The Fog computing paradigm makes use of dispersed, diverse, and resource-limited devices located at the network edge to effectively implement Internet of Things (IoT) application services that demand low latency and substantial bandwidth. At the same time, the adoption of microservice-based architectures in the IoT domain is on the rise due to their ability to align with the swift evolution and deployment demands of highly dynamic IoT applications and to elastically scale to fulfill load demands. In complex environments like Fog federations, characterized by highly heterogeneous computing and networking resources, the effective allocation of microservices to available nodes, while ensuring compliance with required Quality of Service (QoS) constraints, represents a significant challenge. In this paper, we present the design and implementation of OptiFog, a comprehensive framework that enables users to model, simulate, and validate microservice placement solutions within a realistic testbed environment. Compared to state-of-the-art approaches, OptiFog offers developers a controlled environment for experimenting with placement solutions while providing the assurance that the resulting deployments will meet the targeted QoS requirements in real-world scenarios, specifically in terms of service execution time and energy consumption of Fog nodes. To demonstrate the feasibility of the proposed approach, we implemented and evaluated a representative use case, involving both sub-optimal and optimal microservice placement, and utilizing real-world microservices drawn from the IoT domain.

The adoption of Service-Based Architecture (SBA) in 5G Core Networks (5GC) has significantly transformed the design and operation of the control plane, enabling greater flexibility and agility for cloud-native deployments. While the infrastructure has initially evolved by implementing key functions, there remains significant potential for additional services, such as localization, paving the way for the integration of the Location Management Function (LMF). However, the extensive functional decomposition within SBA leads to consequences, such as the increase of control plane operations. Specifically, we observe that the additional signaling traffic introduced by the presence of the LMF overwhelms the Access and Mobility Management Function (AMF) which is responsible for authentication and mobility. In fact, in mobile positioning, each connected mobile device requires a significant amount of control traffic to support location algorithms in the 5GC. To address this scalability challenge, we analyze the impact of three well-known optimization techniques on location procedures to reduce control message traffic in the specific context of the 5GC, namely a caching system, a request aggregation system, and a service scalability system. Our solutions are evaluated in an OpenAirInterface (OAI) emulated environment with real hardware. After the analysis in the emulated environment, we select the caching system – due to its feasibility – for being analyzed in a real 5G testbed. Our results demonstrate a significant reduction in the additional overhead introduced by the LMF, improving scalability by minimizing the impact on AMF processing time up to a 50% reduction.

Traditional SDN controllers are usually deployed as monolithic systems or tightly coupled service chains, limiting their adaptability in distributed or federated network domains. This paper presents eMSN, a microservice-based SDN framework that enables controller decomposition and decentralized multidomain orchestration, providing a foundation for scalable, and domain-aware SDN experimentation. The framework introduces lightweight, containerized microservices that interact via REST APIs and coordinate through a shared ETCD cluster. The main one, called FlowBlocker, collects topology and host information from the emitter, builds a policy-aware decision table, and shares domain-scoped state in ETCD. The latter stores only host/topology data and never flow rules; enforcement decisions remain within FlowBlocker, which installs rules locally via Ryu Core or coordinates with peer FlowBlockers across domains. The architecture supports centralized, partially decentralized, and fully decentralized deployment models. The proof-of-concept implementation uses Docker and Mininet for reproducibility. Functional evaluation demonstrates sub-millisecond Packet-In responsiveness, tens-of-milliseconds policy enforcement latency, and correct blocking of unauthorized traffic.

