Performance of dynamic feedback flow control using VS/VD technique for ABR service in ATM networks

The broadband integrated services digital networks are based on the ATM technology. As these networks will be deployed gradually, the existing high-speed data services, as Frame Relay and SMDS, will continue to exist and, for interoperability purposes, they will also be supported by the ATM networks. Moreover, ATM networks allows to efficiently support a new service, called available bit rate (ABR) service in the ATM Forum, which requires no bandwidth reservation. When this service is requested, data are transmitted through the network with low priority, being the available network resources shaped dynamically among all the active sources. In this paper, we first discuss how to manage FR and SMDS services in the ATM networks, and report the performance evaluation of the proposed interconnection scenarios; then, we present some preliminary simulation results on the ABR service, whose implementation needs a sophisticated reactive congestion control to obtain an acceptable quality of service.

Multipoint-to-multipoint ABR service in ATM

This dissertation investigates and improves the performance of the point-to-multipoint Available Bit Rate (ABR) service in ATM networks. We propose two new consolidation algorithms called "Rate-Queue Balanced" (RQB) and "Selective Backward Resource Management Feedback" (SBF). The RQB employs the Explicit Rate (ER) and Queue Length (QL) field in Backward Resource Management (BRM) cell as parameters to compute a Response-Accuracy Index (RAI) at a branch point. The RQB algorithm is adaptive to the network condition and the branch point uses it as an indication rather to work in a fast response or high accuracy way, however, at a little more expenses of buffer size in branch point nodes. SBF is an effective capacity tracking algorithm that can function in dynamic network scenarios. It achieves a fast response and low consolidation noise by selectively forwarding BRM cell from the most congested branch to the source instead of waiting for BRM cell from all branches. Simulation results show that the proposed algorithms outperform the already existed schemes in terms of response time and consolidation noise. The performance, i.e. the response time and Allowed Cell Rate (ACR) of the source is mathematically analyzed. They show relatively good agreement with the simulation results and can be applied for using in various network topologies. In addition, in this dissertation, the interoperability issue for the multicast ABR services is investigated. We address on a response time, a consolidation noise and an effect of asymmetrical Round Trip Delay (RTD) from branch point to destinations aspects. We found from the simulation results that the consolidation algorithm used at the most upper stream branch point (the nearest one to the source), especially in WAN configuration, plays an important role in determining the performance of the network. While consolidation algorithm used at the lower stream branch point affects the network performance insignificantly In LAN/MAN environment, due to a small difference in time delay, we can say that the consolidation algorithm insignificantly affects the network performance. Therefore, implementation simplicity of the consolidation algorithms should be a major consideration issue for employing to this kind of network.

One of the functions that should be provided in ATM LANs is multicast communication. For multicast communication on ATM LANs, the architecture of the switch fabric and protocols for signaling have been studied. However, when data communication using a multicast connection such as a LAN emulation service which expects the high throughput is provided, ABR (available bit rate) service on a multicast connection (multicast ABR) is also required. ABR service has been actively discussed in the ATM Forum. Unfortunately, the study on flow control mechanism for multicast ABR is not sufficient. This paper discusses a suitable flow control mechanism for multicast ABR and shows its performance. At first, it summarizes the approaches for the flow control and describes the outline of the proposed mechanism based on the suitable approach. Next it evaluates the performance and shows the effectiveness of the mechanism by simulations. Moreover, after pointing out the importance of operations in the case of link failures on the multicast tree, it discusses the cooperation in this case between the flow control and the related functions to detect these failures.

In recent years, there has been a strong interest in transmitting compressed video over packet switched networks, such as asynchronous transfer mode (ATM). Previous work has dealt with transmitting MPEG over constant bit rate (CBR) and variable bit rate (VBR) services of ATM. The available bit rate (ABR) service of ATM is expected to be much more cost effective than CBR or VBR. However, there hasn't been much work done on running interactive client/server applications (for example, video on demand) over ABR. We have developed a framework to design interactive video systems transmitting MPEG video over the ATM ABR service. We have developed models to determine the network connection parameters required to run interactive client/server multimedia applications over an ATM network using the ABR service. We solve our model using real-time dynamic equilation (RTDE) analysis. We conclude that by proper dimensioning of the buffers at the client and the server, it is possible to run interactive video over the ATM ABR service.

High speed networks based on the asynchronous transfer mode (ATM) will use the available bit rate (ABR) service to support best effort type service. The ABR service will use an end-to-end adaptive feedback based rate control, where the sources adapt their rates (at the cell level) based on the state of the network. The performance of this control mechanism depends on a number of control parameters, as well as the delay of the feedback loop. We analyze the feedback based rate control mechanism (as defined by the ATM Forum) and obtain closed-form (approximate) solutions. These design equations will aid in determining appropriate values for the various control parameters.

