Executing bag of distributed tasks on the cloud: Investigating the trade-offs between performance and cost

Bag of Distributed Tasks (BoDT) can benefit from decentralised execution on the Cloud. However, there is a trade-off between the performance that can be achieved by employing a large number of Cloud VMs for the tasks and the monetary constraints that are often placed by a user. The research reported in this paper is motivated towards investigating this trade-off so that an optimal plan for deploying BoDT applications on the cloud can be generated. A heuristic algorithm, which considers the user's preference of performance and cost is proposed and implemented. The feasibility of the algorithm is demonstrated by generating execution plans for a sample application. The key result is that the algorithm generates optimal execution plans for the application over 91% of the time.

Optimal deployment of geographically distributed workflow engines on the cloud

When orchestrating Web service workflows, the geographical placement of the orchestration engine (s) can greatly affect workflow performance. Data may have to be transferred across long geographical distances, which in turn increases execution time and degrades the overall performance of a workflow. In this paper, we present a framework that, given a DAG-based workflow specification, computes the optimal Amazon EC2 cloud regions to deploy the orchestration engines and execute a workflow. The framework incorporates a constraint model that solves the workflow deployment problem, which is generated using an automated constraint modelling system. The feasibility of the framework is evaluated by executing different sample workflows representative of scientific workloads. The experimental results indicate that the framework reduces the workflow execution time and provides a speed up of 1.3x-2.5x over centralised approaches.

Design and Qualitative/Quantitative Analysis of Multi-Agent Spatial Simulation Library

Thesis (Master's)--University of Washington, 2012

Energy-aware Workflow Scheduling and Fuzzy Logic Based Capacity Provisioning in Cloud Environment

Thesis (Master's)--University of Washington, 2015

Providing User Security Guarantees in Public Infrastructure Clouds

The infrastructure cloud (IaaS) service model offers improved resource flexibility and availability, where tenants - insulated from the minutiae of hardware maintenance - rent computing resources to deploy and operate complex systems. Large-scale services running on IaaS platforms demonstrate the viability of this model; nevertheless, many organizations operating on sensitive data avoid migrating operations to IaaS platforms due to security concerns. In this paper, we describe a framework for data and operation security in IaaS, consisting of protocols for a trusted launch of virtual machines and domain-based storage protection. We continue with an extensive theoretical analysis with proofs about protocol resistance against attacks in the defined threat model. The protocols allow trust to be established by remotely attesting host platform configuration prior to launching guest virtual machines and ensure confidentiality of data in remote storage, with encryption keys maintained outside of the IaaS domain. Presented experimental results demonstrate the validity and efficiency of the proposed protocols. The framework prototype was implemented on a test bed operating a public electronic health record system, showing that the proposed protocols can be integrated into existing cloud environments.

Dynamic power- and failure-aware cloud resources allocation for Sets of independent tasks

Cloud computing is increasingly being adopted in different scenarios, like social networking, business applications, scientific experiments, etc. Relying in virtualization technology, the construction of these computing environments targets improvements in the infrastructure, such as power-efficiency and fulfillment of users’ SLA specifications. The methodology usually applied is packing all the virtual machines on the proper physical servers. However, failure occurrences in these networked computing systems can induce substantial negative impact on system performance, deviating the system from ours initial objectives. In this work, we propose adapted algorithms to dynamically map virtual machines to physical hosts, in order to improve cloud infrastructure power-efficiency, with low impact on users’ required performance. Our decision making algorithms leverage proactive fault-tolerance techniques to deal with systems failures, allied with virtual machine technology to share nodes resources in an accurately and controlled manner. The results indicate that our algorithms perform better targeting power-efficiency and SLA fulfillment, in face of cloud infrastructure failures.

