CC-OLIA: A dynamic congestion control algorithm for multipath QUIC in mobile networks^✩

Abstract

High-quality services in today’s mobile networks require stable delivery of bandwidth-intensive network content. Multipath QUIC (MPQUIC), as a multipath protocol that extends QUIC, can utilize multiple paths to support stable and efficient transmission. The standard coupled congestion control algorithm in MPQUIC synchronizes these paths to manage congestion, meeting fairness requirements and improving transmission efficiency. However, current algorithms’ Congestion Window (CWND) reduction approach significantly decreases CWND upon packet loss, which lowers effective throughput, regardless of the congestion origin. Furthermore, the uncoupled Slow-Start (SS) in MPQUIC leads to independent exponential CWND growth on each path, potentially causing buffer overflow. To address these issues, we propose the CC-OLIA, which incorporates Packet Loss Classifcation (PLC) and Coupled Slow-Start (CSS). The PLC distinguishes between congestion-induced and random packet losses, adjusting CWND reduction accordingly to maintain throughput. Concurrently, the CSS module coordinates CWND growth during the SS, preventing abrupt increases. Implementation on MININET shows that CC-OLIA not only maintains fair performance but also enhances transmission efficiency across diverse network conditions.

Keywords

MPQUIC / Mobile network / Congestion control / Packet loss / Slow start

References

[1] M. Lahby, A. Essouiri, A. Sekkaki, A novel modeling approach for vertical handover based on dynamic k-partite graph in heterogeneous networks, Digit.commun. Netw. 5 (4) (2019) 297-307.

[2] P. Austria, C.H. Park, J.-Y. Jo, Y. Kim, R. Sundaresan, K. Pham, BBR congestion control analysis with multipath TCP (MPTCP) and asymmetrical latency subflow,in:2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), IEEE, 2022, pp. 1065-1069.

[3] J. Iyengar, M. Thomson, QUIC: a UDP-based multiplexed and secure transport, https://www.rfc-editor.org/info/rfc9000, 2021. (Accessed 4 February 2024).

[4] Q. De Coninck, O. Bonaventure, Multipath QUIC: design and evaluation,in:Pro-ceedings of the 13th International Conference on Emerging Networking EXperi-ments and Technologies, CoNEXT ’17, Association for Computing Machinery, 2017, pp. 160-166.

[5] C. Raiciu, D. Wischik, M. Handley, Practical congestion control for multipath trans-port protocols, Tech. Rep., Univ. College London, London, U.K., 2009.

[6] W.R. Stevens, TCP slow start, congestion avoidance, fast retransmit, and fast re-covery algorithms, https://www.rfc-editor.org/info/rfc2001, 1997. (Accessed 17 November 2023).

[7] E. Blanton, D.V. Paxson, M. Allman, TCP congestion control, https://www.rfc-editor.org/info/rfc5681, 2009. (Accessed 20 January 2024).

[8] S. Ha, I. Rhee, L. Xu, CUBIC: a new TCP-friendly high-speed TCP variant, SIGOPS Oper. Syst. Rev. 42 (5) (2008) 64-74.

[9] Y. Han, M. Zuo, H. Yuan, Y. Zhong, Z. Yuan, T. Bi, B.M. Elhalawany, A QoS-based fairness-aware BBR congestion control algorithm using QUIC, Wirel.commun. Mob.comput. 2022 (1) (2022) 1-16.

[10] C. Raiciu, M.J. Handley, D. Wischik, Coupled congestion control for multipath transport protocols, https://www.rfc-editor.org/info/rfc6356, 2011. (Accessed 20 November 2023).

[11] R. Khalili, N. Gast, M. Popovic, J.-Y. Le Boudec, MPTCP is not Pareto-optimal: per-formance issues and a possible solution, IEEE/ACM Trans. Netw. 21 (5) (2013) 1651-1665.

[12] W. Li, H. Zhang, S. Gao, C. Xue, X. Wang, S. Lu, SmartCC: a reinforcement learning approach for multipath TCP congestion control in heterogeneous networks, IEEE J. Sel. Areas Commun. 37 (11) (2019) 2621-2633.

[13] B. He, J. Wang, Q. Qi, H. Sun, J. Liao, C. Du, X. Yang, Z. Han, DeepCC: multi-agent deep reinforcement learning congestion control for multi-path TCP based on self-attention, IEEE Trans. Netw. Serv. Manag. 18 (4) (2021) 4770-4788.

[14] J. Iyengar, I. Swett, QUIC loss detection and congestion control, https://www.rfc-editor.org/info/rfc9002, 2021. (Accessed 3 January 2024).

[15] R. Barik, M. Welzl, S. Ferlin, O. Alay, LISA: a linked slow-start algorithm for MPTCP, in: 2016 IEEE International Conference on Communications (ICC), IEEE, 2016, pp. 1-7.

[16] W. Bai, S. Hu, K. Chen, K. Tan, Y. Xiong, One more config is enough: saving (DC)TCP for high-speed extremely shallow-buffered datacenters, IEEE/ACM Trans. Netw. 29 (2) (2021) 489-502.

