Atari: A graph convolutional neural network approach for performance prediction in next-generation wlans
| Autor: | Soto P., Camelo M., Mets K., Wilhelmi F., Góez D., Fletscher L.A., Gaviria N., Hellinckx P., Botero J.F., Latré S. |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Dynamic channel selections
Learning systems Computational costs Performance prediction Wireless local area networks (WLAN) Augmented reality Topology Graph neural networks Machine Learning Next generation networks Data-driven approach Virtual and augmented reality IEEE Standards Evaluation results Dynamic environments Convolutional neural networks Neural Networks Computer Graph structures Wi-Fi Forecasting |
| Zdroj: | SENSORS r-CTTC. Repositorio Institucional Producción Científica del Centre Tecnològic de Telecomunicacions de Catalunya (CTTC) Universitat Oberta de Catalunya (UOC) |
| ISSN: | 1424-3210 |
| Popis: | 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. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|