Lotfi Benmohamed

A control-theoretic ABR explicit rate algorithm for ATM switches with per-VC queueing

There have been numerous studies on congestion control for the ABR service in ATM networks. These studies typically focus on the performance and fairness of the algorithms and make simplistic assumptions regarding the switch architecture and the link scheduling. One central issue of these studies has been the computation of the fair share of the link bandwidth. On the other hand, newer generation of ATM chipsets and switches now implement per-VC queueing and scheduling that is capable of providing flow isolation as well as fair sharing of the link bandwidth among contending connections. As a result, ABR congestion control algorithms can now focus on solving the congestion control problem without unnecessarily being burdened by fairness considerations. In this paper, we take advantage of the per-VC queueing/scheduling capability of the new generation of ATM switches and develop an ABR rate-based congestion control algorithm. In contrast to most algorithms that appeared in the literature which are heuristics-based, this algorithm extends previous work (see IEEE/ACM Trans. on Networking, vol.1, no.6, p.693-707, 1993) using a control-theoretic approach and takes advantage of the per-VC queue length information to achieve a simple to implement and yet complete control of the stability, rate of convergence, and performance of ABR service. Simulation results confirm the excellent performance and fairness characteristics achieved by the algorithm.

Feedback control of congestion in packet switching networks: The case of multiple congested nodes

In this paper, an analytical method for the design of a congestion control scheme in packet switching networks is presented. This scheme is particularly suitable for implementation in ATM switches, for the support of the available bit rate (ABR) service in ATM networks. The control architecture is rate-based with a local feedback controller associated with each switching node. The controller itself is a generalization of the standard proportional-plus-derivative controller, with the difference that extra higher-order derivative terms are involved to accommodate the delay present in high-speed networks. It is shown that, under the specific service discipline introduced here, there exists a set of control gains that result in asymptotic stability of the linearized network model. A method for calculating these gains is given. In addition, it is shown that the resulting steady state rate allocation possesses the so-called max-min fairness property. The theoretical results are illustrated by a simulation example, where it is shown that the controller designed, using the methods developed here, works well for both the service discipline introduced in this paper and for the standard FCFS scheme.

Rate control algorithms for the ATM ABR service

Over the last couple of years both the ATM Forum and ITU-T have converged on a closed-loop, feedback based rate control mechanism as the framework for the Available Bit Rate ATM Transfer Capability. In this framework, an ABR source adapts its transmission rate to changing characteristics of the ATM network by either testing periodically the state of the network or through direct feedback from the network. The state of the network is conveyed to the source either as a simple binary feedback signaling congestion or no congestion, or as an explicit rate indicating the rate at which the source can transmit. In this paper we review the detailed framework for the ABR service standardized by the ATM Forum, the underlying service philosophy and protocol design goals for ABR flow control, and the premises and high-level performance characteristics for the more promising ABR rate control schemes proposed so far.

Architecture and performance analysis of a large-scale archival and retrieval system

With the advances in imaging and storage technology, critical document handling and archiving applications have been migrating to digital technology, thereby reducing the cost and improving the quality and services. Documents are first sorted, scanned and compressed into digital images. Then state-of-the-art computer and networking technology is used to manage these images. In this paper we discuss the architecture and performance of a large, geographically distributed archival and retrieval system for image and document applications. The architecture of interest is a hierarchical one. We examine performance characteristics of the architecture and identify critical resources and parameters of system performance. Using decomposition and aggregation techniques, we model subsystems and study the end-to-end system performance. We show the performance/cost tradeoffs and various approaches to further optimize the system performance.

Dynamic EPD threshold for UBR control

In many ATM switches, only a limited number of delay priority queues are available at each link. In order to support all five service categories defined in ATM Forum, the UBR and ABR service classes may have to be assigned to the same priority queue. In this paper we address the problem of controlling the resource sharing between UBR and ABR when both share the same FIFO queue in an ATM switch. We achieve the desired bandwidth sharing between these two classes by controlling the amount of buffer each class can occupy. In particular, we use the EDP threshold to control UBR by dropping UBR cells when this threshold is exceeded. We show that the control algorithm proposed in this paper achieves a tight control of the resource allocation between UBR and ABR.