Evaluation of congestion control protocols for ABR traffic over ATM networks

Congestion control is very important for effective and stable operation of ATM (Asynchronous Transfer Mode) networks. Owing to the bursty and unpredictable characteristic of data network traffic, its congestion control is particularly a challenge for network researchers and designers. The ATM Forum has recently adopted rate‐based congestion control for ABR (Available Bit‐Rate) traffic which is the service class defined for data network applications. However, there is a number of congestion control schemes prevalent. ATM Forum has decided not to specify switch behaviour for ABR traffic; this has further introduced additional ambiguity. Consequently, an evaluation and comparison of the existing protocols would provide valuable guidance for network designers and engineers; it would also give insight for researchers to explore the essence of different congestion control schemes. In the first part of this paper, we investigate the effectiveness of ABR congestion control in the presence of bursty source traffic and the relationship between the burst time scale and the ABR control time scale. Two ABR congestion control schemes, the ABR Explicit Forward Congestion Indication (EFCI) and ABR Congestion Indication (CI) schemes, are compared with Unspecified Bit Rate (UBR) transport which makes no effort to control congestion. Traffic sources of various burst lengths of 100, 1000, 10000, and an equal mix of 100 and 10000 ATM cells are used in simulations. It is found that ABR congestion control schemes effectively control low frequency, medium to long‐term traffic load transients. This is further supported by the result of integrating TCP over ATM congestion control schemes included in the paper. ABR control schemes do not control high frequency, short‐term load transients well, but ABR control is not necessary in such cases since short‐term transients do not require a large amount of buffering. In the second part of this paper, we evaluate and compare six rate‐based congestion control protocols including Scheme I: EFCI, Scheme II: EFCI with separate RM queues, Scheme III: CI, Scheme IV: CI with separate RM queues, Scheme V: the CAPC2 ER (Explicit Rate), and Scheme VI: the EFCI with utilization‐based congestion indication. Each scheme is simulated and compared in the LAN, WAN, and GFC (General Fairness Configuration) environments specified by the ATM Forum. Effects of varying VC (Virtual Circuits) number and changing endsystem–switch distance has been investigated. Their fairness is also compared using the GFC configuration. We have found that ER control scheme performs significantly better than the other five binary control schemes by its faster response to congestion, smoother regulation of bit‐rates, lower queueing delay, shorter buffer queue length, and fairness. Among the other five schemes, the CI scheme performs better than the EFCI scheme. Providing separate RM queues has significantly improved the EFCI scheme in the WAN environment, but has little effect on the CI scheme. Link utilization‐based congestion detection has suffered from either low utilization or an excess cell loss which is unacceptable in most data applications. Copyright © 2000 John Wiley & Sons, Ltd.     

Parameter tuning of rate-based congestion control algorithm for ABR service class in ATM networks

A rate-based congestion control algorithm has been developed and standardized in the ATM forum for ABR service class. In the standard the behaviour of source and destination end systems is specified by several control parameters such as RIF (rate increase factor) and RDF (rate decrease factor). In spite of the fact that the performance of the rate-based congestion control algorithm depends heavily on the selection of these control parameters, no selection method of parameters is shown in the standard. In this paper, by extending our previous work, appropriate settings of rate-control parameters in the various circumstances are investigated. We first analyse the dynamical behaviour of the rate-based congestion control for multiple groups of ABR connections with different propagation delays. Next we evaluate the effect of CBR traffic on ABR connections. Simulation results for a multihop network configuration are also presented to exhibit the trade-off relationship among cell loss probability, link utilization and fairness. Finally, a selection method of control parameters in the multihop network is proposed based on our analytic methods and simulation results © 1998 John Wiley & Sons, Ltd.     

A simple,scalable and provably stable explicit rate computation scheme for flow control in communication networks

This paper describes fast rate computation (FASTRAC), an explicit rate flow control algorithm for available bit rate (ABR) traffic. Using digital control theory, we develop a simple rate controller for the ABR flow control process. We prove that the controller is stable, fair to all participating sources and configurable with respect to responsiveness. The analysis presented shows that stability of the flow control process depends primarily on two factors, the control update rate and the feedback delay. The implementation of the proposed algorithm is much simpler than other fair rate allocation algorithms. The proposed algorithm demonstrates the ability to scale with speed, distance, different feedback delays, number of users, and number of nodes while remaining robust, efficient, and fair under stressing and dynamic traffic conditions. Copyright © 2001 John Wiley & Sons, Ltd.     

