EP1969782A1 - Mecanisme auto-adaptatif de gestion de flux dans un reseau partage a acces multiple - Google Patents
Mecanisme auto-adaptatif de gestion de flux dans un reseau partage a acces multipleInfo
- Publication number
- EP1969782A1 EP1969782A1 EP06847210A EP06847210A EP1969782A1 EP 1969782 A1 EP1969782 A1 EP 1969782A1 EP 06847210 A EP06847210 A EP 06847210A EP 06847210 A EP06847210 A EP 06847210A EP 1969782 A1 EP1969782 A1 EP 1969782A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- network
- transmission
- state
- priority
- priority data
- 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.)
- Withdrawn
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
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2441—Traffic characterised by specific attributes, e.g. priority or QoS relying on flow classification, e.g. using integrated services [IntServ]
-
- 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
- H04L47/11—Identifying 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
- H04L47/13—Flow control; Congestion control in a LAN segment, e.g. ring or bus
-
- 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
-
- 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
- H04L47/2433—Allocation of priorities to traffic types
Definitions
- the present invention relates to a self-adaptive flow management mechanism in a shared multiple access network.
- a shared network all the terminals are connected to a single channel through which all data frames transmitted or received by said terminals transit.
- this network is multiple access ,. two different terminals can send frames of data at the same time. These frames collide.
- ATS adaptive flow control mechanism
- Adapative Traffic Smoother This mechanism consists of controlling the bit rate of non-priority data frames sent by a terminal.
- the priority data streams are systematically sent to the network regardless of the state of congestion of said network, even in the case of numerous collisions of frames.
- the ATS mechanism makes it possible to obtain a better transmission of the data frames since it makes it possible to reduce the number of collisions, which has the consequence of increasing the effective flow of the network.
- the proposed quality of service remains insufficient.
- the ATS mechanism does not allow their complete deletion, which is problematic in particular for the priority data streams, which must be transmitted in time. real for a satisfactory quality of service.
- an objective of the invention is to improve the quality of service by proposing a method for managing the transmission of data flows by a terminal of a shared access multi-access network, said data streams being structured. in data frames.
- This method is characterized in that it comprises the steps of: determining a state of congestion of said shared multiple access network; managing the transmission of said priority and non-priority data streams by said station, according to said state of congestion.
- the technical problem of improving the quality of service on the network is solved by performing a self-adaptive control of the transmission of the streams according to the state of the network, which was not the case. according to the prior art. Indeed, although it has been envisaged in the state of the art to regulate the flow rate of non-priority flows, it has never been proposed to modify the bit rate of the priority flows, which are real time flows, ei for which the person skilled in the art therefore thought that it was not possible to delay them, and that they should be transmitted without constraints.
- the mechanism of the invention is based on a determination of the congestion state of the network, that is to say the presence or absence of collisions of frames on the network, and their frequency.
- the transmission of data streams, both priority and non-priority is then regulated according to the state of congestion determined in the previous step.
- a first variable representative of a collision rate of said data frames transmitted by said terminal is evaluated and a second variable representative of a number of frames of priority data retransmitted more than N times by said terminal, where N is a predetermined natural integer, during a so-called collection period, and: when said first and second variables are zero, said network is in a state said not congested ; when said first and second variables are strictly positive, said network is in a so-called congested state; when said first variable is strictly p ⁇ sftfve and said second vartabte is ⁇ ufte, said network is in an intermediate state.
- said determining step is implemented at time intervals corresponding to the duration of said collection period, so as to update said congestion state of said network.
- said management step prohibits the transmission of said priority and non-priority data frames when said network is in said congested state, and prohibits transmission of said non-priority data frames when said network is in said intermediate state.
- it also controls the emission of priority streams that, unlike the teaching of the state of the art, is prohibited when the network is congested, although these flows of priority data are real-time data streams.
- said management step implements a token-based mechanism for controlling the transmission rate of said non-priority data frames, the transmission of a frame of non-priority data being conditioned, when said network is in said non-congested state, to the presence of at least one token in said regulation mechanism.
