Cell Loss Ratio Research Articles

Estimation-based call admission control with delay and loss guarantees in ATM networks

Call admission control (CAC) has been accepted as a potential solution for supporting a variety of traffic sources demanding different quality of service guarantees in asynchronous transfer mode networks. Basically, CAC is required to consume a minimum of time and space to make call acceptance decisions. In the paper a CAC algorithm is presented based on a novel estimation method, called quasilinear dual-class correlation (QLDC). All heterogeneous traffic calls are initially categorised into various classes. According to the number of calls in each traffic class, QLDC conservatively and precisely estimates the cell delay and cell loss ratio for each traffic class via simple vector multiplication. These vectors are computed in advance from the results of three dual arrival queuing models, M[N1] + I[N2]/D/1/K, M1[N1] + M2[N2]/D/1/K and I1[N1] + I2[N2]/D/1/K, where M and I represent the Bernoulli process and the interrupted Bernoulli process, respectively. Consequently, the authors' QLDC-based CAC, as will be shown, yields low time complexity O(C) (in vector multiplications) and space complexity O(WC2) (in bytes), where C is the total number of traffic classes and W is the total number of aggregate load levels. Numerical examples are also employed to justify that QLDC-based estimated results profoundly agree with simulation results in both the single-node and end-to-end cases.

Performance Evaluation of a Logical Link Control Protocol for an ATM Air Interface

The paper deals with error control proceduresbased on repetitions necessary for an ATM air interface,which enables a full integration of wireless (W) ATMterminals into a fixed ATM network. The architecture and functionality of an additional LLC layer atthe air interface are explained. A set of ARQ protocolsfor the different ATM service classes is investigated.The protocol for VBR services is able to control the number of retransmissions depending on therequirements on maximum delay and residual cell lossratio. It also takes into account instantaneousconditions such as channel load from other sources.Furthermore, the protocol is able to discard ATM cells toavoid and resolve congestion. The performance of theprotocol has been evaluated by simulations.

Hybrid cell loss concealment methods for MPEG-II-based packet video

Abstract This paper proposes two hybrid codec systems to encode MPEG-II-based packet video. Two-layer coding for ATM transmission has two primary disadvantages: (1) the total bit-rate is increased compared with one-layer coding at the same picture quality; (2) the cell loss caused by the network traffic needs to be dealt with. To reduce the total bit-rate and avoid error propagation, we develop two different layer coding schemes and concealment methods for intracoded macro blocks (MBs) and intercoded MBs. The first proposed system has better concealment for impaired area that makes it more tolerant to higher cell-loss ratio, whereas the second one generates lower bits, but it has the disadvantages of temporal error propagation. In the experiments, we compare our method with previous ones (Ghanbari and Seferidis, 1993; Wada, 1989; Lee et al., 1993; Zhu et al., 1993) and illustrate that our two-layer codec gives a lower bit-rate and produces better error concealment.

Impact of QOS requirements on video coding for ATM networks

The broadband integrated services digital networks (B-ISDN) based on asynchronous transfer mode (ATM) technology can support a wide range of applications such as voice, video, still images, and data. Compression techniques increase the effective bandwidth utilization, but the bursty and asynchronous nature of the traffic can still lead to congestion in the network, and degradation of image quality and quality of service (QOS). Some of the features to provide better coding schemes for ATM networks are layered coding, resynchronization, buffering, interleaved schemes, constrained bit rate due to buffers, encapsulation with the RTP or AAL1 for clock recovery, lapped transforms, motion compensation, and optimal bit allocation for coders based on wavelet transforms. We review various techniques forimage and video coding such as transforms, motion compensation, vector quantization, and subband coding. We outline the impact of the cell loss ratio (CLR), delay and cell delay variation (CDV) on video coding: blocking effects, loss of frame synchronization, motion vectors, and vector quantization codewords. The open problems include tuning coding parameters to the available QOS provided by the network.

