This work presents the design and evaluation of a LoRaWAN-based IoT architecture for wildfire monitoring in rural and forested environments. The proposed system offers a solution for the elaboration of data gathered in the forested area, to support fire prevention and firefighting duties on the edge. To cope with this goal, the solution relies on resourceconstrained sensor nodes and LoRaWAN gateways to enable reliable data transmission under challenging conditions, including dense vegetation and limited communication infrastructure. The study models and analyzes the communication dynamics of largescale LoRaWAN deployments using Generalized Stochastic Petri Nets (GSPNs), capturing the impact of multiple transmission channels and varying traffic loads characterizing the wildfire monitoring system analyzed. Particular emphasis is placed on assessing network scalability and reliability when a large number of sensor nodes concurrently transmit environmental data. The findings contribute to the development of efficient and resilient IoT-based solutions for environmental monitoring and emergency response in remote and resource-constrained scenarios.

The Industrial Revolution changed the picture of industrial systems by making them highly efficient and more manageable. The inclusion of the internet, smart devices, and various protocols has collectively developed Industrial Control Systems (ICS), which are responsible for the entire industrial activity management. However, the devices in ICS may also malfunction and show abnormal behavior, affecting industrial activities. Hence, it is necessary to have a good abnormal condition detection system in ICS, but the presence of a real environment for developing such a detection system is challenging. Therefore, the proposed work addresses this challenge by modeling the ICS to mimic the actual behavior of the industries and collecting the relevant data to train a model for detecting anomalous behavior in the system. The work employed Discrete Event System Specification (DEVS) as a modeling and simulation formalism for designing the ICS. Through this modeling system, the work collects the states associated with every device and trains a machine-learning model to deal with anomalies in ICS further. This work also aims to show the significance of the DEVS formalism in modeling the ICS and how its state-based data may be used further to make an artificial intelligence-oriented solution.

Urban traffic is one of the most important issues for smart cities, and real-time management is critical for improving mobility and reducing congestion. Traditionally, classification methods based on machine learning need frequent retraining, which is inefficient for adaptive traffic management systems. This work introduces a novel hybrid approach that combines Incremental Learning (IL) with Federated Learning (FL) techniques to support continuous model adaptation without centralizing data or restarting the training process from scratch. The proposed approach employs Convolutional Neural Networks (CNNs) to classify traffic conditions from junction camera feeds and includes a specific mechanism to mitigate the Catastrophic Forgetting (CF) issue, a common drawback in IL. This solution enhances model performance in a decentralized way while protecting data privacy and encouraging knowledge sharing across distributed nodes. Experimental results on a publicly available dataset reveal that this approach significantly improves dynamic traffic management, achieving over 96% validation accuracy throughout the IL process for multiple clients, with minimal loss and no need to centralize data. This work sets the basis for a more effective and secure traffic management infrastructure in smart cities.

This paper presents a study on the integration of cloud computing with UAV autopilot systems, aiming to significantly enhance operational efficiency, scalability, and autonomy in UAV operations. By leveraging the synergies between the IoT, cloud computing, and sophisticated UAV autopilot technologies, we introduce a novel architectural framework designed to overcome existing challenges in UAV operations, such as advanced mission planning, real-time data analytics, and dynamic resource management. The presented approach emphasizes the integration of the MAVLink protocol and the ROS with the PX4 autopilot system, marking a crucial step towards achieving autonomous UAV operations characterized by enhanced safety and reduced mission execution times. Empirical assessments, supported by detailed operational scenario analyses, demonstrate the effectiveness of this integration, revealing improvements in UAV performance metrics. The outcomes highlight the potential of cloud computing integration with UAV operational paradigms, paving the way for further exploration in autonomous systems and cloud-assisted IoT applications.

