CN114745309B - Micro burst detection and elimination method and system based on programmable data plane - Google Patents
Micro burst detection and elimination method and system based on programmable data plane Download PDFInfo
- Publication number
- CN114745309B CN114745309B CN202210233618.7A CN202210233618A CN114745309B CN 114745309 B CN114745309 B CN 114745309B CN 202210233618 A CN202210233618 A CN 202210233618A CN 114745309 B CN114745309 B CN 114745309B
- Authority
- CN
- China
- Prior art keywords
- data
- micro
- flow
- priority
- burst
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000001514 detection method Methods 0.000 title abstract description 12
- 230000008030 elimination Effects 0.000 title abstract description 11
- 238000003379 elimination reaction Methods 0.000 title abstract description 11
- 238000012544 monitoring process Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 description 5
- 238000005259 measurement Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0894—Packet rate
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- 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
- H04L47/25—Flow control; Congestion control with rate being modified by the source upon detecting a change of network conditions
-
- 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
- H04L47/32—Flow control; Congestion control by discarding or delaying data units, e.g. packets or frames
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a micro-burst detection and elimination method based on a programmable data plane, and belongs to the technical field of network communication. The invention provides a method for rapidly estimating the speed in the data plane, which can achieve rapid detection by using resources such as a register, a counter and the like and information such as a built-in time stamp and the like without participation of a control plane. The invention provides a method for rapidly estimating queuing delay, which estimates queuing delay by recording arrival time of a data packet and known departure time of the data packet, and does not increase input bandwidth of a pipeline. The method directly takes estimated queuing delay as a guarantee target for the micro burst flow, and rapidly eliminates the micro burst and guarantees the delay requirement of the micro burst flow by discarding a certain amount of flow data packets with the lowest delay requirement in a pipeline packet loss mode.
Description
Technical Field
The invention belongs to the technical field of network communication, and particularly relates to a micro burst detection and elimination method and system based on a programmable data plane.
Background
With the popularity of 5G mobile services worldwide, data traffic is rapidly increasing. The Internet of things in the 5G scene is accessed from the network edge and bears a large amount of data, thereby playing an important role. The internet of things equipment is connected with the internet of things server through the internet of things gateway. The gateway of the Internet of things provides wireless coverage in a mode of honeycomb, bluetooth and the like, and a plurality of gateways form an edge network to aggregate traffic in the coverage area of the gateway and send the traffic to a remote core server of the Internet of things. The sudden increase of aggregate traffic caused by the simultaneous transmission of data by a large number of internet of things devices is called a micro burst. The micro-burst traffic may exceed the queue buffer space of the edge network node gateway, resulting in increased packet delay and even being dropped. Meanwhile, the demand characteristics of the application flow of the Internet of things have differences, such as low-delay and low-jitter requirements of remote operation; video surveillance has little requirement for latency.
The internet of things edge network has certain computing and storage resources and is nearest to the source of the micro-burst, so that the internet of things edge network is an ideal place for solving the micro-burst. The fast detection and elimination of micro-bursts, which have short duration and large flow rates, has been a challenge.
An edge network implemented using Software Defined Networking (SDN) has the flexible advantage of an architecture that separates control and data, but also suffers from latency in communication and interaction between the control plane and the data plane. In an architecture where an integrated SDN controller controls multiple edge switches, the edge switches rely on the controller to obtain instructions. The micro burst duration is very short, typically a few hundred milliseconds, so the first problem is fast detection. The control plane takes periodic monitoring of the data plane. The larger network measurement period and the shorter duration of the micro-bursts results in no micro-bursts being found. The flow generated by micro burst is huge, usually reaches TB grade, and has the adverse effects of extremely high time delay and the like, so that another important problem is quick elimination. The common method and corresponding deficiencies for eliminating micro-bursts are as follows: selecting other switch outlets to reroute the micro burst flow, wherein the method needs the participation of a control plane, has larger delay of communication and interaction and can not eliminate the micro burst in time; the neighbor switch is used as a cache space of micro burst traffic, and the method cannot cope with the situation that the neighbor switch queue also generates micro burst; performing transmission rate adjustment and the like at a host end, wherein the method requires the host end to modify a network protocol; etc.
