TinyML enables efficient on-device machine learning for resource-constrained edge devices, addressing privacy and computational challenges in real-world applications. This paper presents a TinyML-based Edge-Cloud system using the FOMO (Faster Objects, More Objects) model deployed on a constrained edge device to analyze visitor engagement in Smart Museums. Unlike conventional camera-based tracking, our approach ensures privacy-preserving analytics by processing visual data locally, extracting only anonymized metrics (e.g., dwell time) to allow for holding power (HP) calculations. We optimize FOMO via data augmentation (DA) and quantization, significantly improving performance; with the optimal configuration, we achieved 86.5% F1-score at 155ms inference latency (a 9.2× speedup over the baseline configuration) while maintaining 88% precision. Our results demonstrate that TinyML-enhanced edge deployment offers a robust, low-latency, and privacy-compliant solution for museum analytics, outperforming traditional cloud and wearable-based approaches.

Digital Twins (DTs) have emerged as essential tools for virtualizing and enhancing Cyber-Physical Systems (CPS) by providing synchronized digital counterparts that enable monitoring, control, prediction, and optimization. Initially conceived as passive digital shadows, DTs are increasingly evolving into intelligent and proactive entities, enabled by the integration of Artificial Intelligence (AI). Among these advancements, Opportunistic Digital Twins (ODTs) represent a novel class of DTs: living, AI-aided, and actionable models that opportunistically exploit edge-cloud resources to deliver enriched and adaptive representations of physical entities and processes. However, despite their promise, current research lacks systematic engineering methods to ensure reliable coordination, determinism, and real-time responsiveness of ODTs in distributed and resource-constrained CPS. This article addresses this gap by introducing an engineering approach to build dependable and efficient ODTs by leveraging the deterministic concurrency, explicit timing semantics, and disciplined event handling of Lingua Franca (LF). The approach is exemplified through a Smart Traffic Management case study centered on Emergency Vehicle Preemption (EVP), where the ODT dynamically selects AI models based on runtime conditions while ensuring deterministic coordination across distributed nodes. Experimental results confirm the feasibility and effectiveness of our methodology, underscoring the potential of LF-based ODT engineering to enhance reliability, adaptability, and scalability in intelligent and distributed CPS deployments.

Digital Twins (DT) have evolved from static digital mirrors into executable cyber-physical counterparts that predict, optimize, and control complex systems. However, the practical deployment of DT in Internet of Things (IoT) environments suffers from limited data fidelity, model brittleness, and resource constraints across the edge–cloud continuum. Generative DT (GDT) is DT augmented with Generative AI (GenAI). They enable the synthesis of high-fidelity data, bridge model-driven and data-driven paradigms, and provide adaptive decision support under uncertainty. This paper systematically reviews the research progress on GDT in the Manufacturing Internet of Things (MIoT), covering system architectures, key enabling technologies, and representative application scenarios. It also summarizes the main limitations of existing studies and outlines future research directions.

The growing demand for computation-intensive artificial intelligence (AI) and machine learning (ML) applications necessitates carbon-neutral edge computing to enhance resource efficiency, reduce energy consumption, and promote sustainability in Industrial Internet of Things (IIoT) systems. However, reducing service latency and energy consumption while ensuring execution accuracy and a predictable carbon footprint and its associated cost remains a critical research challenge. Existing works in the literature experience significant challenges for task offloading due to a lack of edge collaboration and ineffective management of Carbon Emission Rights (CER) credits. In this paper, we have developed an optimization framework leveraging Mixed Integer Linear Programming (MILP), namely GRELMON, to jointly minimize service latency and energy consumption while maximizing task accuracy in carbon-neutral collaborative edge and cloud computing for IIoT environments. Moreover, a carbon emission forecasting model using a hybrid deep learning approach is also developed to prevent unnecessary CER purchases. The experimental results demonstrate that GRELMON outperforms state-of-the-art methods by reducing latency and energy consumption while improving the accuracy of the execution of ML tasks.

Task failures in decentralized Internet of Things (IoT)-edge computing environments not only lead to inefficiencies, increased latency, and resource wastage but can also introduce system instability and cause application malfunctions. These failures may arise due to network disruptions, resource constraints, or inefficient task scheduling, ultimately affecting the overall reliability and performance of IoT-edge systems. This study presents a novel Long Short-Term Memory (LSTM)-based Federated Learning (FL) framework for proactive task failure prediction, ensuring adaptive scheduling and efficient resource utilization. Unlike existing conventional methods, our approach personalizes failure prediction per device, addressing heterogeneous execution characteristics while preserving data privacy. By integrating LSTM with FL, we improve the failure detection accuracy and reduce unnecessary task executions. We first trained all models using Federated Learning (FL) and then conducted a comparative analysis of Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and LSTM. Our findings show that LSTM achieves the highest accuracy and F1 score, while CNN excels in recall and energy efficiency. These insights validate the effectiveness of our FL-based failure prediction framework and highlight the advantages of model personalization for dynamic decentralized IoT-edge environments.

