Search

Dynamic provisioning of computational resources in cloud platforms is a challenging problem. In this scenario, multiagent system technology may offer noticeable improvements, with intelligent agents to dynamically choose the best computational load distribution reducing execution time and cloud services cost. Thus, this article presents MAS-Cloud, a multiagent system to dynamically monitor, predict and provide computational resources in cloud platforms. Deductive reasoning agents work cooperatively in a three layer architecture to provide transparent horizontal elasticity of virtual machines in public cloud platforms (i.e., Google, Amazon EC2). MAS-Cloud was evaluated with a nondeterministic and CPU intensive application providing a challenging validation case. A multiple linear regression model was used presenting good predictions with reduced mean absolute percent error achieving 3 . 59 % CPU usage and 5 . 28 % of execution time in the Google platform, and 3 . 97 % CPU usage and 5 . 47 % of execution time in the Amazon EC2 platform.

There has been an increasing interest in running High Performance Computing (HPC) applications in the cloud, mainly due to rapid resource provisioning and significant reduction of operational costs. Biological sequence comparison is an important HPC application that compares sequences in search of similarities. MASA-OpenMP is a highly optimized sequence comparison tool that obtains optimal results. Yet, it can take a long time, depending on the number of sequences compared and their lengths. The Covid-19 pandemic study is of particular interest nowadays, and the comparison of SARS-CoV-2 sequences is crucial to understanding this disease. In this paper, we compare SARS-CoV-2 sequences with MASA-OpenMP in the Amazon Elastic Compute Cloud (Amazon EC2), using both spot and on-demand instances. To efficiently execute a MASA-OpenMP application composed of more than 22,000 tasks on EC2 respecting a given deadline, we propose an execution modeling for MASA-OpenMP on top of the Burst-HADS framework. Burst-HADS is a spot instance-based dynamic scheduler for Bag-of-Tasks applications in the cloud, which minimizes both execution time and financial costs regarding a given deadline even in the presence of spot interruptions. Performance results reveal that, by using spots, our Burst-HADS strategy considerably reduces the monetary cost for executing 22,600 SARS-CoV-2 sequence comparisons with MASA-OpenMP when contrasted to the on-demand only approach. We also show that our strategy can meet the deadlines, even in scenarios with several spot interruptions.

Currently, several hundreds of Terabytes of COVID-19 single-cell RNA-seq (scRNA-seq) data are available in public repositories. This data refers to multiple tissues, comorbidities, and conditions. We expect this trend to continue, and it is realistic to predict amounts of COVID-19 scRNA-seq data increasing to several Petabytes in the coming years. However, thoughtful analysis of this data requires large-scale computing infrastructures, and software systems optimized for such platforms to generate biological knowledge. This paper presents CellHeap, a portable and robust workflow for scRNA-seq customizable analyses, with quality control throughout the execution steps and deployable on supercomputers. Furthermore, we present the deployment of CellHeap in the Santos Dumont supercomputer for analyzing COVID-19 scRNA-seq datasets, and discuss a case study that processed dozens of Terabytes of COVID-19 scRNA-seq raw data.

Cloud computing has evolved to provide computing resources on-demand through a virtualized infrastructure, letting applications, computing power, data storage, and network resources to be provisioned and managed over private networks or over the Internet. Cloud services normally run on large data centers and demand a huge amount of electricity. Consequently, the electricity cost represents one of the major concerns of data centers, because it is sometimes nonlinear with the capacity of the data centers, and it is also associated with a high amount of carbon emissioni¾?CO2. However, energy-saving schemes that result in too much degradation of the system performance or in violations of service-level agreement SLA parameters would eventually cause the users to move to another cloud provider. Thus, there is a need to reach a balance between energy savings and the costs incurred by these savings in the execution of the applications. Therefore, in this paper, we propose and evaluate a power and SLA-aware application consolidation solution for cloud federations. It comprises a multi-agent system for server consolidation, taking into account SLA, power consumption, and carbon footprint. Different for similar solutions available in the literature, in our solution, when a cloud is overloaded, its data center needs to negotiate with other data centers before migrating the workload to another cloud. Simulation results show that our approach can reduce up to 46% of the power consumption while trying to meet performance requirements. Furthermore, we show that federated clouds can provide an adequate solution to deal with power consumption in the clouds. Copyright © 2016 John Wiley & Sons, Ltd.

