微信服务号

微信订阅号

2025年4月23日 7:48 星期三
首页 > 过刊浏览>2024年第35卷第8期 >3952-3979. DOI:10.13328/j.cnki.jos.007045
PDF HTML阅读 XML下载 导出引用 引用提醒
网络拥塞控制方法综述
作者:
作者简介:

蒋万春(1986－), 男, 博士, 副教授, 博士生导师, CCF专业会员, 主要研究领域为网络传输协议分析和设计, 流媒体传输优化, 基于机器学习的计算机网络优化;李昊阳(1997－), 男, 博士生, 主要研究领域为网络传输协议分析与设计;陈晗瑜(1996－), 女, 硕士生, 主要研究领域为网络传输协议分析与设计;王洁(1997－), 女, 硕士生, 主要研究领域为网络传输协议分析与设计;王建新(1969－), 男, 博士, 教授, 博士生导师, CCF高级会员, 主要研究领域为计算机算法与优化, 网络优化, 生物信息学;阮昌(1986－), 男, 博士, 讲师, CCF专业会员, 主要研究领域为数据中心网络, 基于机器学习的网络优化.

通讯作者:

阮昌, E-mail: ruanchang@csust.edu.cn

基金项目:

国家重点研发计划(2022YFB2901404); 国家自然科学基金(61972421, 62132007); 华为创新研究计划旗舰项目; 湖南省优秀青年基金(2022JJ20078); 湖南省科技创新项目(2023RC3047)


Survey on Network Congestion Control Algorithms
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [87]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    网络拥塞控制方法是决定网络传输性能的关键因素. 近几年, 网络不断普及、网络带宽不断增长、用户对网络性能的需求不断提升, 为拥塞控制算法的设计带来挑战. 为适应不同的网络环境, 近期不少新颖的拥塞控制算法被研究者们提出来, 极大地提升网络的传输性能, 改善用户体验. 综述最新拥塞控制算法设计思想, 将其分为预约调度式、直接测量式、基于机器学习式以及迭代探测式4大类, 分别介绍相应的代表性拥塞控制算法, 并进一步对各种拥塞控制思想方法的优缺点进行对比和分析, 最后展望拥塞控制的未来发展方向, 以启发该领域的研究.

    Abstract:

    Network congestion control algorithms are the key factor indetermining network transport performance. In recent years, the spreading network, the growing network bandwidth, and the increasing user requirements for network performance have brought challenges to the design of congestion control algorithms. To adapt to different network environments, many novel design ideas of congestion control algorithms have been proposed recently, which have greatly improved the performance of networks and user experience. This study reviews innovative congestion control algorithm design ideas and classifies them into four major categories: reservation scheduling, direct measurement, machine learning-based learning, and iterative detection. It introduces the corresponding representative congestion control algorithms, and further compares and analyzes the advantages and disadvantages of various congestion control ideas and methods. Finally, the study looks forward to future development direction on congestion control to inspire research in this field.

