english Icono del idioma   español Icono del idioma  

Por favor, use este identificador para citar o enlazar este ítem: https://hdl.handle.net/20.500.12008/35269 Cómo citar
Título: GROWS - Improving decentralized resource allocation in wireless networks through graph neural networks
Autor: Randall, Martín
Belzarena, Pablo
Larroca, Federico
Casas, Pedro
Tipo: Preprint
Palabras clave: User Association, Wireless Networks, FANETS, Graph Neural Networks, Deep Reinforcement Learning, Computing methodologies, Machine learning, Learning paradigms, Reinforcement learning, Networks, Network types, Wireless access networks
Fecha de publicación: 2022
Resumen: Wireless networks have progressed exponentially over the last decade, and modern wireless networking is today a complex to manage tangle, serving an ever-growing number of end-devices through a plethora of technologies. The broad range of use cases supported by wireless networking requires the conception of smarter resource allocation approaches, which make the most of the scarce wireless resources. We address the problem of user association (UA) in wireless systems. We consider a particularly challenging setup for UA, represented by modern ad-hoc networks such as FANETS, where connectivity is provided by a group of unmanned aerial vehicles (UAVs). We introduce GROWS, a Deep Reinforcement Learning (DRL) driven approach to efficiently connect wireless users to the network, leveraging Graph Neural Networks (GNNs) to better model the function of expected rewards. While GROWS is not tied to any specific wireless technology, the decentralized nature of FANETS and the lack of a pre-existing infrastructure makes a perfect case study. We show that GROWS learns UA policies for FANETS which largely outperform currently used association heuristics, realizing up to 20% higher throughput utility while reducing user rejection by more than 90%, and that these policies are robust to concept drifts in the expected load of traffic, maintaining performance improvements for previously unseen traffic loads.
Editorial: ACM
EN: GNNet 22 : Proceedings of the 1st International Workshop on Graph Neural Networking, Roma, Italy, 9 dec. 2022, pp. 24-29.
Financiadores: Este trabajo se encuentra parcialmente financiado por la Agencia Nacional de Investigacion e Innovación (ANII) a través del proyecto "Inteligencia Artificial para redes 5G" (FMV 1 2019 1 155700), así como por el proyecto Austrian FFG ICT-of-the-Future DynAISEC (Adaptive AI/ML for Dynamic Cybersecurity Systems).
Beca doctorado ANII
Citación: Randall, M., Belzarena, P., Larroca, F. y otros. GROWS - Improving decentralized resource allocation in wireless networks through graph neural networks [Preprint]. Publicado en: GNNet 22 : Proceedings of the 1st International Workshop on Graph Neural Networking, Roma, Italy, 9 dec., pp. 24-29. DOI: 10.1145/3565473.3569189. ISBN:978-1-4503-9933-3.
Licencia: Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)
Aparece en las colecciones: Publicaciones académicas y científicas - Instituto de Ingeniería Eléctrica

Ficheros en este ítem:
Fichero Descripción Tamaño Formato   
RBLC22.pdfPreprint390,33 kBAdobe PDFVisualizar/Abrir


Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons Creative Commons