Autonomic QoS Optimization of Real-Time Internet Audio Using Loss Prediction and Stochastic Control

Abstract

Quality of Internet audio is highly sensitive to packet loss caused by congestion in links. Packet loss for audio is normally rectified by adding redundancy using Forward Error Correction (FEC). Alternatively, path diversity mechanisms are used to improve reliability and thus session quality. To achieve optimized receiver audio quality for transmissions using single or multiple paths, the authors propose a self-adaptive joint Error and Rate Control framework based on packet loss prediction and on-line quality assessment. The Error Control chooses appropriate FEC proactively to preserve quality with optimal bandwidth, using a Markov Decision Process (MDP) and a stochastic inventory control, a novel approach for multimedia error recovery. The Rate Control uses a quality optimization model to determine the optimal dispersion over single or multiple paths. This paper will present results using simulation and Internet experiments to show the superiority of this mechanism over other similar techniques.

Survey on application-layer mechanisms for speech quality adaptation in VoIP

“…Another approach, taken by Jung and Ibanez [2010], is to characterize the packet loss behavior within a gap or a burst state and apply the most suitable redundancy level accordingly. One more elaborate packet-loss-related approach was taken by Roychoudhuri and Al-Shaer [2008], which not only tracks the PLB, but also tries to predict packet loss due to congestion based on variations of inter-packet gap and end-to-end delay, and near history of these observations.…”

“…For example, codec switching is also employed by the adaptive mechanism of Mazurczyk and Kotulski [2007]; multirate encoding adaptation is employed by Abreu-Sernandez and Garcia-Mateo [2000], Bolot and Vega-García [1996], Huang et al [2005], Matta et al [2003], and Roychoudhuri and Al-Shaer [2008]; and packetization adjustment is adopted by Manousos et al [2005].…”