Many parallel and distributed strategies were created to reduce the execution time of bioinformatics algorithms. One well-known bioinformatics algorithm is the Smith–Waterman, that may be parallelized using the wavefront method. When the wavefront is distributed across many heterogeneous nodes, it must be balanced to create a synchronous data flow. This is a very challenging problem if the nodes have variable computational power. This paper presents an agent-based solution for parallel biological sequence comparison applications that use the multi-node wavefront method. In our approach, autonomous agents are able to identify unbalanced computations and dynamically rebalance the load among the nodes. Two strategies were developed to the balancer agent in order to identify if the computations are balanced, one using global information and other using only local information. The global strategy demands a huge amount of data transfers, incurring in more communication, whereas the local strategy can decide about the balancing status using only local information. The results show that the balancing gains of strategies are very close. Thus, the local strategy is preferred, since it can be implemented in real wavefront balancers with almost the same benefits as the global strategy.

Motivation: Structured RNAs can be hard to search for as they often are not well conserved in their primary structure and are local in their genomic or transcriptomic context. Thus, the need for tools which in particular can make local structural alignments of RNAs is only increasing. Results: To meet the demand for both large-scale screens and hands on analysis through web servers, we present a new multithreaded version of Foldalign. We substantially improve execution time while maintaining all previous functionalities, including carrying out local structural alignments of sequences with low similarity. Furthermore, the improvements allow for comparing longer RNAs and increasing the sequence length. For example, lengths in the range 2000–6000 nucleotides improve execution up to a factor of five. Availability and implementation: The Foldalign software and the web server are available at http://rth.dk/resources/foldalign Contact: gorodkin@rth.dk Supplementary information: Supplementary data are available at Bioinformatics online.

International audience; Configuring and executing application across multiple clouds is a challenging task due to the various terminologies used by cloud providers to describe their services and features. Likewise, the services are regularly offered at different levels of abstraction, such as infrastructure-as-a-service (IaaS) and platform-as-a-service (PaaS). While IaaS services provide low-level access to the infrastructure, PaaS services enable the users to delegate the management of the computing environment to the cloud providers. Consequently, at the IaaS level, the users are responsible for managing the computing resources, whereas, at the PaaS level, the users must develop native cloud applications following the constraints defined by the PaaS provider. These two options exist, mostly because the clouds target web applications, whereas users' applications are commonly batch-oriented. Considering how difficult is the task of configuring and executing applications across various clouds, we advocate the use of autonomic systems to do this work automatically. For this purpose, in this paper, we propose and evaluate an autonomic and goal-oriented system. Our system implements self-configuration, self-healing, and context-awareness properties. In addition, it relies on a hierarchical P2P overlay (a) to manage the virtual machines running on the clouds and (b) to deal with inter-cloud communication. Likewise, it depends on a software product line engineering (SPLE) method to enable applications' deployment and reconfiguration at runtime, without requiring pre-configured virtual machine images. Experimental results show that our system frees the users from the duty of configuring and managing the execution of a non-native application on single clouds and over many clouds. In particular, our system tackles the lack of middleware prototypes that can support different scenarios when using simultaneous services from multiple clouds.

In this paper, we propose and evaluate a flexible architecture for desktop grids that supports multiple task allocation policies on top of a structured P2P overlay. In our proposal, a Bag-of-Tasks application is submitted to random nodes and placed in their local queue, that is processed in a FIFO way. When a node becomes idle, a task allocation policy is executed that fetches tasks from remote nodes. The proposed architecture is flexible since it is decoupled from both the P2P middleware and the P2P overlay. A prototype of the proposed architecture was implemented on top of the JXTA middleware, using the Chord P2P search overlay. The results obtained in a 16-machine heterogeneous desktop grid show that very good performance gains are obtained with multiple task allocation policies. Also, a speedup of 9.85 was achieved for an application composed of 270 network flow balancing tasks, reducing its wallclock execution time from 32.51 min to 3.3 min.

