Inter-cell interference remains to be a bottleneck for conventional cellular networks as cell-edge users continue suffer from poor performance. Cell-free massive MIMO is novel network architecture that suppresses inter-cell by eliminating cell boundaries. It promises uniform performance throughout the coverage area, enabled coherent joint transmission multiple distributed antennas. To make scalable, user-centric approach adopted where each user served cluster of nearby access points (APs)....

The canonical setup of cell-free massive multiple-input multiple-output (MIMO), where all the access points (APs) serve users, does not scale well. In this work, we propose a deep reinforcement learning (DRL) approach to user-centric clustering in which each user is served by only subset APs. clusters are formed such that either given demand satisfied or network sum rate maximized. Unlike previous studies, allow vary size depending on propagation conditions. We design our DRL framework be...

Vehicular communications will foster mobility services and enable mass adoption of future autonomous vehicles, interchanging huge amount data acquired from vehicles’ sensors. 3GPP Release 14 presents the first standard for supporting V2X in LTE. Several enhancements are introduced, including a new arrangement physical resource grid, where subchannels minimum unit instead Resource Blocks. The grid is defined by several design parameters, some them with constraints imposed specifications, that...

Cell-free massive MIMO combines the benefits of and network densification to provide a uniformly good service throughout coverage area. This is achieved by joint transmission from multiple distributed access points (APs)/antennas, as well bringing them closer users. However, its canonical form where all APs are connected only single centralized processing unit (CPU) not scalable hard realize in practice. Motivated this, we propose deep reinforcement learning-based approach for partitioning...

We investigate the deep reinforcement learning (DRL) framework for uplink power control in a cell-free massive multiple-input, multiple-output (MIMO) network. Although DRL does not require prior sets of training data as opposed to supervised or unsupervised machine approaches, existing methods suffer from substantial convergence time, which is prohibitive highly dynamic large-scale mobile environment. To address this crucial issue, we propose that capitalizes on prioritized sampling speed up...

Vehicular communications hold the promise of disrupting mobility services and supporting mass adoption future autonomous vehicles. Regulators have set aside specific spectrum at 5.9 GHz band to support Intelligent Transport Systems (ITS) safety applications, for which a world-wide standardized radio technology is key factor deliver on this promise. Two technologies are currently positioned begin its commercial path, IEEE 802.11p LTE-PC5 Mode-4. The main differences between these lie design...