Thesis (M.Sc.Eng.) PLEASE NOTE: Boston University Libraries did not receive an Authorization To Manage form for this thesis or dissertation. It is therefore not openly accessible, though it may be available by request. If you are the author or principal advisor of this work and would like to request open access for it, please contact us at open-help@bu.edu. Thank you. / Cloud computing demands the reconfigurability on a sub-core basis to maximize the performance per customer application and the overall utilization of hardware resources in a data center. We propose the design of arithmetic units (AUs) using look-up tables (LUTs), which can also function as cache units. We imagine such LUT-based implementations of AUs and caches to be part of a malleable computing paradigm that allows the re-configuration of the core architecture inside a core and across cores. Our envisioned malleable computing can configure an LUT to behave as an AU or a cache at run time depending on the customers, their application requirements, and the computational demand in a data-center. To evaluate the scope for reconfigurability of LUTs, we determined the exchange rate between caches and AUs. This exchange rate tells us the cost of designing a LUT-based AU in kilo bytes of cache. In this thesis, we provide exchange rates for LUT-based adder and multiplier designs. For our analysis, we use CACTI 6.5 to estimate the access time, area, and power of caches varying in size, number of banks, and set associativity, which we fitted by multinomial models. The delay time of these LUT-based designs is comparable to that of logic gate based designs of AUs using the logical effort theory for scaling. As delay time for LUT-based AUs we get 0.5 ns to 1.5 ns (2 GHz to 667 MHz) using the 45 nm Nangate open cell library. The cost of an adder ranges from 0.125 kB to 5 kB cache size. The cost for an multiplier ranges from 2.7 kB to 2.8 kB cache size. The area for these LUT-based designs is smaller or equal compared to logic gate based adder and multiplier designs. Using RRAM technology the area can be reduced by two orders of magnitude with a slowdown in delay time by one order of magnitude. We also compared the robustness of our LUT-based adder and multiplier designs to logic gate equivalent adder and multiplier designs in presence of soft errors using analytical models and simulations. We show that LUT-based designs are more resilient toward soft errors when comparing output error rates of AUs. Our analytical models can help design robust AUs by quantifying design patterns in terms of their robustness. / 2031-01-01

Technology has removed all political boundaries, and has significantly transformed the way business is conducted in the modern age. The world has become a global village in which, by the mere click of a mouse button, anyone can reach any market in any part of the world. This however, has introduced stiff competition among businesses worldwide for markets, where the most affected are SMEs in developing countries. Research has shown these SMEs lack capital to invest in IT in order to improve their competitive advantage. Cloud computing is an emerging computing paradigm, which has been touted as the panacea to help SMEs in developing countries become competitive. For SMEs to be globally competitive, they need to transform and adopt ICT, and use it effectively. A great deal of research has been carried out on the benefits and barriers to ICT adoption by SMEs in both developing and developed countries. The findings obtained from studies from a single country cannot be considered „one size fits all‟ and thus, cannot be applied to all countries, due to the difference in geopolitical and economic development trajectories. Zimbabwe is a developing country, and by virtue of its unique history cannot be compared to any other country in the world. This means that no research conducted outside the borders of Zimbabwe can truly be generalised to SMEs in the country. This study explored the readiness of SMEs in Bulawayo (Zimbabwe) to adopt cloud computing as a business strategy. The study used the NOIIE (which stands for National e-readiness, Organisational preparedness, Industrial relationships, Internal resistance and External influence) conceptual framework to assess the readiness of SMEs in Bulawayo in embracing cloud computing. The study undertook a positivist philosophy, underpinned by quantitative methodology. Questionnaires were sent to systematically sampled SMEs in order to answer the research questions. The data was then collected and analysed by SPSS. The findings revealed that most SMEs are notably young and small, and therefore not mature enough to have foundation for execution. The findings also revealed that top management in SMEs is either not willing to commit or do not have the resources to put in necessary infrastructure to migrate to cloud computing. This indicates a possible lack of awareness of the benefits of the cloud to SMEs. The government has not done enough to promote the use of cloud by SMEs. Power cuts and expensive Internet access exacerbate the plight of the SMEs to move to the cloud. Lack of visible cloud service providers makes the situation even worse. / Computing / M. Sc. (Computing)