In the last decade, we have observed an unprecedented development in molecular biology. An extremely high number of organisms have been sequenced in genome projects and included in genomic databases, for further analysis. These databases present an exponential growth rate and they are intensively accessed daily, all over the world. Once a sequence is obtained, its function and/or structure must be determined. Direct experimentation is considered to be the most reliable method to do that. However, the experiments that must be conducted are very complex and time consuming. For this reason, it is far more productive to use computational methods to infer biological information from a sequence. This is usually done by comparing the new sequence with sequences that already had their characteristics determined. BLAST is the most widely used heuristic tool for sequence comparison. Thousands of BLAST searches are made daily, all over the world. In order to further reduce the BLAST execution time, cluster and grid environments can be effectively used. This paper proposes and evaluates an adaptive task allocation framework to perform BLAST searches in a grid environment. The framework, called PackageBLAST, provides an infrastructure that executes distributed BLAST genomic database comparisons. In addition, it is flexible since the user can choose or incorporate new task allocation strategies. Furthermore, we propose a mechanism to compute grid nodes' execution weight, adapting the chosen allocation policy to the observed computational power and local load of the nodes. Our results present very good speedups. For instance, in a 16-machine heterogeneous grid testbed, a speedup of 14.59 was achieved, reducing the BLAST execution time from 30.88 min to 2.11 min. Also, we show that the adaptive task allocation strategy was able to handle successfully the complexity of a grid environment.

This paper presents a new solution for Air Traffic Flow Management (ATFM) problem. The main objective of our research is to improve computational efficiency for ATFM by combing grid computing with multi-agent coordination techniques. To balance the communication among Multi-Agents in ATFM for grid computing environments, ATFM in Grid Computing (ATFMGC) is proposed for such synchronization problem. To demonstrate the developed model, the function of the agents, their knowledge representation and inference processes are discussed and the grid architecture in which the agents execute is described. Also, as a criterion to measure the effectiveness to reduce the amount of communication among agents and the delay of the flights, a metric called Standard of Balancing among Agents (SBA) is used as a basic index. The simulation results show the efficiency of the developed model and its successful application in a case study.

International audience; IaaS providers often allow the users to specify many re-quirements for their applications. However, users without advanced technical knowledge usually do not provide a good specification of the cloud environment, leading to low per-formance and/or high monetary cost. In this context, the users face the challenges of how to scale cloud-unaware ap-plications without re-engineering them. Therefore, in this paper, we propose and evaluate a cloud architecture, namely Excalibur, to execute applications in the cloud. In our ar-chitecture, the users provide the applications and the archi-tecture sets up the whole environment and adjusts it at run-time accordingly. We executed a genomics workflow in our architecture, which was deployed in Amazon EC2. The ex-periments show that the proposed architecture dynamically scales this cloud-unaware application up to 10 instances, re-ducing the execution time by 73% and the cost by 84% when compared to the execution in the configuration specified by the user.

In this paper, we propose and evaluate a framework for fault tolerant workflow execution in Grid environments. Different from previous work in the literature, our system dynamically chooses an appropriate fault tolerance technique while using a user-defined rule-based system. We also provide a generic interface that can be used to add fault tolerance techniques to the framework. The results obtained with real workflows in an experimental Grid environment show that the overhead introduced by our framework in a failure-free execution is, in the worst evaluated case, approximately 10 %. Moreover, we show that, using our framework, workflows are able to execute successfully in the presence of failures and that the framework can dynamically choose an appropriate fault tolerance technique. The main contributions of our work are twofold: the developed framework and the model-based dependability analysis we performed on it. The purpose in carrying out a model-based dependability analysis consists on evaluating the interaction between our framework and the distributed Grid environment beyond the physical limitations of an empirical evaluation. By doing this, we provide means to plan the assurance of QoS in the Grid resource allocation, while applying the fault-tolerance mechanisms we implement in our framework regardless of the underlying middleware.

This paper proposes and evaluates a strategy to run Biological Sequence Comparison applications on hybrid platforms composed of GPUs and multicores with SIMD extensions. Our strategy provides multiple task allocation policies and the user can choose the one which is more appropriate to his/her problem. We also propose a workload adjustment mechanism that tackles situations that arise when slow nodes receive the last tasks. The results obtained comparing query sequences to 5 public genomic databases in a platform composed of 4 GPUs and 2 multicores show that we are able to reduce the execution time with hybrid platforms, when compared to the GPU-only solution. We also show that our workload adjustment technique can provide significant performance gains in our target platforms.