The increasing diffusion of Smart Environments enabled by the Internet of Things (IoT) technologies has evidenced the limitations of traditional Internet Protocol (IP), thus pushing for a paradigm shift from host-centric to Information-Centric Networking (ICN). The Named Data Networking (NDN) is a particular ICN implementation that prospects more efficient and effective communication and service provision, reason why it is widely considered as an enabler towards Future Internet. Driven by the PRISMA methodology, in this work we systematically survey the current literature and analyze opportunities and limitations of NDN adoption within Smart Environments, targeted application areas, adopted technologies and research gaps. In particular, by means of a research framework, we highlight how, by shifting from the traditional IP-based to NDN, Smart Environments can benefit from unseen degrees of mobility, scalability, security and performance, paving the way to innovative and cutting-edge cyberphysical services.

Artificial Intelligence of Things (AIot) has made Stream Processing (SP) an essential element for data analytics. However, the dynamic nature of AIoT data streams incurs significant challenges in SP systems, especially when real-time data processing is required. While traditional approaches rely on resource scaling to meet the AIoT application requirements, our work explores a complementary approach by optimizing in real-time the configuration of SP systems to balance operational and resource efficiencies with data throughput and latency considerations. At the core of our work is the application of a Q-learning algorithm, enabling dynamic and responsive tuning of the SP system configuration parameters to adapt to the fluctuating demands of real-time data processing. Through empirical testing, our approach’s ability to improve SP efficiency in various data environments is demonstrated, providing insights into its practical application and effectiveness. The research concludes by highlighting the potential of extending this optimization approach to broader real-time data processing scenarios, suggesting avenues for future exploration in SP optimization.

Cities have undergone significant changes due to the rapid increase in urban population, heightened demand for resources, and growing concerns over climate change. To address these challenges, digital transformation has become a necessity. Recent advancements in Artificial Intelligence (AI) and sensing techniques, such as synthetic sensing, can elevate Digital Twins (DTs) from digital copies of physical objects to effective and efficient platforms for data collection and in-situ processing. In such a scenario, this paper presents a compre-hensive approach for developing a Traffic Monitoring System (TMS) based on Edge Intelligence (EI), specifically designed for smart cities. Our approach prioritizes the placement of intelligence as close as possible to data sources, and leverages an “opportunistic” interpretation of DT (ODT), resulting in a novel and interdisciplinary strategy to re-engineering large-scale distributed smart systems. The preliminary results of the proposed system have shown that moving computation to the edge of the network provides several benefits, including (i) enhanced inference performance, (ii) reduced bandwidth and power consumption, (iii) and decreased latencies with respect to the classic cloud -centric approach.

Cognitive networking is a valuable enabler to improve the capability of intelligent transportation system (ITS) by analyzing and utilizing the heterogeneous traffic information. However, the significant increase in the amount of decision-making tasks makes it difficult to guarantee real-time performance of decision response. This paper focuses on the problem of the quality and real-time assurance of collaborative decision-making response in large-scale ITS during multi-task parallelism execution. First, a collaborative decision architecture with cognitive networking is developed, which introduces the advanced 6G communication technology to enhance information interaction capability of vehicle-road-cloud collaboration, and lays the foundation for multi-task real-time decision-making with inevitable fuzzy information in the perception process. Then, a multi-task parallel multi-granularity collaborative decision model (MPMCD) is designed to improve knowledge discovery ability for decision-making process by building multi-granularity information structures. An AI-driven cognitive networking collaborative decision-making (ACNCD) algorithm is further proposed based on MPMCD model to support multi-task parallel vehicle-road-cloud collaborative real-time decision. Extensive simulation experiments are carried out to evaluate ACNCD algorithm in terms of several performance criteria including decision response time, accuracy, and accident rate. The obtained results show that the comprehensive decision-making performance of ACNCD outperforms other relevant existing algorithms.