In recent years, programmable switches rapidly develop, and a programmable data plane formed by a P4 switch (supporting the use of a P4 programming language) provides a flexible way for user-defined data packet processing and forwarding actions, so that communication delay with a control plane is avoided, and therefore, the use of the P4 switch as an entity of an edge switch of the internet of things is a better choice. The P4 switch can be flexibly programmed, but the custom forwarding algorithm has low time and space complexity because of supporting high-speed forwarding of data and less resources such as internal registers. The micro-burst detection and cancellation method implemented on the P4 switch has to take into account resource limitations as well.
Disclosure of Invention
Aiming at the defects or improvement demands of the prior art, the invention provides a micro-burst detection and elimination method and system based on a programmable data plane, which aim at realizing rapid detection and elimination of micro-bursts by considering the time delay demands of micro-bursts and the physical resource limitation of an edge network of the Internet of things.
In order to achieve the above object, the present invention provides a method for detecting and eliminating micro burst based on programmable data plane, comprising:
s1, setting the maximum exit rate and the maximum queuing delay of each priority queue, and micro-burst threshold rate;
S2, analyzing time delay requirements of a plurality of data streams in a pipeline, and distributing the data streams to different priority queues according to the principle that the time delay required by the data streams is lower and the priority of the queues is higher;
s3, for each data stream, predicting the entry rate of the data stream into the priority queue, and predicting the queuing delay of the data stream into the priority queue according to the maximum exit rate of the priority queue to which the data stream belongs;
if the estimated entry rate is greater than the set micro-burst threshold rate and the estimated queuing delay is greater than the maximum queuing delay set by the corresponding priority queue, judging that the data stream is micro-burst, and executing step S4; otherwise, returning to the step S2;
S4, taking the time delay required by the micro burst flow as a guarantee target, and carrying out dynamic rate adjustment on the flow with the priority lower than the priority of the micro burst flow.
Preferably, for each data flow, the entry rate of the data flow into the belonging priority queue is estimated, specifically:
01. Judging the time stamp t c of the current data packet of the data flow entering the exchanger pipeline and the time stamp t p of the data packet on the flow; if T c is greater than T p, setting a time interval T i＝tc-tp between the current data packet and the last data packet; otherwise, T i is set to 0;
02. counting the number N of data packet sequences entering a priority queue to which a data stream belongs;
03. the ingress rate V of a data flow into the belonging priority queue is calculated by the following formula:
i represents the sequence number of the time interval between the current data packet and the last data packet.
Preferably, the queuing delay of the data stream entering the priority queue is estimated according to the maximum exit rate of the priority queue to which the data stream belongs, specifically:
solving the reciprocal of the maximum exit rate of the priority queue to which the data flow belongs, and obtaining the minimum transmission delay T o of the adjacent data packets;
The queuing delay T q of the data flow entering the belonging priority queue is calculated by the following formula:
preferably, the step S4 is specifically,
S4.1, if a plurality of data streams exist and are lower than the priority of the micro burst stream, the data packets of the data stream with the lowest priority are discarded preferentially, and then the data packets with the low priority are discarded, and the like;
s4.2, setting a packet loss interval W and a monitoring time T m for a data stream needing packet loss;
s4.3, discarding the W-th data packet every W data packets;
S4.4, if the elapsed monitoring time T m,Tq is still larger than the set maximum queuing time delay, reducing the packet loss interval W; if not, the packet loss is ended.
Preferably, the packet loss interval W is reduced to half at a time.
Preferably, wmin is 1 and no longer varies.
In general, the above technical solution conceived by the present invention can achieve the following advantageous effects compared to the prior art.
