Navegando por Assunto "Tecnologia 5G"

Agora exibindo 1 - 4 de 4

Acesso aberto (Open Access)
Heurística para provisionamento dinâmico de recursos de hardware em redes híbridas de acesso via rádio considerando o efeito de maré
(Universidade Federal do Pará, 2020-03-06) FALCÃO, Igor Wenner Silva; CARDOSO, Diego Lisboa; http://lattes.cnpq.br/0507944343674734
The increase in the volume of services and applications, in addition to the accelerated growth in wireless access demands, represent significant challenges for the fifth generation of mobile networks, the 5G network. This increase in the volume of applications is a reflection of the growing number of devices connecting to the network, consuming data expansively, generating high data load. Another point of great impact is the large-scale daily migration of people in urban centers, causing the so-called Tide Effect. This promotes the space-time fluctuation of traffic throughout the day, making it difficult to control and manage the network (low efficiency in the use of hardware resources, load imbalance, underutilization and idleness of resources). Based on these indications and considering the knowledge of the service operators, data from the movement of users in New York City were extracted through an LBSN (Location-Based Social Network). Considering the expected high traffic demand for 5G and the problems arising from the Tidal Effect, this dissertation proposes a heuristic with two approaches to provisioning hardware resources (one based on the aggregate throughput and the other on the number of connected users). The results show that the network provisioning met the traffic variability of the scenario used, reducing the Probability of Blocking by 3.7%, maximizing the efficiency of the Base Band Unit (BBU) and quantifying the Small Cells (SCs) necessary to meet user demand.
Acesso aberto (Open Access)
Hybrid CAVIAR Simulations and Reinforcement Learning Applied to 5G Systems: Experiments with Scheduling and Beam Selection
(Universidade Federal do Pará, 2022-01-28) BORGES, João Paulo Tavares; KLAUTAU JÚNIOR, Aldebaro Barreto da Rocha; http://lattes.cnpq.br/1596629769697284
Reinforcement Learning (RL) is a learning paradigm suitable for problems in which an agent has to maximize a given reward, while interacting with an ever-changing environment. This class of problem appears in several research topics of the 5th Generation (5G) and the 6th Generation (6G) of mobile networks. However, the lack of freely available data sets or environments to train and assess RL agents are a practical obstacle that delays the widespread adoption of RL in 5G and future networks. These environments must be able to close the so-called reality gap, where reinforcement learning agents, trained in virtual environments, are able to generalize their decisions when exposed to real, never before seen, situations. Therefore, this work describes a simulation methodology named CAVIAR, or Communication Networks, Artificial Intelligence and Computer Vision with 3D Computer-Generated Imagery, tailored for research on RL methods applied to the physical layer (PHY) of the wireless communications systems. In this work, this simulation methodology is used to generate an environment for the tasks of user scheduling and beam selection, where, at each time step, the RL agent needs to schedule a user and then choose the index of a fixed beamforming codebook to serve it. A key aspect of this proposal is that the simulation of the communication system and the artificial intelligence engine must be closely integrated, such that actions taken by the agent can reflect back on the simulation loop. This aspect makes the trade-off of processing time versus realism of the simulation, an element to be considered. This work also describes the modeling of the communication systems and RL agents used for experimentation, and presents statistics concerning the environment dynamics, such as data traffic, as well as results for baseline systems. Finally, it is discussed how the methods described in this work can be leveraged in the context of the development of digital twins.
Acesso aberto (Open Access)
Meta-heurística para mapeamento BBU-RRH e balanceamento de carga entre BBUs, aplicada a redes de acesso centralizado
(Universidade Federal do Pará, 2022-08-19) CUNHA, Rita de Cássia Porfírio da; CARDOSO, Diego Lisboa; http://lattes.cnpq.br/0507944343674734
The growing demand for information access, generated by multimedia applications, is one of the challenges of the new generation of mobile networks. The fifth generation (5G) aims to meet increasingly stringent user requirements, such as latencies and low power consumption. One of the proposed architectures to supply the demands that arise with 5G and to support this traffic is the Cloud Radio Access Network (C-RAN), which centralizes processing power to solve the load imbalance, allocate resources accordingly based on network demand. This architecture proposes resource sharing while addressing processing scalability issues. Recently, metaheuristic optimization algorithms have been widely used to solve problems of this nature. Meta-heuristic algorithms are used because they are more powerful than conventional methods, which are to on formal logic or mathematical programming, in addition to the fact that the time required for execution is less than the exact algorithms’ one. In this context, the objective of this study is to develop an optimized resource allocation model that performs load balancing between Baseband Units (BBUs) and Remote Radio Heads (RRHs), based on the Particle Swarm Optimization (PSO) method. For this purpose, a variation of the PSO algorithm, the Discrete Particle Swarm Optimization (DPSO) was used, to optimize the proposed objective function. Results indicated a point to superior performance of this objective function in comparison to the adopted benchmarking, both in high and low traffic densities.
Acesso aberto (Open Access)
Sistemas fotovoltaicos aplicados em cenário de rede 5G
(Universidade Federal do Pará, 2020-01-31) OLIVEIRA, Carmela Souza; COSTA, João Crisóstomo Weyl Albuquerque; http://lattes.cnpq.br/9622051867672434
With the deployment of the next generation of mobile networks, a significant increase in data consumption is estimated and, consequently, a substantial impact on energy consumption. In light of this scenario, it is interesting to think of alternative sources that can meet this energy demand and additionally act to mitigate greater environmental impacts. Based on this economic and, above all, environmental perspective, this work proposes the use of a photovoltaic system as a strategy for the potentialization of energy consumption in a less aggressive way to the environment. The experiments carried out evaluate the viability of the proposal from the implementation in two RAN (Radio Access Network) architectures that can be employed to the new generation (5G). The results demonstrate the financial viability in the installation of photovoltaic system when compared to conventional sources of power generation.