This article describes a data rate control system, based on the use of fuzzy controllers, for efficient utilisation of the capacity of the network by connections in the available bit rate (ABR) service category. The control system adapts to the changes of the load produced by constant bit rate and variable bit rate (VBR) connections and shares the available capacity of the network fairly between ABR connections. Results of simulations based on statistical traffic distributions, consisting of several VBR and ABR connections, show the adaptability and efficiency of the fuzzy control system.

We propose a congestion control algorithm and design a state feedback controller for regulating the congestion of available bit rate (ABR) traffic in asynchronous transfer mode (ATM) networks. ABR service is specified as the rate-based feedback mechanism for congestion control and provides a control signal to throttled sources from a bottleneck node in order to adjust the throttled source rates based on available capacity. Our main purposes are as follows: (1) to design a state feedback controller; (2) to place the closed-loop poles in any desired regions based on a pole placement constraint; (3) to use the LMI (linear matrix inequalities) approach for finding the optimal state feedback gain K. The simulation results show that, under pole placement and LMI approaches, our state feedback congestion controller for ABR traffic in ATM networks can possibly guarantee the system stability, provide no buffer overflow, determine the optimal source traffic rates and place the closed-loop poles in any desired regions as well.

A rate-based congestion control algorithm regulates cell emission rate of source end systems based on feedback information from the network. It was standardized by the ATM Forum for application to an ABR (available bit rate) service class. In the standard, two types of congestion notification methods of the switch are specified: EFCI marking and explicit-rate marking. In this paper, we focus on the explicit-rate marking switch. We propose our enhancements on a recently proposed switch algorithm known as the max-min scheme. The main objective of our enhancements is to control the queue length of the switch for preventing cell loss and achieving full link-utilization. We show the effectiveness of our switch algorithm by simulation experiments.

Performance of TCP in IP/ATM internetworks

The study pursues a discrete stability analysis of a control algorithm for the available bit rate (ABR) service, denoted proportional rate and queue control algorithm (PRQCA), applied on an ATM system using FCFS scheduled switch buffers for the ABR traffic. The analysis establishes a stability condition for the control parameters of the PRQCA by using a control theoretic approach to the feedback control. The discrete model enables an implicit relation between the control parameters and the sample rate of the system, which is not possible in a continuous time model. Furthermore, for cases with different feedback delays, a mean value approximation, denoted effective delay, is introduced to replace the individual feedback delays in the analysis. A relation is derived to set the additive increase rate parameter (AIR) to avoid initial oscillations during low rates of backward resource management (RM) cells without affecting the dynamics during sufficient RM cell rates. An enhancement of the algorithm used to estimate the fair share rate (CCR averaging), is introduced to enable a mix of connections with and without rate constraints in the system while the reference values for both the rate and the queue length are still met.

This paper investigates the performance of relative rate marking (RRM) switch algorithms for rate-based available bit rate (ABR) service in asynchronous transfer mode (ATM) networks. An RRM switch can be implemented differently according to the congestion detection and notification methods used. The performance of an RRM switch strongly depends on the choice of the control parameters and the congestion detection scheme used. We introduce two implementation schemes for an RRM switch, and then analyze the maximum and minimum queue lengths for each scheme in steady state. Furthermore, we derive the closed form equations of link utilization and cell loss probability. The analytical results presented can be used to estimate the buffer requirement and to determine appropriate values for the various control parameters.

We propose a novel explicit rate flow control algorithm intended for available-bit-rate (ABR) service on an ATM network subject to loss and fairness constraints. The goal is to guarantee low cell loss in order to avoid throughput collapse due to retransmission by higher level protocols. The mechanism draws on measuring the current queue length and bandwidth availability, as well as tracking the current number of active sessions contending for capacity, to adjust an explicit bound on the source transmission 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 conservative design rules might be relaxed by accounting for statistical multiplexing in bandwidth sharing among bursty ABR sources and variable-bit-rate (VBR) sources.

Switch design for ATM (Asynchronous Transfer Mode) networks needs to take a fresh approach in order to support ABR (Available Bit Rate) services efficiently. In particular, ATM switches designed for data communications should implement flow control functions to prevent data loss while minimizing required memory. These new requirements make the design of ATM switches fundamentally different from that of traditional switch design.

In this paper we present an abstract, rigorous game-theoretic framework for rate-based control of Available Bit Rate (ABR) services in ATM networks. The framework is based on the idea of the Nash arbitration scheme in cooperative game theory which not only provides the rate settings of users which are Pareto optimal from the network point of view of but are also consistent with the fairness axioms of game theory. We first consider the centralized problem and then show that this procedure can be de-centralized such that users can perform the optimization locally such that the overall rates are network optimal. We then consider the problem of charging of ABR connections considering users’ valuations for the best-effort service. We propose a flat-rate charging policy such that the total network revenue is maximum.