The rapid evolution of telecommunication networks is leading to increasingly complex systems, requiring adaptive, flexible, and intelligent mechanisms for resource management, orchestration, and access control. In this context, the Network Digital Twin (NDT) paradigm emerges as a powerful tool to model the behavior of devices, communication links, operating environments, and applications in complex networks. This paper introduces FALCON, a Digital-Twin-based orchestration framework designed to optimize horizontal offloading in UAV-based Flying Ad Hoc Networks (FANETs) providing edge computing services to ground devices in remote areas. FALCON integrates multiple Smart Agents (DQN, A2C, PPO) running concurrently on the Digital Twin to dynamically determine the optimal offloading probabilities. A proof-of-concept demonstrates how the framework performs real-time What-if Scenario analyses and adapts to varying workload and channel conditions. Numerical results highlight the gains achieved through coordinated model selection and reuse, showing reduced end-to-end delay and faster convergence compared to standalone DRL-based controllers. • Digital Twin framework for real-time FANET orchestration. • Parallel Smart Agents enable fast What-if scenario evaluation. • Dynamic model selection adapts to FANET state and intents. • Reduced service delay compared to standalone DRL methods. • Model reuse ensures rapid reaction to changing UAV conditions.

Cloud gaming is a rapidly growing domain that requires low-latency and high-responsiveness architectures to deliver an engaging user experience. This paper presents an innovative Digital Twin (DT)-based framework designed to mitigate the effects of variable network conditions on video streaming and input responsiveness. The proposed architecture integrates Console and User Equipment DTs, which synchronize video streams and user inputs using lightweight RTSP and MQTTbased communication, ensuring real-time interaction even in challenging network scenarios. To validate the framework, we developed a custom cloud gaming application simulating a shark-and-fish pursuit game. This use case allows for precise evaluation of system performance under varying latency and delay conditions. Experimental results demonstrate the architecture’s ability to maintain game responsiveness, revealing critical delay thresholds and highlighting the impact of delay variability on user performance. These findings illustrate the potential of DTbased architectures to enhance the robustness and fairness of cloud gaming systems.

Virtual Reality (VR) and Augmented Reality (AR) are revolutionizing immersive 360° video experiences across education, entertainment, and cultural exploration. This paper introduces a Smart Video Encoder (SVE) system, comprising server- and user-side Virtual Network Functions (VNFs), for adaptive compression and transmission of 360° video streams over 5G/6G networks. Leveraging a Supervised Machine Learning (SML) Video Analyzer, the system enhances user-perceived quality by prioritizing key regions, such as artistic content. Using hierarchical tile-based compression, the SVE adjusts compression dynamically based on real-time user behavior and video content. Results show its effectiveness in maintaining high-quality experiences under bandwidth constraints, particularly for applications like virtual museum tours.

Virtual reality (VR) cloud gaming faces significant challenges in terms of latency and bandwidth consumption, particularly in softwarized 5 G and beyond (5G&B) networks. Ensuring an immersive experience on low-end devices, such as smartphones and cardboard-like headsets, requires innovative solutions to mitigate delay effects and optimize resource usage. This research focuses on enhancing VR cloud gaming performance by leveraging Digital Twins (DTs) and hierarchical compression techniques. The proposed system adopts a client-server architecture, where computationally intensive tasks are offloaded to the server, minimizing processing requirements on the client side. A key contribution is a novel delay estimation and management framework that employs DTs to synchronize video streaming and user input, reducing the impact of latency. Additionally, viewport-based hierarchical compression is applied to optimize bandwidth consumption while maintaining high perceived quality. The proposed architecture is evaluated through extensive experiments analyzing the effects of input delay, delay fluctuations, and compression methods on user performance and perceived quality. Results demonstrate that the system effectively mitigates adverse network conditions, ensuring a seamless and immersive VR gaming experience even in suboptimal environments.

