Public transport is important to society as it provides spatial accessibility and reduces congestion and pollution in comparison to other motorized modes. To assure a high-quality service, all parts of the system need to be well-functioning and properly planned. One important aspect for the system's bus terminals is their capacity. This needs to be high enough to avoid congestion and queues and the delays these may lead to. During planning processes, various suggested designs and solutions for a terminal need to be evaluated. Estimating capacity and how well the suggestions will function is a challenging problem, however. It requires analysis of complex interactions and behaviour of the vehicles. This sort of analyses can preferably be carried out using microsimulation. Furthermore, a discrete event simulation approach can make use of the fact that the path of a vehicle through a terminal can readily be described by a sequence of events (such as arriving, starting to drive to a stop etc.). The overall aim of this thesis is to investigate how discrete event simulation can be used to evaluate bus terminal design and traffic control policies. The main contribution is the development of a method for bus terminal simulation. As a first step, a discrete event simulation model of a combined bus and tram stop is formulated. The model is tested on a real system where the current design is compared to an alternative one. The test shows that a model developed with a discrete event approach can be used to evaluate the situation at a stop and compare design alternatives. In the next step, a general discrete event simulation model of bus terminals is formulated. A modular approach is introduced, where a terminal can be constructed from a set of module building blocks. Another important contribution of the model is its spatial resolution that allows for queues and blockages to occur throughout the terminal. By applying the simulation model in a case study, it is shown that the model can be used to evaluate and compare various scenarios related to the layout, number of passengers and the outside traffic situation. Lastly, the bus terminal simulation model is used in a second case study in order to compare model output with empirical data. This study identified a number of factors that may have had an influence on differences between observations and simulation results and that is of interest to look further into. This includes the actual adherence to terminal rules and the effects of model parameters.

從文件系統設計的角度,我們探索了利用重復數據删除技術來消除硬盤陣列存儲設備當中的重復數據。我們提出了ScaleDFS,一個重復數據删除技術的文件系統, 旨在硬盤陣列存儲設備上實現可擴展的吞吐性能。ScaleDFS有三個主要的特點。第一,利用多核CPU並行計算出用作識別重復數據的加密指紋,以提高寫入速度。第二,緩存曾經讀取過的重復數據塊,以顯著提高讀取速度。第三,優化用作查找指紋的內存數據結構,以更加節省內存。ScaleDFS是一個以Linux系統內核模塊開發的,與POSIX兼容的,可以用在一般低成本硬件配置上的文件系統。我們進行了一系列的微觀性能測試,以及用42個不同版本的Linux虛擬鏡像文件進行了宏觀性能測試。我們證實,ScaleDFS在磁盤陣列上比目前已有的開源重復數據删除文件系統擁有更好的讀寫性能。 / We explore the use of deduplication for eliminating the storage of redundant data in RAID from a file-system design perspective. We propose ScaleDFS, a deduplication file system that seeks to achieve scalable read/write throughput in RAID. ScaleDFS is built on three novel design features. First, we improve the write throughput by exploiting multiple CPU cores to parallelize the processing of the cryptographic fingerprints that are used to identify redundant data. Second, we improve the read throughput by specifically caching in memory the recently read blocks that have been deduplicated. Third, we reduce the memory usage by enhancing the data structures that are used for fingerprint lookups. ScaleDFS is implemented as a POSIX-compliant, kernel-space driver module that can be deployed in commodity hardware configurations. We conduct microbenchmark experiments using synthetic workloads, and macrobenchmark experiments using a dataset of 42 VM images of different Linux distributions. We show that ScaleDFS achieves higher read/write throughput than existing open-source deduplication file systems in RAID. / Detailed summary in vernacular field only. / Ma, Mingcao. / "October 2012." / Thesis (M.Phil.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves 39-42). / Abstracts also in Chinese. / Chapter 1 --- Introduction --- p.2 / Chapter 2 --- Literature Review --- p.5 / Chapter 2.1 --- Backup systems --- p.5 / Chapter 2.2 --- Use of special hardware --- p.6 / Chapter 2.3 --- Scalable storage --- p.6 / Chapter 2.4 --- Inline DFSs --- p.6 / Chapter 2.5 --- VM image storage with deduplication --- p.7 / Chapter 3 --- ScaleDFS Background --- p.8 / Chapter 3.1 --- Spatial Locality of Fingerprint Placement --- p.9 / Chapter 3.2 --- Prefetching of Fingerprint Stores --- p.12 / Chapter 3.3 --- Journaling --- p.13 / Chapter 4 --- ScaleDFS Design --- p.15 / Chapter 4.1 --- Parallelizing Deduplication --- p.15 / Chapter 4.2 --- Caching Read Blocks --- p.17 / Chapter 4.3 --- Reducing Memory Usage --- p.17 / Chapter 5 --- Implementation --- p.20 / Chapter 5.1 --- Choice of Hash Function --- p.20 / Chapter 5.2 --- OpenStack Deployment --- p.21 / Chapter 6 --- Experiments --- p.23 / Chapter 6.1 --- Microbenchmarks --- p.23 / Chapter 6.2 --- OpenStack Deployment --- p.28 / Chapter 6.3 --- VM Image Operations in a RAID Setup --- p.33 / Chapter 7 --- Conclusions and FutureWork --- p.38 / Bibliography --- p.39

