pith. sign in

arxiv: 2510.25079 · v1 · submitted 2025-10-29 · 💻 cs.NI · cs.MM

Performance Evaluation of Multimedia Traffic in Cloud Storage Services over Wi-Fi and LTE Networks

Albert Espinal , V. Sanchez Padilla , Yesenia Cevallos This is my paper

Pith reviewed 2026-05-18 03:57 UTC · model grok-4.3

classification 💻 cs.NI cs.MM
keywords cloud storageWi-FiLTEmultimedia trafficperformance evaluationlatencyjitterpacket size distribution
0
0 comments X

The pith

Google Drive provides the most consistent low-latency performance for multimedia cloud uploads over Wi-Fi and LTE networks.

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

The paper tests how Dropbox, Google Drive, and OneDrive perform when uploading multimedia files over Wi-Fi and LTE connections. By capturing packets and measuring delay, jitter, bandwidth, and loss, it seeks to show which service handles these transfers most reliably. Readers might care because many people store photos and videos in the cloud from their phones and want smooth, interruption-free uploads. The work concludes that Google Drive stays consistent on both networks while Wi-Fi generally beats LTE in stability.

Core claim

Google Drive maintained the most consistent performance across both types of networks, showing low latency and reduced jitter. Dropbox showed efficient bandwidth utilization, but experienced a longer delay over LTE, attributed to a greater number of intermediate hops. OneDrive presented variable behavior, with elevated packet rates and increased sensitivity to fluctuations in the mobile network. A bimodal distribution of packet sizes was observed and modeled using a dual Poisson function. Wi-Fi connections provided greater stability for multimedia transfers, while LTE performance varied depending on platform-specific implementations.

What carries the argument

Wireshark-based traffic capture and analysis of metrics such as delay, jitter, bandwidth, and packet loss, along with dual Poisson modeling of packet sizes.

If this is right

  • Google Drive offers the best consistency for multimedia cloud storage across network types.
  • Wi-Fi is more stable than LTE for these transfers overall.
  • Dropbox experiences longer delays over LTE due to more intermediate hops.
  • OneDrive shows greater sensitivity to mobile network fluctuations because of its higher packet rates.
  • Further analysis with larger datasets and heterogeneous networks would extend the understanding of traffic behavior.

Where Pith is reading between the lines

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

  • Cloud providers might optimize their service implementations specifically for better LTE compatibility based on these metric differences.
  • The dual Poisson model for packet sizes could be tested on other cloud applications to check for similar traffic patterns.
  • Users relying on LTE in variable conditions might benefit from defaulting to Google Drive in their apps for more reliable transfers.
  • Similar evaluations on newer network generations could test whether the observed stability gaps between services narrow.

Load-bearing premise

The measured differences in delay, jitter, and packet behavior are attributable to service-specific implementations and network type rather than to uncontrolled variables such as background traffic, exact file sizes, or transient signal conditions during the captures.

What would settle it

Repeating the uploads with fixed file sizes, no background traffic, stable signal conditions, and multiple trials would show whether Google Drive still ranks highest in consistency or if rankings shift.

read the original abstract

The performance of Dropbox, Google Drive, and OneDrive cloud storage services was evaluated under Wi-Fi and LTE network conditions during multimedia file uploads. Traffic was captured using Wireshark, and key metrics (including delay, jitter, bandwidth, and packet loss) were analyzed. Google Drive maintained the most consistent performance across both types of networks, showing low latency and reduced jitter. Dropbox showed efficient bandwidth utilization, but experienced a longer delay over LTE, attributed to a greater number of intermediate hops. OneDrive presented variable behavior, with elevated packet rates and increased sensitivity to fluctuations in the mobile network. A bimodal distribution of packet sizes was observed and modeled using a dual Poisson function. In general, Wi-Fi connections provided greater stability for multimedia transfers, while LTE performance varied depending on platform-specific implementations. The results contribute to a better understanding of traffic behavior in cloud-based storage applications and suggest further analysis with larger datasets and heterogeneous access networks.

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

1 major / 1 minor

Summary. The paper evaluates the performance of Dropbox, Google Drive, and OneDrive for multimedia file uploads over Wi-Fi and LTE networks using Wireshark captures. It analyzes metrics including delay, jitter, bandwidth, and packet loss, concluding that Google Drive shows the most consistent performance with low latency and reduced jitter across both networks, Dropbox offers efficient bandwidth utilization but longer delays on LTE due to more hops, OneDrive exhibits variable behavior with higher packet rates and sensitivity to network fluctuations, and packet sizes follow a bimodal distribution modeled by a dual Poisson function. Wi-Fi generally provides greater stability than LTE for these transfers.