In today’s fast-evolving technological landscape, the Internet of Things (IoT) is fundamentally reshaping how systems connect, interact, and exchange data. As billions of devices become interconnected, the IoT brings both unprecedented opportunities and significant challenges across various domains. Emerging technologies, particularly quantum communication networks, offer transformative solutions by enabling ultra-secure data exchange within IoT infrastructures through advanced techniques such as Quantum Key Distribution (QKD). However, quantum link delay remains one of the key challenges that hinder the effective utilization of these networks. Traffic engineering is a robust method to address this challenge and optimize the performance of quantum networks. This technique involves assessing the current state of the network and making dynamic adjustments based on real-time conditions. Despite its proven benefits in classical systems, its role in quantum networks remains largely unexplored, with no comprehensive framework to date. As a result, in this paper, we propose a framework for quantum traffic engineering and discuss its core components—non-invasive measurements, quantum traffic matrices, data analysis, and performance control. Additionally, we integrate the Particle Swarm Optimization (PSO) algorithm into our framework to minimize the quantum link delay. Ultimately, this work establishes the foundation for researchers in quantum network traffic engineering and sets the stage for continuous, and dynamic monitoring of these networks.

In today’s fast-evolving technological landscape, the Internet of Things (IoT) is fundamentally reshaping how systems connect, interact, and exchange data. As billions of devices become interconnected, the Internet of Things brings unprecedented opportunities and significant challenges in various domains. Emerging technologies, particularly quantum communication networks, offer transformative solutions by enabling ultra-secure data exchange within IoT infrastructures through advanced techniques such as quantum key distribution. However, a significant obstacle to the efficient use of these networks is the lack of current status knowledge of network parameters, which is essential for continuous and dynamic management through quantum traffic engineering. In this paper, we propose the novel concept of quantum traffic matrices as a foundational framework to capture the dynamic operational state of quantum networks. We begin by distinguishing classical traffic matrices from their quantum counterparts. We then identify and present mathematical models for eleven key quantum network parameters that are essential to enable continuous and dynamic management of quantum networks. Our approach and results serve as crucial input for the development of quantum traffic engineering strategies, paving the way for intelligent control, optimization, and resilience enhancement of future quantum communication infrastructures.

Software-Defined Networking traditionally relies on the separation of the control and data planes, centralizing network intelligence within a logically unified controller. However, centralizing control functionalities often introduces limitations that negatively impact the overall Quality of Service, particularly in distributed and heterogeneous network scenarios. In this paper, we explore an adaptive approach to orchestrate a microservice-based SDN controller dynamically at the Edge. Building upon our previously introduced frameworks for Microservice-based SDN Controller and for flexible service-model-aware orchestration, we investigate the benefits of adaptively deploying our microservice-based SDN controller’s functionalities at the Edge to enhance QoS. We leverage our orchestration framework to dynamically decide and execute the optimal placement of latency-critical microservices according to real-time monitoring data and evolving user demands. We evaluate the performance by comparing various deployment strategies, focusing on the tradeoff between control plane latency and placement of controller functionalities. Results demonstrate that our adaptive Edge deployment approach has the potential to reduces control plane latency, demonstrating the practical benefits of integrating SDN controller modularity with intelligent service orchestration in dynamic and heterogeneous network environments.

Air pollution, particularly fine particulate matter (PM2.5), poses significant environmental and public health risks in urban areas. In New York City (NYC), the dynamic nature of air pollution introduces both temporal and spatial complexities, making accurate forecasting a challenging task especially since the data is hyperlocal. Traditional machine learning and statistical models often fail to capture these complexities effectively, leading to poor predictive performance. Many existing deep learning models struggle with spatial variability and temporal inconsistencies, limiting their ability to provide robust PM2.5 predictions tailored to NYC’s unique urban landscape. To address these challenges, we propose an enhanced PM2.5 forecasting framework that integrates geohash encoding and geospatial joins to augment the dataset with additional geospatial features to make the models spatially aware and leverage linear interpolation with Simple Moving Average (SMA) to ensure temporal consistency. We then train 3 CNN-LSTM hybrid models inspired by ResNet, InceptionNet and EfficientNet and compare their performance to a Temporal Convolutional Network (TCN). CNNs excel at feature extraction, while LSTMs specialize in modeling temporal dependencies, making them well-suited for time-series forecasting. Additionally, TCNs provide an alternative temporal modeling approach with parallel processing advantages. Our approach enhances the ability to model both spatial heterogeneity and temporal dependencies, leading to more accurate and dependable PM2.5 forecasts for hyperlocal NYC. Experimental results demonstrate that the TCN model outperforms the other models, offering improved prediction accuracy and robustness against spatial and temporal variations. This study highlights the importance of integrating geospatial encoding and advanced deep learning architectures for air quality forecasting, paving the way for more effective urban pollution management strategies.

