arxiv: 2605.02510 · v1 · submitted 2026-05-04 · 💻 cs.NI

Recognition: 2 theorem links

· Lean Theorem

Choir: Tackling RTBC Performance Impossible Triangle with 5G Collaboration

Baosen Zhao, Gaogang Xie, Jiaxing Zhang, Qinghua Wu, Tingting Yuan, Wanghong Yang, Wenji Du, Xiaoming Fu, Xu Zhou, Yongmao Ren

Authors on Pith no claims yet

Pith reviewed 2026-05-08 17:51 UTC · model grok-4.3

classification 💻 cs.NI

keywords real-time broadband communication5Grate controlbase stationvideo streamingtail delayfairnesscollaboration

0 comments

The pith

Choir deploys on 5G base stations to guide sender rate control by integrating radio characteristics and video patterns, meeting high bitrate, low delay, and fairness requirements simultaneously.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tries to show that real-time broadband communication over 5G, such as cloud VR and 8K streaming, demands bitrates over 30 Mbps, tail delays under 50 ms, and fairness among users, but current rate control methods cannot hit all three at once. It argues this happens because they ignore the 5G network's changing delays and how it allocates physical resources. Choir fixes this by running mainly on the base stations and using knowledge of the radio link and the video traffic to tell senders how fast to send, as shown in simulations and testbed tests that reach the targets across scenarios. If true, this would let demanding video applications run reliably on 5G without sacrificing quality or responsiveness.

Core claim

Choir is a collaborative solution mainly deployed on 5G base stations that deeply integrates 5G radio characteristics and video streaming traffic patterns to guide efficient sender-side rate control. This overcomes the failure of existing end-to-end and network-assisted algorithms to simultaneously satisfy high average bitrate, low tail delay, and inter-flow fairness in RTBC scenarios.

What carries the argument

Choir, the base-station deployed collaborative controller that fuses 5G physical layer details with video traffic patterns to direct rate decisions at the sender.

If this is right

Achieves video bitrates exceeding 30 Mbps with tail delay below 50 ms
Ensures fairness among multiple concurrent video flows
Maintains performance in varied 5G network conditions as validated by simulations and testbed experiments
Allows RTBC applications like cloud VR and 8K streaming to meet all criteria without trade-offs

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

This approach could extend to other latency-sensitive 5G applications beyond video, such as real-time gaming or remote control.
It suggests that tighter integration between the radio access network and application layer may reduce reliance on purely end-to-end protocols in future networks.
Deploying such logic on base stations might improve scalability for many users by centralizing some control.

Load-bearing premise

Existing solutions fail primarily because they do not adapt to the 5G radio access network's dynamic delays and resource allocation strategies, and that integrating radio and video details at the base station can achieve all performance goals without creating new problems.

What would settle it

An experiment in a real 5G testbed where Choir fails to deliver bitrates above 30 Mbps with tail delays under 50 ms and fair sharing at the same time, while an existing method succeeds.

Figures

Figures reproduced from arXiv: 2605.02510 by Baosen Zhao, Gaogang Xie, Jiaxing Zhang, Qinghua Wu, Tingting Yuan, Wanghong Yang, Wenji Du, Xiaoming Fu, Xu Zhou, Yongmao Ren.

**Figure 1.** Figure 1: Transmission scenario of RTBC services in 5G view at source ↗

**Figure 2.** Figure 2: The transmission procedure of video stream in 5G. view at source ↗

**Figure 3.** Figure 3: Performance of different solutions in 5G networks. view at source ↗

**Figure 4.** Figure 4: The Framework of Choir rate control framework specifically for 5G RAN’s unique concurrency and channel dynamics, Choir. 3 Choir Design 3.1 Overview The overall framework of Choir is shown in view at source ↗

**Figure 5.** Figure 5: Open-source 5G network testbed view at source ↗

**Figure 6.** Figure 6: Bitrate and frame delay achieved by 8 control solution in trace-driven simulation. view at source ↗