Policing and traffic shaping at the user-network-interface (UNI)

A network's decision to accommodate a new ATM connection is based in part on sustained and peak cell rate and peak duration declared by the user in the connection request. As these traffic descriptors are onlyprojections of the traffic, connection admission control must be supplemented by input rate control in order to monitor and regulate theactual traffic. None of the proposed input rate control schemes enforces multiple traffic parameters. Additionally, traffic shaping at the UNI based on regulating average and peak rates may enhance statistical multiplexing performance. This paper presents a performance analysis of the two-stage entry monitor combining a sticky bufferpolicer with aspacer. To the best of our knowledge,no analysis of tandem policers has appeared before this paper. The first stage enforces the sustained rateR/T negotiated in the connection request; the spacer shapes the traffic and controls burstiness by further ensuring that cells enter the network at leastS slots apart. We derive the probability generating function for the combined queue length distribution and evaluate numerically (i) the manner in whichS and burstiness affect the cell-loss probability, and (ii) the performance penalty caused by enforcing two rates. The principal contribution of this paper is the calculation of the buffer size required to police two parameters subject to a specified cell-loss ratio. Our principal conclusion is that the increase in buffer size needed to police the peak sustained rate in addition to the sustained rate is minimal. We will also demonstrate that the leaky bucket and the single-stage sticky buffer have comparable performance, enabling us to conclude that a two-stage sticky buffer can police both peak and sustained rates for almost the same cost as a leaky bucket.

Performance Studies of Real-Time Communications in ATM Networks

This paper presents a performance study of ATM Network in support of realtime multi-media traffic. Multiple classes of traffic with different real-time requirement will be used in the study. The performance of the ATM switch is examined in terms of cell missing ratio due to deadline missing and cell loss ratio due to buffer overflow in both switch and gateway as well. A higher level of abstraction in terms of burst loss ratio will also be collected. The results indicated that first-come-first-serve scheduling algorithm is insufficient to handle real-time traffic. This paper presents a better method to improve the performance significantly especially when the virtual path bandwidth negotiated is conservative.

SIMULATION AND MODELLING OF VARIABLE BIT RATE MPEG VIDEO TRANSMISSION OVER ATM NETWORKS

This paper proposes an efficient transmission mechanism based on frame spreading, for variable bit rate (VBR) MPEG compressed video, through an asynchronous transfer mode (ATM) multiplexer, such as a cable head-end. We implement a priority scheme in a software MPEG encoder which produces proportionate traffic in both (i.e. high and low) priority partitions for all three types of video frames used in MPEG, i.e. intraframe (I), predicted (P) and bidirectionally interpolated (B). Furthermore, we simulate an ATM multiplexing scheme with a pushout buffer mechanism providing priority scheduling at the multiplexer for the two video partitions. We load the multiplexer with VBR MPEG traffic and collect performance statistics such as the cell loss ratios for various frame spreading scenarios. In order to study the transmission mechanisms via simulation, we develop two statistical models, using the transform-expand-sample technique (TES) for VBR MPEG video with two levels of priority. The first model is matched with the empirical histogram and autocorrelation function of each frame type (I, P and B). The second model is created with the assumption of a gamma distribution for the number of bits in each frame type. We conduct experiments using both models and compare the results.

Performance studies of real-time communications in ATM networks

This paper presents a performance study of ATM networks in support of multi-media traffic with different real-time requirements. The performance of the ATM switch is examined in terms of cell missing ratio due to missed deadlines, and cell loss ratio due to buffer overflows, in both switches and gateways. A higher level of abstraction in terms of burst loss ratio will also be included. The results indicate that a first-come-first-serve scheduling algorithm is insufficient to handle real-time traffic. This paper presents a better method, that significantly improves the performance, especially when the negotiated virtual path bandwidth is conservative.

AN ATM‐LIKE SYSTEM ARCHITECTURE FOR SATELLITE COMMUNICATIONS INCLUDING ON‐BOARD SWITCHING

In this paper, an ATM system architecture for satellite communications is described. The proposed architecture includes an on-board switch and implements the adaptation of real-time services (e.g. voice and video) and non-real-time services (e.g. data) to the satellite communication link, while achieving statistical advantage. To this end, the ATM traffic categories defined in recent specifications1,2 are utilized. Real-time and non-real-time traffic components are simultaneously supported by a TDMA/TDM on the satellite uplink/downlink, respectively. By exploiting the burstiness of real-time traffic, the proposed satellite system architecture achieves a significant increase of the overall system throughput. After describing the satellite system architecture and addressing scheme, we derive analytical models, by using sophisticated queueing models that allow a very accurate performance evaluation and an easy dimensioning of the data buffers. The proposed model is validated with simulations. The main result is the assessed feasibility of on-board buffers with current technology, even under very strict performance requirements on cell loss ratio and for quite high load values (e.g. 80 per cent of the downlink capacity). Finally, a congestion control scheme, based on a combination of preventive and reactive strategies, is proposed and analysed.