Significance. If the central comparative claims hold after addressing methodological gaps, the work would provide useful empirical observations on service-specific traffic patterns in wireless cloud storage scenarios, potentially informing user choices and service optimizations for multimedia applications. The direct measurement approach and dual-Poisson modeling of packet sizes are positive elements that could support reproducibility if data and controls are documented.

major comments (1)
  1. [Abstract] Abstract: The abstract reports observations and a dual-Poisson model but supplies no sample sizes, statistical tests, error bars, or description of how network conditions were controlled, so the support for the central comparative claims cannot be verified from the given text.
minor comments (1)
  1. The manuscript would benefit from explicit discussion of file size standardization, trial repetition counts, and any background traffic controls to strengthen the attribution of differences to service implementations versus experimental variables.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address the single major comment below and outline the revisions we will make.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The abstract reports observations and a dual-Poisson model but supplies no sample sizes, statistical tests, error bars, or description of how network conditions were controlled, so the support for the central comparative claims cannot be verified from the given text.

    Authors: We agree that the abstract, as a concise summary, omits key methodological details that would help readers assess the comparative claims at a glance. The full manuscript (Section 3) describes the experimental setup, including repeated upload trials for each service-network combination, Wireshark packet captures for delay/jitter/bandwidth/packet-loss measurements, and controlled conditions achieved by using identical devices, locations, and time-of-day windows for Wi-Fi and LTE tests. No formal hypothesis tests (e.g., ANOVA or t-tests) were applied because the study is observational; instead, we report mean values across trials together with observed variability. To directly address the referee's concern we will revise the abstract to include approximate sample sizes, a brief statement on network controls, and a note that the dual-Poisson model was fitted to the empirical packet-size histograms. We will also ensure error bars appear on the relevant figures in the revised version. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical measurement study without derivations or self-referential reductions

full rationale

This is a direct performance evaluation paper based on Wireshark traffic captures of multimedia uploads to Dropbox, Google Drive, and OneDrive over Wi-Fi and LTE. Metrics such as delay, jitter, bandwidth, and packet loss are measured and compared; a dual-Poisson model is applied descriptively to observed bimodal packet-size distributions. No equations, first-principles derivations, predictions, or uniqueness theorems are claimed. The central findings rest on experimental observations rather than any chain that reduces by construction to fitted inputs or self-citations. The work is therefore self-contained with no load-bearing circular steps.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The study rests on the domain assumption that captured traffic reflects service behavior under representative conditions and introduces a dual Poisson model whose parameters are fitted to the observed packet-size distribution.

free parameters (1)
  • dual Poisson parameters for packet-size distribution
    Fitted to the bimodal packet-size histogram observed in the traffic captures.
axioms (1)
  • domain assumption Traffic captures were performed under representative and stable Wi-Fi and LTE conditions without significant external interference
    Invoked when attributing performance differences to the cloud platforms and network types.

pith-pipeline@v0.9.0 · 5691 in / 1247 out tokens · 52316 ms · 2026-05-18T03:57:03.529013+00:00 · methodology

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

40 extracted references · 40 canonical work pages

  1. [1]

    Cloud technologies: use in the educational pro - cess as a way to high management in business,

    T. Tsalko and S. Nevmerzhytska, “Cloud technologies: use in the educational pro - cess as a way to high management in business,” Zeszyty Naukowe Wyz˙szej Szko-ly Ekonomiczno-Spo-lecznej w Ostro -lece, vol. 50, no. 3, pp. 1 –12, 2023

    work page 2023

  2. [2]

    Cloud computing: A novel digital storage paradigm,

    A. S. Ogunmodede and E. O. Adepoju, “Cloud computing: A novel digital storage paradigm,” Journal of Economic, Social and Educational, vol. 2, no. 2, pp. 108–116, 2023

    work page 2023

  3. [3]

    A review on quality of experience (QoE) in cloud computing,

    A. A. Laghari, X. Zhang, Z. A. Shaikh, A. Khan, V. V. Estrela, and S. Izadi, “A review on quality of experience (QoE) in cloud computing,” Journal of Reliable Intelligent Environments , vol. 10, no. 2, pp. 107 –121, 2024

    work page 2024

  4. [4]