- the number of chips present in said regulation mechanism is reduced when said network is in said intermediate state or in said congested state, so as to reduce the bit rate of said non-priority flows.
- the flow of the token bucket is thus regulated, and thus non-priority flows, depending on the state of congestion of the network, so as to prevent these non-priority flows from encumbering the network when it is already subject to collisions. , and thus promote the transmission of priority flows.
- a weighting coefficient of a transmission instant of a data frame is also calculated, taking into account said first and second evaluated variables during said collection period and during at least one preceding collection period, so as to smooth the instant of transmission of at least some of said data frames during said control step.
- the duration of said collection period is modified as a function of said state of congestion.
- the duration of said collection period is weighted by said weighting parameter, so as to improve the reactivity of said control method.
- the invention further relates to a computer program product comprising program code instructions recorded on a computer readable medium, for carrying out the steps of the method described above, when said program is executed on a computer.
- the invention also relates to a termina! for transmitting / receiving data streams on a shared access shared communication network, tesdsts data streams being structured into data frames and comprising at least one priority data stream and at least one non-priority data stream, characterized in that it comprises: means for determining a congestion state of said shared network to multiple access; means for managing the transmission of said priority and non-priority data streams, according to said state of congestion.
- said means for determining a state of congestion of said network evaluate a first variable representative of a collision rate of said data frames transmitted by said terminal and a second variable representative of a number of priority data frames retransmitted more than N times by said terminal, where N is an integer nature! predetermined, during a so-called collection period, and said determining means deliver a network congestion state information according to which: when said first and second variables are zero, said network is in a said non-congested state; when said first and second variables are strictly positive, said network is in a so-called congested state; when said first variable is strictly positive and said second variable is zero, said network is in an intermediate state.
- said means for managing the transmission of said data streams comprise: a module for regulating the transmission rate of said non-priority data frames, implementing a mechanism, to base of tokens, transmission of a non-priority data frame being conditioned, when said network is in said non-congested state, to the presence of at least one token in said control mechanism; a module for managing the transmission of data frames prohibiting the transmission of said priority and non-priority data frames when said network is in said congested state, and prohibiting the transmission of said non-priority data frames when said network is in said intermediate state.
- the invention also relates to a module for determining a time of transmission of a data frame on a shared access multiple communication network, over which data flows structured in data frames and comprising at least one data stream. priority data and at least one non-priority data stream, said determination module being able to cooperate with an emitter / receiver terminal as described above, said module comprising means for determining the transmission time of the transmission device. data frame, and means for transmitting said data frame on the network.
- a module also comprises means for receiving a weighting parameter of a transmission instant of a data frame calculated by said terminal, and said determining means take account of said weighting parameter received. to determine the transmission time of the data frame.
- Such a module is for example impimacé on a network card, for example an Ethernet card.
- FIG. 1 schematically represents a terminal in which a self-adaptive mechanism for managing data streams according to the invention is impiantated
- FIG. 2 represents the operating algorithm of a congestion state determination module of the constituent network of the data transfer management mechanism implemented in the terminal of FIG. 1,
- FIG. 3 represents the operating algorithm of a non-priority data frame rate management module constituting the data flow management mechanism implemented in the terminal of FIG. 1;
- FIG. 4 represents the operating algorithm of a management module of a transmission instant of a constituent data frame of the data flow management mechanism, implemented in the terminal of FIG. 1;
- FIG. 5 represents an example of variations of a function ⁇ involved in the calculation of the weighting parameter of the transmission time of the frames, as a function of a number of priority frames retransmitted more than N times in the course of the same collection.
- a self-adaptive data flow management system 1 as shown schematically in Figure 1 comprises three modules M1, M2, M30, cooperating with each other to improve the quality of service in a shared multiple access network.
- the auto-adaptive system 1 is implemented in a termina! 2 connected to a shared multiple access network for managing the transmission of data streams from the terminal 2.
- the terminal 2 transmits different types of data streams, so-called priority data streams, because they must to be transmitted in real time, are for example multimedia streams, and non-priority data streams, for example text data.