With the advancement of industrialization, air pollution has become a significant concern. This study presents a predictive analysis of PM2.5 in New York City using Long ShortTerm Memory (LSTM) neural networks to forecast pollution concentration levels. The key challenge is that the LSTM model lacks the spatial awareness needed for inference on a hyperlocal street level. To overcome this limitation, we enrich the dataset with additional geospatial features using geohash referencing and a geospatial join operation to capture PM2.5 patterns using features with varying spatial granularity. This enables the model to incorporate spatial context, shifting the problem from purely temporal to spatial temporal. We evaluated the models using several statistical metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), for the LSTM model, other machine learning (ML) models and networks, such as RNN, MLP, SVR, and LR. A comparison of the results indicates that the LSTM model with a geohash precision of 9 outperformed other models in predicting pollution levels.

The dynamic optimization of antenna tilt angles represents a critical challenge in 5 G networks, directly impacting coverage, capacity, and overall network performance. Traditional manual configuration approaches are becoming inadequate for managing the complexity of modern cellular networks. This paper explores the feasibility of automating 5 G antenna tilt angle optimization using Deep Deterministic Policy Gradient (DDPG) reinforcement learning and explainable AI (XAI) techniques. We train and evaluate a DDPG agent on a publicly available dataset from Kaggle, demonstrating the algorithm’s ability to learn effective tilt adjustment strategies. Counterfactual explanations provide transparency in the decision-making process, addressing the need for interpretable AI systems in critical infrastructure. This initial implementation, designed for eventual integration as an O-RAN compliant xApp, lays the groundwork for future development and experimental validation in simulated and real-world 5 G environments.

Kubernetes (K8S) is a widely used orchestration solution that helps manage complex IT applications by providing mechanisms for autoscaling, health checking, cluster formation, and replication, which are essential to deploy and manage the multitude of connected microservices. However, they may suffer in case of unexpected faults which can severely change the underlying computing infrastructure and lead to service outages, highlighting the need for resilient solutions capable of mitigating the adverse effects of faults. To address this, the TELKA sched-uler integrates Chaos Engineering (CE), Reinforcement Learning (RL), and Digital Twin (DT) to reallocate K8S pods evicted due to unexpected faults. While TELKA showed promising results in reallocating evicted pods, its preliminary implementations suffered from scalability issues, as the RL agent could only effectively operate on scenarios with the same number of nodes seen during training. To overcome this limitation, this paper improves TELKA by incorporating a neural network architecture called Deep Sets (DS), which can generalize the operation of TELKA on different numbers of nodes. Experimental results not only demonstrate the validity of the improved TELKA but also show how it can be used to identify good operating conditions.

The Software-Defined Networking (SDN) paradigm disaggregates the data plane, embodied by switches that only forward data, from the control plane, embodied by SDN controllers that communicate with said switches. SDN also proposes a third, application layer, which implements various functions such as firewalls or service discovery by communicating with the controllers through the northbound interface. However, while state-of-the-art works propose the deployment of multiple, distributed SDN controllers, the software architecture of these controllers is still monolithic, requiring not only the controller runtime but also all the network-level applications to be deployed across all SDN controller hardware. On the other hand, state-of-the-art SDN controllers such as MSN allow treating network-level applications as microservices, which comes with the challenge of orchestrating the microservices across the network. In this paper, we present Grex, a framework to orchestrate network-level applications across microservice-based SDN controllers. We test and validate the optimization model of Grex by performing experiments in a realistic network testbed using the MSN controller.