The entertainment and gaming industries continue to evolve, so they are becoming increasingly reliant on advanced network capabilities to deliver immersive, real-time experiences. In-network computing (INC) is a transformative paradigm in the design of the network architecture in 6G networks. It facilitates the offloading of computational tasks from devices to edge nodes and central servers, enabling faster data processing in network nodes and reducing latency and response times for high-demand applications, enhancing efficiency. This way, it will be possible to provide the final users with advanced applications like Augmented Reality (AR) and Virtual Reality (VR). In this paper we introduce a 6G Network Infrastructure testbed designed for application execution and testing, supporting INC, and we present an Adaptive 360° Video Streaming service using INC facilities. The testbed has been designed to represent a vertical application for SLICES-RI and SUNRISE-6G projects. Some numerical results will assesses the performance of this dynamic video streaming system.

In the last few years, Virtual Reality (VR) is assuming a prominent role and is recognized as a pivotal technology in various sectors. However, transmission of immersive videos produced by real-time 360° cameras or stored on remote servers to reproduce 3D environments, or streamed by video games accessible through headsets, would require a lot of network bandwidth that, in many cases, is not available or too expensive to be obtained. In this paper, we leverage on network softwarization provided by new 5G&B networks, and introduce an Adaptive Closed-loop Encoding VNF named 360-ST for adaptive compression of 360° video streaming. This VNF is able to apply a hierarchical compression that takes into account both the bandwidth currently available in the network, and the user viewport. The agent that is in charge of deciding the different compression ratio at runtime uses Deep Reinforcement Learning to optimize a reward function and adapt to the changes of the network bandwidth, the end-to-end latency, the user movements within the scene and the video content. The results indicate that our proposed method consistently outperforms state-of-the-art algorithms by an average of 8% to 46% in terms of achieved Peak Signal-to-Noise Ratio (PSNR).

The contention window (CW) has a significant impact on the efficiency of Wi-Fi networks. Unfortunately, the basic access method employed by 802.11 networks does not scale well for increasing number of stations. Therefore, in this paper we propose a new CW control method which leverages Deep Reinforcement Learning (DRL) to learn the optimal policies under different network conditions. For this reason, we propose the Online Smart Collision Avoidance Reinforcement learning (OSCAR) algorithm, a DRL-based algorithm that can be deployed online to quickly and efficiently find the best contention window that maximizes the throughput. We also demonstrate through a simulation campaign that it is able to learn the optimal policies way faster than the current state of art methods while also being able to keep the computational cost low.

1 The evolution of smart objects towards the Internet of Softwarized Things (IoST) in 6G networks will provide the society with dynamic and programmable systems of interconnected smart devices interacting with little to no human intervention. One pivotal aspect of this evolution is represented by edge learning, which brings machine-learning algorithms at the network edge to achieve massive connectivity, ultra-low latency, energy efficiency, security and privacy. Unfortunately, in many application scenarios commonly envisioned for 6G, edge learning is not feasible neither locally in the smart objects, due to their computation and energy limitations, nor by servers at the edge of the cabled network, because not connected with adequate powerful links. To this purpose, this paper proposes ODEL, an On-Demand Edge-Learning framework that uses a Flying Ad-hoc NETwork (FANET) to bring computing and networking facilities on-site for edge learning. ODEL is based on a marketplace employing a non-cooperative game theoretic approach: UAVs are provided by different third-party providers in exchange of some economic gain. A non-linear optimization problem is formulated in order to determine the optimal distribution of flows that maximizes revenue for each UAV provider, and is solved by means of the Variational Inequality (VI) theory.

Recently, Flying Ad Hoc Networks (FANET) have been proposed to empower 5G networks to support complex missions and provide ubiquitous connectivity to heterogeneous devices. However, it is needed to cope with the limited UAV capabilities (e.g., limited available energy to supply engines and computing elements, limited computing capabilities), as well as with the need to provide network and application services as foreseen in highly dynamic and time varying 5G ecosystems. This paper presents for the first time a comprehensive framework that integrates a FANET with a 5G network, with the aim of providing services that can be even chained with each other. This model is comprehensive in the sense that it takes into account physical constraints of the devices, as well as features and requirements of traffic flows. For this framework, the paper proposes a mathematical optimization model, allowing Virtual Function (VF) placement and chaining, aimed at minimizing energy consumption and service unsatisfaction probabilities of the FANET as a whole without employing heuristics for the solution of the problem. Two placement strategies named MLP and WMP are introduced and compared with the standard placement strategy named NoShP. An extensive numerical analysis shows that MLP and WMP allow us to well catch network dynamics and to reduce the number of virtual functions needed while decreasing the power consumption, so increasing UAV flight time and network lifetime.