Research trends are pushing artificial intelligence (AI) across the Internet of Things (IoT)–edge–fog–cloud continuum to enable effective data analytics, decision making, as well as the efficient use of resources for QoS targets. Approaches for collective adaptive systems (CASs) engineering, such as aggregate computing, provide declarative programming models and tools for dealing with the uncertainty and the complexity that may arise from scale, heterogeneity, and dynamicity. Crucially, aggregate computing architecture allows for “pulverization”: applications can be decomposed into many deployable micromodules that can be spread across the ICT infrastructure, thus allowing multiple potential deployment configurations for the same application logic. This article studies the deployment architecture of aggregate-based edge services and its implications in terms of performance and cost. The goal is to provide methodological guidelines and a model-based toolchain for the generation and simulation-based evaluation of potential deployments. First, we address this subject methodologically by proposing an approach based on deployment code generators and a simulation phase whose obtained solutions are assessed with respect to their performance and costs. We then tailor this approach to aggregate computing applications deployed onto an IoT–edge–fog–cloud infrastructure, and we develop a corresponding toolchain based on Protelis and EdgeCloudSim. Finally, we evaluate the approach and tools through a case study of edge multimedia streaming, where the edge ecosystem exhibits intelligence by self-organizing into clusters to promote load balancing in large-scale dynamic settings.

Due to their inherent cyber-physical features and high interactivity, IoT services exhibit performances which are simultaneously impacted by different orthogonal factors. Indeed, deployment settings (e.g., Cloud- or Edge-based scenarios, network bandwidth, hardware resource availability), algorithmic aspects (e.g., the specific algorithm used to solve a problem) and data features (e.g., packet size and rate) deeply affect the overall functioning of an IoT service and its compliance with specific requirements such as reactivity, reliability and efficiency. An accurate parameter sweep based on realistic IoT simulations is a viable, yet still unexplored, solution to obtain a full-fledged overview and specific evaluations about the performance of an IoT system under development. In such a direction, in this paper we present an approach for assessing Edge analytic in complex IoT scenarios through a parameter sweep analysis conducted through a simulation-based process, enabling a fine-grained modeling of hybrid IoT systems (both Cloud and Edge) of different scales (small, medium and large). Four typical IoT use cases (autonomous vehicles, smart healthcare, gaming, and industrial IoT) are presented to show the benefits of our approach in finding the right settings for configuring and running them. Indeed, the obtained results show that our approach concretely helps IoT developers in the challenging task of tuning the parameters’ set so as to meet the given requirements, even in the case of large solution spaces and before the actual deployment phase.

The ever-growing aging of the population has emphasized the importance of in-home AAL (Ambient Assisted Living) services for monitoring and improving its well-being and health, especially in the context of care facilities (retirement villages, clinics, senior neighborhood, etc). The paper proposes a novel simulation-driven platform named E-ALPHA (Edge-based Assisted Living Platform for Home cAre) which supports both Edge and Cloud Computing paradigm to develop innovative AAL services in scenarios of different scales. E-ALPHA flexibly combines Edge, Cloud or Edge/Cloud deployments, supports different communication protocols, and fosters the interoperability with other IoT platforms. Moreover, the simulation-based design helps in preliminary assessing (i) the expected performance of the service to be deployed according to the infrastructural characteristics of each specific small, medium and large scenario; and (ii) the most appropriate applications/platform configuration for a real deployment (kind and number of involved devices, Edge- or Cloud-based deployment, required connectivity type, etc). In this direction, two different use cases modeled according to realistic input (coming from past experience involving real testbed) are shown in order to demonstrate the potentials of the proposed simulation-driven AAL platform.

With the increasing number of vehicles, the traffic congestion is becoming more and more serious. In order to alleviate such a problem, this article considers transmission and inference delay of cloud centralized computing in the software defined Internet of Vehicles (SDIoV), and builds a new SDIoV architecture based on edge intelligence, for supporting real-time vehicle routing decision through distributed multi-agent reinforcement learning model. Then, a software defined device collaboration optimization method is designed to improve the efficiency of distributed training. Combined with multi-agent reinforcement learning, a distributed-learning-based vehicle routing decision algorithm (DLRD) is proposed to adaptively adjust vehicle routing online. The performed simulations show that the DLRD can successfully realize real-time routing decision for vehicles and alleviate traffic congestion with the dynamic changes of the road environment.

With the ever-increasing diffusion of smart devices and Internet of Things (IoT) applications, a completely new set of challenges have been added to the Data Mining domain. Edge Mining and Cloud Mining refer to Data Mining tasks aimed at IoT scenarios and performed according to, respectively, Cloud or Edge computing principles. Given the orthogonality and interdependence among the Data Mining task goals (e.g., accuracy, support, precision), the requirements of IoT applications (mainly bandwidth, energy saving, responsiveness, privacy preserving, and security) and the features of Edge/Cloud deployments (de-centralization, reliability, and ease of management), we propose EdgeMiningSim, a simulation-driven methodology inspired by software engineering principles for enabling IoT Data Mining. Such a methodology drives the domain experts in disclosing actionable knowledge, namely descriptive or predictive models for taking effective actions in the constrained and dynamic IoT scenario. A Smart Monitoring application is instantiated as a case study, aiming to exemplify the EdgeMiningSim approach and to show its benefits in effectively facing all those multifaceted aspects that simultaneously impact on IoT Data Mining.

