5G New Radio (NR) network deployment in Non-Stand Alone (NSA) mode means that 5G networks rely on the control plane of existing Long Term Evolution (LTE) modules for control functions, while 5G modules are only dedicated to the user plane tasks, which could also be carried out by LTE modules simultaneously. The first deployments of 5G networks are essentially using this technology. These deployments enable what is known as E-UTRAN NR Dual Connectivity (ENDC), where a user establish a 5G connection simultaneously with a pre-existing LTE connection to boost their data rate. In this paper, a single Federated Deep Reinforcement Learning (FDRL) agent for the optimization of the event that triggers the dual connectivity between LTE and 5G is proposed. First, single Deep Reinforcement Learning (DRL) agents are trained in isolated cells. Later, these agents are merged into a unique global agent capable of optimizing the whole network with Federated Learning (FL). This scheme of training single agents and merging them also makes feasible the use of dynamic simulators for this type of learning algorithm and parameters related to mobility, by drastically reducing the number of possible combinations resulting in fewer simulations. The simulation results show that the final agent is capable of achieving a tradeoff between dropped calls and the user throughput to achieve global optimum without the need for interacting with all the cells for training.

This study addresses the performance of a wideband code-division multiple-access mobile communications system with beamforming antenna arrays (AAs) at the base station, synthesizing a grid of beams. In order to fully exploit the capacity gain from beamforming without jeopardizing the stability of the system, a directional power-based admission control (AC) scheme is applied. Due to the higher capacity offered by beamforming techniques, shortage of orthogonal channelization codes in the downlink becomes an increasingly important factor, which may result in blocking of users before the interference power limit is reached. The problem of channelization code shortage is addressed, and a solution based on splitting the cell into several code regions is proposed. For a network with circuit switched data services operated at 64 kb/s, the capacity gain for an eight-element AA is found to equal a factor of 2.5 for a universal mobile telecommunications equivalent system, with one channelization code set per cell. The capacity gain is limited by severe channelization code shortage under these circumstances. This problem is solved by deploying a cell splitting strategy with multiple code regions, which subsequently results in a capacity gain increase to a factor of 3.4. Furthermore, the soft capacity mechanism associated with partial deployment of AAs in a subset of the cells in the network is also addressed. It is demonstrated that a hot spot cell with AAs also helps increase the capacity of the surrounding cells with conventional sector antennas when using a power-based AC strategy.

The downlink performance enhancement provided by dual antenna terminals in a WCDMA network is evaluated. A UMTS network is taken as a case study and the behaviour of conventional power based radio resource management algorithms is discussed for both circuit and packet switched services. The aim is to clarify: (i) what the available capacity gain is; (ii) whether it is possible to capture this capacity gain without any higher layer overhead; and (iii) how the capacity is distributed among the users. A theoretical analysis of the dependency of the capacity gain upon the proportion of dual antenna terminals is conducted and the outcome matches the simulation results. Moreover, the impact of soft handover on the performance gain is considered. Furthermore, it is shown that the system becomes hard limited due to lack of channelisation codes, rather than excessive interference.