CN109347702A - Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC - Google Patents

Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC Download PDF

Info

Publication number
CN109347702A
CN109347702A CN201811346920.3A CN201811346920A CN109347702A CN 109347702 A CN109347702 A CN 109347702A CN 201811346920 A CN201811346920 A CN 201811346920A CN 109347702 A CN109347702 A CN 109347702A
Authority
CN
China
Prior art keywords
rate
length
buffer queue
congestion
udp
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.)
Pending
Application number
CN201811346920.3A
Other languages
Chinese (zh)
Inventor
赵昶宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Jinhang Computing Technology Research Institute
Original Assignee
Tianjin Jinhang Computing Technology Research Institute
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tianjin Jinhang Computing Technology Research Institute filed Critical Tianjin Jinhang Computing Technology Research Institute
Priority to CN201811346920.3A priority Critical patent/CN109347702A/en
Publication of CN109347702A publication Critical patent/CN109347702A/en
Pending legal-status Critical Current

Links

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
    • H04L43/0882—Utilisation of link capacity
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • 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

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 present invention relates to a kind of methods using Ethernet length of buffer queue prediction UDP Congestion Level SPCC, belong to network communication technology field.The present invention initially sets up UDP message packet and sends buffer queue, defines congestion level according to the extent of deviation that current UDP message packet sends the length of buffer queue and the optimum length of buffer queue, and UDP congestion level is divided into idle and two kinds of congestion.Then transmission rate is adjusted according to congestion level and congestion judgment method, adjustment to guarantee UDP transmission rate is more smooth, jitter present in rate control is reduced, using increasing with formula and adjusting transmission rate with the adaptive parameter control method of formula reduction, effectively alleviates network congestion.