Experimental validation of an ATM traffic control framework in the EXPLOIT testbed

AbstractThis paper deals with the experimental investigation of a preventive traffic control framework for ATM networks as implemented in the EXPLOIT Testbed. This framework comprises a Usage Parameter Control (UPC) function and a Connection Admission Control (CAC) function. The obtained measurement results are complemented and compared with simulation studies and analytical results. For several On/Off traffic types it is shown that the implemented UPC function enforces both the Peak Cell Rate (PCR) and the Sustainable Cell Rate (SCR) simultaneously. By measuring the cell loss ratio as a function of the number of multiplexed sources, admission boundaries for a given network performance objective can be found and compared with the implemented CAC function based on the convolution algorithm. It appears that network performance objectives can be guaranteed, while exploiting most of the possible multiplexing gain in a network with small buffers like the EXPLOIT Testbed. Finally, it is shown that the two co‐operating functions constitute a traffic control framework which is robust against traffic contract violations as well as worst case traffic utilising the contracted UPC function tolerances maximally at both the cell level and the burst level.

In-service monitoring for cell loss quality of service violations in ATM networks

A new method for in-service cell loss ratio (CLR) QoS estimation for asynchronous transfer mode (ATM) networks has been developed. For a typical CLR, a large number of cells must be observed before statistically meaningful results can be achieved. These results may be obsolete resulting in ineffective network management reactions. For a variety of arrival processes, many analyses have shown there exists a relationship between the logarithm of the cell loss probability and buffer size. For models that do not possess long-range dependence, this relationship is often linear. On the other hand, for the fractional Brownian motion model that captures long-range dependent traffic behavior, this relationship has a polynomial form. The proposed method uses these relationships and observations of cell loss for several small pseudo-buffers to characterize the behavior of the actual system. Specifically, a real-time technique to dynamically detect the failure of meeting a cell loss quality of service (QoS) objective has been developed. The method requires a short observation period and is suitable for in-service monitoring of CLR QoS. Simulation studies show the effectiveness of this method for both modeled traffic and measured network trace data.

UPC/NPC algorithm for guaranteed QoS in ATM networks

In Broadband Integrated Services Digital Networks (B-ISDN) based on the Asynchrous Transfer Mode (ATM) technology, the required Quality of Service (QoS) must be guaranteed for connection. Cell loss ratio, which is one of the QoS parameters specified by the user in an ATM traffic contract of connection, may depend on the traffic enforcement mechanism known as the Usage Parameter Control/Network Parameter Control (UPC/NPC) or traffic policing. If two UPC/NPC algorithms are not equivalent with respect to cell discarding/tagging for a given traffic configuration, a common understanding about legality between the user and the network operator does not exist. To cope with this legality problem, the concept of cell conformance has been developed by the International Telecommunication Union-Telecommunication Standardization Sector (ITU-T). However, the Cell Loss Priority (CLP) bit, which ITU-T introduced in the ATM cell header to discriminate between a high priority cell (CLP = 0) and a low priority cell (CLP = 1), may cause the measurement phasing problem in cell conformance testing in ATM networks. This makes it difficult for a network provider to define and commit cell loss ratio as a QoS parameter. In this paper, we investigate measurement phasing problems and difficulties in commitment of the cell loss ratio in ATM networks. We propose a QoS guaranteed UPC/NPC algorithm to commit the cell loss ratio, and show an example of applications of the proposed UPC/NPC algorithm.

The asymptotic behavior of queueing systems: Large deviations theory and dominant pole approximation

This paper presents the exact asymptotics of the steady state behavior of a broad class of single-node queueing systems. First we show that the asymptotic probability functions derived using large deviations theory are consistent (in a certain sense) with the result using dominant pole approximations. Then we present an exact asymptotic formula for the cumulative probability function of the queue occupancy and relate it to the “cell loss ratio”, an important performance measure for service systems such as ATM networks. The analysis relies on a new generalization of the Taylor coefficients of a complex function which we call “characteristic coefficients”. Finally we apply our framework to obtain new results for the M/D/1 system and for a more intricate multiclass M/D/n system.