In this paper, we propose and evaluate a server consolidation approach for efficient power management in virtualized federated Data Centers. The main goal of our approach is to reduce power consumption, trying to meet QoS requirements with limited energy defined by a third party agent. In our model, we address application workload considering the costs due to turning servers on/off and Virtual Machine migrations in same Data Center and between different Data Centers. Our simulation results with 2 data centers and 400 simultaneous Virtual Machines show that our approach is able to reduce more than 50% of energy consumption, while still meeting the QoS requirements.

Smith-Waterman (SW) is a popular application in Bioinformatics which calculates the best score/alignment between two genomic sequences. Even though SW provides the best result, it is not widely used in genome projects due to huge requirements in computing power and memory space. Recently, Cloud Computing has been receiving a lot of attention since it is able to provide utility computing in an elastic environment. The advantages of Cloud Computing can be obtained at zero cost since many of the Public Clouds provide free usage slots, allowing users to run their applications for free in Cloud environments. Also, many Clouds can be put together and seen as a unique environment, creating Federated Clouds. In this paper, we propose and evaluate an approach to implement the SW algorithm in Federated Clouds. A hierarchical Multi-Cloud architecture is proposed which is able to transparently connect and manage several Clouds. The results obtained with our architecture and our MapReduce SW implementation in five Public Clouds show that, only by using the free quota, we were able to run the SW application over a huge genomic database in time that is comparable with the one obtained in multicore clusters, showing the appropriateness of our approach.

Broadcasting is a fundamental task, being used for neighboring discovery in various medium access control and routing protocols. This paper presents a comparative analysis of various broadcast techniques and topology control mechanisms. Overall, nine topology control mechanisms and seven broadcast protocols are combined, generating sixty-three possible solutions. Among the broadcast algorithms studied, two are proposed in this paper: the Record Route Elimination (RRE) and Record Route Elimination with Distance Prediction (RRE-DP). The simulation results show that the RRE and RRE-DP allow for a significant reduction in energy consumption, regardless of the topology control mechanism associated.

Sina Weibo is currently the microblogging web service with the highest number of registered users in China. As in any large social network, the relationship representation is so huge that executing queries over the network is a very challenging problem. The WISE 2012 conference proposed a challenge based on Sina Weibo with two tracks: performance testing and repost prediction. This paper focuses on the first track challenge, which goal is to implement 19 queries with the highest throughput and the lowest latency, using a scalable parallel paradigm. In the input database, there are 265 millions of relations among more than 60 millions of users and more than 400 millions sent messages. This paper formalizes the logical model of the relationship in order to present the queries in precise and simple manner. Some optimization techniques were also proposed, such as the aggregate-rank-delete procedures, which can be applied to some of the queries for improving the performance. The proposed model and optimizations were implemented in a very scalable parallel system and the experimental results show that our solution can obtain high throughput and low latency for most of the queries.

In this paper, we propose and evaluate a framework for fault tolerant work?ow execution in grid environments that dynamically chooses an appropriate fault tolerance technique with a user-defined rule-based system. In this first version, binary trees are used. We also provide a generic interface that can be used to add fault tolerance techniques to the framework. A prototype of our framework was implemented in Java using Integrade as the grid middleware. By now, the fault tolerance techniques Retry and Replication are implemented. The results obtained with 3 real work?ows in an experimental grid environment show that the overhead introduced by our framework in a failure-free execution is small. Moreover, we show that, using our framework, work?ows are able to execute successfully in the presence of failures and that the framework can dynamically choose an appropriate fault tolerance technique.

In this paper, we propose and evaluate GrAMoS, a low-overhead WS-Agreement monitoring service that runs on Globus 4 and is integrated to JSS. To monitor resources and detect agreement violations, GrAMoS uses the stratified random sampling technique and proposes flexible agreement violation actions. The experimental results collected with a prototype of GrAMoS which monitored CPU reservation WS-Agreements show that the overhead incurred is lower than 2.8%, for grid tasks that take longer than 55s.

This paper presents the design and evaluation of a task allocation framework for Biological Sequence Comparison applications that use dynamic programming and run in heterogeneous environments. The framework is composed by four modules and either task allocation policies or applications can be integrated to it. The results obtained with four different task allocation policies in a 10-machine heterogeneous environment show that, for some sequence sizes, we were able to reduce the execution time of the parallel application in 54.2%, with the appropriate allocation policy.

