also needs to record the congestion condition of network entirety.Define congestion parameter α (0≤α≤1) table
Show the Congestion Level SPCC of network.The calculating cycle of alpha parameter is similarly S, and calculation method is as follows:
α=(1-g) × α+g × F;
Wherein, F indicates the grouping ratio that congestion occurs in the S time, and g indicates weight proportion shared by a upper alpha parameter.
(3) transmission rate allocation strategy
The needs of in order to meet network demand and high-priority service, network need to re-start transmission rate allocation.Tool
For body, aggregation node can calculate the adjusting side of different TCP flow congestion windows according to the transmission rate of the different business of acquisition
Method, to achieve the purpose that transmission rate allocation.
Firstly, it is necessary to ensure the transmission rate of high-priority service.According to above-mentioned calculated result, it is known that high-priority service
It needs to be promoted γ times of transmission rate and is just able to satisfy QoS demand.Because the relationship of congestion window and transmission rate is proportional relation,
Therefore the congestion window of high-priority service need be promoted to before (1+ γ):
W(i)*=W (i) × (1+ γ);
Secondly as congestion integrally has occurred in network, according to the suggestion of DCTCP agreement, the congestion window of network entirety is needed
Reduce α/2.In addition, (1+ γ) times before increasing to due to the congestion window of the business of high priority, therefore be also required to reduce
This Partial Incremental.Therefore, it is necessary to the overall congestion window values of reduction are as follows:
According to formula W (i)*=W (i) × (1+ γ) abbreviation is as follows:
It finally obtains each low priority traffice and needs reduced plug window value are as follows:
W(j)*=W (j) × (1- η);
Wherein η is equal to:
Aggregation node passes through formula W (i)*=W (i) × (1+ γ) and formula W (j)*=W (j) × (1- η) gets high priority
With the adjusting method of low priority congestion window, backward work station feedback regulation result.With reference to DCTCP and D2TCP, convergence section
Point carries congestion in ack msg packet and adjusts information.Specifically, ECN is that 1 expression reduces congestion window, ECN is that 0 expression increases
Big congestion window, for carrying γ and η parameter, i.e. γ and η parameter needs to be quantified as discrete value 4 bit reserved bits in ACK.
Experimental study data
In order to verify performance of the present invention for the transmission rate allocation method of Transmission Control Protocol in data center network, pass through
NS2 Network Simulation Software has built corresponding emulation platform, mainly compares the present invention and DCTCP agreement and D2The property of TCP
Energy difference, used Performance Evaluating Indexes are as follows: network throughput, average delay, packet loss.
One, experimental situation: as shown in table 1, high-priority service quantity is fixed as 5, low priority industry for experiment parameter setting
Quantity of being engaged in then is [2,4,6,8,10].The service rate of high-priority service and low priority traffice is 100Mbps.
The configuration of 1 experiment parameter of table
Parameter name | Parameter setting |
High-priority service rate | 100Mbps |
High-priority service quantity | 5 |
Low priority traffice rate | 100Mbps |
Low priority traffice quantity | 2,4,6,8,10 |
Packet size | 1460 bytes |
Work station chain-circuit time delay | 0.025ms |
Data center's chain-circuit time delay | 0.025ms |
Work station bandwidth | 1.1Gbps |
Data center's bandwidth | 1Gbps |
Work station queuing model | First in, first out model |
Data center's queuing model | Random packet loss model |
Data center's queue length | 250 data packets |
Simulation time | 10 seconds |
The target value of handling capacity | 100Mbps |
Two, analysis of experimental results
Experimental result is referring to Fig. 1-3, wherein Fig. 1 is the simulation result diagram of handling capacity;Fig. 2 is the emulation knot of average delay
Fruit figure;Fig. 3 is the simulation result diagram of packet loss;It will be seen from figure 1 that for DCTCP agreement and D2For Transmission Control Protocol, with
Low priority traffice quantity is continuously increased, and the handling capacity of high-priority service constantly declines, and low priority traffice handling capacity
Constantly promoted.In addition, D2The handling capacity of Transmission Control Protocol is lower than DCTCP agreement, this is because D2Transmission Control Protocol needs to guarantee cutting for business
The only time, therefore reduce handling capacity.In contrast, since the present invention is by the transmission rate target T of high-priority service*It is set as
100Mbps, and by the adjustment of congestion window, it ensure that the handling capacity of high priority business stream, compare DCTCP thus, it is possible to obtain
And D2The higher network throughput of TCP.Fig. 2 illustrates the Delay Variation situation of Business Stream, and as can be seen from Figure 2 DCTCP is assisted
View is not concerned with the deadline of business, therefore its average delay is maximum.D2TCP considers the deadline of business, therefore can one
Determine the average delay that degree ensures business, and the average delay of high-priority service is lower than the average delay of low priority traffice.
