Banca de QUALIFICAÇÃO: ERIBERTO DE SOUTO SILVA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : ERIBERTO DE SOUTO SILVA
DATE: 30/08/2024
TIME: 14:00
LOCAL: LANCE - Sala de Reunião 1
TITLE:

andwidth Management of Fractional Frequency Reuse in Dynamic Scenarios with Hotspots using Reinforcement Learning

KEY WORDS:

ICIC, FFR, Hotspot, MAB, Machine Learning.

PAGES: 45
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUBÁREA: Telecomunicações
SPECIALTY: Sistemas de Telecomunicações
SUMMARY:

The present work approach the use of interference coordination techniques between cells, Inter-Cell Interference Coordination (ICIC), based on fractional frequency reuse, \textit{Fractional Frequency Reuse (FFR)}, aimed at mitigating the great challenge faced in mobile network projects, co-channel interference (\textit{ICI}), which causes degradation of system performance, especially in dynamic scenarios with the presence of random agglomerations of users, \textit{hotspots}.
Initially, an exploration of the chosen ICIC technique is carried out, characterizing its current application in resolving the points mentioned.
Then, taking into account the dynamicity of the scenario, the use of machine learning techniques (\textit{Machine Learning}) is proposed as a solution to the problem, more specifically, the \textit{Multi Armed Bandit (MAB) algorithm )}, focused on optimizing bandwidth management of inter-cell interference coordination (\textit{ICIC}) techniques, such as fractional frequency reuse (\textit{FFR}) in 3GPP systems.
The objective of the proposal is to adapt the bandwidth allocation, taking as activation parameters the system load variation and the presence of \textit{hotspots}.
The experiments carried out in the \textit{ns-3} network simulator can prove that the application of \textit{MAB} in ICIC techniques, focused on FFR, is efficient, especially in dynamic scenarios, where different bandwidth distributions are necessary as a way to mitigate co-channel interference and improve the quality of service, \textit{Quality of Service (QoS)} perceived by users.

COMMITTEE MEMBERS:
Presidente - 1412682 - VICENTE ANGELO DE SOUSA JUNIOR
Interno - 2524053 - ANTONIO LUIZ PEREIRA DE SIQUEIRA CAMPOS
Externo ao Programa - 1840342 - MARCIO EDUARDO DA COSTA RODRIGUES - UFRN