The design of accurate Digital Twins (DTs) of electromagnetic environments strictly depends on the fidelity of the underlying environmental modeling. Evaluating the differences among diverse levels of modeling accuracy is key to determine the relevance of the model features towards both efficient and accurate DT simulations. In this paper, we propose two metrics, the Hausdorff ray tracing (HRT) and chamfer ray tracing (CRT) distances, to consistently compare the temporal, angular and power features between two ray tracing simulations performed on 3D scenarios featured by environmental changes. To evaluate the introduced metrics, we considered a high-fidelity digital twin model of an area of Milan, Italy and we enriched it with two different types of environmental changes: (i) the inclusion of parked vehicles meshes, and (ii) the segmentation of the buildings facade faces to separate the windows mesh components from the rest of the building. We performed grid-based and vehicular ray tracing simulations at 28 GHz carrier frequency on the obtained scenarios integrating the NVIDIA Sionna RT ray tracing simulator with the SUMO vehicular traffic simulator. Both the HRT and CRT metrics highlighted the areas of the scenarios where the simulated radio propagation features differ owing to the introduced mesh integrations, while the vehicular ray tracing simulations allowed to uncover the distance patterns arising along realistic vehicular trajectories.

The Line-of-Sight (LoS) identification is crucial to ensure reliable high-frequency communication links, especially those vulnerable to blockages. Network Digital Twins and Artificial Intelligence are key technologies enabling blockage detection (LoS identification) for high-frequency wireless systems, e.g., 6 > GHz. In this work, we enhance Network Digital Twins by incorporating Age of Information (AoI) metrics, a quantification of status update freshness, enabling reliable real-time blockage detection (LoS identification) in dynamic wireless environments. By integrating raytracing techniques, we automate large-scale collection and labeling of channel data, specifically tailored to the evolving conditions of the environment. The introduced AoI is integrated with the loss function to prioritize more recent information to fine-tune deep learning models in case of performance degradation (model drift). The effectiveness of the proposed solution is demonstrated in realistic urban simulations, highlighting the trade-off between input resolution, computational cost, and model performance. A resolution reduction of 4 × 8 from an original channel sample size of ( 32 , 1024 ) along the angle and subcarrier dimension results in a computational speedup of 32 times. The proposed fine-tuning successfully mitigates performance degradation while requiring only 1 % of the available data samples, enabling automated and fast mitigation of model drifts.

This paper addresses the challenge of achieving simultaneous synchronization and localization of all the active terminals within a cellular network from only one Base Station (BS). We propose a novel approach leveraging Digital Network Twins (DNT), which integrates these two critical tasks within a unified framework.We begin by analyzing User Equipment (UE)-to-network time synchronization, both theoretically and through experimental validation using a 5th generation (5G) testbed, identifying it as the primary obstacle to accurate localization. Then, to address this challenge, we introduce a DNT-based framework that leverages high-fidelity ray-tracing simulations on a 3D digital replica of the environment. This enables precise UE-to-network alignment, dynamic environmental mapping, and accurate real-time localization starting from one Next Generation Node Base (gNB). The proposed method integrates Angle Delay Channel Power Matrix (ADCPM) characterization and Time of Flight (ToF) data with the DNT prior knowledge of the environment, eliminating the need for network cooperation or prior on-field channel measurements for precise localization. We first validate the proposed approach through an outdoor measurement campaign and then demonstrate its effectiveness via numerical simulations, compared to existing localization techniques in scenarios where only a single gNB is available. The method achieves on average a positioning accuracy of less than 6m in the static case and 8m in the dynamic scenario, using a ray-tracing granularity that is not excessively fine (4 × 4 m), even under worst-case synchronization and Non-Line of Sight (NLoS) conditions.

The increasing demand for reliable Vehicle-to-Everything (V2X) communications and autonomous mobility necessitates sophisticated simulation frameworks and intelligent optimization strategies. This paper presents a Network Digital Twin (NDT) that integrates high-fidelity ray-tracing with real vehicular traffic data to model wireless propagation in dynamic urban environments and derive theoretical localization bounds. By explicitly exploiting multipath reflections, both line-of-sight (LOS) and non-line-of-sight (NLOS), from static and mobile reflectors such as vehicles, the framework supports the design of an optimized precoding scheme for enhanced user equipment (UE) positioning. Numerical results indicate that the proposed NDT-guided method reduces the Position Error Bound (PEB) by approximately 35%, underscoring NDT benefits and the utility of NLOS exploitation for high-accuracy localization in dense urban scenarios.

