A diminuição no custo de computadores pessoais tem favorecido a construção de sistemas computacionais complexos, tais como aglomerados e grades. Devido ao grande número de recursos existentes nesses sistemas, a probabilidade de que faltas ocorram é alta. Uma abordagem que auxilia a tornar sistemas mais robustos na presença de faltas é a detecção de sua ocorrência, a fim de que processos possam ser reiniciados em estados seguros, ou paralisados em estados que não ofereçam riscos. Abordagens comumente adotadas para detecção seguem, basicamente, três tipos de estratégias: as baseadas em mensagens de controle, em estatística e em aprendizado de máquina. No entanto, elas tipicamente não consideram o comportamento de processos ao longo do tempo. Observando essa limitação nas pesquisas relacionadas, este trabalho apresenta uma abordagem para medir a variação no comportamento de processos ao longo do tempo, a fim de que mudanças inesperadas sejam detectadas. Essas mudanças são consideradas, no contexto deste trabalho, como faltas, as quais representam transições indesejadas entre estados de um processo e podem levá-lo a processamento incorreto, fora de sua especificação. A proposta baseia-se na estimação de cadeias de Markov que representam estados visitados por um processo durante sua execução. Variações nessas cadeias são utilizadas para identificar faltas. A abordagem proposta é comparada à técnica de aprendizado de máquina Support Vector Machines, bem como à técnica estatística Auto-Regressive Integrated Moving Average. Essas técnicas foram escolhidas para comparação por estarem entre as mais empregadas na literatura. Experimentos realizados mostraram que a abordagem proposta possui, com erro \'alfa\' = 1%, um F-Measure maior do que duas vezes o alcançado pelas outras técnicas. Realizou-se também um estudo adicional de predição de faltas. Nesse sentido, foi proposta uma técnica preditiva baseada na reconstrução do comportamento observado do sistema. A avaliação da técnica mostrou que ela pode aumentar em até uma ordem de magnitude a disponibilidade (em horas) de um sistema / The cost reduction for personal computers has enabled the construction of complex computational systems, such as clusters and grids. Because of the large number of resources available on those systems, the probability that faults may occur is high. An approach that helps to make systems more robust in the presence of faults is their detection, in order to restart or stop processes in safe states. Commonly adopted approaches for detection basically follow one of three strategies: the one based on control messages, on statistics or on machine learning. However, they typically do not consider the behavior of processes over time. Observing this limitation in related researches, this work presents an approach to measure the level of variation in the behavior of processes over time, so that unexpected changes are detected. These changes are considered, in the context of this work, as faults, which represent undesired transitions between process states and may cause incorrect processing, outside the specification. The approach is based on the estimation of Markov Chains that represent states visited by a process during its execution. Variations in these chains are used to identify faults. The approach is compared to the machine learning technique Support Vector Machines, as well as to the statistical technique Auto-Regressive Integrated Moving Average. These techniques have been selected for comparison because they are among the ones most employed in the literature. Experiments conducted have shown that the proposed approach has, with error \'alpha\'= 1%, an F-Measure higher than twice the one achieved by the other techniques. A complementary study has also been conducted about fault prediction. In this sense, a predictive approach based on the reconstruction of system behavior was proposed. The evaluation of the technique showed that it can provide up to an order of magnitude greater availability of a system in terms of uptime hours

Submitted by PPG Ci?ncia da Computa??o (ppgcc@pucrs.br) on 2018-10-04T18:59:57Z No. of bitstreams: 1 LUCIANO_ ALVES_DIS.pdf: 1077045 bytes, checksum: ddcbf3be03bec1c7a82f3e07252439a0 (MD5) / Rejected by Sheila Dias (sheila.dias@pucrs.br), reason: Devolvido deviso ? inconsist?ncia de datas no arquivo pdf. Na capa institucional, na ficha catalogr?fica e na folha da banca est? 2016 e na folha de rosto 2018. on 2018-10-05T16:43:09Z (GMT) / Submitted by PPG Ci?ncia da Computa??o (ppgcc@pucrs.br) on 2018-10-08T18:31:55Z No. of bitstreams: 1 LUCIANO_ ALVES_DIS.pdf: 1076874 bytes, checksum: 70823493135f9ec1a577db83eefbd19c (MD5) / Approved for entry into archive by Caroline Xavier (caroline.xavier@pucrs.br) on 2018-10-09T16:36:57Z (GMT) No. of bitstreams: 1 LUCIANO_ ALVES_DIS.pdf: 1076874 bytes, checksum: 70823493135f9ec1a577db83eefbd19c (MD5) / Made available in DSpace on 2018-10-09T16:43:56Z (GMT). No. of bitstreams: 1 LUCIANO_ ALVES_DIS.pdf: 1076874 bytes, checksum: 70823493135f9ec1a577db83eefbd19c (MD5) Previous issue date: 