Leung Cheung-chi. / "July 2004." / Thesis (Ph.D.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (p. 77-81). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Mode of access: World Wide Web. / Abstracts in English and Chinese.

As the number of Internet of Things (IoT) devices that are used daily is increasing, the inadequacy of cloud computing to provide neseccary IoT-related features, such as low latency, geographic distribution and location awareness, is becoming more evident. Fog computing is introduced as a new computing paradigm, in order to solve this problem by extending the cloud‟s storage and computing resources to the network edge. However, the introduction of this new paradigm is also confronted by various security threats and challenges since the security practices that are implemented in cloud computing cannot be applied directly to this new architecture paradigm. To this end, various papers have been published in the context of fog computing security, in an effort to establish the best security practices towards the standardization of fog computing. In this thesis, we perform a systematic literature review of current research in order to provide with a classification of the various security threats and challenges in fog computing. Furthermore, we present the solutions that have been proposed so far and which security challenge do they address. Finally, we attempt to distinguish common aspects between the various proposals, evaluate current research on the subject and suggest directions for future research.

by Ching-Ting, Ng. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1996. / Includes bibliographical references (leaves 79-82). / Abstract --- p.i / Acknowledgement --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Background --- p.5 / Chapter 2.1 --- Protocols tackling site failure --- p.5 / Chapter 2.2 --- Protocols tackling Partition Failure --- p.6 / Chapter 2.2.1 --- Primary site --- p.6 / Chapter 2.2.2 --- Quorum Consensus Protocol --- p.7 / Chapter 2.2.3 --- Missing Writes --- p.10 / Chapter 2.2.4 --- Virtual Partition Protocol --- p.11 / Chapter 2.3 --- Protocols to enhance the Performance of Updating --- p.11 / Chapter 2.3.1 --- Independent Updates and Incremental Agreement in Replicated Databases --- p.12 / Chapter 2.3.2 --- A Transaction Replication Scheme for a Replicated Database with Node Autonomy --- p.13 / Chapter 3 --- Transaction Replication Scheme --- p.17 / Chapter 3.1 --- A TRS for a Replicated Database with Node Autonomy --- p.17 / Chapter 3.1.1 --- Example --- p.17 / Chapter 3.1.2 --- Problem --- p.18 / Chapter 3.1.3 --- Network Model --- p.18 / Chapter 3.1.4 --- Transaction and Data Model --- p.19 / Chapter 3.1.5 --- Histories and One-Copy Serializability --- p.20 / Chapter 3.1.6 --- Transaction Broadcasting Scheme --- p.21 / Chapter 3.1.7 --- Local Transactions --- p.22 / Chapter 3.1.8 --- Public Transactions --- p.23 / Chapter 3.1.9 --- A Conservative Timestamping Algorithm --- p.24 / Chapter 3.1.10 --- Decentralized Two-Phase Commit --- p.25 / Chapter 3.1.11 --- Partition Failures --- p.27 / Chapter 4 --- Simulation Model --- p.29 / Chapter 4.1 --- Simulation Model --- p.29 / Chapter 4.1.1 --- Model Design --- p.29 / Chapter 4.2 --- Implement at ion --- p.37 / Chapter 4.2.1 --- Simulation --- p.37 / Chapter 4.2.2 --- Simulation Language --- p.37 / Chapter 5 --- Performance Results and Analysis --- p.39 / Chapter 5.1 --- Simulation Results and Data Analysis --- p.39 / Chapter 5.1.1 --- Experiment 1 : Variation of TRS Period --- p.44 / Chapter 5.1.2 --- Experiment 2 : Variation of Clock Synchronization --- p.47 / Chapter 5.1.3 --- Experiment 3 : Variation of Ratio of Local to Public Transaction --- p.49 / Chapter 5.1.4 --- Experiment 4 : Variation of Number of Operations --- p.51 / Chapter 5.1.5 --- Experiment 5 : Variation of Message Transmit Delay --- p.55 / Chapter 5.1.6 --- Experiment 6 : Variation of the Interarrival Time of Transactions --- p.58 / Chapter 5.1.7 --- Experiment 7 : Variation of Operation CPU cost --- p.61 / Chapter 5.1.8 --- Experiment 8 : Variation of Disk I/O time --- p.64 / Chapter 5.1.9 --- Experiment 9 : Variation of Cache Hit Ratio --- p.66 / Chapter 5.1.10 --- Experiment 10 : Variation of Number of Data Access --- p.68 / Chapter 5.1.11 --- Experiment 11 : Variation of Read Operation Ratio --- p.70 / Chapter 5.1.12 --- Experiment 12 : Variation of One Site Failed --- p.72 / Chapter 5.1.13 --- Experiment 13 : Variation of Sites Available --- p.74 / Chapter 6 --- Conclusion --- p.77 / Bibliography --- p.79 / Chapter A --- Implementation --- p.83 / Chapter A.1 --- Assumptions of System Model --- p.83 / Chapter A.1.1 --- Program Description --- p.83 / Chapter A.1.2 --- TRS System --- p.85 / Chapter A. 1.3 --- Common Functional Modules for Majority Quorum and Tree Quo- rum Protocol --- p.88 / Chapter A.1.4 --- Majority Quorum Consensus Protocol --- p.90 / Chapter A. 1.5 --- Tree Quorum Protocol --- p.91

