Placing workloads across the Edge and Cloud can be performed through containerization. However, conditions in Edge nodes are very different from Cloud, as environmental factors such as temperature, humidity, voltage provisioning or dust, heavily affect execution performance and device health. Reliability is an important factor when deciding to deploy such load onto Edge devices, indicating their capability to achieve a desired Quality of Service (QoS). For this, research on Edge computing must focus on how to monitor, estimate and manage devices, in a distributed, autonomous and reliable manner. Our current efforts on performance analysis for devices under "wild conditions" are moving towards integrating reliability into orchestrator systems. Here we present our vision and roadmap for expanding Cloud orchestration towards the Edge with technologies capable of providing knowledge about node environmental conditions and mitigate its impact. Through Out-Of-Band telemetry, we can retrieve temperature and power consumption variables from node components, indicating its health and estimating its reliability given external stress factors. In particular, using intent-based orchestration for containerized platforms, such factors can be used for enforcing reliability as a key-performance indicator. The current work in progress focuses on industrial and commercial scenarios, e.g., Edge computing for urban mobility, with road-side nodes performing AI-based Video-Analytics, exposed to uncontrolled weather conditions. The principal objective is to achieve an Edge network orchestration that takes into account node health in an automatic manner for reducing operational costs such as energy consumption, device repair and replacement, while maintaining QoS in the Edge.

Modern distributed applications increasingly span an edge-cloud continuum, where services may need to dynamically migrate between far-edge, near-edge, and cloud environments to meet latency, resource, or policy constraints. Ensuring seamless service continuity during such migrations remains a significant challenge, particularly due to delays in DNS resolution and inconsistent client routing. This paper presents a modular DNS-driven orchestration framework designed for Kubernetes-based infrastructures. Our approach integrates service orchestration logic with a shared DNS component to enable fast and autonomous service redirection without relying on public DNS providers or complex service meshes. By coupling orchestrator-triggered migrations with DNS record updates, the system ensures immediate service reachability after migration. An optional analytics and decision engine complements the framework by triggering orchestrator actions based on monitoring insights. We evaluate the DNS reconfiguration performance of our solution compared to traditional ExternalDNS-based architectures, demonstrating significantly lower propagation latency and higher determinism during service migrations across the edge–cloud continuum.

As industries increasingly embrace digital and intelligent transformation, enterprises face significant challenges in the containerization upgrades for their Artificial Intelligence(AI) applications and dynamic service migration and management in Cloud-Edge continuum(CEC). This paper presents CloudSkin, an innovative platform designed to realize streamlined, seamless and intelligent service migration in Cloud-Edge Continuum by integrating advanced containerization techniques and AI-driven orchestration capabilities. Our approach, leveraging intelligent algorithms for service migration, can seamlessly transit services between cloud and edge environments, ensuring optimised resource allocation and reducing service latency to assure quality of service(QoS). CloudSkin has been enabled in a Mobility Usecase, empowering Cellnex businesses undergoing digital transformation to achieve higher operational efficiency. The experimental results show that compared to traditional reactive service migration, using intelligent proactive service migration can provide better migration detection, improving F1-Score up to 23.5%, and reducing 28.9% the service running time where the service latency violates SLA.

The virtualization and softwarization of 5G/6G mobile networks have enabled the deployment and orchestration of cloud-native network and application functions. The deployment of these functions is crucial, as the placement of data plane elements (i.e., User Plane Function (UPF)) and vertical services can significantly impact the overall user latency. However, in multi-slice edge scenarios, characterized by users with distinct levels of criticality, the problem of UPF and application placement is becoming increasingly complex due to i) the various costs involved and ii) the limited computational resources at the edge. In this paper, the problem of joint UPF and application placement for a multi-slice user scenario is studied, taking into account multiple cost components that influence the placement decision, including service migration, traffic forwarding, server activation and processing costs. To tackle this problem, we introduce a Joint UPF and Application Reinforcement Learning-based (JUAP-RL) algorithm, which decides the UPF and application deployment location and coordinates the placement stages. Extensive experiments have shown that JUAP-RL demonstrates up to 17% gain in terms of user acceptance ratio and up to 23.4% reduction in provisioning cost compared to baseline schemes.