In recent years, Software-Defined Networking (SDN) research literature has proposed the integration of multiple SDN controllers into the same network, improving the scalability and reliability of the network. However, while this evolution has focused on control plane hardware, the architecture of SDN controller software is still monolithic, and its communication with the application plane through the northbound interface is done by the integration of the network-level applications' codebase with the controller software. The proposal of SDN Mi-croservices Architectures (SDN MSAs) is aimed at transforming the application plane, from a monolithic architecture to a set of independently deployable modules named SDN microservices. However, the promising paradigm of SDN MSAs also increases the complexity of network management, as these microservices must be placed through the SDN controllers. This placement is especially complex due to its NP-hard nature. In this work, we present Genetic Algorithm for SDN MSA (GASM), an evolutionary computation-based heuristic to solve this issue in tractable times. Experimental results show that GASM represents an average speed-up of 846.33 × compared to optimal solvers.

The softwarization of networks is increasingly spreading, and one of the main paradigms is SDN (Software-Defined Networking), which allows overcoming the limitations mainly arising from the integration of the control plane and the forwarding plane within the network devices. It extracts the control plane to place it within a new logically centralized component: the SDN controller. Since this is a monolithic architecture that limits reliability and scalability, distributed solutions based on microservices have been proposed in the literature. In parallel, Agents are fully intelligent, atomic, and autonomous decision-making units that can be flexibly recomposed to create a completely autonomous network system. They also have the ability to replicate single or multiple decision-making processes that collaborate with each other. The development of future networks such as 5G, including 6G, is pushing towards the concept of network management automation and integration of intelligence, making agents an excellent means to meet this trend. This paper first introduces intelligence in the form of agents to a distributed SDN controller based on microservices, by implementing two new functionalities: topology _learning and shortest path, Then, it leverages a microservices-based SDN solution based on Ryu SDN framework, named MSN, to run agents in a Docker Container environment. Multiple measurements were performed locally in a single machine. Results show the topology learning performances compared with several network topologies. Moreover, the shortest patti agent experimental evaluations show the knowledge size depends on the network topology and the performances of different algorithms.

Chaos engineering is the discipline of injecting computing and network faults, such as increased network latency and unavailability of computing nodes, into an IT system to help developers in identifying problems that could arise in a production environment and tackle them. Several tools have emerged to ease the application of chaos engineering to complex IT systems, leveraging microservice and container-based applications deployed on Kubernetes. However, applying of such tools requires several phases to be put into practice, from defining a steady state to establishing an effective response plan if something goes wrong. To ease the application of chaos engineering in improving the resilience of Kubernetes applications, this work presents a smart scheduler for Kubernetes called TELKA: a Twin-Enhanced Learning for Kubernetes Applications, which combines chaos engineering, Digital Twin (DT), and Reinforcement Learning (RL) methodologies to mitigate the effects of computing and network faults. Instead of interacting directly with the physical Kubernetes application, TELKA learns by interacting with a digital twin, thus reducing the learning time and the operation costs related to the application of chaos engineering. Experiment results compare TELKA with other approaches to show its effectiveness in mitigating the adverse effects of injected faults.

Microservice architecture is a service-oriented paradigm that enables the decomposition of cumbersome monolithic-based software systems. Using microservice design principles, it is possible to develop flexible, scalable, reusable, and loosely coupled software that could be containerized and deployed in a distributed edge/cloud environment. The flexible deployment of microservices in an edge environment increases system performance in terms due to dynamic service function placement and chaining possibly resulting in latency reduction, fault tolerance, scalability, efficient resource utilization, cost reduction, and energy consumption reduction. On the other hand, virtualization and containerization of microservices add processing and communication overheads. Therefore, to evaluate end-to-end microservices-based system performance, we need to have an end-to-end mathematical formulation of the overall microservice-based network system. Incorporating the virtualization overhead, here we provide end-to-end mathematical formulation considering system parameters: latency, throughput, computational resource usage, and energy consumption. We then evaluate the formulation in a testbed environment with the Microservice-based SDN (MSN) framework that decomposes the Software-defined Networking (SDN) controller in microservices with Docker Container. The final result validates the presented mathematical modeling of the system’s dynamic behavior which can be used to design a microservice-based system.