    Cloud computing and networking for SmartFarm AgriTech,

    M. L. Rathod, A. Shivaputra, H. Umadevi, K. Nagamani, and S. Periyasamy, “Cloud computing and networking for SmartFarm AgriTech,” Journal of Nano - materials, vol. 2022, no. 1, p. 6491747, 2022

    work page 2022

  5. [5]

    Best practices for real -time data processing in media applications,

    M. Mokale, “Best practices for real -time data processing in media applications,” International Journal of Multidisciplinary Research and Growth Evaluation , vol. 1, no. 5, pp. 131 –137, 2020. Performance Evaluation of Multimedia Traffic... 11

    work page 2020

  6. [6]

    Design and implementation of a cloud-based event-driven architecture for real-time data processing in wireless sensor networks,

    S. Khriji, Y. Benbelgacem, R. Ch´eour, D. E. Houssaini, and O. Kanoun, “Design and implementation of a cloud-based event-driven architecture for real-time data processing in wireless sensor networks,” The Journal of Supercomputing , vol. 78, no. 3, pp. 3374 –3401, 2022

    work page 2022

  7. [7]

    Cloud-based e -learning: scaffolding the environment for adaptive e - learning ecosystem based on cloud computing infrastructure,

    A. Alam, “Cloud-based e -learning: scaffolding the environment for adaptive e - learning ecosystem based on cloud computing infrastructure,” in Computer Com - munication, Networking and IoT: Proceedings of 5th ICICC 2021, Volume 2 , pp. 1–

    work page 2021

  8. [8]

    The impact of cloud -based information systems on collaboration and productivity in remote teams,

    S. Holloway, “The impact of cloud -based information systems on collaboration and productivity in remote teams,” Preprints.org , 2024

    work page 2024

  9. [9]

    CHALLENGES IN TRANSMISSION OF DATA AND NETWORK CONNECTIVITY,

    S. M. D. S. AHMAD, “CHALLENGES IN TRANSMISSION OF DATA AND NETWORK CONNECTIVITY,” Authorea Preprints, 2023

    work page 2023

  10. [10]

    Cloud storage cost: a taxonomy and survey,

    A. Q. Khan, M. Matskin, R. Prodan, C. Bussler, D. Roman, and A. Soylu, “Cloud storage cost: a taxonomy and survey,” World Wide Web, vol. 27, no. 4, p. 36, 2024

    work page 2024

  11. [11]

    Performance Evaluation of Voice over WiFi (VoWiFi) Using IP Mul - timedia Subsystem (IMS),

    W. A. Aziz, “Performance Evaluation of Voice over WiFi (VoWiFi) Using IP Mul - timedia Subsystem (IMS),” International Journal of Simulation –Systems, Science & Technology , vol. 24, no. 2, 2023

    work page 2023

  12. [12]

    Exploring the Quality of Service Impacts of Cloud Computing over Wireless Net - works,

    S. K. Gopal, A. S. Mohammed, V. R. Saddi, N. Jiwani, and J. Logeshwaran, “Exploring the Quality of Service Impacts of Cloud Computing over Wireless Net - works,” in 2024 International Conference on E -mobility, Power Control and Smart Systems (ICEMPS) , 2024, pp. 01 –06. doi:10.1109/ICEMPS60684.2024.10559341

    work page doi:10.1109/icemps60684.2024.10559341 2024

  13. [13]

    A systematic review of multimedia tools for cybersecurity awareness and education,

    L. Zhang-Kennedy and S. Chiasson, “A systematic review of multimedia tools for cybersecurity awareness and education,” ACM Computing Surveys (CSUR) , vol. 54, no. 1, pp. 1 –39, 2021

    work page 2021

  14. [14]

    Use of information communication technology by medical educators amid COVID -19 pandemic and beyond,

    I. Chatterjee and P. Chakraborty, “Use of information communication technology by medical educators amid COVID -19 pandemic and beyond,” Journal of Educa - tional Technology Systems, vol. 49, no. 3, pp. 310 –324, 2021

    work page 2021

  15. [15]

    Cloud media video encoding: review and challenges,

    W. Moina -Rivera, M. Garcia -Pineda, J. Guti´errez -Aguado, and J. M. Alcaraz - Calero, “Cloud media video encoding: review and challenges,” Multimedia Tools and Applications , vol. 83, no. 34, pp. 81231 –81278, 2024

    work page 2024

  16. [16]

