Percorrer por autor "Pinho, Luis Miguel"
A mostrar 1 - 10 de 14
Resultados por página
Opções de ordenação
- Guest editorial: real-time networks and systemsPublication . Pinho, Luis Miguel; Faucou, SébastienThis section of Real-Time Systems provides extended journal versions of the outstanding work presented at the 24th International Conference on Real-Time Networks and Systems (RTNS 2016), held at Université de Bretagne Occidentale (November 2016, in Brest, France). The purpose of RTNS is to provide a venue for sharing new ideas, experiences and information among academic researchers, developers and service providers in the field of real-time systems and networks. The 24th edition of the conference continued the established series with a rich program of 34 papers (out of 75 submissions), with a diversity of topics, such as transactions and distributed systems, network analysis, synchronous dataflow graphs, scheduling and schedulability, periodic systems and control, network optimization, many-core and networks-on-chip, multicore scheduling, timing analysis, parallelism, a clear demonstration of the broad scope of real-time systems and networks research. The special issue consists of four papers that cover various areas, from high level system design and optimization to low level timing analysis of computer systems and networks, which have undergone a rigorous peer-review process according to the journal’s high standards.
- Improved Holistic Analysis for Fork–Join Distributed Real-Time Tasks Supported by the FTT-SE ProtocolPublication . Garibay-Martínez, Ricardo; Nelissen, Geoffrey; Lino Ferreira, Luis; Pedreiras, Paulo; Pinho, Luis MiguelModern distributed real-time embedded applications have high processing requirements associated with strict deadlines. For some applications, such constraints cannot be fulfilled by existing single-core embedded platforms. A solution is to parallelize the execution of the applications, by allowing networked nodes to distribute their workload to remote nodes with spare capacity. In that context, this paper presents a holistic timing analysis for fixed-priority fork-join parallel/distributed tasks. Furthermore, we extend the holistic approach to consider the interaction between parallel threads and messages interchanged through a flexible time triggered switched Ethernet network, and we show how the pessimism on the worst case response time computation of such tasks can be reduced by considering the pipeline effect that occurs in such distributed systems. To evaluate the performance and correctness of the holistic model, this paper includes a numerical evaluation based on a real automotive application. The obtained results show that the proposed method is effective in distributing the load by different nodes, allowing a significant reduction of the worst case response time of the tasks. Moreover, the paper also reports an implementation of the model on a Linux library, called parallel/distributed real-time, as well as the corresponding results obtained on a real testbed. The obtained results are in accordance with the predictions of the holistic timing analysis.
- IoT for Energy-Efficiency: connecting a serious game with energy metering in the EnerGAware projectPublication . Barbosa, Paulo; Barros, António; Pinho, Luis MiguelThe Internet of Things (IoT) emerged with the potential to change our daily lives and the way we interact and operate with our environment. However, in practice, IoT mixes a multitude of devices and subsystems, which are required to work together to provide the user with the expected quality of service. This leads to considerable development challenges, which are exacerbated by the speed of development and heterogeneity of IoT devices. This communication describes an IoT solution being implemented in the setting of a serious game application, connected to real homes energy consumption. The solution follows a publish-subscribe architecture to decouple the components of the system.
- Multicore emulation-in-the-loop in the Khronosim projectPublication . Pinho, Luis Miguel
- Platform for Smart Car to Car Content Delivery: Results of CISTER Research Centre within CarCoDe projectPublication . Albano, Michele; Cerqueira, Tiago; Lino Ferreira, Luis; Pinho, Luis Miguel; Pacheco Paulo, FilipeA vehicular mobility model - For simulations on inter-vehicular communication. Both realistic and easy-to-use - Included into the framework “network simulator 3”
- Programming atomic multicasts in CANPublication . Pinho, Luis Miguel; Vasques, Francisco; Ferreira, LuísIn Distributed Computer-Controlled Systems (DCCS), a special emphasis must be given to the communication infrastructure, which must provide timely and reliable communication services. CAN networks are usually suitable to support small-scale DCCS. However, they are known to present some reliability problems, which can lead to an unreliable behaviour of the supported applications. In this paper, an atomic multicast protocol for CAN networks is proposed. This protocol explores the CAN synchronous properties, providing a timely and reliable service to the supported applications. The implementation of such protocol in Ada, on top of the Ada version of Real-Time Linux is presented, which is used to demonstrate the advantages and disadvantages of the platform to support reliable communications in DCCS.
- QoS-based surrogates selection and service proposal formulation in offloading environmentsPublication . Nogueira, Luís; Pinho, Luis MiguelResource constraints are becoming a problem as many of the wireless mobile devices have increased generality. Our work tries to address this growing demand on resources and performance, by proposing the dynamic selection of neighbor nodes for cooperative service execution. This selection is in uenced by user's quality of service requirements expressed in his request, tailoring provided service to user's speci c needs. In this paper we improve our proposal's formulation algorithm with the ability to trade o time for the quality of the solution. At any given time, a complete solution for service execution exists, and the quality of that solution is expected to improve overtime.
- Replica management in real-time Ada 95 applicationsPublication . Pinho, Luis Miguel; Vasques, FranciscoIn this paper, we present some of the fault tolerance management mechanisms being implemented in the Multi-μ architecture, namely its support for replica non-determinism. In this architecture, fault tolerance is achieved by node active replication, with software based replica management and fault tolerance transparent algorithms. A software layer implemented between the application and the real-time kernel, the Fault Tolerance Manager (FTManager), is the responsible for the transparent incorporation of the fault tolerance mechanisms The active replication model can be implemented either imposing replica determinism or keeping replica consistency at critical points, by means of interactive agreement mechanisms. One of the Multi-μ architecture goals is to identify such critical points, relieving the underlying system from performing the interactive agreement in every Ada dispatching point.
- Runtime verification of autopilot systems using a fragment of MTL-∫Publication . Pedro, André; Sousa Pinto, Jorge; Pereira, David; Pinho, Luis MiguelCurrent real-time embedded systems development frameworks lack support for the verification of properties using explicit time where counting time (i.e., durations) may play an important role in the development process. Focusing on the real-time constraints inherent to these systems, we present a framework that addresses the specification of duration properties for runtime verification by employing a fragment of metric temporal logic with durations. We also provide an overview of the framework, the synthesis tools, and the library to support monitoring properties for real-time systems developed in C++11. The results obtained provide clear evidence of the feasibility and advantages of employing a duration-sensitive formalism to increase the dependability of avionic controller systems such as the PX4 and the Ardupilot flight stacks.
- Scheduling Parallel Real-Time Tasks in Multiprocessor PlatformsPublication . Maia, Cláudio; Nogueira, Luis Miguel; Pinho, Luis Miguel• Computing systems are gradually becoming multiprocessor • Opportunity for an increase in application performance, throughput and responsiveness • Real-time systems may take advantage of platform parallelism to distribute workload among the cores for simultaneous execution