This paper presents a model for quality-of-service (QoS)-aware service composition in distributed systems with real-time and fault-tolerance requirements. This model can be applied in application domains like, for example, remote monitoring, control and surveillance. Classic approaches to real-time systems do not provide the flexibility and fault-tolerance required in new emerging environments that need to combine a high degree of dynamism with temporal predictability. Our approach addresses these new challenges by combining concepts from the service oriented paradigm and distributed real-time systems. We propose a concrete system model based on a holistic time-triggered-based approach for design and configuration. Based on this model, we propose two algorithms for the composition of QoS-aware service-based applications with temporal requirements: an exhaustive algorithm that computes the optimal service combination in terms of a figure of merit, suitable for offline composition; and an improved algorithm based on heuristics and partial figures of merit, suitable for online composition. Experimental results show that the latter reduces dramatically the number of combinations explored with a minimal degradation in the quality of the solution, making it feasible for online execution in dynamic environments.

Current trends in industrial systems opt for the use of different big-data engines as a mean to process huge amounts of data that cannot be processed with an ordinary infrastructure. The number of issues an industrial infrastructure has to face is large and includes challenges such as the definition of different efficient architecture setups for different applications, and the definition of specific models for industrial analytics. In this context, the article explores the development of a medium size big-data engine (i.e. implementation) able to improve performance in map-reduce computing by splitting the analytic into different segments that may be processed by the engine in parallel using a hierarchical model. This type of facility reduces end-to-end computation time for all segments with their results then merged with other information from other segments after their processing in parallel. This type of setup increases performance of current clusters improving I/O operations remarkably as empirical results revealed.

Next generation real-time applications demand big-data infrastructures to process huge and continuous data volumes under complex computational constraints. This type of application raises new issues on current big-data processing infrastructures. The first issue to be considered is that most of current infrastructures for big-data processing were defined for general purpose applications. Thus, they set aside real-time performance, which is in some cases an implicit requirement. A second important limitation is the lack of clear computational models that could be supported by current big-data frameworks. In an effort to reduce this gap, this article contributes along several lines. First, it provides a set of improvements to a computational model called distributed stream processing in order to formalize it as a real-time infrastructure. Second, it proposes some extensions to Storm, one of the most popular stream processors. These extensions are designed to gain an extra control over the resources used by the application in order to improve its predictability. Lastly, the article presents some empirical evidences on the performance that can be expected from this type of infrastructure. Model combining stream processing technology and real-time.Extensions to the Storm processor.Performance evaluation of the extension on a cluster.

Communication middleware technologies are powerful instruments to develop and deploy remote laboratories for students to practice the control of real application cases. Middleware allows the rapid development and deployment of actual distributed settings since it abstracts the specifics of the different hardware platforms and communication media involved in the access of students to the lab material. This paper describes the practical settings carried out in the a case of a successful laboratory experience that allows students to simulate the on-line monitoring and control of remote systems, i.e., the train traffic in a simulated metro system. The innovative contribution of this experiment is the usage of data-centric middleware based on the publish/subscribe paradigm that has real-time properties. Up to our knowledge, such deployment with this particular middleware type has not been done, and it has given rise to a flexible setting that grows with the contributions of students. We have validated the idea by gathering the feedback of students with respect to the operation of the assignment, showing that this motivates the students' learning and enrollment in the assignment.

This paper presents a software framework containing a reconfiguration mechanism that provides realtime execution guarantees in intensive media processing consumer electronic devices. Our approach offers real-time guarantees during all of the system operation, i.e., not only during the normal media processing mode but also in the event of reconfigurations (a reconfiguration is a transition among two different system states). This approach enhances the budget scheduling model to provide a time-partition that guarantees the availability of resources during transitions. Results are presented that validate the proposed approach.

In recent years, big data systems have become an active area of research and development. Stream processing is one of the potential application scenarios of big data systems where the goal is to process a continuous, high velocity flow of information items. High frequency trading (HFT) in stock markets or trending topic detection in Twitter are some examples of stream processing applications. In some cases (like, for instance, in HFT), these applications have end-to-end quality-of-service requirements and may benefit from the usage of real-time techniques. Taking this into account, the present article analyzes, from the point of view of real-time systems, a set of patterns that can be used when implementing a stream processing application. For each pattern, we discuss its advantages and disadvantages, as well as its impact in application performance, measured as response time, maximum input frequency and changes in utilization demands due to the pattern.