| 31 | 0 | 17 |
| 下载次数 | 被引频次 | 阅读次数 |
随着生成式人工智能（AIGC）大模型计算应发展，当前广域网基于DiffServ模型的主动队列管理（AQM）技术，难以满足业务在高吞吐，低时延以及低抖动下的不同流量、多样化的业务场景需求。研究了广域网络流量的场景分类技术，并结合AQM技术，提出了一种广域服务质量（QoS）参数自适应优化方法，实现跨数据中心的无损转发，优化吞吐量和时延性能。
Abstract：With the development of generative artificial intelligence (AIGC) large model computing， the active queue management (AQM) technology based on the DiffServ model in current wide area networks can hardly meet the requirements of services for different traffic and diverse business scenarios under high throughput， low latency， and low jitter. The traffic scenario classification technology for wide area networks is studied， and combined with AQM technology， an adaptive optimization method for wide area quality of service (QoS) parameters is proposed to achieve lossless forwarding across data centers and optimize throughput and latency performance.
[1] Jain R. The catch-up game quest for the impact [EB/OL]. (2017-08-22)[2026-08-02]. https://conferences.sigcomm.org/sigcomm/2017/files/program/keynote-1.pdf
[2] 杜鑫乐， 徐恪， 李彤. 数据中心网络的流量控制：研究现状与趋势 [EB/OL]. [2026-08-02]. https://lib.cqvip.com/Qikan/Article/Detail?id=7105063887
[3] King D， Chown T， Rapier C， et al. Current state of the art for high performance wide area networks [EB/OL].(2025-03-01)[2026-08-04]. https://www.ietf.org/archive/id/draft-kcrh-state-of-art-hp-wan-00.txt
[4] FLOYD S. A review of FRED: flow random early detection [J]. ACM SIGCOMM Computer Communication Review， 2000， 30(4): 62-73.
[5] RFC 2309 Recommendations on queue management and congestion avoidance in the internet [S]
[6] Wurtzler M. Analysis and simulation of weighted random early detection (WRED) queues [EB/OL]. [2026-08-05]. https://www.ittc.ku.edu/research/thesis/documents/mark＿wurtzler＿thesis.pdf
[7] Hassan S， Rufai A. Modified dropping-random early detection (MD-RED): a modified algorithm for controlling network congestion [J]. International journal of information technology， 2023， 15(3): 1499-1508. DOI: 10.1007/s41870-023-01201-1
[8] 任金霞， 蒋梦倩， 温春晖. 基于S型函数动态自适应改进的RED算法 [J]. 高技术通讯(中文) ， 2019， 29(5): 449～454. DOI: 10.3772/j.issn.1002-0470.2019.05.005
[9] Patel S. Sensitivity analysis of queue-based AQM over network parameters [J]. IET networks， 2019， 8(4): 280-288. DOI: 10.1049/iet-net.2018.5160
[10] Patel S. Nonlinear performance evaluation model for throughput of AQM scheme using full factorial design approach [J]. International journal of communication systems， 2020， 33(8): e4357. DOI: 10.1002/dac.4357
[11] Floyd S， Gummadi R， Shenker， S. Adaptive RED: an algorithm for increasing the robustness of RED's active queue management [EB/OL]. (2001-08-01)[2026-08-03]. https://www.icir.org/floyd/papers/adaptiveRed.pdf
[12] Yan F Y ， Ma J， Hil G D， et al. Pantheon: the training ground for Internet congestion-control research [EB/OL]. [2026-08-03]. https://pantheon.stanford.edu/static/pantheon/documents/pantheon-paper.pdf
[13] Le Y， Lee J， Blendin J， et al. SFC: Near-source congestion signaling and flow control [PP/OL]. arXiv[2026-08-02]. https://arxiv.org/pdf/2305.00538
[14] Huang H L， Du X L， Li T， et al. Re-architecting buffer management in lossless Ethernet [J]. ACM transactions on networking， 2024， 32(6): 4749-4764. DOI: 10.1109/tnet.2024.3430989
[15] Taheri P， Menikkumbura D， Vanini E， et al. RoCC: robust congestion control for RDMA [C]//Proceedings of the 16th International Conference on Emerging Networking EXperiments and Technologies. ACM， 2020: 17-30. DOI: 10.1145/3386367.3431316
[16] Nichols K， JacobsonV. Controlling queue delay [J]. ACM Queue， 2012， 10(5): 68-81.DOI: 10.1145/2209249.2209264
[17] Cormode G， Muthukrishnan S. An improved data stream summary: the count-Min sketch and its applications [J]. Journal of algorithms， 2005， 55(1): 58-75. DOI: 10.1016/j.jalgor.2003.12.001
[18] Estan C， Varghese G. New directions in traffic measurement and accounting: Focusing on the elephants， ignoring the mice [J]. ACM transactions on computer systems， 2003， 21(3): 270-313. DOI: 10.1145/859716.859719
[19] Tang L， Huang Q， Lee P P C. MV-sketch: a fast and compact invertible sketch for heavy flow detection in network data streams [C]//Proceedings of IEEE INFOCOM 2019 - IEEE Conference on Computer Communications. IEEE， 2019: 2026-2034. DOI: 10.1109/infocom.2019.8737499
[20] Yang T， Zhang H W， Li J Y， et al. HeavyKeeper: an accurate algorithm for finding top-k elephant flows [J]. ACM transactions on networking， 2019， 27(5): 1845-1858. DOI: 10.1109/tnet.2019.2933868
[21] Yang T， Jiang J， Liu P， et al. Elastic sketch: adaptive and fast network-wide measurements [C]//Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication. ACM， 2018: 561-575. DOI: 10.1145/3230543.3230544
基本信息:
中图分类号:TP393.2
引用信息:
[1]杨锋,尹远阳,王江龙,等.基于广域无损网络的QoS参数自适应优化技术应用研究[J].中兴通讯技术().
2026-10-26
2026-10-26
2026-10-26