基于链路容量的多路径拥塞控制算法

doi:10.11959/j.issn.1000-436x.2020106

通信学报 ›› 2020, Vol. 41 ›› Issue (5): 59-71.doi: 10.11959/j.issn.1000-436x.2020106

基于链路容量的多路径拥塞控制算法

王竹^1,²,袁青云^1,²,郝凡凡^1,²,房梁¹(),李凤华^1,²

¹ 中国科学院信息工程研究所，北京 100093
² 中国科学院大学网络空间安全学院，北京 100049

修回日期:2020-04-09 出版日期:2020-05-25 发布日期:2020-05-30
作者简介:王竹（1972- ），女，山西太原人，博士，中国科学院信息工程研究所研究员、在站博士后，主要研究方向为信息安全、人工智能|袁青云（1994- ），男，湖北孝感人，中国科学院信息工程研究所硕士生，主要研究方向为计算机网络、信号处理|郝凡凡（1995- ），女，河北石家庄人，中国科学院信息工程研究所硕士生，主要研究方向为安全协议与理论、计算机网络|房梁（1989- ），男，山西太原人，博士，中国科学院信息工程研究所助理研究员，主要研究方向为信息安全、访问控制|李凤华（1966- ），男，湖北浠水人，博士，中国科学院信息工程研究所研究员、博士生导师，主要研究方向为网络与系统安全、信息保护、隐私计算
基金资助:
国家重点研发计划基金资助项目(2018YFB0803903);国家自然科学基金资助项目(U1836203);国家自然科学基金资助项目(61672515);山东省重点研发计划基金资助项目(2019JZZY020127);中国科学院战略性先导科技专项基金资助项目(XDC02040400)

Multipath congestion control algorithm based on link capacity

Zhu WANG^1,²,Qingyun YUAN^1,²,Fanfan HAO^1,²,Liang FANG¹(),Fenghua LI^1,²

¹ Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100093,China
² School of Cyber Security,University of Chinese Academy of Sciences,Beijing 100049,China

Revised:2020-04-09 Online:2020-05-25 Published:2020-05-30
Supported by:
The National Key Research and Development Program of China(2018YFB0803903);The National Natural Science Foundation of China(U1836203);The National Natural Science Foundation of China(61672515);The Key Research and Development Program of Shandong Province(2019JZZY020127);The Strategic Priority Research Program of the Chinese Academy of Sciences(XDC02040400)

摘要/Abstract

摘要：

多路径传输的链路差异性和TCP友好性约束等因素导致将现有的TCP拥塞控制机制直接用于多路径传输时，会带来带宽分配不公平的问题。针对此问题，提出了一种基于链路容量的多路径拥塞控制算法。所提算法基于反馈调节拥塞的思想，利用M/M/1缓存队列模型调控接收端缓存队列大小，对发送端吞吐量进行调节，实现多路径联合拥塞控制。实验结果证明，所提算法可提升多路径传输带宽利用率、多路径拥塞控制算法响应能力，保证多路径传输公平性。

关键词: 多路径TCP, 拥塞控制, 公平性, 带宽利用率, 反馈调节

Abstract:

Factors such as link differences and TCP friendliness constraints lead to the problem of unfair bandwidth allocation when the TCP congestion control mechanism was applied directly to multi-path transmission.To address the problem,it was proposed that a multipath congestion control algorithm was based on link capacity.The proposed algorithm which was based on the concept of feedback regulation achieved multipath joint congestion control by establishing the M/M/1 cache queue model to adjust the throughput rate of senders.Experimental results show the proposed algorithm can improve the multipath transmission bandwidth utilization and the multipath congestion control algorithm responsiveness,and ensure the fairness of multipath transmission.

Key words: multipath TCP, congestion control, fairness, bandwidth utilization efficiency, feedback regulation

中图分类号:

TN929

王竹,袁青云,郝凡凡,房梁,李凤华. 基于链路容量的多路径拥塞控制算法[J]. 通信学报, 2020, 41(5): 59-71.

Zhu WANG,Qingyun YUAN,Fanfan HAO,Liang FANG,Fenghua LI. Multipath congestion control algorithm based on link capacity[J]. Journal on Communications, 2020, 41(5): 59-71.