**Figure 7.** Figure 7: Bitrate and frame delay achieved by 8 control solution in B210 RAN. view at source ↗

**Figure 8.** Figure 8: The distribution of delay (a) and bitrate (b) of 8 view at source ↗

**Figure 9.** Figure 9: Bitrate and frame delay achieved by 8 control solution in openXG RAN. view at source ↗

**Figure 10.** Figure 10: Comparison of bitrate and tail delay of 4 solutions. view at source ↗

**Figure 12.** Figure 12: Frame bitrate variation. Choir SCONE 0.0 2.5 5.0 7.5 10.0 12.5 15.0 17.5 Avarage Bitrate (Mbps) Choir SCONE 0 5 10 15 20 25 99th Percentile Delay (ms) Default 1-Frame 2-Frame 3-Frame view at source ↗

**Figure 11.** Figure 11: Fairness of Choir. compared to existing solutions. At 10ms wired network latency, Choir demonstrates a more pronounced enhancement, increasing the average bitrate by 2.86% to 35.04% over alternative approaches. For scenarios with 20ms wired network latency, Choir maintains robust performance, delivering a 4.73% to 31.76% improvement in average bitrate relative to all baselines. Further, we scaled Choi… view at source ↗

**Figure 14.** Figure 14: The impact of smoothing factor view at source ↗

**Figure 15.** Figure 15: Openxg bandwidth trace. 0 1 2 3 4 5 Timeline (s) 0 10 20 30 40 Bitrate (Mbps) BandWidth view at source ↗

**Figure 16.** Figure 16: B210 bandwidth trace view at source ↗

read the original abstract

Real-time broadband communication (RTBC) scenarios, such as cloud virtual reality and 8K live streaming, further raise the criteria of the performance triangle, requiring video bitrates exceeding 30 Mbps, tail delay below 50 ms, and fairness guarantees for multi-user concurrent access. Based on our testing and analysis, existing RTBC-oriented rate control solutions, including end-to-end algorithms and network-assisted algorithms, fail to simultaneously satisfy all performance metrics. The native dynamic delay and physical-layer resource allocation strategy inherent to the 5G radio access network (RAN) are the key reasons. These solutions lack adaptation to the 5G architecture, leading to reduced decision performance. This paper proposes Choir, an innovative collaborative solution mainly deployed on 5G base stations that deeply integrates 5G radio characteristics and video streaming traffic patterns to guide efficient sender-side rate control. Extensive simulation and testbed evaluations demonstrate Choir's significant performance in achieving high average bitrate, low tail delay, and inter-flow fairness across different 5G network scenarios.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

Choir puts collaborative rate control on 5G base stations to hit high bitrate, low delay, and fairness, but the evidence for its edge over 5G-aware alternatives is not yet clear.

read the letter

The main thing here is that Choir puts rate control logic on the 5G base station to blend radio-layer details with video flow patterns, aiming to break the bitrate-delay-fairness trade-off that current end-to-end and assisted schemes hit in cloud VR and 8K cases. It does a decent job laying out why 5G's native delay and resource allocation create problems for prior algorithms, and the idea of sender guidance from the BS is a reasonable architectural shift. The simulation and testbed results are presented as showing better average bitrate, lower tail delay, and improved fairness across scenarios, which at least gives some concrete numbers to look at. The weaker part is the lack of direct head-to-head with other 5G-specific rate controls that already pull in CQI or scheduler info. If the testbed abstracts away the actual PHY scheduler, the claim that this integration avoids new trade-offs stays a bit untested. The abstract also skips the exact decision logic or how fairness is enforced, so the reader has to wait for the full methods section to judge reproducibility. This is the kind of paper that matters for wireless systems researchers who care about practical 5G video delivery. It is worth sending out for review because the problem is timely and the approach is grounded in real network constraints, though it will probably need stronger baseline comparisons and more transparent evaluation details to hold up.

Referee Report

3 major / 2 minor

Summary. The manuscript claims that existing end-to-end and network-assisted RTBC rate-control algorithms cannot simultaneously satisfy >30 Mbps average bitrate, <50 ms tail delay, and inter-flow fairness in 5G networks. It attributes this failure to the native dynamic delay and PHY-layer resource allocation in the 5G RAN, and proposes Choir, a collaborative framework deployed primarily on 5G base stations that integrates radio characteristics with video traffic patterns to drive sender-side rate control. Extensive simulation and testbed results are said to demonstrate that Choir meets all three metrics across varied 5G scenarios.