Kubernetes is a well-known orchestration and management solution for complex and large-scale service architectures in the Cloud Continuum. While it provides very valuable functions from the operation perspective, the high number of control loops it implements significantly enlarges the already wide space of configuration parameters and policies to consider for management purposes. We argue that optimizing complex Kubernetes deployments considering a multi-cloud and edge computing environment would significantly benefit from a Digital Twin approach, enabling an accurate virtual representation of a Kubernetes application to optimize its deployment and management policies. Towards that goal, this work illustrates the design of KubeTwin, a framework to implement Digital Twins of Kubernetes deployments. Furthermore, we present a validation of KubeTwin in a Multi-access Edge Computing (MEC) scenario, which shows its soundness in reenacting realistic Digital Twins of complex and highly distributed Kubernetes deployments. We believe that KubeTwin can provide useful guidance to the research community working in this field.

The use of microservice-based applications is becoming more prominent also in the telecommunication field. The current 5G core network, for instance, is already built around the concept of a “Service Based Architecture”, and it is foreseeable that 6G will push even further this concept to enable more flexible and pervasive deployments. However, the increasing complexity of future networks calls for sophisticated platforms that could help network providers with their deployments design. In this framework, a central research trend is the development of digital twins of the physical infrastructures. These digital representations should closely mimic the behavior of the managed system, allowing the operators to test new configurations, analyze what-if scenarios, or train their reinforcement learning algorithms in safe environments. Considering that Kubernetes is becoming the de-facto standard platform for container orchestration and microservice-based application lifecycle management, the implementation of a Kubernetes digital twin requires an accurate characterization of the microservice response time, possibly leveraging suitable Machine Learning techniques trained with measurement data collected in the field. In this paper we introduce a new methodology, based on Mixture Density Networks, to accurately estimate the statistical distribution of the response time of microservice-based applications. We show the improvement in performance with respect to simulation-based inference procedures proposed in literature.

The Software-Defined Networking (SDN) paradigm enables network administrators to manage the behavior of the network thanks to a centralized control plane. By programming network-level applications, it is possible to determine how traffic flows must be handled programmatically. In the same manner that computing applications have evolved from monolithic to microservice-based architectures, network-level applications are expected to evolve into microservice-based SDN controllers, implementing each application as a replicable and individually deployable component of the SDN controller. In such a scenario, the Quality of Service (QoS) experienced by traffic flows depends on how these microservices are placed and deployed through the network topology. In this work, we provide a system to optimize the QoS of the traffic in microservice-based SDN networks by optimally placing and replicating the network-level microservices. Experimental results show the effectiveness of the proposed solution over a real network topology with varying traffic loads.

Kubernetes provides several functions that can help service providers to deal with the management of complex container-based applications. However, most of these functions need a time-consuming and costly customization process to address service-specific requirements. The adoption of Digital Twin (DT) solutions can ease the configuration process by enabling the evaluation of multiple configurations and custom policies by means of simulation-based what-if scenario analysis. To facilitate this process, this paper proposes KubeTwin, a framework to enable the definition and evaluation of DTs of Kubernetes applications. Specifically, this work presents an innovative simulation-based inference approach to define accurate DT models for a Kubernetes environment. We experimentally validate the proposed solution by implementing a DT model of an image recognition application that we tested under different conditions to verify the accuracy of the DT model. The soundness of these results demonstrates the validity of the KubeTwin approach and calls for further investigation.

