Quality of experience measurements of multipath TCP applications on iOS mobile devices

Keller, Katharina; Felka, Patrick; Fornoff, Jan; Hinz, Oliver; Rizk, Amr

doi:10.1145/3339825.3394935

Cited by 4 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCND collect information include the IP session start and end time, device and user identifiers, traffic volume, type of service (i.e., web, email, streaming audio/video). PCND can also be used to infer user preference and user attributes, by monitoring the session length (number of pages a user clicks through) and abandonment rate (if a user leaves the website after visiting the landing page) [11]. Besides, the feedback channel quality is a good perception of the wireless environment.…”

Section: A Perceptionmentioning

confidence: 99%

“…User mobility, and user traffic behavior influence the traffic load of each base station, thus affecting the overall performance. This user-related knowledge can be learned and mined from RAND and MTD [11]. Radio propagation environment account for the propagation mechanisms of electromagnetic waves on a wireless link, which is affected by environment dynamics, obstacles distribution, noise, weather, etc.…”

Section: B Cognitionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence Powered Mobile Networks: From Cognition to Decision

Luo¹,

Yuan²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Mobile networks (MN) are anticipated to provide unprecedented opportunities to enable a new world of connected experiences and radically shift the way people interact with everything. MN are becoming more and more complex, driven by ever-increasingly complicated configuration issues and blossoming new service requirements. This complexity poses significant challenges in deployment, management, operation, optimization, and maintenance, since they require a complete understanding and cognition of MN. Artificial intelligence (AI), which deals with the simulation of intelligent behavior in computers, has demonstrated enormous success in many application domains, suggesting its potential in cognizing the state of MN and making intelligent decisions. In this paper, we first propose an AI-powered mobile network architecture and discuss challenges in terms of cognition complexity, decisions with high-dimensional action space, and self-adaption to system dynamics. Then, potential solutions that are associated with AI are discussed. Finally, we propose a deep learning approach that directly maps the state of MN to perceived QoS, integrating cognition with the decision. Our proposed approach helps operators in making more intelligent decisions to guarantee QoS. Meanwhile, the effectiveness and advantages of our proposed approach are demonstrated on a real-world dataset, involving 31261 users over 77 stations within 5 days.

show abstract

Section: A Perceptionmentioning

confidence: 99%

Section: B Cognitionmentioning

confidence: 99%