Results 1  10
of
44
Enforceable Quality of Service Guarantees for Bursty Traffic Streams
, 1998
"... Providing statistical qualityofservice guarantees introduces the conflicting requirements for both deterministic traffic models to isolate and police users and statistical multiplexing to efficiently utilize and share network resources. We address this issue by introducing two schemes for providin ..."
Abstract

Cited by 52 (7 self)
 Add to MetaCart
Providing statistical qualityofservice guarantees introduces the conflicting requirements for both deterministic traffic models to isolate and police users and statistical multiplexing to efficiently utilize and share network resources. We address this issue by introducing two schemes for providing statistical services to deterministically policed sources: (1) adversarial mode resource allocation in which we bound the stochastic envelopes of policed streams and provide a statistical service for adversarial or worst case sources and (2) nonadversarial mode allocation in which we approximate the stochastic envelopes of policed, but nonworstcase streams in order to exploit a further statistical multiplexing gain in the typical case. Our key technique is to study the problem within the domain of deterministic and stochastic traffic envelopes, which allows us to explicitly consider sources with rate variations over multiple time scales, obtain results for any deterministic traffic model, and apply accurate admission control tests for buffered priority schedulers. We evaluate the scheme’s performance with experiments using traces of compressed video and show that substantial statistical multiplexing gains are achieved.
Dynamic load distribution in the borealis stream processor
 In ICDE
, 2005
"... Distributed and parallel computing environments are becoming cheap and commonplace. The availability of large numbers of CPU’s makes it possible to process more data at higher speeds. Streamprocessing systems are also becoming more important, as broad classes of applications require results in real ..."
Abstract

Cited by 46 (5 self)
 Add to MetaCart
Distributed and parallel computing environments are becoming cheap and commonplace. The availability of large numbers of CPU’s makes it possible to process more data at higher speeds. Streamprocessing systems are also becoming more important, as broad classes of applications require results in realtime. Since load can vary in unpredictable ways, exploiting the abundant processor cycles requires effective dynamic load distribution techniques. Although load distribution has been extensively studied for the traditional pullbased systems, it has not yet been fully studied in the context of pushbased continuous query processing. In this paper, we present a correlation based load distribution algorithm that aims at avoiding overload and minimizing endtoend latency by minimizing load variance and maximizing load correlation. While finding the optimal solution for such a problem is NPhard, our greedy algorithm can find reasonable solutions in polynomial time. We present both a global algorithm for initial load distribution and a pairwise algorithm for dynamic load migration.
Interleaved Polling with Adaptive Cycle Time (IPACT): A Dynamic Bandwidth Distribution Scheme in an Optical Access Network.
 in an Optical Access Network,” Photonic Network Communications
, 2002
"... While in recent years backbone bandwidth has experienced substantial growth, little has changed in the access network. Last mile still remains the bottleneck between a high capacity LAN or home network and the backbone. Passive Optical Network (PON) is a technology viewed by many as an attractive ..."
Abstract

Cited by 29 (2 self)
 Add to MetaCart
While in recent years backbone bandwidth has experienced substantial growth, little has changed in the access network. Last mile still remains the bottleneck between a high capacity LAN or home network and the backbone. Passive Optical Network (PON) is a technology viewed by many as an attractive solution to this problem. In this study, we discuss and evaluate design issues for PON access networks. Specifically, to drive the cost of an access network down, it is very important to have an efficient, scalable solution. We believe that a PON based on polling, with data encapsulated in Ethernet frames, possesses the best qualities, such as dynamic bandwidth distribution, use of a single downstream and a single upstream wavelength, ability to provision a fractional wavelength capacity to each user, and ease of adding a new user. To support dynamic bandwidth distribution, we propose an interleaved polling algorithm. We then suggest a scheme for inband signaling that allows using a single wavelength for both downstream data and control message transmission. To obtain realistic simulation results, we generated synthetic traffic that exhibits the properties of selfsimilarity and longrange dependence. We then analyzed the network performance and its effect on various types of traffic, e.g., besteffort data traffic, VBR video traffic and CBR streams.
Nested AutoRegressive Processes for MPEGEncoded Video Traffic Modeling
 IEEE Trans. on CSVT
, 2001
"... This paper presents a new traffic model for MPEGencoded video sequences. The hybrid Gamma/Pareto distribution is used for all three types of frames in MPEGencoded video sequences, and the present model takes scene changes into account. The autocorrelation structure is modeled using two secondorder ..."
Abstract