    Quality of Experience - Oriented Cloud -Edge Dynamic Adaptive Streaming: Recent Advances, Challenges, and Opportunities,

    W. Wang, X. Wei, W. Tao, M. Zhou, and J. Cheng, “Quality of Experience - Oriented Cloud -Edge Dynamic Adaptive Streaming: Recent Advances, Challenges, and Opportunities,” Symmetry, vol. 17, no. 2, p. 194, 2025

    work page 2025

  17. [17]

    Influence of Product Placement in Netflix Original Shows on Con - sumers’ Brand Recall,

    O. Zagorodnia, “Influence of Product Placement in Netflix Original Shows on Con - sumers’ Brand Recall,” Master’s thesis, Webster University, 2024

    work page 2024

  18. [18]

    Self -healing control: review, framework, and prospect,

    M. T. Sultan and H. El Sayed, “QoE -Aware Analysis and Management of Multi - media Services in 5G and Beyond Heterogeneous Networks,” IEEE Access, vol. 11, pp. 77679–77688, 2023. doi:10.1109/ACCESS.2023.3298556

    work page doi:10.1109/access.2023.3298556 2023

  19. [19]

    Cloud Computing Based Digital Media Content Distribution Technology,

    X. He and Q. Zhang, “Cloud Computing Based Digital Media Content Distribution Technology,” Procedia Computer Science , vol. 247, pp. 461 –468, 2024. The 11th International Conference on Applications and Techniques in Cyber Intelligence. doi:10.1016/j.procs.2024.10.055

    work page doi:10.1016/j.procs.2024.10.055 2024

  20. [20]

    Effective performance metrics for multimedia mission - critical communication systems,

    A. Ali and A. Ware, “Effective performance metrics for multimedia mission - critical communication systems,” Annals of Emerging Technologies in Computing (AETiC), vol. 5, no. 2, pp. 1 –14, 2021

    work page 2021

  21. [21]

    One -way delay measurement from traditional networks to SDN: A survey,

    D. Chefrour, “One -way delay measurement from traditional networks to SDN: A survey,” ACM Computing Surveys (CSUR), vol. 54, no. 7, pp. 1–35, 2021

    work page 2021

  22. [22]

    Data storage management in cloud environments: Taxonomy, survey, and future directions,

    Y. Mansouri, A. N. Toosi, and R. Buyya, “Data storage management in cloud environments: Taxonomy, survey, and future directions,” ACM Computing Surveys (CSUR), vol. 50, no. 6, pp. 1–51, 2017. 12 A. Espinal et al

    work page 2017

  23. [23]

    Cost optimization for cloud storage from user perspec - tives: Recent advances, taxonomy, and survey,

    M. Liu, L. Pan, and S. Liu, “Cost optimization for cloud storage from user perspec - tives: Recent advances, taxonomy, and survey,” ACM Computing Surveys , vol. 55, no. 13s, pp. 1 –37, 2023

    work page 2023

  24. [24]

    Web Content Delivery Optimization,

    H. Bayat Pour, “Web Content Delivery Optimization,” Master’s thesis, Aalto Uni - versity, 2016

    work page 2016

  25. [25]

    5G, 6G, and Beyond: Recent advances and future challenges,

    F. Salahdine, T. Han, and N. Zhang, “5G, 6G, and Beyond: Recent advances and future challenges,” Annals of Telecommunications, vol. 78, no. 9, pp. 525–549, 2023

    work page 2023

  26. [26]

    Bozanic and S

    M. Bozanic and S. Sinha, Mobile communication networks: 5G and a vision of 6G. Springer, 2021

    work page 2021

  27. [27]

    Janevski, Future Fixed and Mobile Broadband Internet, Clouds, and IoT/AI

    T. Janevski, Future Fixed and Mobile Broadband Internet, Clouds, and IoT/AI . John Wiley & Sons, 2024

    work page 2024

  28. [28]

    Toward Decentralized Cloud Storage With IPFS: Opportunities, Challenges, and Future Considerations,

