Abstract
Billions of interconnected Internet of Things (IoT) sensors and devices collect tremendous amounts of data from real-world scenarios. Big data is generating increasing interest in a wide range of industries. Once data is analyzed through compute-intensive Machine Learning (ML) methods, it can derive critical business value for organizations. Powerful platforms are essential to handle and process such massive collections of information cost-effectively and conveniently. This work introduces a distributed and scalable platform architecture that can be deployed for efficient real-world big data collection and analytics. The proposed system was tested with a case study for Predictive Maintenance of Home Appliances, where current and vibration sensors with high acquisition frequency were connected to washing machines and refrigerators. The introduced platform was used to collect, store, and analyze the data. The experimental results demonstrated that the presented system could be advantageous for tackling real-world IoT scenarios in a cost-effective and local approach. © 2022 IEEE.

Abstract
Parallel programming models (e.g., OpenMP) are more and more used to improve the performance of real-time applications in modern processors. Nevertheless, these processors have complex architectures, being very difficult to understand their timing behavior. The main challenge with most of existing works is that they apply static timing analysis for simpler models or measurement-based analysis using traditional platforms (e.g., single core) or considering only sequential algorithms. How to provide an efficient configuration for the allocation of the parallel program in the computing units of the processor is still an open challenge. This paper studies the problem of performing timing analysis on complex multi-core platforms, pointing out a methodology to understand the applications' timing behavior, and guide the configuration of the platform. As an example, the paper uses an OpenMP-based program of the Heat benchmark on a NVIDIA Jetson AGX Xavier. The main objectives are to analyze the execution time of OpenMP tasks, specify the best configuration of OpenMP directives, identify critical tasks, and discuss the predictability of the system/application. A Linux perf based measurement tool, which has been extended by our team, is applied to measure each task across multiple executions in terms of total CPU cycles, the number of cache accesses, and the number of cache misses at different cache levels, including L1, L2 and L3. The evaluation process is performed using the measurement of the performance metrics by our tool to study the predictability of the system/application.

Abstract
OpenMP can be used in real-time applications to enhance system performance. However, predictability of OpenMP applications is still a challenge. This paper investigates heuristics for the mapping of OpenMP task graphs in underlying threads, for the development of time-predictable OpenMP programs. These approaches are based on a global scheduling queue, as well as per-thread allocation queues. The proposed method is divided into scheduling and allocation phases. In the former phase, OpenMP task-parts are discovered from OpenMP graph and placed in the scheduling queue. Afterwards, an appropriate allocation queue is selected for each task-part using four heuristic algorithms. In the latter phase, the best task-part is selected from the allocation queue to be allocated to and executed by an idle thread. Preliminary simulation results show that the new method overcomes BFS and WFS in terms of scheduling time and idle time.

Abstract
The ELASTIC European project addresses the emergence of extreme-scale analytics, providing a software architecture with a new elasticity concept, intended to support smart cyber-physical systems with performance requirements from extreme-scale analytics workloads. One of the main challenges being tackled by ELASTIC is the necessity to simultaneously fulfil the non-functional properties inherited from smart systems, such as real-time, energy efficiency, communication quality or security. This paper presents how the ELASTIC architecture monitors and manages such non-functional requirements, working in close collaboration with the component responsible for the orchestration of elasticity. © 2022, Ada-Europe. All rights reserved.

Abstract
The automotive software industry is gradually introducing new functionalities and technologies that increase the efficiency, safety, and comfort of vehicles. These functionalities are quickly accepted by consumers; however, the consequences of this evolution are twofold. First, developing correct systems that integrate more applications and hardware is becoming more complex. To cope with this, new standards (such as Adaptive AUTOSAR) and frameworks (such as AMALTHEA) are being proposed, to assist the development of flexible systems based on high-performance electronic control units (ECU). Second, the increase of functionality is supported by a dramatic increase of electronic parts on automotive systems. Consequently, the impact of software on the electrical power and energy non-functional requirements of automotive systems has come under focus. In this paper we propose an automatic and self-contained approach that supplements a model of an automotive system described on the AMALTHEA platform with energy-related annotations. From the analysis of simulation (or execution) traces of the modelled software, we estimate the power consumption for each software component, on a target hardware platform. This method enables energy analysis during the entire development life-cycle; furthermore, it contributes for the development of energy management strategies for dynamic and self-adaptive systems. © 2022 IEEE.

Abstract
This chapter describes a software architecture for processing big-data analytics considering the complete compute continuum, from the edge to the cloud. The new generation of smart systems requires processing a vast amount of diverse information from distributed data sources. The software architecture presented in this chapter addresses two main challenges. On the one hand, a new elasticity concept enables smart systems to satisfy the performance requirements of extreme-scale analytics workloads. By extending the elasticity concept (known at cloud side) across the compute continuum in a fog computing environment, combined with the usage of advanced heterogeneous hardware architectures at the edge side, the capabilities of the extreme-scale analytics can significantly increase, integrating both responsive data-in-motion and latent data-at-rest analytics into a single solution. On the other hand, the software architecture also focuses on the fulfilment of the non-functional properties inherited from smart systems, such as real-time, energy-efficiency, communication quality and security, that are of paramount importance for many application domains such as smart cities, smart mobility and smart manufacturing. © The Author(s) 2022. All rights reserved.