This paper describes a novel architecture aiming to create an open-source template for implementing a platform enabling support for the deployment and integration of services and workflows that compose, manage, and continuously evolve a complex system: the Urban Intelligence. More specifically, the proposed Smart City IT architecture is an evolution of a concrete urban intelligence architecture meant mostly to support Data scientist activities and, obviously, the exploitation of Smart City services by citizens and users. The proposed solution, due to its open-source nature, is fully replicable and improves its ancestor by provisioning new characteristics: i) managing facilities of urban Cyber-Physical System via exploitation of a combination of Administrator/Data scientist workflows and IoT management platform, ii) the definition of workflow directly on the Edge (even through the exploitation of FaaS paradigm directly on IoTs), and iii) enhancement of Smart City infrastructure security via the reduction of external attack surface. The prototype of the proposed IT solution has been implemented leveraging open-source frameworks and technologies belonging to the OpenStack ecosystem.

The burgeoning paradigms of Fog and Edge computing propose delegating Cloud-related tasks to the network’s periphery, thus placing computational resources closer to data producers. This shift promises to boost the performance of IoT-based services, providing swift response times while conserving bandwidth. Despite their potential, the current Edge/Fog computing platforms must provide the required flexibility for dynamic service orchestration within a data-oriented context. Addressing this gap, the Function-as-a-Service (FaaS) model emerges as an exceptional strategy for Edge/Fog deployments. Its ability to manage an ever-expanding ecosystem of devices with remarkable flexibility and efficiency holds considerable promise. This paper articulates a novel approach to enhancing the adaptability of IoT Edge/Fog deployments. We propose an innovative extension to OpenStack, an open-source Cloud management system, which pushes its functionality towards the network Edge. Our approach empowers OpenStack to facilitate FaaS services within a distributed IoT infrastructure, thus infusing unprecedented adaptability and efficiency into the Edge/Fog computing paradigms.

A Smart Factory exploits information and communication technologies (ICT) to improve the production process and the working environment, usually addressing safety concerns. To this concern, factory-grade fire protection systems are governed by several procedures and standards whose application often becomes definitely challenging when the factory premises are dispersed across multiple administrative domains. In such contexts, the Smart Factory approach can prove very effective in the management and coordination of the factory-level fire protection system. However, a catastrophic event may compromise the ICT infrastructure, affecting communication among factory domains and therefore its smart services. A strategy to cope with the latter may be the introduction of mechanisms to handle data analysis on-site for a prompt response while enabling seamless data distribution and processing among neighboring (federated) ICT infrastructures and emergency operators. In this work, a novel software-defined approach for the adaptive management of a Smart Factory infrastructure is proposed, centered around business logic rewiring and reconfiguration at runtime across different factory domains. Thereby, even in the case of catastrophic (e.g., potentially disruptive) events, working devices of the emergency system can go on with their operations, including transferring data to rescuers and others emergency control systems. To demonstrate the effectiveness of the proposed software-defined factory approach, a federated fire protection system operating in an industrial setting is implemented as a case study, able to promptly react and adapt to infrastructure-critical fires and their consequences by leveraging all information and computing facilities pooled over cloud/fog/edge devices spanning the premises.

Intelligent Personal Assistants (IPA) are becoming an essential part of our life. The trend aiming at adopting IPA devices is driven by the uncountable applications enabled by the advent of the Internet of Things (IoT) and its role in home automation. Actually, people are able to use, for example, voice-controlled IPA devices (e.g., Amazon Alexa) to interact and control things in their surrounding environment. Yet, to enable such interactions in an environment with multiple devices, the user has to configure each device. Besides, it is not possible to apply the same operation in a specific environment used for a short period, such as a hotel room, i.e., for security reasons: the owner of a hotel cannot permit access to the devices from their customer as it may be risky. To deal with such a limitation, the adoption of a Software-Defined approach, such as Software-Defined I/O (SDI/O), is a relevant approach to decouple the access to IoT resources from their management duties. In the case of accommodation facilities, such as a hotel room, to connect an IPA to IoT devices, a set of repeated configurations has to be performed. This paper proposes “Everywhere IPA” (EIPA), an approach relying on the Software-Defined I/O approach to automatize the configuration of IoT devices.

