This paper presents an adaptive framework for edge inference based on a dynamically configurable transformer-powered deep joint source channel coding (DJSCC) architecture. Motivated by a practical scenario where a resource constrained edge device engages in goal oriented semantic communication, such as selectively transmitting essential features for object detection to an edge server, our approach enables efficient task aware data transmission under varying bandwidth and channel conditions. To achieve this, input data is tokenized into compact high level semantic representations, refined by a transformer, and transmitted over noisy wireless channels. As part of the DJSCC pipeline, we employ a semantic token selection mechanism that adaptively compresses informative features into a user specified number of tokens per sample. These tokens are then further compressed through the JSCC module, enabling a flexible token communication strategy that adjusts both the number of transmitted tokens and their embedding dimensions. We incorporate a resource allocation algorithm based on Lyapunov stochastic optimization to enhance robustness under dynamic network conditions, effectively balancing compression efficiency and task performance. Experimental results demonstrate that our system consistently outperforms existing baselines, highlighting its potential as a strong foundation for AI native semantic communication in edge intelligence applications.

Network Digital Twins represent a key technology in future networks, expected to provide the capability to perform accurate analysis and predictions about the behaviour of 6G mobile networks. However, despite the availability of several theoretical works on the subject, still very few examples of actual implementations of Network Digital Twin are available. This paper provides a detailed description about the characteristics of Network Digital Twin and provides a practical example about real deployment of the technology. The considered network infrastructure is a real 5G private network running in a lab. The Network Digital Twin is built based on open source network emulation software and is available to the community as open source. Measurements on both the physical infrastructure and the related Digital Twin demonstrate a high accuracy in reproducing the state and behavior of the actual 5G system.

This paper investigates a cell-free massive MIMO (multiple-input multiple-output) system where distributed access points (APs) perform integrated sensing and communications (ISAC) tasks, enabling simultaneous user communication and target detection/tracking. A unified framework and signal model are developed for the detection of potential targets and tracking of previously detected ones, even in arbitrary positions. Leveraging the Generalized Likelihood Ratio Test technique, novel detection/tracking algorithms are proposed to handle unknown target responses and interference. Scalable AP-user and AP-target association rules are evaluated, explicitly considering multi-zone sensing scenarios. Additionally, a scalable power control mechanism extends fractional power control principles to ISAC, balancing power allocation between communication and sensing tasks. For benchmarking, a non-scalable power control optimization problem is also formulated to maximize the minimum user data rate while ensuring a Quality of Service constraint for sensing, solved via successive convex approximation. Extensive numerical results validate the proposed framework, demonstrating its effectiveness in both communication and sensing, revealing the impact of interference from other targets, and highlighting fundamental trade-offs between sensing and communication performance.

This study addresses the challenge of access point (AP) and user equipment (UE) association in cell-free massive MIMO networks. It introduces a deep learning algorithm leveraging Bidirectional Long Short-Term Memory cells and a hybrid probabilistic methodology for weight updating. This approach enhances scalability by adapting to variations in the number of UEs without requiring retraining. Additionally, the study presents a training methodology that improves scalability not only with respect to the number of UEs but also to the number of APs. Furthermore, a variant of the proposed AP-UE algorithm ensures robustness against pilot contamination effects, a critical issue arising from pilot reuse in channel estimation. Extensive numerical results validate the effectiveness and adaptability of the proposed methods, demonstrating their superiority over widely used heuristic alternatives.

This paper proposes a novel communication-efficient Split Learning (SL) framework, named Attention-based Double Compression (ADC), which reduces the communication overhead required for transmitting intermediate Vision Transformers activations during the SL training process. ADC incorporates two parallel compression strategies. The first one merges samples' activations that are similar, based on the average attention score calculated in the last client layer; this strategy is class-agnostic, meaning that it can also merge samples having different classes, without losing generalization ability nor decreasing final results. The second strategy follows the first and discards the least meaningful tokens, further reducing the communication cost. Combining these strategies not only allows for sending less during the forward pass, but also the gradients are naturally compressed, allowing the whole model to be trained without additional tuning or approximations of the gradients. Simulation results demonstrate that Attention-based Double Compression outperforms state-of-the-art SL frameworks by significantly reducing communication overheads while maintaining high accuracy.

