Real-time systems are required to answer to external stimuli within a specified time-period. For this to be possible, the systems behaviour must be predictable. The use of active databases in real-time systems introduces unpredictability in the system, e.g. due to their use of active rules. The behaviour in active databases is usually specified in ECA-rules. Sets of ECA-rules are hard to analyse, which implies that the behaviour of the ECA-rule set is hard to predict. The purpose of this project is to evaluate the ability to support the development of a predictable ECA-rule set. Using a formal method for the specification task is desirable, since a formal specification is analysable and can be proven correct. In this project, timed-automata are used for specifying the systems behaviour. A method for deriving predictable ECA-rules from a timed-automaton specification is developed, and successfully applied on a case-study specification. For this case-study specification, a set of ECA-rules preserving the analysed behaviour of the timed-automata specification is derived.

Distributed real-time databases can be used to support data sharing for applications in wireless ad-hoc networks. In such networks, topology changes frequently and partitions may be unpredictable and last for an unbounded period. In this thesis, the existing database replication protocol PRiDe is extended to handle such long-lasting partitions. The protocol uses optimistic and detached replication to provide predictable response times in unpredictable networks and forward conflict resolution to guarantee progress. The extension, pPRiDe, combines update and state transfer strategies. Update transfer for intra-partition communication can reduce bandwidth usage and ease conflict resolution. State transfer for inter partition conflicts removes dependency on a common state between partitions prior to the merge to apply update messages on. This makes the resource usage independent of the life span of partitions. This independence comes at the cost of global data stability guarantees and pPRiDe can thus only provide per partition guarantees. The protocol supports application specific conflict resolution routines for both state and update conflicts. A basic simulator for mobile ad-hoc networks has been developed to validate that pPRiDe provides eventual consistency. pPRiDe shows that a hybrid approach to change propagation strategy can be beneficial in networks where collaboration by data sharing within long lasting partitions and predictable resource usage is necessary. These types of systems already require the conflict management routines necessary for pPRiDe and can benefit from an existing protocol. In addition to pPRiDe and the simulator this thesis provides a flexible object database suitable for future works and an implementation of PRiDe on top of that database.

Admission controllers in dynamic real-time systems perform traditional schedulability tests in order to determine whether incoming tasks will meet their deadlines. These tests are computationally expensive and typically run in n * log n time where n is the number of tasks in the system. An incoming task might therefore miss its deadline while the schedulability test is being performed, when there is a heavy load on the system. In our work we evaluate a new approach for admission control in firm real-time systems. Our work shows that ANNs can be used to perform a schedulability test in order to work as an admission controller in firm real-time systems. By integrating the ANN admission controller to a real-time simulator we show that our approach provides feasible performance compared to a traditional approach. The ANNs are able to make up to 86% correct admission decisions in our simulations and the computational cost of our ANN schedulability test has a constant value independent of the load of the system. Our results also show that the computational cost of a traditional approach increases as a function of n log n where n is the number of tasks in the system.

Real-time systems are computing systems that demand the assurance of not only the logical correctness of computational results but also the timing of these results. To ensure timing constraints, traditional real-time system designs usually adopt a worst-case based deterministic approach. However, such an approach is becoming out of sync with the continuous evolution of IC technology and increased complexity of real-time applications. As IC technology continues to evolve into the deep sub-micron domain, process variation causes processor performance to vary from die to die, chip to chip, and even core to core. The extensive resource sharing on multi-core platforms also significantly increases the uncertainty when executing real-time tasks. The traditional approach can only lead to extremely pessimistic, and thus, unpractical design of real-time systems. Our research seeks to address the uncertainty problem when designing real-time systems on multi-core platforms. We first attacked the uncertainty problem caused by process variation. We proposed a virtualization framework and developed techniques to optimize the system's performance under process variation. We further studied the problem on peak temperature minimization for real-time applications on multi-core platforms. Three heuristics were developed to reduce the peak temperature for real-time systems. Next, we sought to address the uncertainty problem in real-time task execution times by developing statistical real-time scheduling techniques. We studied the problem of fixed-priority real-time scheduling of implicit periodic tasks with probabilistic execution times on multi-core platforms. We further extended our research for tasks with explicit deadlines. We introduced the concept of harmonic to a more general task set, i.e. tasks with explicit deadlines, and developed new task partitioning techniques. Throughout our research, we have conducted extensive simulations to study the effectiveness and efficiency of our developed techniques. The increasing process variation and the ever-increasing scale and complexity of real-time systems both demand a paradigm shift in the design of real-time applications. Effectively dealing with the uncertainty in design of real-time applications is a challenging but also critical problem. Our research is such an effort in this endeavor, and we conclude this dissertation with discussions of potential future work.