abstract: Security has been one of the top concerns in cloud community while cloud resource abuse and malicious insiders are considered as top threats. Traditionally, Intrusion Detection Systems (IDS) and Intrusion Prevention Systems (IPS) have been widely deployed to manipulate cloud security, with the latter one providing additional prevention capability. However, as one of the most creative networking technologies, Software-Defined Networking (SDN) is rarely used to implement IDPS in the cloud computing environment because the lack of comprehensive development framework and processing flow. Simply migration from traditional IDS/IPS systems to SDN environment are not effective enough for detecting and defending malicious attacks. Hence, in this thesis, we present an IPS development framework to help user easily design and implement their defensive systems in cloud system by SDN technology. This framework enables SDN approaches to enhance the system security and performance. A Traffic Information Platform (TIP) is proposed as the cornerstone with several upper layer security modules such as Detection, Analysis and Prevention components. Benefiting from the flexible, compatible and programmable features of SDN, Customized Detection Engine, Network Topology Finder, Source Tracer and further user-developed security appliances are plugged in our framework to construct a SDN-based defensive system. Two main categories Python-based APIs are designed to support developers for further development. This system is designed and implemented based on the POX controller and Open vSwitch in the cloud computing environment. The efficiency of this framework is demonstrated by a sample IPS implementation and the performance of our framework is also evaluated. / Dissertation/Thesis / Masters Thesis Computer Science 2014

Made available in DSpace on 2014-06-12T15:57:46Z (GMT). No. of bitstreams: 2 arquivo3224_1.pdf: 1528247 bytes, checksum: a3554156b6142706a9da81ae71bcfd08 (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2010 / Faculdade de Amparo à Ciência e Tecnologia do Estado de Pernambuco / Atualmente, os computadores vêm experimentando um aumento de capacidades, apesar de passarem por constante miniaturização e ganho de mobilidade. Em paralelo, a velocidade e a confiabilidade das conexões evoluem a passos largos. Para explorar esta nova relação entre comunicação em rede e processamento foi desenvolvido o conceito de computação em nuvem, na qual os serviços são oferecidos através de uma rede difusa e os consumidores destes não têm ciência de como os provedores realizam suas atividades. Devido à natureza heterogênea deste paradigma de provisão e consumo, a descrição e criação desta categoria de serviços têm sua dificuldade aumentada, visto que os produtos de diversos domínios devem funcionar sobre plataformas não padronizadas e ser oferecidos a consumidores diversos de forma direta, contudo mantendo sua funcionalidade. O uso de padrões é uma solução bastante difundida nos mais diversos ramos de criação de processos, pois prega o reuso de trabalho de desenvolvimento, dando um suporte histórico a cada novo processo criado a partir de um padrão. Este trabalho propõe uma forma de acelerar o desenvolvimento e a implantação de serviços para computação em nuvem através da divisão da criação em três etapas. As etapas relacionadas à criação são semiautomatizadas pelo uso de padrões de projeto e de desenvolvimento, enquanto a etapa de implantação é totalmente automatizada pelo uso de moldes de compilação

