The integration of sensing, computation, and communication technologies has accelerated the adoption of Cyber-Physical Systems (CPS), where digital and physical components interact in real time. Although the Internet of Things–Edge–Cloud Continuum (IECC) introduces distributed computing across network layers, most current solutions still depend on centralized ETL (Extract, Transform, and Load) processes and monolithic data platforms. These systems often struggle with interoperability, domain-specific data ownership, and real-time requirements. In this paper, we apply Data Mesh to CPS within the IECC smart-city context. Our contributions include: (i) analyzing how Data Mesh principles address CPS challenges of scalability, latency, and heterogeneity; (ii) designing and deploying a prototype integrating IoT, edge, and cloud components; and (iii) comparing its performance with a microservices-based architecture. Results show slightly higher latency and memory usage from service replication and domain isolation, balanced by improved modularity, scalability, and domain autonomy.

Simulation technology is gaining significant traction in manufacturing, particularly for applications such as circularity assessment. Recent advancements, including serviceoriented distributed manufacturing, require novel methodologies to enable seamless integration and orchestration of simulation models across distributed manufacturing services. This paper introduces a platform architecture built around a simulation middleware (SM) that supports distributed, simulation-based circularity assessment within a Manufacturing-as-a-Service (MaaS) ecosystem. The platform is validated through an industrial use case, demonstrating its applicability while ensuring sovereignty and confidentiality of simulation models and data.

Remote driving has gained increasing attention as a key enabler for connected and automated vehicles. Yet its practical deployment hinges on wireless networks' ability to guarantee low, predictable latency. In this paper, we present an extensive latency analysis of ITS-G5 and cellular (5G) technologies within the Modena Automotive Smart Area (MASA), a real-world, city-scale testbed equipped with a distributed intelligent transportation infrastructure. By conducting controlled experiments under varying network loads and traffic conditions, we measure network and end-to-end latency components relevant to remote driving, in which the uplink consists of a continuous video stream transmitted from the vehicle to the remote operator, and the downlink conveys control commands back to the car. Measurements conducted under diverse conditions reveal how latency and variability differ across the two technologies and how infrastructure coverage impacts video-stream transmission performance. Based on the observed latency distributions and reliability metrics, we assess the practical feasibility and safety margins of remote driving in mixed network environments. The results provide actionable insights for future teleoperation deployments and motivate hybrid communication strategies that combine the strengths of ITS-G5 and cellular networks.

While the Microkernel paradigm is a cornerstone for achieving modularity and extensibility, its application in modern distributed environments is often hampered by a rigid dependency on specific execution contexts. Existing frameworks often entangle business logic with specific communication technologies, necessitating extensive refactoring when transitioning between monolithic and distributed deployments. In this work, we introduce Orbitalis, an open-source framework that extends the Microkernel paradigm to distributed systems. Orbitalis integrates component development, communication, and lifecycle management, enabling seamless execution across both local and distributed environments, enabling applications to operate seamlessly across heterogeneous nodes without requiring a priori knowledge of the deployment topology. At the heart of the framework lies Busline, an asynchronous, protocol-agnostic publish/subscribe backbone that supports dynamic component evolution, replication, and replacement. A DHCP-inspired discovery protocol enables cores and plugins to negotiate, connect, and reconfigure at runtime. Experimental evaluation quantifies the framework’s overhead across various deployment scenarios, demonstrating its practical viability.

In this research, we propose automating network management through data-driven intelligence, with a particular focus on anomalies and network traffic during specific events or periods. We analyze a large dataset collected by Orange mobile network operator in France with the goal of forecasting mobile demand for different classes of services. To model the underlying network infrastructure, we introduce a model for the underlying network based on a hierarchy of virtualization layers and slices. Building on this model, we propose algorithms to optimize the resources allocated to network slices and traffic distribution within the operator’s network. Network performance is evaluated as the fraction of time the mobile traffic is within the capacity of the network. Our results demonstrate that dynamic reallocation of resources among slices, and dynamic load balancing (traffic shaping) between nodes notably improves network performance. These results provide insights into critical aspects related to future 5G network management.

The Industry 4.0 vision aims for high-quality and flexible production processes that are automated with Cyber-Physical Production Systems (CPPSs) to address changes in demand and the environment. Process Quality Monitoring (PQM) shall ensure the desired process quality and low delay in reacting to deviations towards undesired process outcomes. Digital Twin (DT) functions mend CPPS limitations to monitor conditions in a multi-domain environment, including the physical system. However, it remains unclear how to elicit the tacit and scattered knowledge required to specify conditions for effective PQM under uncertainty. This paper introduces the approach Process Quality Monitoring with Behavior-Driven Development (PQM+BDD) to (i) represent the business intelligence architecture, i.e., cause-effect knowledge and data, required for PQM of a valuable process outcome and (ii) leverage capabilities of Behavior-Driven Development scenarios to specify key conditions as input to design a PQM information system with DT functions. We evaluated PQM+BDD on the design of a CPPS to explore its feasibility, effectiveness, and efficiency. The results indicate PQM+BDD to be feasible, and effective in comparison to a best-practice approach.