For the present invention, the average delay of high-priority service has sufficiently been ensured, but corresponding low priority traffice is flat
Equal time delay is higher.From figure 3, it can be seen that DCTCP agreement and D2The packet loss of Transmission Control Protocol all maintains higher level, especially
The packet loss of high-priority service is continuously increased.High-priority service in the present invention then keeps the state of hardly packet loss, low
The packet loss of priority service then maintains higher level.
The comprehensive performance demand of priority and handling capacity for business in data center network, the invention proposes be used for
The transmission rate allocation method of Transmission Control Protocol in data center network.The distribution method is according to high-priority service and low priority
The bandwidth allocation of the quantitative proportion of business adjusts congestion window, has ensured the handling capacity of high-priority service.The simulation experiment result
Show: the distribution method can not only the high priority business of effective guarantee handling capacity, moreover it is possible to reduce being averaged for high-priority service
Time delay and packet loss.
The above described is only a preferred embodiment of the present invention, be not intended to limit the present invention in any form, though
So the present invention is as above with preferred embodiment description, and however, it is not intended to limit the invention, any technology people for being familiar with this profession
Member, without departing from the scope of the present invention, when a little change or modification made using technology contents described above
It is the equivalent embodiment of equivalent variations, but without departing from the technical solutions of the present invention, according to the technical essence of the invention
Any simple modification, equivalent change and modification to the above embodiments, all of which are still within the scope of the technical scheme of the invention.
Claims (7)
1. the transmission rate allocation method for Transmission Control Protocol in data center network, it is characterised in that: the distribution method includes such as
Lower step:
Step 1, aggregation node collect the transmission rate and congestion window information of service with different priority levels, the different priorities industry
Business includes high-priority service and low priority traffice;
Step 2, aggregation node obtain the ratio of high-priority service and low priority traffice, and count the time every S duration
The transmission rate of the service with different priority levels monitored in section, wherein S is the period that aggregation node calculates service transmission rate;
Step 3, aggregation node obtain the adjusting side of different TCP flow congestion windows according to the transmission rate of the different business of acquisition
Method, to carry out transmission rate allocation.
2. the transmission rate allocation method for Transmission Control Protocol in data center network, feature exist as described in claim 1
In: in step 2, high-priority service transmission rate summation isLow priority traffice transmission rate summation isWherein, N is there are the sum of high-priority service in data center network, and T (i) is each high priority industry
The transmission rate of business, M are there are the sum of low priority traffice in data center network, and T (j) is each low priority traffice biography
Defeated rate.
3. the transmission rate allocation method for Transmission Control Protocol in data center network, feature exist as claimed in claim 2
In: the specific monitoring method of step 2 real-time monitoring service with different priority levels transmission rate is as follows:
If step 21, Thigh>=NT*, wherein T*For target transmission speed, then return step 1;Otherwise, step 22 is executed;
After step 22, aggregation node get the transmission rate of service with different priority levels, high-priority service and low excellent is calculated
First grade business proportion relationship β are as follows:
Step 23, in order to judge that can the configuration of current network meet the transmission rate requirements of high-priority service, calculate Gao You
First service transmission rate Lifting Coefficients γ is as follows:
Step 24 defines congestion parameter α, and records the congestion condition of aggregation node network entirety:
α=(1-g) × α+g × F;
Wherein, 0≤α≤1, F are the grouping ratio that congestion occurs in the S time, and g is weight proportion shared by a upper alpha parameter.
4. the transmission rate allocation method for Transmission Control Protocol in data center network, feature exist as claimed in claim 3
In: in step 23, when γ is greater than 0, aggregation node re-starts transmission rate allocation.
5. the transmission rate allocation method for Transmission Control Protocol in data center network, feature exist as claimed in claim 2
In: the adjusting method that step 3 calculates different TCP flow congestion windows includes the following steps:
Step 31, the congestion window that high-priority service can be obtained according to step 2 need to be promoted to before (1+ γ) times, it may be assumed that
W(i)*=W (i) × (1+ γ);
Wherein, W (i) is the congestion window of i-th of high-priority service;
The congestion window reduction of step 32, integrated network entiretyBefore increasing to the congestion window of the business of high priority
(1+ γ) times calculates the overall congestion window value for needing to reduce;
Step 33 calculates the reduced congestion window numerical value of each low priority traffice needs according to step 32, to get height
The adjusting method of priority and low priority congestion window, backward work station feedback regulation result.