Digital Twin (DT) has emerged as a promising solution for channel estimation. By leveraging high-resolution 3D models of the scenario and ray-tracing simulations, DT could provide valuable site-specific prior knowledge on the channel’s space-time (ST) invariant features of the multipath environment, such as angles of arrival, angles of departure, and propagation delays. However, the real-time characterization of these features imposes computational constraints on ray-tracing simulations, hence limiting the prior knowledge of the multipath environment and corresponding ST features, and degrading estimation accuracy. In this paper, we propose and investigate, for the first time, three distinct DT-empowered low-rank methods for channel estimation, under different degrees of prior knowledge corresponding to limited number of paths provided by DT. Specifically, these methods perform modal projection onto a joint space-time, a spatial, and a temporal subspace. We compare our proposed methods with state-of-the-art techniques, and evaluate their performance in a synthetic scenario. Numerical results show that robustness, when prior knowledge is limited to few paths, is achieved when exploiting only temporal features, while estimation accuracy is attained when joint space-time features are considered.

Wireless communication systems can significantly benefit from the availability of spatially consistent representations of the wireless channel to efficiently perform a wide range of communication tasks. Towards this purpose, channel charting has been introduced as an effective unsupervised learning technique to achieve both locally and globally consistent radio maps. In this letter, we propose Chartwin, a case study on the integration of localization-oriented channel charting with dynamic Digital Network Twins (DNTs). Numerical results showcase the significant performance of semi-supervised channel charting in constructing a spatially consistent chart of the considered extended urban environment. The considered method results in ≈ 4.5 m localization error for the static DNT and ≈ 6 m in the dynamic DNT, fostering DNT-aided channel charting and localization.

Integrated sensing and communication (ISAC) systems are recognized as one of the key ingredients of the sixth generation (6G) network. A challenging topic in ISAC is the design of a single waveform combining both communication and sensing functionalities on the same time-frequency-space resources, allowing tuning the performance of both with partial or full hardware sharing. This paper proposes a dual-domain waveform design approach that superposes onto the frequency-time (FT) domain both the legacy orthogonal frequency division multiplexing (OFDM) signal and a sensing one, purposely designed in the delay-Doppler domain. With a proper power downscaling of the sensing signal w.r.t. OFDM, it is possible to exceed regulatory bandwidth limitations proper of legacy multicarrier systems to increase the sensing performance while leaving communication substantially unaffected. Numerical and experimental results prove the effectiveness of the dual-domain waveform, notwithstanding a power abatement of at least 30 dB of the signal used for sensing compared to the one used for communication. The dual-domain ISAC waveform outperforms both OFDM and orthogonal time-frequency-space (OTFS) in terms of Cramér-Rao bound on delay estimation (up to 20 dB), thanks to its superior resolution, with a negligible penalty on the achievable rate.

Integrated sensing and communication (ISAC) is one of the key technologies of future 6G communication networks. Waveform design for 6G ISAC systems shall guarantee a flexible communication and sensing performance trade-off with full time-frequency-space resource sharing and minimal added hardware/complexity. Legacy ISAC schemes based on orthogonal frequency division multiplexing (OFDM) or orthogonal time-frequency-space (OTFS) are currently subject to regulatory bandwidth constraints, limiting the delay/range resolution and requiring advanced processing schemes. This paper proposes to exploit a low-power, wide-bandwidth out-of-band (OOB) sensing signal superposed to the legacy OFDM one to enhance the delay/range resolution compared to standalone OFDM and OTFS ISAC systems. The proper power control of the sensing signal allows for complying with adjacent channel leakage ratio requirements. The analytical findings demonstrate the advantages of the proposed ISAC scheme over existing solutions.

MIMO systems in the context of 6G Vehicle-to-Everything (V2X) will require an accurate channel knowledge to enable efficient communication. Standard channel estimation techniques, such as Unconstrained Maximum Likelihood (UML), are extremely noisy in massive MIMO settings, while structured approaches, e.g., compressed sensing, are sensitive to hardware impairments. We propose a novel multi-vehicular algebraic channel estimation method for 6G V2X based on unsupervised learning which exploits recurrent vehicle passages in typical urban settings. Multiple training sequences from different vehicle passages are clustered via K-medoids algorithm based on their algebraic similarity to retrieve the MIMO channel eigenmodes, which can be used to improve the channel estimates. Numerical results show the presence of an optimal number of clusters and remarkable benefits of the proposed method in terms of Mean Squared Error (MSE) compared to standard U-ML solution (15 dB less).

Machine learning is a highly promising tool to design the physical layer of wireless communication systems, but its scaling properties for this purpose have not been widely studied. Machine learning algorithms are typically evaluated to learn SISO communications and low modulation orders, whereas current wireless standards use MIMO and high-order modulation schemes to increase capacity. The memory requirements of current Machine learning algorithms for wireless communications increase exponentially with the number of antennas and thus they cannot be used for advanced physical layers and massive MIMO. In this paper, we study the requirements of end-to-end Machine learning models for large-scale MIMO systems, determine the bottlenecks of the architecture, and design different solutions that vastly reduce overhead and allow training higher MIMO and modulation orders. We show that by training the autoencoder in a bit-wise manner, the memory requirements are reduced by several orders of magnitude, which is a critical step for Machine learning-based physical layer design in practical scenarios. Additionally, our design also improves performance over the classical autoencoder for MIMO.