QFlow: A Learning Approach to High QoE Video Streaming at the Wireless Edge

Bhattacharyya, R.; Bura, Archana; Rengarajan, Desik; Rumuly, Mason; Xia, Bainan; Shakkottai, Srinivas; Kalathil, Dileep; Mok, Ricky K. P.; Dhamdhere, Amogh

doi:10.1109/tnet.2021.3106675

Cited by 18 publications

(26 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…QFlow [60] paper used reinforcement learning to perform one-way adaptive flow prioritization at the edge network. QFlow argued current link are application agnostic in their scheduling.…”

Section: Papermentioning

confidence: 99%

“…They proposed an edge computing based solution to address these challenges and limitations. QFlow [60] is an Edge computing based ABR system using ML based model to optimize QoE.…”

Section: B Egde Computing Based Abr Systemsmentioning

confidence: 99%

“…Here they provide evidence of PHY layer metrics are used in assigning resources to the users in the cellular network. ABR Adaptive Bitrate Streaming (ABR) ABR based on ML [58,59] Based on DL [10,11,18,40,47] Based on RL [104] Egde computing based ABR systems [60,62,65] Using SDN [63,66] ABR with different optimization goals Improve QoE for vehicles [45,86,87,93] Optimize for user data-plan [67] Chunk Based Filtering [56] Optimizing video during handovers [45,93,96] Video stream in vehicular networks [85][86][87]105] 4K and 360 • video streaming 4K video streaming [51] 360 • video streaming [78,79,[82][83][84] Cross-layer optimizations for Video streaming [55,97,106,107] Fig. 6.…”

Section: Abr Algorithms With Cross-layer Optimizationsmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Bitrate Video Streaming for Wireless nodes: A Survey

Nishat,

Gnawali,

Abdelhadi

2020

Preprint

View full text Add to dashboard Cite

In today's Internet, video is the most dominant application and in addition to this, wireless networks such as WiFi, Cellular, and Bluetooth have become ubiquitous. Hence, most of the Internet traffic is video over wireless nodes. There is a plethora of research to improve video streaming to achieve high Quality of Experience (QoE) over the Internet. Many of them focus on wireless nodes. Recent measurement studies often show QoE of video suffers in many wireless clients over the Internet. Recently, many research papers have presented models and schemes to optimize the Adaptive BitRate (ABR) based video streaming for wireless and mobile users. In this survey, we present a comprehensive overview of recent work in the area of Internet video specially designed for wireless network. Recent research has suggested that there are some new challenges added by the connectivity of clients through wireless. Also these challenges become more difficult to handle when these nodes are mobile. This survey also discusses new potential areas of future research due to the increasing scarcity of wireless spectrum.

show abstract

“…QFlow [60] paper used reinforcement learning to perform one-way adaptive flow prioritization at the edge network. QFlow argued current link are application agnostic in their scheduling.…”

Section: Papermentioning

confidence: 99%

“…They proposed an edge computing based solution to address these challenges and limitations. QFlow [60] is an Edge computing based ABR system using ML based model to optimize QoE.…”

Section: B Egde Computing Based Abr Systemsmentioning

confidence: 99%

Section: Abr Algorithms With Cross-layer Optimizationsmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Bitrate Video Streaming for Wireless nodes: A Survey

Nishat,

Gnawali,

Abdelhadi

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…A large user demand along with advancements in content access devices, such as tablets, smart TVs, and smartphones, have all contributed to a dramatic growth of the video streaming applications in the last decade. Consequently, significant advances were made, both by industry and academia, to develop and deploy ever-improving streaming technologies [11,15,19,21,25,28,30,34].…”

Section: Introductionmentioning

confidence: 99%

Multilateral Micro-Monitoring for Internet Streaming

Shyamsunder¹,

Lazerek²,

Dimoulas³

et al. 2021

Preprint

View full text Add to dashboard Cite

Video streaming is dominating the Internet. To compete with the performance of traditional cable and satellite options, content providers outsource the content delivery to thirdparty content distribution networks and brokers. However, no existing auditing mechanism offers a multilateral view of a streaming service's performance. In other words, no auditing mechanism reflects the mutual agreement of content providers, content distributors and end-users alike about how well, or not, a service performs.In this paper, we present UgoVor, a system for monitoring multilateral streaming contracts, that is enforceable descriptions of mutual agreements among content providers, content distributors and end-users. Our key insight is that real-time multilateral micro-auditing-capable of accounting for every re-buffering event and the resolution of every video chunk in a stream-is not only feasible, but an Internet-scalable task. To demonstrate this claim we evaluate UgoVor in the context of a 10-month long experiment, corresponding to over 25 years of streaming data, including over 430,000 streaming sessions with clients from over 1,300 unique ASes. Our measurements confirm that UgoVor can provide an accurate distributed performance consensus for Internet streaming, and can help radically advance existing performance-agnostic pricing models towards novel and transparent pay-what-you-experience ones.

show abstract

“…However, these algorithms are usually optimized for specific scenarios where pre-programmed mod-els are used to generate adaptive bit rates to optimize Quality of Service (QoS) or Quality of Experience (QoE) metrics. Recently, the integration of machine learning (ML) techniques for video streaming has been proposed in [5], [6], [7], [8]. However, the prime focus in the earlier techniques has been on application of ML to generate adaptive video quality levels for bandwidth fluctuations that may arise due to the congestion in the network.…”

Section: Introductionmentioning

confidence: 99%

Nancy: Neural Adaptive Network Coding Methodology for Video Distribution Over Wireless Networks

Saxena

Naresh

Gupta

et al. 2020

GLOBECOM 2020 - 2020 IEEE Global Communications Conference

View full text Add to dashboard Cite

This paper presents NANCY, a system that generates adaptive bit rates (ABR) for video and adaptive network coding rates (ANCR) using reinforcement learning (RL) for video distribution over wireless networks. NANCY trains a neural network model with rewards formulated as quality of experience (QoE) metrics. It performs joint optimization in order to select: (i) adaptive bit rates for future video chunks to counter variations in available bandwidth and (ii) adaptive network coding rates to encode the video chunk slices to counter packet losses in wireless networks. We present the design and implementation of NANCY, and evaluate its performance compared to state-of-the-art video rate adaptation algorithms including Pensieve and robustMPC. Our results show that NANCY provides 29.91% and 60.34% higher average QoE than Pensieve and robustMPC, respectively.

show abstract

QFlow: A Learning Approach to High QoE Video Streaming at the Wireless Edge

Cited by 18 publications

References 31 publications

Adaptive Bitrate Video Streaming for Wireless nodes: A Survey

Adaptive Bitrate Video Streaming for Wireless nodes: A Survey

Multilateral Micro-Monitoring for Internet Streaming

Nancy: Neural Adaptive Network Coding Methodology for Video Distribution Over Wireless Networks

Contact Info

Product

Resources

About