MIMO-GAN: Generative MIMO Channel Modeling

TL;DR

MIMO-GAN introduces a generative adversarial network-based approach to learn and simulate complex MIMO wireless channels from measurement data, enabling more accurate and efficient channel modeling.

Contribution

It presents a novel GAN-based method for implicit modeling of MIMO channels directly from measurements, improving fidelity and sampling efficiency.

Findings

High consistency in capturing power, delay, and spatial correlation statistics.

Achieved average delay errors under 3.57 ns and power errors of -18.7 dB.

Demonstrated effectiveness on 3GPP TDL MIMO channels.

Abstract

We propose generative channel modeling to learn statistical channel models from channel input-output measurements. Generative channel models can learn more complicated distributions and represent the field data more faithfully. They are tractable and easy to sample from, which can potentially speed up the simulation rounds. To achieve this, we leverage advances in GAN, which helps us learn an implicit distribution over stochastic MIMO channels from observed measurements. In particular, our approach MIMO-GAN implicitly models the wireless channel as a distribution of time-domain band-limited impulse responses. We evaluate MIMO-GAN on 3GPP TDL MIMO channels and observe high-consistency in capturing power, delay and spatial correlation statistics of the underlying channel. In particular, we observe MIMO-GAN achieve errors of under 3.57 ns average delay and -18.7 dB power.