Cited by 13 (0 self)
 Add to MetaCart
This paper presents a new traffic model for MPEGencoded video sequences. The hybrid Gamma/Pareto distribution is used for all three types of frames in MPEGencoded video sequences, and the present model takes scene changes into account. The autocorrelation structure is modeled using two secondorder autoregressive (AR) processes nested with each other. One AR process is used to generate the mean frame size of the scenes to model the longrange dependence, and another AR process is used to generate the fluctuations within the scenes to model the short range dependence. The parameters of the AR processes are estimated from measurements of empirical video sequences. Simulation results show that the present model captures the autocorrelation structure in the empirical traces at both small and large lags. The MPEG traffic model presented in this paper is used to predict the queueing performance of single and multiplexed MPEG video sequences at an asynchronous transfer mode multiplexer. Comparison study shows that the present model provides accurate prediction for quality of service measures, such as cellloss ratio under different traffic loads and various buffer sizes. Index TermsAutoregressive process, MPEG encoded video, traffic modeling, video modeling. I.
Modeling Video Traffic Using MGinfinity Input Processes: A Compromise Between Markovian and LRD Models
"... Statistical evidence suggests that the autocorrelation function ae(k) (k = 0; 1; : : :) of a compressedvideo sequence is better captured by ae(k) = e \Gammafi p k than by ae(k) = k \Gammafi = e \Gammafi log k (longrange dependence) or ae(k) = e \Gammafik (Markovian). A video model with suc ..."
Abstract

Cited by 9 (0 self)
 Add to MetaCart
Statistical evidence suggests that the autocorrelation function ae(k) (k = 0; 1; : : :) of a compressedvideo sequence is better captured by ae(k) = e \Gammafi p k than by ae(k) = k \Gammafi = e \Gammafi log k (longrange dependence) or ae(k) = e \Gammafik (Markovian). A video model with such a correlation structure is introduced based on the socalled M jGj1 input processes. In essence, the M jGj1 process is a stationary version of the busyserver process of a discretetime M jGj1 queue. By varying G, many forms of time dependence can be displayed, which makes the class of M jGj1 input models a good candidate for modeling many types of correlated traffic in computer networks. For video traffic, we derive the appropriate G that gives the desired correlation function ae(k) = e \Gammafi p k . Though not Markovian, this model is shown to exhibit shortrange dependence. Poisson variates of the M jGj1 model are appropriately transformed to capture the marginal distribution of a ...
On the Limitations of the VarianceTime Test for Inference of LongRange Dependence
 In IEEE INFOCOM
, 2001
"... The objective of this paper is to demonstrate the limitations of the variancetime (VT) test as a statistical tool for inferring longrange dependence (LRD) in network traffic. Since the early Bellcore studies [7], [16], LRD has been in the center of a continuous debate within the teletraffic commun ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
The objective of this paper is to demonstrate the limitations of the variancetime (VT) test as a statistical tool for inferring longrange dependence (LRD) in network traffic. Since the early Bellcore studies [7], [16], LRD has been in the center of a continuous debate within the teletraffic community. The controversy is typically focused on the utility of LRD models to predict the performance at network buffers. Our work here is not meant to advocate one modeling approach over another, but to point out (experimentally and theoretically) to the caveats in using the VT test as a tool for detecting LRD. We do that by deriving simple analytical expressions for the slope of the aggregated variance in three autocorrelated traffic models: M=G=1 process (shortrange dependent (SRD) but nonMarkovian), the discrete autoregressive of order one model (SRD Markovian), and the fractional ARIMA process (LRD). Our main result is that the VT test often indicates, falsely, the existence of an LRD structure (i.e., H ? 0:5) in synthetically generated traces from the two SRD models. The bias in the VT test, however, diminishes monotonically with the length of the trace. We provide some guidelines on selecting the minimum trace length so that the bias is negligible.
Efficient Modeling of VBR MPEG1 Coded Video Sources
 IEEE Transactions on Circuits and Systems for Video Technology
, 2000
"... Performance evaluation of broadband networks requires statistical analysis and modeling of the actual network traffic. Since multimedia services, and especially variable bit rate (VBR) MPEGcoded video streams are expected to be a major traffic component carried by these networks, modeling of such s ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
Performance evaluation of broadband networks requires statistical analysis and modeling of the actual network traffic. Since multimedia services, and especially variable bit rate (VBR) MPEGcoded video streams are expected to be a major traffic component carried by these networks, modeling of such services and accurate estimation of network resources are crucial for proper network design and congestioncontrol mechanisms that can guarantee the negotiated quality of service at a minimum cost. The layer modeling of MPEG1 coded video streams and statistical analysis of their traffic characteristics at each layer is proposed in this paper, along with traffic models capable of estimating the network resources over asynchronous transfer mode (ATM) links. First, based on the properties of the entire MPEG1 sequence (frame layer signal), a model (Model A) is presented by correlating three stochastic processes in discrete time (autoregressive models), each of which corresponds to the three types of frames of the MPEG encoder ( , and frames). To simplify the traffic Model A and to reduce the required number of parameters, we study the MPEG stream at a higher layer by considering a signal, which expresses the average properties of , and frames over a group of picture (GOP) period. However, models on this layer cannot accurately estimate the network resources, especially in multiplexing schemes. For this reason, an intermediate layer is introduced, which exploits and efficiently combines information of both the aforementioned layers, producing a model (Model B), which requires much smaller number of parameters than Model A and simultaneously provides satisfactory results as far as the network resources are concerned. Evaluation of the validity of the proposed models is performed t...
Quantifying the Temporal Characteristics of Network Congestion Events for Multimedia Services
, 2003
"... Effective qualityofservice (QoS) metrics must relate to enduser experience. For multimedia services these metrics should focus on phenomena that are observable by the end user. Once a congestion event occurs in the network it tends to persist, resulting in long bursts of consecutive packet loss. ..."
Abstract