Description

Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC
Technical field
The invention belongs to network communication technology fields, and in particular to a kind of to predict UDP using Ethernet length of buffer queue The method of Congestion Level SPCC.
Background technique
In recent years, the Stream Media Application of having a try such as IP phone, the network teleconference and long-distance education largely increases, these are answered With mostly using udp protocol to be transmitted greatly.And udp protocol is a kind of connectionless protocol, it has certain excellent in transmission speed Gesture, but there is also the problems for lacking congestion control mechanism and transmission reliability difference.Network congestion will lead to multiple network transmission Performance is significantly deteriorated, such as throughput degradation, and communication time-delay increases, and packet loss increases etc., results even in when serious entire Network system collapse.Therefore, both had emphatically to industrial network for integrated good, the effective jamming control method of one kind of udp protocol Practical significance is wanted, also there is highly important researching value.
The current most common detection UDP congestion methods have:
1) based on the control of packet loss
The basic thought of this congestion control is that receiving end often receives N number of packet or sent a net to receiving end every T seconds The assessment report of network packet loss, transmitting terminal assess network congestion degree according to the packet loss of return, adjust transmission rate accordingly. This method is the measure for occurring to take after congestion in network, cannot function as the detection of congestion；And this timed interval Size directly affects the control effect of congestion.
2) congestion control based on round trip delay time RTT
This method sends detection group in transmitting terminal to estimate the RTT of future time, although can theoretically do by timing To the early detection of network congestion, but in real network RTT be difficult to calculate accurately, and it there is also chain roads Asymmetry cannot reflect the Network status problem on one way link.
Summary of the invention
(1) technical problems to be solved
The technical problem to be solved by the present invention is a kind of method for predicting UDP Congestion Level SPCC how is designed, it can be in the early stage It detects network congestion and is effectively controlled elm rate is passed, improve the utilization rate of Internet resources, reduce losing for data packet Packet rate.
(2) technical solution
It is gathered around in order to solve the above-mentioned technical problems, the present invention provides a kind of using Ethernet length of buffer queue prediction UDP The method of plug degree, comprising the following steps:
S1: calculate the optimum length of buffer queue
When carrying out network transmission based on udp protocol, transmitting terminal initially sets up a transmission buffer queue, before transmitting Each packet voice to be sent is stored in the transmission buffer queue, is modified the length for sending buffer queue, is being sent After complete message, when transmitting terminal receives the confirmation message of receiving end feedback, then the message is removed the transmission and cached by transmitting terminal Queue, and the length for sending buffer queue is modified, if send every time, the length for sending buffer queue is increasingly It is long, show that congestion phenomenon occurs in network；Conversely, showing that network is in idle condition, being in neither idle in Ethernet nor gathering around The optimum length L of buffer queue under plug-like state0；
S2: define UDP congestion level
Enabling Length is the length that current UDP message packet sends buffer queue, is sent and is cached according to current UDP data packet The extent of deviation L of the optimum length of the length and buffer queue of queue0Define UDP congestion level；
Congestion level is divided into following two grade by according to the form below:
Congestion level 1 2
Network state It is idle Congestion
The range of Length 0 < Length≤L0 L0< Length
S3: transmission rate is adjusted according to congestion level and congestion judgment method.
Preferably, step S3In, enabling UDP message packet transmission speed interval range is [Ratemin, Ratemax], wherein RateminIndicate the acceptable minimum transmission rate of UDP message packet, RatemaxIt indicates the targeted rate of UDP message packet, enables RatenowFor the instant transmission rate of UDP message packet；
(1) when the network is in the idle state, i.e. 0 < Length≤L0, the instant transmission rate Rate of UDP message packetnow Are as follows:
Ratenow=min { Ratenow+ β, Ratemax}；
Network is in state under load at this time, and the value of β is determined by following formula:
I.e. the value range of β is [Ratemax× 10%, Ratemax× 20%].
(2) when network is in congestion state, i.e. L0< Length, the instant transmission rate Rate of UDP message packetnowAre as follows:
RateNow=max{Ratenow- γ, Ratemin}；
Network is in congestion state at this time, and the value of γ is determined by following formula:
Preferably, step S1In, the optimum length L of buffer queue in the case where Ethernet is in neither idle nor congestion state0 Are as follows:
Wherein c1And c2It is weight, and c1+c2=1.
ρ=λ/μ
ρ indicates Ethernet in the mean number of transmitted per unit time data frame, and λ indicates to enter caching team in the unit time The average data frame number of column, μ indicate Ethernet in the mean number of transmitted per unit time data frame.
Preferably, 0 < c1< 1.
Preferably, 0 < c2< 1.
(3) beneficial effect