The distributed robust traffic controller for ATM networks

We propose an approach to design a distributed rate‐based traffic controller to flow‐regulate the best‐effort service (e.g. ABR) traffic and guaranteed service traffic through an ATM switch. The controller is distributed among the source nodes and has a very simple structure. Its local controller at each source node is open‐loop stable and only requires the knowledge of the buffer occupancy at the bottleneck switch. We show that this controller is fair and is not sensitive to the change of VCs over time. It does not have oscillation and can achieve a high utilization. Copyright © 2001 John Wiley & Sons, Ltd.     

A flexible MAC protocol for the integration of high- and low-quality video streams, voice and data traffic over high-speed packet switched wireless networks

In this work, we propose and evaluate mechanisms for the multiplexing and the integrated delivery of various traffic types such as video, data and voice, over a wireless cellular high-speed packet switched network. Two different scenarios are examined where the video traffic results from videoconference sessions and high-quality media playback, respectively. In both cases we focus on the uplink channel and we thoroughly investigate, by using actual MPEG-4 video streams, the system's performance under a variety of possible loads. Our goal is to achieve high-aggregate channel throughput while preserving the quality of service requirements of each traffic type.     

Temporal placement control of video frames in ATM networks

In this paper, we propose a new method of traffic smoothing for frames of different video sources. We assume that each video source transmits frames at fixed intervals and that the network is free to decide the relative temporal spacing of video frames from different sources. This means that the time at which a given source begins to transmit its first frame is under the control of the network; however, after that, all frames from this source are transmitted at fixed intervals. We now address two questions. What are some reasonable policies for spacing the frames of video sources? What is the performance advantage of doing this? We propose three control policies (two heuristic and one based on an optimization problem via some Fourier analysis). These are compared against the case in which the video frames from different sources are randomly distributed (i.e. no control is exercised). We show that significant performance advantages accrue if one controls the temporal placement of the video frames from different sources.     

基于神经网络的ATM网络多媒体流拥塞控制

提出了一种在用户-网络接口（UNI）处利用神经网络方法实现ATM网络多媒体流拥塞控制的新方法。在该方法中，控制器输出为信源编码率及其对应的用户百分比，即根据信源编码率及对应的用户百分比调整进入复用缓冲器多媒体流速率，从而克服了以往拥塞控制方法中仅仅调整编码率带来的对所有信源进行整体调整的缺陷，使摔制系统在信元丢失率最小情况下保证了多媒体流的质量，从而有效地利用了网络资源。本文还给出了两种实现方式，方式1中，神经网络输出层变量包括编码率及对应用户百分比，由连续编码率量化成离散值；方式2中，神经网络输出层变量只有连续的编码率，然后通过一定的换算公式计算出离散的编码率和对应的用户数。这两种实现方式中，方式1较为直观，但比方式2复杂。对话音流、视频流的仿真表明方法的有效性。     

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. © 1997 John Wiley & Sons, Ltd.     

VBR wavelet video coding and its rate control in ATM networks

This paper presents a new video coding system based on wavelet transform and its rate control scheme over ATM networks. First, three dimensional wavelet transform is performed for the original image sequence, and an extension of set partitioning in hierarchical trees algorithm is employed to quantize the wavelet coefficients. Then, the output rate of the coder is controlled at group of frame scale, ensuring that it conforms to the parameters of a leaky bucket controller. Several leaky buckets with different sizes are discussed too. Simulation shows the efficiency of this codec and the effectiveness of the proposed rate control scheme.     

