Gaetano Volpe

AI-native, programmable, and disaggregated 6G networks will be highly dynamic and distributed, demanding tools that can explain, predict, and safely optimize behavior across the edge–cloud continuum. Network Digital Twins (NDTs) promise this capability, yet current efforts in research and industry are fragmented and lack widely accepted formal definitions and architectural guidelines. This paper proposes a structured framework for NDTs in 6G, addressing these gaps by refining the conceptual foundations of NDTs, introducing a functional architecture, inherited from the 6G-TWIN EU consortium, and clarifying key components such as AI-driven workflows, the place of simulation, data management, and orchestration. Concrete examples illustrate how these components enable network automation, optimization, and predictive analytics. The paper proceeds by reviewing related work and standardization efforts, specifying functional and non-functional requirements, presenting the architecture and its various domains, and detailing lifecycle management across cloud to edge. We then report early implementations and evaluation results, and discuss security, privacy, and governance considerations, concluding with directions for validation and uptake. The key objective is to offer a cohesive reference model that guides the community in shaping NDT development, ensuring interoperability, scalability, adaptability, and seamless integration into AI-native 6G networks for improved intelligence and efficiency.

Efficient traffic management in high-density urban areas remains a critical challenge, particularly at highway entry ramps and merging points where congestion, sudden braking, and collision risks frequently occur. This chapter addresses the problem of coordinating vehicles entering ramps and intersections by formulating it as an optimization task aimed at minimizing delays, enhancing safety, and improving overall flow. To tackle this challenge, we propose a deep reinforcement learning approach based on the actor–critic framework, where intelligent traffic light agents are trained to dynamically manage vehicle entries. The design of the reward function plays a central role, as it balances safety and efficiency by penalizing excessive braking events while encouraging smooth traffic throughput. Simulations were conducted in a representative high-density traffic scenario located in Bologna, Italy. The results demonstrate that the proposed approach can significantly reduce congestion, lower waiting times, and increase safety margins compared with conventional management strategies. These findings highlight the potential of reinforcement learning techniques to support intelligent traffic control systems and provide a promising direction for future deployment in real-world urban and highway infrastructures.

The recent need of supporting the diffusion of electric mobility around the world to progressively substitute petrol transport means, leads to the development of new hardware and software technologies to make even more convenient the use of electric vehicles (EVs). High purchasing costs and long recharging times are two major factors slowing this transition. In addition, from the end users perspective, using EV in long distance journeys is still not convenient despite the increasing diffusion of fast charging infrastructures. In this context, to facilitate traveling with EVs in long distance trips, this paper proposes a trip planner prototype based on Deep Reinforcement Learning (DRL). The trip planner prototype has the goal to suggest to the drivers the best charge stops to be performed during the trip according to the user needs and preferences. Charging stops are optimized, using the available Charging Points (CPs) along the route from origin to destination, and are shown to the user on a map taking into account important information like the EV State of Charge (SoC), the cruise velocity, and the presence of point of interest (e.g. restaurant, hotel, shops, etc.) close around. The trip plan can be done according to three objectives: minimizing the travel time, minimizing the charging costs, optimizing travel time and cost. The proposed DRL approach is compared against Genetic Algorithm (GA), heuristic, and optimization approaches considering a real-world EV trip.

Intrusion Detection Systems (IDSs) are a crucial component of modern corporate firewalls. The ability of IDS to identify malicious traffic is a powerful tool to prevent potential attacks and keep a corporate network secure. In this context, Machine Learning (ML)-based methods have proven to be very effective for attack identification. However, traditional approaches are not always applicable in a real-time environment as they do not integrate concrete traffic management after a malicious packet pattern has been identified. In this paper, a novel combined approach to both identify and discard potential malicious traffic in a real-time fashion is proposed. In detail, a Long Short-Term Memory (LSTM) supervised artificial neural network model is provided in which consecutive packet groups are considered as they flow through the corporate network. Moreover, the whole IDS architecture is modeled by a Petri Net (PN) that either blocks or allows packet flow throughout the network based on the LSTM model output. The novel hybrid approach combining LSTM with Petri Nets achieves a 99.71% detection accuracy—a notable improvement over traditional LSTM-only methods, which averaged around 97%. The LSTM–Petri Net approach is an innovative solution combining machine learning with formal network modeling for enhanced threat detection, offering improved accuracy and real-time adaptability to meet the rapid security needs of virtual environments and CPS. Moreover, the approach emphasizes the innovative role of the Intrusion Detection System (IDS) and Intrusion Prevention System (IPS) as a form of “virtual sensing technology” applied to advanced network security. An extensive case study with promising results is provided by training the model with the popular IDS 2018 dataset.

This paper introduces an innovative approach to designing a user-based Heating, Ventilation, and Air-Conditioning (HVAC) system management connected with the District Energy Management System. By classifying the users into dynamic energy consumption classes to reward energy efficiency and penalize excessive use, users can modify their behavior to pass to a less expensive and more virtuous consumption class. To this aim, a blockchain platform determines the rewards and penalties and, by a K-means clustering algorithm, categorizes users into respective groups. Then, a Class Follower Problem is formulated and solved by a Model Predictive Control (MPC) strategy integrated with a Long Short-Term Memory network as a predictive model. If the users follow the suggestions proposed by the controller, i.e., the thermostat set-points and the time intervals in which the HVAC system must be switched off or on, the users can be located in a more virtuous consumption class. A case study conducted within an energy district in Bari (Italy) shows how the proposed architectural framework tuned thermal regulation in intelligent buildings while concurrently achieving energy optimization. Note to Practitioners —This paper addresses the challenge of efficiently managing HVAC systems in smart districts through a novel blockchain-based framework and an optimization strategy solved by an MPC approach. The objective is to incentivize users to optimize their energy consumption by introducing dynamic Consumption Classes that reward energy efficiency and penalize inefficient utilization. For practitioners, this strategy translates to a granular level of energy management that not only adapts to individual behaviors but also aligns with broader sustainability goals. Integrating the blockchain platform ensures a transparent and secure method for managing and recording energy usage. At the same time, adopting MPC with Long Short-Term Memory Networks offers accurate forecasts and adjustments to enhance system responsiveness. Although the study focuses on HVAC systems, the principles may be extended to other energy-intensive applications, providing a comprehensive tool for energy management and user engagement in smart cities. Future research could integrate renewable energy sources and explore the implications of user-driven adjustments on the overall energy distribution and efficiency.

With the advent of Industry 4.0, the demand of high computing power for tasks such as data mining, 3D rendering, file conversion and cryptography is continuously growing. To this extent, distributed and decentralized environments play a fundamental role by dramatically increasing the amount of available resources. However, there are still several issues in the existing resource sharing solutions, such as the uncertainty of task running time, the renting price and the security of transactions. In this work, we present a blockchain-enabled task assignment platform by performance prediction based on Hyperledger Fabric, an open-source solution for private and permissioned blockchains in enterprise contexts that outperforms other technologies in terms of modularity, security and performance. We propose a model-free deep reinforcement learning framework to predict task runtime in agents current load state while the agent is engaged in multiple concurrent tasks. In addition, we let clients choose between prediction accuracy and price saving on each request. This way, we implicitly give inaccurate agents a chance to get assignments by competing in price rather than in time, allowing them to collect new experiences and improve future predictions. We conduct extensive experiments to evaluate the performance of the proposed scheme.