A Self Organizing Map Based Approach for Congestion Avoidance in Autonomous IP Networks

Özen Yelbaşı, Emin Germen

Abstract


This work presents a Self Organizing Map (SOM) based queue management approach against congestion in autonomous Internet Protocol (IP) networks. The new queue management approach is proposed with consideration to the pros and cons of two well-known queue management algorithms: Random Early Detection (RED) and Drop Tail (DT). At the beginning of this study, RED and DT are compared by observing their effects on two important indicators of congestion: end- to-end delay and delay variation. This comparison reveals that the performances of RED and DT vary according to the level of global congestion: under low congestion conditions, when packet losses caused by congestion are unlikely, DT outperforms RED; while under high congestion, RED is superior to DT. The SOM based ap- proach takes into account the variations in the global congestion levels and makes decisions to optimise congestion avoidance. A centralized observation unit is designed for monitoring global congestion levels in autonomous IP networks. A traffic flow is generated between each router and the observation unit so as to follow the changes in the global congestion level. For this purpose, IP routers are specialized to send packets carrying queue length information to the observation unit. A SOM based decision mechanism is used by the observation unit, to make predictions on the future congestion behavior of the network and inform the routers. Routers use this information to update their congestion avoidance behavior, as their ability to update their RED parameters is enhanced by the congestion notications sent by the observation unit. In this work, multiple simulations are undertaken in order to test the performance of the proposed SOM-based method. A considerable improve- ment is observed from the point of view of end-to-end delays and delay variations, by comparison with DT and RED as used in recent IP networks.

Keywords


Self Organizing Map; congestion avoidance; random early detection; drop tail

Full Text:

PDF

References


ATHURALIYA S., LOW S.H., LI V.H., YIN Q. REM: Active queue management. IEEE Network Magazine. 2001, 15, pp. 48-53, doi: 10.1109/65.923940.

ATIQUZZAMAN M., ZHENG B. Active Queue Management in TCP/IP Networks. In: M. HASSAN, R. JAIN, ed. High Performance TCP/IP Networking: Concepts, Issues, and Solutions. U.S.A.: Pearson Prentice Hall, 2004, pp. 281-307.

AWEYA J., OUELLETTE M., MONTUNO D.Y. A control theoretic approach to active queue management. Computer Networks. 2001, 36, pp. 203-235.

BONALD T., MAY M., BOLOT J.-C. Analytic Evaluation of RED performance. In: Proceedings of the Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE INFOCOM 2000), Tel Aviv, Israel: IEEE, 2000, pp. 1415-1424, doi: 10.1109/INFCOM.2000.832539.

ENHAI L., YAN L., RUIMIN P. An improved random early detection algorithm based on flow prediction. In: Proceedings of Second International Conference on Intelligent Networks and Intelligent Systems (ICINIS 2009), Tianjin, China: IEEE, 2009, pp. 425-428, doi: 10.1109/ICINIS.2009.115.

FENG W.-C., KANDLUR D.D., SAHA D., SHIN K.G. A self-configuring RED gateway. In: Proceedings of the Conference on Computer Communications (IEEE INFOCOM 1999), New York, U.S.A.: IEEE, 1999, 3, pp. 1320-1328, doi: 10.1109/INFCOM.1999.752150.

FLOYD S., JACOBSON V. Random early detection gateways for congestion avoidance. IEEE/ACM Transactions on Networking. 1993, 1(4), pp. 397-413, doi: 10.1109/90.251892.

GEVROS P., CROWCROFT J., KIRSTEIN P., BHATTI S. Congestion control mechanisms and the best effort service model. IEEE Network Magazine. 2001, 15, pp. 16-26, doi: 10.1109/65.923937.

HAWKINS C.A., WEBER J.E. Statistical Analysis: Applications to Business and Economics. New York: Harper & Row Publishers, 1980.

HAYKIN S. Neural Networks: A comprehensive foundation. U.S.A.: Prentice Hall, 1999.

HO H.-J., LIN W.-M. AURED – Autonomous random early detection for TCP congestion control. In: Proceedings of the Third International Conference on Systems and Networks Communications (ICSNC 2008), Sliema, Malta: IEEE, 2008, pp. 79-84, doi: 10.1109/ICSNC.2008.22.

