Online Trainable Wireless Link Quality Prediction System using Camera Imagery

TL;DR

This paper presents a real-time, online trainable system using camera imagery to predict wireless link quality, enhancing reliability by adapting to environmental changes in Wi-Fi signals.

Contribution

It introduces a novel real-time, online trainable prediction system that uses camera data to improve wireless link quality forecasting.

Findings

The system accurately predicts Wi-Fi received power in real-time.

It adapts to environmental changes and updates the model dynamically.

Experimental results show effective prediction during LOS blockage.

Abstract

Machine-learning-based prediction of future wireless link quality is an emerging technique that can potentially improve the reliability of wireless communications, especially at higher frequencies (e.g., millimeter-wave and terahertz technologies), through predictive handover and beamforming to solve line-of-sight (LOS) blockage problem. In this study, a real-time online trainable wireless link quality prediction system was proposed; the system was implemented with commercially available laptops. The proposed system collects datasets, updates a model, and infers the received power in real-time. The experimental evaluation was conducted using 5 GHz Wi-Fi, where received signal strength could be degraded by 10 dB when the LOS path was blocked by large obstacles. The experimental results demonstrate that the prediction model is updated in real-time, adapts to the change in environment, and predicts the time-varying Wi-Fi received power accurately.