I dagens samhälle blir fler och fler enheter uppkopplade mot Internet vilket kan ge en annars begränsad hårdvara möjlighet att genomföra större beräkningar. Detta projekt avser att skapa ett system som hanterar en användares radarenheter i ett molnbaserat system. Systemet erbjuder även möjligheten att ladda upp användarens egna applikationer vilka använder data från radarenheten, körs på virtuella maskiner och vid behov har möjlighet att skicka notiser till användarens mobila applikationer. För att underlätta utveckling har systemet delats upp i tre delsystem. Dessa är radarenhet, molntjänst och mobilapplikation. Projektet resulterade i ett komplett system med en webbapplikation som erbjuder användaren möjlighet att registrera sina radarenheter, ladda upp källkod som kompileras och körs på en molntjänst samt möjlighet att skicka notiser till en mobilapplikation. / Todays age sees more and more devices connected to the internet providing otherwise quite limited hardware with the ability to perform more complex calculations. This project aims to create a system for managing a users radar devices using a cloud platform. The system also provides the ability for the user to upload their own custom applications which can make use of data provided by the radar device, run on virtual machines and if required have the ability to push notifications to the users mobile applications. To simplify the system development, it has been divided into three separate subsystems, specifically the radar device, the cloud service and the mobile application. The result of the project is a complete system with a web application which provides the user with the ability to register their radar device(s), upload source code which is compiled and run on the cloud platform and the ability to send push notices to a mobile application.

It was known for a long time that OpenStack has issues with scalability. Peer-to-Peer systems, on the other hand, have proven to scale well without significant reduction of performance. The objectives of this thesis are to study the challenges associated with P2P-enhanced clouds and present solutions for overcoming them. As a case study, we take the architecture of the P2P-enhanced OpenStack implemented at Ericsson that uses the CYCLON P2Pprotocol. We study the OpenStack architecture and P2P technologies and finally propose solutions and provide possibilities in addressing the challenges that are faced by P2P-enhanced OpenStack clouds. We emphasize mainly on a decentralized identity service and management of Virtual machine images. This work also investigates the characterization of P2P architectures for their use in P2P-enhanced OpenStack clouds. The results section shows that the proposed solution enables the existing P2P system to scale beyond what was originally possible. We also show that the P2P-enhanced system performs better than the standard OpenStack. / <p>Ericsson Cloud Research supported this work through the guidance of Dr. Fetahi Wuhib, Dr. Joao Monteiro Soares and Vinay Yadav, Experienced Researchers, Ericsson Cloud Research, Kista, Stockholm.</p>

Server selection is an important problem of cloud computing in which cloud service providers direct user demands to servers in one of the multiple data centers located in different geographical locations. The existing solutions usually assume homogeneity of cloud services (i.e., all users request the same type of service) and handle user demands in an individual basis which incurs high computational overhead. In this study, we propose a new and effective server selection scheme in which diversities of cloud services are taken into account. We focus on a specific cloud service, i.e., online video service, and assume that different videos have different bandwidth requirements. We group users into clusters and handle user demands on a cluster basis for faster and more efficient process. Firstly, we assume that user demands and bandwidth capacities of servers are given in the data centers, our problem is to assign the user demands to the servers under the bandwidth constraint, such that the overall latency (measured by the network distance) between the user clusters and the selected servers is minimized. We design a server selection system and formulate this problem as a linear programming formulation which can be solved by existing techniques. The system periodically executes our scheme and computes an optimal solution for server selection. User demands are assigned to the servers according to the optimal solution and the minimum overall latency can be achieved. The simulation results show that our scheme is significantly better than the random algorithm and the YouTube server selection strategy. Based on the first part, we take the storage capacities of servers constraint into consideration. In the second part, our new problem is to assign the user demands to the servers under the bandwidth and storage constraint, such that the function of overall latency (measured by the network distance) between the user clusters and the selected servers and standard deviation of traffic load of every server in the system is minimized. We design a server selection system and formulate this problem which can be solved by existing techniques. User demands are assigned to the servers according to the optimal solution and the two goals (minimum overall latency and the most balanced traffic load) can be achieved. The simulation results show the influence of different weights of these two goals on the user demands assigning.

