An RNN based DD Channel Estimator for OTFS with Embedded Pilots

Mattu, SR and Chockalingam, A (2022) An RNN based DD Channel Estimator for OTFS with Embedded Pilots. In: IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC, 12 - 15 September 2022, Virtual, Online, pp. 457-462.

PDF PIMRC 2022.pdf - Published Version Restricted to Registered users only Download (813kB)

Abstract

In this paper, we propose a learning based architecture for estimating the delay-Doppler (DD) channel in orthogonal time frequency space (OTFS) systems with embedded pilots. The proposed learning network, called DDNet, is based on a multi-layered recurrent neural network (RNN) framework with a novel training methodology that works seamlessly for both exclusive pilot frames as well as embedded pilot frames. This generalization is attributed to the training methodology, wherein multiple frame realizations with different guard band sizes are used to train the network. Simulation results demonstrate that the proposed DDNet achieves better mean square error and bit error performance compared to impulse based and threshold based DD channel estimation schemes.

Item Type:	Conference Paper
Publication:	IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to the Institute of Electrical and Electronics Engineers Inc.
Keywords:	Channel estimation; Embedded systems; Learning systems; Mean square error; Network layers, Channel estimator; Deep learning; Delay-dopple channel estimation; Doppler channels; Embedded pilots; Network-based; Orthogonal time frequency space modulation; Pilot frame; Space systems; Time-frequency space, Recurrent neural networks
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering > Electrical Communication Engineering - Technical Reports
Date Deposited:	01 Feb 2023 05:06
Last Modified:	01 Feb 2023 05:06
URI:	https://eprints.iisc.ac.in/id/eprint/79641

Actions (login required)

View Item