Reverse-engineering the brain is one of the US National Academy of Engineering’s “Grand Challenges.” The structure of the brain can be examined at many different levels, spanning many disciplines from low-level biology through psychology and computer science. This thesis focusses on real-time computation of large neural networks using the Izhikevich spiking neuron model. Neural computation has been described as “embarrassingly parallel” as each neuron can be thought of as an independent system, with behaviour described by a mathematical model. However, the real challenge lies in modelling neural communication. While the connectivity of neurons has some parallels with that of electrical systems, its high fan-out results in massive data processing and communication requirements when modelling neural communication, particularly for real-time computations. It is shown that memory bandwidth is the most significant constraint to the scale of real-time neural computation, followed by communication bandwidth, which leads to a decision to implement a neural computation system on a platform based on a network of Field Programmable Gate Arrays (FPGAs), using commercial off- the-shelf components with some custom supporting infrastructure. This brings implementation challenges, particularly lack of on-chip memory, but also many advantages, particularly high-speed transceivers. An algorithm to model neural communication that makes efficient use of memory and communication resources is developed and then used to implement a neural computation system on the multi- FPGA platform. Finding suitable benchmark neural networks for a massively parallel neural computation system proves to be a challenge. A synthetic benchmark that has biologically-plausible fan-out, spike frequency and spike volume is proposed and used to evaluate the system. It is shown to be capable of computing the activity of a network of 256k Izhikevich spiking neurons with a fan-out of 1k in real-time using a network of 4 FPGA boards. This compares favourably with previous work, with the added advantage of scalability to larger neural networks using more FPGAs. It is concluded that communication must be considered as a first-class design constraint when implementing massively parallel neural computation systems.

Orientadores: Paulo Sérgio Martins Pedro, Edson Luiz Ursini / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Tecnologia / Made available in DSpace on 2018-08-27T04:51:09Z (GMT). No. of bitstreams: 1 MassaroJunior_FlavioRubens_M.pdf: 3302871 bytes, checksum: aa117bbaac53f7ead30d1a21700e03aa (MD5) Previous issue date: 2015 / Resumo: Modos de operação e mudanças de modo são uma abstração útil para permitir que sistemas de tempo real sejam flexíveis e configuráveis. Trabalhos prévios em escalonamento preemptivo com prioridades fixas permitem que as tarefas passem de um modo de operação para outro provendo garantias de tempo real. No entanto, a configuração adequada dos parâmetros críticos, tais como o offset de uma tarefa, apesar de trabalhos anteriores terem abordado este assunto, permanece uma lacuna a ser explorada. Sem um método que automatize esta etapa do processo, garantindo ao mesmo tempo que os requisitos básicos sejam atendidos, a adoção plena de mudanças de modo em sistemas de tempo real permanece limitada a sistemas relativamente simples, com um conjuntos de tarefas limitado. Propomos um método para atribuir offsets às tarefas em uma mudança modo, através de uma abordagem Metaheurística (algoritmos genéticos). Este método permite a configuração e/ou a minimização da latência de pior caso de uma mudança modo. A latência de uma mudança de modo é um parâmetro crítico para ser minimizado, uma vez que durante a mudança de modo o sistema oferece funcionalidade limitada, uma vez que o conjunto de tarefas está parcialmente em operação. Também elaboramos uma classificação das mudanças de modo de acordo com as necessidades das aplicações. Esta classificação, quando aplicada a uma série de estudos de casos, permitiu validar a abordagem de minimização/configuração, estender a classificação anteriormente existente e demonstrar que o método é flexível, já que pode acomodar uma ampla variedade de tipos de mudanças de modo / Abstract: Modes of operation and mode-changes are a useful abstraction to enable configurable, flexible real-time systems. Substantial work on the fixed priority preemptive scheduling approach allowed tasks across a mode-change to be provided with real-time guarantees. However, the proper configuration of critical parameters such as task offsets, despite initial work, remains a gap in research. Without a method that automates this design step, while assuring that the basic requirements are met, the full adoption of mode-changes in real-time systems remains limited to relatively simple systems with limited task sets. We propose a method to assign offsets to tasks across a mode-change, using a metaheuristic approach (genetic algorithms). This method allows the configuration and/or the minimization of the worst-case latency of a mode-change. The latency of a mode change is a critical parameter to be minimized, since during the mode change the system offers limited functionality due to the fact that the task set is still incomplete. We also provide a classification of mode changes according to applications¿ requirements. This classification was useful, once applied to a number of case studies, both to validate the configuration approach and to a greater extent to show that the method is flexible in that it can accommodate a wide variety of types of mode-changes / Mestrado / Mestre em Tecnologia