Distributed shared memory (DSM) creates an abstraction of a physical shared memory that parallel programmers can access. Most recent software DSM systems provide relaxed-memory models that guarantee consistency only at synchronization operations, such as locks and barriers. As the main goal of DSM systems is to provide support for long-term computation-intensive applications, checkpointing and recovery mechanisms are highly desirable. This article presents and evaluates the integration of a coordinated checkpointing mechanism to the barrier primitive that is usually provided with many DSM systems. Our results on some popular benchmarks and a real parallel application show that the overhead introduced during the failure-free execution is often small.

In this paper, we propose an adaptive task allocation framework to perform BLAST searches in a grid environment against sequence database segments. The framework, called PackageBLAST, provides an infrastructure to choose or incorporate task allocation strategies. Furthermore, we propose a mechanism to compute grid nodes execution weight, adapting the chosen allocation policy to the current computational power of the nodes. Our results present very good speedups and also show that no single allocation strategy is able to achieve the lowest execution times for all scenarios.

In this paper we discuss concepts of an environment, which is being developed, to help programmers to implement parallel applications under the message-passing or distributed-shared memory (DSM) paradigms. The main goal of this environment, called Easy-Par, is to provide some parameters of the distributed environment to application programmers. These parameters can help programmers to decide whether an application should consider the exchange of messages between processes or should access a central pool of shared variables. An early knowledge of the number of available workstations, the homogeneity or heterogeneity of the workstations’ architcture, the load of processors, the memory utilisation, the network workload are some examples that illustrate the desirable information which can enhance the performance of parallel applications. As a result, the Easy-Par environment targets to improve the execution of an parallel application, using when appropriate the message-passing or distributed shared-memory approach, on a network of workstations.

In this article, we address two important issues in DSM research: improving performance and providing reliability. To improve performance, we designed a low-overhead multiple coherence protocol mechanism and to augment the reliability of the system, we propose a coordinated checkpointing/recovery mechanism. Both mechanisms were implemented and incorporated in JIAJIA, a DSM system that implements scope consistency with a write-invalidate protocol. Our results on an eight machine cluster with some popular benchmarks show, for the multiple coherence protocol strategy, a significant reduction on the number of messages exchanged, leading to better performance results. Also, our results for the checkpointing strategy show that the overhead introduced in failure-free executions is small when considering the benefits obtained.

A method to balance the communication among Multi-Agents in real time traffic synchronization is proposed in this research. The paper presents Air Traffic Flow Management (ATFM) problem and its synchronization property. For such a complex problem, combing grid computing with multi-agent coordination techniques to improve ATFM computational efficiency is the main objective of actual research. To demonstrate the developed model – ATFM in Grid Computing (ATFMGC), the grid architecture, the basic components and the relationship among them are described. At the same time, the function of agents (tactical planning agent etc.), their knowledge representation and inference processes are also discussed. As criteria to measure the effective to reduce quantity of the communication among agents and the delay of the flights, Standard of Balancing among Agents (SBA) is used in the analysis. The simulation shows the efficiency of the developed model and successful application in the case study.

Distributed Shared Memory systems allow the use of the shared memory programming paradigm in distributed architectures where no physically shared memory exist. Scope consistent software DSMs provide a relaxed memory model that reduces the coherence overhead by ensuring consistency only at synchronization operations, on a per-lock basis. Much of the work in DSM systems is validated by benchmarks and there are only a few examples of real parallel applications running on DSM systems. Sequence comparison is a basic operation in DNA sequencing projects, and most of sequence comparison methods used are based on heuristics, that are faster but do not produce optimal alignments. Recently, many organisms had their DNA entirely sequenced, and this reality presents the need for comparing long DNA sequences, which is a challenging task due to its high demands for computational power and memory. In this article, we present and evaluate a parallelization strategy for implementing a sequence alignment algorithm for long sequences. This strategy was implemented in JIAJIA, a scope consistent software DSM system. Our results on an eight-machine cluster presented good speedups, showing that our parallelization strategy and programming support were appropriate.

Distributed Shared Memory systems allow the use of the shared memory programming paradigm in distributed architectures where no physically shared memory exist. Scope consistent software DSMs provide a relaxed memory model that reduces the coherence overhead by ensuring consistency only at synchronisation operations, on a per-lock basis. Much of the work in DSM systems is validated by benchmarks and there are only a few examples of real parallel applications running on DSM systems. Sequence comparison is a basic operation in DNA sequencing projects, and most of sequence comparison methods used are based on heuristics, that are faster but do not produce optimal alignments. Recently, many organisms had their DNA entirely sequenced, and this reality presents the need for comparing long DNA sequences, which is a challenging task due to its high demands for computational power and memory. In this article, we present and evaluate a parallelisation strategy for implementing a sequence alignment algorithm for long sequences. This strategy was implemented in JIAJIA, a scope consistent software DSM system. Our results on an eight-machine cluster presented good speedups, showing that our parallelisation strategy and programming support were appropriate.

