Management and orchestration (MANO) of resources by virtual network functions (VNFs) represents one of the key challenges towards a fully virtualized network architecture as envisaged by 5G standards. Current threshold-based policies inefficiently over-provision network resources and under-utilize available hardware, incurring high cost for network operators, and consequently, the users. In this work, we present a MANO algorithm for VNFs allowing a central unit (CU) to learn to autonomously re-configure resources (processing power and storage), deploy new VNF instances, or offload them to the cloud, depending on the network conditions, available pool of resources, and the VNF requirements, with the goal of minimizing a cost function that takes into account the economical cost as well as latency and the quality-of-service (QoS) experienced by the users. First, we formulate the stochastic resource optimization problem as a parameterized action Markov decision process (PAMDP). Then, we propose a solution based on deep reinforcement learning (DRL). More precisely, we present a novel RL approach, called parameterized action twin (PAT) deterministic policy gradient, which leverages an actor-critic architecture to learn to provision resources to the VNFs in an online manner. Finally, we present numerical performance results, and map them to 5G key performance indicators (KPIs). To the best of our knowledge, this is the first work that considers DRL for MANO of VNFs' physical resources.

Both the use of very large arrays of antennas and flexible time division duplexing (TDD) designs have become prominent features of next generation 5G cellular systems. However, both enabling technologies suffer from severe interference effects, respectively known as pilot contamination and base-station-to- base-station (B2B) interference. In this paper, a practical novel TDD design principle is proposed for massive multiple-input multiple-output (MIMO) heterogeneous networks (HetNets) that leverages the inherent features of a flexible TDD design to mitigate both the beamformed interference caused by the pilot contamination effect and B2B interference. The design is based on the key observation that the transmission path chosen for training by the non-massive MIMO base stations plays an important role in the interference behavior of the network, and the data slots need to be configured accordingly. We propose TDFLEX, a low-complexity heuristic solution that follows these design guidelines. Performance evaluation results show significant gains when our design is compared to the standard TD-LTE.

The constant evolution of mobile-phone traffic demands for novel networking solutions especially focused on indoor environment. In this context, the use of femtocells, i.e., cells with very limited coverage area, has been proposed. In this paper, a femtocell network with hybrid access control mode is considered. The activity profile of the Femtocell Users (FUs) is modeled to compute the maximum achievable throughput and the consumed energy per successfully transmitted data bit by the Macrocell Users (MUs), depending on which set of channels are operated in open access mode, i.e., which channels can be used by MUs. Thus, it is identified how many and which channels must be operated in open access mode, depending on the physical capacities of the channels and the amount of time these channels are not occupied by FUs. The results motivate the need for novel resource management schemes which can dynamically adapt the set of open access channels to the network conditions.

Femtocells have emerged as an alternative solution for operators to improve coverage and throughput in indoor environments. However, modeling and development platforms are still needed in order to test implementation-specific characteristics of femtocells, such as interference mitigation techniques and self-organizing algorithms. Using OPNET, a high fidelity simulation environment for wireless networks, a femtocell modeling and development platform is created, closely following the specifications dictated by 3GPP regarding the entities, functionalities, procedures, and message formats for femtocell networks. It is shown how the platform reflects the effect of both interference and backhaul degradation on the overall performance of the network, which represent the key concerns for operators nowadays regarding femtocell deployments.

Two-tier femtocell-based networks have been proposed as an economic solution to improve coverage and capacity in wireless cellular systems. Although widely studied in the literature, interference management in these networks remains as a technical challenge in need of effective solutions. In particular, the interference estimation is a relevant portion of the problem that enables correct operation of interference management schemes relying on this information. In this paper, a novel downlink cross-tier interference estimation approach is proposed based on spatio-temporal correlation techniques. An ordinary Kriging interpolator using Semivariogram Analysis is applied to the interfering signal followed by an autorregressive model. The signal estimation at the interfered users' location is exploited at the radio resource manager of the femtocell or macrocell base station by formulating a resource allocation problem that is solved by means of a heuristic algorithm. A practical procedure implementing this scheme in the network is also proposed. Numerical results show how performance of cross-tier interference management approaches can be optimized by implementing this idea.

In this paper we investigate the time and frequency synchronization as well as the sector and cell search for the 3GPP long term evolution (LTE) downlink. The proposed algorithms rely on the synchronization and cell-specific reference signals and are hence compliant to most recent 3GPP specifications. Time and (fractional) frequency offset coarse synchronization are performed in the time domain with the cyclic prefix based autocorrelation, while the sector and cell as well as the integer frequency offset are estimated in the frequency domain by using the primary and secondary synchronization signals. To improve the cell detection reliability, the estimated cell is afterwards confirmed through the cell-specific reference signal. All algorithms are evaluated under multipath channel conditions and an initial carrier frequency mismatch. Compromising high performance with reasonable implementation complexity, we draw a practical solution for an LTE receiver.