MPEG-4 Internet Traffic Estimation Using Recurrent CGPANN

  • Gul Muhammad Khan
  • Fahad Ullah
  • Sahibzada Ali Mahmud
Part of the Communications in Computer and Information Science book series (CCIS, volume 383)

Abstract

Stretching across the horizon of data communication and networking, in almost every scenario, accurate bandwidth allocation has been a challenging problem. From simple online video streaming to the sophisticated communication network underlying a Smart Grid, efficient management of bandwidth is always desired. One way to achieve such efficiency lies in the science of predication: an intelligent system can be deployed that can estimate the sizes of upcoming data packets by analyzing patterns in the previously received data. This paper presents such a system that implements a fast and robust Neuro-Evolutionary algorithm known as Recurrent-Cartesian Genetic Programming evolved Artificial Neural Network (R-CGPANN). Based on the previously received 10 MPEG-4 video frames, the system estimates the size of the next frame. The simulation results show that the recurrence in CGPANN measurably outperform not only the feed forward version of the said algorithm but other contemporary methods in the field.

Keywords

Neuro-Evolution frame estimation recurrent neural networks bandwidth management Cartesian Genetic Programming 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ullah, F., Khan, G.M., Mahmud, S.A.: Intelligent Bandwidth Management Using Fast Learning Neural Networks. In: 9th International Conference on High Performance Computing and Communication (HPCC-ICESS), pp. 867–872 (June 2012)Google Scholar
  2. 2.
    Yao, X.: Evolving Artificial Neural Networks. Proc. IEEE 87, 1423–1447 (1999)CrossRefGoogle Scholar
  3. 3.
    Gomez, F., Schmidhuber, J., Miikkulainen, R.: Accelerated Neural Evolution Through Cooperatively Coevolved Synapses. J. Mach. Learn. Res. 9, 937–965 (2008)MathSciNetMATHGoogle Scholar
  4. 4.
    Moriarty, D.: Symbiotic Evolution of Neural Networks in Sequential Decision Tasks. PhD thesis, University of Texas at Austin, Tech Rep. UT-A197-257 (1997)Google Scholar
  5. 5.
    Polani, D., Miikkulainen, R.: Eugenic Neuro-Evolution for Reinforcement Learning. In: GECCO, pp. 1041–1046 (2000)Google Scholar
  6. 6.
    Stanley, K.O., Miikkulainen, R.: Efficient reinforcement learning through evolving neural networks topologies. In: GECCO 2002 (2002)Google Scholar
  7. 7.
    Mayer, A., Mayer, H.A.: Multi-Chromosomal Representation in NeuroEvolution. In: Computations Intelligence Conference (2006)Google Scholar
  8. 8.
    Takagi, H.: Interactive Evolutionary Computation: Fusion of the Capabilities of EC Optimization and Human Evaluation. Proc. of the IEEE 89(9), 1275–1296 (2001)CrossRefGoogle Scholar
  9. 9.
    Schmidhuber, J., Wierstra, D., Gomez, F.: Evolino: Hybrid Neuroevolution Optimal Linear Search for Sequence Prediction. In: 19th Int. Conf. on Artificial Intelligence (2005)Google Scholar
  10. 10.
    Tseng, Y.H., Wu, E.H.-K., Chen, G.H.: Scene-Change Aware Dynamic Bandwidth Allocation for Real-Time VBR Video Transmission Over IEEE 802.15.3 Wireless Home Networks. IEEE Transactions on Multimedia 9(3), 642–654 (2007)CrossRefGoogle Scholar
  11. 11.
    Kuo, W.K., Lien, S.Y.: Dynamic resource allocation for supporting real-time multimedia applications in IEEE 802.15.3 WPANs. IET Com. 3(1), 1–9 (2009)CrossRefGoogle Scholar
  12. 12.
    Adas, A.M.: Using adaptive linear prediction to support real-time VBR video under RCBR network service model. IEEE Trans. on Networking 6(5), 635–644 (1998)CrossRefGoogle Scholar
  13. 13.
    Lanfranchi, L.I., Bing, B.K.: MPEG-4 Bandwidth Prediction for Broadband Cable Networks. IEEE Transactions on Broadcasting 54(4), 741–751 (2008)CrossRefGoogle Scholar
  14. 14.
    Mangharam, R., Demirhan, M., Rajkumar, R., Raychaudhuri, D.: Size matters: Size-Based Scheduling for MEPG-4 over wireless channels. In: SPIE & ACM Proceedings in Multimedia Computing and Networking, vol. 3020, pp. 110–122 (January 2004)Google Scholar
  15. 15.
    Doulamis, A.D., Doulamis, N.D., Kollias, S.D.: An adaptable neural-network model for recursive nonlinear traffic prediction and modeling of MPEG video sources. IEEE Transactions on Neural Networks 14(1), 150–166 (2003)CrossRefGoogle Scholar
  16. 16.
    Park, D.-C., Tran, C.N., Song, Y.-S., Lee, Y.: Prediction of MPEG video source traffic using biLinear recurrent neural networks. In: Yang, Q., Webb, G. (eds.) PRICAI 2006. LNCS (LNAI), vol. 4099, pp. 298–307. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  17. 17.
    Aninda, B., Parlos, A.G., Amir, A.F.: Prediction of MPEG-coded video source traffic using recurrent neural networks. IEEE Trans. Signal Processing 51(8), 2177–2190 (2003)CrossRefGoogle Scholar
  18. 18.
    Jibukumar, M.G., Datta, R., Kumar, P.: Kalman filter based Variable Bit Rate video frame size prediction. In: 3rd Int. Symp. on Wireless Pervasive Computing, pp. 459–463 (May 2008)Google Scholar
  19. 19.
    Trlin, G.: VBR video frame size prediction using seasonal ARIMA. In: 20th Int. Conference on Software, Telecommunication and Computer Networks (SoftCOM), pp. 1–5 (September 2012)Google Scholar
  20. 20.
    Miller, J.F., Thomson, P.: Cartesian Genetic Programming. In: EuroGP, pp. 121–132 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Gul Muhammad Khan
    • 1
  • Fahad Ullah
    • 1
  • Sahibzada Ali Mahmud
    • 1
  1. 1.Department of Electrical EngineeringUET PeshawarPakistan

Personalised recommendations