Traditionally, the microprocessor design has focused on the computational aspects of the problem at hand. However, as the number of components on a single chip continues to increase, the design of communication architecture has become a crucial and dominating factor in defining performance models of the overall system. On-chip networks, also known as Networks-on-Chip (NoC), emerged recently as a promising architecture to coordinate chip-wide communication. Although there are numerous interconnection network studies in an inter-chip environment, an intra-chip network design poses a number of substantial challenges to this well-established interconnection network field. This research investigates designs and applications of on-chip interconnection network in next-generation microprocessors for optimizing performance, power consumption, and area cost. First, we present domain-specific NoC designs targeted to large-scale and wire-delay dominated L2 cache systems. The domain-specifically designed interconnect shows 38% performance improvement and uses only 12% of the mesh-based interconnect. Then, we present a methodology of communication characterization in parallel programs and application of characterization results to long-channel reconfiguration. Reconfigured long channels suited to communication patterns enhance the latency of the mesh network by 16% and 14% in 16-core and 64-core systems, respectively. Finally, we discuss an adaptive data compression technique that builds a network-wide frequent value pattern map and reduces the packet size. In two examined multi-core systems, cache traffic has 69% compressibility and shows high value sharing among flows. Compression-enabled NoC improves the latency by up to 63% and saves energy consumption by up to 12%.

Thesis (Ph. D.)--Computing, Georgia Institute of Technology, 2004. / Pande, Santosh, Committee Member ; Pu, Calton, Committee Member ; Schwan, Karsten, Committee Chair ; Franke, Hubertus, Committee Member ; Eisenhauer, Greg, Committee Member. Vita. Includes bibliographical references (leaves 158-169).

published_or_final_version / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

The recent years have observed a tremendous shift from the technology-centric assessment to the user-centric assessment of network services. Consequently, measurement and modelling of Quality of Experience (QoE) attracted many contributions from researchers and practitioners. Generally, QoE is assessed via active and passive measurements. While the former usually allows QoE assessment on the test traffic, the latter opens avenues for continuous QoE assessment on the real traffic generated by the users. This thesis contributes towards passive assessment of QoE. This thesis document begins with a background on the fundamentals of network management and objective QoE assessment. It extends the discussion further to the QoE-centric monitoring and management of network, complimented by the details about QoE estimator agent developed within the Celtic project QuEEN (Quality of Experience Estimators in Network). The discussion on findings starts with results from subjective tests to understand the relationship between waiting times and user subjective feedback over time. These results strengthen the understanding of timescales on which users react, as well as, the effect of user memory on QoE. The findings show that QoE drops significantly when the user faces recurring waiting times of 0.5 s to 4 s durations in case of video streaming and web browsing services. With recurring network disturbances within every 8 s – 16 s time intervals, the user tolerance to waiting times decreases constantly, showing the sign of user memory of recent disturbances. Subsequently, this document introduces and evaluates a passive wavelet-based QoE monitoring method. The method detects timescales on which transient outages occur frequently. A study presents results from qualitative measurements, showing the ability of wavelet to differentiate on-fly between “Good” and “Bad” traffic streams. In sequel, a quantitative study systematically evaluates wavelet-based metrics. Subsequently, the subjective evaluation and wavelet analysis of 5 – 6 minutes long video streaming sessions on mobile networks show that wavelet-based metrics is indeed useful for passive monitoring of QoE issues. Finally, this thesis investigates a method for passive monitoring of user reactions to degrading network performance. The method is based on the TCP termination flags. With a systematic evaluation in a test environment, the results characterise termination of data transfers in case of different user actions in the web browser.

Thesis (PhD)--University of South Australia, 2002.

Thesis (Ph. D.)--School of Computing and Engineering. University of Missouri--Kansas City, 2006. / "A dissertation in computer networking and telecommunication networking." Advisor: Deep Medhi. Typescript. Vita. Title from "catalog record" of the print edition Description based on contents viewed Oct. 31, 2007. Includes bibliographical references (leaves 168-172). Online version of the print edition.

Recent advances in fiber optics technology have enabled extremely high-speed transport of different forms of data, on multiple wavelengths of an optical fiber, using Dense Wavelength Division Multiplexing (DWDM). It has now become possible to deploy high-speed, multi-service networks using DWDM technology. As the amount of traffic carried has increased, any single failure can be catastrophic. Survivability becomes indispensable in such networks. Therefore, it is imperative to design networks that can quickly and efficiently recover from failures. Most research to date in survivable optical network design and operation focuses on single link failures, however, the occurrence of multiple-link failures are not uncommon in networks today. Multi-link failure scenarios can arise out of two common situations. First, an arbitrary link may fail in the network, and before that link can be repaired, another link fails, thus creating a multi-link failure sequence. Secondly, it might happen in practice that two distinct physical links may be routed via the same common duct or physical channel. A failure at that shared physical location creates a logical multiple-link failure. In this dissertation, we conduct an intensive study of mechanisms for achieving survivability in optical networks. From the many mechanisms presented in the literature the focus of this work was on protection as a mechanism of survivability. In particular four protection schemes were simulated and their results analyzed to ascertain which protection scheme achieves the best survivability in terms of number of wavelengths recovered for a specific failure scenario. A model network was chosen and the protection schemes were evaluated for both single and multiple link and node failures. As an indicator of the performance of these protection schemes over a period of time average service availability and average loss in traffic for each protection scheme was also simulated. Further simulations were conducted to observe the percentage link and node utilization of each scheme hence allowing us to determine the strain each protection scheme places on network resources when traffic in the network increases. Finally based on these simulation results, recommendations of which protection scheme and under what failure conditions they should be used are made. / Recent advances in fiber optics technology have enabled extremely high-speed transport / Thesis (M.Sc.)-University of KwaZulu-Natal, 2006. / Thesis (M.Sc.Eng.)-University of KwaZulu-Natal, 2006.

