由於網際網路的普及與現代人生活習慣的改變，因而使當前網路頻寬使用量大幅增長，進而導致傳統網路傳輸協定已逐漸無法負荷，而為解決此問題，Google開發一名為QUIC(快速UDP網際網路連接，Quick UDP Internet Connection)之網路傳輸控制協定，該協定以UDP做為基底來逐漸取代當前通用之TCP協定，以此來縮短客戶端與服務端連線之間的傳輸時間。但由於單一路徑下QUIC傳輸，依然受到單一鏈路頻寬之影響，因而多路徑QUIC的相關研究亦漸漸受到重視，但現階段所發展之多路徑QUIC的研究只透過最短時間或定時傳輸，進而導致鏈路壅塞或傳輸時間的延遲等情況發生。綜上所述，本論文基於多路徑QUIC，提出一種結合延遲與封包遺失率之多路徑演算法，來達到最小化封包的傳輸時間之目標。而於最終的實驗結果顯示，本論文所提出之演算法於傳輸延遲與封包遺失率等各項指標皆優於單路徑QUIC、LRF (Lowest-RTT-First，最低RTT 優先)和PQUIC (Pluginized QUIC)排程方法。

With the popularity of the Internet and the changes in modern people's living habits, the current network bandwidth has increased significantly, which caused the traditional network transmission protocols has been overloaded gradually. In order to solve this problem, Google developed a network transmission control protocol called QUIC (Quick UDP Internet Connect), which uses UDP as the substitute for TCP protocol which is in common use currently, so as to shorten the transmission time of connection between client and server. However, QUIC transmission based on single path is still affected by the bandwidth of a single link, so the related research on multi-path QUIC has received more and more attention gradually, but the research on multi-path QUIC developed at the present stage only transmits via shortest time or timing, which caused the congestion of link or the delay in transmission time. In summary, this paper proposes a multi-path algorithm which combines with delay and packet loss rate to achieve the goal of minimizing packet transmission time based on muiti-path QUIC. The final experimental results show that the algorthm proposed in this paper is superior to scheduling methods such as single-path QUIC, LRF (Lowest-RTT-First) and PQUIC (Pluginized QUIC) in various indicators such as transmission delay and packet loss rate.

[1] CISCO, “Cisco annual internet report (2018–2023) white paper,” in Cisco Annual
Internet Report, 2020.
[2] RFC9114, “https://www.rfc-editor.org/rfc/rfc9114.html.”
[3] C. Raiciu, C. Paasch, S. Barre, A. Ford, M. Honda, F. Duchene, O. Bonaventure,
and M. Handley, “How hard can it be? designing and implementing a deployable
multipath TCP,” in 9th USENIX Symposium on Networked Systems Design and
Implementation (NSDI 12). San Jose, CA: USENIX Association, Apr. 2012, pp.
399–412.
[4] P. Megyesi, Z. Krämer, and S. Molnár, “How quick is quic?” in 2016 IEEE Interna-
tional Conference on Communications (ICC), 2016, pp. 1–6.
[5] R. Fielding, J. Gettys, J. Mogul, H. Frystyk, L. Masinter, P. Leach, and T. Berners-
Lee, “Hypertext transfer protocol–http/1.1,” 1999.
[6] T. Berners-Lee, R. Fielding, and H. Frystyk, “Hypertext transfer protocol–http/1.0,”
1996.
[7] H. F. Nielsen, J. Gettys, A. Baird-Smith, E. Prud’hommeaux, H. W. Lie, and C. Lil-
ley, “Network performance effects of http/1.1, css1, and png,” in Proceedings of
the ACM SIGCOMM’97 conference on Applications, technologies, architectures, and
protocols for computer communication, 1997, pp. 155–166.
8] X. S. Wang, A. Balasubramanian, A. Krishnamurthy, and D. Wetherall, “How speedy
is {SPDY}?” in 11th usenix symposium on networked systems design and implemen-
tation (nsdi 14), 2014, pp. 387–399.
[9] D. Stenberg, “Http2 explained,” pp. 120–128, 2014.
[10] R. Marx, J. Herbots, W. Lamotte, and P. Quax, “Same standards, different decisions:
A study of quic and http/3 implementation diversity,” in Proceedings of the Workshop
on the Evolution, Performance, and Interoperability of QUIC, 2020, pp. 14–20.
[11] GEEKFLARE, “https://geekflare.com/http3-test/.”
[12] CanIuse, “https://caniuse.com/http3.”
[13] RFC6824, “https://datatracker.ietf.org/doc/html/rfc6824.”
[14] N. Kuhn, E. Lochin, A. Mifdaoui, G. Sarwar, O. Mehani, and R. Boreli, “Daps:
Intelligent delay-aware packet scheduling for multipath transport,” in 2014 IEEE
International Conference on Communications (ICC), 2014, pp. 1222–1227.
[15] S. Ferlin, ￿. Alay, O. Mehani, and R. Boreli, “Blest: Blocking estimation-based mptcp
scheduler for heterogeneous networks,” in 2016 IFIP Networking Conference (IFIP
Networking) and Workshops, 2016, pp. 431–439.