Significance. If the evaluations prove rigorous and include appropriate 5G-aware controls, the work could meaningfully advance practical integration of RAN feedback with application-layer adaptation for demanding real-time broadband services such as cloud VR and 8K streaming. The base-station-centric design choice is a concrete architectural contribution that leverages 5G infrastructure.

major comments (3)

[Abstract] Abstract: the assertion of 'significant performance' from simulations and testbeds supplies no methodology, baselines, quantitative metrics, or statistical evidence, rendering the central performance-triangle claims unverifiable from the given text.
[Introduction] Introduction (and § on related work): the diagnosis that 'native dynamic delay and physical-layer resource allocation strategy' in the 5G RAN is the primary reason prior solutions fail must be tested against 5G-aware baselines that already exploit CQI, MCS, or RB-allocation feedback; without such comparisons the root-cause attribution and the 'no new trade-offs' claim are unanchored.
[Evaluation] Evaluation section: the simulation and testbed descriptions must demonstrate that actual PHY scheduler dynamics and per-RB allocation are exposed rather than replaced by abstracted delay models; otherwise the claimed superiority of Choir's radio-video integration cannot be distinguished from simpler 5G-specific feedback mechanisms.

minor comments (2)

[Abstract] The abstract sentence 'demonstrate Choir's significant performance in achieving' is grammatically awkward and should be rephrased for clarity.
Clarify the precise signaling path and deployment split: which components run on the BS versus the sender or client, and what control messages are exchanged.

Simulated Author's Rebuttal

3 responses · 0 unresolved

Thank you for the constructive review and the recommendation for major revision. We appreciate the specific feedback on the abstract, the root-cause diagnosis in the introduction, and the need for clearer evaluation details. We will revise the manuscript to incorporate more quantitative evidence, additional baselines, and expanded descriptions of the PHY modeling.

read point-by-point responses

Referee: [Abstract] Abstract: the assertion of 'significant performance' from simulations and testbeds supplies no methodology, baselines, quantitative metrics, or statistical evidence, rendering the central performance-triangle claims unverifiable from the given text.

Authors: We agree that the abstract is currently too high-level and lacks the requested details. In the revised manuscript, we will expand the abstract to explicitly state the evaluation methodology (simulations with 5G RAN model and real testbed), the primary baselines (end-to-end algorithms such as BBR and network-assisted schemes), key quantitative metrics (e.g., >35 Mbps average bitrate, <40 ms 99th-percentile delay, and fairness index >0.9 across flows), and the number of runs/scenarios with statistical significance. This will make the performance-triangle claims directly verifiable. revision: yes
Referee: [Introduction] Introduction (and § on related work): the diagnosis that 'native dynamic delay and physical-layer resource allocation strategy' in the 5G RAN is the primary reason prior solutions fail must be tested against 5G-aware baselines that already exploit CQI, MCS, or RB-allocation feedback; without such comparisons the root-cause attribution and the 'no new trade-offs' claim are unanchored.

Authors: We acknowledge that strengthening the attribution requires direct comparisons to 5G-aware baselines. While the current related-work discussion highlights limitations of prior methods, we will add new evaluation results against 5G-aware variants that incorporate CQI, MCS, and RB feedback. These will show that such feedback alone is insufficient for simultaneous satisfaction of the three metrics due to missing video-pattern integration, whereas Choir achieves all three without new trade-offs. The introduction will be updated to reference these results and refine the diagnosis accordingly. revision: yes
Referee: [Evaluation] Evaluation section: the simulation and testbed descriptions must demonstrate that actual PHY scheduler dynamics and per-RB allocation are exposed rather than replaced by abstracted delay models; otherwise the claimed superiority of Choir's radio-video integration cannot be distinguished from simpler 5G-specific feedback mechanisms.

Authors: Our simulation employs a detailed 5G PHY-layer model that explicitly simulates per-RB allocation, CQI-based MCS selection, and base-station scheduler dynamics rather than relying solely on abstracted delay models; the testbed uses real 5G hardware exposing RAN metrics. To make this distinction clearer and address the concern, we will add expanded descriptions, traces of RB allocations, and delay-component breakdowns in the evaluation section, along with direct comparisons showing how Choir's radio-video integration outperforms simpler 5G feedback mechanisms. revision: partial

Circularity Check

0 steps flagged

No circularity: architectural proposal with external validation, no derivations or self-referential fits

full rationale

The paper frames its contribution as an engineering architecture (Choir deployed on 5G BSes) that integrates radio characteristics and video patterns, justified by 'testing and analysis' plus simulation/testbed results. No equations, parameters, or derivation chain appear in the provided text. The root-cause attribution to 5G RAN dynamics is presented as an empirical observation rather than a mathematical reduction. No self-citation load-bearing steps, uniqueness theorems, or ansatzes are visible. The central claims rest on external evaluations, not on any quantity that is defined in terms of itself or fitted then renamed as prediction. This is the common case of a self-contained systems paper.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Abstract-only review limits visibility; the central claim rests on the domain assumption that 5G RAN dynamics are the root cause of prior failures and that radio-aware integration will resolve the performance triangle.

axioms (1)

domain assumption 5G RAN exhibits native dynamic delay and physical-layer resource allocation that existing rate control solutions cannot adapt to
Explicitly stated in abstract as the key reason for failure of prior methods.

pith-pipeline@v0.9.0 · 5506 in / 1247 out tokens · 37723 ms · 2026-05-08T17:51:06.481688+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

46 extracted references · 2 canonical work pages

[1]

Immersive interconnected virtual and augmented reality: A 5g and iot perspective.Jour- nal of Network and Systems Management, 28:796–826, 2020

Maria Torres Vega, Christos Liaskos, Sergi Abadal, Evangelos Papapetrou, Akshay Jain, Belkacem Mouhouche, Gökhan Kalem, Salih Ergüt, Marian Mach, Tomas Sabol, et al. Immersive interconnected virtual and augmented reality: A 5g and iot perspective.Jour- nal of Network and Systems Management, 28:796–826, 2020

2020
[2]

Cloudvr solution white paper

HUAWEI-iLab. Cloudvr solution white paper
[3]

Immersive environments and virtual reality: Systematic review and advances in com- munication, interaction and simulation.Multimodal technologies and interaction, 1(4):21, 2017

Jose Luis Rubio-Tamayo, Manuel Gertrudix Barrio, and Francisco García García. Immersive environments and virtual reality: Systematic review and advances in com- munication, interaction and simulation.Multimodal technologies and interaction, 1(4):21, 2017

2017
[4]

A measurement study on achieving imperceptible latency in mobile cloud gaming

Teemu Kämäräinen, Matti Siekkinen, Antti Ylä-Jääski, Wenxiao Zhang, and Pan Hui. A measurement study on achieving imperceptible latency in mobile cloud gaming. InProceedings of the 8th ACM on Multimedia Systems Conference, pages 88–99, 2017

2017
[5]

Congestion control for web real-time communication.IEEE/ACM Transactions on Network- ing, 25(5):2629–2642, 2017

Gaetano Carlucci, Luca De Cicco, Stefan Holmer, and Saverio Mascolo. Congestion control for web real-time communication.IEEE/ACM Transactions on Network- ing, 25(5):2629–2642, 2017

2017
[6]

Per- formance analysis of receive-side real-time congestion control for webrtc

Varun Singh, Albert Abello Lozano, and Jorg Ott. Per- formance analysis of receive-side real-time congestion control for webrtc. In2013 20th International Packet Video Workshop, pages 1–8. IEEE, 2013

2013
[7]

Release 16

3GPP. Release 16. https://www.3gpp.org/ specifications-technologies/releases/ release-16, 2024

2024
[8]

Self- Clocked Rate Adaptation for Multimedia

Ingemar Johansson and Zaheduzzaman Sarker. Self- Clocked Rate Adaptation for Multimedia. RFC 8298, December 2017

2017
[9]

Copa: Practical {Delay-Based} congestion control for the internet

Venkat Arun and Hari Balakrishnan. Copa: Practical {Delay-Based} congestion control for the internet. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18), pages 329–342, 2018

2018
[10]

SQP: Congestion control for low-latency interactive video streaming.arXiv preprint arXiv:2207.11857, 2022

Devdeep Ray, Connor Smith, Teng Wei, David Chu, and Srinivasan Seshan. Sqp: Congestion control for low-latency interactive video streaming.arXiv preprint arXiv:2207.11857, 2022

work page arXiv 2022
[11]

Pudica: Toward {Near- Zero} queuing delay in congestion control for cloud gaming

Shibo Wang, Shusen Yang, Xiao Kong, Chenglei Wu, Longwei Jiang, Chenren Xu, Cong Zhao, Xuesong Yang, Jianjun Xiao, Xin Liu, et al. Pudica: Toward {Near- Zero} queuing delay in congestion control for cloud gaming. In21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pages 113–129, 2024

2024
[12]

{ABC}: A sim- ple explicit congestion controller for wireless networks

Prateesh Goyal, Anup Agarwal, Ravi Netravali, Moham- mad Alizadeh, and Hari Balakrishnan. {ABC}: A sim- ple explicit congestion controller for wireless networks. In17th USENIX Symposium on Networked Systems De- sign and Implementation (NSDI 20), pages 353–372, 2020

2020
[13]

Rfc 9330: Low latency, low loss, and scalable throughput (l4s) in- ternet service: Architecture, 2023

K De Schepper, M Bagnulo, and G White. Rfc 9330: Low latency, low loss, and scalable throughput (l4s) in- ternet service: Architecture, 2023

2023
[14]

Achiev- ing consistent low latency for wireless real-time commu- nications with the shortest control loop

Zili Meng, Yaning Guo, Chen Sun, Bo Wang, Justine Sherry, Hongqiang Harry Liu, and Mingwei Xu. Achiev- ing consistent low latency for wireless real-time commu- nications with the shortest control loop. InProceedings of the ACM SIGCOMM 2022 Conference, pages 193– 206, 2022

2022
[15]

SCONE Real Time Communi- cation Requirement

Hang Shi, Xuesong Geng, Qiangzhou Gao, Qinghua Wu, and Jiaxing Zhang. SCONE Real Time Communi- cation Requirement. Internet-Draft draft-shi-scone-rtc- requirement-02, Internet Engineering Task Force, April
[16]

Bbr: Congestion-based congestion control: Measuring bottle- neck bandwidth and round-trip propagation time.ACM Queue, 14(5):20–53, 2016

Neal Cardwell, Yuchung Cheng, C Stephen Gunn, Soheil Hassas Yeganeh, and Van Jacobson. Bbr: Congestion-based congestion control: Measuring bottle- neck bandwidth and round-trip propagation time.ACM Queue, 14(5):20–53, 2016

2016
[17]

Cubic: a new tcp-friendly high-speed tcp variant.ACM SIGOPS operating systems review, 42(5):64–74, 2008

Sangtae Ha, Injong Rhee, and Lisong Xu. Cubic: a new tcp-friendly high-speed tcp variant.ACM SIGOPS operating systems review, 42(5):64–74, 2008

2008
[18]

Pbe-cc: Congestion control via endpoint-centric, physical-layer bandwidth measurements

Yaxiong Xie, Fan Yi, and Kyle Jamieson. Pbe-cc: Congestion control via endpoint-centric, physical-layer bandwidth measurements. InProceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, ar- chitectures, and protocols for computer communication, pages 451–464, 2020

2020
[19]

The addition of explicit congestion notification (ecn) to ip

Kadangode Ramakrishnan, Sally Floyd, and David Black. The addition of explicit congestion notification (ecn) to ip. Technical report, 2001

2001
[20]

Adaptable l4s congestion control for cloud-based real-time streaming over 5g.IEEE Open Journal of Signal Processing, 2024

Jangwoo Son, Yago Sanchez, Cornelius Hellge, and Thomas Schierl. Adaptable l4s congestion control for cloud-based real-time streaming over 5g.IEEE Open Journal of Signal Processing, 2024

2024
[21]

Implementing the’prague requirements’ for low latency low loss scalable throughput (l4s).Netdev 0x13, 2019

Bob Briscoe, Koen De Schepper, Olivier Tilmans, Mirja Kühlewind, Joakim Misund, Olga Albisser, and A Sajjad Ahmed. Implementing the’prague requirements’ for low latency low loss scalable throughput (l4s).Netdev 0x13, 2019

2019
[22]

Principles for internet congestion management

Lloyd Brown, Albert Gran Alcoz, Frank Cangialosi, Ak- shay Narayan, Mohammad Alizadeh, Hari Balakrish- nan, Eric Friedman, Ethan Katz-Bassett, Arvind Krish- namurthy, Michael Schapira, et al. Principles for internet congestion management. InProceedings of the ACM SIGCOMM 2024 Conference, pages 166–180, 2024

