Router mechanisms designed to achieve fair bandwidth allocations, like Fair Queueing, have many desirable properties for congestion control in the Internet. However, such mechanisms usually need to maintain state, manage buffers, and/or perform packet scheduling on a per flow basis, and this complexity may prevent them from being cost-effectively implemented and widely deployed. In this paper, we propose an architecture that significantly reduces this implementation complexity yet still achieves approximately fair bandwidth allocations. We apply this approach to an island of routers -- that is, a contiguous region of the network -- and we distinguish between edge routers and core routers. Edge routers maintain per flow state; they estimate the incoming rate of each flow and insert a label into each packet header based on this estimate. Core routers maintain no per flow state; they use FIFO packet scheduling augmented by a probabilistic dropping algorithm that uses the packet labels and an estimate of the aggregate traffic at the router. We call the scheme Core-Stateless Fair Queueing. We present simulations and analysis on the performance of this approach.

This paper describes the "explicit rate indication for congestion avoidance" (ERICA) scheme for rate-based feedback from asynchronous transfer mode (ATM) switches. In ERICA, the switches monitor their load on each link and determine a load factor, the available capacity, and the number of currently active virtual channels. This information is used to advise the sources about the rates at which they should transmit. The algorithm is designed to achieve high link utilization with low delays and fast transient response. It is also fair and robust to measurement errors caused by the variations in ABR demand and capacity. We present performance analysis of the scheme using both analytical arguments and simulation results. The scheme is being considered for implementation by several ATM switch manufacturers.

Today’s Internet provides one simple service: best effort datagram delivery. This minimalist service allows the Internet to be stateless, that is, routers do not need to maintain any fine grained information about traffic. As a result of this stateless architecture, the Internet is both highly scalable and robust. However, as the Internet evolves into a global commercial infrastructure that is expected to support a plethora of new applications such as IP telephony, interactive TV, and e-commerce, the existing best effort service will no longer be sufficient. In consequence, there is an urgent need to provide more powerful services such as guaranteed services, differentiated services, and flow protection. Over the past decade, there has been intense research toward achieving this goal. Two classes of solutions have been proposed: those maintaining the stateless property of the original Internet (e.g., Differentiated Services), and those requiring a new stateful architecture (e.g., Integrated Services). While stateful solutions can provide more powerful and flexible services such as per flow bandwidth and delay guarantees, they are less scalable than stateless solutions. In particular, stateful solutions require each router to maintain and manage per flow state on the control path, and to perform per flow classification, scheduling, and buffer management on the data path. Since today’s routers can

Abstract — 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 compu-tation of the fair- share of the link bandwidth. On the other hand, newer generation of ATM chipsets and switches now implement per-VC queueingand schedu~mgthat 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 queueinglscheduling capability of the new generation of ATM switches and develop an AM? rate-based congestion control algorithm. In contrast to most algorithms that appeared in the literature which are heuristics-based, this algorithm extends the work of [4] 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.

viii Acknowledgements ix 1. Introduction 1 1.1 Thesis Overview : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 6 2. Congestion Control Approaches in Computer Networks 8 2.1 Performance Metrics : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 8 2.2 Congestion and Flow Control in Connectionless Networks : : : : : : : : : : 11 2.2.1 Source-based Schemes : : : : : : : : : : : : : : : : : : : : : : : : : : 12 2.2.2 Gateway-based Schemes : : : : : : : : : : : : : : : : : : : : : : : : : 14 2.2.2.1 Drop-Tail Gateways : : : : : : : : : : : : : : : : : : : : : : 15 2.2.2.2 Source-Quench : : : : : : : : : : : : : : : : : : : : : : : : : 15 2.2.2.3 Random Drop and Random Early Detection Gateways : : 16 2.2.3 Combined Schemes : : : : : : : : : : : : : : : : : : : : : : : : : : : : 17 2.2.3.1 Binary Feedback Scheme for Congestion Avoidance : : : : 18 2.2.3.2 TCP with Explicit Congestion Notification : : : : : : : : : 19 2.3 Congestion Control in ATM networks : : : : :...

We generalize the classical max-min rate allocation policy with the support of the minimum rate requirement and peak rate constraint for each connection. Since a centralized algorithm for the generalized maxmin (GMM) rate allocation requires global information, which is difficult to maintain and manage in a large network, we develop a distributed protocol to achieve the GMM policy using the available bit rate (ABR) flow control mechanism. We give a proof that our distributed protocol converges to the GMM rate allocation through distributed and asynchronous iterations under any network configuration and any set of link distances.

Abstract-- Algorithms for controlling congestion are critical for the success of ATM networks. The various sample algorithms appearing in the literature have in common significant nonlinearities that make these algorithms difficult to analyze using the tools of classical control theory. This paper reports on the beginnings of a research program that considers the ATM congestion control problem from the point of view of control theorist. A control scheme is developed that can be designed and analyzed using well established linear control theory. There is promise that as this approach is further developed it offers hope that analysis can assure reasonable behavior in the large scale system setting of ATM networks. I.

Abstract--We propose a novel explicit rate-flow-control algo-rithm intended for available-bit-rate (ABR) service on an ATM net-work subject to loss and fairness constraints. The goal is to guar-antee low cell loss in order to avoid throughput collapse due tore-transmission by higher level protocols. The mechanism draws on measuring the current queue length and bandwidth availability, as well as tracking tile current number of active sessions contending for capacity, to adjust an explicit bound on the source transmis-sion rates. We identify the factors that affect queue overflows and propose simple design rules aimed at achieving transmission with controlled loss in a dynamic environment. We also discuss how con-servative design rules might be relaxed by accounting for statistical multiplexing in bandwidth sharing among bursty ABR sources and variable-bit-rate (VBR) sources. Index Terms--ABR service, ATM networks, delay differential equations, explicit rate flow control. A

This paper gives a new definition of general weighted (GW) fairness and shows how this can achieve various fairness definitions, such as those mentioned in the ATM Forum TM 4.0 specifications. The GW fairness can be achieved by calculating the ExcessFairshare (weighted fairshare of the left over bandwidth) for each VC. We show how a switch algorithm can be modified to support the GW fairness by using the ExcessFairshare term. We use ERICA+ as an example switch algorithm and show how it can be modified to achieve the GW fairness. For simulations, the weight parameters of the GW fairness are chosen to map a typical pricing policy. Simulation results are presented to demonstrate that, the modified switch algorithm achieves GW fairness. An analytical proof for convergence of the modified ERICA+ algorithm is given in the appendix.

Traffic sources that do not have intrinsic temporal characteristics are expected to be transported over ATM networks using the Available Bit Rate (ABR) service. These sources are amenable to reactive flow control and are expected to use bandwidth left over after servicing the guaranteed QoS services (CBR and VBR). Fair allocation of the available bandwidth to competing ABR connections is based on the concept of MaxMin fairness. The ABR service definition allows sources to specify a Minimum Cell Rate (MCR) that is acceptable to them. Most studies of Max-Min fair rate allocation assume zero MCRs. In this paper, we first develop a natural extension of the concept of Max-Min fair rate allocation to the case of ABR sessions with nonzero MCR values. Then we present a centralised algorithm and discuss the construction of distributed algorithms for obtaining the Max-Min allocation. We show that the Max-Min allocation can be obtained as the solution of a certain vector equation, and discuss how...