Next Article in Journal
Semantic Data Mining in Ubiquitous Sensing: A Survey
Next Article in Special Issue
Densely Deployed Indoor Massive MIMO Experiment: From Small Cells to Spectrum Sharing to Cooperation
Previous Article in Journal
Event Encryption for Neuromorphic Vision Sensors: Framework, Algorithm, and Evaluation
Previous Article in Special Issue
Spectrum Occupancy Model Based on Empirical Data for FM Radio Broadcasting in Suburban Environments
 
 
Article

ATARI: A Graph Convolutional Neural Network Approach for Performance Prediction in Next-Generation WLANs

1
Department of Computer Science, University of Antwerp—imec, 2000 Antwerp, Belgium
2
Department of Telecommunications Engineering, Universidad de Antioquia, Medellín 050010, Colombia
3
Centre Tecnològic de Telecomunicacions de Catalunya, 08860 Castelldefels, Spain
*
Author to whom correspondence should be addressed.
Academic Editor: Jae-Hyun Kim
Sensors 2021, 21(13), 4321; https://doi.org/10.3390/s21134321
Received: 10 May 2021 / Revised: 15 June 2021 / Accepted: 18 June 2021 / Published: 24 June 2021
(This article belongs to the Special Issue Cognitive Radio Applications and Spectrum Management)
IEEE 802.11 (Wi-Fi) is one of the technologies that provides high performance with a high density of connected devices to support emerging demanding services, such as virtual and augmented reality. However, in highly dense deployments, Wi-Fi performance is severely affected by interference. This problem is even worse in new standards, such as 802.11n/ac, where new features such as Channel Bonding (CB) are introduced to increase network capacity but at the cost of using wider spectrum channels. Finding the best channel assignment in dense deployments under dynamic environments with CB is challenging, given its combinatorial nature. Therefore, the use of analytical or system models to predict Wi-Fi performance after potential changes (e.g., dynamic channel selection with CB, and the deployment of new devices) are not suitable, due to either low accuracy or high computational cost. This paper presents a novel, data-driven approach to speed up this process, using a Graph Neural Network (GNN) model that exploits the information carried in the deployment’s topology and the intricate wireless interactions to predict Wi-Fi performance with high accuracy. The evaluation results show that preserving the graph structure in the learning process obtains a 64% increase versus a naive approach, and around 55% compared to other Machine Learning (ML) approaches when using all training features. View Full-Text
Keywords: channel bonding; graph neural network; machine learning; performance prediction; WLANs channel bonding; graph neural network; machine learning; performance prediction; WLANs
Show Figures

Figure 1

MDPI and ACS Style

Soto, P.; Camelo, M.; Mets, K.; Wilhelmi, F.; Góez, D.; Fletscher, L.A.; Gaviria, N.; Hellinckx, P.; Botero, J.F.; Latré, S. ATARI: A Graph Convolutional Neural Network Approach for Performance Prediction in Next-Generation WLANs. Sensors 2021, 21, 4321. https://doi.org/10.3390/s21134321

AMA Style

Soto P, Camelo M, Mets K, Wilhelmi F, Góez D, Fletscher LA, Gaviria N, Hellinckx P, Botero JF, Latré S. ATARI: A Graph Convolutional Neural Network Approach for Performance Prediction in Next-Generation WLANs. Sensors. 2021; 21(13):4321. https://doi.org/10.3390/s21134321

Chicago/Turabian Style

Soto, Paola, Miguel Camelo, Kevin Mets, Francesc Wilhelmi, David Góez, Luis A. Fletscher, Natalia Gaviria, Peter Hellinckx, Juan F. Botero, and Steven Latré. 2021. "ATARI: A Graph Convolutional Neural Network Approach for Performance Prediction in Next-Generation WLANs" Sensors 21, no. 13: 4321. https://doi.org/10.3390/s21134321

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop