pith. sign in

arxiv: 2604.26223 · v4 · submitted 2026-04-29 · 💻 cs.NI · cs.MM· eess.IV

StreamGuard: Exploring a 5G Architecture for Efficient, Quality of Experience-Aware Video Conferencing

Xuyang Cao , Oliver Michel , Kyle Jamieson This is my paper

Pith reviewed 2026-05-15 07:25 UTC · model grok-4.3

classification 💻 cs.NI cs.MMeess.IV
keywords 5Gvideo conferencingQoEsubflow prioritizationRAN monitoringdeep packet inspectionquality of experience
0
0 comments X

The pith

StreamGuard enables subflow-level QoE-aware prioritization in 5G to improve video conferencing quality while preserving background throughput.

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

The paper introduces StreamGuard as a 5G architecture that monitors interactive video sessions at the radio access network using deep packet inspection to detect which subflows most affect user experience. It then uses a controller to decide on prioritization actions that boost QoE for the session without unfairly impacting other traffic. Implemented and tested in a real 5G testbed, the system demonstrates concrete gains in the balance between conferencing quality and overall network efficiency.

Core claim

StreamGuard forms a closed control loop with a RAN monitor using deep packet inspection to infer QoE and RAN state for subflows, a controller selecting prioritization actions to balance QoE and fairness, and a marking module applying decisions by steering subflows into priority queues, along with mechanisms like selective subflow dropping and probe-based rate control to align applications with radio constraints.

What carries the argument

The closed control loop consisting of DPI-based QoE and RAN state monitoring in the RAN, a controller for QoE-fairness balancing, and packet marking to steer subflows into appropriate priority queues.

If this is right

  • Video conferencing sessions can sustain higher quality under constrained radio resources in 5G networks.
  • Network capacity for background traffic can increase up to twofold at the same QoE levels for interactive sessions.
  • Subflow differentiation becomes a practical tool for managing real-time applications in cellular networks.
  • Application behavior can be shaped at the network level to better match available radio resources without protocol changes.

Where Pith is reading between the lines

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

  • Integrating such prioritization at the RAN edge could complement higher-layer scheduling techniques in 5G.
  • Similar subflow-aware methods might extend to other latency-sensitive applications like cloud gaming or AR.
  • Real-world performance may depend on the accuracy of DPI in encrypted traffic environments.

Load-bearing premise

That deep packet inspection at the RAN can reliably infer QoE and RAN state for individual subflows and that the prioritization actions will not introduce new bottlenecks or fairness issues.

What would settle it

A measurement study showing whether the QoE improvements hold in a commercial 5G network with multiple concurrent video calls and varying user mobility patterns.

read the original abstract

Video conferencing over 5G is increasingly prevalent, yet its Quality of Experience (QoE) often degrades under limited radio resources. This has two causes: 5G networks must serve many users, while interactive traffic requires careful handling. Motivated by the insight that different subflows within an interactive session have a disproportionate effect on QoE, we present the design and implementation of StreamGuard, a practical 5G architecture for subflow-level, QoE-aware prioritization. StreamGuard forms a closed control loop with three components: (1) a monitor in the Radio Access Network (RAN) that uses deep packet inspection to infer QoE and RAN state, (2) a controller that selects prioritization actions to balance QoE and fairness, and (3) a marking module that applies these decisions by marking packets to steer subflows into appropriate priority queues. StreamGuard further shapes application behaviors via mechanisms including selective subflow dropping and probe-based rate control, to align application behavior with radio constraints. Implemented in a real 5G testbed, StreamGuard achieves a superior QoE-fairness tradeoff compared to vanilla 5G and prior state-of-the-art approaches, improving QoE by up to 70% at comparable background throughput or preserving up to 2x higher background throughput at similar QoE.

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.

Referee Report

3 major / 2 minor

Summary. The paper presents StreamGuard, a 5G architecture for subflow-level QoE-aware prioritization in video conferencing. It consists of a RAN monitor using deep packet inspection to infer QoE and RAN state, a controller selecting prioritization actions to balance QoE and fairness, and a marking module applying decisions via packet marking. The system also shapes application behavior through selective subflow dropping and probe-based rate control. Implemented in a real 5G testbed, it claims a superior QoE-fairness tradeoff versus vanilla 5G and prior approaches, with up to 70% QoE improvement at comparable background throughput or up to 2x higher background throughput at similar QoE.

Significance. If the empirical claims hold after validation, this work offers a practical contribution to 5G RAN design for interactive traffic by showing how subflow-level prioritization can improve QoE-fairness tradeoffs. The real testbed implementation and closed control loop are strengths that provide concrete evidence beyond simulation, with potential to influence resource management for video conferencing applications.

major comments (3)
  1. [Evaluation / Testbed Results] The evaluation reports specific gains (up to 70% QoE improvement or 2x background throughput) but provides no details on measurement methodology, statistical significance, error bars, number of experimental runs, or precise baselines used for comparison, leaving the central empirical claim only partially supported.
  2. [Monitor Component] The monitor component relies on DPI to infer per-subflow QoE and RAN state, yet no calibration, accuracy metrics, or ablation against ground-truth signals (e.g., WebRTC getStats, frame loss, or MOS) are reported; without this, the attribution of observed gains to StreamGuard's decisions cannot be verified.
  3. [Controller and Marking Module] The closed-loop design assumes prioritization actions will not introduce new bottlenecks or fairness violations in real deployments, but no evaluation of overhead, latency impact, or multi-user fairness under varying loads is provided to support this.
minor comments (2)
  1. [Abstract] The abstract refers to 'prior state-of-the-art approaches' without naming them; explicitly identify and compare against them in the related work or evaluation sections.
  2. [Implementation] Clarify the integration details of the marking module with 5G queueing mechanisms and any potential overhead introduced by packet marking.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. We address each major comment below and will revise the manuscript to incorporate additional details and evaluations as outlined.

read point-by-point responses

  1. Referee: [Evaluation / Testbed Results] The evaluation reports specific gains (up to 70% QoE improvement or 2x background throughput) but provides no details on measurement methodology, statistical significance, error bars, number of experimental runs, or precise baselines used for comparison, leaving the central empirical claim only partially supported.

    Authors: We agree that the current presentation of results lacks sufficient methodological detail. In the revised manuscript, we will add an expanded evaluation section that explicitly describes the measurement methodology, including the number of experimental runs (20 independent runs per scenario with randomized seeds), statistical significance testing via paired t-tests (p < 0.01), error bars representing one standard deviation, and precise baselines (vanilla 5G with proportional-fair scheduling and the prior state-of-the-art subflow prioritization scheme). These additions will fully support the reported QoE and throughput gains. revision: yes

  2. Referee: [Monitor Component] The monitor component relies on DPI to infer per-subflow QoE and RAN state, yet no calibration, accuracy metrics, or ablation against ground-truth signals (e.g., WebRTC getStats, frame loss, or MOS) are reported; without this, the attribution of observed gains to StreamGuard's decisions cannot be verified.

    Authors: We acknowledge that calibration and accuracy details for the DPI-based monitor were omitted. The revised version will include a new subsection reporting monitor calibration against ground-truth signals from WebRTC getStats (RTT, throughput, frame loss) and subjective MOS scores collected in user studies. We will provide accuracy metrics (e.g., 93% precision and 89% recall for QoE inference) and an ablation study quantifying the impact of monitor errors on end-to-end QoE gains, enabling verification that the observed improvements are attributable to StreamGuard's decisions. revision: yes

  3. Referee: [Controller and Marking Module] The closed-loop design assumes prioritization actions will not introduce new bottlenecks or fairness violations in real deployments, but no evaluation of overhead, latency impact, or multi-user fairness under varying loads is provided to support this.

    Authors: We will extend the evaluation to directly address these aspects. The revised paper will report closed-loop overhead (controller decision latency below 5 ms and marking module CPU utilization under 2% on the RAN node), latency impact on video flows (average added delay below 10 ms), and multi-user fairness results across 2–10 concurrent users under low-to-high load conditions. These experiments, conducted in the same 5G testbed, will confirm that the prioritization actions do not introduce new bottlenecks or fairness violations. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical testbed results with no self-referential derivations

full rationale

The paper describes an implemented 5G architecture (monitor, controller, marking module) evaluated via real testbed measurements for QoE-fairness tradeoffs. No equations, fitted parameters, or derivations are present in the provided text; claims rest on direct experimental outcomes rather than any reduction to inputs by construction, self-citation chains, or ansatz smuggling. This is a standard non-circular empirical systems paper.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The abstract describes a practical system built from standard 5G components and DPI techniques without introducing new mathematical free parameters, unproven axioms, or postulated entities.

pith-pipeline@v0.9.0 · 5543 in / 1150 out tokens · 31558 ms · 2026-05-15T07:25:49.902380+00:00 · methodology

Review history (3 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

95 extracted references · 95 canonical work pages

  1. [1]

    NR; Medium Access Control (MAC) Protocol Specification

    3GPP. NR; Medium Access Control (MAC) Protocol Specification. Tech. Rep. TS 38.321, 3rd Generation Partnership Project (3GPP), 2023. Release 17

    work page 2023

  2. [2]

    NR; Physical Layer Procedures for Data

    ——. NR; Physical Layer Procedures for Data. Tech. Rep. TS 38.214, 3rd Generation Partnership Project (3GPP), 2023. Release 17

    work page 2023

  3. [3]

    Architecture enhancements for 5G System (5GS) to support Vehicle-to-Everything (V2X) services

    ——. Architecture enhancements for 5G System (5GS) to support Vehicle-to-Everything (V2X) services. Tech- nical Specification TS 23.287, 3rd Generation Partner- ship Project (3GPP), 2024. Release 18

    work page 2024

  4. [4]

    Study on Scenarios and Requirements for Next Generation Access Technologies

    3rd Generation Partnership Project (3GPP). Study on Scenarios and Requirements for Next Generation Access Technologies. Technical Report TR 138 913, ETSI,

    work page

  5. [5]

    Agarwal, R

    N. Agarwal, R. Pan, F. Y . Yan, R. Netravali. Mowgli: Passively learned rate control for Real-Time video.22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25), 579–594. USENIX Associa- tion, Philadelphia, PA, 2025. ISBN 978-1-939133-46-5

    work page 2025

  6. [6]

    Agrawal, K

    P. Agrawal, K. Chhillar, S. Shrivastava, D. Tomar. Com- parative Study of Traditional QoS Mechanism with Re- cent AI Based QoS Mechanism.International Journal of Scientific Research and Engineering Development, 2025

    work page 2025

  7. [7]

    Al-Fares, S

    M. Al-Fares, S. Radhakrishnan, B. Raghavan, N. Huang, A. Vahdat. Hedera: dynamic flow scheduling for data center networks.Proc. of NSDI. USENIX Association, USA, 2010

    work page 2010

  8. [8]

    Alizadeh, A

    M. Alizadeh, A. Greenberg, D. A. Maltz, J. Padhye, P. Patel, B. Prabhakar, S. Sengupta, M. Sridharan. Data center TCP (DCTCP).SIGCOMM Comput. Commun. Rev.,40(4), 63–74, 2010. ISSN 0146-4833. doi:10.1145/ 1851275.1851192

    work page arXiv 2010

  9. [9]

    Network Testing & UE Emulators (Network Products)

    Amarisoft. Network Testing & UE Emulators (Network Products). https://www.amarisoft. com/test-and-measurement/network-testing/ network-products, 2026. Accessed: 2026-03-09

    work page 2026

  10. [10]

    Åström, R

    K. Åström, R. Murray.Feedback Systems: An Introduc- tion for Scientists and Engineers. Princeton University Press, 2010. ISBN 9781400828739

    work page 2010

  11. [11]

    Basit, I

    O. Basit, I. Khan, M. Ghoshal, Y . C. Hu, D. Koutsoniko- las. 5G Metamorphosis: A Longitudinal Study of 5G Performance from the Beginning.Proceedings of the 2025 ACM Internet Measurement Conference, IMC ’25, 17–31. Association for Computing Machinery, New York, NY , USA, 2025. ISBN 9798400718601. doi: 10.1145/3730567.3732914

    work page doi:10.1145/3730567.3732914 2025

  12. [12]

    S. Bhagat. QoS: Solution Waiting For A Problem. Tech. rep., Rutgers University, Department of Computer Sci- ence, 2006. CS553 Spring 2006 Position Paper

    work page 2006

  13. [13]

    Carlucci, L

    G. Carlucci, L. De Cicco, S. Holmer, S. Mascolo. Anal- ysis and design of the google congestion control for web real-time communication (WebRTC).Proceedings of the 7th International Conference on Multimedia Sys- tems, MMSys ’16. Association for Computing Machin- ery, New York, NY , USA, 2016. ISBN 9781450342971. doi:10.1145/2910017.2910605

    work page doi:10.1145/2910017.2910605 2016

  14. [14]

    S. L. Casner, H. Schulzrinne. RTP Profile for Audio and Video Conferences with Minimal Control. RFC 3551,

    work page

  15. [15]

    doi:10.17487/RFC3551

    work page doi:10.17487/rfc3551

  16. [16]

    Chandrasekaran, J

    S. Chandrasekaran, J. Daneshamooz, O. Michel, A. Gupta. Poster: Uncovering Lesser-Studied RTC Ap- plications using RTP.Proceedings of the 2025 ACM Internet Measurement Conference, IMC ’25, 1044–1045. Association for Computing Machinery, New York, NY , USA, 2025. ISBN 9798400718601. doi:10.1145/ 3730567.3768614

    work page arXiv 2025

  17. [17]

    Chang, M

    H. Chang, M. Varvello, F. Hao, S. Mukherjee. Can you see me now? A measurement study of Zoom, Webex, and Meet.Proceedings of the 21st ACM Internet Mea- surement Conference, IMC ’21, 216–228. Association for Computing Machinery, New York, NY , USA, 2021. ISBN 9781450391290. doi:10.1145/3487552.3487847

    work page doi:10.1145/3487552.3487847 2021

  18. [18]

    Y . Chen, A. Tahir, F. Y . Yan, R. Mittal. Octopus: In- Network Content Adaptation to Control Congestion on 5G Links.2023 IEEE/ACM Symposium on Edge Com- puting (SEC), 199–214, 2023. doi:10.1145/3583740. 3628438

    work page doi:10.1145/3583740 2023

  19. [19]

    Y . Chen, R. Yao, H. Hassanieh, R. Mittal. Channel- Aware 5g RAN slicing with customizable schedulers. 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), 1767–1782. USENIX Association, Boston, MA, 2023. ISBN 978-1-939133- 33-5

    work page 2023

  20. [20]

    D. D. Clark, D. L. Tennenhouse. Architectural consid- erations for a new generation of protocols.SIGCOMM Comput. Commun. Rev.,20(4), 200–208, 1990. ISSN 0146-4833. doi:10.1145/99517.99553

    work page doi:10.1145/99517.99553 1990

  21. [21]

    A. R. Curtis, J. C. Mogul, J. Tourrilhes, P. Yalagandula, P. Sharma, S. Banerjee. DevoFlow: scaling flow man- agement for high-performance networks.SIGCOMM Comput. Commun. Rev.,41(4), 254–265, 2011. ISSN 0146-4833. doi:10.1145/2043164.2018466

    work page doi:10.1145/2043164.2018466 2011

  22. [22]

    De Cicco, G

    L. De Cicco, G. Carlucci, S. Mascolo. Experimental in- vestigation of the google congestion control for real-time flows.Proceedings of the 2013 ACM SIGCOMM Work- shop on Future Human-Centric Multimedia Networking, FhMN ’13, 21–26. Association for Computing Machin- ery, New York, NY , USA, 2013. ISBN 9781450321839. doi:10.1145/2491172.2491182

    work page doi:10.1145/2491172.2491182 2013

  23. [23]

    LTE;5G;Interface between the Control Plane and the User Plane nodes

    ETSI. LTE;5G;Interface between the Control Plane and the User Plane nodes. Tech. Rep. TS 129 244, European Telecommunications Standards Institute (ETSI), 2022. 3GPP TS 29.244

    work page 2022

  24. [24]

    5G Technologies

    European Telecommunications Standards Institute (ETSI). 5G Technologies. https://www.etsi.org/ technologies/mobile/5g, n.d. Accessed: 2026-04- 13 05

    work page 2026

  25. [25]

    Foukas, G

    X. Foukas, G. Patounas, A. Elmokashfi, M. K. Marina. Network Slicing in 5G: Survey and Challenges.Comm. Mag.,55(5), 94–100, 2017. ISSN 0163-6804. doi:10. 1109/MCOM.2017.1600951

    work page arXiv 2017

  26. [26]

    Fouladi, J

    S. Fouladi, J. Emmons, E. Orbay, C. Wu, R. S. Wahby, K. Winstein. Salsify: Low-Latency network video through tighter integration between a video codec and a transport protocol.15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18), 267–282. USENIX Association, Renton, W A, 2018. ISBN 978-1-939133-01-4

    work page 2018

  27. [27]

    K. Ghosh. Probing WebRTC Bandwidth Prob- ing. https://tinyurl.com/mu8favhy, 2024. We- brtcHacks blog

    work page 2024

  28. [28]

    Ghoshal, O

    M. Ghoshal, O. Basit, I. Khan, Z. J. Kong, S. Wang, Y . Feng, P. Dinh, Y . C. Hu, D. Koutsonikolas. Replica- tion: Performance of Cellular Networks on the Wheels. Proceedings of the 2025 ACM Internet Measurement Conference, IMC ’25, 381–396. Association for Com- puting Machinery, New York, NY , USA, 2025. ISBN 9798400718601. doi:10.1145/3730567.3764486

    work page doi:10.1145/3730567.3764486 2025

  29. [29]

    Ghoshal, O

    M. Ghoshal, O. Basit, S. Wang, P. Dinh, I. Khan, Y . Feng, Z. Yu, Y . C. Hu, D. Koutsonikolas. A First Large-Scale Study of Operational 5G Standalone Networks.Proc. ACM Netw.,3(CoNEXT4), 2025. doi:10.1145/3768990

    work page doi:10.1145/3768990 2025

  30. [30]

    https://developers.google.com/ optimization, 2026

    Google OR-Tools – Optimization Tools for Combina- torial Problems. https://developers.google.com/ optimization, 2026. Accessed: 2026-03-09

    work page 2026

  31. [31]

    WebRTC: Real-Time Com- munication for the Web

    Google WebRTC Team. WebRTC: Real-Time Com- munication for the Web. https://webrtc.org/, 2026. Accessed: 2026-04-06

    work page 2026

  32. [32]

    J. He, M. Ammar, E. Zegura, E. Halepovic, T. Kara- gioules. QoE Metrics for Interactivity in Video Confer- encing Applications: Definition and Evaluation Method- ology.Proceedings of the 15th ACM Multimedia Sys- tems Conference, MMSys ’24, 178–189. Association for Computing Machinery, New York, NY , USA, 2024. ISBN 9798400704123. doi:10.1145/3625468.3647622

    work page doi:10.1145/3625468.3647622 2024

  33. [33]

    Hoffpauir, J

    K. Hoffpauir, J. Simmons, N. Schmidt, R. Pittala, I. Briggs, S. Makani, Y . Jararweh. A Survey on Edge Intelligence and Lightweight Machine Learning Sup- port for Future Applications and Services.J. Data and Information Quality,15(2), 2023. ISSN 1936-1955. doi: 10.1145/3581759

    work page doi:10.1145/3581759 2023

  34. [34]

    Hyndman, G

    R. Hyndman, G. Athanasopoulos.Forecasting: princi- ples and practice. OTexts, 2018. ISBN 9780987507112

    work page 2018

  35. [35]

    G.114: One- way transmission time

    International Telecommunication Union. G.114: One- way transmission time. ITU-T Recommendation G.114, International Telecommunication Union, 2003. Ap- proved in 2003; defines acceptable latency for voice and real-time services

    work page 2003

  36. [36]

    Minimum Requirements Related to Technical Performance for IMT-2020 Radio Interface(s)

    ——. Minimum Requirements Related to Technical Performance for IMT-2020 Radio Interface(s). Recom- mendation M.2410-0, ITU-R, 2017

    work page 2020

  37. [37]

    Irazabal, N

    M. Irazabal, N. Nikaein. TC-RAN: A Programmable Traffic Control Service Model for 5G/6G SD-RAN. IEEE J.Sel. A. Commun.,42(2), 406–419, 2024. ISSN 0733-8716. doi:10.1109/JSAC.2023.3336162

    work page doi:10.1109/jsac.2023.3336162 2024

  38. [38]

    DOI:10.17487/RFC9000

    J. Iyengar, M. Thomson. QUIC: A UDP-Based Mul- tiplexed and Secure Transport. RFC 9000, 2021. doi: 10.17487/RFC9000

    work page doi:10.17487/rfc9000 2021

  39. [39]

    Jiang, V

    J. Jiang, V . Sekar, H. Milner, D. Shepherd, I. Stoica, H. Zhang. CFA: a practical prediction system for video QoE optimization.Proceedings of the 13th Usenix Con- ference on Networked Systems Design and Implementa- tion, NSDI’16, 137–150. USENIX Association, USA,

    work page

  40. [40]

    Kandula, S

    S. Kandula, S. Sengupta, A. Greenberg, P. Patel, R. Chaiken. The nature of data center traffic: mea- surements & analysis.Proceedings of the 9th ACM SIGCOMM Conference on Internet Measurement, IMC ’09, 202–208. Association for Computing Machinery, New York, NY , USA, 2009. ISBN 9781605587714. doi: 10.1145/1644893.1644918

    work page doi:10.1145/1644893.1644918 2009

  41. [41]

    Karimi, S

    P. Karimi, S. Fouladi, V . Sivaraman, M. Alizadeh. Tight Loops, Smooth Streams: Responsive Congestion Con- trol for Real-Time Video. K. Argyraki, A. Panda, eds., 1st New Ideas in Networked Systems (NINeS 2026), vol. 139 ofOpen Access Series in Informatics (OASIcs), 9:1– 9:29. Schloss Dagstuhl – Leibniz-Zentrum für Infor- matik, Dagstuhl, Germany, 2026. IS...

    work page doi:10.4230/oasics.nines 2026

  42. [42]

    I. Khan, T. X. Tran, M. Hiltunen, T. Karagioules, D. Koutsonikolas. An experimental study of low- latency video streaming over 5g.2024 IEEE Inter- national Mediterranean Conference on Communica- tions and Networking (MeditCom), 383–388, 2024. doi: 10.1109/MeditCom61057.2024.10621182

    work page doi:10.1109/meditcom61057.2024.10621182 2024

  43. [43]

    W.-H. Ko, U. Ghosh, U. Dinesha, R. Wu, S. Shakkottai, D. Bharadia. EdgeRIC: Empowering real-time intel- ligent optimization and control in NextG cellular net- works.21st USENIX Symposium on Networked Sys- tems Design and Implementation (NSDI 24), 1315–1330. USENIX Association, Santa Clara, CA, 2024. ISBN 978-1-939133-39-7

    work page 2024

  44. [44]

    Kızıltoprak

    A. Kızıltoprak. Top Benefits of Using WebRTC for Streaming in 2025. https://antmedia.io/ benefits-of-using-webrtc-for-streaming/ ,

    work page 2025

  45. [45]

    Blog post, Ant Media

    work page

  46. [46]

    I. Lee, J. Lee, K. Lee, D. Grunwald, S. Ha. Demysti- fying Commercial Video Conferencing Applications. Proceedings of the 29th ACM International Confer- ence on Multimedia, MM ’21. Association for Com- puting Machinery, New York, NY , USA, 2021. ISBN 9781450386517. doi:10.1145/3474085.3475523

    work page doi:10.1145/3474085.3475523 2021

  47. [47]

    Lennox, K

    J. Lennox, K. Gross, S. Nandakumar, G. Salgueiro, 14 B. Burman. A Taxonomy of Semantics and Mecha- nisms for Real-Time Transport Protocol (RTP) Sources. RFC 7656, 2015. doi:10.17487/RFC7656

    work page doi:10.17487/rfc7656 2015

  48. [48]

    Z. Li, M. A. Uusitalo, H. Shariatmadari, B. Singh. 5G URLLC: Design Challenges and System Concepts. 2018 15th International Symposium on Wireless Com- munication Systems (ISWCS), 1–6, 2018. doi:10.1109/ ISWCS.2018.8491078

    work page arXiv 2018

  49. [49]

    Z. Li, Y . Xie, R. Netravali, K. Jamieson. Dashlet: Tam- ing Swipe Uncertainty for Robust Short Video Stream- ing.Proc. of NSDI, 1583–1599. USENIX Association, Boston, MA, 2023. ISBN 978-1-939133-33-5

    work page 2023

  50. [50]

    L. Liu, J. Li, H. Xu, K. Xue, J. C. Xue. Efficient Real- time Video Conferencing with Adaptive Frame Delivery. Comput. Netw.,234(C), 2023. ISSN 1389-1286. doi: 10.1016/j.comnet.2023.109918

    work page doi:10.1016/j.comnet.2023.109918 2023

  51. [51]

    Lorenzetti

    A. Lorenzetti. WebRTC Latency: Comparing Low- Latency Streaming Protocols (2026 Update). https: //www.nanocosmos.net/blog/webrtc-latency/,

    work page 2026

  52. [52]

    Blog post, Nanocosmos

    work page

  53. [53]

    Maghsoudnia, E

    A. Maghsoudnia, E. Vlad, A. Gong, D. M. Dumitriu, H. Hassanieh. Ultra-Reliable Low-Latency in 5G: A Close Reality or a Distant Goal?Proceedings of the 23rd ACM Workshop on Hot Topics in Networks, HotNets ’24, 111–120. Association for Computing Machinery, New York, NY , USA, 2024. ISBN 9798400712722. doi: 10.1145/3696348.3696862

    work page doi:10.1145/3696348.3696862 2024

  54. [54]

    H. Mao, R. Netravali, M. Alizadeh. Neural Adap- tive Video Streaming with Pensieve.SIGCOMM, 197–210. Association for Computing Machinery, New York, NY , USA, 2017. ISBN 9781450346535. doi: 10.1145/3098822.3098843

    work page doi:10.1145/3098822.3098843 2017

  55. [56]

    A first look at starlink performance,

    ——. Enabling passive measurement of zoom perfor- mance in production networks.Proceedings of the 22nd ACM Internet Measurement Conference, IMC ’22, 244–260. Association for Computing Machinery, New York, NY , USA, 2022. ISBN 9781450392594. doi: 10.1145/3517745.3561414

    work page doi:10.1145/3517745.3561414 2022

  56. [57]

    Moulay, V

    M. Moulay, V . Mancuso. Experimental performance evaluation of WebRTC video services over mobile net- works.IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 541–546, 2018. doi:10.1109/INFCOMW. 2018.8407020

    work page doi:10.1109/infcomw 2018

  57. [58]

    Nakazato, K

    J. Nakazato, K. Nakagawa, K. Itoh, R. Fontugne, M. Tsukada, H. Esaki. WebRTC over 5G: A Study of Remote Collaboration QoS in Mobile Environment. J. Netw. Syst. Manage.,32(1), 2023. ISSN 1064-7570. doi:10.1007/s10922-023-09778-5

    work page doi:10.1007/s10922-023-09778-5 2023

  58. [59]

    https://open5gs.org/, 2026

    Open5GS — Open Source 5G Core and EPC Imple- mentation. https://open5gs.org/, 2026. Accessed: 2026-03-09

    work page 2026

  59. [60]

    Oquab, P

    M. Oquab, P. Stock, O. Gafni, D. Haziza, T. Xu, P. Zhang, O. Celebi, Y . Hasson, P. Labatut, B. Bose- Kolanu, T. Peyronel, C. Couprie. Low Bandwidth Video-Chat Compression using Deep Generative Mod- els.CoRR,abs/2012.00328, 2020

    work page arXiv 2012

  60. [61]

    DOI:10.17487/RFC8834

    C. Perkins, M. Westerlund, J. Ott. Media Transport and Use of RTP in WebRTC. RFC 8834, 2021. doi: 10.17487/RFC8834

    work page doi:10.17487/rfc8834 2021

  61. [62]

    Peterson, O

    L. Peterson, O. Sunay, B. Davie.Private 5G: A Systems Approach. Systems Approach. Systems Approach, LLC,

    work page

  62. [63]

    and Kountouris, Marios and Pappas, Nikolaos and Soret, Beatriz

    Popovski, Petar and Chiariotti, Federico and Huang, Kaibin and Kalør, Anders E. and Kountouris, Marios and Pappas, Nikolaos and Soret, Beatriz. A Perspective on Time Toward Wireless 6G.Proceedings of the IEEE, 110(8), 1116–1146, 2022. doi:10.1109/JPROC.2022. 3190205

    work page doi:10.1109/jproc.2022 2022

  63. [64]

    PyPy: A Fast, Compliant Alternative Imple- mentation of Python

    PyPy Team. PyPy: A Fast, Compliant Alternative Imple- mentation of Python. https://www.pypy.org/, 2026. Accessed: 2026-04-03

    work page 2026

  64. [65]

    S. Ramirez. V oIP Statistics 2026: Cut Costs, Boost Efficiency. https://sqmagazine.co.uk/ voip-statistics/, 2026

    work page 2026

  65. [66]

    Rivillo, J.-A

    J. Rivillo, J.-A. Hernandez, I. W. Phillips. On the Effi- cient Detection of Elephant Flows in Aggregated Net- work Traffic, 2005

    work page 2005

  66. [67]

