IMDEA Networks Institute Publications Repository

A Mixture Density Channel Model for Deep Learning-Based Wireless Physical Layer Design

Garcia Marti, Dolores and Palacios, Joan and Lacruz, Jesús Omar and Widmer, Joerg (2020) A Mixture Density Channel Model for Deep Learning-Based Wireless Physical Layer Design. In: The 23rd International ACM Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM 2020), 16-20 November 2020, Virtual event (previously at Alicante, Spain).

[img] PDF (A Mixture Density Channel Model for Deep Learning-Based Wireless Physical Layer Design) - Published Version
Download (2960Kb)

Abstract

Machine learning is a highly promising tool to design the physicallayer of wireless communication systems, but it usually requiresthat a channel model is known. As data rates increase and wirelesstransceivers become more complex, the wireless channel, hard-ware imperfections, and their interactions become more difficult tomodel and compensate explicitly. New machine learning schemesfor the physical layer do not require an explicit model butimplic-itly learnthe end-to-end link including channel characteristics andnon-linearities of the system directly from the training data.In this paper, we present a novel neural network architecturethat provides anexplicitstochastic channel model, by learning theparameters of a Gaussian mixture distribution from real channelsamples. We use this channel model in conjunction with an au-toencoder for physical layer design to learn a suitable modulationscheme. Since our system learns an explicit model for the channel,we can use transfer learning to adapt more quickly to changes inthe environment. We apply our model to millimeter wave commu-nications with its challenges of phased arrays with a large numberof antennas, high carrier frequencies, wide bandwidth and complexchannel characteristics. We experimentally validate the systemusing a 60 GHz FPGA-based testbed and show that it is able toreproduce the channel characteristics with good accuracy.

Item Type: Conference or Workshop Papers (Paper)
Uncontrolled Keywords: Machine Learning, Neural Networks, Channel Modelling, PhysicalLayer, Autoencoder, Gaussian Mixture Network.
Subjects: UNSPECIFIED
Divisions: UNSPECIFIED
Depositing User: Dolores Garcia
Date Deposited: 12 Nov 2020 12:10
Last Modified: 12 Nov 2020 12:10
URI: http://eprints.networks.imdea.org/id/eprint/2224

Actions (login required)

View Item View Item