HOLLOT C.V., MISRA V., TOWSLEY D., GONG W.-B. Analysis and design of controllers for AQM routers supporting TCP flows. IEEE Transactions on Automatic Control. 2002, 47, pp. 945-959, doi: 10.1109/TAC.2002.1008360.

HOLLOT C.V., MISRA V., TOWSLEY D., GONG W.-B. On designing improved controllers for AQM routers supporting TCP flows. In: Proceeding of the Twentieth Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE INFOCOM 2001), Anchorage (Alaska), U.S.A.: IEEE, 2001, 3, pp. 1726-1734, doi: 10.1109/INFCOM.2001.916670.

INTERNET ENGINEERING TASK FORCE (IETF). RFC 2309: Recommendations on queue management and congestion avoidance in the Internet [online]. Written by BRADEN B., et al. April 1998. Available from: https://tools.ietf.org/html/rfc2309.

KOHONEN T. The Self-Organizing Map. In: Proceedings of the IEEE, 1990, 78(9), pp. 1464-1480, doi: 10.1109/5.58325.

KOHONEN T. Things you haven’t heard about the self-organizing map. In: Proceedings of the IEEE International Conference on Neural Networks 1993, San Francisco, CA: IEEE, 1993, 3, pp. 1147-1156, doi: 10.1109/ICNN.1993.298719.

KOHONEN T. The self-organizing map. Neurocomputing. 1998, 21, pp. 1-6.

LOCHIN E., TALAVERA B. Managing network congestion with a Kohonen-based RED queue. In: Proceedings of IEEE International Conference on Communications (ICC 2008), Beijing, China: IEEE, 2008, pp. 5586-5590, doi: 10.1109/ICC.2008.1047.

MANASA S. ANLRED: A Robust AQM Mechanism for Congestion Avoidance. International Journal of Computer Applications. 2013, 81(15), pp. 1-9, doi: 10.5120/14196-2259.

MASUGI M. QoS mapping of VoIP communication using self-organizing neural network. In: IEEE workshop on IP operations and management (IPOM 2002), 2002, Dallas, Texas, U.S.A.: IEEE, pp. 13-17, doi: 10.1109/IPOM.2002.1045749.

MASUGI M., TAKUMA T. Multi-fractal analysis of IP network traffic for assessing time variations in scaling properties. Physica D. 2007, 225, pp. 119-126, doi: 10.1016/j.physd.2006.10.015.

PATEL S., GUPTA P., SINGH G. Performance Measure of Drop Tail and RED Algorithm. In: Proceedings of International Conference on Electronic Computer Technology (ICECT 2010), Kuala Lumpur, Malaysia: IEEE, 2010, pp. 35-38, doi: 10.1109/ICECTECH.2010.5479996.

QUET P.-F., ÖZBAY H. On the design of AQM supporting TCP flows using robust control theory. IEEE Transactions on Automatic Control. 2004, 49(6), pp. 1031-1036, doi: 10.1109/TAC.2004.829643.

ROUHANI M., TANHATALAB M.R., SHOKOHI-ROSTAMI A. Nonlinear Neural Network Congestion Control Based on Genetic Algorithm for TCP/IP Networks. In: Proceedings of Second International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN 2010), Liverpool, United Kingdom: IEEE, 2010, pp. 1-6, doi: 10.1109/CICSyN.2010.21.

RYU S., RUMP C., QIAO C. Advances in Internet congestion control. IEEE Communications Surveys. 2003, 5(1), pp. 28-39, doi: 10.1109/COMST.2003.5342228.

SOM TOOLBOX TEAM. SOM Toolbox 2.0 [software]. [accessed 2002-10-1]. Available from: http://www.cis.hut.fi/projects/somtoolbox.

YELBAŞI Ö. Self Organizing Map Based RED Parameter Estimation for Congestion Avoidance. Türkiye, 2011. PhD thesis, Anadolu University. Available from: https://tez.yok.gov.tr/UlusalTezMerkezi/tarama.jsp.




DOI: http://dx.doi.org/10.14311/NNW.2015.25.007

Refbacks

  • There are currently no refbacks.


Should you encounter an error (non-functional link, missing or misleading information, application crash), please let us know at nnw.ojs@fd.cvut.cz.
Please, do not use the above address for non-OJS-related queries (manuscript status, etc.).
For your convenience we maintain a list of frequently asked questions here. General queries to items not covered by this FAQ shall be directed to the journal editoral office at nnw@fd.cvut.cz.