Learning Latent Wireless Dynamics from Channel State Information

TL;DR

This paper introduces a machine learning approach that models wireless channel dynamics in a latent space, improving prediction accuracy of wireless environment changes from high-dimensional channel state information.

Contribution

It presents a joint-embedding predictive architecture (JEPA) that jointly learns a channel encoder and a predictor for modeling wireless channel dynamics in latent space.

Findings

Two-fold increase in prediction accuracy over benchmarks

Effective modeling of wireless channel dynamics from CSI

Improved long-term prediction performance

Abstract

In this work, we propose a novel data-driven machine learning (ML) technique to model and predict the dynamics of the wireless propagation environment in latent space. Leveraging the idea of channel charting, which learns compressed representations of high-dimensional channel state information (CSI), we incorporate a predictive component to capture the dynamics of the wireless system. Hence, we jointly learn a channel encoder that maps the estimated CSI to an appropriate latent space, and a predictor that models the relationships between such representations. Accordingly, our problem boils down to training a joint-embedding predictive architecture (JEPA) that simulates the latent dynamics of a wireless network from CSI. We present numerical evaluations on measured data and show that the proposed JEPA displays a two-fold increase in accuracy over benchmarks, for longer look-ahead prediction tasks.