A temporal-spatial flow control protocol for ABR in integrated networks
Many end-to-end feedback flow control protocols experience the rate oscillations caused by latency phase shift (LPS). This problem comes from time-varying bandwidth and non-zero feedback latency. A temporal flow control (TFC) protocol called MTS (Multiple-Time-Scale) was proposed to significantly reduce the oscillations in our earlier publication . In this paper, the class of temporal flow control is further studied and a fundamental theorem relating LPS rate oscillations to the ratio of feedback latency to available bandwidth window duration is proved. The MTS protocol is generalized and two propositions showing the advantages of the generic MTS protocol is proved. Simulation results show MTS significantly improves network performance in terms of stability, throughput and cell loss. In particular, MTS smoothens the output traffic very effectively, thus further reducing the traffic fluctuations.
KeywordsShort Latency Bandwidth Allocation Long Latency Queue Size Integrate Network
Unable to display preview. Download preview PDF.
- 1.The ATM Forum, “The ATM Forum Traffic Management Specification”, v.4.0, 1996.Google Scholar
- 2.L. Hu, Y. Kim, and W. Tsai, “An Oscillation Reducing Rate-based Protocol based on Multiple Time Scale for ABR Flow Control”, IEEE SICON '98, Singapore, July 1998. Also available from http://www.eng.uci.edu/~netrol.Google Scholar
- 3.A. Arulambalam, X. Chen, and N. Ansari, “Allocating Fair Rates for Available Bit Rate Service in ATM Networks”, IEEE Comm. Mag., Nov. 1996.Google Scholar
- 4.K. Siu and H. Tzeng, “Intelligent Congestion Control for ABR Service in ATM Networks”, ACM SIGCOMM, Comp. Commun. Rev., Oct. 1996, pp.81–106.Google Scholar
- 5.L. Roberts, “Enhanced PRCA (Proportional Rate-Control Algorithm)”, ATMF 94-0735R1, Aug. 1994.Google Scholar
- 6.L. C. Hu, Y. Kim, and W. Tsai, “A Space-Time Fair Temporal Flow Control for Integrated Networks”, To be submitted to IEEE Infocom'99.Google Scholar
- 7.N. Golmie, A. Koenig, and D. Su, ‘The NIST ATM Network Simulator Operation and Programming', NISTIR 5703, Version 1.0, August 1995.Google Scholar
- 8.L.C. Hu and K-J. Lin, “A Forward Error Control Scheme for Real-Time VBR Traffic in ATM”, Proc. Pacific Rim Int'l Symp. on Fault-Tolerant Systems, 1995, Newport Beach, Calif., Dec. 1995.Google Scholar
- 9.W. Tsai, Y. Kim, and C.-K. Toh, “A Stability and Sensitivity Theory for Rate-based Max-Min Flow Control for ABR Service”, Invited Paper, IEEE SICON '98, Singapore, 1998. Also available from http://www.eng.uci.edu/~netrol.Google Scholar
- 10.S. Kalyanaraman, R. Jain, S. Fahmy, R. Goyal, and B. Vandalore, “The ERICA Switch Algorithm for ABR Traffic Management in ATM Networks”, Submitted to IEEE/ACM Transactions on Networking, November 1997.Google Scholar
- 11.L. Hu, Y. Kim, and W. Tsai, “A Temporal Flow Control Protocol for Best-Effort Service in Integrated Networks”, UCI ECE Tech. Report 97-12-01, University of California, Irvine, 1997.Google Scholar