[16] D. T. Yeon-sup Lim, Erich M Nahum and R. J. Gibbens, “Ecf:an mptcp path sched-
uler to manage heterogeneous paths,” in 2017 SIGMETRICS, 2017, pp. 431–439.
[17] G. Carlucci, L. De Cicco, and S. Mascolo, “Http over udp: an experimental inves-
tigation of quic,” in Proceedings of the 30th Annual ACM Symposium on Applied
Computing, 2015, pp. 609–614.
[18] S. Ha, I. Rhee, and L. Xu, “Cubic: a new tcp-friendly high-speed tcp variant,” ACM
SIGOPS operating systems review, vol. 42, no. 5, pp. 64–74, 2008.
[19] N. Cardwell, Y. Cheng, C. S. Gunn, S. H. Yeganeh, and V. Jacobson, “Bbr:
congestion-based congestion control,” Communications of the ACM, vol. 60, no. 2,
pp. 58–66, 2017.
[20] K. Wolsing, J. Rüth, K. Wehrle, and O. Hohlfeld, “A performance perspective on
web optimized protocol stacks: Tcp+ tls+ http/2 vs. quic,” in Proceedings of the
Applied Networking Research Workshop, 2019, pp. 1–7.
[21] Q. De Coninck and O. Bonaventure, “Multipath quic: Design and evaluation,” in
Proceedings of the 13th international conference on emerging networking experiments
and technologies, 2017, pp. 160–166.
[22] RFC9000, “https://datatracker.ietf.org/doc/html/rfc9000.”
[23] T. Viernickel, A. Froemmgen, A. Rizk, B. Koldehofe, and R. Steinmetz, “Multi-
path quic: A deployable multipath transport protocol,” in 2018 IEEE International
Conference on Communications (ICC), 2018, pp. 1–7.
[24] Y. G. Jing Wang and C. Xu, “A stream-aware multipath quic scheduler for hetero-
geneous paths,” in 2019 ACM 3rd Asia-Pacific Workshop on Networking(APNet),
2019, pp. 43–49.
[25] A. Rabitsch, P. Hurtig, and A. Brunstrom, “A stream-aware multipath quic sched-
uler for heterogeneous paths,” in Proceedings of the Workshop on the Evolution,
Performance, and Interoperability of QUIC, 2018, pp. 29–35.
[26] X. Shi, L. Wang, F. Zhang, B. Zhou, and Z. Liu, “Pstream: Priority-based stream
scheduling for heterogeneous paths in multipath-quic,” in 2020 29th International
Conference on Computer Communications and Networks (ICCCN), 2020, pp. 1–8.
[27] X. Shi, F. Zhang, and Z. Liu, “Prioritybucket: A multipath-quic scheduler on accel-
erating first rendering time in page loading,” in Proceedings of the Eleventh ACM
International Conference on Future Energy Systems, 2020, pp. 572–577.
[28] H. Wu, ￿. Alay, A. Brunstrom, S. Ferlin, and G. Caso, “Peekaboo: Learning-based
multipath scheduling for dynamic heterogeneous environments,” IEEE Journal on
Selected Areas in Communications, vol. 38, no. 10, pp. 2295–2310, 2020.
[29] V. A. Vu and B. Walker, “On the latency of multipath-quic in real-time applica-
tions,” in 2020 16th International Conference on Wireless and Mobile Computing,
Networking and Communications (WiMob), 2020, pp. 1–7.
[30] Q. De Coninck, F. Michel, M. Piraux, F. Rochet, T. Given-Wilson, A. Legay,
O. Pereira, and O. Bonaventure, “Pluginizing quic,” in Proceedings of the ACM
Special Interest Group on Data Communication, 2019, pp. 59–74.
[31] MPQUICdraft, “https://datatracker.ietf.org/doc/html/draft-ietf-quic-multipath.”
[32] Z. Wang and J. Crowcroft, “Quality-of-service routing for supporting multimedia
applications,” IEEE Journal on Selected Areas in Communications, vol. 14, no. 7,
pp. 1228–1234, Sept. 1996.
[33] C.-L. Hu, C.-Y. Hsu, and W.-M. Sung, “Fitpath: Qos-based path selection with
fittingness measure in integrated edge computing and software-defined networks,”
IEEE Access, vol. 10, pp. 45 576–45 593, 2022.
[34] R. M. Karp, “Reducibility among combinatorial problems„” in Complexity of Com-
puter Computations. Boston, MA, USA: Plenum Press, 1972, pp. 85–103.
[35] J. Y. Yen, “Finding the k shortest loopless paths in a network,” management Science,
vol. 17, no. 11, pp. 712–716, 1971.
[36] S. Knight, H. X. Nguyen, N. Falkner, R. Bowden, and M. Roughan, “The internet
topology zoo,” IEEE Journal on Selected Areas in Communications, vol. 29, no. 9,
pp. 1765–1775, 2011.