Learning Latent Wireless Dynamics from Channel State Information
This work addresses the challenge of predicting wireless network dynamics for improved communication systems, representing an incremental advance by combining channel charting with predictive modeling.
The paper tackles the problem of modeling and predicting wireless propagation dynamics from channel state information (CSI) by proposing a joint-embedding predictive architecture (JEPA) that learns latent representations and captures system dynamics, resulting in a two-fold increase in accuracy over benchmarks for longer look-ahead prediction tasks.
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.