Approximating the Void: Learning Stochastic Channel Models from Observation with Variational Generative Adversarial Networks
This work addresses the need for more realistic channel models in communications system design, moving beyond simplified analytic models, though it is incremental as it builds on prior GAN-based approaches.
The paper tackled the problem of accurately learning stochastic channel probability distribution functions from real measurements, which previous GAN-based methods failed to do, by introducing a variational GAN architecture and loss function that captures stochastic behavior effectively.
Channel modeling is a critical topic when considering designing, learning, or evaluating the performance of any communications system. Most prior work in designing or learning new modulation schemes has focused on using highly simplified analytic channel models such as additive white Gaussian noise (AWGN), Rayleigh fading channels or similar. Recently, we proposed the usage of a generative adversarial networks (GANs) to jointly approximate a wireless channel response model (e.g. from real black box measurements) and optimize for an efficient modulation scheme over it using machine learning. This approach worked to some degree, but was unable to produce accurate probability distribution functions (PDFs) representing the stochastic channel response. In this paper, we focus specifically on the problem of accurately learning a channel PDF using a variational GAN, introducing an architecture and loss function which can accurately capture stochastic behavior. We illustrate where our prior method failed and share results capturing the performance of such as system over a range of realistic channel distributions.