The combination of multiple-input multiple-output (MIMO) systems and intelligent reflecting surfaces (IRSs) is foreseen as a critical enabler of beyond 5G (B5G) and 6G. In this work, two different approaches are considered for the joint optimization of the IRS phase-shift matrix and MIMO precoders of an IRS-assisted multi-stream (MS) multi-user MIMO (MU-MIMO) system. Both approaches aim to maximize the system sum-rate for every channel realization. The first proposed solution is a novel contextual bandit (CB) framework with continuous state and action spaces called deep contextual bandit-oriented deep deterministic policy gradient (DCB-DDPG). The second is an innovative deep reinforcement learning (DRL) formulation where the states, actions, and rewards are selected such that the Markov decision process (MDP) property of reinforcement learning (RL) is appropriately met. Both proposals perform remarkably better than state-of-the-art heuristic methods in scenarios with high multi-user interference.

Efficient resource allocation strategies are pivotal in vehicular communications as connected devices steeply increase in scenarios with much more stringent requirements. In this work, we propose a DRL-based sequential scheduling approach for sum-rate maximization in the uplink of IRS-assisted MU MIMO vehicular communications. We formulate the scheduling task as a partially observable Markov decision process (POMDP) and propose a novel stream-level sequential solution based on the PPO algorithm. We consider a realistic imperfect channel state information (ICSI) model and assess the proposal in several communication setups comprising both spatially uncorrelated and correlated links. Simulation results show that the proposed DRL-based sequential scheduling approach is a robust alternative to more computationally demanding benchmarks.

In the last decade, the transition of digital terrestrial television (DTT) systems from multi-frequency networks (MFNs) to single-frequency networks (SFNs) has become a reality. SFN offers multiple advantages concerning MFN, such as more efficient management of the radioelectric spectrum, homogenizing the network parameters, and a potential SFN gain. However, the transition process can be cumbersome for operators due to the multiple measurement campaigns and required finetuning of the final SFN system to ensure the desired quality of service. To avoid time-consuming field measurements and reduce the costs associated with the SFN implementation, this paper aims to predict the performance of an SFN system from the legacy MFN and position data through machine learning (ML) algorithms. It is proposed a ML concatenated structure based on classification and regression to predict SFN electric-field strength, modulation error ratio, and gain. The model’s training and test process are performed with a dataset from an SFN/MFN trial in Ghent, Belgium. Multiple algorithms have been tuned and compared to extract the data patterns and select the most accurate algorithms. The best performance to predict the SFN electric-field strength is obtained with a coefficient of determination (R ² ) of 0.93, modulation error ratio of 0.98, and SFN gain of 0.89 starting from MFN parameters and position data. The proposed method allows classifying the data points according to positive or negative SFN gain with an accuracy of 0.97.

Massive MIMO (mMIMO) communication systems are recognized as key enablers of next-generation wireless networks. However, the orthogonal pilot assignments typical of multiple-input multiple-output (MIMO) systems are not well suited to emerging use cases characterized by short channel coherence times and a high number of connected user equipments (UEs). In this work, we propose a novel approach for intra-cell pilot reuse that leverages the spatial features of correlated mMIMO channels to attain low pilot contamination while using a small number of pilot sequences. The first part of the proposed solution is a groundbreaking clustering algorithm termed K-beams, which splits the complex intra-cell pilot allocation into tractable problems without significant loss of optimality. Then, we introduce a heuristic approach called best-first pilot assignment (BFPA), designed to manage intra-cluster pilot assignments by minimizing interference among the most contaminating UEs. We evaluated the performance of our proposed solution (K-beams+BFPA) in terms of sum-normalized mean-squared error (NMSE) and sum-rate under various challenging network setups. The simulation results show that our approach is a robust alternative to more computationally demanding benchmarks.

The deep reinforcement learning (DRL)-based deep deterministic policy gradient (DDPG) framework is proposed to solve the joint optimization of the IRS phase-shift matrix and the precoding matrix in an IRS-assisted multi-stream multi-user MIMO communication.The combination of multiple-input multiple-output(MIMO) communications and intelligent reflecting surfaces(IRSs) is foreseen as a key enabler of beyond 5G (B5G) and 6Gsystems. In this work, we develop an innovative deep reinforcement learning (DRL)-based approach to the joint optimization of the MIMO precoders and the IRS phase-shift matrices that is proved to be efficient in high dimensional systems. The proposed approach is termed deep deterministic policy gradient (DDPG)and maximizes the sum rate of an IRS-assisted multi-stream(MS) multi-user MIMO (MU-MIMO) system by learning the best matrix configuration through online trial-and-error interactions. The proposed approach is formulated in terms of continuous state and action spaces, and a sum-rate-based reward function. The computational complexity is reduced by using artificial neural networks (ANNs) for function approximations and it is shown that the proposed solution scales better than other state-of-the-art methods, while reaching a competitive performance.

The single frequency network (SFN) has been assumed worldwide by telecommunication operators to save radio frequency resources and homogenize the network. Its applications have transcended the digital terrestrial television and digital radio to become part of the key techniques of the broadband and broadcast convergence for LTE-A, 5G and beyond. However, the transition from a multi frequency network (MFN) to an SFN involves multiple measurement campaigns and tuning of the network to achieve the expected up-performance and quality of service. This paper aims to propose a machine learning model to predict the SFN performance from the legacy MFN parameters. The model is based on regression and classification machine learning algorithms concatenated in three consecutive stages to predict SFN electric-field strength, modulation error ratio and gain. The training and test processes are performed with a dataset of 389 samples from an SFN/MFN trial in Ghent, Belgium. The best performance is obtained with concatenating gradient boosting, random forest, and linear regression, which allows predicting the SFN electric-field strength with an R ² of 92%, the modulation error ratio with 95%, and SFN gain with 87% from only MFN and position data. Besides, the model allows classifying the data points according to positive or negative SFN gain with an accuracy of 93%.