arXiv subjects

Cristian J. Vaca-Rubio

Publications and source records attributed to Cristian J. Vaca-Rubio.

At least 19 recordsLinked to original sources

arXiv2026

Semantic CSI Feedback for Beam Selection: When Task-Aware Embeddings from Sparse Pilots Outperform Full-Bandwidth Reconstruction

Classical CSI feedback in FDD massive MIMO transmits a compressed reconstruction of the channel, optimizing fidelity to the original signal regardless of the downstream task. We propose a semantic communication perspective: instead of reconstructing the channel, the UE transmits a learned \emph{semantic embedding} optimized end-to-end for beam selection at the gNB. Comparing reconstruction-oriented feedback (CsiNet) against task-aware semantic feedback across two input domains and three observation scenarios, we show that a semantic embedding of just $d=8$ real values from only 43 NR CSI-RS pilots in the angular-delay domain achieves the highest beam prediction accuracy, outperforming every method with access to the full 512-subcarrier channel. The key insight is that beam-relevant information is intrinsically low-dimensional: the semantic encoder learns to discard reconstruction-irrelevant structure and retain only a compact representation that is relevant to beam selection, realizing the core principle of semantic communication: transmit the intent, not the signal.

eess.SP↗

arXiv2026

Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks

Efficient physical resource block (PRB) allocation in 5G networks requires accurate demand forecasting. Conventional methods minimize symmetric error metrics (MAE, RMSE), ignoring the operational cost asymmetry where under-provisioning (service degradation) is far costlier than over-provisioning (wasted capacity). We propose a goal-oriented probabilistic forecasting framework that aligns model training with the operator's decision-making objectives. Specifically, we train DeepAR and Temporal Fusion Transformer (TFT) models using the Pinball Loss function and derive the optimal allocation quantile from the operator's cost matrix. Evaluation on a real beam-level 5G traffic dataset shows that the proposed approach reduces operational cost compared to MSE-trained baselines while maintaining calibrated uncertainty estimates. The framework enables dynamic PRB allocation that explicitly balances service reliability against resource efficiency.

eess.SP↗

arXiv2025

Learn More by Using Less: Distributed Learning with Energy-Constrained Devices

Federated Learning (FL) has emerged as a solution for distributed model training across decentralized, privacy-preserving devices, but the different energy capacities of participating devices (system heterogeneity) constrain real-world implementations. These energy limitations not only reduce model accuracy but also increase dropout rates, impacting on convergence in practical FL deployments. In this work, we propose LeanFed, an energy-aware FL framework designed to optimize client selection and training workloads on battery-constrained devices. LeanFed leverages adaptive data usage by dynamically adjusting the fraction of local data each device utilizes during training, thereby maximizing device participation across communication rounds while ensuring they do not run out of battery during the process. We rigorously evaluate LeanFed against traditional FedAvg on CIFAR-10 and CIFAR-100 datasets, simulating various levels of data heterogeneity and device participation rates. Results show that LeanFed consistently enhances model accuracy and stability, particularly in settings with high data heterogeneity and limited battery life, by mitigating client dropout and extending device availability. This approach demonstrates the potential of energy-efficient, privacy-preserving FL in real-world, large-scale applications, setting a foundation for robust and sustainable pervasive AI on resource-constrained networks.

cs.LG↗

arXiv2025

A Primer on Kolmogorov-Arnold Networks (KANs) for Probabilistic Time Series Forecasting

This work introduces Probabilistic Kolmogorov-Arnold Network (P-KAN), a novel probabilistic extension of Kolmogorov-Arnold Networks (KANs) for time series forecasting. By replacing scalar weights with spline-based functional connections and directly parameterizing predictive distributions, P-KANs offer expressive yet parameter-efficient models capable of capturing nonlinear and heavy-tailed dynamics. We evaluate P-KANs on satellite traffic forecasting, where uncertainty-aware predictions enable dynamic thresholding for resource allocation. Results show that P-KANs consistently outperform Multi Layer Perceptron (MLP) baselines in both accuracy and calibration, achieving superior efficiency-risk trade-offs while using significantly fewer parameters. We build up P-KANs on two distributions, namely Gaussian and Student-t distributions. The Gaussian variant provides robust, conservative forecasts suitable for safety-critical scenarios, whereas the Student-t variant yields sharper distributions that improve efficiency under stable demand. These findings establish P-KANs as a powerful framework for probabilistic forecasting with direct applicability to satellite communications and other resource-constrained domains.