The next generation of wireless communications networks, namely 6G, will be aimed at realizing a fully connected world, and at providing ubiquitous connectivity to people and objects even in remote areas that are very far from the structured Internet core network. These goals include the definition and the design of intelligent communications environments mainly characterized by pervasive artificial intelligence and large-scale automation. The target of this paper is the design of a management framework for edge networks realized with Flying Ad-Hoc Networks (FANET) consisting of a set of Unmanned Aerial Vehicles (UAVs) to provide a remote geographic area with computing and networking facilities for delay-sensitive applications. To this purpose, each UAV is equipped with a Computing Element (CE) to process jobs received through vertical offloading from ground devices. In addition, horizontal offload among UAVs of the FANET is introduced for load balancing purposes, to guarantee that the FANET computation delay for each received job is minimized and is almost independent of the activity state of the area covered by the UAV receiving that job. The proposed FANET management framework is based on Deep Reinforcement Learning (DRL) to allow zero-touch adaptation to the time-variant activity state of the area covered by each UAV. Numerical results demonstrate the power of the proposed framework and the enhancements achieved with respect to the current literature.

The fifth generation (5G) of mobile networks has the goal of providing ultra-high-speed access everywhere and enabling connectivity of massive number of devices in an ultra-reliable and affordable way. However, in many environments that are considered strategic for 5G applications, a structured network is not available. A solution to extend the features provided by Multi-access Edge Computing (MEC), one of the main enabler of 5G, in these contexts, is to use fleets of MEC UAVs, each equipped with a computing element (CE), and organized in Flying Ad-hoc Networks (FANET).In this paper, we propose a FANET platform with “horizontal” offload from the most overloaded UAVs to the least overloaded ones, aimed at balancing load among UAVs. A decision policy called UAV Smart Offloading (USO), based on Deep Reinforcement Learning, is also defined to optimize performance in terms of delay perceived by the ground devices connected to the FANET. A numerical analysis is introduced to evaluate performance achieved by the proposed platform.

Network slices for delay-constrained applications in 5G systems require computing facilities at the edge of the network to guarantee ultra-low latency in processing data flows generated by connected devices, which is challenging with larger volumes of data, and larger distances to the edge of the network. To address this challenge, we propose to extend 5G network slices with Unmanned Aerial Vehicles (UAV) equipped with multi-access edge computing (MEC) facilities. However, onboard computing elements (CE) consume UAV's battery power thus impacting its flight duration. We propose a framework where a System Controller (SC) can turn on and off UAV's CEs, with the possibility of offloading jobs to other UAVs, to maximize an objective function defined in terms of power consumption, job loss, and incurred delay. Management of this framework is achieved by reinforcement learning. A Markov model of the system is introduced to enable reinforcement learning and provide guidelines for the selection of system parameters. A use case is considered to demonstrate the gain achieved by the proposed framework and discuss numerical results.

Internet of Things (IoT) has emerged as a huge paradigm shift by connecting a versatile and massive collection of smart objects to the Internet, coming to play an important role in our daily lives. Data produced by IoT devices can generate a number of computational tasks that cannot be executed locally on the IoT devices. The most common solution is offloading these tasks to external devices with higher computational and storage capabilities, usually provided by centralized servers in remote clouds or on the edge by using the fog computing paradigm. Nevertheless, in some IoT scenarios there are remote or challenging areas where it is difficult to connect an IoT network to a fog platform with appropriate links, especially if IoT devices produce a lot of data that require processing in real-time. To this purpose, in this article, we propose to use unmanned aerial vehicles (UAVs) as fog nodes. Although this idea is not new, this is the first work that considers power consumption of the computing element installed on board UAVs, which is crucial, since it may influence flight mission duration. A System Controller (SC) is in charge of deciding the number of active CPUs at runtime by maximizing an objective function weighing power consumption, job loss probability, and processing latency. Reinforcement Learning (RL) is used to support SC in its decisions. A numerical analysis is carried out in a use case to show how to use the model introduced in the article to decide the computation power of the computing element in terms of number of available CPUs and CPU clock speed, and evaluate the achieved performance gain of the proposed framework.