DQN-GNN-Based User Association Approach for Wireless Networks

Ibtihal Alablani and Mohammed J. F. Alenazi ()
Additional contact information
Ibtihal Alablani: Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh P.O. Box 11451, Saudi Arabia
Mohammed J. F. Alenazi: Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh P.O. Box 11451, Saudi Arabia

Mathematics, 2023, vol. 11, issue 20, 1-21

Abstract: In the realm of advanced mobile networks, such as the fifth generation (5G) and beyond, the increasing complexity and proliferation of devices and unique applications present a substantial challenge for User Association (UA) in wireless systems. The problem of UA in wireless networks is multifaceted and requires comprehensive exploration. This paper presents a pioneering approach to the issue, integrating a Deep Q-Network (DQN) with a Graph Neural Network (GNN) to enhance user-base station association in wireless networks. This novel approach surpasses recent methodologies, including Q-learning and max average techniques, in terms of average rewards, returns, and success rate. This superiority is attributed to its capacity to encapsulate intricate relationships and spatial dependencies among users and base stations in wireless systems. The proposed methodology achieves a success rate of 95.2%, outperforming other methodologies by a margin of up to 5.9%.

Keywords: Graph Neural Networks; Deep Q-Network; User Association; 5G; Machine Learning; Reinforcement Learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/20/4286/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/20/4286/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:20:p:4286-:d:1259755

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().