Benchmarking de uma aproximação de ticketing as a service (Taas)

Dissertação de natureza científica realizada para obtenção do grau de Mestre em Engenharia de Redes de Computadores e Multimédia

Ownserver: sistema doméstico de prestação de serviços cloud

Neste trabalho foi considerada a possibilidade de incorporar serviços remotos, normalmente associados a serviços web e cloud computing, numa solução local que centralizasse os vários serviços num único sistema e permitisse aos seus utilizadores consumir e configurar os mesmos, quer a partir da rede local, quer remotamente a partir da Internet. Desta forma seria possível conciliar o acesso a partir de qualquer local com internet, característico nas clouds, com a simplicidade de concentrar num só sistema vários serviços que são por norma oferecidos por entidades distintas e ainda permitir aos seus utilizadores o controlo e configuração sobre os mesmos. De forma a validar que este conceito é viável, prático e funcional, foram implementadas duas componentes. Um cliente que corre nos dispositivos dos utilizadores e que proporciona a interface para consumir os serviços disponíveis e um servidor que irá conter e prestar esses serviços aos clientes. Estes serviços incluem lista de contactos, mensagens instantâneas, salas de conversação, transferência de ficheiros, chamadas e conferências de voz e vídeo, pastas remotas, pastas sincronizadas, backups, pastas partilhadas, VoD (Video-on Demand) e AoD (Audio-on Demand). Para o desenvolvimento do cliente e do servidor foi utilizada a framework Qt que recorre à linguagem de programação C++ e ao conjunto de bibliotecas que possui, para o desenvolvimento de aplicações multiplataforma. Para as comunicações entre clientes e servidor, foi utilizado o protocolo XMPP (Extensible Messaging and Presence Protocol), pela forma da biblioteca qxmpp e do servidor XMPP ejabberd. Pelo facto de conter um conjunto de centenas de extensões atualmente ativas que auferem funcionalidades como salas de conversação, transferências de ficheiros e até estabelecer sessões multimédia, graças à sua flexibilidade permitiu ainda a criação de extensões personalizada necessárias para algumas funcionalidades que se pretendeu implementar. Foi ainda utilizado no servidor a framework ffmpeg para suportar algumas funcionalidades multimédia. Após a implementação do cliente para Windows e Linux, e de implementar o servidor em Linux foi realizado um conjunto de testes funcionais para perceber se as funcionalidades e seus mecanismos funcionam corretamente. No caso onde a análise da performance e do consumo de recursos era importante, foram realizados testes de performance e testes de carga.

Las TIC en la administración de la cadena de suministro y su incidencia en el desempeño operacional

Las tecnologías de la información han empezado a ser un factor importante a tener en cuenta en cada uno de los procesos que se llevan a cabo en la cadena de suministro. Su implementación y correcto uso otorgan a las empresas ventajas que favorecen el desempeño operacional a lo largo de la cadena. El desarrollo y aplicación de software han contribuido a la integración de los diferentes miembros de la cadena, de tal forma que desde los proveedores hasta el cliente final, perciben beneficios en las variables de desempeño operacional y nivel de satisfacción respectivamente. Por otra parte es importante considerar que su implementación no siempre presenta resultados positivos, por el contrario dicho proceso de implementación puede verse afectado seriamente por barreras que impiden maximizar los beneficios que otorgan las TIC.

The assessment of benchmarks executed on bare-metal and using para-virtualization