The adoption of Digital Twins (DT) as a paradigm to realise a pervasive softwarisation of the physical world, across different application domains and different network levels (from cloud to edge), calls for software architectures and platforms featuring levels of flexibility beyond the ones provided by the solutions available in the state of the art. In this paper we introduce an architectural blueprint and implementation for an event-driven notion of DT, meant to tackle such limitations by promoting flexibility and decoupling. As validation, we present its conceptual application to the challenging context of healthcare emergency missions management and initial experimental evaluation through open-source DT solutions.

The convergence of Artificial Intelligence (AI) and the Industrial Internet of Things (IIoT) is reshaping Cyber-Physical Systems (CPSs), enabling intelligent automation, real-time decision-making, and adaptive control across diverse industrial domains. A key enabler of this transformation is On-Device AI, where training and inference occur directly on edge devices. While deploying AI models in constrained environments presents challenges-such as limited computational resources and hardware heterogeneity-the benefits of reduced latency, improved energy efficiency, and enhanced data privacy make this approach essential for next-generation CPSs. However, scaling and managing AI-enabled CPSs introduces new complexities, including efficient coordination among sensing, computation, and actuation, as well as the need for dynamic model adaptation in resource-constrained settings. Addressing these challenges requires architectural solutions that support distributed intelligence while maintaining system responsiveness and robustness. This paper investigates the use of Digital Twins (DTs) as a cyber-physical abstraction layer that enhances the deployment and management of On-Device AI. By maintaining synchronized, high-level digital representations of physical assets, DTs facilitate local AI execution, optimize resource allocation, and support low-latency decision-making. We validate our approach through experimental evaluation in a microfactory testbed, demonstrating how DTs improve lifecycle management, operational efficiency, and system adaptability in constrained environments. The results highlight the potential of DTs as a foundational technology for scalable, secure, and efficient AI-driven CPSs, offering valuable insights into the deployment of intelligent systems in heterogeneous industrial ecosystems.

This paper introduces the NOUS Smart City Architecture (NSCA), an extensible middleware designed to enable intelligent, interoperable urban services across the edge–cloud continuum. Developed within the NOUS project, NSCA addresses a central challenge in urban digitalization: supporting scalable, efficient communication among heterogeneous actors while integrating with emerging data space infrastructures. On the edge side , NSCA builds on the lightweight and widely adopted MQTT protocol, enabling reliable, low-latency, and semantically structured communication among distributed assets such as edge devices, vehicles, roadside units, and localized digital services. On the cloud side , it integrates a Data Space Ecosystem based on the SIMPL Open architecture, providing a scalable foundation for cross-stakeholder data exchange and governance. The two layers are bridged through a standard MQTT inter-broker connector that can be deployed on either edge nodes or cloud hosts, offering flexibility in how topics are forwarded, filtered, and federated. NSCA supports both real-time data dissemination and service composition at scale, allowing new applications to be integrated with minimal configuration. This makes the architecture suitable for a wide range of smart city verticals, including road safety, mobility management, environmental monitoring, and citizen services. The platform’s practical value is demonstrated through two operational services deployed in a real-world smart city testbed. The Vulnerable Road User (VRU) Safety Service leverages edge-to-cloud communication to detect pedestrians, cyclists, and other users at risk, issuing proactive collision warnings based on real-time situational awareness. The GeoPerception Service enables cooperative sensing by sharing localized perception among vehicles and smart infrastructures, improving environmental understanding and mobility intelligence. Together, these services showcase NSCA’s ability to integrate IoT data flows, edge analytics, and data-space–enabled cloud services, supporting next-generation, interoperable urban applications.

Digital twins (DTs) are increasingly used in industrial environments to mediate interactions between applications and physical assets. However, existing orchestration approaches treat DTs as conventional software components, overlooking their cyber-physical nature and the resulting trustworthiness challenges. In such systems, violations of timing, resource, or data constraints can compromise the fidelity of the DT-physical twin (PT) relationship. In this article, we propose a trustworthiness-driven orchestration system, where trustworthiness is modeled as a multidimensional runtime invariant. The system implements a continuous control loop that monitors relevant metrics and enforces corrective actions, such as resource reallocation or migration across the cloud-to-edge continuum. We validate the approach through a Kubernetes-based prototype and large-scale simulations. Results show that the system effectively detects violations and restores DT-PT entanglement under dynamic conditions, demonstrating the feasibility of invariant-driven orchestration for industrial DTs.

