Chinatsu Ikeda

Rate-based congestion control for ATM networks

Congestion control plays an important role in the effective and stable operation of ATM networks. This paper first gives a historical overview of rate-based congestion control algorithms developed in the ATM Forum, showing how the current ATM Forum standard regarding the traffic management control methods is exploited, by these algorithm. Then, analytical approach is used to quantitatively evaluate their performance and show the effectiveness of the rate-based approach. In presenting the numerical examples, we emphasize that appropriate control parameter settings are essential for proper traffic management in an ATM network environment.

ATM connection and traffic management schemes for multimedia internetworking

The rapid advances being made in microprocessor technology have stimulated significant interest in distributed multimedia applications supported by high-speed networks. Examples of distributed multimedia applications include multimedia database retrieval, distributed multimedia documents, and video mail. Due to the large amount of multimedia traffic for audio/visual applications, these applications require high speed networks to retrieve data in real time, instead of huge local disk storage

Adaptive congestion control schemes for ATM LANs

New congestion control schemes using the adaptive rate control for ATM LANs are presented. It is preferable for hosts in LANs to be able to send bursts at the same speed as the interface link speed in a lightly loaded condition, and as the network load increases, to reduce their traffic rate adaptively in order to avoid network congestion. The authors propose to apply such a rate control concept for two different traffic classes in the ATM LANs. For the first traffic class requiring no bandwidth reservation, i.e. a best effort service class, a combination of the end-to-end adaptive peak rate control with the link-by-link backpressure control is proposed. For the second traffic class, requiring the bandwidth reservation for the burst transmission, i.e. a guaranteed burst service class, a combination of the adaptive peak rate control with the fast bandwidth reservation (FRP) is proposed. It is shown through simulations that, in the first class traffic, cell loss is avoided by the backpressure, while the unfairness problems caused by the backpressure in a heavy load situation are resolved with the adaptive rate control. In the second class traffic, the network throughput characteristics are shown to be improved in the heavily loaded situations, owing to the fact that the adaptive rate control reduces the bandwidth reservation blocking probability.<<ETX>>

A simulation study of TCP performance in ATM networks with ABR and UBR services

We present a simulation study of the TCP performance in ATM networks with available bit rate (ABR) service and unspecified bit rate (UBR) service with early packet discard (EPD) schemes. We focus our study in a LAN environment using some benchmark network configurations proposed in the ATM Forum. Our simulation results show the following: (1) with UBR service and EPD schemes, TCP suffers significant performance degradation in terms of fairness and requires relatively large switch buffer even with a small number of active virtual connections over a LAN configuration, and (2) for the same set of network configurations and with ABR service using explicit rate feedback schemes, TCP achieves a good performance in terms of fairness and link utilization, and requires a relatively small switch buffer.

Performance of TCP over UBR service in ATM networks with Per-VC early packet discard schemes

Both available bit rate (ABR) service and unspecified bit rate (UBR) service with early packet discard (EPD) schemes have been considered for supporting data applications in ATM networks. Since transmission control protocol (TCP) is perhaps the most widely used transport layer protocol in existing data networks, the performance of TCP over ATM using ABR service and UBR service with EPD schemes is of great interest to ATM equipment vendors and service providers. With regard to this interesting issue, we demonstrate in a companion paper [Li et al., 1996] some simulation results, which show that (1) with UBR, service and EPD schemes, TCP suffers significant performance degradation in terms of fairness and requires a relatively large switch buffer even with a small number of active virtual connections over a LAN configuration, and (2) for the same set of network configurations and with ABR service, TCP achieves good performance in terms of fairness and link utilization, and requires a relatively small switch buffer. In this paper, we extend our work in Li et al. by studying the performance of TCP over UBR service when EPD schemes are improved by using per-VC accounting and per-VC queueing techniques. In particular, our simulation results show that in a LAN environment, per-VC based EPD schemes can significantly improve the performance of TCP over UBR service in terms of fairness.

On TCP performance in ATM networks with per-VC early packet discard mechanisms

Both available bit rate (ABR) service and unspecified bit rate (UBR) service with early packet discard (EPD) schemes have been considered for supporting data applications in ATM networks. Since the transmission control protocol (TCP) is perhaps the most widely used transport layer protocol in existing data networks, the performance of TCP over ATM using ABR and UBR services with EPD schemes is of great interest to ATM equipment vendors and service providers. With regard to this interesting issue, we demonstrate in earlier work [1] some simulation results, which show that (1) with UBR service and EPD schemes, TCP suffers significant performance degradation in terms of fairness and requires a relatively large switch buffer even with a small number of active virtual connections over a LAN configuration, and (2) for the same set of network configurations and with ABR service, TCP achieves good performance in terms of fairness and link utilization, and requires relatively small switch buffer. In this paper, we extend our work [1] by studying the performance of TCP over UBR service where EPD schemes are improved by using per-VC accounting and per-VC queueing techniques. In particular, our simulation results show that in a LAN environment, per-VC based EPD schemes can significantly improve the performance of TCP over UBR service in terms of fairness.