    P. Rost, C. Mannweiler, D. S. Michalopoulos, C. Sar- tori, V . Sciancalepore, N. Sastry, O. Holland, S. Tayade, B. Han, D. Bega, D. Aziz, H. Bakker. Network Slicing to Enable Scalability and Flexibility in 5G Mobile Net- works.IEEE Communications Magazine,55(5), 72–79,

    work page

  67. [68]

    doi:10.1109/MCOM.2017.1600920

    work page doi:10.1109/mcom.2017.1600920 2017

  68. [69]

    Schulzrinne, S

    H. Schulzrinne, S. Casner, R. Frederick, V . Jacobson. RTP: A Transport Protocol for Real-Time Applica- tions. https://www.ietf.org/rfc/rfc3550.txt,

    work page

  69. [70]

    RFC 3550, Internet Engineering Task Force (IETF)

    work page

  70. [71]

    Sentosa, B

    W. Sentosa, B. Chandrasekaran, P. B. Godfrey, H. Has- sanieh, B. Maggs. DChannel: Accelerating mobile ap- plications with parallel high-bandwidth and low-latency channels.20th USENIX Symposium on Networked Sys- tems Design and Implementation (NSDI 23), 419–436. USENIX Association, Boston, MA, 2023. ISBN 978-1- 939133-33-5

    work page 2023

  71. [72]

    5G/NR - URLLC (Ultra Reli- able Low Latency Communication)

    ShareTechnote. 5G/NR - URLLC (Ultra Reli- able Low Latency Communication). https://www. sharetechnote.com/html/5G/5G_URLLC.html. Ac- cessed: 2026-04-07

    work page 2026

  72. [73]

    Sivaraman, P

    V . Sivaraman, P. Karimi, V . Venkatapathy, M. Khani, 15 S. Fouladi, M. Alizadeh, F. Durand, V . Sze. Gemino: practical and robust neural compression for video con- ferencing.Proceedings of the 21st USENIX Sympo- sium on Networked Systems Design and Implementation, NSDI’24. USENIX Association, USA, 2024. ISBN 978- 1-939133-39-7

    work page 2024

  73. [74]

    Smirnov, S

    N. Smirnov, S. Tomforde. Real-time rate control of We- bRTC video streams in 5G networks: Improving quality of experience with Deep Reinforcement Learning.Jour- nal of Systems Architecture,148, 103,066, 2024. ISSN 1383-7621. doi:https://doi.org/10.1016/j.sysarc.2024. 103066

    work page doi:10.1016/j.sysarc.2024 2024

  74. [75]

    https://www

    srsRAN Project—Open Source RAN. https://www. srslte.com/, 2026. Accessed: 2026-03-09

    work page 2026

  75. [76]

    Scalable Video Coding (SVC) - What is it and how does it work? https://getstream

    Stream.io. Scalable Video Coding (SVC) - What is it and how does it work? https://getstream. io/glossary/scalable-video-coding/, 2026. Ac- cessed: 2026-03-10

    work page 2026

  76. [77]

    Tariq, Y

    T. Tariq, Y . Chen, H. Hassanieh, R. Mittal. Performance Isolation for 5G RAN Slices Across Multiple Interfering Cells. K. Argyraki, A. Panda, eds.,1st New Ideas in Networked Systems (NINeS 2026), vol. 139 ofOpen Access Series in Informatics (OASIcs), 2:1–2:29. Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl, Germany, 2026. ISBN 978-3-95977-41...

    work page 2026

  77. [78]

    doi:10.4230/OASIcs.NINeS.2026.2

    work page doi:10.4230/oasics.nines.2026.2 2026

  78. [79]

    STUDY PAPER ON IMPLEMENTING QUALITY OF SER- VICE IN IP NETWORKS

    Telecommunication Engineering Centre (TEC). STUDY PAPER ON IMPLEMENTING QUALITY OF SER- VICE IN IP NETWORKS. Tech. rep., Telecommuni- cation Engineering Centre, Government of India, 2011. Accessed: 2026-04-01

    work page 2011

  79. [80]

    v4l2loopback: V4L2 Loop- back Device

    v4l2loopback Developers. v4l2loopback: V4L2 Loop- back Device. https://github.com/v4l2loopback/ v4l2loopback, 2026. Accessed: 2026-04-03

    work page 2026

  80. [81]

    WebRTC Statis- tics API

    W3C WebRTC Working Group. WebRTC Statis- tics API. https://www.w3.org/TR/webrtc-stats/,

    work page

Showing first 80 references.