The present invention initially sets up UDP message packet and sends buffer queue, and the length of buffer queue is sent according to current UDP message packet The extent of deviation of degree and the optimum length of buffer queue defines congestion level, and UDP congestion level is divided into idle and congestion Two kinds.Then transmission rate is adjusted according to congestion level and congestion judgment method, the adjustment to guarantee UDP transmission rate is more flat It is sliding, jitter present in rate control is reduced, the adaptive parameter control method adjustment using increasing with formula and with formula reduction Transmission rate effectively alleviates network congestion.Method proposed by the present invention can be predicted according to the Network status of one way link UDP network congestion, while not will increase network burden, cause network packet loss rate to increase；This method calculates simply, to greatest extent Have compressed the judgement interval time of congestion level, and using linear function dynamic adjustment transmission rate, it is greatly smooth to send The adjustment of rate improves the utilization rate of Internet resources, reduces the packet loss of data packet.
Detailed description of the invention
Fig. 1 is method overview flow chart of the invention；
Fig. 2 is the flow chart of prediction UDP congestion level of the invention.
Specific embodiment
To keep the purpose of the present invention, content and advantage clearer, with reference to the accompanying drawings and examples, to of the invention Specific embodiment is described in further detail.
Aiming at the problem that udp protocol transmission reliability difference and shortage congestion control mechanism, the invention proposes a kind of predictions The method of UDP Congestion Level SPCC.This method initially sets up UDP message packet and sends buffer queue, and transmitting terminal message to be sent is deposited Enter buffer queue；Then the deviation of the length of buffer queue and the optimum length of buffer queue is sent according to current UDP message packet Degree defines congestion level；Finally, according to congestion level and congestion judgment method, it is adaptive using being reduced with formula increase and with formula Parameter control method is answered to adjust transmission rate.Method proposed by the present invention can predict UDP according to the Network status of one way link Network congestion, while not will increase network burden, cause network packet loss rate to increase；This method calculates simple, maximum pressure The judgement interval time for the congestion level that contracted, and using linear function dynamic adjustment transmission rate, it is greatly smooth to send speed The adjustment of rate improves the utilization rate of Internet resources, reduces the packet loss of data packet.
As shown in Figure 1, a kind of stabbed using Ethernet length of buffer queue proposed by the present invention predicts UDP Congestion Level SPCC Method, comprising the following steps:
S1: calculate the optimum length of buffer queue
When carrying out network transmission based on udp protocol, transmitting terminal initially sets up a transmission buffer queue, before transmitting Each packet voice to be sent is stored in the transmission buffer queue, modifies the length for sending buffer queue.It is sending After complete message, when transmitting terminal receives the confirmation message of receiving end feedback, then the message is removed the transmission and cached by transmitting terminal Queue, and modify the length for sending buffer queue.If send every time, the length for sending buffer queue is increasingly It is long, show that congestion phenomenon occurs in network；Conversely, showing that network is in idle condition.
The optimum length L of buffer queue in the case where Ethernet is in neither idle nor congestion state0Are as follows:
Wherein c1(0 < c1< 1) and c2(0 < c2< 1) it is weight, and c1+c2=1.
ρ=λ/μ
ρ indicates Ethernet in the mean number of transmitted per unit time data frame, and λ indicates to enter caching team in the unit time The average data frame number of column, μ indicate Ethernet in the mean number of transmitted per unit time data frame.
S2: define UDP congestion level
Enabling Length is the length that current UDP message packet sends buffer queue, is sent and is cached according to current UDP data packet The extent of deviation L of the optimum length of the length and buffer queue of queue0Define UDP congestion level.
Predict that the flow chart of UDP congestion level is as shown in Figure 2.
Congestion level is divided into following two grade:
Congestion level 1 2
Network state It is idle Congestion
The range of Length 0 < Length≤L0 L0< Length
S3: transmission rate is adjusted according to congestion level and congestion judgment method
The opportunity that the present invention adjusts data package transmission velocity is to have judged congestion after having executed primary " transmission-reception " operation It is adjusted immediately after rank, has compressed the judgement interval time of congestion level to greatest extent.It is being passed to meet UDP message packet To the requirement of load flatness during defeated, using auto-adaptive parameter setting and formula increase and formula reduction rate control side Method.
Enabling UDP message packet transmission speed interval range is [Ratemin, Ratemax], wherein RateminIndicate UDP message packet Acceptable minimum transmission rate, RatemaxThe targeted rate for indicating UDP message packet, enables RatenowFor the instant of UDP message packet Transmission rate.
(1) when the network is in the idle state, i.e. 0 < Length≤L0, the instant transmission rate Rate of UDP message packetnow Are as follows:
RateNow=min{Ratenow+ β, Ratemax}；
Network is in state under load at this time, and in order to quickly adequately utilize Internet resources, the value of β is determined by following formula:
I.e. the value range of β is [Ratemax× 10%, Ratemax× 20%].
(2) when network is in congestion state, i.e. L0< Length, the instant transmission rate Rate of UDP message packetnowAre as follows:
Ratenow=max { Ratenow- γ, Ratemin}；
Network is in congestion state at this time, and in order to realize that network load is smooth, the value of γ is determined by following formula:
β in above formula is and formula adds the factor, and γ is and formula subtracting coefficient that the value of β and γ send slow according to current UDP message packet The value for depositing the length Length of queue is dynamically determined.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations Also it should be regarded as protection scope of the present invention.