ATM network testing and measurement

This contribution addresses some very general problems of testing and measuring in ATM networks. The paper outlines important aspects of the basic types of test such as conformance, functionality and performance. Furthermore, it highlights the several aspects and problems of tests at the level of an interface, a switch and a whole network. As ATM traffic has almost no structure, it is impossible to make rules for testing and measurement from traffic modeling. We demonstrate the limitations of the standardized performance parameters, which are generally used as estimators. This e.g. shows that it is possible to obtain with the same estimator completely different cell loss ratios for the same traffic flow.

Analysis of a discrete-time queue with general three-state Markovian traffic sources

In this paper, we analyze the performance characteristics of an ATM switch, where cell arrivals are generated according to a three-state Markovian arrival law. This arrival process is an extension for the two-state ON/OFF source model that has already been extensively treated in the literature, and it allows a much more flexible modeling of a wide variety of VBR sources. As a result, for the finite storage capacity case, the system contents distribution, as well as the cell loss ratio are derived. On the other hand, for the infinite storage capacity case, a method for deriving an expression for the probability generating function of the system contents is presented. Furthermore, an approximation (consisting of multiple geometric terms) for the tail distribution of the system contents is given. The accuracy of this approximation as well as the impact of the traffic parameters on the buffer behavior are discussed via some numerical examples.

Revenue maximization in ATM networks using the CLP capability and buffer priority management

The cell loss priority (CLP) bit in the header of the ATM cell may be used either by the network to tag noncompliant cells, or by the application to declare two levels of quality-of-service (QoS) within the same virtual circuit (VC). We study the possibility of the use of this bit by the application alone. An application can offer two types of traffic streams to the network, namely, a precious traffic stream (with stringent QoS requirements, e.g., cell loss ratio (CLR) <10/sup -9/ and identified by the CLP bit=0) and a less precious stream (CLP=1 and less stringent QoS requirements, e.g., CLR <10/sup -4/). We study the performance of an ATM multiplexer with two traffic classes with different QoS requirements. The buffer priority schemes adopted are partial buffer sharing (PBS) and PBS+push-out (PO). We first obtain the engineering trade-off curves, between CLP=0 and CLP=1 traffic. To identify an operating point, we formulate a revenue optimization problem in which the constraints are the engineering trade-off curve and a simple model of the variation of CLP=1 demand with its price.

An approximate analytical technique for the performance evaluation of ATM switching elements with burst routing

In this paper we consider an ATM (Asynchronous Transfer Mode) switching element with output queueing. One separate infinite-capacity output buffer is used for each possible destination (output). The cell arrival processes on the inlets of the switching element are of a bursty nature. Specifically, geometrically distributed on/off-periods are assumed to describe this burstiness. Cells are routed from the inputs to the outputs of the switching element in a uniform but correlated manner, i.e., all cells belonging to the same on-period are routed to the same destination, but all destinations are equiprobable. The queueing performance of the switch is analyzed here by a combination of analytic techniques and approximations. Close analytic upper bounds are obtained for such measures as the means and the tail distributions of the buffer contents and the cell delay in a tagged output buffer. The formulas are easy to evaluate and the results are useful in practice, for instance, to calculate the cell loss ratio or the delay jitter in an output queue. The influence of the degree of burstiness in the cell arrival processes is investigated. Also, the results are compared with the case of uncorrelated routing.

Packet loss resilience of MPEG-2 scalable video coding algorithms

Transmission of compressed video over packet networks with nonreliable transport benefits when packet loss resilience is incorporated into the coding. One promising approach to packet loss resilience, particularly for transmission over networks offering dual priorities such as ATM networks, is based on layered coding which uses at least two bitstreams to encode video. The base-layer bitstream, which can be decoded independently to produce a lower quality picture, is transmitted over a high priority channel. The enhancement-layer bitstream(s) contain less information, so that packet losses are more easily tolerated. The MPEG-2 standard provides four methods to produce a layered video bitstream: data partitioning, signal-to-noise ratio scalability, spatial scalability, and temporal scalability. Each was included in the standard in part for motivations other than loss resilience. This paper compares the performance of these techniques (excluding temporal scalability) under various loss rates using realistic length material and discusses their relative merits. Nonlayered MPEG-2 coding gives generally unacceptable video quality for packet loss ratios of 10/sup -3/ for small packet sizes. Better performance can be obtained using layered coding and dual-priority transmission. With data partitioning, cell loss ratios of 10/sup -4/ in the low-priority layer are definitely acceptable, while for SNR scalable encoding, cell loss ratios of 10/sup -3/ are generally invisible. Spatial scalable encoding can provide even better visual quality under packet losses; however, it has a high implementation complexity.