In this paper, we propose a novel design for AI-native goal-oriented communications, exploiting transformer neural networks under dynamic inference constraints on bandwidth and computation. Transformers have become the standard architecture for pretraining large-scale vision and text models, and preliminary results have shown promising performance also in deep joint source-channel coding (JSCC). Here, we consider a dynamic model where communication happens over a channel with variable latency and bandwidth constraints. Leveraging recent works on conditional computation, we exploit the structure of the transformer blocks and the multihead attention operator to design a trainable semantic token selection mechanism that learns to select relevant tokens (e.g., image patches) from the input signal. This is done dynamically, on a per-input basis, with a rate that can be chosen as an additional input by the user. We show that our model improves over state-of-the-art token selection mechanisms, exhibiting high accuracy for a wide range of latency and bandwidth constraints, without the need for deploying multiple architectures tailored to each constraint. Last, but not least, the proposed token selection mechanism helps extract powerful semantics that are easy to understand and explain, paving the way for interpretable-by-design models for the next generation of AI-native communication systems.

As the standardization of 5G is being solidified, researchers are speculating what 6G will be. Integrating sensing functionality is emerging as a key feature of the 6G Radio Access Network (RAN), allowing to exploit the dense cell infrastructure of 5G for constructing a perceptive network. In this paper, we provide a comprehensive overview on the background, range of key applications and state-of-the-art approaches of Integrated Sensing and Communications (ISAC). We commence by discussing the interplay between sensing and communications (S&C) from a historical point of view, and then consider multiple facets of ISAC and its performance gains. By introducing both ongoing and potential use cases, we shed light on industrial progress and standardization activities related to ISAC. We analyze a number of performance tradeoffs between S&C, spanning from information theoretical limits, tradeoffs in physical layer performance, to the tradeoff in cross-layer designs. Next, we discuss signal processing aspects of ISAC, namely ISAC waveform design and receive signal processing. As a step further, we provide our vision on the deeper integration between S&C within the framework of perceptive networks, where the two functionalities are expected to mutually assist each other, i.e., communication-assisted sensing and sensing-assisted communications. Finally, we summarize the paper by identifying the potential integration between ISAC and other emerging communication technologies, and their positive impact on the future of wireless networks.

The Internet of Drones (IoD) is a networking architecture that stems from the interplay between Unmanned Aerial Vehicles (UAVs) and wireless communication technologies. Networked drones can unleash disruptive scenarios in many application domains. At the same time, to really capitalize their potential, accurate modeling techniques are required to catch the fine details that characterize the features and limitations of UAVs, wireless communications, and networking protocols. To this end, the present contribution proposes the Internet of Drones Simulator (IoD-Sim), a comprehensive and versatile open source tool that addresses the many facets of the IoD. IoD-Sim is a Network Simulator 3 (ns-3)-based simulator organized in a 3-layer stack, composed by (i) the Underlying Platform, which provides the telecommunication primitives for different standardized protocol stacks, (ii) the Core, that implements all the fundamental features of an IoD scenario, and (iii) the Simulation Development Platform, mainly composed by a set of tools that speeds up the graphical design for every possible use-case. In order to prove the huge potential of this proposal, three different scenarios are presented and analyzed from both a software perspective and a telecommunication standpoint. The peculiarities of this open-source tool are of interest for researchers in academia, as they will be able to extend to model upcoming specifications, including, but not limited to, mobile networks and satellite communications. Still, it will certainly be of relevance in industry to accelerate the design phase, thus improving the time-to-market of IoD-based services.

In this paper we evaluated the performance of a reconfigurable intelligent surface tested with a fifth generation signal provided by a commercial fifth generation base station. We adopted a reverberation chamber as a real life propagating environment. Tests were conducted at the millimeter wave frequency range. This measurement campaign was carried out under the H2020 European project RISE-6G and a collaboration program between TIM S.p.A., Nokia and Universit\`a Politecnica delle Marche.

Fleets of autonomous vehicles (AV) often are at the core of intelligent transportation scenarios for smart cities, and may require a wireless Internet connection to offload computer vision tasks to data centers located either in the edge or the cloud section of the network. Cooperation among AVs is successful when the environment is unknown, or changes dynamically, so as to improve coverage and trip time, and minimize the traveled distance. The AVs, while mapping the environment with range-based sensors, move across the wireless coverage areas, with consequences on the achieved access bit rate, latency, and handover rate. In this paper, we propose to modify the cost of path planning algorithms such as Dijkstra and A*, so that not only the traveled distance is considered in the best path solution, but also the radio coverage experience. To this aim, several radio-related cost-weighting functions are introduced and tested, to assess the performance of the proposed techniques with extensive simulations. The proposed mapping algorithm can achieve a mapping error probability below 2%, while the proposed path-planning algorithms extend the experienced radio coverage of the AVs, with limited distance increase with respect to shortest-path existing methods, such as conventional Dijkstra and A* algorithms.

