Resource Prediction for Admission Control of Interactive Multimedia Sessions

Abstract Interactive multimedia sessions have uncertain, varying consumption rates due to users' interactive behavior. In this paper, wepropose two approaches for prediction of consumption rates required for admission control. They differ in the assumptions ofthe available knowledge: The observation-based approach predicts the future consumption from the past system behavior. Thestochastical approach requires a user behavior model from which the prediction is deduced. We discuss the pros and cons ofthe two approaches with respect to available information sources, accuracy of prediction, and suitable scenarios. Keywords: interactive multimedia applications, user modeling, predictive service 1 Motivation In highly interactive applications a user controls the course of a running session in terms of which media(-combinations)will bepresentedat what time. Such applicationsplay a keyrolein domainslike homeentertainment(e.g., news-on-demand, interactive VoD, action games), home shopping (e.g., product catalogs), education andtraining (e.g., interactive computer-based training - CBT), tourist information (e.g., virtual travel guides), andmultimedia production (e.g., video editing).Multimedia systems have to provide mechanisms that are able to deal with the special characteristics of suchapplications to enforce QoS parameters like continuous playout of media data and low start-up latency betweentwo subsequent media presentations. To achieve the required QoS, the clients compete for limited resources onthe server. Resource management for multimedia applications is a classical problem of research in the area ofdistributed multimedia systems. An admission control mechanism usually checks at the server if enough resourcesare available for the adequate delivery of data to a new request, given the current set of admitted clients.Figure 1 classifies related work on admission control by the reservation duration

[1]  Rajeev Rastogi,et al.  The Fellini Multimedia Storage Server , 1996 .

[2]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Gerald W. Neufeld,et al.  An evaluation of VBR disk admission algorithms for continuous media file servers , 1997, MULTIMEDIA '97.

[4]  Leonard Kleinrock,et al.  Queueing Systems: Volume I-Theory , 1975 .

[5]  A. L. Narasimha Reddy.  Improving latency in an interactive video server , 1997, Electronic Imaging.

[6]  Prathima Agrawal,et al.  Use of statistical methods to reduce delays for media playback buffering , 1998, Proceedings. IEEE International Conference on Multimedia Computing and Systems (Cat. No.98TB100241).

[7]  K. Selçuk Candan,et al.  Management and Rendering of Multimedia Views , 1998, Multimedia Information Systems.

[8]  Raymond Ng,et al.  Statistical Modeling and Buffer Allocation for Mpeg Streams , 1996 .

[9]  Karl Aberer,et al.  An Admission Control Framework for Applications with Variable Consumption Rates in Client-Pull Architectures , 1998, Multimedia Information Systems.

[10]  Ulrich Thiel,et al.  Concept-based browsing in video libraries , 1999, Proceedings IEEE Forum on Research and Technology Advances in Digital Libraries.

[11]  Harrick M. Vin,et al.  An observation-based admission control algorithm for multimedia servers , 1994, 1994 Proceedings of IEEE International Conference on Multimedia Computing and Systems.

[12]  Edward W. Knightly,et al.  RED-VBR: a renegotiation-based approach to support delay-sensitive VBR video , 1997, Multimedia Systems.

[13]  Karl Aberer,et al.  Stochastic resource prediction and admission for interactive sessions on multimedia servers , 2000, ACM Multimedia.

[14]  Gerhard Weikum,et al.  Vertical Data Migration in Large Near-Line Document Archives Based on Markov-Chain Predictions , 1997, VLDB.

[15]  Gultekin Özsoyoglu,et al.  Delivering presentations from multimedia servers , 1998, The VLDB Journal.

[16]  Karl Aberer,et al.  Gmd Report 40 Resource Prediction and Admission Control for Interactive Video Browsing Scenarios Using Application Semantics , 1999 .