2024
[23]

Cellre- play: Towards accurate record-and-replay for cellular networks

William Sentosa, Balakrishnan Chandrasekaran, P Brighten Godfrey, and Haitham Hassanieh. Cellre- play: Towards accurate record-and-replay for cellular networks. NSDI 2025

2025
[24]

An e2e simulator for 5g nr networks

Natale Patriciello, Sandra Lagen, Biljana Bojovic, and Lorenza Giupponi. An e2e simulator for 5g nr networks. Simulation Modelling Practice and Theory, 96:101933, 2019

2019
[25]

An ns-3 implementation of a bursty traffic framework for virtual reality sources

Mattia Lecci, Andrea Zanella, and Michele Zorzi. An ns-3 implementation of a bursty traffic framework for virtual reality sources. InProceedings of the 2021 Work- shop on ns-3, pages 73–80, 2021

2021
[26]

Calibration of the 5g-lena system level sim- ulator in 3gpp reference scenarios.Simul

Katerina Koutlia, Biljana Bojovic, Zoraze Ali, and San- dra Lagén. Calibration of the 5g-lena system level sim- ulator in 3gpp reference scenarios.Simul. Model. Pract. Theory, 119:102580, 2022

2022
[27]

Openairin- terface: Democratizing innovation in the 5g era.Com- puter Networks, 176:107284, 2020

Florian Kaltenberger, Aloizio P Silva, Abhimanyu Go- sain, Luhan Wang, and Tien-Thinh Nguyen. Openairin- terface: Democratizing innovation in the 5g era.Com- puter Networks, 176:107284, 2020

2020
[28]

xgproduct

WITCOMM. xgproduct. https://witcomm.net/ xgstation, 2023

2023
[29]

Openairinterface 5g: Feature set documentation

OpenAirInterface. Openairinterface 5g: Feature set documentation. https://gitlab.eurecom.fr/ oai/openairinterface5g/blob/develop/doc/ FEATURE_SET.md. Accessed: 2024-10-09

2024
[30]

Technical specification group radio access network; nr; radio re- source control (rrc) protocol specification

3rd Generation Partnership Project (3GPP). Technical specification group radio access network; nr; radio re- source control (rrc) protocol specification. 3GPP TS 38.331, September 2023. Version 17.7.0

2023
[31]

Technical specification group radio access network; nr; radio link control (rlc) protocol specification

3rd Generation Partnership Project (3GPP). Technical specification group radio access network; nr; radio link control (rlc) protocol specification. 3GPP TS 38.322, September 2023. Version 17.7.0

2023
[32]

3GPP TS 23.288: Architecture enhancements for 5g system (5gs) to support network data analytics ser- vices

3GPP. 3GPP TS 23.288: Architecture enhancements for 5g system (5gs) to support network data analytics ser- vices. Technical Specification (TS) 23.288, 3rd Genera- tion Partnership Project (3GPP), December 2019. Ver- sion 15.4.0

2019
[33]

XQUIC Library released by Alibaba is a cross- platform implementation of QUIC and HTTP/3 protocol

Alibaba. XQUIC Library released by Alibaba is a cross- platform implementation of QUIC and HTTP/3 protocol. 2022

2022
[34]

RTP over QUIC (RoQ)

Mathis Engelbart, Joerg Ott, and Spencer Dawkins. RTP over QUIC (RoQ). Internet-Draft draft-ietf-avtcore- rtp-over-quic-11, Internet Engineering Task Force, July
[35]

Application-aware IPv6 Networking (APN6) Encapsulation

Zhenbin Li, Shuping Peng, Chongfeng Xie, and Shuai Zhang. Application-aware IPv6 Networking (APN6) Encapsulation. Internet-Draft draft-li-6man-apn-ipv6- encap-00, Internet Engineering Task Force, March 2024. Work in Progress

2024
[36]

Analysis and design of the google congestion control for web real-time communication (webrtc)

Gaetano Carlucci, Luca De Cicco, Stefan Holmer, and Saverio Mascolo. Analysis and design of the google congestion control for web real-time communication (webrtc). InProceedings of the 7th International Con- ference on Multimedia Systems, pages 1–12, 2016