Classical Federated Learning relies on a multi-round iterative process of model exchange and aggregation between server and clients, with high communication costs and privacy risks from repeated model transmissions. In contrast, one-shot federated learning (OFL) alleviates these limitations by reducing communication to a single round, thereby lowering overhead and enhancing practical deployability. Nevertheless, most existing one-shot approaches remain either impractical or constrained, for example, they often depend on the availability of a public dataset, assume homogeneous client models, or require uploading additional data or model information. To overcome these issues, we introduce the Gaussian-Head OFL (GH-OFL) family, a suite of one-shot federated methods that assume class-conditional Gaussianity of pretrained embeddings. Clients transmit only sufficient statistics (per-class counts and first/second-order moments) and the server builds heads via three components: (i) Closed-form Gaussian heads (NB/LDA/QDA) computed directly from the received statistics; (ii) FisherMix, a linear head with cosine margin trained on synthetic samples drawn in an estimated Fisher subspace; and (iii) Proto-Hyper, a lightweight low-rank residual head that refines Gaussian logits via knowledge distillation on those synthetic samples. In our experiments, GH-OFL methods deliver state-of-the-art robustness and accuracy under strong non-IID skew while remaining strictly data-free.

The increasing capabilities of Digital Twins (DTs) in the context of the Internet of Things (IoT) and Industrial IoT (IIoT) call for seamless integration with simulation platforms to support system design, validation, and real-time operation. This paper introduces the concept, design, and experimental evaluation of the DT Simulation Bridge - a software framework that enables diverse interaction patterns between active DTs and simulation environments. The framework supports both the DT development lifecycle and the incorporation of simulations during active operation. Through bidirectional data exchange, simulations can update DT models dynamically, while DTs provide real-time feedback to adapt simulation parameters. We describe the architectural design and core software components that ensure flexible interoperability and scalable deployment. Experimental results show that the DT Simulation Bridge enhances design agility, facilitates virtual commissioning, and supports live behavioral analysis under realistic conditions, demonstrating its effectiveness across a range of industrial scenarios.

Context: The adoption of Artificial Intelligence (AI) in industrial production systems has raised significant expectations for increased efficiency and innovation. Nevertheless, challenges such as the distributed nature of industrial operations, the heterogeneity of physical devices, and the complexity of real-world processes continue to hinder AI integration. Digital Twins (DTs) have emerged as a promising abstraction to decouple physical complexity from digital representations, facilitating more effective system management. Objective: This work investigates how AI can be systematically integrated with DTs in industrial contexts. The goal is to identify and characterize a set of interaction patterns that leverage the complementary strengths of AI and DTs to enhance industrial intelligence and performance. Methods: Drawing on a structured view of how responsibilities can be shared between AI technologies and DT-enabled shop floors, the paper defines four interaction patterns-AI Observing DTs, AI Advising DTs, AI Controlling DTs, and AI Embedded in DT. Each pattern is analyzed in terms of its roles, data and control flows, and typical application scenarios, and is illustrated on a DT-enabled physical micro-factory that reproduces realistic production conditions. Results: The four patterns show how different placements and responsibilities of AI components with respect to DT layers impact modularity, reuse of AI models, maintainability, and integration with legacy industrial systems. The micro-factory illustration highlights how the patterns can support practical use cases, including root-cause analysis of performance degradation, machine-level health monitoring, and AI-based production scheduling. Conclusion: Structuring AI-DT integration around interaction patterns provides a concrete way to bridge the gap between conceptual opportunities and operational industrial systems. The proposed patterns offer a reusable design vocabulary for positioning AI with respect to DT layers in cyber-physical production systems, and for reasoning about the architectural trade-offs of alternative integration strategies.

Effective demand forecasting is crucial for reducing food waste. However, data privacy concerns often hinder collaboration among retailers, limiting the potential for improved predictive accuracy. In this study, we explore the application of Federated Learning (FL) in Sustainable Supply Chain Management (SSCM), with a focus on the grocery retail sector dealing with perishable goods. We develop a baseline predictive model for demand forecasting and waste assessment in an isolated retailer scenario. Subsequently, we introduce a Blockchain-based FL model, trained collaboratively across multiple retailers without direct data sharing. Our preliminary results show that FL models have performance almost equivalent to the ideal setting in which parties share data with each other, and are notably superior to models built by individual parties without sharing data, cutting waste and boosting efficiency.