- the function of the module M1 is to determine the congestion state of the network. To do this, the module M1 collects information relating to the data traffic on the network. The collection of information is done by listening to the carriers of the network during a period of collection of duration ⁇ t ,. Once the information has been collected, it is used to determine the congestion state of the network for the collection performed as well as a parameter of weighting of a transmission instant of a data frame Sj. This module M1 is located in the terminal 2.
- Carrier listening consists of an analysis, performed by each of the terminals connected to the network, of information flows transiting the network. This listening is carried out by means of protocols such as, for example, the CSMA protocol (acronym Carrier Sensé Multiple Access).
- This listening allows a first terminal to determine if a second terminal transmits frames of data on the network.
- the first ended! detects a transmission made by the second terminal, it delays the sending of its frames of data on the network in order to avoid a collision between its frames of data from the two terminals. Indeed, when a collision intervenes on the network, the data contained in the collapsed data frames are lost.
- Carrier listening allows terminals that have transmitted the collision frames to detect the collision.
- the terminals concerned then stop their emissions. Then, they emit on the network a scrambling frame whose function is to amplify the collision so that all the terminals of the network detect the collision and delay the transmission of their data in order to avoid network congestion.
- a second module M2 and a third module M30 have the function of managing the bit rate of the data frames transmitted by the terminal 2 as a function of a congestion state of the network.
- the function of the module M2 is to manage the bit rate of the non-priority data streams, which are the most frequently sent flows in the network, so as to provide a constant bit rate of non-priority data streams at the input of the module M30.
- the module M2 is located in the terminal 2.
- the M30 module meanwhile, has the function of managing the transmission on the network of data streams, whether they are priority data streams or non-priority data streams.
- the module M30 consists of an M32 module whose function is to determine, as a function of the weighting parameter of a transmission instant of a data frame S 1 , instant of transmission of the data frames on the network.
- This module M32 is, for example, a network card connected to the terminal 2. Such a card interconnects the terminal 2 and the network.
- the module in another embodiment, the module
- M30 is composed of an M31 module and the M32 module.
- the function of the module M31 is to issue transmission authorizations according to the state of congestion of the network determined by the module M1.
- the module M31 is also located in the terminal 2.
- the various modules M1, M2, M30 constituting the self-adaptive data flow management system 1 are distinct from each other so that each can be modified independently of the others. However, the modifications made to the various modules must not impair their ability to cooperate with each other 11 is the same for the modules M31 and M32 constituting the module M30 for managing the transmission of data streams.
- a collection is a period of observation of the network of duration ⁇ t.
- the module M1 collects data necessary for determining a congestion state of the network. This corresponds to step EO.
- the module M1 performs successive collections.
- the duration At 1 of a collection i depends on the state of congestion of the determined network tors of the previous collection t-1. This makes the system 1 according to the invention more reactive.
- the module M1 stores three distinct values: the total number of bytes transmitted during the collection OT 1 , the number of priority frames retransmitted more than N times during said collection PR 1 , and finally the number of bytes collided during said OC 1 collection.
- the number N is a predetermined integer. In a particular embodiment of the present invention, N is set to 10.
- the index i represents the period during îaqueile TOs 5 PR and OC values have been stored by the module M 1.
- the module M1 calculates a collision rate R 1 for the collection i.
- the collision rate R is the result of the ratio of the number of OC 1 collision bytes on the total number of bytes transmitted OT 1 .
- the module M1 determines a weighting coefficient R, for the collection performed according to the measurements made during previous collections.
- the weighting coefficient Rr is obtained by the following formula: & t ⁇ [(1 - ⁇ ) * R,] + ( ⁇ * RO-
- the weighting function ⁇ whose variations are according to the number of priority prerollers PR, retransmitted more than during the collection i stored in the module M 1.
- the values of ⁇ vary between 0 and 1 and increase with the value of PR, an example of variations of ⁇ is shown in Figure 5.
- Values of the function ⁇ are given, as examples, in the following table:
- the module M1 determines the value of the weighting parameter of a transmission instant of a data frame Si during a step E4.
- the value of the weighting parameter Si is the minimum value of a pair (R,; ⁇ ) in which ⁇ is a constant whose value is set by the user of the terminal 2.
