Goal-Oriented Access Optimization for ISAC-Enabled Digital Twins

The digital twins (DTs) of physical systems and environments enable real-time remote tracking, control, and learning, but require low-latency transmission of updates and sensory data to maintain alignment with their physical counterparts. In this context, augmenting sensory data with the network's own integrated sensing and communication (ISAC)capabilities can expand the DT's awareness of the environment by allowing it to precisely non-radar locate measurements from mobile nodes. However, this integration increases the complexity of the communication system, and can only be supported through intelligent resource allocation and access optimization. In this work, we propose a two-step goal-oriented approach to solve this problem: we design a push-based random access in which sensors with a high Value of Information (VoI) inform the network of their access requirements, followed by a pull-based scheduled transmission of the actual sensory data. This design allows to combine the ISAC and reliable transmission requirements and maximize the VoI of the information delivered to the DT, significantly outperforming existing schemes.

A Novel Near-Field Dictionary Design for Hybrid MIMO with Uniform Planar Arrays

Near-field ultra-massive MIMO (U-MIMO) systems provide enhanced spatial resolution but present challenges for channel estimation, particularly when hybrid architectures are employed. Within this framework, dictionary-based channel estimation schemes are needed to achieve accurate reconstruction from a reduced set of measurements. However, existing near-field dictionaries generally provide full three-dimensional coverage, which is unnecessary when user equipments are primarily located on the ground. In this paper, we propose a novel near-field grid design tailored to this common scenario. Specifically, grid points lie on a reference plane located at an arbitrary height with respect to the U-MIMO system, equipped with a uniform planar array. Furthermore, a channel accuracy metric is used to improve codebook performance, and to remark the limitations of the traditional far-field angular sampling in the near field. Results show that, as long as user equipments are not far from the reference plane, the proposed grid outperforms state-of-the-art designs in both channel estimation accuracy and spectral efficiency.

An Enhanced Polar-Domain Dictionary Design for Elevated BSs in Near-Field U-MIMO

Near-field U-MIMO communications require carefully optimized sampling grids in both angular and distance domains. However, most existing grid design methods neglect the influence of base station height, assuming instead that the base station is positioned at ground level - a simplification that rarely reflects real-world deployments. To overcome this limitation, we propose a generalized grid design framework that accommodates arbitrary base station locations. Unlike conventional correlation-based approaches, our method optimizes the grid based on the minimization of the optimal normalized mean squared error, leading to more accurate channel representation. We evaluate the performance of a hybrid U-MIMO system operating at sub-THz frequencies, considering the P-SOMP algorithm for channel estimation. Analytical and numerical results show that the proposed design enhances both channel estimation accuracy and spectral efficiency compared to existing alternatives.

Tree Meets Transformer: A Hybrid Architecture for Scalable Power Allocation in Cell-Free Networks

Power allocation remains a fundamental challenge in wireless communication networks, particularly under dynamic user loads and large-scale deployments. While Transformerbased models have demonstrated strong performance, their computational cost scales poorly with the number of users. In this work, we propose a novel hybrid Tree-Transformer architecture that achieves scalable per-user power allocation. Our model compresses user features via a binary tree into a global root representation, applies a Transformer encoder solely to this root, and decodes per-user uplink and downlink powers through a shared decoder. This design achieves logarithmic depth and linear total complexity, enabling efficient inference across large and variable user sets without retraining or architectural changes. We evaluate our model on the max-min fairness problem in cellfree massive MIMO systems and demonstrate that it achieves near-optimal performance while significantly reducing inference time compared to full-attention baselines.

Linear Attention for Joint Power Optimization and User-Centric Clustering in Cell-Free Networks

Optimal AP clustering and power allocation are critical in user-centric cell-free massive MIMO systems. Existing deep learning models lack flexibility to handle dynamic network configurations. Furthermore, many approaches overlook pilot contamination and suffer from high computational complexity. In this paper, we propose a lightweight transformer model that overcomes these limitations by jointly predicting AP clusters and powers solely from spatial coordinates of user devices and AP. Our model is architecture-agnostic to users load, handles both clustering and power allocation without channel estimation overhead, and eliminates pilot contamination by assigning users to AP within a pilot reuse constraint. We also incorporate a customized linear attention mechanism to capture user-AP interactions efficiently and enable linear scalability with respect to the number of users. Numerical results confirm the model's effectiveness in maximizing the minimum spectral efficiency and providing near-optimal performance while ensuring adaptability and scalability in dynamic scenarios.