图/表 20

图1

图2

图3

图5

图6

图4

图7

表1

图8

图9

图10

图11

表2

图12

图13

图14

表3

图15

图16

表4

参考文献 29

[1]	FORD A , RAICIU C , HANDLEY M ,et al. Architectural guidelines for multipath TCP development:RFC6182[S].IETF,(2011-03)[2019-02-03]. IETF,(2011-03)[2019-02-03].
[2]	YE J , FENG L T , XIE Z Q ,et al. Fine-grained congestion control for multipath TCP in data center networks[J]. IEEE Access, 2019:1.
[3]	LUCAS C , AHMED A , PRATEEK S ,et al. Performance evaluation of multipath TCP for data center and cloud workloads[M]. New York: Association for ComputingPress, 2019: 13-24.
[4]	MAI T , YAO H , JING Y ,et al. Self-learning congestion control of MPTCP in satellites communications[C]// 2019 15th International Wireless Communications and Mobile Computing Conference. Piscataway:IEEE Press, 2019: 775-780.
[5]	WISCHIK D , RAICIU C , GREEHAKGH A ,et al. Design,implementation and evaluation of congestion control for multipath TCP[C]// Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation. Berkeley:USENIX Association, 2011: 8-22.
[6]	RAICIU C , HANDLEY M , WISCHIK D . Coupled congestion control for multipath transport protocols:RFC6356[S]. IETF,(2011-10)[2020-02-04]
[7]	KHALILI R , GAST N G , POPOVIC M ,et al. MPTCP is not pareto-optimal:performance issues and a possible solution[J]. IEEE/ACM Transactions on Networking, 2013,21(5): 1651-1665.
[8]	CAO Y , XU M , FU X . Delay-based congestion control for multipath TCP[C]// 2012 20th IEEE International Conference on Network Protocols (ICNP). Piscataway:IEEE Press, 2013: 1-10.
[9]	GONZALEZ R , PRADILLA J , ESTEVE M ,et al. Hybrid delay-based congestion control for multipath TCP[C]// 2016 18th Mediterranean Electrotechnical Conference. Piscataway:IEEE Press, 2016: 1-6.
[10]	LI H , WANG Y , SUN R . Delay-based congestion control for multipath TCP in heterogeneous wireless networks[C]// 2019 IEEE Wireless Communications and Networking Conference Workshop. Piscataway:IEEE Press, 2019: 1-6.
[11]	HASSAYOUN S , IYENGAR J , ROS D . Dynamic window coupling for multipath congestion control[C]// Proceedings of the 19th Annual IEEE International Conference on Network Protocols. Piscataway:IEEE Press, 2011: 341-352.
[12]	FERLIN S , ALAY O , HAYES D ,et al. Revisiting congestion control for multipath TCP with shared bottleneck detection[C]// IEEE INFO COM-The IEEE International Conference on Computer Communications. Piscataway:IEEE Press, 2016: 1-9.
[13]	ZHANG S , LEI W , ZHANG W ,et al. Shared bottleneck detection based on trend line regression for multipath transmission[EB/OL].(2018-12-14)[2020-02-04]
[14]	YEGANEH S H , HASSAS S , CHENG Y Z ,et al. BBR:congestion-based congestion control[J]. Communications of the ACM, 2017,60(2): 58-66.
[15]	WALID A , PENG Q Y , HWANG J ,et al. Balanced linked adaptation congestion control algorithm for MPTCP:Internet draft draftwalid-MPTCP-congestion-control-04[S].IETF,(2016-01-26)[2020-02-03]. IETF,(2016-01-26)[2020-02-03].
[16]	HONDA M , NISHIDA Y , EGGERT L ,et al. Multipath congestion control for shared bottleneck[C]// Proceedings of the 7th International Workshop on Protocols for Future,Large-Scale and Diverse network Transports. New York:ACM Press, 2009: 19-24.
[17]	XUE K P , HAN J P , ZHANG H ,et al. Migrating unfairness among subflows in MPTCP with network coding for wired-wireless networks[J]. IEEE Transactions on Vehicular Technology, 2017,66(1): 798-809.
[18]	TRINH B , MURPHY L , MUNTEAN G . An energy-efficient congestion control scheme for MPTCP in wireless multimedia sensor networks[C]// 2019 IEEE 30th Annual International Symposium on Personal,Indoor and Mobile Radio Communications . Piscataway:IEEE Press, 2019: 1-7.
[19]	XU Z Y , TANG J , YIN C X ,et al. Experience-driven congestion control:when multi-path TCP meets deep reinforcement learning[J]. IEEE Journal on Selected Areas in Communications, 2019,37(6): 1325-1336.
[20]	BARAKABITZE A A , MKWAWA I H , SUN L F ,et al. QualitySDN:improving video quality using MPTCP and segment routing in SDN/NFV[C]// 4th IEEE Conference on Network Softwarization and Workshops. Piscataway:IEEE Press, 2018: 182-186.
[21]	HANDLEY M , BONAVENTURE O , RAICIU C ,et al. TCP extensions for multipath operation with multiple addresses：RFC6824[S]. IETF,(2013-11)[2020-02-04].
[22]	KLEINROCK L , . Power and deterministic rules of thumb for probabilistic problems in computer communications[C]// Proceedings of the International Conference On Communications. Piscataway:IEEE Press, 1979:1.
[23]	FLOYD S , FALL K . Promoting the use of end-to-end congestion control in the Internet[J]. IEEE/ACM Transactions on Networking, 1999(7): 458-472.
[24]	CAO J , RAMANAN K . A poisson limit for buffer overflow probabilities[C]// Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies.Proceedings. Piscataway:IEEE Press, 2002: 994-1003.
[25]	SALVAODR P , VALADAS R , PACHECO A . multiscale fitting procedure using Markov modulated poisson processes[J]. Telecommunication Systems, 2003,23(1-2): 123-148.
[26]	GitHup. Multipath congestion control algorithm based on link capacity[EB].(2019-12-28)[2020-02-04].
[27]	WEI W J , WANG Y S , XUE K P ,et al. Shared bottleneck detection based on congestion interval variance measurement[J]. IEEE Communications Letters, 2018,22(12): 2467-2470.
[28]	FLOYD S , . Equation-based congestion control for unicast applications[C]// Conference on Applications. New York:ACM Press, 2000(30): 43-56.
[29]	NGUYEN V D , RO S . Performance evaluation of MPTCP over shared bottleneck link[J]. The Journal of Korean Institute of Communications and Information Sciences, 2015,40(1): 70-77.