    T. V. Doan, Y. Psaras, J. Ott, and V. Bajpai, “Toward Decentralized Cloud Storage With IPFS: Opportunities, Challenges, and Future Considerations,” IEEE Internet Computing, vol. 26, no. 6, pp. 7 –15, 2022. doi:10.1109/MIC.2022.3209804

    work page doi:10.1109/mic.2022.3209804 2022

  29. [29]

    Intelligent Network Traffic Control with AI and Machine Learning,

    S. Shetty, T. M. S., V. H. M., and R. N. Shaikh, “Intelligent Network Traffic Control with AI and Machine Learning,” in 2024 IEEE 16th International Conference on Computational Intelligence and Communication Networks (CICN) , 2024, pp. 353 –

    work page 2024

  30. [30]

    doi:10.1109/CICN63059.2024.10847397

    work page doi:10.1109/cicn63059.2024.10847397 2024

  31. [31]

    Overview of versatile video coding (H. 266/VVC) and its coding perfor - mance analysis,

    M. Lee, H. Song, J. Park, B. Jeon, J. Kang, J.-G. Kim, Y.-L. Lee, J.-W. Kang, and D. Sim, “Overview of versatile video coding (H. 266/VVC) and its coding perfor - mance analysis,” IEIE Transactions on Smart Processing & Computing, vol. 12, no. 2, pp. 122 –154, 2023

    work page 2023

  32. [32]

    A Review of Emerging Video Codecs: Challenges and Opportunities,

    A. Punchihewa and D. Bailey, “A Review of Emerging Video Codecs: Challenges and Opportunities,” in 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ) , 2020, pp. 1 –6. doi:10.1109/IVCNZ51579.2020.9290536

    work page doi:10.1109/ivcnz51579.2020.9290536 2020

  33. [33]

    Video transcoding for adaptive bitrate streaming over edge - cloud continuum,

    G. Gao and Y. Wen, “Video transcoding for adaptive bitrate streaming over edge - cloud continuum,” Digital Communications and Networks , vol. 7, no. 4, pp. 598 – 604, 2021. doi:10.1016/j.dcan.2020.12.006

    work page doi:10.1016/j.dcan.2020.12.006 2021

  34. [34]

    Artificial intelligence (AI) and machine learning for multimedia and edge information processing,

    J. K. P. Seng, K. Li -minn Ang, E. Peter, and A. Mmonyi, “Artificial intelligence (AI) and machine learning for multimedia and edge information processing,” Elec- tronics, vol. 11, no. 14, p. 2239, 2022

    work page 2022

  35. [35]

    A Survey on Multimedia Services QoE Assessment and Machine Learning -Based Prediction,

    G. Kougioumtzidis, V. Poulkov, Z. D. Zaharis, and P. I. Lazaridis, “A Survey on Multimedia Services QoE Assessment and Machine Learning -Based Prediction,” IEEE Access, vol. 10, pp. 19507 –19538, 2022. doi:10.1109/ACCESS.2022.3149592

    work page doi:10.1109/access.2022.3149592 2022

  36. [36]

    Torrent Poisoning Protection with a Reverse Proxy Server,

    A. Godinho, J. Rosado, F. S´a, F. Caldeira, and F. Cardoso, “Torrent Poisoning Protection with a Reverse Proxy Server,” Electronics, vol. 12, no. 1, p. 165, 2023

    work page 2023

  37. [37]

    Applications of Cloud Computing: A Review,

    I. Shah, “Applications of Cloud Computing: A Review,” Authorea Preprints, 2023

    work page 2023

  38. [38]

    A Review of Secure Cloud Storage-Based on Cloud Computing,

    P. Aneja, A. Bhatia, and A. Shankar, “A Review of Secure Cloud Storage-Based on Cloud Computing,” in Emerging Technologies in Data Mining and Information Security: Proceedings of IEMIS 2020, Volume 1 , pp. 923–933. Springer, 2021

    work page 2020

  39. [39]

    Bock, Learn Wireshark: A definitive guide to expertly analyzing protocols and troubleshooting networks using Wireshark

    L. Bock, Learn Wireshark: A definitive guide to expertly analyzing protocols and troubleshooting networks using Wireshark. Packt Publishing Ltd, 2022

    work page 2022

  40. [40]

    Traffic model using a novel sniffer that ensures the user data privacy,

    A. Espinal, R. Estrada, and C. Monsalve, “Traffic model using a novel sniffer that ensures the user data privacy,” in MATEC Web of Conferences , vol. 292, p. 03002. EDP Sciences, 2019

    work page 2019