2016-09-23 / Software fault prediction is a significant part of software quality assurance and it is commonly used to detect faulty software modules based on software measurement data. Several machine learning based approaches have been proposed for generating predictive models from collected data, although none has become standard given the specificities of each software project. Hence, we believe that recommending the best algorithm for each project is much more important and useful than developing a single algorithm for being used in any project. For achieving that goal, we propose in this dissertation a novel framework for recommending machine learning algorithms that is capable of automatically identifying the most suitable algorithm according to the software project that is being considered. Our solution, namely FMA-PFS, makes use of the metalearning paradigm in order to learn the best learner for a particular project. Results show that the FMA-PFS framework provides both the best single algorithm recommendation and also the best ranking recommendation for the software fault prediction problem. / A predi??o de falhas de software ? uma parte significativa da garantia de qualidade do software e ? normalmente utilizada para detectar m?dulos propensos a falhar baseados em dados coletados ap?s o processo de desenvolvimento do projeto. Diversas t?cnicas de aprendizado de m?quina t?m sido propostas para gera??o de modelos preditivos a partir da coleta dos dados, por?m nenhuma se tornou a solu??o padr?o devido as especificidades de cada projeto. Por isso, a hip?tese levantada por este trabalho ? que recomendar algoritmos de aprendizado de m?quina para cada projeto ? mais importante e ?til do que o desenvolvimento de um ?nico algoritmo de aprendizado de m?quina a ser utilizado em qualquer projeto. Para alcan?ar este objetivo, prop?e-se nesta disserta??o um framework para recomendar algoritmos de aprendizado de m?quina capaz de identificar automaticamente o algoritmo mais adequado para aquele projeto espec?fico. A solu??o, chamada FMA-PFS, faz uso da t?cnica de meta-aprendizado, a fim de aprender o melhor algoritmo para um projeto em particular. Os resultados mostram que o framework FMA-PFS recomenda tanto o melhor algoritmo, quanto o melhor ranking de algoritmos no contexto de predi??o de falhas de software.

A diminuição no custo de computadores pessoais tem favorecido a construção de sistemas computacionais complexos, tais como aglomerados e grades. Devido ao grande número de recursos existentes nesses sistemas, a probabilidade de que faltas ocorram é alta. Uma abordagem que auxilia a tornar sistemas mais robustos na presença de faltas é a detecção de sua ocorrência, a fim de que processos possam ser reiniciados em estados seguros, ou paralisados em estados que não ofereçam riscos. Abordagens comumente adotadas para detecção seguem, basicamente, três tipos de estratégias: as baseadas em mensagens de controle, em estatística e em aprendizado de máquina. No entanto, elas tipicamente não consideram o comportamento de processos ao longo do tempo. Observando essa limitação nas pesquisas relacionadas, este trabalho apresenta uma abordagem para medir a variação no comportamento de processos ao longo do tempo, a fim de que mudanças inesperadas sejam detectadas. Essas mudanças são consideradas, no contexto deste trabalho, como faltas, as quais representam transições indesejadas entre estados de um processo e podem levá-lo a processamento incorreto, fora de sua especificação. A proposta baseia-se na estimação de cadeias de Markov que representam estados visitados por um processo durante sua execução. Variações nessas cadeias são utilizadas para identificar faltas. A abordagem proposta é comparada à técnica de aprendizado de máquina Support Vector Machines, bem como à técnica estatística Auto-Regressive Integrated Moving Average. Essas técnicas foram escolhidas para comparação por estarem entre as mais empregadas na literatura. Experimentos realizados mostraram que a abordagem proposta possui, com erro \'alfa\' = 1%, um F-Measure maior do que duas vezes o alcançado pelas outras técnicas. Realizou-se também um estudo adicional de predição de faltas. Nesse sentido, foi proposta uma técnica preditiva baseada na reconstrução do comportamento observado do sistema. A avaliação da técnica mostrou que ela pode aumentar em até uma ordem de magnitude a disponibilidade (em horas) de um sistema / The cost reduction for personal computers has enabled the construction of complex computational systems, such as clusters and grids. Because of the large number of resources available on those systems, the probability that faults may occur is high. An approach that helps to make systems more robust in the presence of faults is their detection, in order to restart or stop processes in safe states. Commonly adopted approaches for detection basically follow one of three strategies: the one based on control messages, on statistics or on machine learning. However, they typically do not consider the behavior of processes over time. Observing this