Cross-Layer Effects on Training Neural Algorithms for Video Streaming

Pereira, Pablo Gil; Schmidt, Andreas; Herfet, Thorsten

doi:10.1145/3210445.3210453

Cited by 11 publications

(4 citation statements)

References 16 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several papers have reported issues with Pensieve , hence we conducted a comprehensive experimental evaluation of Pensive, using different sets of video content and network traces. For lack of space, we only present the summary of our finding here, for that were not reported in the literature (for more details on other issues please refer to [5]). :…”

Section: Background and Motivationmentioning

confidence: 99%

SMASH: A Supervised Machine Learning Approach to Adaptive Video Streaming over HTTP

Sani

Raca

Quinlan

et al. 2020

2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX)

View full text Add to dashboard Cite

The growth of online video-on-demand consumption continues unabated. Existing heuristic-based adaptive bitrate (ABR) selection algorithms are typically designed to optimise video quality within a very narrow context. This may lead to video streaming providers implementing different ABR algorithms/players, based on a network connection, device capabilities, video content, etc., in order to serve the multitude of their users' streaming requirements.In this paper, we present SMASH: a Supervised Machine learning approach to Adaptive Streaming over HTTP, which takes a tentative step towards the goal of a one-size-fits-all approach to ABR. We utilise the streaming output from the adaptation logic of nine ABR algorithms across a variety of streaming scenarios (generating nearly one million records) and design a machine learning model, using systematically selected features, to predict the optimal choice of the bitrate of the next video segment to download. Our evaluation results show that not only does SMASH guarantee a high QoE but its performance is consistent across a variety of streaming contexts.

show abstract

Section: Background and Motivationmentioning

confidence: 99%

SMASH: A Supervised Machine Learning Approach to Adaptive Video Streaming over HTTP

Sani

Raca

Quinlan

et al. 2020

2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX)

View full text Add to dashboard Cite

show abstract

“…The details of selected ABR baselines are described in §6.1. We use EnvivoDash3, a widely used [6,28,36,51] reference video clip [1] and QoE v to measure the ABR performance.…”

Section: Comyco Vs Abr Schemesmentioning

confidence: 99%

“…Recall that the key principle of RL-based method is to maximize reward of each action taken by the agent in given states per step, since the agent doesn't really know the optimal strategy [45]. However, recent work [6,18,28,36,43,51] has demonstrated that the ABR process can be precisely emulated by an offline virtual player ( §6.1) with complete future network information. What's more, by taking several steps ahead, we can further accurately estimate the near-optimal expert policy of any ABR state within an acceptable time ( §4.2).…”

Section: Training Abrs Via Imitation Learningmentioning

confidence: 99%

See 1 more Smart Citation

Comyco: Quality-Aware Adaptive Video Streaming via Imitation Learning

Huang

Zhou

Zhang

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Learning-based Adaptive Bit Rate (ABR) method, aiming to learn outstanding strategies without any presumptions, has become one of the research hotspots for adaptive streaming. However, it is still suffering from several issues, i.e., low sample efficiency and lack of awareness of the video quality information. In this paper, we propose Comyco, a video quality-aware ABR approach that enormously improves the learning-based methods by tackling the above issues. Comyco trains the policy via imitating expert trajectories given by the instant solver, which can not only avoid redundant exploration but also make better use of the collected samples. Meanwhile, Comyco attempts to pick the chunk with higher perceptual video qualities rather than video bitrates. To achieve this, we construct Comyco's neural network architecture, video datasets and QoE metrics with video quality features. Using trace-driven and real world experiments, we demonstrate significant improvements of Comyco's sample efficiency in comparison to prior work, with 1700x improvements in terms of the number of samples required and 16x improvements on training time required. Moreover, results illustrate that Comyco outperforms previously proposed methods, with the improvements on average QoE of 7.5% -16.79%. Especially, Comyco also surpasses state-of-the-art approach Pensieve by 7.37% on average video quality under the same rebuffering time.

show abstract

DeepSHARQ: hybrid error coding using deep learning

Pereira

Vogelgesang

Miodek

et al. 2023

J Reliable Intell Environ

View full text Add to dashboard Cite

Cyber-physical systems operate under changing environments and on resource-constrained devices. Communication in these environments must use hybrid error coding, as pure pro- or reactive schemes cannot always fulfill application demands or have suboptimal performance. However, finding optimal coding configurations that fulfill application constraints—e.g., tolerate loss and delay—under changing channel conditions is a computationally challenging task. Recently, the systems community has started addressing these sorts of problems using hybrid decomposed solutions, i.e., algorithmic approaches for well-understood formalized parts of the problem and learning-based approaches for parts that must be estimated (either for reasons of uncertainty or computational intractability). For DeepSHARQ, we revisit our own recent work and limit the learning problem to block length prediction, the major contributor to inference time (and its variation) when searching for hybrid error coding configurations. The remaining parameters are found algorithmically, and hence we make individual contributions with respect to finding close-to-optimal coding configurations in both of these areas—combining them into a hybrid solution. DeepSHARQ applies block length regularization in order to reduce the neural networks in comparison to purely learning-based solutions. The hybrid solution is nearly optimal concerning the channel efficiency of coding configurations it generates, as it is trained so deviations from the optimum are upper bound by a configurable percentage. In addition, DeepSHARQ is capable of reacting to channel changes in real time, thereby enabling cyber-physical systems even on resource-constrained platforms. Tightly integrating algorithmic and learning-based approaches allows DeepSHARQ to react to channel changes faster and with a more predictable time than solutions that rely only on either of the two approaches.

show abstract

Cross-Layer Effects on Training Neural Algorithms for Video Streaming

Cited by 11 publications

References 16 publications

SMASH: A Supervised Machine Learning Approach to Adaptive Video Streaming over HTTP

SMASH: A Supervised Machine Learning Approach to Adaptive Video Streaming over HTTP

Comyco: Quality-Aware Adaptive Video Streaming via Imitation Learning

DeepSHARQ: hybrid error coding using deep learning

Contact Info

Product

Resources

About