This paper tackles the problem of designing proper uplink multiple access (MA) schemes for coexistence between enhanced mobile broadband+ (eMBB+) users and massive machine-type communications+ (mMTC+) devices in a terminal-centric cell-free massive MIMO system. Specifically, the use of a time-frequency spreading technique for the mMTC+ devices has been proposed. Coupled with the assumption of imperfect channel knowledge, closed-form bounds of the achievable (ergodic) rate for the two types of data services are derived. Using suitable power control mechanisms, we show it is possible to efficiently multiplex eMBB+ and mMTC+ traffic in the same time-frequency resource grid. Numerical experiments reveal interesting trade-offs in the selection of the spreading gain and the number of serving access points within the system. Results also demonstrate that the performance of the mMTC+ devices is slightly affected by the presence of the eMBB+ users. Overall, our approach can endow good quality of service to both 6G cornerstones at once.

Deep Neural Network (DNN) splitting is one of the key enablers of edge Artificial Intelligence (AI), as it allows end users to pre-process data and offload part of the computational burden to nearby Edge Cloud Servers (ECSs). This opens new opportunities and degrees of freedom in balancing energy consumption, delay, accuracy, privacy, and other trustworthiness metrics. In this work, we explore the opportunity of DNN splitting at the edge of 6G wireless networks to enable low energy cooperative inference with target delay and accuracy with a goal-oriented perspective. Going beyond the current literature, we explore new trade-offs that take into account the accuracy degradation as a function of the Splitting Point (SP) selection and wireless channel conditions. Then, we propose an algorithm that dynamically controls SP selection, local computing resources, uplink transmit power and bandwidth allocation, in a goal-oriented fashion, to meet a target goal-effectiveness. To the best of our knowledge, this is the first work proposing adaptive SP selection on the basis of all learning performance (i.e., energy, delay, accuracy), with the aim of guaranteeing the accomplishment of a goal (e.g., minimize the energy consumption under latency and accuracy constraints). Numerical results show the advantages of the proposed SP selection and resource allocation, to enable energy frugal and effective edge AI.

Emerging from the symbiotic combination of nanotechnology and communications, the field of nanonetworking has come a long way since its inception more than fifteen years ago. Significant progress has been achieved in several key communication technologies as enablers of the paradigm, as well as in the multiple application areas that it opens. In this paper, the focus is placed on the electromagnetic nanonetworking paradigm, providing an overview of the advances made in wireless nanocommunication technology from microwave through terahertz to optical bands. The characteristics and potential of the compared technologies are then confronted with the requirements and challenges of the broad set of nanonetworking applications in the Internet of NanoThings (IoNT) and on-chip networks paradigms, including quantum computing applications for the first time. Finally, a selection of cross-cutting issues and possible directions for future work are given, aiming to guide researchers and practitioners towards the next generation of electromagnetic nanonetworks.

The future envisaged global-scale quantum communication network will comprise various nodes interconnected via optical fibers or free-space channels, depending on the link distance. The free-space segment of such a network should guarantee certain key requirements, such as daytime operation and the compatibility with the complementary telecom-based fiber infrastructure. In addition, space-to-ground links will require the capability of designing light and compact quantum devices to be placed in orbit. For these reasons, investigating available solutions matching all the above requirements is still necessary. Here we present a full prototype for daylight quantum key distribution at 1550 nm exploiting an integrated silicon-photonics chip as state encoder. We tested our prototype in the urban area of Padua (Italy) over a 145m-long free-space link, obtaining a quantum bit error rate around 0.5% and an averaged secret key rate of 30 kbps during a whole sunny day (from 11:00 to 20:00). The developed chip represents a cost-effective solution for portable free-space transmitters and a promising resource to design quantum optical payloads for future satellite missions.

This paper explores a structured application of the One-Class approach and the One-Class-One-Network model for supervised classification tasks, focusing on vowel phonemes classification and speakers recognition for the Automatic Speech Recognition (ASR) domain. For our case-study, the ASR model runs on a proprietary sensing and lightning system, exploited to monitor acoustic and air pollution on urban streets. We formalize combinations of pseudo-Neural Architecture Search and Hyper-Parameters Tuning experiments, using an informed grid-search methodology, to achieve classification accuracy comparable to nowadays most complex architectures, delving into the speaker recognition and energy efficiency aspects. Despite its simplicity, our model proposal has a very good chance to generalize the language and speaker genders context for widespread applicability in computational constrained contexts, proved by relevant statistical and performance metrics. Our experiments code is openly accessible on our GitHub.