Industrial digital twin (DT) ecosystems consist of potentially heterogeneous DTs interacting with their respective counterparts in the physical space and with digital entities in the virtual space. Such interactions may vary dynamically and unpredictably, making their engineering a complex and largely unexplored research field. To address this gap, this work revisits the service interaction patterns originally identified in the context of collaborative business processes. This includes a discussion on whether, and to what extent, such patterns are suitable for industrial DT ecosystems. The focus is on the issues of entanglement and composition in cyber-physical interactions. Next, the paper proposes a set of requirements to engineer cyber-physical interactions and engineers a DT implementation compliant with such requirements. Finally, the implemented DT is experimentally evaluated in an industrial scenario.

The increasing complexity of production systems, supply chains, and asset management in the industrial sector demands advanced digital solutions to enhance efficiency, reduce downtime, and support data-driven decision-making. Digital Twin (DT) technology has emerged as a key enabler, allowing real-time monitoring, optimization, and simulation of industrial processes. However, many existing Digital Twin implementations remain highly application-specific, lacking a modular framework for their design, development, and deployment. Such a framework is essential to enable effective interoperability across physical and digital layers, facilitate component reuse, and support the integration of augmentation functions. This paper introduces how DTs implemented with the White Label Digital Twins (WLDT) framework can leverage its general-purpose modular approach to enhance system simplicity and extensibility. DT instances can hence be deployed as individual software components and be easily integrated to build cyber-physical systems. We showcase and validate the proposed framework in a realistic microfactory environment, demonstrating its effectiveness in developing scalable and flexible DT ecosystems of industrial systems.

The Digital Twin (DT) lifecycle plays a pivotal role in accurately and reliably representing its associated Physical Twin (PT). Modeling such representation may be complicated since PTs can adapt telemetry frequency and have different value ranges over time in different phases of their lifecycle with respect to their operational context. If not appropriately accounted for, these variations introduce complexity in maintaining synchronization with the DT: the changes may be misinterpreted as failures while only reflecting expected alterations in the PT's behavior in a given phase. The proposed approach provides a foundation for explicitly modeling and harmonizing the phases of PTs and DTs lifecycles, improving decision-making and operational awareness in cyber-physical systems. We present an experimental evaluation within a reference industrial use case, demonstrating the practical benefits of explicitly mirroring the PT lifecycle in the DT.

Digital Twins (DTs) are increasingly adopted in Internet of Things (IoT) systems to provide real-time virtual representations of physical assets. Their growing interconnectivity, however, exposes them to cybersecurity threats that can compromise fidelity and reliability. This work-in-progress study evaluates how representative attacks—Denial of Service, packet loss, and message manipulation—affect DT operational metrics: timeliness, reliability, availability, and consistency. Using a simulation framework based on NS-3, MQTT, and Eclipse Ditto, we emulate realistic DT environments and quantify the resulting degradations. Results show that cyber-attacks leave measurable deviations in these metrics, and that a revised Overall Digital Twin Entanglement (ODTE) score calibrated on normal operation effectively amplifies such anomalies. Metric-based observability thus emerges as a lightweight, non-intrusive approach for early detection and resilience assessment in DT-enabled infrastructures.

The increasing complexity of Cyber-Physical Systems (CPS), particularly in the industrial domain, has amplified the challenges associated with the effective integration of Artificial Intelligence (AI) and Machine Learning (ML) techniques. Fragmentation across IoT and IIoT technologies, manifested through diverse communication protocols, data formats and device capabilities, creates a substantial gap between low-level physical layers and high-level intelligent functionalities. Recently, Digital Twin (DT) technology has emerged as a promising solution, offering structured, interoperable and semantically rich digital representations of physical assets. Current approaches are often siloed and tightly coupled, limiting scalability and reuse of AI functionalities. This work proposes a modular and interoperable solution that enables seamless AI pipeline integration into CPS by minimizing configuration and decoupling the roles of DTs and AI components. We introduce the concept of Zero Configuration (ZeroConf) AI pipelines, where DTs orchestrate data management and intelligent augmentation. The approach is demonstrated in a MicroFactory scenario, showing support for concurrent ML models and dynamic data processing, effectively accelerating the deployment of intelligent services in complex industrial settings.

This paper presents the Smart City Architecture (SCA), a middleware system built upon the MQTT (Message Queuing Telemetry Transport) protocol and developed within the MASA (Modena Automotive Smart Area) initiative. SCA enables intelligent urban applications by facilitating seamless and scalable communication among heterogeneous entities, including assets, services, and observers. Its structured, topic-based messaging layer supports efficient telemetry exchange, event-driven processing, and dynamic service interaction. The capabilities of SCA are exemplified through two real-world services—Vulnerable Road User (VRU) and GeoPerception—which provide real-time risk detection and localized situational awareness in smart city scenarios.