Results 1 
7 of
7
Local Area Network Traffic Characteristics, with Implications for Broadband Network Congestion Management
"... This paper examines the phenomenon of congestion in order to better understand the congestion management techniques that will be needed in highspeed, cellbased networks. The first step of this study is to use high timeresolution local area network (LAN) traffic data to explore the nature of LAN t ..."
Abstract

Cited by 92 (0 self)
 Add to MetaCart
This paper examines the phenomenon of congestion in order to better understand the congestion management techniques that will be needed in highspeed, cellbased networks. The first step of this study is to use high timeresolution local area network (LAN) traffic data to explore the nature of LAN traffic variability. Then, we use the data for a tracedriven simulation of a connectionless service that provides LAN interconnection. The simulation allows us to characterize what congestion might look like in a highspeed, cellbased network. The most
Discrete Queueing Analysis of Multimedia Traffic with Diversity of Correlation and Burstiness Properties
 Proc. of IEEE Infocom'91
, 1991
"... Key properties of multimedia traffic are characterized by the great diversity of correlation and burstiness. Construct the multimedia traffic by heterogeneous 2state Markov chains as in [1] [2]. Here we allow each 2state MC to be defined on different transition intervals, representing the diversit ..."
Abstract

Cited by 13 (7 self)
 Add to MetaCart
Key properties of multimedia traffic are characterized by the great diversity of correlation and burstiness. Construct the multimedia traffic by heterogeneous 2state Markov chains as in [1] [2]. Here we allow each 2state MC to be defined on different transition intervals, representing the diversity of peak access rate from individual sources. Upon time renormalization, the queue is modeled by a multidimensional discrete Markov process. Generalizing the technique developed in [2] [3], we are able to construct the entire solution of queue length distributions. It uses generating function approach. By matrix spectral decomposition, one can decompose the evaluation of each individual vanishing/nonvanishing root. Each vanishing root is used to obtain the queue boundary values; each nonvanishing root constructs a geometric term in the expression of the queue length distribution. It is found that all the vanishing roots must be real and all the complex nonvanishing roots can be ignored....
Second Order Effect of Binary Sources on Characteristics of Queue and Loss Rate
 IEEE
, 1995
"... A wideband source in high speed networks is typically represented by a binary random process. In this paper we characterize the secondorder properties of each binary source by a multistate MMPP. A comprehensive numerical study is carried out to identify the individual effect of the source secondo ..."
Abstract

Cited by 12 (8 self)
 Add to MetaCart
A wideband source in high speed networks is typically represented by a binary random process. In this paper we characterize the secondorder properties of each binary source by a multistate MMPP. A comprehensive numerical study is carried out to identify the individual effect of the source secondorder dynamics on the queue length and loss rate. The results can be used to verify the validity of the twostate Markov chain binary source assumption which is commonly made within the framework of input rate control and bandwidth allocation in high speed networks. The concept of input power spectrum is then developed as a unified source characterization for multimedia traffic queueing analyses. The research reported here was supported by NSF under Grants NCR9009926 and NCR9015757, and by Texas Advanced Research Program under grant TARP129. This paper was submitted to IEEE Transaction on Communications in Jan. 1992. 1 Introduction A wideband source in high speed networks is expected ...
The Superposition of DiscreteTime Markov Renewal Processes with an Application to Statistical Multiplexing of Bursty Traffic Sources
, 1994
"... The main contribution in this paper is the introduction of a methodology for approximately characterizing the superposition process of N 2 arbitrary ( and possibly heterogeneous) discretetime Markov Renewal Processes (MRP). In this model, the superposition process is characterized by a MRP with ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
The main contribution in this paper is the introduction of a methodology for approximately characterizing the superposition process of N 2 arbitrary ( and possibly heterogeneous) discretetime Markov Renewal Processes (MRP). In this model, the superposition process is characterized by a MRP with a state space that grows exponentially with N . We consider an on/off traffic source model, where the distribution of the on and off periods is arbitrary, as a special case of the general MRP. Subsequently, a queueing model for a FIFO finitebuffer multiplexer with arbitrary on/off input sources is analyzed. We provide numerical results for testing the algorithms introduced in the paper. We also study the effect of some of the statistical properties of on/off input sources on the multiplexer's performance.
NonDeterministic Periodic Packet Streams and Their Impact on a FiniteCapacity Multiplexer
 In IEEE INFOCOM'94
, 1994
"... This paper considers the multiplexing of nondeterministic periodic traffic sources which deliver packets periodically according to an arbitrary i.i.d. batch arrival process. The proposed traffic sources are representative of the packetstream periodicities commonly found in highspeed packet network ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
This paper considers the multiplexing of nondeterministic periodic traffic sources which deliver packets periodically according to an arbitrary i.i.d. batch arrival process. The proposed traffic sources are representative of the packetstream periodicities commonly found in highspeed packet networks such as ATM. An exact analytical technique, which entails the solution of Markov chains whose dimensions are independent of the periods associated with the input sources, is presented for the study of a finitecapacity multiplexer fed by N of the proposed traffic models. Numerical results indicate that the source periodicities have a significant impact on the multiplexer's performance. In fact, for some regions of operating conditions, even a Poisson traffic assumption is shown to provide an extremely pessimistic estimate of the queue performance measured in terms of packetloss probabilities. 1
Traffic Shaping for Congestion Control in High Speed ATM Networks
, 1992
"... Congestion control will be an essential part of BISDN in order to guarantee its performance level. The high transmission rate of such networks and the support of new services with diverse traffic characteristics make the congestion control problem more complicated and more challenging than in conve ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
Congestion control will be an essential part of BISDN in order to guarantee its performance level. The high transmission rate of such networks and the support of new services with diverse traffic characteristics make the congestion control problem more complicated and more challenging than in conventional networks. Voice, data and video traffic have radically different performance requirements and are of a very bursty nature. The bursty nature of the traffic is the primary cause of congestion. Congestion results in undesirable performance degradation such as long packet delay, high packet loss and large buffer requirements. Congestion control is a network function that attempts to avoid or control congestion and limit its effects. Traffic shaping has been proposed as a congestion control mechanism to control the input rate and smooth the burstiness of traffic. Shaping the traffic when it enters the network makes the traffic smoother and more predictable, thus reducing the probabilit...
Multiplexing ATM Traffic Streams with TimeScaleDependent Arrival Processes
, 1997
"... This paper presents a flexible traffic model which is capable of describing traffic dynamics on a variety of timescales associated with broadband packet networks such as ATM. The model is applied to the study of NonDeterministic Periodic (NDP) sources as well as Variable Bit Rate (VBR) video so ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
This paper presents a flexible traffic model which is capable of describing traffic dynamics on a variety of timescales associated with broadband packet networks such as ATM. The model is applied to the study of NonDeterministic Periodic (NDP) sources as well as Variable Bit Rate (VBR) video sources in which cells are delivered at a subframe level referred to as a slice. An efficient numerical technique is presented for the study of a finitecapacity multiplexer under an input process determined by the superposition of N of the proposed traffic models. Numerical results support the assertion that the timescales at which variations in a cell arrival stream occur have a significant impact on multiplexer performance, thereby illustrating the relevance of the proposed modeling and analytical techniques.