A Spatio-temporal Prediction Methodology Based on Deep Learning and Real Wi-Fi Measurements

TL;DR

This paper introduces a deep learning-based spatio-temporal prediction methodology for Wi-Fi network metrics, utilizing real measurements from 100 access points to enhance network management.

Contribution

It proposes a hybrid CNN-RNN deep learning approach for accurate Wi-Fi network metric prediction, validated with real-world data from university deployments.

Findings

Hybrid CNN-RNN improves prediction accuracy

Deep learning models outperform traditional methods

Real measurements validate the methodology

Abstract

The rapid development of Wi-Fi technologies in recent years has caused a significant increase in the traffic usage. Hence, knowledge obtained from Wi-Fi network measurements can be helpful for a more efficient network management. In this paper, we propose a methodology to predict future values of some specific network metrics (e.g. traffic load, transmission failures, etc.). These predictions may be useful for improving the network performance. After data collection and preprocessing, the correlation between each target access point (AP) and its neighbouring APs is estimated. According to these correlations, either an only-temporal or a spatio-temporal based prediction is done. To evaluate the proposed methodology, real measurements are collected from 100 APs deployed in different university buildings for 3 months. Deep Learning (DL) methods (i.e. Convolutional Neural Network (CNN), Simple Recurrent Neural Network (SRNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Transformer) are evaluated and compared for both temporal and spatio-temporal based predictions. Moreover, a hybrid prediction methodology is proposed using a spatial processing based on CNN and a temporal prediction based on RNN. The proposed hybrid methodology provides an improvement in the prediction accuracy at expenses of a slight increase in the Training Computational Time (TCT) and negligible in Prediction Computational Time (PCT).