The Internet of Things (IoT) is the latest example of the System of Systems (SoS), demanding for both innovative and evolutionary approaches to tame its multifaceted aspects. Over the years, different IoT methodologies, frameworks, platforms, and tools have been proposed by industry and academia, but the jumbled abundance of such development products have resulted into a high (and disheartening) entry-barrier to IoT system engineering. In this survey, we steer IoT developers by: 1) providing baseline definitions to identify the most suitable class of development products-methodologies, frameworks, platforms, and tools-for their purposes and 2) reviewing seventy relevant products through a comparative and practical approach, based on general SoS engineering features revised in the light of main IoT systems desiderata (i.e., interoperability, scalability, smartness, and autonomy). Indeed, we aim to lessen the confusion related to IoT methodologies, frameworks, platforms, and tools as well as to freeze their current state, for eventually easing the approach towards IoT system engineering.

In Smart Factories, automated guided vehicles (AGVs) accomplish heterogeneous tasks as moving objects, restoring connectivity, or performing different manufacturing activities into production lines. These kinds of devices combine several capabilities, as artificial intelligence (visual and speech recognition, automatic fault detecting, proactive behavior) and mobility, into the so-called “mobile intelligence.” A typical scenario is represented by a workshop with a large number of mobile intelligent devices with associated agents, mutually interacting on their behalf. Here, to reach a given target by contemporary satisfying some basic requirements like effectiveness and efficiency, it is often necessary to organize ad hoc teams of free-moving vehicles, sensors, and smart devices. Therefore, a specific issue is the adequate representation of the reciprocal agent/device trustworthiness for advantaging such team formation processes within a smart factory environment. To this end, in this article, first, we define a trust measure based on reliability and reputation of AGVs, which are computed based on the feedbacks released for the AGVs activities in the factory; second, we design a trust framework exploiting the defined measures to support the formation of virtual, temporary, and trust-based teams of mobile intelligent devices; and third, we present a set of experimental results highlighting that the proposed trust framework can improve the workshop performance in terms of effectiveness and efficiency.

In this paper, we describe how the microservices paradigm can be used to design and implement distributed edge services for Internet of Things applications. As a case study, traditionally monolithic user mobility analysis service is developed, with distributed and extendable microservices, for the standardized ETSI MEC system reference architecture. In each of the edge system three tiers, microservices implement the service logic with components for movement trace analysis, movement prediction and visualization of the results. The distributed service is implemented with Docker containers and evaluated on real-world settings with low capacity edge servers and real user mobility data. The results show that the edge promise of low latency can be met in such as implementation. The integration of a software development technology with a standardized edge system provides solid background for further development.

The Internet of Things (IoT) enables the interconnection of new cyber-physical devices which generate significant traffic of distributed, heterogeneous and dynamic data at the network edge. Since several IoT applications demand for short response times (e.g., industrial applications, emergency management, real-time systems) and, at the same time, rely on resource-constrained devices, the adoption of traditional Data Mining techniques is neither effective nor efficient. Therefore, conventional Data Mining techniques need to be adjusted for optimizing response times, energy consumption and data traffic while still providing adequate accuracy as required by the IoT application. In this paper, new Data Mining approaches particularly tailored for the IoT scenario have been investigated, in particular with respect to the promising, emerging novel distributed computing paradigm of Edge Computing. In detail, two approximated versions of K-Means clustering algorithm, centralized and distributed, have been implemented in the EdgeCloudSim simulation framework and validated on a real system. As highlighted by the algorithm performance analysis, choosing an approximated and distributed clustering solution can provide benefits in terms of computation, communication and energy consumption, while maintaining high levels of accuracy. The management of such trade-off, obviously, has to be done in the light of the specific IoT application requirements.

The integration of existing and future smart cyberphysical systems within a fully realized Internet of Things (IoT) cannot dismiss the requirement of interoperability. The absence of standards for the IoT along with its intrinsic complexity demand for proper methodologies in order to fully support the development of heterogeneous, but interoperable, IoT systems as well as their integration. However, at the state-of-the-art, no methodologies for IoT systems integration are available. To fill this gap, in this paper the INTER-METH engineering methodology is presented. Developed in the context of the European H2020 project named INTER-IoT, INTER-METH supports the integration process of heterogeneous IoT platforms from the analysis to the maintenance phase. Its main features as well as its abstract and instantiated process schema are described; in particular, in this paper the focus is on the analysis phase that is fundamental for driving the integration process.