cs.LG↗

arXiv2025

On the Architectural Split and Radio Intelligence Controller Placement in Integrated O-RAN-enabled Non-Terrestrial Networks

The integration of Terrestrial Networks (TNs) with Non-Terrestrial Networks (NTNs) poses unique architectural and functional challenges due to heterogeneous propagation conditions, dynamic topologies and limited on-board processing capabilities. This paper examines architectural and functional split strategies that are consistent with O-RAN principles for future integrated TN-NTN systems. A taxonomy of split options is proposed that distributes RAN and core functions between satellites and ground nodes, and trade-offs in terms of performance, latency, autonomy and deployment are analysed. In particular, we evaluate configurations ranging from pure on-board DU deployments to full gNB and UPF integration into satellites, including variations based on intra- and inter-satellite processing. In addition, the placement of Near-RT and Non-RT RAN Intelligent Controllers (RICs) is discussed, proposing flexible split strategies between space and ground to optimise the performance and scalability of the control loop. A comprehensive mapping between architectural splits and RIC placement options is provided, emphasising implementation constraints and interoperability considerations. The paper concludes by identifying key challenges and outlining future directions to enable standardised, modular and efficient TN-NTN convergence in the context of the O-RAN.

cs.NI↗

arXiv2025

Probabilistic Forecasting for Network Resource Analysis in Integrated Terrestrial and Non-Terrestrial Networks

Efficient resource management is critical for Non-Terrestrial Networks (NTNs) to provide consistent, high-quality service in remote and under-served regions. While traditional single-point prediction methods, such as Long-Short Term Memory (LSTM), have been used in terrestrial networks, they often fall short in NTNs due to the complexity of satellite dynamics, signal latency and coverage variability. Probabilistic forecasting, which quantifies the uncertainties of the predictions, is a robust alternative. In this paper, we evaluate the application of probabilistic forecasting techniques, in particular SFF, to NTN resource allocation scenarios. Our results show their effectiveness in predicting bandwidth and capacity requirements in different NTN segments of probabilistic forecasting compared to single-point prediction techniques such as LSTM. The results show the potential of black probabilistic forecasting models to provide accurate and reliable predictions and to quantify their uncertainty, making them indispensable for optimizing NTN resource allocation. At the end of the paper, we also present application scenarios and a standardization roadmap for the use of probabilistic forecasting in integrated Terrestrial Network (TN)-NTN environments.

eess.SP↗

arXiv2025

Fed-KAN: Federated Learning with Kolmogorov-Arnold Networks for Traffic Prediction

Non-Terrestrial Networks (NTNs) are becoming a critical component of modern communication infrastructures, especially with the advent of Low Earth Orbit (LEO) satellite systems. Traditional centralized learning approaches face major challenges in such networks due to high latency, intermittent connectivity and limited bandwidth. Federated Learning (FL) is a promising alternative as it enables decentralized training while maintaining data privacy. However, existing FL models, such as Federated Learning with Multi-Layer Perceptrons (Fed-MLP), can struggle with high computational complexity and poor adaptability to dynamic NTN environments. This paper provides a detailed analysis for Federated Learning with Kolmogorov-Arnold Networks (Fed-KAN), its implementation and performance improvements over traditional FL models in NTN environments for traffic forecasting. The proposed Fed-KAN is a novel approach that utilises the functional approximation capabilities of KANs in a FL framework. We evaluate Fed-KAN compared to Fed-MLP on a traffic dataset of real satellite operator and show a significant reduction in training and test loss. Our results show that Fed-KAN can achieve a 77.39% reduction in average test loss compared to Fed-MLP, highlighting its improved performance and better generalization ability. At the end of the paper, we also discuss some potential applications of Fed-KAN within O-RAN and Fed-KAN usage for split functionalities in NTN architecture.

cs.NI↗

arXiv2024

F-KANs: Federated Kolmogorov-Arnold Networks

In this paper, we present an innovative federated learning (FL) approach that utilizes Kolmogorov-Arnold Networks (KANs) for classification tasks. By utilizing the adaptive activation capabilities of KANs in a federated framework, we aim to improve classification capabilities while preserving privacy. The study evaluates the performance of federated KANs (F- KANs) compared to traditional Multi-Layer Perceptrons (MLPs) on classification task. The results show that the F-KANs model significantly outperforms the federated MLP model in terms of accuracy, precision, recall, F1 score and stability, and achieves better performance, paving the way for more efficient and privacy-preserving predictive analytics.