[17] P. Geurts, I. El Khayat, G. Leduc, A machine learning approach to improve congestion control over wireless computer networks, in: Fourth IEEE International Conference on Data Mining (ICDM’04), IEEE, 2004, pp. 383-386.

[18] S. Patel, Y. Shukla, N. Kumar, T. Sharma, K. Singh, A comparative performance analysis of tcp congestion control algorithms: newreno, westwood, veno, bic, and cubic, in: 2020 6th International Conference on Signal Processing and Communica-tion (ICSC), IEEE, 2020, pp. 23-28.

[19] Y. Cai, H. Xiong, S. Yu, M. Chen, X. Zhou, D-OLIA: the packet loss differentiation based opportunistic linked-increases algorithm for MPTCP in wireless heterogeneous network, in: 2021 31st International Telecommunication Networks and Applications Conference (ITNAC), IEEE, 2021, pp. 78-85.

[20] Y. Wang, K. Xue, H. Yue, J. Han, Q. Xu, P. Hong,Coupled slow-start: improving the efficiency and friendliness of mptcp’s slow-start, in: 2017-2017 IEEE Global Com-munications Conference (GLOBECOM), IEEE, 2017, pp. 1-6.

[21] M. Kosek, T. Shreedhar, V. Bajpai, Beyond QUIC v1: a first look at recent transport layer IETF standardization efforts, IEEE Commun. Mag. 59 (4) (2021) 24-29.

[22] T. Viernickel, A. Froemmgen, A. Rizk, B. Koldehofe, R. Steinmetz, Multipath QUIC: a deployable multipath transport protocol, in: 2018 IEEE International Conference on Communications (ICC), IEEE, 2018, pp. 1-7.

[23] Y. Xing, K. Xue, Y. Zhang, J. Han, J. Li, D.S. Wei, R. Li, Q. Sun, J. Lu, A stream-aware MPQUIC scheduler for HTTP traffic in mobile networks, IEEE Trans. Wirel.commun. 22 (4) (2022) 2775-2788.

[24] Q. De Coninck, The packet number space debate in multipath QUIC, SIGCOMM Com-put. Commun. Rev. 52 (3) (2022) 2-9.

[25] J. Wang, Y. Gao, C. Xu,A multipath QUIC scheduler for mobile HTTP/2, in:Pro-ceedings of the 3rd Asia-Pacific Workshop on Networking, 2019, pp. 43-49.

[26] Y. Liu, Y. Ma, C. Huitema, Q. An, Z. Li, Multipath extension for QUIC, https://datatracker.ietf.org/doc/draft-ietf-quic-multipath/05/, 2023. (Accessed 10 Novem-ber 2023).

[27] C. Xu, J. Zhao, G.-M. Muntean, Congestion control design for multipath transport protocols: a survey, IEEE Commun. Surv. Tutor. 18 (4) (2016) 2948-2969.

[28] J. Yang, J. Han, K. Xue, Y. Wang, J. Li, Y. Xing, H. Yue, D.S.L. Wei, TCCC: a through-put consistency congestion control algorithm for MPTCP in mixed transmission of long and short flows, IEEE Trans. Netw. Serv. Manag. 20 (3) (2023) 2652-2667.

[29] M. Kozuka, Y. Okabe, A policy-based path selection mechanism in QUIC multipath extension, in: 2023 IEEE 47th Annual Computers, Software, and Applications Con-ference (COMPSAC), 2023, pp. 1255-1259.

[30] N. Handigol, B. Heller, V. Jeyakumar, B. Lantz, N. McKeown,Reproducible network experiments using container-based emulation, in:Proceedings of the 8th Interna-tional Conference on Emerging Networking Experiments and Technologies, 2012, pp. 253-264.

[31] S. Jamali, A. Badirzadeh, M.S. Siapoush, On the use of the genetic programming for balanced load distribution in software-defined networks, Digit.commun. Netw. 5 (4) (2019) 288-296.

[32] Y. Liu, Z. Yang, Y. Peng, T. Bi, T. Jiang, Bandwidth-delay-product-based ACK opti-mization strategy for QUIC in Wi-Fi networks, IEEE Int. Things J. 10 (20) (2023) 17635-17646.

[33] P.K. Donta, S.N. Srirama, T. Amgoth, C.S.R. Annavarapu, Survey on recent advances in IoT application layer protocols and machine learning scope for research directions, Digit.commun. Netw. 8 (5) (2022) 727-744.

[34] W. Wei, K. Xue, J. Han, D.S. Wei, P. Hong, Shared bottleneck-based congestion con-trol and packet scheduling for multipath TCP, IEEE/ACM Trans. Netw. 28 (2) (2020) 653-666.

[35] P. Garrido, I. Sanchez, S. Ferlin, R. Aguero, O. Alay, rQUIC: integrating FEC with QUIC for robust wireless communications, in: 2019 IEEE Global Communications Conference (GLOBECOM), IEEE, 2019, pp. 1-7.

[36] J. Yu, S. Pan, R. Gao, Y. Li, Low-delay transmission for non-terrestrial networks based on FEC and reinforcement learning, in: 2023 IEEE/CIC International Conference on Communications in China (ICCC), IEEE, 2023, pp. 1-6.