Predicting packet loss statistics with hidden Markov models for FEC control

Media streaming applications often try to cope with packet losses using end-to-end recovery mechanisms like FEC. Predicting future losses is critical to choose the proper amount of redundancy needed to recover data. We propose a hierarchical model where the short-term dynamics of losses is driven by 2-state Markov chains while longer-term network changes (e.g., congestion) are modeled by a HMM. Based on this model, we develop two adaptive algorithms that predict future loss statistics and dynamically adjust FEC parameters. First, we predict loss rates and use these estimates to tune redundancy in Reed-Solomon codes. Second, we predict both loss rate and burstiness to select the optimal scheme among a set of parity-based FEC schemes. We perform experiments with packet loss traces to evaluate these algorithms, and compare their performance to standard approaches of FEC selection. Our results show that HMM-based prediction is more effective than other approaches, achieving higher quality improvements with small transmission overhead.

[1]  Donald F. Towsley,et al.  Continuous-time hidden Markov models for network performance evaluation , 2002, Perform. Evaluation.

[2]  Nobuhiko Kitawaki,et al.  Perceptual QoS assessment technologies for VoIP , 2004, IEEE Communications Magazine.

[3]  Yali Zhu,et al.  A simulation-based methodology and tool for automating the modeling and analysis of voice-over-IP perceptual quality , 2003, Perform. Evaluation.

[4]  Elwyn R. Berlekamp,et al.  Algebraic coding theory , 1984, McGraw-Hill series in systems science.

[5]  Kuan-Ta Chen,et al.  Tuning Skype's Redundancy Control Algorithm for User Satisfaction , 2009, IEEE INFOCOM 2009.

[6]  Donald F. Towsley,et al.  An adaptive FEC algorithm using hidden Markov chains , 2003, PERV.

[7]  Yoram Singer,et al.  The Hierarchical Hidden Markov Model: Analysis and Applications , 1998, Machine Learning.

[8]  Kavé Salamatian,et al.  Hidden Markov modeling for network communication channels , 2001, SIGMETRICS '01.

[9]  Mark Handley,et al.  RTP Payload for Redundant Audio Data , 1997, RFC.

[10]  Donald F. Towsley,et al.  Modeling frame-level errors in GSM wireless channels , 2002, Global Telecommunications Conference, 2002. GLOBECOM '02. IEEE.

[11]  Alain Jean-Marie,et al.  On the compromise between burstiness and frequency of events , 2005, Perform. Evaluation.

[12]  V. Hardman,et al.  A survey of packet loss recovery techniques for streaming audio , 1998, IEEE Network.

[13]  Fernando Silveira,et al.  Modeling the short-term dynamics of packet losses , 2006, PERV.

[14]  Henning Schulzrinne,et al.  An RTP Payload Format for Generic Forward Error Correction , 1999, RFC.

[15]  Roch Guérin,et al.  On-line estimation of internet path performance: an application perspective , 2004, IEEE INFOCOM 2004.

[16]  Edmundo de Souza e Silva,et al.  QRPp1-6: Adaptive Forward Error Correction for Interactive Streaming Over the Internet , 2006, IEEE Globecom 2006.

[17]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[18]  Edmundo de Souza e Silva,et al.  Efficient mechanisms for recovering voice packets in the Internet , 1999, Seamless Interconnection for Universal Services. Global Telecommunications Conference. GLOBECOM'99. (Cat. No.99CH37042).

[19]  Xusheng Tian,et al.  The accuracy of Gilbert models in predicting packet-loss statistics for a single-multiplexer network model , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[20]  Fernando Silveira,et al.  Predicting packet loss statistics with hidden Markov models , 2007, PERV.

[21]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[22]  Donald F. Towsley,et al.  Measurement and modelling of the temporal dependence in packet loss , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[23]  Donald F. Towsley,et al.  Adaptive FEC-based error control for Internet telephony , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).