    参考文献
    [1] 中国互联网络信息中心. 第49次中国互联网络发展状况统计报告. 北京: 中国互联网络信息中心, 2022. https://www.cnnic.com.cn/IDR/ReportDownloads/202204/P020220424336135612575.pdf
    China Internet Network Information Center. The 49th statistical report on the development of Internet in China. Beijing: China Internet Network Information Center, 2022 (in Chinese). https://www.cnnic.com.cn/IDR/ReportDownloads/202204/P020220424336135612575.pdf
    [2] Li YL, Miao R, Liu HH, Zhang Y, Feng F, Tang LB, Cao Z, Zhang M, Kelly F, Alizadeh M, Yu ML. HPCC: High precision congestion control. In: Proc. of the 2019 ACM Special Interest Group on Data Communication. Beijing: ACM, 2019. 44–58.
    [3] Cerf V, Jacobson V, Weaver N, Gettys J. BufferBloat: What’s wrong with the Internet? A discussion with Vint Cerf, Van Jacobson, Nick Weaver, and Jim Gettys. Queue, 2011, 9(12): 10–20.
    [4] Gao PX, Narayan A, Kumar G, Agarwal R, Ratnasamy S. pHost: Distributed near-optimal datacenter transport over commodity network fabric. In: Proc. of the 11th ACM Conf. on Emerging Networking Experiments and Technologies. Heidelberg: ACM, 2015. 1.
    [5] Handley M, Raiciu C, Agache A, Voinescu A, Moore AW, Antichi G, Wójcik M. Re-architecting datacenter networks and stacks for low latency and high performance. In: Proc. of the 2017 Conf. of the ACM Special Interest Group on Data Communication. Los Angeles: ACM, 2017. 29–42.
    [6] Montazeri B, Li YL, Alizadeh M, Ousterhout J. Homa: A receiver-driven low-latency transport protocol using network priorities. In: Proc. of the 2018 Conf. of the ACM Special Interest Group on Data Communication. Budapest: ACM, 2018. 221–235.
    [7] Zhu YB, Eran H, Firestone D, Guo CX, Lipshteyn M, Liron Y, Padhye J, Raindel S, Yahia MH, Zhang M. Congestion control for large-scale RDMA deployments. ACM SIGCOMM Computer Communication Review, 2015, 45(4): 523–536.
    [8] Cho I, Jang K, Han DS. Credit-scheduled delay-bounded congestion control for datacenters. In: Proc. of the 2017 Conf. of the ACM Special Interest Group on Data Communication. Los Angeles: ACM, 2017. 239–252.
    [9] Mittal R, Lam VT, Dukkipati N, Blem E, Wassel H, Ghobadi M, Vahdat A, Wang YG, Wetherall D, Zats D. TIMELY: RTT-based congestion control for the datacenter. ACM SIGCOMM Computer Communication Review, 2015, 45(4): 537–550.
    [10] Kumar G, Dukkipati N, Jang K, Wassel HMG, Wu X, Montazeri B, Wang YG, Springborn K, Alfeld C, Ryan M, Wetherall D, Vahdat A. Swift: Delay is simple and effective for congestion control in the datacenter. In: Proc. of the 2020 Annual Conf. ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication. ACM, 2020. 514–528.
    [11] Chen G, Lu YW, Li BJ, Tan K, Xiong YQ, Cheng P, Zhang JS, Moscibroda T. MP-RDMA: Enabling RDMA with multi-path transport in datacenters. IEEE/ACM Trans. on Networking, 2019, 27(6): 2308–2323.
    [12] Cardwell N, Cheng YC, Gunn CS, Yeganeh SH, Jacobson V. BBR: Congestion-based congestion control. Communications of the ACM, 2017, 60(2): 58–66.
    [13] Arun V, Balakrishnan H. Copa: Practical delay-based congestion control for the Internet. In: Proc. of the 15th USENIX Symp. on Networked Systems Design and Implementation. Renton: USENIX Association, 2018. 329–342.
    [14] Winstein K, Balakrishnan H. TCP ex machina: Computer-generated congestion control. ACM SIGCOMM Computer Communication Review, 2013, 43(4): 123–134.