Claims (5)

1. a kind of method using Ethernet length of buffer queue prediction UDP Congestion Level SPCC, which is characterized in that including following step It is rapid:
S1: calculate the optimum length of buffer queue
When carrying out network transmission based on udp protocol, transmitting terminal initially sets up a transmission buffer queue, before transmitting will The each packet voice sent is stored in the transmission buffer queue, is modified the length for sending buffer queue, is being sent report Wen Hou, when transmitting terminal receives the confirmation message of receiving end feedback, then the message is removed the transmission buffer queue by transmitting terminal, And the length for sending buffer queue is modified, if send every time, the length for sending buffer queue is increasingly longer, shows There is congestion phenomenon in network；Conversely, showing that network is in idle condition, in the case where Ethernet is in neither idle nor congestion state The optimum length L of buffer queue0；
S2: define UDP congestion level
Enabling Length is the length that current UDP message packet sends buffer queue, sends buffer queue according to current UDP message packet The extent of deviation L of the optimum length of length and buffer queue0Define UDP congestion level；
Congestion level is divided into following two grade by according to the form below:
Congestion level 1 2 Network state It is idle Congestion The range of Length 0 < Length≤L0 L0< Length
S3: transmission rate is adjusted according to congestion level and congestion judgment method.
2. the method as described in claim 1, which is characterized in that step S3In, enable the UDP message packet transmission speed interval range be [Ratemin, Ratemax], wherein RateminIndicate the acceptable minimum transmission rate of UDP message packet, RatemaxIndicate UDP message The targeted rate of packet, enables RatenowFor the instant transmission rate of UDP message packet；
(1) when the network is in the idle state, i.e. 0 < Length≤L0, the instant transmission rate Rate of UDP message packetnowAre as follows:
RateNow=min{Ratenow+ β, Ratemax}；
Network is in state under load at this time, and the value of β is determined by following formula:
I.e. the value range of β is [Ratemax× 10%, Ratemax× 20%]；
(2) when network is in congestion state, i.e. L0< Length, the instant transmission rate Rate of UDP message packetnowAre as follows:
Ratenow=max { Ratenow- γ, Ratemin}；
Network is in congestion state at this time, and the value of γ is determined by following formula:
3. the method as described in claim 1, which is characterized in that step S1In, neither idle nor congestion shape are in Ethernet The optimum length L of buffer queue under state0Are as follows:
Wherein c1And c2It is weight, and c1+c2=1；
ρ=λ/μ
ρ indicates Ethernet in the mean number of transmitted per unit time data frame, and λ indicates to enter buffer queue in the unit time Average data frame number, μ indicate Ethernet in the mean number of transmitted per unit time data frame.
4. method as claimed in claim 3, which is characterized in that 0 < c1< 1.
5. method as claimed in claim 3, which is characterized in that 0 < c2< 1.
CN201811346920.3A 2018-11-13 2018-11-13 Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC Pending CN109347702A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811346920.3A CN109347702A (en) 2018-11-13 2018-11-13 Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811346920.3A CN109347702A (en) 2018-11-13 2018-11-13 Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC

Publications (1)

Publication Number Publication Date
CN109347702A true CN109347702A (en) 2019-02-15

Family

ID=65314783

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811346920.3A Pending CN109347702A (en) 2018-11-13 2018-11-13 Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC

Country Status (1)

Country Link
CN (1) CN109347702A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114337916A (en) * 2021-12-03 2022-04-12 广州杰赛科技股份有限公司 Network transmission rate adjusting method, device, equipment and storage medium
CN116886622A (en) * 2023-09-08 2023-10-13 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) Network congestion control method, device, equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101232455A (en) * 2008-02-04 2008-07-30 中兴通讯股份有限公司 Congestion control method and apparatus
CN104994031A (en) * 2015-07-13 2015-10-21 天津理工大学 Active queue self-adaptive management method ASRED
CN105791143A (en) * 2016-03-09 2016-07-20 大连理工大学 Adaptive rate control method based on mobility and DSRC/WAVE network relevance feedback
US20170171099A1 (en) * 2015-12-14 2017-06-15 Mellanox Technologies Tlv Ltd. Congestion estimation for multi-priority traffic
CN107040961A (en) * 2017-06-15 2017-08-11 吉林大学 A kind of wireless sensor network jamming control method
CN108718283A (en) * 2018-05-03 2018-10-30 电子科技大学 The TCP jamming control methods that centralized end net is coordinated in data center network