- ⁇ is a constant whose value is set by the user of the terminal 2.
- the value ⁇ makes it possible to avoid its stagnation. instant of transmission of a data frame when there are collisions.
- the initial value of S, is equal to ⁇ .
- the module M1 proceeds to determine a congestion state of the network.
- module M1 uses the variables are the number of priority frames retransmitted more than N times during said collection PR ,, and the collision rate R, to the current collection.
- the combination of these two variables generates four states for the network, three of which are orthogonal: a first state for which the collision rate R 1 is impaired and no priority data frame has been retransmitted, it is the non-congested state, a second state for which the collision rate R 1 is not zero but no priority data frame has been retransmitted, it is the intermediate state; in this state, only the non-priority data frames collide, a third state for which the collision rate Ri is not zero and at least one priority data frame has been retransmitted more than N times during the collection, it is the congested state, the fourth state is an impossible state for which the collision rate R would be impaired but at least one priority data frame would have been retransmitted more than N times during the collection.
- step E5 M1 module tests the collision rate R ,. If the value of the collision rate Ri is zero, then the network is in the uncongested state. If the result of the test reveals that its value of the collision rate Ri is not zero, the module M1 executes the step E6. During the step E6, the module M1 tests the number of priority frames PRj retransmitted more than N times during the collection. If this number is zero, then the network is in the intermediate state.
- step E6 If the test performed in step E6 reveals that the number of priority frames PRi retransmitted more than N times during the collection is not zero, then the network is in the congested state.
- the module M2 modifies the value of several parameters among which the duration of the collection.
- the module M2 manages the bit rate of non-priority data frames by means of an algorithm called the token bucket algorithm.
- the token bucket algorithm is a mechanism for regulating the data flow rate.
- the bucket modeled by this algorithm contains a maximum number of CBD tokens. All RP seconds, RP corresponding to the refresh period of the token bucket, a new token is generated by the algorithm and injected into the bucket.
- the number of chips in the bucket is reduced by an amount equal to the number of bytes that make up the packet.
- the token bucket no longer contains tokens, no data packets can be transmitted over the network. However, if a single token remains in the token bucket when a data packet arises, it is transmitted over the network and the number Q of chips left in the token bucket can become negative.
- the module M2 tests whether the network is in the non-congested state.
- the modulus M2 executes step F20.
- the module M2 determines the refresh period RP, the token bucket algorithm ensuring the flow control of non-priority data frames.
- This value is chosen as the maximum value of a couple ⁇ RPMIN; RPM - D) where RPMIN is the minimum value RP and D can take a decrement.
- the values of RPM I N and D are set by the end user or can be predetermined, by example by the network operator. Increasing the value of the refresh period RP of the token bucket limits the risk of sending non-priority data frames as a burst. Such an event would have the effect of generating collisions on the network and would move the network from a non-congested state to an intermediate state or even congested which is detrimental to the quality of service.
- the module M2 determines the duration of the next collection ⁇ W This value is chosen as being the minimum value of a pair ( ⁇ ÎMAX; 2 ⁇ t ⁇ ) where ⁇ ÎMAX is the maximum duration of a collection and ⁇ t, the duration of the previous collection.
- the value of ⁇ ty A ⁇ is set by the user of the terminal 2 or for example by the operator of the network.
- This new collection period is sent to the module M1 so that the module M1 can proceed to a new collection according to the conditions defined by the module M2.
- the module M2 tests whether the time indicated by its internal clock corresponds to a refresh schedule of the token bucket algorithm. If it is not the case, the module M2 executes again the step F1.
- the module M2 executes the step F23.
- the module M2 adds a CBD number of chips to the quantity G of chips already present in the token bucket.
- the number of chips contained in the bucket is the minimum value of the couple (Q + CBD, CBD).
- Steps F20, F21, F22 and F23 have the consequence of increasing the transmission rate of non-priority data frames. Since the network is in an unencumbered state, it is interesting to increase the number frames transmitted since there are no collisions, and the quality of service is satisfactory.
- step F1 If the result of the test performed in step F1 indicates that the network is not in the uncongested state, then the module M2 executes step F10.