    [15] Dong M, Li QX, Zarchy D, Godfrey PB, Schapira M. PCC: Re-architecting congestion control for consistent high performance. In: Proc. of the 12th USENIX Symp. on Networked Systems Design and Implementation. Oakland: USENIX Association, 2015. 395–408.
    [16] Dong M, Meng T, Zarchy D, Arslan E, Gilad Y, Godfrey PB, Schapira M. PCC Vivace: Online-learning congestion control. In: Proc. of the 15th USENIX Symp. on Networked Systems Design and Implementation. Renton: USENIX Association, 2018. 343–356.
    [17] Meng T, Schiff NR, Godfrey PB, Schapira M. PCC Proteus: Scavenger transport and beyond. In: Proc. of the 2020 ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication. ACM, 2020. 615–631.
    [18] Yan FY, Ma J, Hill GD, Raghavan D, Wahby RS, Levis PA, Winstein K. Pantheon: The training ground for Internet congestion-control research. In: Proc. of the 2018 USENIX Annual Technical Conf. Boston: USENIX Association, 2018. 731–743.
    [19] Abbasloo S, Yen CY, Chao HJ. Classic meets modern: A pragmatic learning-based congestion control for the Internet. In: Proc. of the 2020 ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication. ACM, 2020. 632–647.
    [20] Carlucci G, De Cicco L, Holmer S, Mascolo S. Analysis and design of the Google congestion control for Web real-time communication (WebRTC). In: Proc. of the 7th Int’l Conf. on Multimedia Systems. Klagenfurt: ACM, 2016. 13.
    [21] Zaki Y, Pötsch T, Chen J, Subramanian L, Görg C. Adaptive congestion control for unpredictable cellular networks. ACM SIGCOMM Computer Communication Review, 2015, 45(4): 509–522.
    [22] Goyal P, Agarwal A, Netravali R, Alizadeh M, Balakrishnan H. ABC: A simple explicit congestion controller for wireless networks. In: Proc. of the 17th USENIX Symp. on Networked Systems Design and Implementation. Santa Clara: USENIX Association, 2020. 353–372.
    [23] Xie YX, Yi F, Jamieson K. PBE-CC: Congestion control via endpoint-centric, physical-layer bandwidth measurements. In: Proc. of the 2020 ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication. ACM, 2020. 451–464.
    [24] Huang S, Dong DZ, Bai W. Congestion control in high-speed lossless data center networks: A survey. Future Generation Computer Systems, 2018, 89: 360–374.
    [25] Guo ZH, Liu S, Zhang ZL. Traffic control for RDMA-enabled data center networks: A survey. IEEE Systems Journal, 2020, 14(1): 677–688.
    [26] Al-Saadi R, Armitage G, But J, Branch P. A survey of delay-based and hybrid TCP congestion control algorithms. IEEE Communications Surveys & Tutorials, 2019, 21(4): 3609–3638.
    [27] 曾高雄, 胡水海, 张骏雪, 陈凯. 数据中心网络传输协议综述. 计算机研究与发展, 2020, 57(1): 74–84.
    Zeng GX, Hu SH, Zhang JX, Chen K. Transport protocols for data center networks: A survey. Journal of Computer Research and Development, 2020, 57(1): 74–84 (in Chinese with English abstract).
    [28] 杜鑫乐, 徐恪, 李彤, 郑凯, 付松涛, 沈蒙. 数据中心网络的流量控制: 研究现状与趋势. 计算机学报, 2021, 44(7): 1287–1309.
    Du XL, Xu K, Li T, Zheng K, Fu ST, Shen M. Traffic control for data center network: State of the art and future research. Chinese Journal of Computers, 2021, 44(7): 1287–1309 (in Chinese with English abstract).
    [29] Rojas-Cessa R, Kaymak Y, Dong ZQ. Schemes for fast transmission of flows in data center networks. IEEE Communications Surveys & Tutorials, 2015, 17(3): 1391–1422.
    [30] Perry J, Ousterhout A, Balakrishnan H, Shah D, Fugal H. FastPass: A centralized “zero-queue” datacenter network. Proc. of the 2014 ACM Conf. on SIGCOMM, 2014, 44(4): 307–318.