Parallel simulation of statistical multiplexers

The simulation of high-speed telecommunication systems such as ATM (Asynchronous Transfer Mode) networks has generally required excessively long run times. This paper reviews alternative approaches using parallelism to speed up simulations of discrete event systems, and telecommunication networks in particular. Subsequently, a new simulation method is introduced for the fast parallel simulation of a common network element, namely, a work-conserving finite capacity statistical multiplexer of bursty ON/OFF sources arriving on input links of equal peak rate. The primary performance measure of interest is the cell loss ratio, due to buffer overflows. The proposed method is based on two principal techniques: (1) the derivation of low-level (cell level) statistics from a higher level (burst level) simulation and (2) parallel execution of the burst level simulation program. For the latter, atime-division parallel simulation method is used where simulations operating at different intervals of simulated time are executed concurrently on different processors. Both techniques contribute to the overall speedup. Furthermore, these techniques support simulations that are driven by traces of actual network traffic (trace-driven simulation), in addition to standard models for source traffic. An analysis of this technique is described, indicating that it offers excellent potential for delivering good performance. Measurements of an implementation running on a 32 processor KSR-2 multiprocessor demonstrate that, for certain model parameter settings, the simulator is able to simulate up to 10 billion cell arrivals per second of wallclock time.

Deterministic rule based traffic descriptors for broadband ISDN: Worst case behaviour and its impact on connection acceptance controls

AbstractDeterministic rule based traffic descriptors in general, and leaky bucket based (LBB) traffic descriptors in particular, offer many advantages over statistical descriptors for specifying and monitoring traffic in the ATM based broadband ISDN (BISDN). However, these traffic descriptors do not specify the traffic pattern uniquely. Thus, acceptance of a connection request with specific traffic descriptor parameter values implies that the network has agreed to guaranteeing the quality of service (QOS) for the worst case traffic compliant with the traffic descriptor (and hence allowed by the monitor). This poses challenges which have not been addressed adequately. Two of the important ones are: (i) definition of the worst case behaviour and characterization of the worst case traffic compliant with the traffic descriptor; (ii) connection acceptance controls (CAC) for the worst case traffic sources compliant with the traffic descriptors. In this paper we address these questions for leaky bucket based (LBB) traffic descriptors. The focus is on the first problem. The implications on the second problem are discussed briefly. The performance measure and QOS requirements are in terms of the cell loss ratios.We first define the worst case behaviour for homogeneous and heterogeneous environments in terms of collective cell loss ratio (CLR)) from the multiplexer. We consider both the unbuffered and buffered cases. However, most of the results here are for the unbuffered case. FOTthe case of an unbuffered multiplexer and homogeneous source environment, we show that a simple on‐off source represents the worst case behaviour of an LBB source. In a heterogeneous source traffic environment, the on‐off behaviour is the worst only in a limited sense and the use of a collective measure results in anomalous relationships between the source behaviour and the CLR. A more appropriate measure should be based on individual cell loss ratios or on the maximum of the individual CLRs. We analyse LBB sources with respect to these measures and unbuffered resources, and obtain further characterization of the worst case behaviour. However, we also uncover some counter‐intuitive relationships. In particular, a seemingly ‘smooth’ source may be worse for the other sources than a seemingly ‘bursty’ source.For a buffered multiplexer, we show, via an example, that a three‐state source may be worse than an on‐off source even in a homogeneous source traffic environment. A complete characterization of the worst case behaviour for a buffered multiplexer remains an open challenge. Moreover, the LBB sources exhibit deterministic behaviour and their equivalent bandwidth need not be sub‐additive in sources. That is, adding the equivalent bandwidths of individual sources to obtain an ‘estimate’ of the equivalent bandwidth for a collection of such sources could be too optimistic in some situations. A fresh look at the connection acceptance control for such sources is therefore warranted.