LSTM-Based Power Delay Profile Predictions for Intra-Bus Wireless Propagation

TL;DR

This paper introduces an LSTM-based model to predict power delay profiles for intra-bus wireless channels at 60 GHz, achieving less than 10% error in predictions, aiding in better wireless communication planning.

Contribution

It presents a novel application of LSTM neural networks for predicting channel transfer functions and power delay profiles inside buses at millimeter wave frequencies.

Findings

Average error of PDP taps prediction was less than 10%.

LSTM effectively captures short-term variations in wireless channels.

The model improves accuracy of intra-bus wireless channel modeling.

Abstract

Longlshort-term memory (LSTM) is a deep learning model that can capture long-term dependencies of wireless channel models and is highly adaptable to short-term changes in a wireless environment. This paper proposes a simple LSTM model to predict the channel transfer function (CTF) for a given transmitter-receiver location inside a bus for the 60 GHz millimetre wave band. The average error of the derived power delay profile (PDP) taps, obtained from the predicted CTFs, was less than 10% compared to the ground truth.