Air pollution is one of today's most biggest problems, mostly due to greenhouse gas emissions that have increased exponentially since the mid-twentieth century. Today's society is the main culprit due to the emissions caused by the industriaV-manufacturing processes and the different transportation means. In particular, the cities, always affected by traffic congestion and traversed by uncountable vehicles, are crucial points where actuate solutions can mitigate the pollutants generated by the vehicles. The cities, enhanced by the Internet of Things (IoT) advent, are becoming “Smart” thanks to the data generated by IoT devices. The ubiquitous distribution and the possibility of correlating data from different sources (voluntary shared or freeware) have enabled the crowdsourced initiative to realize applications exploiting these data. In this work, a multilevel IoT/Cloud infrastructure lends itself to offering solutions to citizens to solve daily life problems. The architecture, putting in place means to conceive an exciting application, is investigated through different use cases linked to current cities issues: public mobility, free parking slot detection, and air quality monitoring.

The Internet of Medical Things (IoMT), combined with interconnected wearable devices and medical-grade sensors, can play an essential role in healthcare evolution. By exploiting the data generated by the plethora of interconnected devices (vital parameters, location-based info, patients activity and more), advanced ICT systems can be put in place with predicting capabilities. This way potentially critical situations, that may evolve in serious complications to patients’ well-being, can be promptly recognized and successfully addressed, first of all, to save lives and secondarily to limit economical damages. To support continuous patient monitoring in public and private healthcare, this paper proposes "DILoCC", an architecture to manage wearable devices, sensors and applications, that uses a Distributed Incremental Learning (DIL) approach to exploit cooperation among the sensing devices and increase the overall system efficiency through the mitigation of "Catastrophic Forgetting" consequences.

Smart Building/Environment management is an interesting topic that, although widely investigated in the literature, has not seen wide adoption in real case studies. Current Smart Building solutions provide facilities for: i) automatically managing HVAC (Heating, Ventilation and Air Conditioning) systems; ii) energy management, iii) building automation. Current solutions are tightly coupled with the underlying IT infrastructure of the building and cannot be rearranged according to the events, catastrophic or otherwise, that may modify the building structure (e.g., a disruption to sections of a building). In this work, we present a novel approach for Smart Buildings (we refer to it as "Software Defined Building 2.0") to customize and reprogram IT infrastructure powering buildings, this way enabling cooperation among Cyber-Physical Systems (CPSs) operating within. We analyze an architecture enabling this approach, evaluating overhead management and its impact on systems’ performance.

In this work, we propose a low-cost Smart and Healthy Intelligent Room System (SHIRS), able to monitor Indoor Air Quality (IAQ) by enhancing edge-based computation. SHIRS exploits the ability to run Machine Learning (ML) algorithms to infer humans presence (headcount) from environmental data analysis. Experimental results show the validity of the proposed approach, demonstrate the potential of edge-based computing and push towards the adoption of smart integrated Cloud-IoT frameworks for environmental monitoring and control.

Global warming and climate changes are due to several factors, not least vehicle and transportation emissions. Smart City technologies can provide mechanisms for emission (greenhouse gases, particles) containment that may significantly impact on the environment. This paper proposes a solution, based on an intelligent cruise control system, allowing a vehicle to interact with the Smart City infrastructure facilities for cutting down its emissions on the planned route while saving fuel. The proposed approach aims at implementing a (virtually) continuous green wave for a vehicle lowering its emissions by modulating the speed only considering local traffic congestion and traffic light information provided by the Smart City infrastructure, without actuating on the latter. A green-green (green2) wave also reducing the fuel consumption and ensuring a good trade off with travel time. To demonstrate the effectiveness of the proposed solution, a power train model of a c-segment car traveling on while interacting with Smart City facilities has been implemented and evaluated, providing significant insights.

