Chan Ming-fei. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1999. / Includes bibliographical references (leaves 63-66). / Abstract --- p.i / Acknowledgments --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Challenging Issues --- p.2 / Chapter 1.2 --- Previous Work --- p.4 / Chapter 1.3 --- Organization of the Thesis --- p.5 / Chapter 2 --- Distributed Virtual Environment --- p.6 / Chapter 2.1 --- Possible Architectures --- p.6 / Chapter 2.2 --- Representations of Clients as Avatars --- p.7 / Chapter 2.3 --- Dynamic Membership --- p.9 / Chapter 3 --- Bandwidth and Computation Reduction Techniques --- p.11 / Chapter 3.1 --- Network Communication --- p.12 / Chapter 3.2 --- Dead Reckoning --- p.13 / Chapter 3.3 --- Message Aggregation --- p.15 / Chapter 3.3.1 --- Network-Based Aggregation --- p.15 / Chapter 3.3.2 --- Organization-Based Aggregations --- p.16 / Chapter 3.3.3 --- Grid-Based Aggregations --- p.16 / Chapter 3.4 --- Relevance Filtering --- p.17 / Chapter 3.4.1 --- Entity-Based Filtering --- p.17 / Chapter 3.4.2 --- Grid-Based Filtering --- p.19 / Chapter 3.5 --- Quiescent Entities --- p.20 / Chapter 3.6 --- Spatial Partitioning --- p.21 / Chapter 3.6.1 --- Necessity of Spatial Partitioning --- p.22 / Chapter 3.6.2 --- Binary Space Partitioning Tree --- p.23 / Chapter 3.6.3 --- BSP Tree Construction --- p.23 / Chapter 4 --- Partitioning Algorithm --- p.25 / Chapter 4.1 --- Problem Formulation --- p.25 / Chapter 4.2 --- Exhaustive Partition (EP) Algorithm --- p.28 / Chapter 4.3 --- Partitioning Algorithm --- p.29 / Chapter 4.3.1 --- Recursive Bisection Partition (RBP) Algorithm --- p.30 / Chapter 4.3.2 --- Layering Partitioning (LP) Algorithm --- p.32 / Chapter 4.3.3 --- Communication Refinement Partitioning (CRP) Algorithm --- p.38 / Chapter 4.4 --- Parallel Approach --- p.42 / Chapter 4.5 --- Further Observation --- p.43 / Chapter 5 --- Experiments --- p.44 / Chapter 5.1 --- Experiment 1: Small Virtual World --- p.45 / Chapter 5.2 --- Experiment 2: Large Virtual World --- p.46 / Chapter 5.3 --- Experiment 3: Moving of Avatars --- p.47 / Chapter 5.4 --- Experiment 4: Dynamic Joining and Leaving --- p.48 / Chapter 5.5 --- Experiment 5: Parallel Approach --- p.49 / Chapter 6 --- Implementation Considerations --- p.55 / Chapter 6.1 --- Different Environments --- p.55 / Chapter 6.2 --- Platform --- p.56 / Chapter 6.3 --- Lessons learned --- p.57 / Chapter 7 --- Conclusion --- p.59 / A Simplex Method --- p.60 / Bibliography --- p.63

