Banca de QUALIFICAÇÃO: VICTOR FERREIRA ALMEIDA MOTA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : VICTOR FERREIRA ALMEIDA MOTA
DATE: 26/05/2023
TIME: 14:00
LOCAL: GoogleMeet (meet.google.com/msk-pwfo-xss)
TITLE:

Signal prediction model optimization cell phone using Artificial Intelligence - Study of the 5G network application (NR)


KEY WORDS:

Cellular coverage simulation, Signal propagation model, Telecommunications, Geoprocessing


PAGES: 60
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUMMARY:

This work presents the development of a new cell coverage prediction model based on theoretical (Free Space) and empirical (Okumuta-Hata) models, but with the differential of applying signal propagation concepts through data geoprocessing combining the use of different maps such as relief (SRTM), visibility map, population density and also use signal collections measured in the field for calibration and optimization of the model through artificial intelligence applied with genetic algorithm. The test environment and visualization of the generated maps was QGIS, a open source data geoprocessing tool, and after validation of the studies, a code was developed in the programming language Python, to replicate the formula of the new suggested model. The study scenario in this work was the application of the model to simulate the coverage of a 5G (NR) network at the 3.5 GHz frequency of signal propagation. The results obtained suggest that the new model had a better accuracy of the predicted signal, having a greater correlation with the measured signal in 5% more when compared with the results of the Okumura-Hata model, and after calibration with a genetic algorithm the correlation passed to 10% more, which represented a synergy of 80% with the signal measured in the field. This model can be used to assist in decision-making regarding network planning in the telecommunications sector, such as 5G (NR), 4G (LTE), NB-IoT, LoRa, etc.


BANKING MEMBERS:
Presidente - 1587083 - MARCONI DE ARRUDA PEREIRA
Interno - 1803365 - VINICIUS DA FONSECA VIEIRA
Interna - 1777390 - CAROLINA RIBEIRO XAVIER
Externo ao Programa - 2000268 - MARCOS TOMIO KAKITANI
Notícia cadastrada em: 12/05/2023 13:20
SIGAA | NTInf - Núcleo de Tecnologia da Informação - | Copyright © 2006-2024 - UFSJ - sigaa02.ufsj.edu.br.sigaa02