The time to detect micro-bursts is reduced. The Meter in P4 measures the rate of the flow, and the Meter tristimulus marker (trTCM) measures the IP data flow and marks its packets as green, yellow or red. It is necessary to set both PIR and CIR in advance, with PIR being greater than CIR. If the data stream rate exceeds PIR, it is marked red. Otherwise, it is marked as yellow or green depending on whether it exceeds the CIR. A certain pair of fixed PIR, CIR is usually set to fail to achieve the expected measurement effect. Meter of data plane usually needs to combine control plane to adjust PIR, CIR dynamically to achieve more accurate measurement effect, but because of delay of control plane and data plane, good measurement effect can not be obtained for micro burst flow rate. The invention provides a method for rapidly estimating the speed in the data plane, which can achieve rapid detection by using resources such as a register, a counter and the like and information such as a built-in time stamp and the like without participation of a control plane.
The input bandwidth of the pipeline is not increased when detecting micro bursts. The P4 switch uses a pipelined architecture to process and forward packets that either select an ingress egress queue or are discarded on the pipeline, followed by a non-programmable traffic manager (containing the queue) where relevant information in the queue (queue length, queuing delay, etc.) can be obtained. The related queue information can be used as a flag for judging the micro-burst, and the related queue information is usually required to be transferred to a pipeline through packet replication so as to adopt a corresponding processing strategy for the micro-burst flow. If a packet duplication and transmission mode using queue information as a packet header is adopted for all data packets, the input bandwidth of a pipeline is increased and the processing cost is relatively high. The invention provides a method for rapidly estimating queuing delay, which estimates queuing delay by recording arrival time of a data packet and known departure time of the data packet, and does not increase input bandwidth of a pipeline.
And 3, the micro burst is eliminated rapidly, and the time delay requirement of the micro burst flow is ensured. The micro burst elimination method introduced in the background directly considers the size of the traffic and does not directly aim at the delay requirement of the traffic. The method directly takes estimated queuing delay as a guarantee target for the micro burst flow, and rapidly eliminates the micro burst and guarantees the delay requirement of the micro burst flow by discarding a certain amount of flow data packets with the lowest delay requirement in a pipeline packet loss mode.
Drawings
FIG. 1 is a flow chart of a method for detecting and eliminating micro bursts based on a programmable data plane;
fig. 2 is a schematic diagram of micro burst cancellation (packet loss process) for latency requirements.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
A micro burst detection and elimination method based on programmable data plane,
The micro burst traffic input by the method of the invention should include corresponding time delay requirements, such as maximum queuing time delay through a certain switch, etc., and corresponding traffic can be generated by carrying corresponding time delay information in the IP packet header. For traffic that already contains delay sensitive requirements, the process flow of the method comprises the following steps:
Step 1: and setting the maximum exit rate and the maximum queuing delay of each priority queue, and micro-burst threshold rate. All three parameters are set before the program runs, are adjustable parameters, and the rate expression mode is the number of data packets passing in unit time.
Step 2: and analyzing the time delay requirements of a plurality of data streams in the pipeline, and distributing the time delay requirements to the priority queues. The lower the latency required by the flow, the higher the queue priority.
Step 3: and detecting micro burst flow. The ingress rate of the flow into the priority queue is estimated. The queuing delay in the priority queue is estimated in combination with the maximum exit rate of the priority queue to which the flow belongs. If the estimated ingress rate of the flow is greater than the set micro-burst threshold rate and the estimated queuing delay is greater than the set priority queue maximum queuing delay, then the flow is considered to be a micro-burst.
Step 4: and taking time delay as a guarantee target for micro burst elimination. The specific method for eliminating the micro burst comprises the following steps: dynamic rate adjustment is performed for certain flows having a lower priority than the flow.
Preferably, step 3 comprises the sub-steps of:
Step 3-1: the time stamp of the current data packet of the stream entering the switch pipeline is recorded as t c, and the time stamp of one data packet on the stream is read as t p. If T c is greater than T p, the time interval between the recording of the current packet and the previous packet is T i, i.e., T i＝tc-tp. Otherwise, T i is 0.
Step 3-3: and obtaining the minimum transmission delay T o of the adjacent data packet according to the maximum outlet rate of the priority queue to which the flow belongs. The minimum propagation delay is the inverse of the maximum egress rate, and if the maximum egress rate is set to 1000 packets per second, T o is 0.001 seconds.
