Using Bayesian Belief Networks for Burst Detection in Ethernet Passive Optical Networks

Naghmeh Moradpoor, Abul Bashar, Gerard Parr, Sally McClean, Bryan Scotney, G Owusu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The Ethernet Passive Optical Networks (EPONs) have been considered as a promising candidate for the next generation wired access networks for quite some time. In EPONs bandwidth requests and bandwidth allocations are critical issues which need to be addressed efficiently in order to guarantee the End-to-End (ETE) Quality of Service (QoS) for diverse classes of services. In this paper, we discuss the application of a statistical prediction technique based on the Bayesian Belief Networks (BBNs) which provides real-time decision support to the EPONs Dynamic Bandwidth Allocation (DBA) function. We show that in situations of burst traffic it helps the DBA to predict additional bandwidth requirements.
Original languageEnglish
Title of host publicationUnknown Host Publication
PublisherIEEE
Number of pages5
Publication statusPublished (in print/issue) - May 2011
EventInternational Conference on Wireless and Optical Communications - Zhengzhou, China
Duration: 1 May 2011 → …

Conference

ConferenceInternational Conference on Wireless and Optical Communications
Period1/05/11 → …

Bibliographical note

Reference text: [1] HUGIN Lite 6.9, available at: www.hugin.com.
[2] OPNET Modeler 16.0, available at: www.opnet.com
[3] G.Kramer et al., "EPON: Building a Next-Generation Optical Access Network", IEEE Communications Magazine, 66-73, Feb 2002.
[4] N. Moradpoor et al., "Simulation and Performance Evaluation of Bandwidth Allocation Algorithms for Ethernet Passive Optical Networks", OPNETWORK2010.
[5] C.Chien et al.,"Using Bayesian Network for Fault Location on Distribution Feeder," IEEE Transactions On Power Delivery, 17:13, July. 2002.
[6] G. Kramer et al., "Ethernet PON (EPON): Design and Analysis of an Optical Access Network", PNC, 3:3, 307-319, 2001.
[7] A. Bashar et al., "Employing Bayesian Belief Networks for energy efficient Network Management," in Proc. of 16th IEEE National Conference on Communications (NCC 2010), pp.1-5, 29-31 Jan. 2010.
[8] B. Lannoo et al., "Analytical model for the IPACT dynamic bandwidth allocation algorithm for EPONs", JON., vol. 6, pp. 677–688, June. 2007.
[9] F. Aurzada et al., "Delay analysis of Ethernet passive optical networks with gated service", J. Opt. Netw. 7, pp. 25–41, Jan. 2008.
[10] G. Kramer et al., "IPACT a dynamic protocol for an EPON", IEEE Commun. Mag., vol. 40, pp. 74–80, Feb. 2002.
[11] B. Skubic et al., "A comparison of dynamic bandwidth allocation for EPON, GPON, and next generation TDM PON", IEEE Commun. Mag., vol. 47, pp. S40–S48, March 2009.
[12] S. Zahr et al., "An analytical model of the IEEE 802.3ah MAC protocol for EPON-based access systems", Telecom Paris, May 2006.
[13] Y. Zhu et al., "IPACT with grant estimation (IPACT-GE) scheme for EPONs", IEEE JLW. Tech., vol.26, pp. 2055-2063, Jul.2008.
[14] S. Choi et al., "Dynamic bandwidth allocation algorithm for multimedia services over Ethernet PONs", ETRI J., vol. 24, pp. 465–468, Dec. 2002.
[15] C. Assi et al., "DBA for Quality-of-Service over Ethernet PONs", IEEE JSAC., 3:9, 1467-77, Nov. 2003.
[16] H. Xiong et al., "Broadcast polling-an uplink access scheme for the Ethernet passive optical network", JON., vol. 3, pp. 728–735, Oct. 2004.
[17] D. Heckerman, "A tutorial on learning with Bayesian networks", Learning in Graphical Models, M. Jordan, ed. MIT Press, Cambridge, MA, 1999.
[18] S. Hussain et al., "EPON: an extensive review of up-to-date DBA schemes", in Canadian Conf. on Electrical and Computer Eng, 2008, Niagara Falls, ON, Canada, pp. 511–516, May, 2008.
[19] M. R. Jason et al., "Online excess bandwidth distribution for Ethernet passive optical networks", J. Opt. Netw., vol. 8, pp. 358–369, Apr. 2009.
[20] X.Zhang et al, "Better Burst Detection", Proceedings of the 22nd International Conference on Data Engineering ,ICDE, 2006.

Keywords

  • EPON
  • BBN
  • DBA

Fingerprint

Dive into the research topics of 'Using Bayesian Belief Networks for Burst Detection in Ethernet Passive Optical Networks'. Together they form a unique fingerprint.

Cite this