Navegando por Assunto "MIMO - Múltiplas entradas múltiplas saídas"

Agora exibindo 1 - 2 de 2

Acesso aberto (Open Access)
5G MIMO and LIDAR data for machine learning: mmWave beam-selection using deep learning
(Universidade Federal do Pará, 2019-08-29) DIAS, Marcus Vinicius de Oliveira; KLAUTAU JÚNIOR, Aldebaro Barreto da Rocha; http://lattes.cnpq.br/1596629769697284
Modern communication systems can exploit the increasing number of sensor data currently used in advanced equipment and reduce the overhead associated with link configuration. Also, the increasing complexity of networks suggests that machine learning (ML), such as deep neural networks, can effectively improve 5G technologies. The lack of large datasets make harder to investigate the application of deep learning in wireless communication. This work presents a simulation methodology (RayMobTime) that combines a vehicle traffic simulation (SUMO) with a ray-tracing simulator (Remcom’s Wireless InSite), to generate channels that represents realistic 5G scenarios, as well as the creation of LIDAR sensor data (via Blensor). The created dataset is utilized to investigate beam-selection techniques on vehicle-to-infrastructure using millimeter waves on different architectures, such as distributed architecture (usage of the information of only a selected vehicle, and processing of data on the vehicle) and centralized architectures (usage of all present information provided by the sensors in a given moment, processing at the base station). The results indicate that deep convolutional neural networks can be utilized to select beams under a top-M classification framework. It also shows that a distributed LIDAR-based architecture provides robust performance irrespective of car penetration rate, outperforming other architectures, as well as can be used to detect line-of-sight (LOS) with reasonable accuracy.
Acesso aberto (Open Access)
Compression of Channel State Information in Multiple Input Multiple Output Mobile Systems
(Universidade Federal do Pará, 2019-05-24) VILAS BOAS, Brenda; KLAUTAU JÚNIOR, Aldebaro Barreto da Rocha; http://lattes.cnpq.br/1596629769697284
The firsts trials of the Fifth generation of wireless networks (5G) are taking place worldwide. A variety of use cases are envisaged, requiring flexible and scalable technologies to meet their key performance indicators. Massive MIMO is a 5G-enabling technology that improves spectral efficiency. To exploit the advantages of MIMO, the transmitter needs to have information about the channel condition (CSI) of each User equipment (UE). 5G is being standardized in Frequency division duplexing (FDD) and Time division duplexing (TDD) operational modes; hence, MIMO has to be feasible in both duplexing modes. As TDD operates downlink and uplink on the same frequency, it can rely on channel reciprocity to acquire the CSI needed to further design precoding and user scheduling, for instance. However, FDD cannot exploit channel reciprocity; therefore, massive MIMO in FDD mode is more challenging because the increasing number of antennas may turn the feedback of CSI impractical. Hence, compressing CSI in MIMO FDD systems is of interest. Furthermore, the use of vast spectrum ranges, sub-6 GHz and mmWaves bands, leads to different channel characteristics. Moreover, the close packaging of antenna elements increases the spatial correlation among a MIMO array. Consequently, this correlation can be exploited to leverage compression of CSI. This dissertation presents an overview of CSI compression methods, proposes an heuristic transform coding method with low computational cost, and do a systematic evaluation of the transform coding methods based on realistic MIMO channel simulations. Besides, the impact of different 5G use cases and design of transmitter and receiver antennas are also included on the evaluation to chose