Cited by 4 (3 self)
 Add to MetaCart
Effective qualityofservice (QoS) metrics must relate to enduser experience. For multimedia services these metrics should focus on phenomena that are observable by the end user. Once a congestion event occurs in the network it tends to persist, resulting in long bursts of consecutive packet loss. Such an event is observable to the network customer. There is a need to increase our understanding of the temporal characteristics of congestion. It has become increasingly apparent that the temporal characteristics of congestion events have the dominant effect on userperceived QoS. A rigorous definition of the time between congestion events is given here, as well as an associated prediction methodology. The intercongestion event time or the rate of congestion events per unit time provides a network quality metric that is easily understandable to network users and is conveniently predicted and measured. The contribution of this paper is the definition of a metric to characterize congestion events and development of an analytic methodology to predict the expected number of congestion events per unit time. The proposed methodology is evaluated for a variety of traffic models.
A Joint SourceChannel Coding Approach to Network Transport of Digital Video
 in Proc. IEEE INFOCOM
, 2000
"... The use of forward errorcontrol (FEC) coding, possibly in conjunction with passiveerror recovery techniques, has emerged as a promising approach for realtime video transport over ATM networks for cellloss recovery and/or bit error correction, such as might be required for wireless links. Althoug ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
The use of forward errorcontrol (FEC) coding, possibly in conjunction with passiveerror recovery techniques, has emerged as a promising approach for realtime video transport over ATM networks for cellloss recovery and/or bit error correction, such as might be required for wireless links. Although FEC provides cellloss recovery, through its erasure correcting capabilities, it also introduces transmission overhead which can possibly cause additional cell losses. A joint sourcechannel coding methodology is described to maximize the number of video sources multiplexed at a given quality of service (QoS), measured in terms of overall reproduced video quality. The transport channel is modeled as a block interference channel (BIC) and the multiplexer as a single server, deterministic service, finite buffer supporting N users. Based upon an informationtheoretic characterization of the BIC and large deviation bounds on the buffer overflow probability, we describe a methodology that provi...
Policies for swapping MPI processes
 In Proceedings of HPDC12, the Symposium on High Performance and Distributed Computing
, 2003
"... Despite the enormous amount of research and development work in the area of parallel computing, it is a common observation that simultaneous performance and easeofuse are elusive. We believe that easeofuse is critical for many end users, and thus seek performance enhancing techniques that can be ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
Despite the enormous amount of research and development work in the area of parallel computing, it is a common observation that simultaneous performance and easeofuse are elusive. We believe that easeofuse is critical for many end users, and thus seek performance enhancing techniques that can be easily retrofitted to existing parallel applications. In a previous paper we have presented MPI process swapping, a simple addon to the MPI programming environment that can improve performance in shared computing environments. MPI process swapping requires as few as three lines of source code change to an existing application. In this paper we explore a question that we had left open in our previous work: based on which policies should processes be swapped for best performance? Our results show that, with adequate swapping policies, MPI process swapping can provide substantial performance benefits with very limited implementation effort. 1.