limitation in related researches, this work presents an approach to measure the level of variation in the behavior of processes over time, so that unexpected changes are detected. These changes are considered, in the context of this work, as faults, which represent undesired transitions between process states and may cause incorrect processing, outside the specification. The approach is based on the estimation of Markov Chains that represent states visited by a process during its execution. Variations in these chains are used to identify faults. The approach is compared to the machine learning technique Support Vector Machines, as well as to the statistical technique Auto-Regressive Integrated Moving Average. These techniques have been selected for comparison because they are among the ones most employed in the literature. Experiments conducted have shown that the proposed approach has, with error \'alpha\'= 1%, an F-Measure higher than twice the one achieved by the other techniques. A complementary study has also been conducted about fault prediction. In this sense, a predictive approach based on the reconstruction of system behavior was proposed. The evaluation of the technique showed that it can provide up to an order of magnitude greater availability of a system in terms of uptime hours

This thesis explores mining the evolutionary history of a software system to support software developers and managers in their endeavors to build and maintain complex software systems. We introduce the idea of evolutionary extractors which are specialized extractors that can recover the history of software projects from software repositories, such as source control systems. The challenges faced in building C-REX, an evolutionary extractor for the C programming language, are discussed. We examine the use of source control systems in industry and the quality of the recovered C-REX data through a survey of several software practitioners. Using the data recovered by C-REX, we develop several approaches and techniques to assist developers and managers in their activities. We propose <em>Source Sticky Notes</em> to assist developers in understanding legacy software systems by attaching historical information to the dependency graph. We present the <em>Development Replay</em> approach to estimate the benefits of adopting new software maintenance tools by reenacting the development history. We propose the <em>Top Ten List</em> which assists managers in allocating testing resources to the subsystems that are most susceptible to have faults. To assist managers in improving the quality of their projects, we present a complexity metric which quantifies the complexity of the changes to the code instead of quantifying the complexity of the source code itself. All presented approaches are validated empirically using data from several large open source systems. The presented work highlights the benefits of transforming software repositories from static record keeping repositories to active repositories used by researchers to gain empirically based understanding of software development, and by software practitioners to predict, plan and understand various aspects of their project.

This thesis explores mining the evolutionary history of a software system to support software developers and managers in their endeavors to build and maintain complex software systems. We introduce the idea of evolutionary extractors which are specialized extractors that can recover the history of software projects from software repositories, such as source control systems. The challenges faced in building C-REX, an evolutionary extractor for the C programming language, are discussed. We examine the use of source control systems in industry and the quality of the recovered C-REX data through a survey of several software practitioners. Using the data recovered by C-REX, we develop several approaches and techniques to assist developers and managers in their activities. We propose <em>Source Sticky Notes</em> to assist developers in understanding legacy software systems by attaching historical information to the dependency graph. We present the <em>Development Replay</em> approach to estimate the benefits of adopting new software maintenance tools by reenacting the development history. We propose the <em>Top Ten List</em> which assists managers in allocating testing resources to the subsystems that are most susceptible to have faults. To assist managers in improving the quality of their projects, we present a complexity metric which quantifies the complexity of the changes to the code instead of quantifying the complexity of the source code itself. All presented approaches are validated empirically using data from several large open source systems. The presented work highlights the benefits of transforming software repositories from static record keeping repositories to active repositories used by researchers to gain empirically based understanding of software development, and by software practitioners to predict, plan and understand various aspects of their project.