A full assessment of para-­virtualization is important, because without knowledge about the various overheads, users can not understand whether using virtualization is a good idea or not. In this paper we are very interested in assessing the overheads of running various benchmarks on bare-­‐metal, as well as on para-­‐virtualization. The idea is to see what the overheads of para-­‐ virtualization are, as well as looking at the overheads of turning on monitoring and logging. The knowledge from assessing various benchmarks on these different systems will help a range of users understand the use of virtualization systems. In this paper we assess the overheads of using Xen, VMware, KVM and Citrix, see Table 1. These different virtualization systems are used extensively by cloud-­‐users. We are using various Netlib1 benchmarks, which have been developed by the University of Tennessee at Knoxville (UTK), and Oak Ridge National Laboratory (ORNL). In order to assess these virtualization systems, we run the benchmarks on bare-­‐metal, then on the para-­‐virtualization, and finally we turn on monitoring and logging. The later is important as users are interested in Service Level Agreements (SLAs) used by the Cloud providers, and the use of logging is a means of assessing the services bought and used from commercial providers. In this paper we assess the virtualization systems on three different systems. We use the Thamesblue supercomputer, the Hactar cluster and IBM JS20 blade server (see Table 2), which are all servers available at the University of Reading. A functional virtualization system is multi-­‐layered and is driven by the privileged components. Virtualization systems can host multiple guest operating systems, which run on its own domain, and the system schedules virtual CPUs and memory within each Virtual Machines (VM) to make the best use of the available resources. The guest-­‐operating system schedules each application accordingly. You can deploy virtualization as full virtualization or para-­‐virtualization. Full virtualization provides a total abstraction of the underlying physical system and creates a new virtual system, where the guest operating systems can run. No modifications are needed in the guest OS or application, e.g. the guest OS or application is not aware of the virtualized environment and runs normally. Para-­‐virualization requires user modification of the guest operating systems, which runs on the virtual machines, e.g. these guest operating systems are aware that they are running on a virtual machine, and provide near-­‐native performance. You can deploy both para-­‐virtualization and full virtualization across various virtualized systems. Para-­‐virtualization is an OS-­‐assisted virtualization; where some modifications are made in the guest operating system to enable better performance. In this kind of virtualization, the guest operating system is aware of the fact that it is running on the virtualized hardware and not on the bare hardware. In para-­‐virtualization, the device drivers in the guest operating system coordinate the device drivers of host operating system and reduce the performance overheads. The use of para-­‐virtualization [0] is intended to avoid the bottleneck associated with slow hardware interrupts that exist when full virtualization is employed. It has revealed [0] that para-­‐ virtualization does not impose significant performance overhead in high performance computing, and this in turn this has implications for the use of cloud computing for hosting HPC applications. The “apparent” improvement in virtualization has led us to formulate the hypothesis that certain classes of HPC applications should be able to execute in a cloud environment, with minimal performance degradation. In order to support this hypothesis, first it is necessary to define exactly what is meant by a “class” of application, and secondly it will be necessary to observe application performance, both within a virtual machine and when executing on bare hardware. A further potential complication is associated with the need for Cloud service providers to support Service Level Agreements (SLA), so that system utilisation can be audited.

Cloud-assisted body area networks: state-of-the-art and future challenges

Body area networks (BANs) are emerging as enabling technology for many human-centered application domains such as health-care, sport, fitness, wellness, ergonomics, emergency, safety, security, and sociality. A BAN, which basically consists of wireless wearable sensor nodes usually coordinated by a static or mobile device, is mainly exploited to monitor single assisted livings. Data generated by a BAN can be processed in real-time by the BAN coordinator and/or transmitted to a server-side for online/offline processing and long-term storing. A network of BANs worn by a community of people produces large amount of contextual data that require a scalable and efficient approach for elaboration and storage. Cloud computing can provide a flexible storage and processing infrastructure to perform both online and offline analysis of body sensor data streams. In this paper, we motivate the introduction of Cloud-assisted BANs along with the main challenges that need to be addressed for their development and management. The current state-of-the-art is overviewed and framed according to the main requirements for effective Cloud-assisted BAN architectures. Finally, relevant open research issues in terms of efficiency, scalability, security, interoperability, prototyping, dynamic deployment and management, are discussed.

Forensiska Undersökningar av Molntjänster

Användning av molntjänster har gjort forensiska undersökningar mer komplicerade. Däremot finns det goda förutsättningar om molnleverantörerna skapar tjänster för att få ut all information. Det skulle göra det enklare och mer tillförlitligt. Informationen som ska tas ut från molntjänsterna är svår att få ut på ett korrekt sätt. Undersökningen görs inte på en skrivskyddad kopia, utan i en miljö som riskerar att förändras. Det är då möjligt att ändringar görs under tiden datan hämtas ut, vilket inte alltid syns. Det går heller inte att jämföra skillnaderna genom att ta hashsummor på filerna som görs vid forensiska undersökningar av datorer. Därför är det viktigt att dokumentera hur informationen har tagits ut, helst genom att filma datorskärmen under tiden informationen tas ut. Informationen finns sparad på flera platser då molntjänsterna Office 365 och Google Apps används, både i molnet och på den eller de datorer som har använts för att ansluta till molntjänsten. Webbläsare sparar mycket information om vad som har gjorts. Därför är det viktigt att det går att ta reda på vilka datorer som har använts för att ansluta sig till molntjänsten, vilket idag inte möjligt. Om det är möjligt att undersöka de datorer som använts kan bevis som inte finns kvar i molnet hittas. Det bästa ur forensisk synvinkel skulle vara om leverantörerna av molntjänster erbjöd en tjänst som hämtar ut all data som rör en användare, inklusive alla relevanta loggar. Då skulle det ske på ett mycket säkrare sätt, då det inte skulle gå att ändra informationen under tiden den hämtas ut. 