- the module determines whether the network is in the intermediate or congested state.
- the modulus M2 executes the step F 11.
- the number of tokens contained in the token bucket is halved if Q is positive or is multiplied by two if Q is negative. This has the consequence of reducing the number of transmitted non-priority data frames, and thus of encouraging the sending of priority data frames, by reducing the number of collisions generated by the non-priority frames.
- step F12 the value of the refresh period RPj is chosen as the minimum value of the torque (RPMAX; 2RPj -1 ).
- the duration of the collection ⁇ tj is the maximum value of a pair ( ⁇ I MSN ; S ⁇ i * ⁇ t ⁇ i) where S M is the weighting parameter of a transmission instant of a frame of data determined for the previous collection. This new collection time is sent to the module
- the steps F11, F12 and F13 are intended to reduce the bit rate of non-priority data frames and to lengthen the duration of the collection. This makes it possible, by reducing the number of frames of non-priority data sent in the network to reduce the number of collisions occurring on the network in order to bring the network back into the unencumbered state as quickly as possible. If the network is in the congested state, then the module M2 executes step F30.
- the value of the refresh period of the token bucket is the minimum value of a couple (RPMAX; 2RPM).
- the duration of the collection is ⁇ t M iN-
- the duration of the collection is sent to the module M1 so that it can proceed to a new collection.
- the duration of the collection is reduced in order to react more quickly to the congestion state of the network and, if the newly determined congestion state allows it, restart the transmission of data frames on the network.
- step G1 the module M31 tests the nature of the data frame arriving at the input of said module. If the incoming data frame is a priority data frame, the M31 module executes step G20.
- the module M31 tests the congestion state of the network. If the network is in the congested state, module M31 executes step G4. During this step, the priority data frames are blocked. This has the consequence that these data frames are not transmitted to the module M32. Thus any transmission of data frames, priority or not, being stopped, any risk of creating additional collisions on the network is deleted.
- the module M31 performs step G21. During this step, the priority data frames are sent over the network.
- the number of chips in the token bucket is updated according to the number of bytes transmitted on the network. Although the priority data frames are not processed by the token bucket, the token bucket number is still updated to reduce the number of frames of non-priority data that can be issued and thus [imitate the risk collisions on the network.
- the M31 module executes step G30.
- the module M31 tests the congestion state of the network. If the network is in the uncongested state, the module M31 executes step G31.
- step G31 the module M31 tests the number of tokens contained in the token bucket. If at least one token remains, the method performs steps G21 and G22. In the opposite case, the data frame is not sent, which corresponds to step G32.
- the module M31 executes step G4.
- the frames of non-priority data are then blocked in order to limit the risk of congestion and allow efficient transmission of priority data frames.
- the module M32 of calculating moment of transmission of a data frame does not calculate a transmission time of a data frame for the data frames being transmitted from the module M31 in the embodiment where the modules M31 and M32 cooperate with each other.
- W. 2 (mfn (m ⁇ ⁇ - ⁇ K denoting the number of retransmissions of the data frame.
- the value of W 1 is reset.
- the value of W is the maximum value of a pair (1; SM * W M ).
