arXiv subjects

Leopoldo Carro-Calvo

Publications and source records attributed to Leopoldo Carro-Calvo.

2 recordsLinked to original sources

arXiv2026

Evolutionary AP Switch ON/OFF Techniques for Energy-efficient Cell-free Massive MIMO Networks

Cell-free massive multiple input multiple output (CF-mMIMO) is an emerging technology for next-generation wireless systems, where dynamically adapting the set of active access points (APs) is crucial to balance quality of service (QoS) requirements and network energy consumption under highly time-varying and spatially non-uniform traffic loads. Existing AP ON/OFF mechanisms--typically based on worst-case dimensioning or greedy heuristics--explore the combinatorial activation space inadequately, leading to suboptimal energy-efficiency outcomes. This paper introduces two evolutionary AP-selection strategies tailored to CF-mMIMO networks. The first, a constrained genetic algorithm (CGA), identifies the near-optimal subset of active APs for any fixed activation cardinality, while an outer search determines the globally optimal operating point. The second, a Pareto-driven genetic algorithm (PDGA), jointly optimizes spectral and energy efficiency by evolving a Pareto front over all feasible activation patterns. A detailed computational-complexity analysis is provided for both techniques. Simulations conducted under realistic spatially inhomogeneous traffic and considering both conjugate beamforming (CB) and minimum mean square error (MMSE) processing confirm consistent performance gains. The proposed methods consistently outperform state-of-the-art greedy benchmarks, delivering noticeable improvements in energy efficiency for both CB and MMSE schemes, while simultaneously enhancing the energy-spectral efficiency tradeoff, which is typically difficult to improve without incurring penalties elsewhere. These results highlight the strong potential of evolutionary optimization as a powerful and reliable approach for energy-efficient CF-mMIMO deployments.

eess.SP↗

arXiv2026

Deep Learning-Assisted Multicast Subgrouping in Massive MIMO

Efficient content delivery in massive multiple-input multiple-output (mMIMO) multicasting is fundamentally limited by pilot overhead and the need to serve heterogeneous users with a common transmission rate. Conventional approaches either suffer from pilot contamination or are constrained by the worst-user effect, motivating the need for adaptive subgrouping strategies. In this paper, we propose a deep learning-assisted multicast subgrouping framework that infers the number of multicast subgroups directly from users' spatial channel statistics. A snapshot-specific principal component analysis (PCA) is applied to user covariance matrices to obtain a compact representation, which is processed by a sequential long short-term memory (LSTM) encoder capable of handling variable-size user sets. The model predicts the number of subgroups and groups of users based on their statistical similarity. To further improve system performance, we introduce a transfer learning (TL) extension where a pretrained LSTM encoder is reused, and a lightweight dense head is fine-tuned to estimate the sum spectral efficiency (SE) as a function of the subgroup configuration. This enables selecting near-optimal subgrouping solutions without exhaustive search. Simulation results demonstrate that the proposed approach consistently outperforms benchmark methods, including unicast transmission, conventional multicast, random subgrouping, and density-based clustering. The TL-enhanced model achieves up to 85% of the maximum achievable spectral efficiency while maintaining robust performance across diverse spatial user distributions and under imperfect covariance information.

eess.SP↗