Thesis (Ph.D.)--Hong Kong University of Science and Technology, 2006. / Includes bibliographical references (leaves [188]-195). Also available in electronic version.

Transmission Control Protocol (TCP) is the dominant transport protocol today and likely to be adopted in future high‐speed and optical networks. A number of literature works have been done to modify or tune the Additive Increase Multiplicative Decrease (AIMD) principle in TCP to enhance the network performance. In this work, to efficiently take advantage of the available high bandwidth from the high‐speed and optical infrastructures, we propose a Stratified TCP (STCP) employing parallel virtual transmission layers in high‐speed networks. In this technique, the AIMD principle of TCP is modified to make more aggressive and efficient probing of the available link bandwidth, which in turn increases the performance. Simulation results show that STCP offers a considerable improvement in performance when compared with other TCP variants such as the conventional TCP protocol and Layered TCP (LTCP).

This thesis proposes a new problem of identifying large and tangled logic structures in a synthesized netlist. Large groups of cells that are highly interconnected to each other can often create potential routing hotspots that require special placement constraints. They can also indicate problematic clumps of logic that either require resynthesis to reduce wiring demand or specialized datapath placement. At a glance, this formulation appears similar to conventional circuit clustering, but there are two important distinctions. First, we are interested in finding large groups of cells that represent entire logic structures like adders and decoders, as opposed to clusters with only a handful of cells. Second, we seek to pull out only the structures of interest, instead of assigning every cell to a cluster to reduce problem complexity. This work proposes new metrics for detecting structures based on Rent’s rule that, unlike traditional cluster metrics, are able to fairly differentiate between large and small groups of cells. Next, we demonstrate how these metrics can be applied to identify structures in a netlist. Finally, our experiments demonstrate the ability to predict and alleviate routing hotspots on a real industry design using our metrics and method.

In wireless sensor networks (WSN), nodes have very limited power due to hardware constraints. Packet losses and retransmissions resulting from congestion cost precious energy and shorten the lifetime of sensor nodes. This problem motivates the need for congestion control mechanisms in WSN. In this thesis, an observation of multiple non-empty queues in sensor networks is first reported. Other aspects affected by congestion like queue length, delay and packet loss are also studied. The simulation results show that the number of occupied queues along a path can be used to detect congestion. Based on the above result, a congestion control scheme for the transport layer is proposed in this thesis. It is composed of three parts: (i) congestion detection by tracking the number of non-empty queues; (ii) On-demand midway non-binary explicit congestion notification (CN) feedback; and (iii) Adaptive rate control based on additive increase and multiplicative decrease (AIMD). This scheme has been implemented in ns2. Extensive simulations have been conducted to evaluate it. Results show that it works well in mitigating and avoiding congestion and achieves good performance in terms of energy dissipation, latency and transmission effciency.

Thesis (Ph. D.)--Virginia Polytechnic Institute and State University, 1991. / Vita. Abstract. Includes bibliographical references (leaves 151-156). Also available via the Internet

Thesis (Ph. D.)--University of Washington, 2001. / Vita. Includes bibliographical references (leaves 134-144).

Thesis (M. Sc.)--University of Hong Kong, 2001. / Includes bibliographical references (leaves 146-149).

published_or_final_version / Transport Policy and Planning / Master / Master of Arts in Transport Policy and Planning

No description available.

Congestion control in wireline networks has been studied extensively since the seminal work by Mazumdar et al in 1998. It is well known that this global optimization problem can be implemented in a distributed manner. Stability and fairness are two main design objectives of congestion control mechanisms. Most literatures make the assumption that the number of flows is fixed in the network and each flow has infinite backlog for transfer in developing congestion control schemes. However, this assumption may not hold in reality. Thus, there is a need to study congestion control algorithm in the presence of dynamic flows. It is only until recently that short-lived flows have been taken into account. In this thesis, we study utility maximization problems for networks with dynamic flows. In particular, we consider the case where each class of flows arrives according to a Poisson process and has a length given by a certain distribution. The goal is to maximize the long-term expected system utility, which is a function of the number of flows and the rate (identical within a given class) allocated to each flow. Our investigation shows that, as long as the average work brought by the arrival processes is strictly within the network stability region, the fairness and stability issues are independent. While stability can be guaranteed by, for example, a FIFO policy, utility maximization becomes an unconstrained optimization. We also provide a queueing interpretation of this seemingly surprising result and show that not all utility functions make sense under dynamic flows. Finally, we use simulation results to show that our algorithm indeed maximizes the expected system utility.