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Small-Scale Networks (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR0554111A FR2895616A1 (fr) | 2005-12-27 | 2005-12-27 | Mecanisme auto-adaptatif de gestion de flux dans un reseau partage a acces multiple |
| PCT/FR2006/051421 WO2007074310A1 (fr) | 2005-12-27 | 2006-12-22 | Mecanisme auto-adaptatif de gestion de flux dans un reseau partage a acces multiple |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP1969782A1 true EP1969782A1 (fr) | 2008-09-17 |
Family
ID=37057193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP06847210A Withdrawn EP1969782A1 (fr) | 2005-12-27 | 2006-12-22 | Mecanisme auto-adaptatif de gestion de flux dans un reseau partage a acces multiple |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US8213454B2 (fr) |
| EP (1) | EP1969782A1 (fr) |
| FR (1) | FR2895616A1 (fr) |
| WO (1) | WO2007074310A1 (fr) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109600320A (zh) * | 2017-09-30 | 2019-04-09 | 华为技术有限公司 | 拥塞处理方法及设备、数据中心网络 |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008112233A2 (fr) | 2007-03-14 | 2008-09-18 | Interdigital Technology Corporation | Procédé et appareil pour aider à éviter une insuffisance de liaison montante dans un système d'évolution à long terme |
| US8619573B2 (en) * | 2010-03-24 | 2013-12-31 | Telefonaktiebolaget Lm Ericsson (Publ) | Delayed flow control action in transport network layer WCDMA communications |
| US8493860B2 (en) * | 2010-03-24 | 2013-07-23 | Telefonaktiebolaget Lm Ericsson (Publ) | Fair congestion detection for transport network layer WCDMA communications |
| US8483059B2 (en) * | 2010-09-15 | 2013-07-09 | Accelera Mobile Broadband, Inc. | Method for congestion avoidance in 4G networks |
| JP2012231445A (ja) * | 2011-04-11 | 2012-11-22 | Toshiba Corp | パケット配信装置およびパケット配信方法 |
| US9130763B2 (en) * | 2011-06-20 | 2015-09-08 | Microsoft Technology Licensing, Llc | Automatic sharing of event content by linking devices |
| US9414239B2 (en) * | 2012-06-14 | 2016-08-09 | Digimarc Corporation | Space time calibration for networks using state model of node clock parameters |
| CN102984096B (zh) * | 2012-10-12 | 2015-05-13 | 中国船舶重工集团公司第七一九研究所 | 应用于船舶动力信息采集装置的can数据帧的组装方法 |
| CN105100886B (zh) * | 2014-04-22 | 2019-03-15 | 腾讯科技(北京)有限公司 | 网络媒介信息的发布控制方法、及装置、服务器和系统 |
| US9558147B2 (en) * | 2014-06-12 | 2017-01-31 | Nxp B.V. | Fine-grained stream-policing mechanism for automotive ethernet switches |
| US10271376B2 (en) * | 2016-09-29 | 2019-04-23 | Intel IP Corporation | Optimized transmission for priority data on a radio access technology network |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5311513A (en) * | 1992-09-10 | 1994-05-10 | International Business Machines Corp. | Rate-based congestion control in packet communications networks |
| JP3525656B2 (ja) * | 1996-12-06 | 2004-05-10 | 株式会社日立製作所 | パケット交換機、および輻輳通知方式 |
| US6091709A (en) * | 1997-11-25 | 2000-07-18 | International Business Machines Corporation | Quality of service management for packet switched networks |
| US6452915B1 (en) * | 1998-07-10 | 2002-09-17 | Malibu Networks, Inc. | IP-flow classification in a wireless point to multi-point (PTMP) transmission system |
| US6714517B1 (en) * | 1998-11-10 | 2004-03-30 | Extreme Networks | Method and apparatus for interconnection of packet switches with guaranteed bandwidth |
| JP3556495B2 (ja) * | 1998-12-15 | 2004-08-18 | 株式会社東芝 | パケットスイッチ及びパケット交換方法 |
| US6580697B1 (en) * | 1999-09-21 | 2003-06-17 | 3Com Corporation | Advanced ethernet auto negotiation |
| US7324522B2 (en) * | 2003-09-18 | 2008-01-29 | Raytheon Company | Encapsulating packets into a frame for a network |
-
2005
- 2005-12-27 FR FR0554111A patent/FR2895616A1/fr active Pending
-
2006
- 2006-12-22 WO PCT/FR2006/051421 patent/WO2007074310A1/fr not_active Ceased
- 2006-12-22 EP EP06847210A patent/EP1969782A1/fr not_active Withdrawn
- 2006-12-22 US US12/087,327 patent/US8213454B2/en not_active Expired - Fee Related
Non-Patent Citations (1)
| Title |
|---|
