We investigate the performance of a multiple re-configurable intelligence surface (RIS)-aided millimeter wave (mmWave) beamspace multiple-input multiple-output (MIMO) system with multiple users (UEs). We focus on a challenging scenario in which the direct links between the base station (BS) and all UEs are blocked, and communication is facilitated only via RISs. The maximum ratio transmission (MRT) is utilized for data precoding, while a low-complexity algorithm based on particle swarm optimization (PSO) is designed to jointly perform beam selection, power allocation, and RIS profile configuration. The proposed optimization approach demonstrates positive trade-offs between the complexity (in terms of running time) and the achievable sum rate. In addition, our results demonstrate that due to the sparsity of beamspace channels, increasing the number of unit cells (UCs) at RISs can lead to higher achievable rates than activating a larger number of beams at the MIMO BS.

High peak-to-average power ratio (PAPR) in orthogonal frequency division multiplexing (OFDM) signals presents a persistent challenge in satellite communications (SatCom), impacting signal quality and causing adjacent channel interference. This paper introduces a novel framework that combines the elastic net-based machine learning (ML) model with the partial transmit sequence (PTS) technique to effectively reduce PAPR. Additionally, the potential of artificial intelligence (AI) approaches are investigated, specifically swarm intelligence and ML methods, for high-performance, low-complexity solutions. In this regard, ML models are applied to mitigate PAPR in SatCom networks under the presence of a traveling wave tube amplifier (TWTA) model and a land mobile satellite (LMS) channel, employing 16-quadrature amplitude modulation (16-QAM). Compared with the baseline schemes, simulation results demonstrate that the proposed ML framework, integrating principal component analysis (PCA) with the elastic net learning model, achieves comparable PAPR performance and minimal computational complexity.

In this paper, we investigate the performance of the rate-splitting multiple access (RSMA) framework in a mmWave cell-free massive multiple-input multiple-output (CF-mMIMO) system assisted by multiple reconfigurable intelligent surfaces (RISs). We consider the practical scenario of low-resolution digital-to-analog converters (DACs) at the distributed access points (APs) to reduce hardware complexity and power consumption. Our main objective is to maximize the minimum rate among the users by jointly optimizing the precoding vectors at each AP, the common rates, and the reflection coefficients of RISs. The resultant non-convex optimization problem is then solved using alternating optimization and successive convex approximation-based methods. Numerical results demonstrate the superior performance of the proposed RSMA-based scheme over traditional methods across several deployment scenarios, with performance gains from RIS deployment notably improved in hotspot scenarios.

The Internet of Vehicles (IoV) is undergoing swift advancements in capability and intelligence, poised to facilitate a diverse range of innovative applications. Within the IoV, edge learning empowers intelligent applications and services by leveraging data -driven tasks. Therefore, in this paper, we propose optimizing the edge learning error prediction within an edge-supported Non-Orthogonal Multiple Access (NOMA) in task-oriented communications. Specifically, we consider three autonomous vehicle perception tasks, called: object detection, traffic sign, and weather classification. For this purpose, we propose a novel approach based on the Particle Swarm Optimization (PSO) algorithm to jointly minimize the edge learning error and optimize power allocation variables. Moreover, we investigate alternative benchmark schemes, including Quantum Particle Swarm Optimization, Cuckoo Search, and Butterfly Op-timization algorithms. Satisfactorily, our simulations substantiate the superiority of the PSO algorithm over the baseline schemes, delivering superior performance with reduced computation time.