cs.LG↗

arXiv2024

Kolmogorov-Arnold Networks (KANs) for Time Series Analysis

This paper introduces a novel application of Kolmogorov-Arnold Networks (KANs) to time series forecasting, leveraging their adaptive activation functions for enhanced predictive modeling. Inspired by the Kolmogorov-Arnold representation theorem, KANs replace traditional linear weights with spline-parametrized univariate functions, allowing them to learn activation patterns dynamically. We demonstrate that KANs outperforms conventional Multi-Layer Perceptrons (MLPs) in a real-world satellite traffic forecasting task, providing more accurate results with considerably fewer number of learnable parameters. We also provide an ablation study of KAN-specific parameters impact on performance. The proposed approach opens new avenues for adaptive forecasting models, emphasizing the potential of KANs as a powerful tool in predictive analytics.

eess.SP↗

arXiv2024

Minimizing Power Consumption under SINR Constraints for Cell-Free Massive MIMO in O-RAN

This paper deals with the problem of energy consumption minimization in Open RAN cell-free (CF) massive Multiple-Input Multiple-Output (mMIMO) systems under minimum per-user signal-to-noise-plus-interference ratio (SINR) constraints. Considering that several access points (APs) are deployed with multiple antennas, and they jointly serve multiple users on the same time-frequency resources, we design the precoding vectors that minimize the system power consumption, while preserving a minimum SINR for each user. We use a simple, yet representative, power consumption model, which consists of a fixed term that models the power consumption due to activation of the AP and a variable one that depends on the transmitted power. The mentioned problem boils down to a binary-constrained quadratic optimization problem, which is strongly non-convex. In order to solve this problem, we resort to a novel approach, which is based on the penalized convex-concave procedure. The proposed approach can be implemented in an O-RAN cell-free mMIMO system as an xApp in the near-real time RIC (RAN intelligent Controller). Numerical results show the potential of this approach for dealing with joint precoding optimization and AP selection.

cs.NI↗

arXiv2024

On the Impact of PRB Load Uncertainty Forecasting for Sustainable Open RAN

The transition to sustainable Open Radio Access Network (O-RAN) architectures brings new challenges for resource management, especially in predicting the utilization of Physical Resource Block (PRB)s. In this paper, we propose a novel approach to characterize the PRB load using probabilistic forecasting techniques. First, we provide background information on the O-RAN architecture and components and emphasize the importance of energy/power consumption models for sustainable implementations. The problem statement highlights the need for accurate PRB load prediction to optimize resource allocation and power efficiency. We then investigate probabilistic forecasting techniques, including Simple-Feed-Forward (SFF), DeepAR, and Transformers, and discuss their likelihood model assumptions. The simulation results show that DeepAR estimators predict the PRBs with less uncertainty and effectively capture the temporal dependencies in the dataset compared to SFF- and Transformer-based models, leading to power savings. Different percentile selections can also increase power savings, but at the cost of over-/under provisioning. At the same time, the performance of the Long-Short Term Memory (LSTM) is shown to be inferior to the probabilistic estimators with respect to all error metrics. Finally, we outline the importance of probabilistic, prediction-based characterization for sustainable O-RAN implementations and highlight avenues for future research.

cs.NI↗

arXiv2023

Proximal Policy Optimization for Integrated Sensing and Communication in mmWave Systems

In wireless communication systems, mmWave beam tracking is a critical task that affects both sensing and communications, as it is related to the knowledge of the wireless channel. We consider a setup in which a Base Station (BS) needs to dynamically choose whether the resource will be allocated for one of the three operations: sensing (beam tracking), downlink, or uplink transmission. We devise an approach based on the Proximal Policy Optimization (PPO) algorithm for choosing the resource allocation and beam tracking at a given time slot. The proposed framework takes into account the variable quality of the wireless channel and optimizes the decisions in a coordinated manner. Simulation results demonstrate that the proposed method achieves significant performance improvements in terms of average packet error rate (PER) compared to the baseline methods while providing a significant reduction in beam tracking overhead. We also show that our proposed PPO-based framework provides an effective solution to the resource allocation problem in beam tracking and communication, exhibiting a great generalization performance regardless of the stochastic behavior of the system.

eess.SP↗

arXiv2023

EMF Exposure Mitigation in RIS-Assisted Multi-Beam Communications

This paper proposes a method for reducing {third-party} exposure to electromagnetic fields (EMF) by exploiting the capability of a reconfigurable intelligent surfaces' (RIS) to manipulate the electromagnetic environment. We consider users capable of multi-beam communication, such that a user can use a set of different propagation paths enabled by the RIS. The optimization objective is to find propagation alternatives that allow to maintain the target quality of service while minimizing the level of EMF at surrounding non-intended users (NUEs). We provide an evolutionary heuristic solution based on Genetic Algorithm (GA) for power equalization and multi-beam selection of a codebook at the Base Station. Our results show valuable insights into how RIS-assisted multi-beam communications can mitigate EMF exposure with minimal degradation of the spectral efficiency.