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

In this era of exascale computing, conventional synchronous design techniques are facing unprecedented challenges. The consumer electronics market is replete with many-core systems in the range of 16 cores to thousands of cores on chip, integrating multi-billion transistors. However, with this ever increasing complexity, the traditional design approaches are facing key issues such as increasing chip power, process variability, aging, thermal problems, and scalability. An alternative paradigm that has gained significant interest in the last decade is asynchronous design. Asynchronous designs have several potential advantages: they are naturally energy proportional, burning power only when active, do not require complex clock distribution, are robust to different forms of variability, and provide ease of composability for heterogeneous platforms. Networks-on-chip (NoCs) is an interconnect paradigm that has been introduced to deal with the ever-increasing system complexity. NoCs provide a distributed, scalable, and efficient interconnect solution for today’s many-core systems. Moreover, NoCs are a natural match with asynchronous design techniques, as they separate communication infrastructure and timing from the computational elements. To this end, globally-asynchronous locally-synchronous (GALS) systems that interconnect multiple processing cores, operating at different clock speeds, using an asynchronous NoC, have gained significant interest. While asynchronous NoCs have several advantages, they also face a key challenge of supporting new types of traffic patterns. Once such pattern is multicast communication, where a source sends packets to arbitrary number of destinations. Multicast is not only common in parallel computing, such as for cache coherency, but also for emerging areas such as neuromorphic computing. This important capability has been largely missing from asynchronous NoCs. This thesis introduces several efficient multicast solutions for these interconnects. In particular, techniques, and network architectures are introduced to support high-performance and low-power multicast. Two leading network topologies are the focus: a variant mesh-of-trees (MoT) and a 2D mesh. In addition, for a more realistic implementation and analysis, as well as significantly advancing the field of asynchronous NoCs, this thesis also targets synthesis of these NoCs on commercial FPGAs. While there has been significant advances in FPGA technologies, there has been only limited research on implementing asynchronous NoCs on FPGAs. To this end, a systematic computeraided design (CAD) methodology has been introduced to efficiently and safely map asynchronous NoCs on FPGAs. Overall, this thesis makes the following three contributions. The first contribution is a multicast solution for a variant MoT network topology. This topology consists of simple low-radix switches, and has been used in high-performance computing platforms. A novel local speculation technique is introduced, where a subset of the network’s switches are speculative that always broadcast every packet. These switches are very simple and have high performance. Speculative switches are surrounded by non-speculative ones that route packets based on their destinations and also throttle any redundant copies created by the former. This hybrid network architecture achieved significant performance and power benefits over other multicast approaches. The second contribution is a multicast solution for a 2D-mesh topology, which is more complex with higher-radix switches and also is more commonly used. A novel continuous-time replication strategy is introduced to optimize the critical multi-way forking operation of a multicast transmission. In this technique, a multicast packet is first stored in an input port of a switch, from where it is sent through distinct output ports towards different destinations concurrently, at each output’s own rate and in continuous time. This strategy is shown to have significant latency and energy benefits over an approach that performs multicast using multiple distinct serial unicasts to each destination. Finally, a systematic CAD methodology is introduced to synthesize asynchronous NoCs on commercial FPGAs. A two-fold goal is targeted: correctness and high performance. For ease of implementation, only existing FPGA synthesis tools are used. Moreover, since asynchronous NoCs involve special asynchronous components, a comprehensive guide is introduced to map these elements correctly and efficiently. Two asynchronous NoC switches are synthesized using the proposed approach on a leading Xilinx FPGA in 28 nm: one that only handles unicast, and the other that also supports multicast. Both showed significant energy benefits with some performance gains over a state-of-the-art synchronous switch.

Lin, Yangyang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2009. / Includes bibliographical references (p. 50-53). / Abstract also in Chinese. / Chapter Chapter 1 --- Introduction --- p.1 / Chapter Chapter 2 --- Background and Related Work --- p.5 / Chapter 2.1 --- Latency-based Approaches --- p.5 / Chapter 2.2 --- Bandwidth-based Approaches --- p.6 / Chapter 2.3 --- Other Approaches --- p.8 / Chapter 2.4 --- Comparisons and Contributions --- p.9 / Chapter Chapter 3 --- RTT-based Path Selection Revisit --- p.11 / Chapter 3.1 --- Experimental Setting --- p.11 / Chapter 3.2 --- Relationship between RTT and Available Bandwidth --- p.12 / Chapter 3.3 --- Path Selection Accuracy and Efficiency of RTT --- p.13 / Chapter Chapter 4 --- Path Bandwidth measurement --- p.16 / Chapter 4.1 --- In-band Bandwidth Probing --- p.17 / Chapter 4.2 --- Scheduling Constraints --- p.19 / Chapter 4.3 --- Cascaded Bandwidth Probing --- p.20 / Chapter 4.4 --- Model Verification --- p.23 / Chapter Chapter 5 --- Adaptive Multi-overlay ALM --- p.26 / Chapter 5.1 --- Overlay Construction --- p.26 / Chapter 5.2 --- Overlay Adaptation --- p.28 / Chapter 5.3 --- RTT-based Path Selection --- p.30 / Chapter 5.4 --- Topology-Adaptation-Induced Data Loss --- p.31 / Chapter Chapter 6 --- Performance Evaluation --- p.33 / Chapter 6.1 --- Simulation Setting --- p.33 / Chapter 6.2 --- Topology-Adaptation-Induced Data Loss --- p.34 / Chapter 6.3 --- Data Delivery Performance --- p.36 / Chapter 6.4 --- Performance Variation across Peers --- p.38 / Chapter 6.5 --- Performance of Cross Traffic --- p.40 / Chapter 6.6 --- Overlay Topology Convergence --- p.42 / Chapter 6.7 --- Impact of Overlay Adaptation Triggering Threshold --- p.44 / Chapter 6.8 --- Impact of Peer Buffer Size --- p.46 / Chapter Chapter 7 --- Conclusion and future work --- p.48 / References --- p.50