Distributed shared memory systems allow the use of the shared memory programming paradigm in distributed architectures where no physically shared memory exist. To reduce coherence overhead, relaxed memory consistency models were proposed. Scope consistent software DSMs provide a relaxed memory model that guarantees consistency only at synchronization operations, on a per-lock basis. Much of the work in DSM systems is validated by benchmarks and there are only a few examples of real parallel applications running on DSM systems. Binary space partition trees are widely used in computer graphics and pattern recognition to accelerate hidden surface removal. Depending on the size of the scene, the computational cost of generating BSP trees can be very high. We propose and evaluate a parallel algorithm that distributes the task of calculating BSP sub-trees among several nodes. This algorithm was implemented in JIAJIA, a scope consistent software DSM system. Our results on an eight-machine cluster presented very good speedups, showing that our parallelization strategy and programming support were appropriate.

Distributed Shared Memory systems allow the use of the shared memory programming paradigm in distributed architectures where no physically shared memory exist. Scope consistent software DSMs provide a relaxed memory model that reduces the coherence overhead by ensuring consistency only at synchronisation operations, on a per-lock basis. Sequence comparison is a basic operation in DNA sequencing projects, and most of sequence comparison methods used are based on heuristics, that are faster but do not produce optimal alignments. Recently, many organisms had their DNA entirely sequenced, and this reality presents the need for comparing long DNA sequences, which is a challenging task due to its high demands for computational power and memory. In this article, we present and evaluate a parallelisation strategy for implementing a sequence alignment algorithm for long sequences in a DSM system. Our results on an eight-machine cluster presented good speedups, showing that our parallelisation strategy and programming support were appropriate.

In dynamic object groups, objects are allowed to join or leave the group at any time during the group lifetime. Each time the number of members in a group changes, a new view is created. Virtual synchrony is an useful property in dynamic groups which guarantees that if two processes stay in the same view after a view change, the same set of messages will be delivered to them. Most of the protocols that implement virtual synchrony stop regular message activity while a view change is under way. Optimistic virtual synchrony (OVS) allows messages to be sent and received while a view is changing by estimating which members would be present in the next view. If the estimation is wrong, messages are "rolled back". In this paper, we propose and evaluate an approach to integrate OVS to a CORBA group service called OGS. Our results show that OVS provides very good performance improvements during view changes when compared with other protocols that guarantee virtual synchrony.