eess.SP↗

arXiv2023

OnRMap: An Online Radio Mapping Approach for Large Intelligent Surfaces

We introduce OnRMap, an online radio mapping (RMap) approach for the sensing and localization of active users (AUs), devices that are transmitting radio signals, and passive elements (PEs), elements that are in the environment and are illuminated by the AUs' radio signals. OnRMap processes the signals received by a large intelligent surface and produces a radio map (RM) of the environment based on signal processing techniques. The method then senses and locate the different elements without the need for offline scanning phases, which is important for environments with frequently changing spatial layouts. Empirical results demonstrate that OnRMap presents a higher localization accuracy than an offline method, but the price paid for being an online method is a moderate reduction in the detection rate.

eess.SP↗

arXiv2022

Floor Map Reconstruction Through Radio Sensing and Learning By a Large Intelligent Surface

Environmental scene reconstruction is of great interest for autonomous robotic applications, since an accurate representation of the environment is necessary to ensure safe interaction with robots. Equally important, it is also vital to ensure reliable communication between the robot and its controller. Large Intelligent Surface (LIS) is a technology that has been extensively studied due to its communication capabilities. Moreover, due to the number of antenna elements, these surfaces arise as a powerful solution to radio sensing. This paper presents a novel method to translate radio environmental maps obtained at the LIS to floor plans of the indoor environment built of scatterers spread along its area. The usage of a Least Squares (LS) based method, U-Net (UN) and conditional Generative Adversarial Networks (cGANs) were leveraged to perform this task. We show that the floor plan can be correctly reconstructed using both local and global measurements.

eess.SP↗

arXiv2022

User Clustering for Rate Splitting using Machine Learning

Hierarchical Rate Splitting (HRS) schemes proposed in recent years have shown to provide significant improvements in exploiting spatial diversity in wireless networks and provide high throughput for all users while minimising interference among them. Hence, one of the major challenges for such HRS schemes is the necessity to know the optimal clustering of these users based only on their Channel State Information (CSI). This clustering problem is known to be NP hard and, to deal with the unmanageable complexity of finding an optimal solution, in this work a scalable and much lighter clustering mechanism based on Neural Network (NN) is proposed. The accuracy and performance metrics show that the NN is able to learn and cluster the users based on the noisy channel response and is able to achieve a rate comparable to other more complex clustering schemes from the literature.

eess.SP↗

arXiv2022

User Localization using RF Sensing: A Performance comparison between LIS and mmWave Radars

Since electromagnetic signals are omnipresent, Radio Frequency (RF)-sensing has the potential to become a universal sensing mechanism with applications in localization, smart-home, retail, gesture recognition, intrusion detection, etc. Two emerging technologies in RF-sensing, namely sensing through Large Intelligent Surfaces (LISs) and mmWave Frequency-Modulated Continuous-Wave (FMCW) radars, have been successfully applied to a wide range of applications. In this work, we compare LIS and mmWave radars for localization in real-world and simulated environments. In our experiments, the mmWave radar achieves 0.71 Intersection Over Union (IOU) and 3cm error for bounding boxes, while LIS has 0.56 IOU and 10cm distance error. Although the radar outperforms the LIS in terms of accuracy, LIS features additional applications in communication in addition to sensing scenarios.

eess.SP↗

arXiv2022

Radio Sensing with Large Intelligent Surface for 6G

This paper leverages the potential of Large Intelligent Surface (LIS) for radio sensing in 6G wireless networks. Major research has been undergone about its communication capabilities but it can be exploited as a formidable tool for radio sensing. By taking advantage of arbitrary communication signals occurring in the scenario, we apply direct processing to the output signal from the LIS to obtain a radio map that describes the physical presence of passive devices (scatterers, humans) which act as virtual sources due to the communication signal reflections. We then assess the usage of machine learning (k-means clustering), image processing and computer vision (template matching and component labeling) to extract meaningful information from these radio maps. As an exemplary use case, we evaluate this method for both active and passive user detection in an indoor setting. The results show that the presented method has high application potential as we are able to detect around 98% of humans passively and 100% active users by just using communication signals of commodity devices even in quite unfavorable Signal-to-Noise Ratio (SNR) conditions.

eess.SP↗