Os motores de indução desempenham um importante papel na indústria, fato este que destaca a importância do correto diagnóstico e classificação de falhas ainda em fase inicial de sua evolução, possibilitando aumento na produtividade e, principalmente, eliminando graves danos aos processos e às máquinas. Assim, a proposta desta tese consiste em apresentar um multiclassificador inteligente para o diagnóstico de motor sem defeitos, falhas de curto-circuito nos enrolamentos do estator, falhas de rotor e falhas de rolamentos em motores de indução trifásicos acionados por diferentes modelos de inversores de frequência por meio da análise das amplitudes dos sinais de corrente de estator no domínio do tempo. Para avaliar a precisão de classificação frente aos diversos níveis de severidade das falhas, foram comparados os desempenhos de quatro técnicas distintas de aprendizado de máquina; a saber: (i) Rede Fuzzy Artmap, (ii) Rede Perceptron Multicamadas, (iii) Máquina de Vetores de Suporte e (iv) k-Vizinhos-Próximos. Resultados experimentais obtidos a partir de 13.574 ensaios experimentais são apresentados para validar o estudo considerando uma ampla faixa de frequências de operação, bem como regimes de conjugado de carga em 5 motores diferentes. / Induction motors play an important role in the industry, a fact that highlights the importance of correct diagnosis and classification of faults on these machines still in early stages of their evolution, allowing increase in productivity and mainly, eliminating major damage to the processes and machines. Thus, the purpose of this thesis is to present an intelligent multi-classifier for the diagnoses of healthy motor, short-circuit faults in the stator windings, rotor broken bars and bearing faults in induction motors operating with different models of frequency inverters by analyzing the amplitude of the stator current signal in the time domain. To assess the classification accuracy across the various levels of faults severity, the performances of four different learning machine techniques were compared; namely: (i) Fuzzy ARTMAP network, (ii) Multilayer Perceptron Network, (iii) Support Vector Machine and (iv) k-Nearest-Neighbor. Experimental results obtained from 13.574 experimental tests are presented to validate the study considering a wide range of operating frequencies and also load conditions using 5 different motors.

Os motores de indução desempenham um importante papel na indústria, fato este que destaca a importância do correto diagnóstico e classificação de falhas ainda em fase inicial de sua evolução, possibilitando aumento na produtividade e, principalmente, eliminando graves danos aos processos e às máquinas. Assim, a proposta desta tese consiste em apresentar um multiclassificador inteligente para o diagnóstico de motor sem defeitos, falhas de curto-circuito nos enrolamentos do estator, falhas de rotor e falhas de rolamentos em motores de indução trifásicos acionados por diferentes modelos de inversores de frequência por meio da análise das amplitudes dos sinais de corrente de estator no domínio do tempo. Para avaliar a precisão de classificação frente aos diversos níveis de severidade das falhas, foram comparados os desempenhos de quatro técnicas distintas de aprendizado de máquina; a saber: (i) Rede Fuzzy Artmap, (ii) Rede Perceptron Multicamadas, (iii) Máquina de Vetores de Suporte e (iv) k-Vizinhos-Próximos. Resultados experimentais obtidos a partir de 13.574 ensaios experimentais são apresentados para validar o estudo considerando uma ampla faixa de frequências de operação, bem como regimes de conjugado de carga em 5 motores diferentes. / Induction motors play an important role in the industry, a fact that highlights the importance of correct diagnosis and classification of faults on these machines still in early stages of their evolution, allowing increase in productivity and mainly, eliminating major damage to the processes and machines. Thus, the purpose of this thesis is to present an intelligent multi-classifier for the diagnoses of healthy motor, short-circuit faults in the stator windings, rotor broken bars and bearing faults in induction motors operating with different models of frequency inverters by analyzing the amplitude of the stator current signal in the time domain. To assess the classification accuracy across the various levels of faults severity, the performances of four different learning machine techniques were compared; namely: (i) Fuzzy ARTMAP network, (ii) Multilayer Perceptron Network, (iii) Support Vector Machine and (iv) k-Nearest-Neighbor. Experimental results obtained from 13.574 experimental tests are presented to validate the study considering a wide range of operating frequencies and also load conditions using 5 different motors.