Coherent and Noncoherent Detection in Dense Arrays: Can We Ignore Mutual Coupling?

This paper investigates the impact of mutual coupling on MIMO systems with densely deployed antennas. Leveraging multiport communication theory, we analyze both coherent and noncoherent detection approaches in a single-user uplink scenario where the receiver ignores mutual coupling effects. Simulation results indicate that while coherent detection is generally more accurate, it is highly sensitive to mismatches in the coupling model, leading to severe performance degradation when antennas are closely spaced, to the point of becoming unusable. Noncoherent detection, on the other hand, exhibits a higher error probability but is more robust to coupling model mismatches.

Parametric Near-Field MMSE Channel Estimation for sub-THz XL-MIMO Systems

Accurate channel estimation is essential for reliable communication in sub-THz extremely large (XL) MIMO systems. Deploying XL-MIMO in high-frequency bands not only increases the number of antennas, but also fundamentally alters channel propagation characteristics, placing the user equipments (UE) in the radiative near-field of the base station. This paper proposes a parametric estimation method using the multiple signal classification (MUSIC) algorithm to extract UE location data from uplink pilot signals. These parameters are used to reconstruct the spatial correlation matrix, followed by an approximation of the minimum mean square error (MMSE) channel estimator. Numerical results show that the proposed method outperforms the least-squares (LS) estimator in terms of the normalized mean-square error (NMSE), even without prior UE location knowledge.

Transformer-Based Power Optimization for Max-Min Fairness in Cell-Free Massive MIMO

Power allocation is an important task in wireless communication networks. Classical optimization algorithms and deep learning methods, while effective in small and static scenarios, become either computationally demanding or unsuitable for large and dynamic networks with varying user loads. This letter explores the potential of transformer-based deep learning models to address these challenges. We propose a transformer neural network to jointly predict optimal uplink and downlink power using only user and access point positions. The max-min fairness problem in cell-free massive multiple input multiple output systems is considered. Numerical results show that the trained model provides near-optimal performance and adapts to varying numbers of users and access points without retraining, additional processing, or updating its neural network architecture. This demonstrates the effectiveness of the proposed model in achieving robust and flexible power allocation for dynamic networks.

Harnessing Wavefront Curvature and Spatial Correlation in Noncoherent MIMO Communications

Noncoherent communication systems have regained interest due to the growing demand for high-mobility and low-latency applications. Most existing studies using large antenna arrays rely on the far-field approximation, which assumes locally plane wavefronts. This assumption becomes inaccurate at higher frequencies and shorter ranges, where wavefront curvature plays a significant role and antenna arrays may operate in the radiative near field. In this letter, we adopt a model for the channel spatial correlation matrix that remains valid in both near and far field scenarios. Using this model, we demonstrate that noncoherent systems can leverage the benefits of wavefront spherical curvature, even beyond the Fraunhofer distance, revealing that the classical far-field approximation may significantly underestimate system performance. Moreover, we show that large antenna arrays enable the multiplexing of various users and facilitate near-optimal noncoherent detection with low computational complexity.

Efficient Channel Estimation With Shorter Pilots in RIS-Aided Communications: Using Array Geometries and Interference Statistics

Accurate estimation of the cascaded channel from a user equipment (UE) to a base station (BS) via each reconfigurable intelligent surface (RIS) element is critical to realizing the full potential of the RIS's ability to control the overall channel. The number of parameters to be estimated is equal to the number of RIS elements, requiring an equal number of pilots unless an underlying structure can be identified. In this paper, we show how the spatial correlation inherent in the different RIS channels provides this desired structure. We first optimize the RIS phase-shift pattern using a much-reduced pilot length (determined by the rank of the spatial correlation matrices) to minimize the mean square error (MSE) in the channel estimation under electromagnetic interference. In addition to considering the linear minimum MSE (LMMSE) channel estimator, we propose a novel channel estimator that requires only knowledge of the array geometry while not requiring any user-specific statistical information. We call this the reduced-subspace least squares (RS-LS) estimator and optimize the RIS phase-shift pattern for it. This novel estimator significantly outperforms the conventional LS estimator. For both the LMMSE and RS-LS estimators, the proposed optimized RIS configurations result in significant channel estimation improvements over the benchmarks.