Tillit och misstro till molntjänster : Identifiering av vilka kriterier som skapar tillit till molntjänster

Cloud computing innebär att datorkraft och IT-resurser i form av servrar, lagring och lokala nätverk görs tillgängliga via internet, cloud computing har ökat snabbt i användning de senaste åren. Möjligheterna med molntjänster har lett till nya utmaningar avseende tillit till molntjänster genom att öppna för helt nya förhållanden mellan leverantör och kund. I dagsläget så är tillit till molntjänsterna ett stort problem för kunder såsom mikroföretag samt små och medelstora företag. Vårt examensarbete syftar till att beskriva mikroföretags samt små och medelstora företags tillit och misstro till molntjänster, samt identifiera vilka kriterier som bidrar till detta. Resultatet visar att det är svårt att tydligt definiera tillit och misstro hos företag, då deras situationer och verksamheter skiljer sig. Tack vare vår litteraturstudie i kombination med våra intervjuer har vi skapat oss en bra bild av vilka kriterier som bidrar med tillit och misstro till molntjänster. Baserat på vårt arbete har vi sammanställt en konceptuell modell som beskriver tillit och misstro till molntjänster.

Aplicação do método de análise hierárquica na tomada de decisão para adoção de computação em nuvem: um estudo de caso na federação das indústrias do RN

The progresses of the Internet and telecommunications have been changing the concepts of Information Technology IT, especially with regard to outsourcing services, where organizations seek cost-cutting and a better focus on the business. Along with the development of that outsourcing, a new model named Cloud Computing (CC) evolved. It proposes to migrate to the Internet both data processing and information storing. Among the key points of Cloud Computing are included cost-cutting, benefits, risks and the IT paradigms changes. Nonetheless, the adoption of that model brings forth some difficulties to decision-making, by IT managers, mainly with regard to which solutions may go to the cloud, and which service providers are more appropriate to the Organization s reality. The research has as its overall aim to apply the AHP Method (Analytic Hierarchic Process) to decision-making in Cloud Computing. There to, the utilized methodology was the exploratory kind and a study of case applied to a nationwide organization (Federation of Industries of RN). The data collection was performed through two structured questionnaires answered electronically by IT technicians, and the company s Board of Directors. The analysis of the data was carried out in a qualitative and comparative way, and we utilized the software to AHP method called Web-Hipre. The results we obtained found the importance of applying the AHP method in decision-making towards the adoption of Cloud Computing, mainly because on the occasion the research was carried out the studied company already showed interest and necessity in adopting CC, considering the internal problems with infrastructure and availability of information that the company faces nowadays. The organization sought to adopt CC, however, it had doubt regarding the cloud model and which service provider would better meet their real necessities. The application of the AHP, then, worked as a guiding tool to the choice of the best alternative, which points out the Hybrid Cloud as the ideal choice to start off in Cloud Computing. Considering the following aspects: the layer of Infrastructure as a Service IaaS (Processing and Storage) must stay partly on the Public Cloud and partly in the Private Cloud; the layer of Platform as a Service PaaS (Software Developing and Testing) had preference for the Private Cloud, and the layer of Software as a Service - SaaS (Emails/Applications) divided into emails to the Public Cloud and applications to the Private Cloud. The research also identified the important factors to hiring a Cloud Computing provider