Zhang, Shuqiang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2010. / Includes bibliographical references (p. 74-80). / Abstracts in English and Chinese. / Abstract --- p.i / 摘要 --- p.iv / Acknowledgements --- p.v / Table of Contents --- p.vi / Chapter Chapter 1 --- Background --- p.1 / Chapter 1.1 --- Routing and Wavelength Assignment --- p.1 / Chapter 1.2 --- Survivability in Optical Networks --- p.3 / Chapter 1.3 --- Optical Multicasting --- p.4 / Chapter 1.3.1 --- Routing and Wavelength Assignment of Optical Multicast --- p.5 / Chapter 1.3.2 --- Current Research Topics about Optical Multicast --- p.8 / Chapter 1.4 --- Traffic Grooming --- p.10 / Chapter 1.4.1 --- Static Traffic Grooming --- p.11 / Chapter 1.4.2 --- Dynamic Traffic Grooming --- p.13 / Chapter 1.5 --- Contributions --- p.15 / Chapter 1.5.1 --- Multicast Protection with Scheduled Traffic Model --- p.15 / Chapter 1.5.2 --- Energy Efficient Time-Aware Traffic Grooming --- p.16 / Chapter 1.6 --- Organization of Thesis --- p.18 / Chapter Chapter 2 --- Multicast Protection in WDM Optical Network with Scheduled Traffic --- p.19 / Chapter 2.1 --- Introduction --- p.19 / Chapter 2.2 --- Multicast Protection under FSTM --- p.22 / Chapter 2.3 --- Illustrative Examples --- p.28 / Chapter 2.4 --- Two-Step Optimization under SSTM --- p.37 / Chapter 2.5 --- Summary --- p.40 / Chapter Chapter 3 --- Energy Efficient Time-Aware Traffic Grooming in Wavelength Routing Networks --- p.41 / Chapter 3.1 --- Introduction --- p.41 / Chapter 3.2 --- Energy consumption model --- p.43 / Chapter 3.3 --- Static Traffic Grooming with Time awareness --- p.44 / Chapter 3.3.1 --- Scheduled Traffic Model for Traffic Grooming --- p.44 / Chapter 3.3.2 --- ILP Formulation --- p.44 / Chapter 3.3.3 --- Illustrative Numerical Example --- p.48 / Chapter 3.4 --- Dynamic Traffic Grooming with Time Awareness --- p.49 / Chapter 3.4.1 --- Time-Aware Traffic Grooming (TATG) --- p.51 / Chapter 3.5 --- Simulation Results of Dynamic Traffic Grooming --- p.54 / Chapter 3.5.1 --- 24-node USNET: --- p.55 / Chapter 3.5.2 --- 15-node Pacific Bell Network: --- p.59 / Chapter 3.5.3 --- 14-node NSFNET: --- p.63 / Chapter 3.5.4 --- Alternative Configuration of Simulation Parameters: --- p.67 / Chapter 3.6 --- Summary --- p.71 / Chapter Chapter 4 --- Conclusions and Future Work --- p.72 / Chapter 4.1 --- Conclusions --- p.72 / Chapter 4.2 --- Future Work --- p.73 / Bibliography --- p.74 / Publications during M.Phil Study --- p.80

Thesis (M. Phil.)--University of Hong Kong, 2007. / Title proper from title frame. Also available in printed format.

Thesis (Ph.D.)--University of Nebraska-Lincoln, 2006. / Title from title screen (viewed Mar. 30, 2007). PDF text: vii, 83 p. : ill. (some col.) ; 0.44 Mb. UMI publication number: AAT 3225887. Includes bibliographical references. Also available in microfilm and microfiche formats.