Edge computing aims at better supporting low-latency applications. One of its key techniques is computation offloading, the process that outsources computing tasks from resourced-constrained mobile devices and moves them to edge data centers. In this paper, we tackle an emerging problem within the umbrella of computation offloading, i.e., migration of offloaded inference tasks of Artificial Intelligence (AI) trained models. Such context tailors migration aspects of data-sensitive services where i) the value of the updates is inversely proportional to the data age and ii) outage is highly detrimental to accuracy. To tackle this challenge, we propose Mobile Edge Data-handoff (MED) a framework able to relocate inference or online training tasks from one edge datacenter to another by moving only the necessary data to minimize any accuracy drop during the process. We implemented MED in a well-known edge computing emulator, openLEON, and experimentally verified its performance with an AI-based Industry 4.0 application that forecasts the gas flow in a chemical plant. For our experiments, we use a real, open-source dataset that contains sensors readings. Collected results show that MED, employing proactive data handoff algorithms, is able to minimize the packet loss during the handoff thereby providing guarantees on the inference accuracy.

Fog computing emerged as a novel approach to deliver micro-services that support innovative applications.This paradigm is consistent with the modern approach to application development, that leverages the composition of small micro-services that can be combined to create value-added applications.These applications typically require the access from distributed data sources, such as sensors located in multiple geographic locations or mobile users.In such scenarios, the traditional cloud approach is not suitable because latency constraints may not be compatible with having time-critical computations occurring on a far away data-center; furthermore, the amount of data to exchange may cause high costs imposed by the cloud pricing model.A layer of fog nodes close to application consumers can host pre-processing and data aggregation tasks that can reduce the response time of latency-sensitive elaboration as well as the traffic to the cloud data-centers.However, the problem of smartly placing micro-services over fog nodes that can fulfill Service Level Agreements is far more complex than in the more controlled scenario of cloud computing, due to the heterogeneity of fog infrastructures in terms of performance of both the computing nodes and inter-node connectivity.In this paper, we tackle such problem proposing a mathematical model for the performance of complex applications deployed on a fog infrastructure.We adapt the proposed model to be used in a genetic algorithm to achieve optimized deployment decisions about the placement of micro-services chains.Our experiments prove the viability of our proposal with respect to meeting the SLA requirements in a wide set of operating conditions.

Nowadays, Machine learning (ML) plays a significant role in Industrial Analytics. It enables predictive analytics, and helps uncovering essential insights to transform industries. As a result, real-time data analytics has become an essential requirement for industrial engineering jobs. Edge computing enables local intelligence and real-time analytics that are key for industry processes to take autonomous decisions locally at the edge of the network. However, outages in edge datacenters can jeopardize the whole plant security. In this paper, we proposed a practical approach to effectively handling service and data migration of ML-based applications in Industrial Analytics scenarios in the presence of a lack of computing resources at the edge. We argue that in this context the value of data is inversely proportional to their age and is very important to work with fresher data. In this paper, we describe our architectural approach for service and data handoff and show a predictive diagnostics case study deployed in an edge-enabled IIoT infrastructure. We evaluate our proposed approach in terms of drop of accuracy in a well-known edge computing emulator, i.e., openLEON. The experimental results show the benefit of our solution with respect to standard techniques.

The Multi-access Edge Computing (MEC) enables a new layer of edge middleboxes, acting as local proxies with virtualized resources deployed at edge localities. To support scalable, low-latency, and locally managed service provisioning, MEC relies on computation offloading, the process that outsources computing tasks from resourced constrained mobile devices and moves it to edge data centers. In this paper, we tackle a specific sub-problem within the umbrella of computation offloading. We argue that it is convenient to migrate a service because of the lack of computing resources in the anchor edge data center even if a device, such as industrial IoT devices, is not moving. In this paper, we extensively evaluate the efficiency of data and service handoff protocols. Specifically, we thoroughly assess protocols, that we designed in our past work, in a well-known edge computing emulator, i.e., openLEON. These protocols migrate data and service either in a reactive fashion, i.e., upon realizing of resource exhaustion, or proactively, i.e., beforehand to swiftly minimize the downtime. We experimentally verify their performance for a typical MEC use case, i.e., video. Our results show that by being proactive, the service interruption downtime reduces by a factor of 4 times.

