Thesis (Ph. D.)--Electrical and Computer Engineering, Georgia Institute of Technology, 2007. / Chang, Gee-Kung, Committee Chair ; Zhou, G.Tong, Committee Member ; Copeland, John, Committee Member ; Riley, George, Committee Member ; Ingram, Mary Ann, Committee Member ; Ammar, Mostafa, Committee Member.

Thesis (Ph. D.)--School of Computing and Engineering. University of Missouri--Kansas City, 2004. / Typescript. "A dissertation in engineering and telecommunication networking." Advisor: Ghulam M. Chaudhry. Vita. Title from "catalog record" of the print edition Description based on contents viewed Feb. 23, 2006. Includes bibliographical references (leaves 150-158) and index. Online version of the print edition.

M.Ing. / Recent traffic analyses have shown the existence of long-range dependencies in network traffic, specifically self-similar long-range dependencies. Due to the inability of traditional traffic models to capture these long-range dependencies, new network traffic models were developed that are able to capture it. In this paper we compare three self-similar long-range dependent traffic models, namely the FARIMA model, the wavelet independent Gaussian model and the multifractal wavelet model. We present results on their marginal distributions, their correlation matching to real traffic and their queuing behaviour. We show that the multifractal wavelet model is the best of the three models in all of the test aspects.

Audio Engineers are required to design and deploy large multi-channel sound systems which meet a set of requirements and use networking technologies such as Firewire and Ethernet AVB. Bandwidth utilisation and parameter groupings are among the factors which need to be considered in these designs. An implementation of an extensible, generic simulation framework would allow audio engineers to easily compare protocols and networking technologies and get near real time responses with regards to bandwidth utilisation. Our hypothesis is that an application-level capability can be developed which uses a network simulation framework to enable this process and enhances the audio engineer’s experience of designing and configuring a network. This thesis presents a new, extensible simulation framework which can be utilised to simulate professional audio networks. This framework is utilised to develop an application - AudioNetSim - based on the requirements of an audio engineer. The thesis describes the AudioNetSim models and implementations for Ethernet AVB, Firewire and the AES- 64 control protocol. AudioNetSim enables bandwidth usage determination for any network configuration and connection scenario and is used to compare Firewire and Ethernet AVB bandwidth utilisation. It also applies graph theory to the circular join problem and provides a solution to detect circular joins.

No description available.

No description available.

The Metro Ethernet network (MEN) expands the advantages of Ethernet to cover areas wider than LAN. MENs running Ethernet Services as specified by the Metro Ethernet Forum (MEF) are known as Carrier Ethernet Networks (CENs). CENs can cover not only metro areas, but it can expand to cover global areas by connecting multiple MENs. Next-generation CENs are expected to support 100 GbE. With arising technologies for Ultra Long-haul (ULH) networks the bandwidth bottleneck of CENs is shifting to other areas like the transport layer protocol (such as the Transport Control Protocol or TCP) and the chip-to-chip channel capacity found at the network edge, which in general has an electrical backplane. Traditional TCP is well known to have difficulties reaching the full available bandwidth, due to its inefficient AIMD mechanisms under a high-delay-bandwidth-product environment. At the network edge, network equipment with electrical backplanes poses many problems including inductive-capacitive effects that limit its bandwidth. These are the two main issues addressed in this work. To resolve the transport layer issue, this work proposes a transport protocol that fully utilizes the available bandwidth while preserving TCP-friendliness and providing QoS support that is compatible with Ethernet Services. It can guarantee throughputs above the Committed Information Rate (CIR), which is specified in the Service Level Agreement (SLA). To resolve the physical layer limitations, a novel optical coupling technique is examined to encourage the use of optical backplanes for network-edge and core technology. The proposed technique consists of aligning the normal of the laser emission plane, waveguide plane and the normal of the photodetector active region plane with the purpose of reducing optical power loss caused by common methods of light manipulation. By addressing the shortcomings of both Traditional TCP and electrical backplane technology the overall throughput can be significantly increased.

Ring networks are appropriate for the full range of network levels, including multiprocessor systems, local area computer networks and high speed backbones. The most well known and widely implemented examples are the IBM token ring and FDDI networks. Ring networks have the advantages of high channel utilisation and bounded delay if an n-limited service policy is used. The packet transfer delay, defined as the average time a packet spends in the network from the time it is generated until the time it is received at its destination node, improves with the number of rings on which a node is connected. However, many ring connections are not economically feasible since the cost of the ring interface increases with the number of rings. There has been an abundance of previous work on single token ring networks. A number of papers on slotted rings, register insertion rings and more complex ring architectures have also been published. However, there is very little existing literature on multiple ring networks as well as ring networks in clustered traffic environments, i.e. where nodes from the same cluster tend to communicate more with each other than with other nodes in the network. This thesis focuses on two network topologies that make use of multiple rings and are well suited to clustered traffic environments: the two-connected multiple ring (2-MR) and the destination removal double ring (DRDR). For the 2-MR network, three different practical token-based protocols are investigated in an attempt to optimise performance. It is further shown that significant performance improvements can be achieved by employing a slotted ring protocol rather than the token ring protocol. The DRDR network is also examined and its performance compared to the aforementioned architectures. For each of the six cases, both random and clustered traffic patterns are considered and compared. Analytical results are derived which are verified by results obtained from computer simulations. Furthermore, we look at exact methods of analysing ring networks. A mean value analysis of a single token ring network with a I-limited service discipline is performed, which clearly shows the complexity exact methods introduce. Finally, although it has been stated in the literature that an exact analysis of a multiple symmetrical token ring network is intractable, we present a novel Markov chain approach that gives exact results for near zero loads. / Thesis (M.Sc.-Electronic Engineering)-University of Natal, 1998.

No description available.

Thesis (Ph.D.) - Carleton University, 2006. / Includes bibliographical references (p. 139-144). Also available in electronic format on the Internet.