With the widespread emergence of the Internet of Things (IoT), our environment and locations are turning progressively into smart environments ranging from individual houses/offices to schools, factories, and hospitals. Even more interesting, with the rise of Fog/Edge paradigms, the IoT application scope has been extended to provide critical services. By pushing resources such as compute and storage to the network edge, IoT-based services are taking benefits from their proximity to provide better performances. However, albeit an exciting development in and by itself, Edge/Fog computing platforms currently do not provide a convenient level of flexibility and efficiency to support the dynamic composition of services with a data-oriented approach. In this context, the Function-as-a-Service computing paradigm rises as a convenient/suitable paradigm to be adopted in the IoT landscape. For the sake of providing flexible IoT Edge/Fog deployments, this paper introduces a system providing FaaS services based on a distributed IoT infrastructure. Besides, we provide a dashboard based on Node-RED that exploits, in the backend, the FaaS system to make the users able to conceive customized applications using the resources (i.e., sensors and actuators) that the IoT devices can host.

Nowadays, the study of nucleic acids (DNA/RNA) has become a digital science thanks to the advent of modern massive parallel sequencing technologies, better known with the acronym NGS standing for next-generation sequencing, and to the availability of a vast amount of genetic data easily accessible from publicly available databases. Due to the quantity and complexity of such data, its processing requires strong computer science knowledge and skills. This background includes topics such as programming and scripting languages, command-line interfaces, low-level data management tools, which are not always part of the toolbox of molecular biologists and geneticists. The need to adapt to entirely new IT tools and workflows slow down even the more experienced researchers, thus dedicated and customizable GUIs would be much more preferable and conducive. In this paper, we tackle this issue by proposing a preliminary architecture for a framework providing the following benefits: i) it supports the post-NGS analysis process definition phase (commonly called pipeline definition) via a graphical dashboard designed with NodeRED; ii) it automatically deploys the workflows on top of a cluster of computational resources, according to the Function-as-a-Service paradigm, i.e., treating each step of the pipeline as a function to be executed within Linux-based containers, pre-configured with all the necessary dependencies; iii) it runs such containers taking care automatically of resource load balancing. Finally, the framework is thought to include human feedback in the loop, thanks to the availability of a smart notification system, allowing the researcher to monitor the workflows and make any decision needed for its continuation.

A Smart City can be envisioned as an ecosystem of smart environments that can be federated to interact one another, making infrastructure suitable to host innovative services for citizens and improve quality of city life. In such a context, interoperability and the presence of different administrative domains are the main challenges. In this paper, we propose to extend the Software-Defined City paradigm to both I/O and networking functions for implementing this vision. Through a motivating use case, we show how this approach can help in making city infrastructure a fully programmable ecosystem of resources that can be rewired any time at will.

Nowadays, Edge computing allows to push the application intelligence at the boundaries of a network in order to get high-performance processing closer to both data sources and end-users. In this scenario, the Horizon 2020 BEACON project - enabling federated Cloud-networking - can be used to setup Fog computing environments were applications can be deployed in order to instantiate Edge computing applications. In this paper, we focus on the deployment orchestration of Edge computing distributed services on such fog computing environments. We assume that a distributed service is composed of many microservices. Users, by means of geolocation deployment constrains can select regions in which microservices will be deployed. Specifically, we present an Orchestration Broker that starting from an ad-hoc OpenStack-based Heat Orchestraton Template (HOT) service manifest of an Edge computing distributed service produces several HOT microservice manifests including the the deployment instruction for each involved Fog computing node. Experiments prove the goodness of our approach.

Cloud computing is becoming a relatively mature paradigm in the ICT landscape. In light of the growing appetite for resources and service levels on par with user expectations, multi-cloud scenarios are becoming the next frontier in the usage of distributed datacenters for private and hybrid Cloud scenarios. Application deployment in particular is a noteworthy feature to be evaluated as microservices become mainstream in adoption. Especially so when considered jointly with orchestration services; indeed OpenStack, as the most widely adopted Cloud middleware among the OpenSource community, features an orchestration subsystem, and may orchestrate the deployment of applications and services. In this work the authors will describe an architecture, developed within the H2020 BEACON project, for a standardized approach to orchestrated application deployment in multi-Cloud OpenStack- based setups, with TOSCA providing the specifications.