Modern computer networks pose a great challenge for monitoring the network performance due to their large scale and high complexity. Directly measuring the performance of internal network elements is prohibitive due to the tremendous overhead. Alternatively, network tomography, a technique that infers the unobserved network characteristics (e.g., link delays) from a small number of measurements (e.g., end-to-end path delays), is a promising solution for monitoring the internal network state in an e cient and e ective manner. This thesis initiates two variants of network tomography: concentrated network tomography and bound-based network tomography. The former is motivated by the practical needs that network operators normally concentrate on the performance of critical paths; the latter is due to the need of estimating performance bounds whenever exact performance values cannot be determined. This thesis tackles core technical di culties in concentrated network tomography and bound- based network tomography, including (1) the path identi ability problem and the monitor deploy- ment strategy for identifying a set of target paths, (2) strategies for controlling the total error bound as well as the maximum error bound over all network links, and (3) methods of constructing measure- ment paths to obtain the tightest total error bound. We evaluate all the solutions with real-world Internet service provider (ISP) networks. The theoretical results and the algorithms developed in this thesis are directly applicable to network performance management in various types of networks, where directly measuring all links is practically impossible. / Graduate

published_or_final_version / Mechanical Engineering / Master / Master of Philosophy

Gao Yan. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references (leaves 70-73). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Literature Survey and Background --- p.6 / Chapter 2.1 --- Capacity of Wireless Networks --- p.6 / Chapter 2.2 --- Physical Layer Techniques --- p.8 / Chapter 2.2.1 --- Radio Propagation Models --- p.8 / Chapter 2.2.2 --- Multiple Access Techniques --- p.11 / Chapter 2.3 --- MAC layer --- p.13 / Chapter 2.3.1 --- An Introduction to the IEEE 802.11 protocol --- p.13 / Chapter 2.3.2 --- Performance Analysis of the IEEE 802.11 protocol in single cell networks --- p.15 / Chapter 3 --- Model and Methodology --- p.18 / Chapter 3.1 --- System Model --- p.18 / Chapter 3.1.1 --- DCF Model --- p.19 / Chapter 3.1.2 --- The Problems of Hidden Node --- p.21 / Chapter 3.2 --- A Methodology to Compute Throughput Capacity --- p.23 / Chapter 3.2.1 --- Constructing a Contention Graph --- p.24 / Chapter 3.2.2 --- Determining the Link Capacity Ei --- p.27 / Chapter 3.2.3 --- Determining the Channel Idle Probability zi --- p.30 / Chapter 3.2.4 --- Detennining the Collision Probability γi --- p.32 / Chapter 3.3 --- Throughput Analysis of a Chain network --- p.35 / Chapter 4 --- Applications of the Proposed Methodology --- p.38 / Chapter 4.1 --- Application 1: Determining the End-to-End Throughput Capacity in Multi-hop Networks --- p.38 / Chapter 4.1.1 --- Routing Optimization --- p.40 / Chapter 4.1.2 --- Offered Load Control --- p.45 / Chapter 4.2 --- Application 2: Determining the Equilibrium Throughput of onehop Networks --- p.47 / Chapter 4.2.1 --- Throughput Capacity of One-Hop Networks --- p.49 / Chapter 4.3 --- Application 3: Optimal Hop Distance in Multi-hop Networks --- p.51 / Chapter 4.3.1 --- Analysis of Regular One-Dimension Network --- p.51 / Chapter 4.3.2 --- Optimal Hop Distance --- p.53 / Chapter 5 --- Simulation and Validation --- p.55 / Chapter 5.1 --- Simulation Environment --- p.55 / Chapter 5.2 --- MAC layer Collisions --- p.56 / Chapter 5.3 --- Single Flow Capacity: --- p.58 / Chapter 5.4 --- Neighboring Traffic Effect: --- p.59 / Chapter 5.5 --- Routing Optimization: --- p.60 / Chapter 5.6 --- Optimal Offered Load Control: --- p.62 / Chapter 5.7 --- Optimal Hop Distance --- p.63 / Chapter 5.7.1 --- One-Source ROD Network --- p.63 / Chapter 5.7.2 --- Two-Source ROD Network --- p.64 / Chapter 5.7.3 --- Simulation Investigation on Hop Distance --- p.65 / Chapter 6 --- Related Work --- p.68 / Chapter 7 --- Conclusion --- p.69