On the Prediction of Wi-Fi Performance through Deep Learning
Gabriele Formis, Amanda Ericson, Stefan Forsstrom, Kyi Thar, Gianluca Cena, Stefano Scanzio
TL;DR
This work tackles predicting Wi‑Fi channel quality, quantified by the Frame Delivery Ratio (FDR), in industrial settings using deep learning. It compares a 1D CNN and an LSTM on time-series data derived from binary success/failure sequences, demonstrating that both can forecast FDR with good accuracy from minimal input, while CNN achieves substantially lower latency and smaller memory usage. The results indicate negligible accuracy loss when choosing CNN over LSTM, making CNN the better option for embedded, real-time deployment; LSTM remains viable when resources are abundant. The study highlights practical pathways for deploying predictive Wi‑Fi robustness mechanisms and outlines avenues for hybrid architectures, transfer learning, and richer input features.
Abstract
Ensuring reliable and predictable communications is one of the main goals in modern industrial systems that rely on Wi-Fi networks, especially in scenarios where continuity of operation and low latency are required. In these contexts, the ability to predict changes in wireless channel quality can enable adaptive strategies and significantly improve system robustness. This contribution focuses on the prediction of the Frame Delivery Ratio (FDR), a key metric that represents the percentage of successful transmissions, starting from time sequences of binary outcomes (success/failure) collected in a real scenario. The analysis focuses on two models of deep learning: a Convolutional Neural Network (CNN) and a Long Short-Term Memory network (LSTM), both selected for their ability to predict the outcome of time sequences. Models are compared in terms of prediction accuracy and computational complexity, with the aim of evaluating their applicability to systems with limited resources. Preliminary results show that both models are able to predict the evolution of the FDR with good accuracy, even from minimal information (a single binary sequence). In particular, CNN shows a significantly lower inference latency, with a marginal loss in accuracy compared to LSTM.