    [31] Hu SH, Bai W, Zeng GX, Wang ZL, Qiao BC, Chen K, Tan K, Wang Y. Aeolus: A building block for proactive transport in datacenters. In: Proc. of the 2020 Annual Conf. of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication. ACM, 2020. 422–434.
    [32] Yan SY, Wang XL, Zheng XL, Xia YB, Liu DR, Deng WS. ACC: Automatic ECN tuning for high-speed datacenter networks. In: Proc. of the 2021 ACM SIGCOMM Conf. ACM, 2021. 384–397.
    [33] Meng ZL, Guo YN, Sun C, Wang B, Sherry J, Liu HH, Xu MW. Achieving consistent low latency for wireless real-time communications with the shortest control loop. In: Proc. of the 2022 ACM SIGCOMM Conf. Amsterdam: ACM, 2022. 193–206.
    [34] Goyal P, Narayan A, Cangialosi F, Narayana S, Alizadeh M, Balakrishnan H. Elasticity detection: A building block for Internet congestion control. In: Proc. of the 2022 AACM SIGCOMM Conf. Amsterdam: ACM, 2022. 158–176.
    [35] Addanki V, Michel O, Schmid S. PowerTCP: Pushing the performance limits of datacenter networks. In: Proc. of the 19th USENIX Symp. on Networked Systems Design and Implementation. Renton: USENIX Association, 2022. 51–70.
    [36] Yen CY, Abbasloo S, Chao HJ. Computers can learn from the heuristic designs and master Internet congestion control. In: Proc. of the 2023 ACM SIGCOMM Conf. New York: ACM, 2023. 255–274.
    [37] Agarwal S, Krishnamurthy A, Agarwal R. Host congestion control. In: Proc. of the 2023 ACM SIGCOMM Conf. New York: ACM, 2023. 275–287.
    [38] Arslan S, Li YL, Kumar G, Dukkipati N. Bolt: Sub-RTT congestion control for ultra-low latency. In: Proc. of the 20th USENIX Symp. on Networked Systems Design and Implementation. Boston: USENIX Association, 2023. 219–236.
    [39] Wang WT, Moshref M, Li YL, Kumar G, Ng TSE, Cardwell N, Dukkipati N. Poseidon: Efficient, robust, and practical datacenter CC via deployable INT. In: Proc. of the 20th USENIX Symp. on Networked Systems Design and Implementation. Boston: USENIX Association, 2023. 255–274.
    [40] Alizadeh M, Greenberg A, Maltz DA, Padhye J, Patel P, Prabhakar B, Sengupta S, Sridharan M. Data center TCP (DCTCP). ACM SIGCOMM Computer Communication Review, 2010, 40(4): 63–74.
    [41] Zhang H, Zhang JX, Bai W, Chen K, Chowdhury M. Resilient datacenter load balancing in the wild. In: Proc. of the 2017 ACM Special Interest Group on Data Communication. Los Angeles: ACM, 2017. 253–266.
    [42] Jacobson V. Congestion avoidance and control. ACM SIGCOMM Computer Communication Review, 1988, 18(4): 314–329.
    [43] Allman M, Paxson V, Stevens W. TCP congestion control. RFC2581, 1999.
    [44] Floyd S, Henderson T. The NewReno modification to TCP’s fast recovery algorithm. RFC2582, 1999.
    [45] Mathis M, Mahdavi J, Floyd S, Romanow A. TCP selective acknowledgement options. RFC2018, 1996.
    [46] Brakmo LS, Peterson LL. TCP Vegas: End to end congestion avoidance on a global Internet. IEEE Journal on Selected Areas in Communications, 1995, 13(8): 1465–1480.
    [47] Floyd S. HighSpeed TCP for large congestion windows. RFC3649, 2003.
    [48] Kelly T. Scalable TCP: Improving performance in highspeed wide area networks. ACM SIGCOMM Computer Communication Review, 2003, 33(2): 83–91.
    [49] Jin C, Wei D, Low SH, Bunn J, Choe HD, Doyle JC, Newman H, Ravot S, Singh S, Paganini F, Buhrmaster G, Cottrell L, Martin O, Feng WC. FAST TCP: From theory to experiments. IEEE Network, 2005, 19(1): 4–11.