Step 3-4: the number of data packets entering the priority queue is recorded as N. The estimated queuing delay T q for this flow, the estimated ingress rate V i is calculated by the following formula:
if the estimated ingress rate V i of the flow is greater than the set micro-burst threshold rate and the estimated queuing delay T q is greater than the set priority queue maximum queuing delay, then the flow is considered a micro-burst and a guaranteed delay is required.
Preferably, step4 comprises the sub-steps of:
Step 4-1: dynamic rate adjustment is performed for certain flows having a lower priority than the micro-burst. If there are multiple flows with lower priority than the flow, the rate of the lowest priority flow is preferably adjusted, such as in the present example, if the flow has priority 7, the packets of the flow with priority 0 are preferably discarded, the packets of the flow with priority 1 are discarded, and so on.
Step 4-2: and judging whether the packet of the flow with the priority is lost or not. If the packet is lost, a packet loss interval W and a monitoring time T m are set. Every W data packets discard the W data packets (for example, the counter counts 10 data packets, when 10 data packets are counted, the 10 data packets are discarded), if the elapsed monitoring time T m,Tq is still greater than the set maximum queuing delay, the packet loss interval is reduced, and referring to FIG. 2, the embodiment of the invention changes the packet loss interval W into half, and the Wmin is 1 and is not changed any more. If the packet is not lost, no operation is performed.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (5)
1. A method for detecting and eliminating micro-bursts based on a programmable data plane, comprising:
s1, setting the maximum exit rate and the maximum queuing delay of each priority queue, and micro-burst threshold rate;
S2, analyzing time delay requirements of a plurality of data streams in a pipeline, and distributing the data streams to different priority queues according to the principle that the time delay required by the data streams is lower and the priority of the queues is higher;
s3, for each data stream, predicting the entry rate of the data stream into the priority queue, and predicting the queuing delay of the data stream into the priority queue according to the maximum exit rate of the priority queue to which the data stream belongs;
for each data flow, the entry rate of the data flow into the priority queue is estimated, specifically:
01. Judging the time stamp t c of the current data packet of the data flow entering the exchanger pipeline and the time stamp t p of the data packet on the flow; if T c is greater than T p, setting a time interval T i＝tc-tp between the current data packet and the last data packet; otherwise, T i is set to 0;
02. counting the number N of data packet sequences entering a priority queue to which a data stream belongs;
03. the ingress rate V of a data flow into the belonging priority queue is calculated by the following formula:
i represents the sequence number of the time interval between the current data packet and the last data packet;
According to the maximum outlet rate of the priority queue to which the data flow belongs, the queuing delay of the data flow entering the priority queue is estimated, specifically:
solving the reciprocal of the maximum exit rate of the priority queue to which the data flow belongs, and obtaining the minimum transmission delay T o of the adjacent data packets;
The queuing delay T q of the data flow entering the belonging priority queue is calculated by the following formula:
if the estimated entry rate is greater than the set micro-burst threshold rate and the estimated queuing delay is greater than the maximum queuing delay set by the corresponding priority queue, judging that the data stream is micro-burst, and executing step S4; otherwise, returning to the step S2;
S4, taking the time delay required by the micro burst flow as a guarantee target, and carrying out dynamic rate adjustment on the flow with the priority lower than the priority of the micro burst flow.
2. The method of claim 1, wherein step S4 is performed by,
S4.1, if a plurality of data streams exist and are lower than the priority of the micro burst stream, the data packets of the data stream with the lowest priority are discarded preferentially, and then the data packets with the low priority are discarded, and the like;
s4.2, setting a packet loss interval W and a monitoring time T m for a data stream needing packet loss;
s4.3, discarding the W-th data packet every W data packets;
S4.4, if the elapsed monitoring time T m,Tq is still larger than the set maximum queuing time delay, reducing the packet loss interval W; if not, the packet loss is ended.