Dans cette thèse, nous nous sommes intéressés aux problèmes d'ordonnancement et d'optimisation dans des contextes probabilistes. Les contributions de cette thèse se déclinent en deux parties. La première partie est dédiée à l’optimisation de différents mécanismes de tolérance aux pannes pour les machines de très large échelle qui sont sujettes à une probabilité de pannes. La seconde partie est consacrée à l’optimisation du coût d’exécution des arbres d’opérateurs booléens sur des flux de données.Dans la première partie, nous nous sommes intéressés aux problèmes de résilience pour les machines de future génération dites « exascales » (plateformes pouvant effectuer 1018 opérations par secondes).Dans le premier chapitre, nous présentons l’état de l’art des mécanismes les plus utilisés dans la tolérance aux pannes et des résultats généraux liés à la résilience.Dans le second chapitre, nous étudions un modèle d’évaluation des protocoles de sauvegarde de points de reprise (checkpoints) et de redémarrage. Le modèle proposé est suffisamment générique pour contenir les situations extrêmes: d’un côté le checkpoint coordonné, et de l’autre toute une famille de stratégies non-Coordonnées. Nous avons proposé une analyse détaillée de plusieurs scénarios, incluant certaines des plateformes de calcul existantes les plus puissantes, ainsi que des anticipations sur les futures plateformes exascales.Dans les troisième, quatrième et cinquième chapitres, nous étudions l'utilisation conjointe de différents mécanismes de tolérance aux pannes (réplication, prédiction de pannes et détection d'erreurs silencieuses) avec le mécanisme traditionnel de checkpoints et de redémarrage. Nous avons évalué plusieurs modèles au moyen de simulations. Nos résultats montrent que ces modèles sont bénéfiques pour un ensemble de modèles d'applications dans le cadre des futures plateformes exascales.Dans la seconde partie de la thèse, nous étudions le problème de la minimisation du coût de récupération des données par des applications lors du traitement d’une requête exprimée sous forme d'arbres d'opérateurs booléens appliqués à des prédicats sur des flux de données de senseurs. Le problème est de déterminer l'ordre dans lequel les prédicats doivent être évalués afin de minimiser l'espérance du coût du traitement de la requête. Dans le sixième chapitre, nous présentons l'état de l'art de la seconde partie et dans le septième chapitre, nous étudions le problème pour les requêtes exprimées sous forme normale disjonctive. Nous considérons le cas plus général où chaque flux peut apparaître dans plusieurs prédicats et nous étudions deux modèles, le modèle où chaque prédicat peut accéder à un seul flux et le modèle où chaque prédicat peut accéder à plusieurs flux. / In this thesis, we are interested in scheduling and optimization problems in probabilistic contexts. The contributions of this thesis come in two parts. The first part is dedicated to the optimization of different fault-Tolerance mechanisms for very large scale machines that are subject to a probability of failure and the second part is devoted to the optimization of the expected sensor data acquisition cost when evaluating a query expressed as a tree of disjunctive Boolean operators applied to Boolean predicates. In the first chapter, we present the related work of the first part and then we introduce some new general results that are useful for resilience on exascale systems.In the second chapter, we study a unified model for several well-Known checkpoint/restart protocols. The proposed model is generic enough to encompass both extremes of the checkpoint/restart space, from coordinated approaches to a variety of uncoordinated checkpoint strategies. We propose a detailed analysis of several scenarios, including some of the most powerful currently available HPC platforms, as well as anticipated exascale designs.In the third, fourth, and fifth chapters, we study the combination of different fault tolerant mechanisms (replication, fault prediction and detection of silent errors) with the traditional checkpoint/restart mechanism. We evaluated several models using simulations. Our results show that these models are useful for a set of models of applications in the context of future exascale systems.In the second part of the thesis, we study the problem of minimizing the expected sensor data acquisition cost when evaluating a query expressed as a tree of disjunctive Boolean operators applied to Boolean predicates. The problem is to determine the order in which predicates should be evaluated so as to shortcut part of the query evaluation and minimize the expected cost.In the sixth chapter, we present the related work of the second part and in the seventh chapter, we study the problem for queries expressed as a disjunctive normal form. We consider the more general case where each data stream can appear in multiple predicates and we consider two models, the model where each predicate can access a single stream and the model where each predicate can access multiple streams.