Tese (doutorado)—Universidade de Brasília, Instituto de Ciências Exatas, Departamento de Ciência da Computação, 2014. A computação em nuvem tem sido considerada como uma opção para executar aplicações de alto desempenho. Entretanto, enquanto as plataformas de alto desempenho tradicionais como grid e supercomputadores oferecem um ambiente estável quanto à falha, desempenho e número de recursos, a computação em nuvem oferece recursos sob demanda, geralmente com desempenho imprevisível à baixo custo financeiro. Além disso, em ambiente de nuvem, as falhas fazem parte da sua normal operação. No entanto, as nuvens podem ser combinadas, criando uma federação, para superar os limites de uma nuvem muitas vezes com um baixo custo para os usuários. A federação de nuvens pode ajudar tanto os provedores quanto os usuários das nuvens a atingirem diferentes objetivos tais como: reduzir o tempo de execução de uma aplicação, reduzir o custo financeiro, aumentar a disponibilidade do ambiente, reduzir o consumo de energia, entre outros. Por isso, a federação de nuvens pode ser uma solução elegante para evitar o sub-provisionamento de recursos ajudando os provedores a reduzirem os custos operacionais e a reduzir o número de recursos ativos, que outrora ficariam ociosos consumindo energia, por exemplo. No entanto, a federação de nuvens aumenta as opções de recursos disponíveis para os usuários, requerendo, em muito dos casos, conhecimento em administração de sistemas ou em computação em nuvem, bem como um tempo considerável para aprender sobre as opções disponíveis. Neste contexto, surgem algumas questões, tais como: (a) qual dentre os recursos disponíveis é apropriado para uma determinada aplicação? (b) como os usuários podem executar suas aplicações na nuvem e obter um desempenho e um custo financeiro aceitável, sem ter que modificá-las para atender as restrições do ambiente de nuvem? (c) como os usuários não especialistas em nuvem podem maximizar o uso da nuvem, sem ficar dependente de um provedor? (d) como os provedores podem utilizar a federação para reduzir o consumo de energia dos datacenters e ao mesmo tempo atender os acordos de níveis de serviços? A partir destas questões, este trabalho apresenta uma solução para consolidação de aplicações em nuvem federalizadas considerando os acordos de serviços. Nossa solução utiliza um sistema multi-agente para negociar a migração das máquinas virtuais entres as nuvens. Simulações mostram que nossa abordagem pode reduzir em até 46% o consumo de energia e atender os requisitos de qualidade. Nós também desenvolvemos e avaliamos uma solução para executar uma aplicação de bioinformática em nuvens federalizadas, a custo zero. Nesse caso, utilizando a federação, conseguimos diminuir o tempo de execução da aplicação em 22,55%, considerando o seu tempo de execução na melhor nuvem. Além disso, este trabalho apresenta uma arquitetura chamada Excalibur, que possibilita escalar a execução de aplicações comuns em nuvem. Excalibur conseguiu escalar automaticamente a execução de um conjunto de aplicações de bioinformática em até 11 máquinas virtuais, reduzindo o tempo de execução em 63% e o custo financeiro em 84% quando comparado com uma configuração definida pelos usuários. Por fim, este trabalho apresenta um método baseado em linha de produto de software para lidar com as variabilidades dos serviços oferecidos por nuvens de infraestrutura (IaaS), e um sistema que utiliza deste processo para configurar o ambiente e para lidar com falhas de forma automática. O nosso método utiliza modelo de feature estendido com atributos para descrever os recursos e para selecioná-los com base nos objetivos dos usuários. Experimentos realizados com dois provedores diferentes mostraram que utilizando o nosso processo, os usuários podem executar as suas aplicações em um ambiente de nuvem federalizada, sem conhecer as variabilidades e limitações das nuvens. Cloud computing has been seen as an option to execute high performance computing (HPC) applications. While traditional HPC platforms such as grid and supercomputers offer a stable environment in terms of failures, performance, and number of resources, cloud computing offers on-demand resources generally with unpredictable performance at low financial cost. Furthermore, in cloud environment, failures are part of its normal operation. To overcome the limits of a single cloud, clouds can be combined, forming a cloud federation often with minimal additional costs for the users. A cloud federation can help both cloud providers and cloud users to achieve their goals such as to reduce the execution time, to achieve minimum cost, to increase availability, to reduce power consumption, among others. Hence, cloud federation can be an elegant solution to avoid over provisioning, thus reducing the operational costs in an average load situation, and removing resources that would otherwise remain idle and wasting power consumption, for instance. However, cloud federation increases the range of resources available for the users. As a result, cloud or system administration skills may be demanded from the users, as well as a considerable time to learn about the available options. In this context, some questions arise such as: (a) which cloud resource is appropriate for a given application? (b) how can the users execute their HPC applications with acceptable performance and financial costs, without needing to re-engineer the applications to fit clouds’ constraints? (c) how can non-cloud specialists maximize the features of the clouds, without being tied to a cloud provider? and (d) how can the cloud providers use the federation to reduce power consumption of the clouds, while still being able to give service-level agreement (SLA) guarantees to the users? Motivated by