Comparison of different congestion control strategies for low priority controllable traffic in packet switched backbone networks

It is expected that a significant part of the data flows of future multi‐service packet switched backbone networks will use low priority, non‐real‐time data transmission services of the networks. The common benefit for both user applications and network operators is that the data flows of the low priority services could use the free capacity of the networks, after the load of higher priority data flows. Congestion control methods are needed for these low priority data flows to reach an optimal utilisation level of the networks, high throughput and low packet loss ratios. This kind of low priority data transmission service which adjusts the data rates of the data flows according to the data rate changes of higher priority data flows, but does not guarantee any specific service for these data flows, is called a controlled load service. In this paper, we have compared the performance, efficiency and scalability of four different congestion control methods designed for the controlled load service. Two of these methods were based on very simple congestion control algorithms and the other two used relatively complex control algorithms based on control methods utilising computational intelligence. The principal aim of this study was to research how remarkable were the effects that the different complexities of the congestion control methods had on the achieved level of service. The simulation tests indicate that the complexity of the methods clearly affects the performance and efficiency of the methods. Copyright © 2001 John Wiley & Sons, Ltd.     

Characteristics of ABR explicit rate control algorithms in WAN environments and an ABR control algorithm suitable for public networks

This paper investigates the characteristics of available bit rate (ABR) explicit rate control algorithms in wide area network (WAN) environments. An ABR service is expected to make more effective bandwidth utilization possible through closed loop congestion control, and several control algorithms have been proposed. However, in WAN environments a long propagation control delay will affect the effectiveness of the control algorithms. Additionally, if a network supports a large number of connections, some of the algorithms may not work well. Thus we have categorized the control algorithms according to their purpose and mechanism and have evaluated their characteristics by simulation in WAN environments from the viewpoint of throughput, robustness, quickness, stability and fairness. Based on this analysis, we have developed an ABR control algorithm suitable for public networks. © 1998 John Wiley & Sons, Ltd.     

An algorithm for sizing trunks carrying mixtures of constant and variable bit rate traffic

As new broadband networks based on the asynchronous transfer mode (ATM) protocol emerge to support a variety of services, the need for analytical models and tools for sizing network components carrying mixtures of different kinds of traffic will be increasingly felt. This paper presents a simple, yet efficient algorithm for sizing trunks carrying mixtures of constant and variable bit rate traffic. It combines theoretical results for the multi-dimensional Erlang model and the concept of equivalent bandwidth with some heuristic arguments to produce an analytic method for sizing trunks subject to blocking and quality of service constraints for traffic classes.     

A slotted multicode CDMA protocol for efficient integration of voice and data in cellular networks

This paper presents a novel radio channel structure based on slotted CDMA technology intended for carrying traffic with diverse bandwidth/QoS requirements in mobile environments, e.g. personal communication systems (PCS). The essence of our approach is a combination of flexible slotting with allocation of multiple codes to high‐bandwidth mobiles. As demonstrated by our performance studies, the proposed scheme efficiently integrates multiple traffic classes into a unified CDMA system. It is highly flexible and incurs low overheads for a wide range of realistic traffic conditions. Copyright © 2002 John Wiley & Sons, Ltd.     

Performance analysis of an improved soft preemptive scheme for unevenly distributed traffic in optical wavelength-division multiplexing networks

In optical wavelength-division multiplexing (WDM) networks, traffic can be unevenly distributed across the network causing inefficient utilization of resources. To solve this problem, an improved soft preemptive (SP) scheme is proposed by considering dynamic resource distribution to deal with the uneven network utilization. A novel unevenly distributed traffic model in cross-time-zone networks is also presented to evaluate the efficiency of the new scheme. Compared with other schemes such as normal shortest path first (SPF) routing and wavelength conversion (WC), the new proposed scheme results demonstrate significantly better performance with respect to the network utilization and overall network blocking probability.