符号	含义
λ	数据分组到达节点缓冲区服从参数为λ的泊松分布
μ	数据分组离开节点缓冲区服从参数为μ的负指数分布
N	缓冲区大小，即可容纳的数据分组个数
P_n	系统稳定时，缓冲区中有n个数据分组的概率
t₀	传输时延与处理时延之和
λ_limit	系统瓶颈带宽
W	发送端一次向网络中发送的数据量
B_max	链路中最大可用带宽

参数	值
段大小/ B	1 500
初始窗口/ B	7×1 500
瓶颈带宽/ (Mbit·s^-1)	100
接入带宽/ (Mbit·s^-1)	200
往返时延（RTT）/ ms	5
分组丢失率（P）	0
仿真启动时间/ s	0.01
仿真结束时间/ s	60
MPTCP流的对数（N₁）	1
TCP流的个数（N₂）	1
Inflight调节因子（α）	2
PacingGain调节因子（β）	0.25

路径			分组丢失率
路径1	0	0.01%	0.1%	1%	5%
路径2	0	0.01%	0.1%	1%	5%

算法	响应速度/ s
EWTCP	3.25
OLIA	58.50
BALIA	14.73
MPLC	2.00

基于链路容量的多路径拥塞控制算法

Multipath congestion control algorithm based on link capacity

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 20

参考文献 29

相关文章 15

Metrics

推荐阅读 0

[1]	孙彦景, 程枫陟, 周家思, 李松. 公平性驱动的RSMA-SDMA预编码设计[J]. 通信学报, 2022, 43(4): 177-185.
[2]	叶迎晖,施丽琴,卢光跃. 反向散射辅助的无线供能通信网络中用户能效公平性研究[J]. 通信学报, 2020, 41(7): 84-94.
[3]	谭国真,韩国栋,张福新,丁男,刘明剑. 基于网络效用最大化理论的分布式车联网拥塞控制策略[J]. 通信学报, 2019, 40(2): 82-91.
[4]	苏成龙,金光,江先亮,钮俊. 公平和低时延的主动队列管理算法研究[J]. 通信学报, 2017, 38(5): 199-206.
[5]	张恩,耿魁,金伟,李勇俊,孙韵清,李凤华. 抗隐蔽敌手的云外包秘密共享方案[J]. 通信学报, 2017, 38(5): 57-65.
[6]	谢显中,卢华兵,施赵媛. 基于轮询机制的公平高效机会干扰对齐算法[J]. 通信学报, 2017, 38(10): 1-9.
[7]	丁男,林滔,宋彩霞,谭国真. 面向车联网按需驱动的多宿主多链路TCP拥塞控制算法[J]. 通信学报, 2016, 37(7): 96-106.
[8]	刘明剑,谭国真,李帅兵,丁男,宋彩霞. 基于信道拥塞代价计算的车联网自适应消息发送速率控制方法[J]. 通信学报, 2016, 37(10): 108-116.
[9]	燕洪成,张庆君,孙勇. 空间延迟/中断容忍网络拥塞控制策略研究[J]. 通信学报, 2016, 37(1): 142-150.
[10]	夏奕,邓广宏. DTN分发网络中基于数据投递概率的拥塞控制机制[J]. 通信学报, 2015, 36(Z1): 22-39.
[11]	朱更明,王志强,李哲涛,李仁发. 信道公平分配的局部拥塞控制算法[J]. 通信学报, 2015, 36(4): 9-18.
[12]	王志军,胡封晔,尹颖奇,刘小兰. 基于无线体域网的传输功率控制和调度算法[J]. 通信学报, 2015, 36(10): 271-277.
[13]	田波，杨宜民，蔡述庭. 基于半马尔科夫决策过程的视频传输拥塞控制算法[J]. 通信学报, 2014, 35(8): 19-161.
[14]	田波,杨宜民,蔡述庭. 基于半马尔科夫决策过程的视频传输拥塞控制算法[J]. 通信学报, 2014, 35(8): 154-161.
[15]	卢笛,马建峰,王一川,习宁,孟宪佳. 面向云计算环境的动态公平性度量方法[J]. 通信学报, 2014, 35(7): 140-150.