QoE-driven in-network optimization for Adaptive Video Streaming based on packet sampling measurements

Bouten, Niels; Schmidt, Ricardo de O.; Famaey, Jeroen; Latré, Steven; Pras, Aiko; Turck, Filip De

doi:10.1016/j.comnet.2015.02.007

Cited by 30 publications

(19 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Others have proposed network-assisted quality selection for HAS clients based on network-based monitoring [8], or used measurements to model and characterize user satisfaction when using online services [38].…”

Section: Related Workmentioning

confidence: 99%

Buffest

Krishnamoorthi

Carlsson

Halepovic

et al. 2017

Proceedings of the 8th ACM on Multimedia Systems Conference

View full text Add to dashboard Cite

Stalls during video playback are perhaps the most important indicator of a client's viewing experience. To provide the best possible service, a proactive network operator may therefore want to know the bufer conditions of streaming clients and use this information to help avoid stalls due to empty bufers. However, estimation of clients' bufer conditions is complicated by most streaming services being rate-adaptive, and many of them also encrypted. Rate adaptation reduces the correlation between network throughput and client bufer conditions. Usage of HTTPS prevents operators from observing information related to video chunk requests, such as indications of rate adaptation or other HTTP-level information.This paper presents BUFFEST, a novel classiication framework that can be used to classify and predict streaming clients' bufer conditions from both HTTP and HTTPS traic. To illustrate the tradeofs between prediction accuracy and the available information used by classiiers, we design and evaluate classiiers of diferent complexity. At the core of BUFFEST is an event-based bufer emulator module for detailed analysis of clients' bufer levels throughout a streaming session, as well as for automated training and evaluation of online packet-level classiiers. We then present example results using simple threshold-based classiiers and machine learning classiiers that only use TCP/IP packet-level information. Our results are encouraging and show that BUFFEST can distinguish streaming clients with low bufer conditions from clients with signiicant bufer margin during a session even when HTTPS is used.

show abstract

Section: Related Workmentioning

confidence: 99%

Buffest

Krishnamoorthi

Carlsson

Halepovic

et al. 2017

Proceedings of the 8th ACM on Multimedia Systems Conference

View full text Add to dashboard Cite

show abstract

“…Therefore, quite often, developers propose hybrid solutions, where the throughput prediction is only part of them. In [19], the authors propose to deploy in-network quality optimization agents, which should monitor the available throughput using sampling-based measurement techniques and optimize the quality of each client, based on throughput prediction. For the prediction, the authors employed an autoregressive model, a support vector regression and ANNs.…”

Section: Related Workmentioning

confidence: 99%

“…The adjustment of prediction results of the RAE is supported by the z-NN as the output of RAE is modified and takes form The training of z-NN aims at minimization of the prediction error of the whole RDF network by adjusting the weight parameters of z-NN. To train the RAE network, the optimization objective is to minimize both the reconstruction error (19) of the RAE and the RPE (9). After this process, the output x t of the trained RAE is used as a parameter of the training process of z-NN.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Traffic prediction methods for quality improvement of adaptive video

Biernacki

2017

Multimedia Systems

View full text Add to dashboard Cite

During the past years, adaptive video based on HTTP has become very popular. Streaming of the adaptive video relies heavily on an estimation of end-to-end network throughput, which can be challenging especially in mobile networks, where the capacity highly fluctuates. In this work, we propose to predict the network throughput using its past measurements. As the analysis shows, the network throughput forms a long range-dependent process; thus, for the throughput prediction, we apply a fractional ARIMA process and artificial neural networks. Our approach does not require any modifications to the network infrastructure or the TCP stack. The predictions are performed for data traces obtained from measurements of throughput of a real mobile network. As the experiment shows, the obtained traffic models are able to enhance the performance of an adaptive streaming algorithm. Compared to the throughput predictors employed in contemporary systems dedicated to adaptive video streaming, the proposed technique obtains better results when taking into account effectiveness of network capacity utilisation and stability of video play-out.

show abstract

“…Bouten et al propose to introduce intelligence in the network that steers the client's local quality decisions, by modifying the announced adaptation set [13], [14]. Using HAS aware network elements, video quality levels are assigned to specific clients subject to their respective subscription terms, improving fairness among users while still allowing them to adapt to dynamic network changes [15].…”

Section: Related Work a Http Adaptive Streamingmentioning

confidence: 99%

An HTTP/2 push-based approach for SVC adaptive streaming

Hooft

Petrangeli

Bouten

et al. 2016

NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium

Self Cite

View full text Add to dashboard Cite

Abstract-HTTP Adaptive Streaming (HAS) is the de facto standard for over-the-top video streaming. In HAS, video content is encoded at multiple quality levels and temporally divided into multiple segments. The client can select the quality level for every video segment, allowing smoother playback and a better Quality of Experience (QoE). Although results are promising, current solutions often suffer from high round-trip time (RTT) cycles in mobile networks. This is especially true for scalable video coding (SVC), where multiple requests are required to retrieve a single video segment. Meanwhile, the IETF has standardized the HTTP/2 protocol since February 2015, providing new features that allow a reduction of the page load time in web browsing. In this paper, we propose a novel approach based on HTTP/2's server push feature to actively push the base layer of live, SVCencoded content from server to client. This allows to eliminate one RTT cycle for every video segment, which has a significant impact on the user's QoE. Evaluating the proposed approach, we show that compared with HTTP/1.1, an improvement of 65.42% can be achieved for the average video quality in high-RTT networks. Compared to an AVC-based solution, the freeze frequency and duration are reduced by 54.55% and 53.06% respectively, while the loss in video quality is limited to 4.51%. Since playout freezes should be avoided at the cost of a lower video quality, we conclude that the proposed approach beneficially impacts the user's QoE.

show abstract

QoE-driven in-network optimization for Adaptive Video Streaming based on packet sampling measurements

Cited by 30 publications

References 50 publications

Buffest

Buffest

Traffic prediction methods for quality improvement of adaptive video

An HTTP/2 push-based approach for SVC adaptive streaming

Contact Info

Product

Resources

About