these questions, this thesis presents a SLA-aware application consolidation solution for cloud federation. Using a multi-agent system (MAS) to negotiate virtual machine (VM) migrations between the clouds, simulation results show that our approach could reduce up to 46% of the power consumption, while trying to meet performance requirements. Using the federation, we developed and evaluated an approach to execute a huge bioinformatics application at zero-cost. Moreover, we could decrease the execution time in 22.55% over the best single cloud execution. In addition, this thesis presents a cloud architecture called Excalibur to auto-scale cloud-unaware application. Executing a genomics workflow, Excalibur could seamlessly scale the applications up to 11 virtual machines, reducing the execution time by 63% and the cost by 84% when compared to a user’s configuration. Finally, this thesis presents a software product line engineering (SPLE) method to handle the commonality and variability of infrastructure-as-a-service (IaaS) clouds, and an autonomic multi-cloud architecture that uses this method to configure and to deal with failures autonomously. The SPLE method uses extended feature model (EFM) with attributes to describe the resources and to select them based on the users’ objectives. Experiments realized with two different cloud providers show that using the proposed method, the users could execute their application on a federated cloud environment, without needing to know the variability and constraints of the clouds. Le cloud computing a été considéré comme une option pour exécuter des applications de calcul haute performance (HPC). Bien que les plateformes traditionnelles de calcul haute performance telles que les grilles et les supercalculateurs offrent un environnement stable du point de vue des défaillances, des performances, et de la taille des ressources, le cloud computing offre des ressources à la demande, généralement avec des performances imprévisibles mais à des coûts financiers abordables. En outre, dans un environnement de cloud, les défaillances sont perçues comme étant ordinaires. Pour surmonter les limites d’un cloud individuel, plusieurs clouds peuvent être combinés pour former une fédération de clouds, souvent avec des coûts supplémentaires légers pour les utilisateurs. Une fédération de clouds peut aider autant les fournisseurs que les utilisateurs à atteindre leurs objectifs tels la réduction du temps d’exécution, la minimisation des coûts, l’augmentation de la disponibilité, la réduction de la consummation d’énergie, pour ne citer que ceux-là. Ainsi, la fédération de clouds peut être une solution élégante pour éviter le sur-approvisionnement, réduisant ainsi les coûts d’exploitation en situation de charge moyenne, et en supprimant des ressources qui, autrement, resteraient inutilisées et gaspilleraient ainsi de énergie. Cependant, la fédération de clouds élargit la gamme des ressources disponibles. En conséquence, pour les utilisateurs, des compétences en cloud computing ou en administration système sont nécessaires, ainsi qu’un temps d’apprentissage considérable pour maîtrises les options disponibles. Dans ce contexte, certaines questions se posent : (a) Quelle ressource du cloud est appropriée pour une application donnée ? (b) Comment les utilisateurs peuvent-ils exécuter leurs applications HPC avec un rendement acceptable et des coûts financiers abordables, sans avoir à reconfigurer les applications pour répondre aux norms et contraintes du cloud ? (c) Comment les non-spécialistes du cloud peuvent-ils maximiser l’usage des caractéristiques du cloud, sans être liés au fournisseur du cloud ? et (d) Comment les fournisseurs de cloud peuvent-ils exploiter la fédération pour réduire la consommation électrique, tout en étant en mesure de fournir un service garantissant les normes de qualité préétablies ? À partir de ces questions, la presente thèse propose une solution de consolidation d’applications pour la fédération de clouds qui garantit le respect des normes de qualité de service. On utilise un système multi-agents (SMA) pour négocier la migration des machines virtuelles entre les clouds. Les résultats de simulations montrent que notre approche pourrait réduire jusqu’à 46% la consommation totale d’énergie, tout en respectant les exigencies de performance. En nous basant sur la fédération de clouds, nous avons développé et évalué une approche pour exécuter une énorme application de bioinformatique à coût zéro. En outre, nous avons pu réduire le temps d’exécution de 22,55% par rapport à la meilleure exécution dans un cloud individuel. Cette thèse présente aussi une architecture de cloud baptisée « Excalibur » qui permet l’adaptation automatique des applications standards pour le cloud. Dans l’exécution d’une chaîne de traitements de la génomique, Excalibur a pu parfaitement mettre à l’échelle les applications sur jusqu’à 11 machines virtuelles, ce qui a réduit le temps d’exécution de 63% et le coût de 84% par rapport à la configuration de l’utilisateur. Enfin, cette thèse présente un processus d’ingénierie des lignes de produits (PLE) pour gérer la variabilité de l’infrastructure à la demande du cloud, et une architecture multi-cloud autonome qui utilise ce processus pour configurer et faire face aux défaillances de manière indépendante. Le processus PLE utilise le modele étendu de fonction (EFM) avec des attributs pour décrire les ressources et les sélectionner en fonction dês objectifs de l’utilisateur. Les expériences réalisées avec deux fournisseurs de cloud différents montrent qu’em utilisant le modèle proposé, les utilisateurs peuvent exécuter leurs applications dans un environnement de clouds fédérés, sans avoir besoin de connaître les variabilités et contraintes du cloud.