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101232455A (en) * 2008-02-04 2008-07-30 中兴通讯股份有限公司 Congestion control method and apparatus
CN104994031A (en) * 2015-07-13 2015-10-21 天津理工大学 Active queue self-adaptive management method ASRED
US20170171099A1 (en) * 2015-12-14 2017-06-15 Mellanox Technologies Tlv Ltd. Congestion estimation for multi-priority traffic
CN105791143A (en) * 2016-03-09 2016-07-20 大连理工大学 Adaptive rate control method based on mobility and DSRC/WAVE network relevance feedback
CN107040961A (en) * 2017-06-15 2017-08-11 吉林大学 A kind of wireless sensor network jamming control method
CN108718283A (en) * 2018-05-03 2018-10-30 电子科技大学 The TCP jamming control methods that centralized end net is coordinated in data center network

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
CHUNNA CAO: "An improved RED algorithm with combined of queue length and sending-rate inspection", 《SECOND INTERNATIONAL MULTI-SYMPOSIUMS ON COMPUTER AND COMPUTATIONAL SCIENCES》 *
丁云青: "自适应主动队列管理算法研究", 《中国优秀硕士学位论文全文数据库》 *
郭翠娟: "具有拥塞控制机制的可靠UDP的实现", 《小型微型计算机***》 *
金海波: "工业以太网实时通信与***维护的建模与优化", 《中国博士学位论文全文数据库》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114337916A (en) * 2021-12-03 2022-04-12 广州杰赛科技股份有限公司 Network transmission rate adjusting method, device, equipment and storage medium
CN114337916B (en) * 2021-12-03 2023-06-27 广州杰赛科技股份有限公司 Network transmission rate adjustment method, device, equipment and storage medium
CN116886622A (en) * 2023-09-08 2023-10-13 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) Network congestion control method, device, equipment and storage medium
CN116886622B (en) * 2023-09-08 2023-11-24 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) Network congestion control method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN111683393B (en) Adaptive congestion control method for dynamically adjusting gain coefficient
CN102325274B (en) Network bandwidth-adaptive video stream transmission control method
EP2432175B1 (en) Method, device and system for self-adaptively adjusting data transmission rate
US7876696B2 (en) Adaptive upstream bandwidth estimation and shaping
Zhu et al. NADA: A unified congestion control scheme for low-latency interactive video
CN103647722B (en) A kind of Link Congestion Control Method based on prestige
KR101920114B1 (en) Voip bandwidth management
CN109361566A (en) Utilize the method for test serial number and message time stamp prediction UDP Congestion Level SPCC
US20190356602A1 (en) Predictive management of a network buffer
US20110013514A1 (en) Device and Method for Adaptation of Target Rate of Video Signals
CN106533963B (en) A kind of method for controlling network congestion of streaming media
US20110205889A1 (en) Controlling packet transmission
CN111935441B (en) Network state detection method and device
Lautenschlaeger et al. Global synchronization protection for bandwidth sharing TCP flows in high-speed links
Kim et al. Receiver buffer requirement for video streaming over TCP
CN109347702A (en) Utilize the method for Ethernet length of buffer queue prediction UDP Congestion Level SPCC
CN107395325B (en) Adaptive estimation transmission method serving tactical communication network
CN103428104A (en) Content-center network-based congestion control method
Attiya et al. Improving internet quality of service through active queue management in routers
US9439100B2 (en) System and method for dynamic rate adaptation based on real-time call quality metrics
Talau et al. Improving TCP performance over a common IoT scenario using the Early Window Tailoring method
Liu et al. An adaptive receiver buffer adjust algorithm for VoIP applications considering voice characters
Szilágyi et al. Efficient LTE PDCP buffer management
RU2782231C1 (en) Method for managing the buffer memory of streaming video
Zhang et al. Adaptive fast TCP

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190215