Edge Computing is becoming more and more essential for the Industrial Internet of Things (IIoT) for data acquisition from shop floors. The shifting from central (cloud) to distributed (edge nodes) approaches will enhance the capabilities of handling real-time big data from IoT. Furthermore, these paradigms allow moving storage and network resources at the edge of the network closer to IoT devices, thus ensuring low latency, high bandwidth, and location-based awareness. This research aims at developing a reference architecture for data collecting, smart processing, and manufacturing control system in an IIoT environment. In particular, our architecture supports data analytics and Artificial Intelligence (AI) techniques, in particular decentralized and distributed hybrid twins, at the edge of the network. In addition, we claim the possibility to have distributed Machine Learning (ML) by enabling edge devices to learn local ML models and to store them at the edge. Furthermore, edges have the possibility of improving the global model (stored at the cloud) by sending the reinforced local models (stored in different shop floors) towards the cloud. In this paper, we describe our architectural proposal and show a predictive diagnostics case study deployed in an edge-enabled IIoT infrastructure. Reported experimental results show the potential advantages of using the proposed approach for dynamic model reinforcement by using real-time data from IoT instead of using an offline approach at the cloud infrastructure.

Nowadays, the massive usage of mobile and IoT applications generate large amounts of data. Due to several reasons, including latency and bandwidth, it is not practical to send all generated data to the cloud. Recent standardization efforts, namely, Fog computing and the Multi-access Edge Computing (MEC), provide an extension of Cloud computing storage and network resources placed in a geographically distributed manner at the edge of the network closer to mobiles and IoT devices. These paradigms allow low latency, high bandwidth, and location-based awareness. In this paper, we present an infrastructure to support distributed Machine Learning (ML) by enabling edge devices to collaboratively learn a shared model while keeping local knowledge stored at the edge of the network. In addition, we claim the possibility of improving the model through the cloud that acts as a supervisor of the system that contains the global knowledge of the entire system through the integration of local edge models. We describe our architectural proposal and analyze a case study, namely video streaming processing for face recognition, deployed in a collaborative edge network. Finally, we report experimental results that show the potential advantages of using our approach instead of ML algorithms completely expected at the cloud infrastructure.

Smart factory management is going through a remarkable change, in terms of quality and diversity of services provided to customers. The companies that produce manufacturing machines now can follow the products throughout the production chain, from the project to the deployment in real scenarios. Industry 4.0 is pushing this trend forward, demanding for servitization of products and machines, mainly for the manufacturing sector where human and production machine are in strict collaboration. The data produced by the machines must be processed quickly to allow the implementation of reactive services such as predictive maintenance and remote control, always taking care of the safety of nearby people. This paper proposes a multilayer architecture to tackle the main issues in monitoring legacy manufacturing machines and to provide general guidelines to solve them. We derived some guidelines from a real Industry 4.0 transition experiment performed together with the company technical departments to accomplish an efficient system for monitoring and servitization of manufacturing machines, with a scalable platform that confirms its usefulness in many production facilities with different needs.

Computation offloading is employed by mobile apps running over resource-constrained devices to leverage the cloud in overcoming their resource limits. The advent of the Multi-access Edge Computing (MEC) paradigm further extends the potential opportunities of mobile-cloud offloading, allowing new service provisioning scenarios, such as mobile gaming and multimedia, where responsiveness of mobile devices at the network edge significantly benefits from low latency interactions. However, state-of-the-art offloading platforms for MEC architectures have not addressed the technical challenge of supporting specific file systems for this MEC-enabled class of applications, with components running at three hosting environments, i.e., mobile, edge, and cloud. This paper proposes the Mobile Edge File System (MEFS), an application-level distributed file system designed to be highly resilient and able to efficiently maintain consistency among the mobile, edge, and cloud entities. MEFS supports application handoff through live migration as end devices move between edges. The cloud transparently helps with recovery from faulty edge nodes or in the case of unavailability of edges in the user's proximity. We implemented a MEFS prototype in Android along with MEFS-based MEC-enabled mobile apps. The experimental results show how MEFS can achieve low latency and low overhead.