6. the transmission rate allocation method for Transmission Control Protocol in data center network, feature exist as claimed in claim 5
In: in step 32, the overall congestion window value calculating method that needs to reduce are as follows:
Wherein, W (j) is the congestion window of j-th of low priority traffice;In conjunction with W (i)*=W (i) × (1+ γ), can obtain:
7. the transmission rate allocation method for Transmission Control Protocol in data center network, feature exist as claimed in claim 6
In: in step 33, each low priority traffice is calculated and needs reduced congestion window numerical value are as follows:
W(j)*=W (j) × (1- η);
Wherein,η is that low priority traffice transmission rate reduces ratio.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910805843.1A CN110535778B (en) | 2019-08-29 | 2019-08-29 | Transmission rate distribution method for TCP protocol in data center network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910805843.1A CN110535778B (en) | 2019-08-29 | 2019-08-29 | Transmission rate distribution method for TCP protocol in data center network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110535778A true CN110535778A (en) | 2019-12-03 |
CN110535778B CN110535778B (en) | 2022-09-23 |
Family
ID=68664973
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910805843.1A Active CN110535778B (en) | 2019-08-29 | 2019-08-29 | Transmission rate distribution method for TCP protocol in data center network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110535778B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114900476A (en) * | 2022-05-09 | 2022-08-12 | 中国联合网络通信集团有限公司 | Data transmission method, device, network equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080225721A1 (en) * | 2007-03-12 | 2008-09-18 | Robert Plamondon | Systems and methods for providing quality of service precedence in tcp congestion control |
US8004991B1 (en) * | 2006-10-11 | 2011-08-23 | Qlogic, Corporation | Method and system for processing network information |
US20130135996A1 (en) * | 2011-11-29 | 2013-05-30 | Hughes Networks Systems, Llc | Method and system for traffic management and resource allocation on a shared access network |
CN104301254A (en) * | 2014-09-30 | 2015-01-21 | 广东石油化工学院 | Data package dispatching method for data center network |
CN105827540A (en) * | 2016-05-30 | 2016-08-03 | 清华大学深圳研究生院 | Data center network transmission layer stream data transmission method based on priority |
CN108881045A (en) * | 2018-06-04 | 2018-11-23 | 河南科技大学 | A kind of jamming control method ensured in heterogeneous network based on QoS |
-
2019
- 2019-08-29 CN CN201910805843.1A patent/CN110535778B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8004991B1 (en) * | 2006-10-11 | 2011-08-23 | Qlogic, Corporation | Method and system for processing network information |
US20080225721A1 (en) * | 2007-03-12 | 2008-09-18 | Robert Plamondon | Systems and methods for providing quality of service precedence in tcp congestion control |
US20130135996A1 (en) * | 2011-11-29 | 2013-05-30 | Hughes Networks Systems, Llc | Method and system for traffic management and resource allocation on a shared access network |
CN104301254A (en) * | 2014-09-30 | 2015-01-21 | 广东石油化工学院 | Data package dispatching method for data center network |
CN105827540A (en) * | 2016-05-30 | 2016-08-03 | 清华大学深圳研究生院 | Data center network transmission layer stream data transmission method based on priority |
CN108881045A (en) * | 2018-06-04 | 2018-11-23 | 河南科技大学 | A kind of jamming control method ensured in heterogeneous network based on QoS |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114900476A (en) * | 2022-05-09 | 2022-08-12 | 中国联合网络通信集团有限公司 | Data transmission method, device, network equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110535778B (en) | 2022-09-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104994036B (en) | A kind of dynamic data dispatching method in multi-path transmission protocol | |
US8904025B2 (en) | Systems and methods for traffic management | |
CN113746748B (en) | Explicit congestion control method in named data network | |
CN101969408B (en) | Active queue management method based on packet DSCP (Differentiated Services Code Point) marks | |
CN109873773B (en) | Congestion control method for data center | |
RU2012155863A (en) | METHOD AND MANAGEMENT SYSTEM OF THE BANDBAND | |
CN103795643A (en) | Method for processing synchronous priority bursty flow in data center network | |
CN101860488A (en) | Network congestion control method | |
CN109150756B (en) | Queue scheduling weight quantification method based on SDN power communication network | |
CN114866474A (en) | End network cooperative traffic scheduling method, device, system and storage medium | |
CN109150346A (en) | A kind of method that car networking broadcast background flows down transmission of video | |
CN110535778A (en) | Transmission rate allocation method for Transmission Control Protocol in data center network | |
CN111082978A (en) | SDN-oriented utility bandwidth allocation method | |
CN103795646B (en) | Distributed priority congestion control method for IEEE802.11P vehicle-mounted system | |
CN113452618A (en) | M/M/1 queuing model scheduling method based on congestion control | |
CN110943927B (en) | Named data network transmission control method, device and equipment based on time delay management | |
CN116302578A (en) | QoS (quality of service) constraint stream application delay ensuring method and system | |
CN107770082B (en) | Transmission control method based on task flow characteristics in data center network | |
CN110891027B (en) | Named data network transmission control method, device and equipment based on queue scheduling | |
FARZANEH et al. | An adaptive congestion alleviating protocol for healthcare applications in wireless body sensor networks: learning automata approach | |
CN101102169A (en) | A multi-service type self-adapted receiving and control method | |
Lu et al. | Contention window adaptive adjustment strategy for fairness in multi-rate IEEE 802.11 network | |
CN112055382A (en) | Service access method based on refined differentiation | |
CN108768874B (en) | Method for relieving blocking performance of avionics network based on command efficiency loss | |
CN113784390B (en) | Wireless communication system for realizing dynamic distribution of network load |
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 |