Lee Chung Hing. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2001. / Includes bibliographical references (leaves 61-63). / Abstracts in English and Chinese. / Acknowledgements --- p.ii / Abstract --- p.iii / List of Figures --- p.vii / Chapter 1. --- Introduction --- p.1 / Chapter 1.1 --- Contributions of This Thesis --- p.3 / Chapter 1.2 --- Organizations of This Thesis --- p.3 / Chapter 1.3 --- Publication --- p.4 / Chapter 2. --- Overview of VoD Systems --- p.5 / Chapter 2.1 --- True VoD --- p.6 / Chapter 2.2 --- Near VoD --- p.7 / Chapter 2.3 --- Related Works --- p.9 / Chapter 2.3.1 --- Batching --- p.9 / Chapter 2.3.2 --- Patching --- p.11 / Chapter 2.3.3 --- Mcache --- p.11 / Chapter 2.3.4 --- Unified VoD --- p.12 / Chapter 2.4 --- Discussions --- p.15 / Chapter 3. --- Super-Scalar Architecture --- p.17 / Chapter 3.1 --- Transmission Scheduling --- p.20 / Chapter 3.2 --- Admission Control --- p.21 / Chapter 3.3 --- Channel Merging --- p.26 / Chapter 3.4 --- Interactive Control --- p.29 / Chapter 4. --- Performance Modeling --- p.31 / Chapter 4.1 --- Waiting Time for Statically-Admitted Clients --- p.32 / Chapter 4.2 --- Waiting Time for Dynamically-Admitted Clients --- p.33 / Chapter 4.3 --- Admission Threshold --- p.38 / Chapter 4.4 --- Channel Partitioning --- p.39 / Chapter 5. --- Performance Evaluation --- p.40 / Chapter 5.1 --- Model Validation --- p.40 / Chapter 5.2 --- Channel Partitioning --- p.42 / Chapter 5.3 --- Latency Comparisons --- p.44 / Chapter 5.4 --- Channel Requirement --- p.46 / Chapter 5.5 --- Performance at Light Loads --- p.47 / Chapter 5.6 --- Multiplexing Gain --- p.49 / Chapter 6. --- Implementation and Benchmarking --- p.51 / Chapter 6.1 --- Implementation Description --- p.51 / Chapter 6.2 --- Benchmarking --- p.53 / Chapter 6.2.1 --- Benchmarking Setup --- p.53 / Chapter 6.2.2 --- Benchmarking Result --- p.55 / Chapter 7. --- Conclusion --- p.56 / Appendix --- p.57 / Bibliography --- p.61

by Kelvin Kwok-wai Law. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1997. / Includes bibliographical references (leaves 66-68). / Abstract --- p.i / Acknowledgments --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.2 --- Motivation --- p.2 / Chapter 1.3 --- Scope --- p.3 / Chapter 1.4 --- Dissertation Outline --- p.4 / Chapter 2 --- Background and Related Researches --- p.6 / Chapter 2.1 --- Interactive Services --- p.6 / Chapter 2.2 --- VOD Architecture --- p.7 / Chapter 2.3 --- Video Compression --- p.10 / Chapter 2.3.1 --- DCT Based Compression --- p.11 / Chapter 2.3.2 --- Subband Video Compression --- p.12 / Chapter 2.4 --- Related Research --- p.14 / Chapter 3 --- Multiple Resolutions Video File System --- p.16 / Chapter 3.1 --- Physical Disk Storage System --- p.16 / Chapter 3.2 --- Multi-resolution Video Data Placement Scheme --- p.17 / Chapter 3.3 --- Example of our Video Block Assignment Algorithm --- p.23 / Chapter 3.4 --- An Assignment Algorithm for Homogeneous Video Files --- p.26 / Chapter 4 --- Disk Scheduling and Admission Control --- p.33 / Chapter 4.1 --- Disk Scheduling Algorithm --- p.33 / Chapter 4.2 --- Admission Control --- p.40 / Chapter 5 --- Load Balancing of the Disk System --- p.43 / Chapter 6 --- Buffer Management --- p.49 / Chapter 6.1 --- Buffer Organization --- p.49 / Chapter 6.2 --- Buffer Requirement For Different Video Playback Mode --- p.51 / Chapter 7 --- Conclusions --- p.63 / Bibliography --- p.66

Bibliography: leaves 211-234. / xiv, 234 p. : ill. ; 30 cm. / Title page, contents and abstract only. The complete thesis in print form is available from the University Library. / The general problem of scheduling is investigated, with focus on jobs consisting of both independent and dependent programs. Using the constraint of restricted placement of programs, presents a scheduling system that produces heuristically good execution schedules in the absence of complete global system state information. / Thesis (Ph.D.)--University of Adelaide, Dept. of Computer Science, 1999

Bibliography: leaves 211-234. The general problem of scheduling is investigated, with focus on jobs consisting of both independent and dependent programs. Using the constraint of restricted placement of programs, presents a scheduling system that produces heuristically good execution schedules in the absence of complete global system state information.

Parallel computing on heterogeneous workstation clusters has proved to be a very efficient use of available resources, increasing their overall utilization. However, for it to be a viable alternative to expensive, dedicated parallel machines, a number of key issues need to be resolved. One of the major challenges of heterogeneous computing is coping with the inherent heterogeneity of the system, with the availability of workstations from different vendors of varying processing speeds and capabilities. The existence of multiple jobs and users further complicates the task. The time taken for a parallel job is constrained by the time taken by the slowest or the most heavily loaded workstation. Therefore, load sharing of parallel computations is imperative in ensuring good overall utilization of the system. Since load sharing is essentially independent of the particular parallel job being run, the development of program independent, automatic, scheduling and load sharing strategies have become vital to the efficient use of the heterogeneous cluster. This thesis discusses various prior approaches to load sharing, examines a new strategy developed for heterogeneous workstations, and evaluates its performance. / Graduation date: 1996

published_or_final_version / Electrical and Electronic Engineering / Master / Master of Philosophy

Indiana University-Purdue University Indianapolis (IUPUI) / In today's internet world with such a high traffic, it becomes inevitable to have multiple servers representing a single logical server to share enormous load. A very common network configuration consists of multiple servers behind a load balancer. The load balancer determines which server would service a clients request or incoming load from the client. Such a hardware is expensive, runs a fixed policy or algorithm and is a single point of failure. In this paper, we will implement and analyze an alternative load balancing architecture using OpenFlow. This architecture acquires flexibility in policy, costs less and has the potential to be more robust. This paper also discusses potential usage of OpenFlow based load balancing for media gateway selection in SIP-PSTN networks to improve VoIP performance.