The Information Bottleneck (IB) method is an information theoretical framework to design a parsimonious and tunable feature-extraction mechanism, such that the extracted features are maximally relevant to a specific learning or inference task. Despite its theoretical value, the IB is based on a functional optimization problem that admits a closed form solution only on specific cases (e.g., Gaussian distributions), making it difficult to be applied in most applications, where it is necessary to resort to complex and approximated variational implementations. To overcome this limitation, we propose an approach to adapt the closed-form solution of the Gaussian IB to a general task. Whichever is the inference task to be performed by a (possibly deep) neural-network, the key idea is to opportunistically design a regression sub-task, embedded in the original problem, where we can safely assume a (joint) multivariate normality between the sub-task's inputs and outputs. In this way we can exploit a fixed and pre-trained neural network to process the input data, using a tunable number of features, to trade data-size and complexity for accuracy. This approach is particularly useful every time a device needs to transmit data (or features) to a server that has to fulfil an inference task, as it provides a principled way to extract the most relevant features for the task to be executed, while looking for the best trade-off between the size of the feature vector to be transmitted, inference accuracy, and complexity. Extensive simulation results testify the effectiveness of the proposed method and encourage to further investigate this research line.

In the upcoming 6G era, mobile networks must deal with more challenging applications (e.g., holographic telepresence and immersive communication) and meet far more stringent application requirements stemming along the edge-cloud continuum. These new applications will create an elevated level of expectations on performance, reliability, ubiquity, trustworthiness, security, openness, and sustainability, pushing the boundaries of innovation and driving transformational change across the architecture of future mobile networks. Towards this end, ADROIT6G proposes a set of disruptive innovations with a clear vision on setting a 6G network architecture that can be tailored to the requirements of innovative applications and match the ambitious KPIs set for 6G networks. More specifically, the key transformations that ADROIT6G considers essential to 6G network evolution are: i) AI/ML-powered optimisations across the network, exploring solutions in the "Distributed Artificial Intelligence (DAI)" domain for high performance and automation; ii) Transforming to fully cloud-native network software, which can be implemented across various edge-cloud platforms, with security built integrally into the network user plan; and iii) Software driven, zero-touch operations and ultimately automation of every aspect of the network and the services it delivers.

The impressive growth of wireless data networks has recently led to increased attention to the issue of electromagnetic pollution. Specific absorption rates and incident power densities have become popular indicators for measuring electromagnetic field (EMF) exposure. This paper tackles the problem of power control in user-centric cell-free massive multiple-input-multiple-output (CF-mMIMO) systems under EMF constraints. Specifically, the power allocation maximizing the minimum data rate across users is derived for both the uplink and the downlink under EMF constraints. The developed solution is also applied to a cellular mMIMO system and compared to other benchmark strategies. Simulation results prove that EMF safety restrictions can be easily met without jeopardizing the minimum data rate, that the CF-mMIMO outperforms the multi-cell massive MIMO deployment, and that the proposed power control strategy greatly improves the system fairness.

The coupling of cell-free massive MIMO (CF-mMIMO) with Mobile Edge Computing (MEC) is investigated in this paper. A MEC-enabled CF-mMIMO architecture implementing a distributed user-centric approach both from the radio and the computational resource allocation perspective is proposed. A multi-objective optimization problem (MOOP) for the joint allocation of radio and remote computational resources is formulated, aimed at striking an optimal balance between total uplink power minimization and sum spectral efficiency maximization, under resource budget and latency constraints. In order to solve such a challenging non-convex problem, we convert the MOOP to an equivalent single-objective optimization problem (SOOP) through the weighted sum method and propose an iterative algorithm based on alternating optimization and sequential convex programming, along with an alternative heuristic resource allocation for distributed networks. Finally, we provide a detailed performance comparison between the proposed MEC-enabled CF-mMIMO architecture with its co-located counterpart, and its small-cell implementation. Numerical results reveal the effectiveness of the proposed resource allocation scheme, under different access point selection strategies, and the natural suitability of CF-mMIMO in supporting computation-offloading applications with benefits over users' transmit power and energy consumption, the effective latency experienced, and the computation offloading efficiency.

A reconfigurable intelligent surface (RIS) is a nearly-passive flat layer made of inexpensive elements that can add a tunable phase shift to the impinging electromagnetic wave and are controlled by a low-power electronic circuit. This paper considers the fundamental problem of target detection in a RIS-aided multiple-input multiple-output (MIMO) radar. At first, a general signal model is introduced, which includes the possibility of using up to two RISs (one close to the radar transmitter and one close to the radar receiver) and subsumes both a monostatic and a bistatic radar configuration with or without a line-of-sight view of the prospective target. Upon resorting to a generalized likelihood ratio test (GLRT), the design of the phase shifts introduced by the RIS elements is formulated as the maximization of the probability of detection in the location under inspection for a fixed probability of false alarm, and suitable optimization algorithms are proposed. The performance analysis shows the benefits granted by the presence of the RISs and shed light on the interplay among the key system parameters, such as the radar-RIS distance, the RIS size, and location of the prospective target. A major finding is that the RISs should be better deployed in the near-field of the radar arrays at both the transmit and the receive side. The paper is concluded by discussing some open problems and foreseen applications.