Control of real-time multimedia applications in best-effort networks

摘要

The increasing demand for real-time multimedia applications and the lackof quality of service (QoS) support in public best-effort or Internet Protocol (IP)networks has prompted many researchers to propose improvements on the QoS of suchnetworks. This research aims to improve the QoS of real-time multimedia applicationsin public best-effort networks, without modifying the core network infrastructure orthe existing codecs of the original media applications.A source buffering control is studied based on a fluid model developed for a singleflow transported over a best-effort network while allowing for flow reversal. It is shownthat this control is effective for QoS improvement only when there is sufficient flowreversal or packet reordering in the network.An alternate control strategy based on predictive multi-path switching is studiedwhere only two paths are considered as alternate options. Initially, an emulation studyis performed, exploring the impact of path loss rate and traffic delay signal frequencycontent on the proposed control. The study reveals that this control strategy providesthe best QoS improvement when the average comprehensive loss rates of the two pathsinvolved are between 5% and 15%, and when the delay signal frequency content isaround 0.5 Hz. Linear and nonlinear predictors are developed using actual networkdata for use in predictive multi-path switching control. The control results showthat predictive path switching is better than no path switching, yet no one predictor developed is best for all cases studied. A voting based control strategy is proposedto overcome this problem. The results show that the voting based control strategyresults in better performance for all cases studied. An actual voice quality test isperformed, proving that predictive path switching is better than no path switching.Despite the improvements obtained, predictive path switching control has somescalability problems and other shortcomings that require further investigation. Ifthere are more paths available to choose from, the increasing overhead in probingtraffic might become unacceptable. Further, if most of the VoIP flows on the Internetuse this control strategy, then the conclusions of this research might be different,requiring modifications to the proposed approach. Further studies on these problemsare needed.