This action might not be possible to undo. Are you sure you want to continue?

Overview

This paper presents a fuzzy logic-based system to deal with the real-time traffic control problem in ATM networks. The Fuzzy Leaky Bucket ( FLB ) modifies the token rate. In this the modified Leaky Bucket ( LB ) technique is combined with the moving window mechanism to identify the traffic parameters.

.WHAT IS FUZZY LOGIC????? It is the logic applied to handle the uncertainity due to vagueness by representing the human response in proper mathematical algorithms.

.

.transmitter receiver Asynchronous transfer Mode is preferred over synchronous mode.

To guarantee a certain quality of service in terms of delay and cell-loss probability.Asynchronous Transfer Mode ATM is the suitable transfer mode for transmission in new high-speed integrated service networks. suitable traffic control is required. . The most popular traffic control method is the Leaky Bucket ( LB ) mechanism .

pp.Behrouz A Forouzan.´Tata McGrawHill Publishing Company Limited. .2006.Leaky Bucket Technique Reference:.4th Edition.´Data Communications And Networking.761-780.

smoothing out bursts .Leaky Bucket Technique This mechanism turns an uneven flow of packets from the user processes inside the host into an even flow of packets onto the network. .

a fuzzy logic-based system is presented to deal with the real-time traffic control problem in ATM networks. In this paper.Modified Leaky Bucket Mechanism But for many applications. so a more flexible algorithm is needed. it is better to speed up the output when large bursts arrive. .

it should be smooth the traffic and improve utilisation efficiency of the bandwidth. On the other hand.Requirements of Real Time Traffic Control Mechanism We try to build a dynamic control mechanism which will provide quality of services to all connections sharing the network resources. .

.

Fuzzy Logic Control Mechanism We have combined the modified LB technique with the moving window mechanism to identify the traffic parameters. It needs to be point out that the token rate R and queue buffer length M are crucial to cell loss rate and mean time delay. . The Fuzzy Leaky Bucket ( FLB ) modifies the token rate according to the peak rate and the burst time which characterize the source behavior.

³Design of a FuzzyTraffic Controller for ATM Networks´. Cheng-Ju Chang. No 3. pp 460-469. June 1996.FUZZY LOGIC CONTROLLER Reference:-Ray-Guang Cheng. . Vol 4. IEEE/ACM Transactions on Networking.

1488±1494.Reference- T.´ IEEE J. . Ndousse.. D. 1994. Dec. pp. Select. 12. vol. Areas Commun. ³Fuzzy neural control in ATM networks.

Working Principle FLB chooses the burst time ( x ) and the peak cell rate ( PCR ) as the crisp input parameters. then Token rate R = K*h.l ). High ( H ) . The input and output variables are divided into five fuzzy subsets: Very Low ( VL ). Low ( L). decision making and defuzzification. K ( 0. After fuzzification. get the crisp output value K . . Medium ( M ). Very High ( VH ). The membership functions chosen for the fuzzy sets are shown below.

Fuzzification. Define the set of RuleBase. Choose the Universe where Fuzzy is defined. .Steps of Fuzzy Logic Define the Input and Output.

Membership Function for the input X Membership Function for the input PCR. .

Membership Function for the output K .

that is. the K will be Medium. If the PCR is low or medium. .X PCR VL L M H VH VL VH VH VH H M L VH VH H M L M H H M L VL H M M L VL VL VH L L VL VL VL Table: Fuzzy Rule Base The above table gives the fuzzy conditional rules. its credit is increased and K will increase. a sign of possible beginning of violation on the part of source. the source continues nonviolating behavior. If the PCR is high.

Ndousse. Dec. vol. . Select. ³Fuzzy neural control in ATM networks. pp. D. 1488±1494.. 1994. 12. Areas Commun.Simulation Results a) Cell loss prob vs peak rate variation time variation b) Cell loss prob vs mean burst Performance compare of FLB and LB algorithm Reference-T.´ IEEE J.

Simulation results show that FLB is better than the LB in terms of cell loss probability and mean delay time. while the curve 1 is the response curve of the LB mechanism. focusing on the cell loss probability curves as a function of the peak rate and burst time violations.Simulation Results (contd) The performance of FLB is compared with LB system. . The curve 2 is the response curve of modified FLB system.

The Fuzzy Leaky Bucket ( FLB ) modifies the token rate according to the peak rate and the burst time which characterize the source behavior. Due to this token rate we get maximum utilisation of bandwidth with less conjestion in the network. .Conclusion We have modified the Leaky Bucket technique( LB ) to identify the traffic parameters.

761-780.pp.157-221.´Data Communications And Networking.4th Edition.2006.Rajasekaran and G.Fuzzy Logic and Genetic Algorithms Synthesis and Applications. .. ³Congestion control and traffic management in ATM networks: recent advances and a survey.References S. no.A.2006.Pearson Education.Hall of India Private Limited.pp.´Neural Networks.´Learning and Soft Computing´.4th Edition. Networks ISDN Syst. Behrouz A Forouzan.2006. 13. pp. Oct.365-391.´Tata Mc Graw-Hill Publishing Company Limited. vol.pp. 1996. 28. R. Jain.Vijayalakshmi.´ Comput. Vojislav Kecman.´Prentice. 1723±1738.

Melamed.S.T.pp.´ IEEE Commun. Mag.JANG AND C. pp 460-469. Vol 4. .SUN. 32. IEEE Transactions on Networking. Cheng-Ju Chang. 1994.Pearson Education. ³Traffic modeling for ATM Networks.. ³Design of a FuzzyTraffic Controller for ATM Networks´.2004.47-70. Mar. Frost and B. RayV.References -Guang Cheng. vol.´Neuro Fuzzy and Soft Computing´. No 3.R. June 1996. J.

Thank You!!! .

- FSM Design
- Ed A
- Interview Questions
- Pinch Analysis Intro
- AIAA-2009-863
- 161396903
- Distance Restraint Gromacs
- Silk Test
- Practise
- Training4 Nortel Feature Evolution V15.1.1 to V17
- CauseandEffectDiagram.ppt
- PBIL Project Description 8th July 2014
- Algorithms of Informatics, Vol.2.. Applications (2007)(ISBN 9638759623) [Ivanyi A. (Ed.)]
- 04OLAP
- MM74C00
- PR7.pdf
- 10.1.1.20
- Verification Tut Austin 032207 Tutorial
- D00SAA55_27.PDF
- There Are Three Ways of Optimizing Handovers in LTE
- TAU- DLR Deutsh Software Flow Aero Solver
- Response Optimisation Sloptim Gsg
- Telecommunications Switching Systems 16
- Array and System Losses
- paper report 1
- Python Notes 1
- SDL Seminar Presentation
- Chapter 8 - Code Generation
- d 032021027
- SATHYAMM
- Real-time Traffic Control in Atm Networks

Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

We've moved you to where you read on your other device.

Get the full title to continue

Get the full title to continue reading from where you left off, or restart the preview.

scribd