CONCLUSION AND FUTURE WORKS
5.1 Conclusion
As the computer and networking technologies advance at a fast pace in recent years, the demand for multimedia communication services has also been growing at a similar pace. These multimedia communication services have characteristic s such as various QoS, burst traffic, and application-based bandwidth requirement. Hence, high-speed networks are requested to be capable of handling burst traffic and satisfying various QoS (e.g., delay, cell loss ratio) and bandwidth requirements to support the multimedia communication sources. Traffic control plays an important role in high-speed networks.
Traffic controls in networks have been presented for years, but they suffer from some basic limitations because most of them are based on the source modeling. Given that the present day complex networks are dynamic, there is great uncertainty associa ted with the input traffics. Fuzzy logic appears to be a promising approach to address key aspects of networks. In this thesis we present two fuzzy logic based traffic controllers in ATM network. In Chapter 3, we propose a fuzzy logic based CAC, which only use four rules, thus is easy to implement and is suitable for high-speed network. In Chapter 4 we present a fuzzy adaptive traffic flow controller (FATFC),
which takes the ABR services into account. The control rules and the parameters of the membership functions of the fuzzy traffic controller are established based on intuition and experience. Simulation results show that the proposed fuzzy traffic controllers guarantee the QoS requirement and achieve high system utilization. The fuzzy traffic controllers are effective because they utilize the actual measurements of the traffic dynamics and the linguistic capability of fuzzy logic, which are better than source modeling approach and provide soft controls.
5.2 Future works
In the proposed traffic controlle rs, the setting of membership functions and the establishing of control rules are based on experience and intuition, which have some disadvantages. Besides, when dealing with multimedia sources, the traffics full of uncertainties. So designing a self- tuning traffic controller is necessary. Genetic algorithm (GA) is a robust search and optimization algorithm based on natural selection in environments and natural genetics in biology. GA is better than traditional methods in optimal search. Hence, our next works are:
1. Apply GA to search the optimal parameters for the control rules and the membership functions.
2. Design a self-tuning strategy to on-line tune these parameters.
BIBLIOGRAPHY
[1] D.K. Ahn and J.S. Park*, ”Analysis on statistical characteristics of WWW traffic on IP Level”, 14th ICOIN, pp6c-1.1-6c-1.6, January 2000.
[2] ATM Forum. ATM Forum Traffic Management Specification 4.0 April 1996.
[3] J. Aweya and Q.J. Zhang, “A direct neural controller for flow control in computer networks”, Neural Networks Proc., Vol. 1, pp. 140-145, 1998.
[4] J.J. Bae and T. Suda, “Survey of Traffic Control Schemes and Protocols in ATM Networks”, Proc. of the IEEE, Vol. 79, No. 2, pp. 170-189, February 1991.
[5] B. Bensaou, S. T.C. Lam, H.W. Chu and D.H.K. Tsang, “Estimation of the Cell Loss Ratio in ATM Networks with a Fuzzy System and Application to Measurement-Based Call Admission Control”, IEEE/ACM Trans. Networking, Vol. 5, No. 4, pp. 572-584, August 1997.
[6] A.R. Bonde, Jr. and S. Ghosh, “A comparative study of fuzzy versus “Fixed”
thresholds for robust queue management in cell-switching networks”, IEEE/ACM Trans. Networking, Vol. 2, No. 4, pp. 337-345, August 1994.
[7] D. Botis, “A Fuzzy based bandwidth reservation scheme for VBR services”, Proc.
of the IASTED, pp. 226-230, August 1999.
[8] A. Burrlee, H.P. Stern and P.P. Kazakos, “Transmission policies and traffic management in multimedia wireless networks”, Wireless Networks, Vol. 3, pp.
103-112, 1997.
[9] Z. Cao and E.W. Zegura, “Utility Max-Min: an application-oriented bandwidth allocation scheme”, INFOCOM '99, Vol. 2, pp. 793-801.
[10] V. Catania and G. Ficili, “A Comparative Analysis of Fuzzy versus Conventional Policing Mechanisms for ATM Networks”, IEEE/ACM Trans. Networking, Vol. 4, No. 3, pp.449-459, June 1996.
[11] R.G. Cheng and C.J. Cheng, ”Design of a Fuzzy Traffic Controller for ATM Networks”, IEEE/ACM Trans. Networking, Vol. 4, No. 3, pp. 460-469, June 1996.
[12] R.G. Cheng, C.J. Chang and L.F. Lin, “A QoS-provisioning neural fuzzy
connection admission controller for multimedia high-speed networks”, IEEE/ACM/ Trans. Networking, Vol. 7, No. 1, pp. 111-121, February 1999.
[13] F.M. Chiussi, Y.X. and V.P. Kumar, “Virtual queueing techniques for ABR service:
Improving ABR/VBR Interaction”, INFOCOM '97, Vol. 2, pp. 406-418.
[14] M.E. Crovella and A. Bestavros, “Self-Simalarity in World Wide Web Traffic:
Evidence and Possible Causes”, IEEE/ACM Trans. Networking, Vol. 5, No. 6, pp.
835-846, December 1997.
[15] C. Douligeris and G. Develekos, “Neuro-Fuzzy control in ATM networks”, IEEE Communications Magazine, pp. 154-162, May 1997.
[16] Z. Fan, “New trends in ATM networks: a research view”, Computer Communications 22, pp. 499-515, 1999.
[17] M. Fontaine and D.G. Smith, “Automatically designed fuzzy system for connection admission control in ATM networks”, IEE Proc. Communications, Vol.
140, No. 2, pp. 113-119, April 1999.
[18] S. Ghosh and Q. Razouqi, “A survey of recent advances in fuzzy logic in telecommunications networks and new challenges”, IEEE Trans. Fuzzy System, Vol. 6, No. 3, pp. 443-447, August 1998.
[19] D.P. Heyman and T.V. Lakshman, “Source Models for VBR Broadcast-Video Traffic”, IEEE/ACM Trans. Networking, Vol. 4, No. 1, pp. 40-48, February 1996.
[20] A. Hiramatsu, “ATM Communications Network Control by Neural Networks”, IEEE Trans. Neural Networks, Vol. 1, No. 1, pp.122-130, March 1990.
[21] S. Jamin, “A Measurement-Based Admission Control Algorithm for Integrate Service Packet Networks”, IEEE/ACM Trans. Networking, Vol. 5, No. 1, pp.
56-70, February 1997.
[22] T.H. Lee, K.C. Lai and S.T. Duann, “Design of a Real- Time Call Admission Controller for ATM Networks”, IEEE/ACM Trans. Networking, Vol. 4, No. 5, pp.
758-765, October 1996.
[23] W.E. Leland, “On the Self-Similar Nature of Ethernet Traffic (Extended Version)”, IEEE/ACM Trans. Networking, Vol. 2, No. 1, pp. 1-15, February 1994.
[24] S. Mukherjee and D. Re ininger, “An Adaptive Connection Admission Control Policy for VBR+ Service class”, INFOCOM '98, Vol. 2, pp. 849-857.