Physics-Informed Generative Modeling of Wireless Channels

Benedikt Böck, Andreas Oeldemann, Timo Mayer, Francesco Rossetto, Wolfgang Utschick

TL;DR: We propose a physically interpretable and generalizable generative model for wireless channels that can learn from corrupted channel observations.

Abstract: Learning the site-specific distribution of the wireless channel within a particular environment of interest is essential to exploit the full potential of machine learning (ML) for wireless communications and radar applications. Generative modeling offers a promising framework to address this problem. However, existing approaches pose unresolved challenges, including the need for high-quality training data, limited generalizability, and a lack of physical interpretability. To address these issues, we combine the physics-related compressibility of wireless channels with generative modeling, in particular, sparse Bayesian generative modeling (SBGM), to learn the distribution of the underlying physical channel parameters. By leveraging the sparsity-inducing characteristics of SBGM, our methods can learn from compressed observations received by an access point (AP) during default online operation. Moreover, they are physically interpretable and generalize over system configurations without requiring retraining.

Lay Summary: Learning the environment-specific statistical properties of how electromagnetic signals get manipulated when transmitting them over the air is essential to exploit the full potential of Machine Learning in wireless communications. To do so, we introduce an AI-based model that can learn these properties from corrupted data while simultaneously incorporating the underlying pre-known laws of physics. This circumvents the need for high-quality measurement campaigns to yield training samples in every environment of interest and simultaneously allows our method to dynamically adapt to the system's operation mode without requiring additional training.

Application-Driven Machine Learning: This submission is on Application-Driven Machine Learning.

Primary Area: Applications->Chemistry, Physics, and Earth Sciences

Keywords: sparse Bayesian generative modeling, wireless channel modeling, physics-informed, generative model

Submission Number: 11946