3. The method of claim 2, wherein the packet loss interval W is reduced to half at a time.
4. The method of claim 2, wherein wminium is 1 and no longer changed.
5. A programmable data plane based packet forwarding system comprising: a computer readable storage medium and a processor;
the computer-readable storage medium is for storing executable instructions;
The processor is configured to read executable instructions stored in the computer readable storage medium and perform a method of detecting and eliminating micro-bursts based on a programmable data plane as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210233618.7A CN114745309B (en) | 2022-03-10 | 2022-03-10 | Micro burst detection and elimination method and system based on programmable data plane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210233618.7A CN114745309B (en) | 2022-03-10 | 2022-03-10 | Micro burst detection and elimination method and system based on programmable data plane |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114745309A CN114745309A (en) | 2022-07-12 |
| CN114745309B true CN114745309B (en) | 2024-05-24 |
Family
ID=82274395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210233618.7A Active CN114745309B (en) | 2022-03-10 | 2022-03-10 | Micro burst detection and elimination method and system based on programmable data plane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114745309B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116582507B (en) * | 2023-07-12 | 2023-10-03 | 华中科技大学 | Network micro burst flow detection method based on programmable switch and related equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102064679B1 (en) * | 2018-07-25 | 2020-01-09 | 고려대학교 산학협력단 | Method for processing data |
| CN112187586A (en) * | 2020-10-13 | 2021-01-05 | 盛科网络（苏州）有限公司 | Method and device for monitoring micro burst flow |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5958327B2 (en) * | 2012-12-21 | 2016-07-27 | 富士通株式会社 | Relay device and buffer control method |
| US10587486B2 (en) * | 2018-04-30 | 2020-03-10 | Hewlett Packard Enterprise Development Lp | Detecting microbursts |
-
2022
- 2022-03-10 CN CN202210233618.7A patent/CN114745309B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102064679B1 (en) * | 2018-07-25 | 2020-01-09 | 고려대학교 산학협력단 | Method for processing data |
| CN112187586A (en) * | 2020-10-13 | 2021-01-05 | 盛科网络（苏州）有限公司 | Method and device for monitoring micro burst flow |
Non-Patent Citations (1)
| Title |
|---|
| 基于5G移动通信的集中式无线接入网络负载均衡算法研究;张曼;《硕士电子期刊》;20210915;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114745309A (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11005769B2 (en) | Congestion avoidance in a network device | |
| US9674102B2 (en) | Methods and network device for oversubscription handling | |
| US8665892B2 (en) | Method and system for adaptive queue and buffer control based on monitoring in a packet network switch | |
| CN107948103B (en) | Switch PFC control method and control system based on prediction | |
| CN102804714B (en) | Controlling packet transmission | |
| US20060203730A1 (en) | Method and system for reducing end station latency in response to network congestion | |
| CN112087804B (en) | Time-sensitive network gating time slot adjusting method and system | |
| US10637792B2 (en) | Real-time analysis of quality of service for multimedia traffic in a local area network | |
| Hock et al. | TCP LoLa: Congestion control for low latencies and high throughput | |
| US8234401B2 (en) | Adaptive policers responsive to utilization levels of a resource | |
| TW201340648A (en) | Reducing headroom | |
| US9350669B2 (en) | Network apparatus, performance control method, and network system | |
| CN114745309B (en) | Micro burst detection and elimination method and system based on programmable data plane | |
| WO2021083160A1 (en) | Data transmission method and apparatus | |
| US20140241160A1 (en) | Scalable, Low Latency, Deep Buffered Switch Architecture | |
| US7233578B1 (en) | Network with self regulating quality of service (QoS) | |
| CN111108728B (en) | Method and device for processing message | |
| US8867350B2 (en) | Method and apparatus for packet buffering measurement | |
| JP2020022023A (en) | Packet transfer device, method, and program | |
| US8660001B2 (en) | Method and apparatus for providing per-subscriber-aware-flow QoS | |
| Lakkakorpi et al. | Minimizing delays in mobile networks: With dynamic gateway placement and active queue management | |
| CN109347761B (en) | Flow forwarding control method and device | |
| JP2003258881A (en) | Adaptive quality control system | |
| Qiao et al. | Fine-Grained Active Queue Management in the Data Plane with P4 | |
| CN114979011A (en) | Congestion control method applied to park network |
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 |