    [50] Xu LS, Harfoush K, Rhee I. Binary increase congestion control (BIC) for fast long-distance networks. In: Proc. of 2004 Int’l Conf. on Computer Communications. Hong Kong: IEEE, 2004. 2514–2524.
    [51] Ha S, Rhee I, Xu LS. CUBIC: A new TCP-friendly high-speed TCP variant. ACM SIGOPS Operating Systems Review, 2008, 42(5): 64–74.
    [52] Braden B, Clark D, Crowcroft J, Davie B, Deering S, Estrin D, Floyd S, Jacobson V, Minshall G, Partridge C, Peterson L, Ramakrishnan K, Shenker S, Wroclawski J, Zhang L. Recommendations on queue management and congestion avoidance in the Internet. RFC2309, 1998.
    [53] Floyd S, Jacobson V. Random early detection gateways for congestion avoidance. IEEE/ACM Trans. on Networking, 1993, 1(4): 397–413.
    [54] Ramakrishnan K, Floyd S, Black D. The addition of explicit congestion notification (ECN) to IP. RFC3168, 2001.
    [55] 任丰原, 王福豹, 任勇, 山秀明. 主动队列管理中的PID控制器. 电子与信息学报, 2003, 25(1): 94–99.
    Ren FY, Wang FB, Ren Y, Shan XM. PID controller for active queue management. Journal of Electronics & Information Technology, 2003, 25(1): 94–99 (in Chinese with English abstract).
    [56] 续欣, 汤凯, 马刈非. 无线误码信道上的拥塞控制策略. 通信学报, 2004, 25(12): 8–13.
    Xu X, Tang K, Ma YF. Congestion control scheme on wireless loss-prone links. Journal of China Institute of Communications, 2004, 25(12): 8–13 (in Chinese with English abstract).
    [57] 杨吉文, 顾诞英, 张卫东. 主动队列管理中PID控制器的解析设计方法. 软件学报, 2006, 17(9): 1989–1995. http://www.jos.org.cn/1000-9825/17/1989.htm
    Yang JW, Gu DY, Zhang WD. An analytical design method of PID controller based on AQM/ARQ. Ruan Jian Xue Bao/Journal of Software, 2006, 17(9): 1989–1995 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/17/1989.htm
    [58] 吴清亮, 陶军, 姚婕. 一种基于预测PI控制器的自相似网络主动队列管理算法. 电子学报, 2006, 34(5): 938–943.
    Wu QL, Tao J, Yao J. An active queue management algorithm based on predictable PI controller in self-similar network. Acta Electronica Sinica, 2006, 34(5): 938–943 (in Chinese with English abstract).
    [59] Hwang J, Yoo J, Lee SH, Jin HW . Scalable congestion control protocol based on SDN in data center networks. In: Proc. of the 2015 IEEE Global Communications Conf. (GLOBECOM). San Diego: IEEE, 2015. 1–6.
    [60] Jouet S, Perkins C, Pezaros D. OTCP: SDN-managed congestion control for data center networks. In: Proc. of the 2016 IEEE/IFIP Network Operations and Management Symp. Istanbul: IEEE, 2016. 171–179.
    [61] Raiciu C, Barre S, Pluntke C, Greenhalgh A, Wischik D, Handley M. Improving datacenter performance and robustness with multipath TCP. ACM SIGCOMM Computer Communication Review, 2011, 41(4): 266–277.
    [62] Nakayama Y. Rate-based path selection for shortest path bridging in access networks. In: Proc. of the 2014 IEEE Int’l Conf. on Communications. Sydney: IEEE, 2014. 1266–1271.
    [63] Allan D, Farkas J, Mansfield S. Intelligent load balancing for shortest path bridging. IEEE Communications Magazine, 2012, 50(7): 163–167.
    [64] Carofiglio G, Gallo M, Muscariello L. ICP: Design and evaluation of an Interest control protocol for content-centric networking. In: Proc. of the 2012 IEEE INFOCOM Workshops. Orlando: IEEE, 2012. 304–309.
    [65] Saino L, Cocora C, Pavlou G. CCTCP: A scalable receiver-driven congestion control protocol for content centric networking. In: Proc.of the 2013 IEEE Int’l Conf. on Communications (ICC). Budapest: IEEE, 2013. 3775–3780.
