Michigan State University,
Abstract:
In the single-ER-rate (SER) flow control, at a time point, the feedback rate for a link to each ABR sessions will be the same. In this paper, we use networkflow approach to obtain a set of conditions for the max-min fairness convergence for a class of single-ER-rate flow control algorithms. Based on these conditions, we have derived three update rules-- SUR, MoSUR and SHARE. The update rules SUR and MoSUR are simple. As the simulation results show, the transient response of SUR is slow but the transient behavior of MoSUR is very close to that of SHARE. Keywords: ER-based ABR flow control, network flow.
Citations
| 37 | Network buffer requirements of the rate-based control mechanism for ABR services – Ritter - 1996 |
| 29 | A linear control approach to explicit rate feedback in ATM networks – Rohrs, Berry - 1997 |
| 26 | Dynamic model for design of stable explicit-rate ABR control schemes – Zhao, Li, et al. - 1997 |
| 18 | UT: ABR feedback control with tracking – Fulton, Li, et al. - 1997 |
| 15 | Max-Min Fair Rate Control of ABR Connections with Nonzero MCRs – Abraham, Kumar - 1997 |
| 12 | A stochastic approximation approach for max-min fair adaptive rate control of ABR sessions with MCRs – Abraham, Kumar - 1998 |
| 5 | The ERICA Switch Algorithm for ABR Traffic Management in ATM Networks – al - 1997 |
| 2 | NIST ER switch mechanism (an example – Golmie, Chang, et al. - 1995 |
| 1 | Bounded-cell-loss-ratio flow control – Liao, Esfahanian, et al. - 1999 |

