Please use this identifier to cite or link to this item: http://www.repositorio.ufc.br/handle/riufc/60409
Title in Portuguese: A Q-learning Based Approach to Spectral Efficiency Maximization in Multiservice Wireless Systems
Title: A Q-learning Based Approach to Spectral Efficiency Maximization in Multiservice Wireless Systems
Author: Saraiva, Juno Vitorino
Monteiro, Victor Farias
Lima, Francisco Rafael Marques
Maciel, Tarcísio Ferreira
Cavalcanti, Francisco Rodrigo Porto
Keywords: Radio resource allocation
Satisfaction guarantees
Machine learning
Reinforcement learning
Q-learning
Issue Date: 2019
Publisher: https://www.sbrt.org.br/sbrt2019
Citation: SARIAVA, Juno Vitorino; MONTEIRO, Victor Farias; LIMA, Francisco Rafael Marques; MACIEL, Tarcísio Ferreira; CAVALCANTI, Francisco Rodrigo Porto. A Q-learning based approach to spectral efficiency maximization in multiservice wireless systems. In: SIMPÓSIO BRASILEIRO DE TELECOMUNICAÇÕES - SBrT, XXXIII., 29 set.-02 out. 2019, Petrópolis-RJ., SP. Anais […], Petrópolis-RJ., SP., 2019.
Abstract: In this article, we study Radio Resource Allocation (RRA) as a non-convex optimization problem, aiming at maximizing the spectral efficiency subject to satisfaction guarantees in multiservice wireless systems. This problem has already been previously investigated and efficient heuristics have been proposed. However, in order to assess the performance of Machine Learning (ML) algorithms when solving optimization problems in the context of RRA, we revisit that problem and propose a solution based on a Reinforcement Learning (RL) framework. Specifically, our proposal is based on the Q-learning technique, where an agent gradually learns a policy by interacting with its local environment, until reaching convergence. Thus, in this article, the task of searching for an optimal solution in a combinatorial optimization problem is transformed into finding an optimal policy in Q-learning. Lastly, through computational simulations we compare the state-of-art proposals of the literature with our approach and we show a near optimal performance of the latter for a well-trained agent.
URI: http://www.repositorio.ufc.br/handle/riufc/60409
metadata.dc.type: Artigo de Evento
Appears in Collections:DETE - Trabalhos apresentados em eventos

Files in This Item:
File Description SizeFormat 
2019_eve_ jvsaraiva.pdf453,76 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.