Statistical characterization of a real video on demand service: User behaviour and streaming-media workload analysis

Garcı́a, Roberto; Pañeda, Xabiel G.; García, Víctor G.; Melendi, David; Vilas, Manuel

doi:10.1016/j.simpat.2007.02.004

Cited by 28 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The parameter set of case (a) leads to a workload variation which is different from case (b) and (c) and the buzzes are not easily identifiable here. Nonetheless, for all 3 configurations, the empirical means estimated from the 2 21 samples of the traces are in good agreement with the expected values of Eq. (3).…”

Section: Proposed Video On Demand (Vod) Modelsupporting

confidence: 81%

“…We reported the result in Table I. Particular realizations of these processes generated over 2 21 points are displayed in Fig. 2.…”

Section: Proposed Video On Demand (Vod) Modelmentioning

confidence: 99%

“…The box plots of Fig. 5 indicate for each estimated parameter (centered and normalized by the corresponding actual value) the sample median (red line), the inter-quartile range (blue box height) along with the extreme samples (whiskers) obtained from time series of length 2 21 points. As expected (from maximum likelihood), estimation of γ shows to be the most accurate, both in terms of bias and variance.…”

Section: B Numerical Validationmentioning

confidence: 99%

“…But it develops a long range memory which does not seem to match the dynamic feature of our real traces. In a distinct approach, server workloads have been thoroughly studied in many works, such as [18], [11], [19], [20] or [21]. These works, however, provide a statistical analysis of server workloads in context of usage pattern, caching, pre-fetching, or content distribution and do not focus primarily on workload modelling.…”

Section: Model Fitting To Real Workload Datamentioning

confidence: 99%

See 3 more Smart Citations

A complete framework for modelling and generating workload volatility of a VoD system

Roy

Begin

Gonçalvès

2013

2013 9th International Wireless Communications and Mobile Computing Conference (IWCMC)

View full text Add to dashboard Cite

Abstract-We propose a modelling framework, that can be used to reproduce the workload volatility of a Video on Demand (VoD) system. Based on numerical simulations, we evaluate the precision of the estimation procedure we derive to calibrate our parametric model. We also compare its performance to that of other existing models examining the goodness-of-fit of the steady state distribution and of the autocorrelation function of real workload traces. We then give each parameter of the model an interpretation in terms of the workload volatility, that enlightens on some origins of the system dynamics, like the users behaviour.

show abstract

Section: Proposed Video On Demand (Vod) Modelsupporting

confidence: 81%

“…We reported the result in Table I. Particular realizations of these processes generated over 2 21 points are displayed in Fig. 2.…”

Section: Proposed Video On Demand (Vod) Modelmentioning

confidence: 99%

Section: B Numerical Validationmentioning

confidence: 99%

Section: Model Fitting To Real Workload Datamentioning

confidence: 99%

See 2 more Smart Citations

A complete framework for modelling and generating workload volatility of a VoD system

Roy

Begin

Gonçalvès

2013

2013 9th International Wireless Communications and Mobile Computing Conference (IWCMC)

View full text Add to dashboard Cite

show abstract

“…Several works in the literature (e.g., [24][25][26][27][28]) analyze real streaming multimedia workloads to establish realistic simulation scenarios. These scenarios are organized with different parameters and functionalities as shown in Table 1.…”

Section: Scenario Characterization and Workloadsmentioning

confidence: 99%

Improving BitTorrent's Peer Selection for Multimedia Content On-Demand Delivery

Streit¹,

Rodrigues²

2015

IJCNC

View full text Add to dashboard Cite

The great efficiency achieved by the BitTorrent protocol for the distribution of large amounts of data inspired its adoption to provide multimedia content on-demand delivery over the Internet. As it is not designed for this purpose, some adjustments have been proposed in order to meet the related QoS requirements like low startup delay and smooth playback continuity. Accordingly, this paper introduces a BitTorrent-like proposal named as Quota-Based Peer Selection (QBPS). This proposal is mainly based on the adaptation of the original peer-selection policy of the BitTorrent protocol. Its validation is achieved by means of simulations and competitive analysis. The final results show that QBPS outperforms other recent proposals of the literature. For instance, it achieves a throughput optimization of up to 48.0% in lowprovision capacity scenarios where users are very interactive. KEYWORDSBitTorrent, Multimedia, Streaming, Video on Demand, Interactivity. 1.INTRODUCTIONThe fast growth of companies dedicated to provide multimedia content on-demand motivated studies focusing on maximizing the end-user experience. One potential solution identified by researchers (e.g., [1][2][3][4][5]) is the application of a Peer-to-Peer (P2P) network architecture to supply the demand for high-quality content distribution.The leading purpose of the above solution is to take advantage of the resources available at the edge of the network, addressing significant or even total autonomy from central servers. Plenty of practical P2P approaches, like the BitTorrent protocol [6], have been successful in the past years. In fact, the great efficiency achieved by BitTorrent for the distribution of large amounts of data inspired its adoption for on-demand video streaming [7][8][9].Peer-Selection Policy is the term assigned to one of the core concepts of BitTorrent. By stimulating direct reciprocity and cooperation, its design specifies who makes use of the uplink capacity from all the peers inside the swarm (i.e., a group of peers downloading a same content). One observed outcome of this policy is that in a heterogeneous system, i.e., where users have different bandwidth capacities, peers with higher upload capacities typically have higher download speeds than slower peers [7].However, one essential understanding is that peers receiving a multimedia stream do not need a download rate higher than the playback rate of the media file. Rigorously, all they need is a policy that makes the whole system efficiently allocate its total upload/download capacity so that all of its participants may be served satisfactorily.International Journal of Computer Networks & Communications (IJCNC) Vol.7, No.6, November 2015 112 Streaming using BitTorrent thus deserves particular concerns focused on the Peer-Selection Policy's concept in order to fulfill QoS requirements like low start up delay and smooth playback continuity. Despite the relevance of the matter, an efficient algorithm capable of equally sharing peers' upload bandwidth among fast and slo...

show abstract