    [66] Ren YM, Li J, Shi SS, Li LL, Chang XQ. An interest control protocol for named data networking based on explicit feedback. In: Proc. of the 2015 ACM/IEEE Symp. on Architectures for Networking and Communications Systems. Oakland: IEEE, 2015. 199–200.
    [67] Rozhnova N, Fdida S. An effective hop-by-hop Interest shaping mechanism for CCN communications. In: Proc. of the 2012 IEEE INFOCOM Workshops. Orlando: IEEE, 2012. 322–327.
    [68] Carofiglio G, Gallo M, Muscariello L. Joint hop-by-hop and receiver-driven interest control protocol for content-centric networks. ACM SIGCOMM Computer Communication Review, 2012, 42(4): 491–496.
    [69] Katabi D, Handley M, Rohrs C. Congestion control for high bandwidth-delay product networks. ACM SIGCOMM Computer Communication Review, 2002, 32(4): 89–102.
    [70] Dukkipati N. Rate Control Protocol (RCP): Congestion control to make flows complete quickly [Ph.D. Thesis]. Stanford: Stanford University, 2008.
    [71] Zhang J, Ren FY, Shu R, Cheng P. TFC: Token flow control in data center networks. In: Proc. of the 11th European Conf. on Computer Systems. London: ACM, 2016. 23.
    [72] Jay N, Rotman N, Godfrey B, Schapira M, Tamar A. A deep reinforcement learning perspective on Internet congestion control. In: Proc. of the 36th Int’l Conf. on Machine Learning. Long Beach: PMLR, 2019. 3050–3059.
    [73] Emara S, Li BC, Chen YJ. Eagle: Refining congestion control by learning from the experts. In: Proc. of the 29th IEEE Conf. on Computer Communications. Toronto: IEEE, 2020. 676–685.
    [74] Du ZX, Zheng JQ, Yu HB, Kong LT, Chen GH. A unified congestion control framework for diverse application preferences and network conditions. In: Proc. of the 17th Int’l Conf. on Emerging Networking Experiments and Technologies. ACM, 2021. 282–296.
    [75] Tessler C, Shpigelman Y, Dalal G, Mandelbaum A, Kazakov DH, Fuhrer B, Chechik G, Mannor S. Reinforcement learning for datacenter congestion control. ACM SIGMETRICS Performance Evaluation Review, 2021, 49(2): 43–46.
    [76] Ketabi S, Chen HK, Dong HW, Ganjali Y. A deep reinforcement learning framework for optimizing congestion control in data centers. In: Proc. of the 36th IEEE/IFIP Network Operations and Management Symp. Miami: IEEE, 2023. 1–7.
    [77] Tan K, Song J, Zhang Q, Sridharan M. A compound TCP approach for high-speed and long distance networks. In: Proc. of the 25th IEEE Int’l Conf. on Computer Communications. Barcelona: IEEE, 2006. 1–12.
    [78] Hock M, Bless R, Zitterbart M. Experimental evaluation of BBR congestion control. In: Proc. of the 25th Int’l Conf. on Network Protocols. Toronto: IEEE, 2017. 1–10.
    [79] Pan R, Prabhakar B, Laxmikantha A. QCN: Quantized congestion notification an overview. 2007. https://www.ieee802.org/1/files/public/docs2007/au_prabhakar_qcn_overview_geneva.pdf
    [80] Teymoori P, Welzl M. LGCC: Food chain multi-hop congestion control. Technical Report, 949, Oslo: University of Oslo, 2020. 1–16.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

蒋万春,李昊阳,陈晗瑜,王洁,王建新,阮昌.网络拥塞控制方法综述.软件学报,2024,35(8):3952-3979

复制
分享
文章指标
  • 点击次数:1039
  • 下载次数: 5599
  • HTML阅读次数: 1040
  • 引用次数: 0
历史
  • 收稿日期:2023-02-06
  • 最后修改日期:2023-04-11
  • 在线发布日期: 2024-02-05
  • 出版日期: 2024-08-06
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会CCF数字图书馆Int'l J of Softw Info计算机系统应用
您是第19856710位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京市海淀区中关村南四街4号,邮政编码：100190
电话：010-62562563 传真：010-62562533 Email：jos@iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号