Dynamic bandwidth partition schemes for integrated voice,video, and data traffic in the IEEE 802.11e distributed wireless LANs

In mobile cellular networks, bandwidth is deterministic in terms of the number of channels by frequency division, time division, or code division. On the other hand, bandwidth partition schemes in the contention‐based medium access control (MAC) in distributed wireless LANs are extremely challenging due to the contention‐based nature, packet‐based network, and the most important aspect: only one channel available, competed by an unknown number of stations. In this paper, we study this challenging issue. We propose and study four different bandwidth partition schemes for integrated voice/video/data traffic in the IEEE 802.11e wireless LANs: a Static bandwidth Partition (SP) scheme, a Dynamic budget Partition (DP) scheme, a Dynamic bandwidth Partition with Finer‐Tune (DP‐FT) scheme, and a Dynamic bandwidth Partition with Reserved Region (DP‐RR). The proposed schemes are compared and evaluated via extensive simulations. Results show that the DP‐FT scheme is the best scheme. Copyright © 2009 John Wiley & Sons, Ltd.     

An energy‐efficient localized topology control algorithm for wireless ad hoc and sensor networks

Topology control plays an important role in the design of wireless ad hoc and sensor networks and has demonstrated its high capability in constructing networks with desirable characteristics such as sparser connectivity, lower transmission power, and smaller node degree. However, the enforcement of a topology control algorithm in a network may degrade the energy‐draining balancing capability of the network and thus reduce the network operational lifetime. For this reason, it is important to take into account energy efficiency in the design of a topology control algorithm in order to achieve prolonged network lifetime. In this paper, we propose a localized energy‐efficient topology control algorithm for wireless ad hoc and sensor networks with power control capability in network nodes. To achieve prolonged network lifetime, we introduce a concept called energy criticality avoidance and propose an energy criticality avoidance strategy in topology control and energy‐efficient routing. Through theoretical analysis and simulation results, we prove that the proposed topology control algorithm can maintain the global network connectivity with low complexity and can significantly prolong the lifetime of a multi‐hop wireless network as compared with existing topology control algorithms with little additional protocol overhead. Copyright © 2008 John Wiley & Sons, Ltd.     

ARC: an integrated admission and rate control framework for competitive wireless CDMA data networks using noncooperative games

The competition among wireless data service providers brings in an option for the unsatisfied customers to switch their providers, which is called churning. The implementation of Wireless Local Number Portability (WLNP) is expected to further increase the churn rate (the probability of users switching the provider). However, the existing resource management algorithms for wireless networks fail to fully capture the far-reaching impact of this unforeseen competitiveness. From this perspective, we first formulate noncooperative games between the service providers and the users. A user's decision to leave or join a provider is based on a finite set of strategies. A service provider can also construct its game strategy set so as to maximize their utility (revenue) considering the churn rate. Based on the game theoretic framework, we propose an integrated admission and rate control (ARC) framework for CDMA-based wireless data networks. The admission control is at the session (macro) level while the rate control is at the link layer packet (micro) level. Two admission control modes are considered - one-by-one mode and batch processing mode, in which multiple users are admitted at a time. We show that: 1) for the one-by-one mode, the Nash equilibrium using pure strategy can be established for both under-loaded and fully-loaded systems and 2) for batch processing mode, there is either an equilibrium in pure strategy or a dominant strategy exists for the service provider. Therefore, the providers have clearly defined admission criteria as outcome of the game. Users are categorized into multiple classes and offered differentiated services based on the price they pay and the service degradation they can tolerate. We show that the proposed ARC framework significantly increases the provider's revenue and also successfully offers differentiated QoS to the users.     

Design and performance evaluation of an RRA scheme for voice‐data channel access in outdoor microcellular environments

In PCS networks, the multiple access problem is characterized by spatially dispersed mobile source terminals sharing a radio channel connected to a fixed base station. In this paper, we design and evaluate a reservation random access (RRA) scheme that multiplexes voice traffic at the talkspurt level to efficiently integrate voice and data traffic in outdoor microcellular environments. The scheme involves partitioning the time frame into two request intervals (voice and data) and an information interval. Thus, any potential performance degradation caused by voice and data terminals competing for channel access is eliminated. We consider three random access algorithms for the transmission of voice request packets and one for the transmission of data request packets. We formulate an approximate Markov model and present analytical results for the steady state voice packet dropping probability, mean voice access delay and voice throughput. Simulations are used to investigate the steady state voice packet dropping distribution per talkspurt, and to illustrate preliminary voice-data integration considerations. This revised version was published online in June 2006 with corrections to the Cover Date.