Recentes pesquisas têm investigado modelos de garantia de desempenho baseados em restrições temporais, parametrizadas pela especificação de limites superiores de tempo médio de resposta. Este trabalho estende o desenvolvimento da política de escalonamento de temporeal EBS, aplicável a esse problema, apresentando um mecanismo de controle de admissão de requisições em aplicações com tais requisitos. A abordagem baseia-se em um método adaptativo capaz de administrar o nível de degradação do sistema, de forma a isolar o efeito do comportamento de um usuário sobre a qualidade de serviço oferecida aos demais usuários. Também é proposta uma modificação na implementação do algoritmo originalmente definido para a EBS, de forma a diminuir sua complexidade temporal. Resultados de simulação demonstram a efetividade dos mecanismos propostos / In recent research works performance guarantee models based on temporal constraints with specified response-time upper bounds have been investigated. This work extends the development of the EBS real-time scheduling policy, applicable to this problem, by proposing an admission control mechanism. The introduced approach is based on an adaptive model which, based on the system degradation level, tries to isolate the impact of the behavior of a given user upon the quality of service offered to the other users. Its also proposed a new algorithm to reduce the complexity order of the original EBS implementation. Simulation results illustrate the effectiveness of proposed methods

The goal of the thesis is to examine possibilities of dynamic reconfiguration in real-time component systems, especially to formally describe support of operating modes. The thesis introduces a reconfiguration mechanism based on properties and relations between them. The mechanism is designed to facilitate a straight forward modeling of operating modes and reconfiguration rules and preserves re-usability of assembled components. The thesis also presents a realization of the mechanism suitable for the domain of embedded real-time systems.

Originating in the theory of distributed computing, the optimistic consistency control method known as Operational Transformation (OT) has been studied by researchers since the late 1980s. Algorithms were devised for managing the concurrent nature of user actions and for maintaining the consistency of replicated data as changes are introduced by multiple geographically-distributed users in real-time. Web-Based Collaborative Platforms are now essential components of modern organizations, with real-time protocols and standards such as WebSocket enabling the development of online collaboration tools to facilitate information sharing, content creation, document management, audio and video streaming, and communication among team members. Products such as Google Docs have shown that centralized web-based co-editing is now possible in a reliable way, with benefits in user productivity and efficiency. However, as the demand for effective real-time collaboration between team members continues to increase, web applications require new synchronization algorithms and architectures to resolve the editing conflicts that may appear when multiple individuals are modifying the same data at the same time. In addition, collaborative applications need to be supported by scalable distributed backend services, as can be achieved with "serverless" technologies. While much existing research has addressed problems of optimistic consistency maintenance, previous approaches have not focused on capturing the dynamic client-server interactions of OT systems by modeling them as real-time systems using Finite State Machine (FSM) theory. This thesis includes an exploration of how the principles of control theory and hierarchical FSMs can be applied to model the distributed system behavior when processing and transforming HTML DOM changes initiated by multiple concurrent users. The FSM-based OT implementation is simulated, including with random inputs, and the approach is shown to be invaluable for organizing the algorithms required for synchronizing complex data structures. The real-time feedback control mechanism is used to develop a Web-Based Collaborative Platform based on a new OT integration algorithm and architecture that brings "Virtual DOM" concepts together with state-of-the-art OT principles to enable the next generation of collaborative web-based experiences, as shown with implementations of a rich-text editor and a 3D virtual environment.

The mixed-criticality toolbox promises system architects a powerful framework for consolidating real-time tasks with different safety properties on a single computing platform. Thanks to the research efforts in the mixed-criticality field, guarantees provided to the highest criticality level are well understood. However, lower-criticality job execution depends on the condition that all high-criticality jobs complete within their more optimistic low-criticality execution time bounds. Otherwise, no guarantees are made. In this paper, we add to the mixed-criticality toolbox by providing a probabilistic analysis method for low-criticality tasks. While deterministic models reduce task behavior to constant numbers, probabilistic analysis captures varying runtime behavior. We introduce a novel algorithmic approach for probabilistic timing analysis, which we call symbolic scheduling. For restricted task sets, we also present an analytical solution. We use this method to calculate per-job success probabilities for low-criticality tasks, in order to quantify, how low-criticality tasks behave in case of high-criticality jobs overrunning their optimistic low-criticality reservation.