The future Internet of Things (IoT) is expected to enable a new and wide range of decentralized systems (from small-scale smart homes to large-scale smart cities) in which “things” are able to sense/actuate, compute, and communicate, and thus play a central and crucial role. The growing importance of such novel networked cyber-physical context demands suitable and effective computing paradigms to fulfill the various requirements of IoT systems engineering. In this paper, we propose to explore an agent-based computing paradigm to support IoT systems analysis, design, and implementation. The synergic meeting of agents with IoT makes it possible to develop smart and dynamic IoT systems of diverse scales. Our agent-oriented approach is specifically based on the agent-based cooperating smart object (ACOSO) methodology and on the related ACOSO middleware: they provide effective agent design and programming models along with efficient tools for the actual construction of an IoT system in terms of a multiagent system. A case study concerning the development of a complex IoT system, namely a Smart University Campus, is described to show the effectiveness and efficiency of the proposed approach.

Internet of Things (IoT) networks are being continually developed in several domains, however no systematic processes for their modeling and simulation exist so far.In this paper, an agent-oriented approach to IoT networks modeling is proposed by exploiting the ACOSO model.Then, agent-modelled IoT networks of different scales are simulated through the Omnet++ simulation platform, with the goal of analyzing issues and bottlenecks at communication level.

The Internet of Things (IoT) is a large-scale complex networked cyber physical system in which the Smart Objects (SOs) will be the fundamental building blocks. Although, many research efforts in the IoT realm have been to date devoted to device, networking and application service perspectives, software engineering approaches for the development of IoT systems are still in their infancy. This paper introduces a novel software engineering approach aiming to support a systematic development of SOs-based systems. The proposed approach is based on metamodels that are defined at different levels of abstraction to support the development phases of analysis, design and implementation. The effectiveness of the proposed approach is demonstrated through a simple yet effective case study, showing the development of a smart office SO from the high-level design to its agent-based implementation.

In the future Internet of Things (IoT), smart objects will be the fundamental building blocks for the creation of cyber-physical smart pervasive systems in a great variety of application domains ranging from health-care to transportation, from logistics to smart grid and cities. The implementation of a smart objects-oriented IoT is a complex challenge as distributed, autonomous, and heterogeneous IoT components at different levels of abstractions and granularity need to cooperate among themselves, with conventional networked IT infrastructures, and also with human users. In this paper, we propose the integration of two complementary mainstream paradigms for large-scale distributed computing: Agents and Cloud. Agent-based computing can support the development of decentralized, dynamic, cooperating and open IoT systems in terms of multi-agent systems. Cloud computing can enhance the IoT objects with high performance computing capabilities and huge storage resources. In particular, we introduce a cloud-assisted and agent-oriented IoT architecture that will be realized through ACOSO, an agent-oriented middleware for cooperating smart objects, and BodyCloud, a sensor-cloud infrastructure for large-scale sensor-based systems.

Sensor Networks are increasingly playing a fundamental role in many application scenarios such as agriculture, maritime, healthcare, industrial and even military application. However, the high heterogeneity of sensor networks poses a great challenge in interoperability and cooperative work, and the building of technological bridges among wireless sensor network (WSN) islands is more and more a must for smart cities for an efficient operation. In this paper, we present a model for an Area Sensor Network (ASN) that combines and connects small networks (Body Sensor Networks), WSNs and even fixed sensor networks within a particular area of interest. Initial tests show that the combination of sensed data from multiple sources (sensor networks) produces synergetic services useful for smart cities.

Wireless sensor networks have been widely used in many different applications and in the future they will play an increasingly important role. Since these networks have no fixed infrastructure and are usually distributed over large areas, the use of routing protocols is indispensable. However, when the number of nodes within an area increases, the communication interferences and collisions increase significantly, thus reducing the network performance. In this paper, we first introduce a new measurable quantity, the "node concentration", in contrast to the standard network density. Then, the performance of the AODV (Ad-hoc On-demand Distance Vector) routing protocol is evaluated with respect to the variation in node concentration. Finally, we propose an enhancement of AODV, called CG-AODV, by introducing a "node concentration-driven gossiping" approach for limiting the flooding of control packets. The simulation results demonstrate that CG-AODV provides significant improvements in terms of packet delivery ratio and path discovery delay.