This dissertation addresses the problem of providing a®ordable mobile mul-timedia services in wide area wireless networks. The approach is to con-sider novel system architectures, based on reusing and sharing of the ex-isting network infrastructure for cellular and terrestrial TV broadcastingsystems. The focus has been on the radio resource management techniques,and the evaluation of the potential cost savings, compared to traditionalevolution tracks of the cellular and broadcasting systems.The studies show that deployment cost of a wide area broadcastingnetwork, using DVB-H technology, is very large if high data rate and fullarea coverage is targeted. For this reason we propose to avoid the broad-casting infrastructure dimensioning for full area coverage, and use insteadthe cellular systems to enable error correction for broadcasting transmis-sions. For the special case of mobile users, the chosen approach is to tradesystem's cost and capacity for improved perceived coverage. This trade-o®is enabled by the use of application layer forward error correction, usingRaptor coding.The general purpose Ambient Networks technology was chosen to en-able a platform for inter-operability between cellular and broadcasting sys-tems, especially the necessary interfaces. Under the Ambient Networksframework, we investigate the achievable cost savings o®ered by a hybridcellular-broadcasting system when combinations of broadcast and point-to-point transmissions are jointly utilized to provide ¯le transfers and stream-ing services. Two cases were investigated: one where the cellular systemacts as a replacement and deliver the data in the areas where broadcastingtransmissions cannot reach, and another one where cellular system carriesparity data to users that experience temporary outage in the broadcastingsystem. The results are encouraging, as they show that ¯le transfer costcan be reduced by more than 50%, but only under certain conditions.On a short term, hybrid cellular-broadcasting systems based on 3G andDVB-H, o®er a good platform for testing new and innovative mobile TVservices, enriched with interactivity and content personalization. From atechnical perspective, the outcomes of the presented studies indicate thatfuture systems built on hybrid cellular-broadcasting infrastructures are ableprovide a long term and cost e±cient solution for delivery of a®ordablebroadband multimedia services to mobile users. However, today's cellularand broadcasting systems live in di®erent worlds, are driven by di®erentrevenue models, and they are now starting to compete, instead of cooperate,for controlling the multimedia delivery channels to mobile users. / QC 20100708

In the emerging wireless Internet environment involving m-commerce and other mobile applications, an increasing number of users are likely to adopt mobile transactions. These transactions are likely to have very diverse requirements and some of them may require significant amount of network resources and/or bounded delays. Most quality-of-service research in wireless networks has hitherto focused on call or connection-level QoS. Many mobile transactions are expected to be distinct from the previously investigated applications in their criticality, level of resource required, and in their group characteristics. Examples of such transactions are ones involving a financial value. These unique requirements of mobile transactions necessitate introduction of new metrics for quality-of-service. To measure QoS effectiveness of mobile transactions, two new metrics, namely transaction completion probability and transaction response time are introduced in this research. Moreover, it is well known that wireless networks are constrained for bandwidth. Mobile transactions are expected to require varying degree of bandwidth which makes the resource allocation only at connection level very inefficient. This research proposes a new framework to support QoS requirements of mobile transactions by allocating bandwidth at connection and transaction levels. The proposed framework helps in achieving a balance between transaction completion probability and the response time. Simulation and analytical modeling are used to evaluate the QoS metrics under varying network and traffic scenarios and to validate the effectiveness of the new framework. The results show that the balanced transaction and connection level resource allocation can improve the probability of transactions completion and resource utilization but at the cost of slightly increased response time.

In this thesis, we focus on mobile networks consist of a single base station as the source transceiver, and multiple mobile stations as the receiving party. Applying energy management on multicasting between the base station and mobile stations, network users can conserve the energy consumed while wating for subscribing data contents to come. We referenced the SMBC-D (Scheduling over Multiple Broadcast Channels--the dynamic model) algorithm proposed by R. Cohen et al., grouping users with high request similarity, partitioning channels with a time-division duplexing scheme, and putting mobile stations into sleep mode during channels that include no subscribing data contents. Since SMBC-D statically schedules fixed size channels, groups request fewer data items will idle their channels after finishing their transmision, while groups request more data items take longer time to finish their transmission. For such problem, we propose a heuristic algorithm that makes use of these idle channels by combining adequate consecutive idle channels, to improve channel utility, and lower the overall energy consumed. We also process relevant computer simulations, verifying that our method has better performance.