Magister Artium - MA / Cloud computing, as a shifting paradigm, is expanding its “bandwagon effect” across industries worldwide. This is due to the several advantages of cloud computing that have been revealed by the public sectors (empirical setting of this study), including improved levels of flexibility and mobility, lower total cost of ownership, reduced energy savings and carbon missions. Most importantly, cloud computing can free government from building, maintaining and upgrading its infrastructures and technologies, and focus more on serving the citizens with optimised resources. Hence, this paper focuses on the readiness assessment of cloud-computing adoption within a Provincial Government of South Africa, which is in its cloud-computing embryonic phase. An extensive study of the literature on cloud-computing concepts, its characteristics, the possible non-technological readiness indicators for cloud-computing adoption, was conducted. This led to the identification of three main groups of readiness indicators: (i) Infrastructural indicators; (ii) organisational indicators; and (iii) environmental indicators. A conceptual model was then developed, according to these three main groups, with twelve sub-indicators. This model was subsequently tested in the empirical setting of the studied Provincial Government of South Africa by using the qualitative approach through the case-study methodology. The intended audience for this study are both academic and practitioners as it brings a conceptual model and the guidelines for assessing the government‟s readiness for the adoption of these cloud-computing technologies and services.

As the size of cloud systems and the number of hosted virtual machines (VMs) rapidly grow, the scalability of shared VM storage systems becomes a serious issue. Client-side flash-based caching has the potential to improve the performance of cloud VM storage by employing flash storage available on the VM hosts to exploit the locality inherent in VM IOs. However, there are several challenges to the effective use of flash caching in cloud systems. First, cache configurations such as size, write policy, metadata persistency and RAID level have significant impacts on flash caching. Second, the typical capacity of flash devices is limited compared to the dataset size of consolidated VMs. Finally, flash devices wear out and face serious endurance issues which are aggravated by the use for caching. This dissertation presents the research for addressing these problems of cloud flash caching in the following three aspects. First, it presents a thorough study of different cache configurations including a new cache-optimized RAID configuration using a large amount of long-term traces collected from real-world public and private clouds. Second, it studies an on-demand flash cache management solution for meeting VM cache demands and minimizing device wear-out. It uses a new cache demand model Reuse Working Set (RWS) to capture the data with good temporal locality, and uses the RWS size (RWSS) to model a workload?s cache demand. Finally, to handle situations where a cache is insufficient for VMs? demands, it employs dynamic cache migration to balance cache load across hosts by live migrating cached data along with the VMs. The results show that the cache-optimized RAID improves performance by 137% without sacrificing reliability, compared to traditional RAID. The RWSS-based on-demand cache allocation reduces workload?s cache usage by 78% and lowers the amount of writes sent to cache device by 40%, compared to traditional working set based cache allocation. Combining on-demand cache allocation with dynamic cache migration for 12 concurrent VMs, results show 28% higher hit ratio and 28% lower 90th percentile IO latency, compared to the case without cache allocation.

The Govan Mbeki Mathematics Development Unit (GMMDU) provides additional mathematics content to learners via mathematics workshops and DVDs. Mathematics is presented in PPT format. The prominence of feature phone usage has been confirmed amongst learners in socio-economic disadvantaged schools, specifically those learners participating in the GMMDU mathematics workshops. Feature phones typically contain limited device resources such as memory, battery power, and network resources. Distributed computing provides the potential to facilitate a new class of mobile applications with the provision of off-device resources. The objective of this research was the design of an architecture using Cloud Computing for the provision of mathematics in the form of PPT slides to feature phones. The capabilities of typical feature phones were reviewed as well as various distributed computing architectures that demonstrate potential benefit to the mobile environment. An Architecture using Cloud Computing for Content Provision (AC3P) was subsequently designed and applied as a proof of concept to facilitate the provision of mathematics in the form of PPT slides to feature phones. The application of AC3P was evaluated for efficiency and effectiveness. It was demonstrated that the application of AC3P provided efficient and effective provision of PPT to feature phones. The successful application of AC3P provided evidence that Cloud Computing may be used to facilitate the provision of mathematics content to feature phones. It is evident that AC3P may be applied in domains other than the provision of mathematics.