Thesis (M.S.V.S.)--Massachusetts Institute of Technology, Dept. of Architecture, 1982. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ROTCH. VIDEODISC IN ARCHIVES AND ROTCH VISUAL COLLECTIONS. / Includes bibliographical references (leaves 87-90). / A technique of pictorially synthesizing facial imagery using optical videodiscs under computer control is described. Search, selection and averaging processes are performed on a catalogue of whole faces and facial features to yield a composite, expressive, recognizable face. An immediate application of this technique is the reconstruction of a particular face from memory for police identification, thus the project is called , IDENTIDISC. Part I-PACEMAKER describes the production and implementation of the IDENTIDISC system to produce composite faces. Part II-EXPRESSIONMAKER describes animation techniques to add expression and motion to composite faces . Expression sequences are manipulated to make 'anyface' make any face. Historical precedents of making facial composites, theories of facial recognition, classification and expression are also discussed. This thesis is accompanied by two copies of PACEMAKER-III, an optical videodisc produced at the Architecture Machine Group in 1982. The disc can be played on an optical videodisc player . The length is approximately 15 , 0000 frames. Frame numbers are indicated in the text by [ ]. / by Peggy Weil. / M.S.V.S.

Thesis. 1977. Ph.D.--Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. / Vita. / Bibliography : leaves 261-265. / by Peter B. Bishop. / Ph.D.

Thesis (M.S.V.S.)--Massachusetts Institute of Technology, Dept. of Architecture, 1982. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ROTCH. / Bibliography: leaves 111-116. / The human face is a highly significant visual display which we are able to remember and recognize easily despite the fact that we are exposed to thousands of faces which may be metrically very similar. caricature is a graphical coding of facial features which seeks to be more like the face than the face itself: selected information is exaggerated, noise is reduced, and the processes involved in recognition are exploited. After studying the methods of caricaturists, examining perceptual phenomena regarding individuating features, and surveying automatic and man-machine systems which represent and manipulate the face, some heuristics for caricature are defined . An algorithm is implemented to amplify the nuance of a human face in a computer- generated caricature. This is done by comparing the face to a norm and then distorting the face even further away from that norm . Issues of style, context and animation are discussed. The applications of the caricature generator in the areas of teleconferencing, games, and interactive graphic interfaces are explored. / by Susan Elise Brennan. / M.S.V.S.

Thesis (M.S.V.S.)--Massachusetts Institute of Technology, Dept. of Architecture, 1982. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ROTCH. VIDEOCASSETTE IN ROTCH VISUAL COLLECTIONS. / Bibliography: leaves 90-93. / by Ann Ross Marion. / M.S.V.S.

When deploying software engineering applications in the cloud there are two similar software components used. These are Virtual Machines and Containers. In recent years containers have seen an increase in popularity and usage, in part because of tools such as Docker and Kubernetes. Virtual Machines (VM) have also seen an increase in usage as more companies move to solutions in the cloud with services like Amazon Web Services, Google Compute Engine, Microsoft Azure and DigitalOcean. There are also some solutions using auto-scaling, a technique where VMs are commisioned and deployed to as load increases in order to increase application performace. As the application load decreases VMs are decommisioned to reduce costs. In this thesis we implement and evaluate auto-scaling policies that use both Virtual Machines and Containers. We compare four different policies, including two baseline policies. For the non-baseline policies we define a policy where we use a single Container for every Virtual Machine and a policy where we use several Containers per Virtual Machine. To compare the policies we deploy an image serving application and run workloads to test them. We find that the choice of deployment strategy and policy matters for response time and error rate. We also find that deploying applications as described in the methodis estimated to take roughly 2 to 3 minutes.