2016
[37]

Network-assisted dynamic adaptation (nada): a unified congestion control scheme for real-time media.RFC 8698, 2020

Xiaoqing Zhu, Rong Pan, M Ramalho, and S Mena. Network-assisted dynamic adaptation (nada): a unified congestion control scheme for real-time media.RFC 8698, 2020

2020
[38]

Congestion control for rtp media: A com- parison on simulated environment

Songyang Zhang, Weimin Lei, Wei Zhang, and Yun- chong Guan. Congestion control for rtp media: A com- parison on simulated environment. InInternational Conference on Simulation Tools and Techniques, pages 43–52. Springer, 2019

2019
[39]

Confucius: Achieving consistent low latency with practical queue management for real- time communications.arXiv preprint arXiv:2310.18030, 2023

Zili Meng, Nirav Atre, Mingwei Xu, Justine Sherry, and Maria Apostolaki. Confucius: Achieving consistent low latency with practical queue management for real- time communications.arXiv preprint arXiv:2310.18030, 2023

work page arXiv 2023
[40]

Enabling high quality {Real-Time} communications with adaptive {Frame-Rate}

Zili Meng, Tingfeng Wang, Yixin Shen, Bo Wang, Ming- wei Xu, Rui Han, Honghao Liu, Venkat Arun, Hongxin Hu, and Xue Wei. Enabling high quality {Real-Time} communications with adaptive {Frame-Rate}. In20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 1429–1450, 2023

2023
[41]

Jitbright: towards low-latency mobile cloud rendering through jitter buffer optimiza- tion

Yuankang Zhao, Qinghua Wu, Gerui Lv, Furong Yang, Jiuhai Zhang, Feng Peng, Yanmei Liu, Zhenyu Li, Ying Chen, Hongyu Guo, et al. Jitbright: towards low-latency mobile cloud rendering through jitter buffer optimiza- tion. InProceedings of the 34th edition of the Workshop on Network and Operating System Support for Digital Audio and Video, pages 36–42, 2024

2024
[42]

Hairpin: Rethinking packet loss recov- ery in edge-based interactive video streaming

Zili Meng, Xiao Kong, Jing Chen, Bo Wang, Mingwei Xu, Rui Han, Honghao Liu, Venkat Arun, Hongxin Hu, and Xue Wei. Hairpin: Rethinking packet loss recov- ery in edge-based interactive video streaming. In21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pages 907–926, 2024

2024
[43]

Tambur: Efficient loss recovery for videoconferencing via streaming codes

Michael Rudow, Francis Y Yan, Abhishek Ku- mar, Ganesh Ananthanarayanan, Martin Ellis, and KV Rashmi. Tambur: Efficient loss recovery for videoconferencing via streaming codes. In20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 953–971, 2023

2023
[44]

Learning to co- ordinate video codec with transport protocol for mobile video telephony

Anfu Zhou, Huanhuan Zhang, Guangyuan Su, Leilei Wu, Ruoxuan Ma, Zhen Meng, Xinyu Zhang, Xiufeng Xie, Huadong Ma, and Xiaojiang Chen. Learning to co- ordinate video codec with transport protocol for mobile video telephony. InThe 25th Annual International Con- ference on Mobile Computing and Networking, pages 1–16, 2019

2019
[45]

Onrl: Improving mobile video telephony via online reinforcement learning

Huanhuan Zhang, Anfu Zhou, Jiamin Lu, Ruoxuan Ma, Yuhan Hu, Cong Li, Xinyu Zhang, Huadong Ma, and Xi- aojiang Chen. Onrl: Improving mobile video telephony via online reinforcement learning. InProceedings of the 26th Annual International Conference on Mobile Computing and Networking, pages 1–14, 2020

2020
[46]

Loki: improving long tail performance of learning-based real-time video adaptation by fusing rule-based models

Huanhuan Zhang, Anfu Zhou, Yuhan Hu, Chaoyue Li, Guangping Wang, Xinyu Zhang, Huadong Ma, Leilei Wu, Aiyun Chen, and Changhui Wu. Loki: improving long tail performance of learning-based real-time video adaptation by fusing rule-based models. InProceedings of the 27th Annual International Conference on Mobile Computing and Networking, pages 775–788, 2021. ...

2021