Adaptive audio streaming in mobile ad hoc networks using neural networks

We design a transport protocol that uses artificial neural networks (ANNs) to adapt the audio transmission rate to changing conditions in a mobile ad hoc network. The response variables of throughput, end-to-end delay, and jitter are examined. For each, statistically significant factors and interactions are identified and used in the ANN design. The efficacy of different ANN topologies are evaluated for their predictive accuracy. The Audio Rate Cognition (ARC) protocol incorporates the ANN topology that appears to be the most effective into the end-points of a (multi-hop) flow, using it to adapt its transmission rate. Compared to competing protocols for media streaming, ARC achieves a significant reduction in packet loss and increased goodput while satisfying the requirements of end-to-end delay and jitter. While the average throughput of ARC is less than that of TFRC, its average goodput is much higher. As a result, ARC transmits higher quality audio, minimizing root mean square and Itakura-Saito spectral distances, as well as several parametric distance measures. In particular, ARC minimizes linear predictive coding cepstral (sic) distance, which closely correlates to subjective audio measures.

[1]  Charles E. Perkins,et al.  Ad-hoc on-demand distance vector routing , 1999, Proceedings WMCSA'99. Second IEEE Workshop on Mobile Computing Systems and Applications.

[2]  Donald F. Towsley,et al.  Modeling TCP throughput: a simple model and its empirical validation , 1998, SIGCOMM '98.

[3]  Francis Lepage,et al.  Analysing End-to-End Packet Delay and Loss in mobile ad hoc networks for interactive audio applications , 2003 .

[4]  Madhav V. Marathe,et al.  Characterizing the interaction between routing and MAC protocols in ad-hoc networks , 2002, MobiHoc '02.

[5]  Violet R. Syrotiuk,et al.  Anova-Informed Decision Trees for Voice Applications Overmanets , 2004, MWCN.

[6]  Shivkumar Kalyanaraman,et al.  Route fragility: a novel metric for route selection in mobile ad hoc networks , 2003, The 11th IEEE International Conference on Networks, 2003. ICON2003..

[7]  Douglas M. Bates,et al.  Nonlinear Regression Analysis and Its Applications , 1988 .

[8]  Michael D. Colagrosso,et al.  Intelligent Broadcasting in Mobile Ad Hoc Networks: Three Classes of Adaptive Protocols , 2007, EURASIP J. Wirel. Commun. Netw..

[9]  Klara Nahrstedt,et al.  Limitations of equation-based congestion control in mobile ad hoc networks , 2004, 24th International Conference on Distributed Computing Systems Workshops, 2004. Proceedings..

[10]  Songwu Lu,et al.  A transport protocol for supporting multimedia streaming in mobile ad hoc networks , 2003, IEEE J. Sel. Areas Commun..

[11]  Mark Handley,et al.  RFC 5348: TCP Friendly Rate Control (TFRC): Protocol Specification , 2008 .

[12]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[13]  Leslie Pack Kaelbling,et al.  Mobilized ad-hoc networks: a reinforcement learning approach , 2004 .

[14]  Vittorio Maniezzo,et al.  Genetic evolution of the topology and weight distribution of neural networks , 1994, IEEE Trans. Neural Networks.

[15]  András Faragó,et al.  Meta-MAC protocols: automatic combination of MAC protocols to optimize performance for unknown conditions , 2000, IEEE Journal on Selected Areas in Communications.

[16]  Louis C. W. Pols,et al.  A distant measure for objective quality evaluation of speech communication channels using also dynamic spectural features , 1996 .

[17]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[18]  Jim Dowling,et al.  Using feedback in collaborative reinforcement learning to adaptively optimize MANET routing , 2005, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[19]  Peter D. Welch,et al.  Response surface methodology and its application in simulation , 1993, WSC '93.

[20]  Sathya Narayanan,et al.  MRTP: a multiflow realtime transport protocol for ad hoc networks , 2003, 2003 IEEE 58th Vehicular Technology Conference. VTC 2003-Fall (IEEE Cat. No.03CH37484).

[21]  R. H. Myers,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[22]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[23]  David B. Johnson,et al.  Routing in Ad Hoc Networks of Mobile Hosts , 1994, 1994 First Workshop on Mobile Computing Systems and Applications.

[24]  Tracy Camp,et al.  Stationary distributions for the random waypoint mobility model , 2004, IEEE Transactions on Mobile Computing.

[25]  Violet R. Syrotiuk,et al.  Factor interaction on service delivery in mobile ad hoc networks , 2004, IEEE Journal on Selected Areas in Communications.

[26]  Manthos Kazantzidis.  MAC intelligence for adaptive multimedia in 802.11 networks , 2005, IEEE Journal on Selected Areas in Communications.

[27]  Frank H. P. Fitzek,et al.  Voice quality evaluation in wireless packet communication systems: a tutorial and performance results for RHC , 2005, IEEE Wireless Communications.

[28]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[29]  André I. Khuri,et al.  Response surface methodology: 1966–1988 , 1989 .

[30]  Charles B. Owen,et al.  Factors affecting the performance of ad hoc networks , 2002, 2002 IEEE International Conference on Communications. Conference Proceedings. ICC 2002 (Cat. No.02CH37333).

[31]  Aravind Srinivasan,et al.  Scalable resilient media streaming , 2004, NOSSDAV '04.

[32]  Jon Postel,et al.  User Datagram Protocol , 1980, RFC.

[33]  Michael D. Colagrosso,et al.  A classification approach to broadcasting in mobile ad hoc network , 2005, IEEE International Conference on Communications, 2005. ICC 2005. 2005.

[34]  Henning Schulzrinne,et al.  RTP: A Transport Protocol for Real-Time Applications , 1996, RFC.

[35]  G. Velev,et al.  TCP-friendly streaming in next generation wireless networks , 2004, First IEEE Consumer Communications and Networking Conference, 2004. CCNC 2004..