Hardware platforms are evolving towards parallel and heterogeneous architectures to overcome the increasing necessity of more performance in the real-time domain. Parallel programming models are fundamental to exploit the performance capabilities of these architectures. This paper proposes a novel response time analysis (RTA) for verifying the schedulability of DAG tasks supporting heterogeneous computing. It analyzes the impact of executing part of the DAG in the accelerator device. As a result, the response time upper bound of the system is more precise than the one provided by currently existing RTA targeting homogeneous architectures.

Parallel computation is fundamental to satisfy the performance requirements of advanced safety-critical systems. OpenMP is a good candidate to exploit the performance opportunities of parallel platforms. However, safety-critical systems are often based on static allocation strategies, whereas current OpenMP implementations are based on dynamic schedulers. This paper proposes two OpenMP-compliant static allocation approaches: an optimal but costly approach based on an ILP formulation, and a sub-optimal but tractable approach that computes a worst-case makespan bound close to the optimal one.

DAG-based scheduling models have been shown to effectively express the parallel execution of current many-core heterogeneous architectures. However, their applicability to real-time settings is limited by the difficulties to find tight estimations of the worst-case timing parameters of tasks that may arbitrarily be preempted/migrated at any instruction. An efficient approach to increase the system predictability is to limit task preemptions to a set of pre-defined points. This limited preemption model supports two different preemption approaches, eager and lazy, which have been analyzed only for sequential task-sets. This paper proposes a new response time analysis that computes an upper bound on the lower priority blocking that each task may incur with eager and lazy preemptions. We evaluate our analysis with both, synthetic DAG-based task-sets and a real case-study from the automotive domain. Results from the analysis demonstrate that, despite the eager approach generates a higher number of priority inversions, the blocking impact is generally smaller than in the lazy approach, leading to a better schedulability performance.

OpenMP is increasingly being adopted by current many-core embedded processors to exploit their parallel computation capabilities. Unfortunately, current run-time implementations of the latest specification (v4.0) are not suitable for processors relying on small and fast on-chip memories, due to its memory consumption. This paper proposes an OpenMP4 run-time that reduces the memory consumption while providing the same performance. Our run-time relies on a new compiler pass capable to generate the task dependency graph of OpenMP programs, which is then efficiently stored in memory.

OpenMP is increasingly being supported by the newest high-end embedded many-core processors. Despite the lack of any notion of real-time execution, the latest specification of OpenMP (v4.0) introduces a tasking model that resembles the way real-time embedded applications are modeled and designed, i.e., as a set of periodic task graphs. This makes OpenMP4 a convenient candidate to be adopted in future real-time systems. However, OpenMP4 incorporates as well features to guarantee backward compatibility with previous versions that limit its practical usability in real-time systems. The most notable example is the distinction between tied and untied tasks. Tied tasks force all parts of a task to be executed on the same thread that started the execution, whereas a suspended untied task is allowed to resume execution on a different thread. Moreover, tied tasks are forbidden to be scheduled in threads in which other non-descendant tied tasks are suspended. As a result, the execution model of tied tasks, which is the default model in OpenMP to simplify the coexistence with legacy constructs, clearly restricts the performance and has serious implications on the response time analysis of OpenMP4 applications, making difficult to adopt it in real-time environments. In this paper, we revisit OpenMP design choices, introducing timing predictability as a new and key metric of interest. Our first results confirm that even if tied tasks can be timing analyzed, the quality of the analysis is much worse than with untied tasks. We thus reason about the benefits of using untied tasks, deriving a response time analysis for this model, and so allowing OpenMP4 untied model to be applied to real-time systems.