| MIN-GYU CHO ET AL: "On Soft Real-Time Guarantees on Ethernet", 8 April 2004, REAL-TIME AND EMBEDDED COMPUTING SYSTEMS AND APPLICATIONS; [LECTURE NOTES IN COMPUTER SCIENCE;LNCS], SPRINGER-VERLAG, BERLIN/HEIDELBERG, ISBN: 978-3-540-21974-3, pages: 158 - 175, XP019005390 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109600320A (zh) * | 2017-09-30 | 2019-04-09 | 华为技术有限公司 | 拥塞处理方法及设备、数据中心网络 |
| CN109600320B (zh) * | 2017-09-30 | 2022-04-05 | 华为技术有限公司 | 拥塞处理方法及设备、数据中心网络 |
Also Published As
| Publication number | Publication date |
|---|---|
| US8213454B2 (en) | 2012-07-03 |
| FR2895616A1 (fr) | 2007-06-29 |
| WO2007074310A1 (fr) | 2007-07-05 |
| US20090219815A1 (en) | 2009-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1096827B1 (fr) | Procédé de mise en conformité à un contrat de trafic d'un flux de paquets d'un réseau de transport de paquets à longueur variable | |
| EP1969782A1 (fr) | Mecanisme auto-adaptatif de gestion de flux dans un reseau partage a acces multiple | |
| FR2805112A1 (fr) | Procede et unite de controle de flux d'une connexion tcp sur un reseau a debit controle | |
| EP2052503A1 (fr) | Procede d'optimisation du transfert d'informations dans un reseau de telecommunication | |
| EP2862324B1 (fr) | Procede et dispositif d'estimation rapide et peu intrusive de la bande passante disponible entre deux n uds ip | |
| FR2877176A1 (fr) | Procede et dispositif pour ordonnancer et transmettre des paquets de donnees a partir d'un emetteur commun vers une pluralite d'utilisateurs partageant un canal de transmission coummun. | |
| EP3917233A1 (fr) | Procédé de sélection de canal de communication | |
| FR2925808A1 (fr) | Procede de communication dans un reseau comprenant un reseau primaire et un reseau secondaire | |
| EP0874533B1 (fr) | Procédé d'ordonnancement de paquets à pertes équitables | |
| EP1779701A1 (fr) | Procede de gestion de ressources dans un systeme de communication et equipements pour la mise en oeuvre du procede | |
| EP3989494B1 (fr) | Procédé d'agrégation et de régulation de messages via un canal de communication bidirectionnel contraint | |
| US8982702B2 (en) | Control of rate adaptive endpoints | |
| EP2103055B1 (fr) | Procédé d'optimisation du partage d'une pluralité de ressources réseau entre une pluralité de flux applicatifs | |
| EP0885508B1 (fr) | Procede d'espacement de cellules atm et dispositif pour sa mise en oeuvre | |
| FR3007919A1 (fr) | Procede d'adaptation de lien pour selectionner un mode de transmission de trames et point d'acces wifi correspondant | |
| EP2633651B1 (fr) | Procédé et dispositif de détection de la congestion d'un lien de transmission | |
| EP3861693A1 (fr) | Procédé de préservation d'un débit d'émission de données d'un terminal dans un réseau de communications | |
| WO2007034122A1 (fr) | Procede et systeme de gestion dynamique de qualite de service | |
| Okumura | Traffic control algorithm offering multi-class fairness in PON based access networks | |
| Ho et al. | A TCP-friendly stateless AQM scheme for fair bandwidth allocation | |
| WO2009004212A1 (fr) | Modification de quantite de ressource equivalente lors de controle d'admission | |
| Orman et al. | Increasing Quality of Services with Priority Active Package Management | |
| EP4020926A1 (fr) | Procédé de routage pour router un flux élastique dans un réseau de transport | |
| EP2553888B1 (fr) | Procédé et système de transmission de flux multimédia | |
| Liu | Promoting node-to-node congestion control in internet |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| 17P | Request for examination filed |
Effective date: 20080703 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC NL PL PT RO SE SI SK TR |
|
| 17Q | First examination report despatched |
Effective date: 20081105 |
|
| DAX | Request for extension of the european patent (deleted) | ||
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: ORANGE |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20141014 |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Free format text: PREVIOUS MAIN CLASS: H04L0012560000 Ipc: H04L0012819000 |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Free format text: PREVIOUS MAIN CLASS: H04L0012560000 Ipc: H04L0012819000 Effective date: 20150311 |