Randall Landry

Study of delay jitter with and without peak rate enforcement

In this paper, the modification of a tagged traffic stream due to statistical multiplexing is studied by presenting a numerical approach for the calculation of the tagged delay jitter and interdeparture processes. Both the single- and multiple-node cases are considered. Unlike the past work, the developed approach is applicable under both the standard first come first served (FCFS) policy and a peak-rate enforcing multiplexing policy. The latter policy can be adopted to reshape the tagged traffic stream within the network. Restoring a shaped traffic profile within the network may be necessary to obtain some of the benefits for which the original shaping is carried out at the network edge. This study also provides results and insight regarding the potential gains of reregulation within the network.

Traffic shaping of a tagged stream in an ATM network: approximate end-to-end analysis

Traffic streams-originally shaped to comply with desired traffic descriptors-may suffer substantial distortion within an ATM network due to statistical multiplexing. As a consequence, traffic re-shaping within the network may be necessary. In this work the modification of a tagged traffic stream due to a series of multiplexing operations is studied. The standard FCFS service policy, as well as a peak-rate enforcing multiplexing discipline, are considered. Tagged cell delay, jitter and inter-departure processes are considered for the characterization of the tagged traffic stream.

Delay analysis of the DQDB MAN based on a simple model

The distributed queue dual bus (DQDB) medium access protocol has been adopted as a metropolitan area network (MAN) standard. The performance of the DQDB protocol is analyzed under underloaded operation. No bandwidth balancing mechanism is assumed to be in effect. Packet delay results are derived analytically by considering an approximate model for the queuing behavior of a DQDB station. Delay results are obtained for a traffic load of 80% and for DQDB networks of up to 50 stations.<<ETX>>

Flow control and congestion avoidance in switched Ethernet LANs

With the increasing popularity of full-duplex, switched Ethernet-a point-to-point technology as opposed to classical CSMA/CD-efforts to standardize a vehicle for flow control at or below the MAC (media access control) sublayer have been initiated. In this paper, the end-to-end transport layer flow control and congestion avoidance mechanisms of TCP, as well as a new hop-by-hop MAC layer flow control being standardized by the IEEE, are considered. Simulation studies are performed to evaluate network performance with and without the explicit congestion indication provided by the MAC layer approach.

Queueing study of a 3-priority policy with distinct service strategies

A discrete-time, single server, 3-queue system is presented and analyzed. A distinct service strategy, namely the consistent-gated (c-G), 1-limited (L) and head-of-line (HoL), is applied to each of the queues (c-G/L/HoL policy). It is shown that this queueing system provides for an accurate analytical model for a DQDB station, as well as a means for an approximate evaluation of the correlation associated with key traffic processes in that network. In addition, the developed queueing system could be useful for the modeling of the queueing behavior of an ATM link shared by high-priority, low priority and control traffic. Through an asymptotic analysis under heavy low-priority traffic, the worst case performance for the high priority traffic is determined. Furthermore, it is illustrated that the asymptotic analysis provides for a potentially tight delay bounding technique. Finally, the delay performance of the developed queueing system is compared to that of a similar system in which one of the queues receives 1-limited service and the other two exhaustive (HoL/sup -//L/HoL/sup +/ policy). >

Non-deterministic periodic packet streams and their impact on a finite-capacity multiplexer

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 packet-stream periodicities commonly found in high-speed 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 finite-capacity multiplexer fed by N of the proposed traffic models. Numerical results indicate that the source periodicities have a significant impact on the multiplexers 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 packet-loss probabilities.<<ETX>>

Multiplexing generalized periodic Markovian sources with an application to the study of VBR video

Presents a stochastic traffic model which is capable of capturing the time-scale dynamics associated with the potentially large disparity between source and output-link speeds in packet networks such as ATM. The model is applied to the study of variable bit rate (VBR) video sources in which cells are delivered at a sub-frame level referred to as a slice. A tractable analytical technique is presented for the study of a finite-capacity multiplexer under an input process determined by the superposition of N of the proposed traffic models.<<ETX>>

Multiplexing ATM traffic streams with time-scale-dependent arrival processes

This paper presents a flexible traffic model which is capable of describing traffic dynamics on a variety of time-scales associated with broadband packet networks such as ATM. The model is applied to the study of Non-Deterministic Periodic (NDP) sources as well as Variable Bit Rate (VBR) video sources in which cells are delivered at a sub-frame level referred to as a slice. An efficient numerical technique is presented for the study of a finite-capacity multiplexer under an input process determined by the superposition of N of the proposed traffic models. Numerical results support the assertion that the time-scales 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.

Series editorial: military communications

This feature topic on military communications includes five articles that deal primarily with wireless tactical networks, covering topics ranging from security to software defined radio design and mobile ad hoc networks (MANETs) for covert battlefield operations.

Guest editorial: military communications

Since its introduction in the late 1990s, the concept of network-centric operations to enable information sharing has been a fundamental element of the vision of military organizations throughout the world. As the complexity of operational environments increases, military communications network technologies must provide key characteristics such as self-organization and decentralization, which will speed information flow and increase situational awareness. In addition, given the rapid evolution of commercial communications network technologies, and the applications and services that utilize them, military organizations are increasingly looking at adopting commercial communications technologies where practical. This is especially true in the mobile wireless communications that are at the heart of tactical military operations and have seen such rapid adoption in the commercial space. The five articles that make up this years Feature Topic on Military Communications provide an excellent overview of these trends in military communications - increasing dependence on advanced technologies and leveraging of commercial technology where possible.