ARBITER: Adaptive rate-based intelligent HTTP streaming algorithm

Zahran, Ahmed H.; Sreenan, Cormac J.

doi:10.1109/icmew.2016.7574709

Cited by 7 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, FESTIVE improved the performance of adaptive streaming when multi-users compete for bottleneck links. While most other rate-based methods also used the mean for network throughput estimates, ARBITER proposed in [8] employed the first and second moments of the throughput samples to better accommodate the high variability of the wireless network throughput, and incorporated both video and network dynamics in its adaptation decisions. Therefore, ARBITER achieved the leverage between the separate factors that affect the experience quality of streaming video.…”

Section: B Heuristic Abr Methodsmentioning

confidence: 99%

“…where Q is the online network, Q is the target network and π θ is as defined in equation (8). In terms of the DASH bitrate adaptation scenario, the introduction of double Q-Learning makes the estimated target value more balanced when using the greedy action to bootstrap for the next chunk's rate.…”

Section: A Improvements On Network Structurementioning

confidence: 99%

“…Improvements and variants of BB have also been proposed in [5] and [6]. The rate-based (RB) method is based on the knowledge of the previously downloaded video chunks to make prediction about the network bandwidth and select the most suitable video bitrate, as is presented in [7] and [8]. The hybrid method comprehensively utilizes the buffer occupancy information and the knowledge of the network bandwidth and then adopts some optimization methods such as model predictive control (MPC) for rate adaptation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

QoE-Oriented Rate Adaptation for DASH With Enhanced Deep Q-Learning

Liu

Tao

2019

IEEE Access

View full text Add to dashboard Cite

With the popularity of handheld devices, the development of wireless communication technology and the proliferation of multimedia resources, mobile video has become the main business in LTE networks with explosive traffic demands. How to improve the quality of experience (QoE) of mobile video in the dynamic and complex network environment has become a research focus. Dynamic adaptive streaming over HTTP technology introduces adaptive bitrate (ABR) requests at the client side to improve video QoE and various rate adaptation algorithms are also constantly proposed. In view of the limitations of the existing heuristic or learning-based ABR methods, we propose redirecting enhanced Deep Q-learning toward DASH video QoE (RDQ), a QoE-oriented rate adaptation framework based on enhanced deep Q-learning. First, we establish a chunkwise subjective QoE model and utilize it as the reward function in reinforcement learning so that the strategy can converge toward the direction of maximizing the subjective QoE score. Then, we apply several effective improvements of deep Q-learning to the RDQ agent's neural network architecture and learning mechanism to achieve faster convergence and higher average reward than other learning-based methods. The proposed RDQ agent has been thoroughly evaluated using trace-based simulation on the realtime LTE network data. For disparate network scenarios and different video contents, the RDQ agent can outperform the existing methods in terms of the QoE score. The breakdown analysis shows that RDQ can suppress the number and the duration of the stalling events to the minimum while maintaining high video bitrate, thus achieving better QoE performance than other methods.INDEX TERMS Quality of experience (QoE), dynamic adaptive streaming over HTTP (DASH), enhanced deep-Q learning, rate adaptation.

show abstract

Section: B Heuristic Abr Methodsmentioning

confidence: 99%

Section: A Improvements On Network Structurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

QoE-Oriented Rate Adaptation for DASH With Enhanced Deep Q-Learning

Liu

Tao

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In our testbed, DASH clients are running over a version of Ubuntu installed in Raspberry Pi 2 and standard net-books. The clients use GPAC 0.5.2-DEV-rev985 5 that we extend with well-known/recent adaptation algorithms such as BBA2 [15], FESTIVE [16], conventional (CONV) [16,20], and ARBITER [37]. BBA2 represents the class of buffer-based algorithms in which the quality selection mainly depends on the current buffer-level.…”

Section: Streaming Clientsmentioning

confidence: 99%

Asap

Zahran

Quinlan

Ramakrishnan

et al. 2018

ACM Trans. Multimedia Comput. Commun. Appl.

Self Cite

View full text Add to dashboard Cite

The dramatic growth of video traffic represents a practical challenge for cellular network operators in providing a consistent streaming Quality of Experience (QoE) to their users. Satisfying this objective has so-far proved elusive, due to the inherent characteristics of wireless networks and varying channel conditions as well as variability in the video bitrate that can degrade streaming performance. In this article, we propose stall-aware pacing as a novel MPEG DASH video traffic management solution that reduces playback stalls and seeks to maintain a consistent QoE for cellular users, even those with diverse channel conditions. These goals are achieved by leveraging both network and client state information to optimize the pacing of individual video flows. We evaluate the performance of two versions of stall-aware pacing techniques extensively, including stall-aware pacing (SAP) and adaptive stall-aware pacing (ASAP), using real video content and clients, operating over a simulated LTE network. We implement state-of-the-art client adaptation and traffic management strategies for direct comparisons with SAP and ASAP. Our results, using a heavily loaded base station, show that SAP reduces the number of stalls and the average stall duration per session by up to 95%. Additionally, SAP ensures that clients with good channel conditions do not dominate available wireless resources, evidenced by a reduction of up to 40% in the standard deviation of the QoE metric across clients. We also show that ASAP achieves additional performance gains by adaptively pacing video streams based on the application buffer state.

show abstract

“…In our testbed, DASH clients are running over a version of Ubuntu installed in Raspberry Pi 2 and standard net-books. The clients use GPAC 0.5.2-DEV-rev985 4 that we extend with well-known/recent adaptation algorithms such as BBA2 [14], FESTIVE [15], conventional (CONV) [15,16], and ARBITER [29]. BBA2 represents the class of buffer-based algorithms in which the quality selection mainly depends on the current buffer-level.…”

Section: Streaming Clientsmentioning

confidence: 99%

Sap

Zahran

Quinlan

Ramakrishnan

et al. 2017

Proceedings of the 8th ACM on Multimedia Systems Conference

Self Cite

View full text Add to dashboard Cite

The dramatic growth of cellular video traffic represents a practical challenge for cellular network operators in providing a consistent streaming Quality of Experience (QoE) to their users. Satisfying this objective has so-far proved elusive, due to the inherent system complexities that degrade streaming performance, such as variability in both video bitrate and network conditions. In this paper, we present SAP as a DASH video traffic management solution that reduces playback stalls and seeks to maintain a consistent QoE for cellular users, even those with diverse channel conditions. SAP achieves this by leveraging both network and client state information to optimize the pacing of individual video flows. We extensively evaluate SAP performance using real video content and clients, operating over a simulated LTE network. We implement state-of-the-art client adaptation and traffic management strategies for direct comparison. Our results, using a heavily loaded base station, show that SAP reduces the number of stalls and the average stall duration per session by up to 95%. Additionally, SAP ensures that clients with good channel conditions do not dominate available wireless resources, evidenced by a reduction of up to 40% in the standard deviation of the QoE metric.

show abstract

ARBITER: Adaptive rate-based intelligent HTTP streaming algorithm

Cited by 7 publications

References 15 publications

QoE-Oriented Rate Adaptation for DASH With Enhanced Deep Q-Learning

QoE-Oriented Rate Adaptation for DASH With Enhanced Deep Q-Learning

Asap

Sap

Contact Info

Product

Resources

About